Author: "Computer Vision Laboratory - ETHZ [Zurich]" - Searchworks@Jio Institute Digital Library Search Results

Your search keyword '"Computer Vision Laboratory - ETHZ [Zurich]"' showing total 38 results

Start Over Author "Computer Vision Laboratory - ETHZ [Zurich]"

38 results on '"Computer Vision Laboratory - ETHZ [Zurich]"'

1. Vision et apprentissage dans le contexte des rovers planétaires

Author: de Curtò, J., Computer Vision Laboratory - ETHZ [Zurich], Eidgenössische Technische Hochschule - Swiss Federal Institute of Technology [Zürich] (ETH Zürich), ETH Zürich, Luc van Gool, and De Curtò i DíAz, J.
Subjects: [INFO.INFO-AI] Computer Science [cs]/Artificial Intelligence [cs.AI], Computer vision and image understanding, [INFO.INFO-CV] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, [INFO.INFO-TS] Computer Science [cs]/Signal and Image Processing, [INFO.INFO-RB] Computer Science [cs]/Robotics [cs.RO], [SDU.ASTR.EP]Sciences of the Universe [physics]/Astrophysics [astro-ph]/Earth and Planetary Astrophysics [astro-ph.EP], [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], [INFO.INFO-RB]Computer Science [cs]/Robotics [cs.RO], [SDU.ASTR.EP] Sciences of the Universe [physics]/Astrophysics [astro-ph]/Earth and Planetary Astrophysics [astro-ph.EP], Computer Vision und Bildverständnis, Vision par ordinateur et compréhension de l'image, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI]
Abstract: Generative Adversarial Networks (GANs) hatten enorme Anwendungen in Computer Vision. Im Kontext der Weltraumforschung und der Erforschung der Planeten steht die Tür jedoch offen für große Fortschritte. Wir stellen Werkzeuge für den Umgang mit Planetendaten aus der Mission Chang'E-4 vor und präsentieren ein Framework für die Übertragung des neuronalen Stils unter Verwendung der Zykluskonsistenz aus gerenderten Bildern.Wir führen auch eine neue Echtzeit-Pipeline für Simultaneous Localization and Mapping (SLAM) und Visual Inertial Odometry (VIO) im Kontext von Planetenrovern ein. Wir nutzen vorherige Informationen über den Standort des Landers, um einen SLAM-Ansatz auf Objektebene vorzuschlagen, der die Pose und Form des Landers zusammen mit den Kameratrajektorien des Rovers optimiert. Als weiteren Verfeinerungsschritt schlagen wir vor, Interpolationstechniken zwischen benachbarten zeitlichen Abtastwerten zu verwenden. videlicet synthetisiert nicht vorhandene Bilder, um die Gesamtgenauigkeit des Systems zu verbessern.Die Experimente werden im Rahmen des Iris Lunar Rover durchgeführt, eines Nano-Rovers, der 2021 als Flaggschiff von Carnegie Mellon als erstem unbemannten Rover Amerikas auf dem Mond im Mondgelände eingesetzt wird., Generative Adversarial Networks (GANs) have had tremendous applications in Computer Vision. Yet, in the context of space science and planetary exploration the door is open for major advances. We introduce tools to handle planetary data from the mission Chang'E-4 and present a framework for Neural Style Transfer using Cycle-consistency from rendered images. We also introduce a new real-time pipeline for Simultaneous Localization and Mapping (SLAM) and Visual Inertial Odometry (VIO) in the context of planetary rovers. We leverage prior information of the location of the lander to propose an object-level SLAM approach that optimizes pose and shape of the lander together with camera trajectories of the rover. As a further refinement step, we propose to use techniques of interpolation between adjacent temporal samples; videlicet synthesizing non-existing images to improve the overall accuracy of the system.The experiments are conducted in the context of the Iris Lunar Rover, a nano-rover that will be deployed in lunar terrain in 2021 as the flagship of Carnegie Mellon, being the first unmanned rover of America to be on the Moon., Generative Adversarial Networks (GAN) ont eu d'énormes applications en vision par ordinateur. Pourtant, dans le contexte de la science spatiale et de l'exploration planétaire, la porte est ouverte à des avancées majeures. Nous introduisons des outils pour gérer les données planétaires de la mission Chang'E-4 et présentons un cadre pour le transfert de style neuronal utilisant la cohérence de cycle à partir d'images rendues. Nous introduisons également un nouveau pipeline en temps réel pour Simultaneous Localization and Mapping (SLAM) et Visual Inertial Odometry (VIO) dans le contexte des rovers planétaires. Nous exploitons les informations préalables sur l'emplacement de l'atterrisseur pour proposer une approche SLAM au niveau de l'objet qui optimise la pose et la forme de l'atterrisseur ainsi que les trajectoires de caméra du rover. Comme étape de raffinement supplémentaire, nous proposons d'utiliser des techniques d'interpolation entre échantillons temporels adjacents; videlicet synthétise des images inexistantes pour améliorer la précision globale du système. Les expériences sont menées dans le contexte de l'Iris Lunar Rover, un nano-rover qui sera déployé sur un terrain lunaire en 2021 en tant que vaisseau amiral de Carnegie Mellon, étant le premier rover sans pilote d'Amérique à être sur la Lune.
Published: 2021

2. Vision und Lernen im Kontext exploratorischer Rover

Author: de Curtò, J., Computer Vision Laboratory - ETHZ [Zurich], Eidgenössische Technische Hochschule - Swiss Federal Institute of Technology [Zürich] (ETH Zürich), ETH Zürich, Luc van Gool, and De Curtò i DíAz, J.
Subjects: [INFO.INFO-AI] Computer Science [cs]/Artificial Intelligence [cs.AI], Computer vision and image understanding, [INFO.INFO-CV] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, [INFO.INFO-TS] Computer Science [cs]/Signal and Image Processing, [INFO.INFO-RB] Computer Science [cs]/Robotics [cs.RO], [SDU.ASTR.EP]Sciences of the Universe [physics]/Astrophysics [astro-ph]/Earth and Planetary Astrophysics [astro-ph.EP], [SDU.ASTR.EP] Sciences of the Universe [physics]/Astrophysics [astro-ph]/Earth and Planetary Astrophysics [astro-ph.EP], [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], [INFO.INFO-RB]Computer Science [cs]/Robotics [cs.RO], Computer Vision und Bildverständnis, Vision par ordinateur et compréhension de l'image, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI]
Abstract: Generative Adversarial Networks (GANs) hatten enorme Anwendungen in Computer Vision. Im Kontext der Weltraumforschung und der Erforschung der Planeten steht die Tür jedoch offen für große Fortschritte. Wir stellen Werkzeuge für den Umgang mit Planetendaten aus der Mission Chang'E-4 vor und präsentieren ein Framework für die Übertragung des neuronalen Stils unter Verwendung der Zykluskonsistenz aus gerenderten Bildern.Wir führen auch eine neue Echtzeit-Pipeline für Simultaneous Localization and Mapping (SLAM) und Visual Inertial Odometry (VIO) im Kontext von Planetenrovern ein. Wir nutzen vorherige Informationen über den Standort des Landers, um einen SLAM-Ansatz auf Objektebene vorzuschlagen, der die Pose und Form des Landers zusammen mit den Kameratrajektorien des Rovers optimiert. Als weiteren Verfeinerungsschritt schlagen wir vor, Interpolationstechniken zwischen benachbarten zeitlichen Abtastwerten zu verwenden. videlicet synthetisiert nicht vorhandene Bilder, um die Gesamtgenauigkeit des Systems zu verbessern.Die Experimente werden im Rahmen des Iris Lunar Rover durchgeführt, eines Nano-Rovers, der 2021 als Flaggschiff von Carnegie Mellon als erstem unbemannten Rover Amerikas auf dem Mond im Mondgelände eingesetzt wird., Generative Adversarial Networks (GANs) have had tremendous applications in Computer Vision. Yet, in the context of space science and planetary exploration the door is open for major advances. We introduce tools to handle planetary data from the mission Chang'E-4 and present a framework for Neural Style Transfer using Cycle-consistency from rendered images. We also introduce a new real-time pipeline for Simultaneous Localization and Mapping (SLAM) and Visual Inertial Odometry (VIO) in the context of planetary rovers. We leverage prior information of the location of the lander to propose an object-level SLAM approach that optimizes pose and shape of the lander together with camera trajectories of the rover. As a further refinement step, we propose to use techniques of interpolation between adjacent temporal samples; videlicet synthesizing non-existing images to improve the overall accuracy of the system.The experiments are conducted in the context of the Iris Lunar Rover, a nano-rover that will be deployed in lunar terrain in 2021 as the flagship of Carnegie Mellon, being the first unmanned rover of America to be on the Moon., Generative Adversarial Networks (GAN) ont eu d'énormes applications en vision par ordinateur. Pourtant, dans le contexte de la science spatiale et de l'exploration planétaire, la porte est ouverte à des avancées majeures. Nous introduisons des outils pour gérer les données planétaires de la mission Chang'E-4 et présentons un cadre pour le transfert de style neuronal utilisant la cohérence de cycle à partir d'images rendues. Nous introduisons également un nouveau pipeline en temps réel pour Simultaneous Localization and Mapping (SLAM) et Visual Inertial Odometry (VIO) dans le contexte des rovers planétaires. Nous exploitons les informations préalables sur l'emplacement de l'atterrisseur pour proposer une approche SLAM au niveau de l'objet qui optimise la pose et la forme de l'atterrisseur ainsi que les trajectoires de caméra du rover. Comme étape de raffinement supplémentaire, nous proposons d'utiliser des techniques d'interpolation entre échantillons temporels adjacents; videlicet synthétise des images inexistantes pour améliorer la précision globale du système. Les expériences sont menées dans le contexte de l'Iris Lunar Rover, un nano-rover qui sera déployé sur un terrain lunaire en 2021 en tant que vaisseau amiral de Carnegie Mellon, étant le premier rover sans pilote d'Amérique à être sur la Lune.
Published: 2021

3. A Unifying Theory of Learning: DL Meets Kernel Methods

Author: de Zarzà, I., Computer Vision Laboratory - ETHZ [Zurich], Eidgenössische Technische Hochschule - Swiss Federal Institute of Technology [Zürich] (ETH Zürich), ETH Zürich, and Luc van Gool
Subjects: Deep learning in robotics and automation, [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, [MATH.MATH-ST]Mathematics [math]/Statistics [math.ST], Tiefes Lernen in Robotik und Automatisierung, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], [INFO.INFO-RB]Computer Science [cs]/Robotics [cs.RO], Apprentissage profond en robotique et automatisation, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI]
Abstract: Wir führen ein Framework ein, um Kernel-Approximationen in der Mini-Batch-Einstellung mit Stochastic Gradient Descent (SGD) als Alternative zu Deep Learning zu verwenden. Basierend auf Random Kitchen Sinks bieten wir eine C++ Bibliothek für ML in großem Maßstab. Es enthält eine CPU-optimierte Implementierung des Algorithmus in Le et al. 2013, mit der ungefähre Kernel-Erweiterungen in logarithmisch linearer Zeit berechnet werden können. Der Algorithmus erfordert die Berechnung des Produkts der Matrizen Walsh Hadamard. Es wurde ein cachefreundlicher Fast Walsh Hadamard entwickelt, der eine überzeugende Geschwindigkeit erreicht und die aktuellen Methoden auf dem neuesten Stand der Technik übertrifft. McKernel legt die Grundlage für eine neue Lernarchitektur, die es ermöglicht, eine nichtlineare Klassifizierung in großem Maßstab zu erhalten, die Blitzkernerweiterungen und einen linearen Klassifizierer kombiniert. Es funktioniert in der Mini-Batch-Einstellung analog zu neuronalen Netzen. Wir zeigen die Gültigkeit unserer Methode durch umfangreiche Experimente mit MNIST und FASHION MNIST.Wir schlagen auch eine neue Architektur vor, um die Überparametrisierung in neuronalen Netzen zu reduzieren. Es wird ein Operand für die schnelle Berechnung im Rahmen von Deep Learning eingeführt, der gelernte Gewichte nutzt. Der Formalismus wird ausführlich beschrieben und bietet sowohl eine genaue Aufklärung der Mechanik als auch der theoretischen Implikationen.; We introduce a framework to use kernel approximates in the mini-batch setting with Stochastic Gradient Descent (SGD) as an alternative to Deep Learning. Based on Random Kitchen Sinks, we provide a C++ library for Large-scale ML. It contains a CPU optimized implementation of the algorithm in Le et al. 2013, that allows the computation of approximated kernel expansions in log-linear time. The algorithm requires to compute the product of matrices Walsh Hadamard. A cache friendly Fast Walsh Hadamard that achieves compelling speed and outperforms current state-of-the-art methods has been developed.McKernel establishes the foundation of a new architecture of learning that allows to obtain large-scale non-linear classification combining lightning kernel expansions and a linear classifier. It travails in the mini-batch setting working analogously to Neural Networks. We show the validity of our method through extensive experiments on MNIST and FASHION MNIST.We also propose a new architecture to reduce over-parametrization in Neural Networks. It introduces an operand for rapid computation in the framework of Deep Learning that leverages learned weights. The formalism is described in detail providing both an accurate elucidation of the mechanics and the theoretical implications.; Nous introduisons un framework pour utiliser les méthodes à noyaux dans le paramètre mini-batch avec Stochastic Gradient Descent (SGD) comme alternative à Deep Learning. Basé sur Random Kitchen Sinks, nous fournissons une bibliothèque C ++ pour le ML à grande échelle. Il contient une implémentation optimisée pour le processeur de l'algorithme de Le et al. 2013, qui permet le calcul des extensions approximatives du noyau en temps log-linéaire. L'algorithme nécessite de calculer le produit des matrices de Walsh Hadamard. Un Fast Walsh Hadamard compatible avec le cache, qui atteint une vitesse irréprochable et surpasse les méthodes actuelles de pointe, a été développé. McKernel jette les bases d'une nouvelle architecture d'apprentissage qui permet d'obtenir une classification non linéaire à grande échelle combinant des méthodes à noyaux rapides et un classificateur linéaire. Il fonctionne dans le cadre du mini-lot fonctionnant de manière analogue aux réseaux de neurones. Nous montrons la validité de notre méthode à travers des expériences approfondies sur MNIST et FASHION MNIST. Nous proposons également une nouvelle architecture pour réduire la sur-paramétrisation dans les réseaux de neurones. Il introduit un opérande pour le calcul rapide dans le cadre du Deep Learning qui exploite les poids appris. Le formalisme est décrit en détail, fournissant à la fois une élucidation précise de la mécanique et des implications théoriques.
Published: 2021

4. Eine einheitliche Theorie des Lernens: DL trifft Kernel-Methoden

Author: de Zarzà, I., De Zarzà i Cubero, I., Computer Vision Laboratory - ETHZ [Zurich], Eidgenössische Technische Hochschule - Swiss Federal Institute of Technology [Zürich] (ETH Zürich), ETH Zürich, and Luc van Gool
Subjects: [INFO.INFO-AI] Computer Science [cs]/Artificial Intelligence [cs.AI], [INFO.INFO-TS] Computer Science [cs]/Signal and Image Processing, Tiefes Lernen in Robotik und Automatisierung, [INFO.INFO-RB] Computer Science [cs]/Robotics [cs.RO], [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], [INFO.INFO-LG] Computer Science [cs]/Machine Learning [cs.LG], Apprentissage profond en robotique et automatisation, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], [INFO.INFO-CV] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, Deep learning in robotics and automation, [MATH.MATH-ST]Mathematics [math]/Statistics [math.ST], [INFO.INFO-RB]Computer Science [cs]/Robotics [cs.RO], [MATH.MATH-ST] Mathematics [math]/Statistics [math.ST]
Abstract: Wir führen ein Framework ein, um Kernel-Approximationen in der Mini-Batch-Einstellung mit Stochastic Gradient Descent (SGD) als Alternative zu Deep Learning zu verwenden. Basierend auf Random Kitchen Sinks bieten wir eine C++ Bibliothek für ML in großem Maßstab. Es enthält eine CPU-optimierte Implementierung des Algorithmus in Le et al. 2013, mit der ungefähre Kernel-Erweiterungen in logarithmisch linearer Zeit berechnet werden können. Der Algorithmus erfordert die Berechnung des Produkts der Matrizen Walsh Hadamard. Es wurde ein cachefreundlicher Fast Walsh Hadamard entwickelt, der eine überzeugende Geschwindigkeit erreicht und die aktuellen Methoden auf dem neuesten Stand der Technik übertrifft. McKernel legt die Grundlage für eine neue Lernarchitektur, die es ermöglicht, eine nichtlineare Klassifizierung in großem Maßstab zu erhalten, die Blitzkernerweiterungen und einen linearen Klassifizierer kombiniert. Es funktioniert in der Mini-Batch-Einstellung analog zu neuronalen Netzen. Wir zeigen die Gültigkeit unserer Methode durch umfangreiche Experimente mit MNIST und FASHION MNIST.Wir schlagen auch eine neue Architektur vor, um die Überparametrisierung in neuronalen Netzen zu reduzieren. Es wird ein Operand für die schnelle Berechnung im Rahmen von Deep Learning eingeführt, der gelernte Gewichte nutzt. Der Formalismus wird ausführlich beschrieben und bietet sowohl eine genaue Aufklärung der Mechanik als auch der theoretischen Implikationen., We introduce a framework to use kernel approximates in the mini-batch setting with Stochastic Gradient Descent (SGD) as an alternative to Deep Learning. Based on Random Kitchen Sinks, we provide a C++ library for Large-scale ML. It contains a CPU optimized implementation of the algorithm in Le et al. 2013, that allows the computation of approximated kernel expansions in log-linear time. The algorithm requires to compute the product of matrices Walsh Hadamard. A cache friendly Fast Walsh Hadamard that achieves compelling speed and outperforms current state-of-the-art methods has been developed.McKernel establishes the foundation of a new architecture of learning that allows to obtain large-scale non-linear classification combining lightning kernel expansions and a linear classifier. It travails in the mini-batch setting working analogously to Neural Networks. We show the validity of our method through extensive experiments on MNIST and FASHION MNIST.We also propose a new architecture to reduce over-parametrization in Neural Networks. It introduces an operand for rapid computation in the framework of Deep Learning that leverages learned weights. The formalism is described in detail providing both an accurate elucidation of the mechanics and the theoretical implications., Nous introduisons un framework pour utiliser les méthodes à noyaux dans le paramètre mini-batch avec Stochastic Gradient Descent (SGD) comme alternative à Deep Learning. Basé sur Random Kitchen Sinks, nous fournissons une bibliothèque C ++ pour le ML à grande échelle. Il contient une implémentation optimisée pour le processeur de l'algorithme de Le et al. 2013, qui permet le calcul des extensions approximatives du noyau en temps log-linéaire. L'algorithme nécessite de calculer le produit des matrices de Walsh Hadamard. Un Fast Walsh Hadamard compatible avec le cache, qui atteint une vitesse irréprochable et surpasse les méthodes actuelles de pointe, a été développé. McKernel jette les bases d'une nouvelle architecture d'apprentissage qui permet d'obtenir une classification non linéaire à grande échelle combinant des méthodes à noyaux rapides et un classificateur linéaire. Il fonctionne dans le cadre du mini-lot fonctionnant de manière analogue aux réseaux de neurones. Nous montrons la validité de notre méthode à travers des expériences approfondies sur MNIST et FASHION MNIST. Nous proposons également une nouvelle architecture pour réduire la sur-paramétrisation dans les réseaux de neurones. Il introduit un opérande pour le calcul rapide dans le cadre du Deep Learning qui exploite les poids appris. Le formalisme est décrit en détail, fournissant à la fois une élucidation précise de la mécanique et des implications théoriques.
Published: 2021

5. Video‐Based Rendering of Dynamic Stationary Environments from Unsynchronized Inputs

Author: Theo Thonat, Frédo Durand, Miika Aittala, George Drettakis, Sylvain Paris, Yagiz Aksoy, GRAPHics and DEsign with hEterogeneous COntent (GRAPHDECO), Inria Sophia Antipolis - Méditerranée (CRISAM), Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Université Côte d'Azur (UCA), Adobe Research, Computer Vision Laboratory - ETHZ [Zurich], Eidgenössische Technische Hochschule - Swiss Federal Institute of Technology [Zürich] (ETH Zürich), Massachusetts Institute of Technology (MIT), NVIDIA (NVIDIA), and European Project: 788065,H2020 Pilier ERC,FUNGRAPH(2018)
Subjects: business.industry, Computer science, Volume (computing), ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, 020207 software engineering, 02 engineering and technology, Variable bitrate, Image-based modeling and rendering, Computer Graphics and Computer-Aided Design, [INFO.INFO-GR]Computer Science [cs]/Graphics [cs.GR], Rendering (computer graphics), Image (mathematics), Dimension (vector space), Rippling, Simplicity (photography), 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, Computer vision, Artificial intelligence, Image-Based Rendering, business, Video-Based Rendering, ComputingMethodologies_COMPUTERGRAPHICS
Abstract: International audience; Image-Based Rendering allows users to easily capture a scene using a single camera and then navigate freely with realistic results. However, the resulting renderings are completely static, and dynamic effects – such as fire, waterfalls or small waves – cannot be reproduced. We tackle the challenging problem of enabling free-viewpoint navigation including such stationary dynamic effects, but still maintaining the simplicity of casual capture. Using a single camera – instead of previous complex synchronized multi-camera setups – means that we have unsynchronized videos of the dynamic effect from multiple views, making it hard to blend them when synthesizing novel views. We present a solution that allows smooth free-viewpoint video-based rendering (VBR) of such scenes using temporal Laplacian pyramid decomposition video, enabling spatio-temporal blending. For effects such as fire and waterfalls, that are semi-transparent and occupy 3D space, we first estimate their spatial volume. This allows us to create per-video geometries and alpha-matte videos that we can blend using our frequency-dependent method. We also extend Laplacian blending to the temporal dimension to remove additional temporal seams. We show results on scenes containing fire, waterfalls or rippling waves at the seaside, bringing these scenes to life.
Published: 2021
Full Text: View/download PDF

6. Unsupervised learning of category-specific symmetric 3D keypoints from point sets

Author: Danda Pani Paudel, Cédric Demonceaux, Luc Van Gool, Clara Fernandez-Labrador, José Jesús Guerrero, Ajad Chhatkuli, Equipe VIBOT - VIsion pour la roBOTique [ImViA EA7535 - ERL CNRS 6000] (VIBOT), Centre National de la Recherche Scientifique (CNRS)-Imagerie et Vision Artificielle [Dijon] (ImViA), Université de Bourgogne (UB)-Université de Bourgogne (UB), Aragón Institute of Engineering Research [Zaragoza] (I3A), University of Zaragoza - Universidad de Zaragoza [Zaragoza], Computer Vision Laboratory - ETHZ [Zurich], Eidgenössische Technische Hochschule - Swiss Federal Institute of Technology [Zürich] (ETH Zürich), Department of Electrical Engineering [Leuven] (ESAT), Catholic University of Leuven - Katholieke Universiteit Leuven (KU Leuven), ANR-18-CE33-0004,CLARA,Couplage Apprentissage et Vision pour Contrôle de Robots Aeriens(2018), Demonceaux, Cédric, APPEL À PROJETS GÉNÉRIQUE 2018 - Couplage Apprentissage et Vision pour Contrôle de Robots Aeriens - - CLARA2018 - ANR-18-CE33-0004 - AAPG2018 - VALID, Vedaldi, Andrea, Bischof, Horst, Brox, Thomas, and Frahm, Jan-Michael
Subjects: [INFO.INFO-AI] Computer Science [cs]/Artificial Intelligence [cs.AI], FOS: Computer and information sciences, Computer science, Plane symmetry, Computer Vision and Pattern Recognition (cs.CV), Point cloud, Computer Science - Computer Vision and Pattern Recognition, 02 engineering and technology, 010501 environmental sciences, 01 natural sciences, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], [INFO.INFO-CV] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], Linear basis, 0202 electrical engineering, electronic engineering, information engineering, ComputingMilieux_COMPUTERSANDEDUCATION, Point (geometry), 0105 earth and related environmental sciences, business.industry, Category specific, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], Pattern recognition, 16. Peace & justice, Benchmark (computing), Unsupervised learning, 020201 artificial intelligence & image processing, Artificial intelligence, Symmetry (geometry), business
Abstract: Lecture Notes in Computer Science, 12370, ISSN:0302-9743, ISSN:1611-3349, Computer Vision – ECCV 2020 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part V, ISBN:978-3-030-58594-5, ISBN:978-3-030-58595-2
Published: 2020

7. Early reactivity of sodium silicate-activated slag pastes and its impact on rheological properties

Author: Coralie Brumaud, S. Gismera, J.B. d’Espinose de Lacaillerie, Francisca Puertas, Marta Palacios, Barbara Lothenbach, M. M. Alonso, Aurélie Favier, Ministerio de Ciencia e Innovación (España), Institute of Construction Science Eduardo Torroja, Sciences et Ingénierie de la Matière Molle (UMR 7615) (SIMM), Ecole Superieure de Physique et de Chimie Industrielles de la Ville de Paris (ESPCI Paris), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Institut de Chimie du CNRS (INC)-Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS), Laboratory for Concrete & Construction Chemistry, Swiss Federal Laboratories for Materials Science and Technology [Thun] (EMPA), Computer Vision Laboratory - ETHZ [Zurich], Eidgenössische Technische Hochschule - Swiss Federal Institute of Technology [Zürich] (ETH Zürich), and Comunidad de Madrid
Subjects: Materials science, Alkali-activated slag cement, Reaction, Sodium, Aluminate, 0211 other engineering and technologies, chemistry.chemical_element, Sodium silicate, 02 engineering and technology, Ion, [SPI]Engineering Sciences [physics], chemistry.chemical_compound, Thermodynamic calculations, Rheology, 021105 building & construction, General Materials Science, [PHYS.COND]Physics [physics]/Condensed Matter [cond-mat], Building and Construction, Dynamic mechanical analysis, 021001 nanoscience & nanotechnology, Microstructure, 6. Clean water, Silicate, chemistry, Chemical engineering, 0210 nano-technology, [PHYS.COND.CM-SCM]Physics [physics]/Condensed Matter [cond-mat]/Soft Condensed Matter [cond-mat.soft], Sodium silicate activator
Abstract: The fast loss of fluidity of sodium silicate-activated slag (SS-AAS) systems have been widely studied in the literature. In this study, the rheology of these cements has been correlated with the evolution of the reaction products formed over time. For this purpose, a combination of experimental characterization techniques, to study the pore solution composition and microstructure of SS-AAS pastes and hermodynamic calculations have been applied. The initial precipitation of ill-defined N-A-S-H and C-N-A-S-H producta leads to a fast increase of the storage modulus after 40 min of reaction. These products are formed from the reaction of the Na+ ions and silicate ions of the activator with the Ca2+ and aluminate species dissolved from the slag. However, when a shear is applied, the structure breaks down and fluidity is recovered, that infers that the attractive forces between the particles are low at the early stages of hydration., The authors thank Prof. Habert (ETHZ) for constructive discussion. Dr. Francesco Caruso (SIK-ISEA) is thanked for helping to develop a protocol for the ICP-OES measurements. Dr. M. Palacios acknowledges Consejería de Educacion ´ e Investigacion ´ (Comunidad de Madrid) for funding the 2016-T1/AMB-1434 project in the frame of “Ayudas de Atraccion ´ de Talento Investigador” and MCIU/AEI/FEDER, UE for funding the RTI2018-099326-A-I00 project. Prof. F. Puertas thanks the Spanish Ministry of Science and Innovation for funding BIA2013-47876- C2-1-P and BIA2016-77252-P projects.
Published: 2020

8. Robust and Optimal Registration of Image Sets and Structured Scenes via Sum-of-Squares Polynomials

Author: Cédric Demonceaux, Adlane Habed, Danda Pani Paudel, Pascal Vasseur, Computer Vision Laboratory - ETHZ [Zurich], Eidgenössische Technische Hochschule - Swiss Federal Institute of Technology [Zürich] (ETH Zürich), Laboratoire des sciences de l'ingénieur, de l'informatique et de l'imagerie (ICube), Institut National des Sciences Appliquées - Strasbourg (INSA Strasbourg), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Strasbourg (UNISTRA)-Centre National de la Recherche Scientifique (CNRS)-École Nationale du Génie de l'Eau et de l'Environnement de Strasbourg (ENGEES)-Réseau nanophotonique et optique, Centre National de la Recherche Scientifique (CNRS)-Université de Strasbourg (UNISTRA)-Université de Haute-Alsace (UHA) Mulhouse - Colmar (Université de Haute-Alsace (UHA))-Centre National de la Recherche Scientifique (CNRS)-Université de Strasbourg (UNISTRA)-Université de Haute-Alsace (UHA) Mulhouse - Colmar (Université de Haute-Alsace (UHA))-Matériaux et nanosciences d'Alsace (FMNGE), Institut de Chimie du CNRS (INC)-Université de Strasbourg (UNISTRA)-Université de Haute-Alsace (UHA) Mulhouse - Colmar (Université de Haute-Alsace (UHA))-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)-Institut de Chimie du CNRS (INC)-Université de Strasbourg (UNISTRA)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS), Equipe VIBOT - VIsion pour la roBOTique [ImViA EA7535 - ERL CNRS 6000] (VIBOT), Centre National de la Recherche Scientifique (CNRS)-Imagerie et Vision Artificielle [Dijon] (ImViA), Université de Bourgogne (UB)-Université de Bourgogne (UB), Laboratoire d'Informatique, de Traitement de l'Information et des Systèmes (LITIS), Université Le Havre Normandie (ULH), Normandie Université (NU)-Normandie Université (NU)-Université de Rouen Normandie (UNIROUEN), Normandie Université (NU)-Institut national des sciences appliquées Rouen Normandie (INSA Rouen Normandie), Institut National des Sciences Appliquées (INSA)-Normandie Université (NU)-Institut National des Sciences Appliquées (INSA), Equipe Systèmes de Transport Intelligent (STI - LITIS), Institut National des Sciences Appliquées (INSA)-Normandie Université (NU)-Institut National des Sciences Appliquées (INSA)-Université Le Havre Normandie (ULH), Region Bourgogne-Franche-Comte, European Union (EU), ANR-15-CE23-0010,pLaTINUM,Cartographie Long Terme pour la Mobilité Urbaine(2015), ANR-11-IS03-0003,DrAACaR,Anneau de caméras asynchrones pour l'assistance au conducteur(2011), École Nationale du Génie de l'Eau et de l'Environnement de Strasbourg (ENGEES)-Université de Strasbourg (UNISTRA)-Institut National des Sciences Appliquées - Strasbourg (INSA Strasbourg), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Les Hôpitaux Universitaires de Strasbourg (HUS)-Centre National de la Recherche Scientifique (CNRS)-Matériaux et Nanosciences Grand-Est (MNGE), Université de Strasbourg (UNISTRA)-Université de Haute-Alsace (UHA) Mulhouse - Colmar (Université de Haute-Alsace (UHA))-Institut National de la Santé et de la Recherche Médicale (INSERM)-Institut de Chimie du CNRS (INC)-Centre National de la Recherche Scientifique (CNRS)-Université de Strasbourg (UNISTRA)-Université de Haute-Alsace (UHA) Mulhouse - Colmar (Université de Haute-Alsace (UHA))-Institut National de la Santé et de la Recherche Médicale (INSERM)-Institut de Chimie du CNRS (INC)-Centre National de la Recherche Scientifique (CNRS)-Réseau nanophotonique et optique, Université de Strasbourg (UNISTRA)-Université de Haute-Alsace (UHA) Mulhouse - Colmar (Université de Haute-Alsace (UHA))-Centre National de la Recherche Scientifique (CNRS)-Université de Strasbourg (UNISTRA)-Centre National de la Recherche Scientifique (CNRS), Demonceaux, Cédric, Cartographie Long Terme pour la Mobilité Urbaine - - pLaTINUM2015 - ANR-15-CE23-0010 - AAPG2015 - VALID, and Blanc International II - Anneau de caméras asynchrones pour l'assistance au conducteur - - DrAACaR2011 - ANR-11-IS03-0003 - Blanc International II - VALID
Subjects: Polynomial, Computer science, 02 engineering and technology, Artificial Intelligence, Robustness (computer science), Polynomial Sum-of-Squares optimization, 2D-3D registration, 0202 electrical engineering, electronic engineering, information engineering, Structure from motion, Structure-from-Motion, ALGORITHM, [SPI.SIGNAL] Engineering Sciences [physics]/Signal and Image processing, Explained sum of squares, Maximization, POSE, Outlier, 020201 artificial intelligence & image processing, Computer Vision and Pattern Recognition, Plane segmentation, CONSENSUS, Algorithm, Assignment problem, MATRIX, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing, Software, 3D
Abstract: International audience; This paper addresses the problem of registering a known structured 3D scene, typically a 3D scan, and its metric Structure-from-Motion (SfM) counterpart. The proposed registration method relies on a prior plane segmentation of the 3D scan. Alignment is carried out by solving either the point-to-plane assignment problem, should the SfM reconstruction be sparse, or the plane-to-plane one in case of dense SfM. A Polynomial Sum-of-Squares optimization theory framework is employed for identifying point-to-plane and plane-to-plane mismatches, i.e. outliers, with certainty. An inlier set maximization approach within a Branch-and-Bound search scheme is adopted to iteratively build potential inlier sets and converge to the solution satisfied by the largest number of assignments. Plane visibility conditions and vague camera locations may be incorporated for better efficiency without sacrificing optimality. The registration problem is solved in two cases: (i) putative correspondences (with possibly overwhelmingly many outliers) are provided as input and (ii) no initial correspondences are available. Our approach yields outstanding results in terms of robustness and optimality.
Published: 2019

9. TDP-43 extracted from frontotemporal lobar degeneration subject brains displays distinct aggregate assemblies and neurotoxic effects reflecting disease progression rates

Author: Sandrine C. Foti, Ulrich Wagner, Florent Laferrière, Paul J. Boersema, Magdalini Polymenidou, Erwan Bezard, Marian Hruska-Plochan, Tammaryn Lashley, Amanda J Lewis, Ashraf Al-Amoudi, Francesca De Giorgi, Yasmine T. Asi, Henning Stahlberg, Larissa A. B. Gilhespy, Zuzanna Maniecka, Eva-Maria Hock, Paola Picotti, Gery Barmettler, Tariq Afroz, Adrian M. Isaacs, John Ravits, François Ichas, Manuela Pérez-Berlanga, Unité de recherche Virologie et Immunologie Moléculaires (VIM (UR 0892)), Institut National de la Recherche Agronomique (INRA), Universität Zürich [Zürich] = University of Zurich (UZH), Computer Vision Laboratory - ETHZ [Zurich], Eidgenössische Technische Hochschule - Swiss Federal Institute of Technology [Zürich] (ETH Zürich), Institute of Neurology [London], University College of London [London] (UCL), University of Basel (Unibas), Department of Neurology and Center for Neuroscience, University of California at Davis, Sacramento, University of California [Davis] (UC Davis), University of California-University of California, Institut des Maladies Neurodégénératives [Bordeaux] (IMN), Université de Bordeaux (UB)-Centre National de la Recherche Scientifique (CNRS), University of Zurich, Polymenidou, Magdalini, University hospital of Zurich [Zurich], UCL, Institute of Neurology [London], University of California [San Diego] (UC San Diego), University of California (UC), Laboratoire de neurosciences expérimentales et cliniques (LNEC), Université de Poitiers-Institut National de la Santé et de la Recherche Médicale (INSERM), Laferriere, Florent, University of California, Unité de recherche Virologie et Immunologie Moléculaires (VIM), University of Zürich [Zürich] (UZH), and Eidgenössische Technische Hochschule - Swiss Federal Institute of Technology in Zürich [Zürich] (ETH Zürich)
Subjects: 0301 basic medicine, TDP-43, [SDV.NEU.NB]Life Sciences [q-bio]/Neurons and Cognition [q-bio.NC]/Neurobiology, Disease duration, 610 Medicine & health, Disease, Protein aggregation, Biology, Mass Spectrometry, protein aggregation, Mice, Protein Aggregates, 03 medical and health sciences, [SCCO]Cognitive science, 0302 clinical medicine, neurotoxicity, mental disorders, medicine, Animals, Humans, Phosphorylation, Amyotrophic lateral sclerosis, Pathological, ComputingMilieux_MISCELLANEOUS, Inclusion Bodies, Neurons, prion-like seeding, General Neuroscience, [SCCO.NEUR]Cognitive science/Neuroscience, Disease progression, [SDV.NEU.NB] Life Sciences [q-bio]/Neurons and Cognition [q-bio.NC]/Neurobiology, Neurotoxicity, Brain, nutritional and metabolic diseases, 2800 General Neuroscience, FTD, Frontotemporal lobar degeneration, medicine.disease, nervous system diseases, DNA-Binding Proteins, HEK293 Cells, 030104 developmental biology, Disease Progression, Frontotemporal Lobar Degeneration, ALS, FTLD, Neuroscience, 11493 Department of Quantitative Biomedicine, 030217 neurology & neurosurgery
Abstract: International audience; Accumulation of abnormally phosphorylated TDP-43 (pTDP-43) is the main pathology in affected neurons of people with amyotrophic lateral sclerosis (ALS) and frontotemporal lobar degeneration (FTLD). Morphological diversity and neuroanatomical distribution of pTDP-43 accumulations allowed classification of FTLD cases into at least four subtypes, which are correlated with clinical presentations and genetic causes. To understand the molecular basis of this heterogeneity, we developed SarkoSpin, a new method for biochemical isolation of pathological TDP-43. By combining SarkoSpin with mass spectrometry, we revealed proteins beyond TDP-43 that become abnormally insoluble in a disease subtype–specific manner. We show that pTDP-43 extracted from brain forms stable assemblies of distinct densities and morphologies that are associated with disease subtypes. Importantly, biochemically extracted pTDP-43 assemblies showed differential neurotoxicity and seeding that were correlated with disease duration of FTLD subjects. Our data are consistent with the notion that disease heterogeneity could originate from alternate pathological TDP-43 conformations, which are reminiscent of prion strains
Published: 2019

10. 2D–3D synchronous/asynchronous camera fusion for visual odometry

Author: Danda Pani Paudel, Cédric Demonceaux, Adlane Habed, Pascal Vasseur, Computer Vision Laboratory - ETHZ [Zurich], Eidgenössische Technische Hochschule - Swiss Federal Institute of Technology [Zürich] (ETH Zürich), Equipe VIBOT - VIsion pour la roBOTique [ImViA EA7535 - ERL CNRS 6000] (VIBOT), Centre National de la Recherche Scientifique (CNRS)-Imagerie et Vision Artificielle [Dijon] (ImViA), Université de Bourgogne (UB)-Université de Bourgogne (UB), Laboratoire des sciences de l'ingénieur, de l'informatique et de l'imagerie (ICube), Institut National des Sciences Appliquées - Strasbourg (INSA Strasbourg), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Strasbourg (UNISTRA)-Centre National de la Recherche Scientifique (CNRS)-École Nationale du Génie de l'Eau et de l'Environnement de Strasbourg (ENGEES)-Réseau nanophotonique et optique, Centre National de la Recherche Scientifique (CNRS)-Université de Strasbourg (UNISTRA)-Université de Haute-Alsace (UHA) Mulhouse - Colmar (Université de Haute-Alsace (UHA))-Centre National de la Recherche Scientifique (CNRS)-Université de Strasbourg (UNISTRA)-Université de Haute-Alsace (UHA) Mulhouse - Colmar (Université de Haute-Alsace (UHA))-Matériaux et nanosciences d'Alsace (FMNGE), Institut de Chimie du CNRS (INC)-Université de Strasbourg (UNISTRA)-Université de Haute-Alsace (UHA) Mulhouse - Colmar (Université de Haute-Alsace (UHA))-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)-Institut de Chimie du CNRS (INC)-Université de Strasbourg (UNISTRA)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS), Laboratoire d'Informatique, de Traitement de l'Information et des Systèmes (LITIS), Université Le Havre Normandie (ULH), Normandie Université (NU)-Normandie Université (NU)-Université de Rouen Normandie (UNIROUEN), Normandie Université (NU)-Institut national des sciences appliquées Rouen Normandie (INSA Rouen Normandie), Institut National des Sciences Appliquées (INSA)-Normandie Université (NU)-Institut National des Sciences Appliquées (INSA), Equipe Systèmes de Transport Intelligent (STI - LITIS), Institut National des Sciences Appliquées (INSA)-Normandie Université (NU)-Institut National des Sciences Appliquées (INSA)-Université Le Havre Normandie (ULH), ANR-15-CE23-0010,pLaTINUM,Cartographie Long Terme pour la Mobilité Urbaine(2015), École Nationale du Génie de l'Eau et de l'Environnement de Strasbourg (ENGEES)-Université de Strasbourg (UNISTRA)-Institut National des Sciences Appliquées - Strasbourg (INSA Strasbourg), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Les Hôpitaux Universitaires de Strasbourg (HUS)-Centre National de la Recherche Scientifique (CNRS)-Matériaux et Nanosciences Grand-Est (MNGE), Université de Strasbourg (UNISTRA)-Université de Haute-Alsace (UHA) Mulhouse - Colmar (Université de Haute-Alsace (UHA))-Institut National de la Santé et de la Recherche Médicale (INSERM)-Institut de Chimie du CNRS (INC)-Centre National de la Recherche Scientifique (CNRS)-Université de Strasbourg (UNISTRA)-Université de Haute-Alsace (UHA) Mulhouse - Colmar (Université de Haute-Alsace (UHA))-Institut National de la Santé et de la Recherche Médicale (INSERM)-Institut de Chimie du CNRS (INC)-Centre National de la Recherche Scientifique (CNRS)-Réseau nanophotonique et optique, and Université de Strasbourg (UNISTRA)-Université de Haute-Alsace (UHA) Mulhouse - Colmar (Université de Haute-Alsace (UHA))-Centre National de la Recherche Scientifique (CNRS)-Université de Strasbourg (UNISTRA)-Centre National de la Recherche Scientifique (CNRS)
Subjects: Asynchronous cameras, 0209 industrial biotechnology, Visual Odometry, Computer science, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, 02 engineering and technology, Motion (physics), Synchronization, Nonlinear programming, Set (abstract data type), 020901 industrial engineering & automation, Artificial Intelligence, Motion estimation, 2D-3D registration, 0202 electrical engineering, electronic engineering, information engineering, Structure from motion, Structure-from-Motion, Computer vision, Visual odometry, 2D, business.industry, Asynchronous communication, REGISTRATION, 020201 artificial intelligence & image processing, Artificial intelligence, business, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing
Abstract: International audience; We propose a robust and direct 2D-3D registration method for camera synchronization. Once the cameras are synchronizedor for synchronous setupswe also propose a visual odometry framework that benefits from both 2D and 3D acquisitions. Our method does not require a precise set of 2D-to-3D correspondences, handles occlusions and works when the scene is only partially known. It is carried out through a 2D-3D based initial motion estimation followed by a constrained nonlinear optimization for motion refinement. The problems of occlusion and that of missing scene parts are handled by comparing the image-based reconstruction and 3D sensor measurements. The results of our experiments demonstrate that the proposed framework allows to obtain a good initial motion estimate and a significant improvement through refinement.Keywords
Published: 2019

11. Evaluation of 2D and 3D ultrasound tracking algorithms and impact on ultrasound-guided liver radiotherapy margins

Author: Alex Rothberg, Camiel Klink, Adriaan Moelker, Lucas Royer, Orcun Goksel, Julia A. Schnabel, Theo van Walsum, Muyinatu A. Lediju Bell, Mark Gooding, Guillaume Dardenne, Alexandre Krupa, Wiro J. Niessen, Satoshi Kondo, Daniel Nouri, Amalia Cifor, Emma J. Harris, Andre Hallack, Valeria De Luca, Jyotirmoy Banerjee, Maxim Makhinya, Maud Marchal, Christine Tanner, Bartlomiej W. Papiez, Anthony Le Bras, Centre de Recherches Sémiotiques (CeReS), Institut Sciences de l'Homme et de la Société (IR SHS UNILIM), Université de Limoges (UNILIM)-Université de Limoges (UNILIM), University College of London [London] (UCL), University of Oxford, Konica Minolta Inc. [Osaka], Computer Vision Laboratory - ETHZ [Zurich], Eidgenössische Technische Hochschule - Swiss Federal Institute of Technology [Zürich] (ETH Zürich), Natural Vision UG [Berlin], Sensor-based and interactive robotics (RAINBOW), Inria Rennes – Bretagne Atlantique, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-SIGNAUX ET IMAGES NUMÉRIQUES, ROBOTIQUE (IRISA-D5), Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT), Institut de Recherche Technologique b-com (IRT b-com), Institute of Biomedical Engineering [Oxford] (IBME), Mirada Medical Ltd. [Oxford], Erasmus University Medical Center [Rotterdam] (Erasmus MC), 3D interaction with virtual environments using body and mind (Hybrid), Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-MEDIA ET INTERACTIONS (IRISA-D6), Image sciences institute - University of Utrecht (ISI), University Medical Center [Utrecht], 4Catalyzer Inc. [Guilford], The institute of cancer research [London], Department of Electrical and Computer Engineering [Johns Hopkins University] (ECE), Johns Hopkins University (JHU), Radiology & Nuclear Medicine, University of Oxford [Oxford], Université de Bretagne Sud (UBS)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National de Recherche en Informatique et en Automatique (Inria)-École normale supérieure - Rennes (ENS Rennes)-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-CentraleSupélec-IMT Atlantique Bretagne-Pays de la Loire (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Bretagne Sud (UBS)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-École normale supérieure - Rennes (ENS Rennes)-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes 1 (UR1), Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique Bretagne-Pays de la Loire (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Rennes 1 (UR1), and Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique Bretagne-Pays de la Loire (IMT Atlantique)
Subjects: Adult, medicine.medical_specialty, respiratory motion, medicine.medical_treatment, motion prediction, Liver ultrasound, 030218 nuclear medicine & medical imaging, Young Adult, 03 medical and health sciences, Imaging, Three-Dimensional, 0302 clinical medicine, Motion prediction, medicine, Humans, [INFO.INFO-RB]Computer Science [cs]/Robotics [cs.RO], 3D ultrasound, image guidance, treatment margins, Image guidance, Ultrasonography, medicine.diagnostic_test, business.industry, ultrasound, Ultrasound, Respiratory motion, General Medicine, Healthy Volunteers, Ultrasound guided, 3. Good health, Radiation therapy, Liver, 030220 oncology & carcinogenesis, Radiology, business, Algorithms, Radiotherapy, Image-Guided
Abstract: Purpose: Compensation for respiratory motion is important during abdominal cancer treatments. In this work we report the results of the 2015 MICCAI Challenge on Liver Ultrasound Tracking and extend the 2D results to relate them to clinical relevance in form of reducing treatment margins and hence sparing healthy tissues, while maintaining full duty cycle.Methods: We describe methodologies for estimating and temporally predicting respiratory liver motion from continuous ultrasound imaging, used during ultrasound‐guided radiation therapy. Furthermore, we investigated the trade‐off between tracking accuracy and runtime in combination with temporal prediction strategies and their impact on treatment margins.Results: Based on 2D ultrasound sequences from 39 volunteers, a mean tracking accuracy of 0.9 mm was achieved when combining the results from the 4 challenge submissions (1.2 to 3.3 mm). The two submissions for the 3D sequences from 14 volunteers provided mean accuracies of 1.7 and 1.8 mm. In combination with temporal prediction, using the faster (41 vs 228 ms) but less accurate (1.4 vs 0.9 mm) tracking method resulted in substantially reduced treatment margins (70% vs 39%) in contrast to mid‐ventilation margins, as it avoided non‐linear temporal prediction by keeping the treatment system latency low (150 vs 400 ms). Acceleration of the best tracking method would improve the margin reduction to 75%.Conclusions: Liver motion estimation and prediction during free‐breathing from 2D ultrasound images can substantially reduce the in‐plane motion uncertainty and hence treatment margins. Employing an accurate tracking method while avoiding non‐linear temporal prediction would be favorable. This approach has the potential to shorten treatment time compared to breath‐hold and gated approaches, and increase treatment efficiency and safety.
Published: 2018

12. A Generative Probabilistic Model and Discriminative Extensions for Brain Lesion Segmentation— With Application to Tumor and Stroke

Author: Tammy Riklin-Raviv, Gábor Székely, Bjoern H. Menze, Ezequiel Geremia, Marc-André Weber, Esther Alberts, Susanne Wegener, Danial Lashkari, Nicholas Ayache, Philipp Gruber, Polina Golland, Koen Van Leemput, Computer Science and Artificial Intelligence Laboratory [Cambridge] (CSAIL), Massachusetts Institute of Technology (MIT), Analysis and Simulation of Biomedical Images (ASCLEPIOS), Inria Sophia Antipolis - Méditerranée (CRISAM), Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Computer Vision Laboratory - ETHZ [Zurich], Eidgenössische Technische Hochschule - Swiss Federal Institute of Technology [Zürich] (ETH Zürich), Institute for Advanced Study [Munich] (TUM-IAS), Technische Universität Munchen - Université Technique de Munich [Munich, Allemagne] (TUM), Department of radiology (Massachusetts General Hospital), Massachusetts General Hospital [Boston], Universitätsspital Zürich (USZ), Diagnostic and Interventional Radiology [Heidelberg], Heidelberg University Hospital [Heidelberg], Division of Medical Physics in Radiology [Heidelberg], German Cancer Research Center - Deutsches Krebsforschungszentrum [Heidelberg] (DKFZ), Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory, Menze, Bjoern Holger, Lashkari, Danial, and Golland, Polina
Subjects: Computer science, Gaussian, Physics::Medical Physics, 030218 nuclear medicine & medical imaging, 0302 clinical medicine, Discriminative model, Segmentation, Computer vision, Image segmentation, Radiological and Ultrasound Technology, medicine.diagnostic_test, Brain Neoplasms, Brain, Magnetic Resonance Imaging, Bayes methods, Computer Science Applications, Stroke, Generative model, Anatomical structure, Feature (computer vision), symbols, medicine.symptom, Algorithms, Object segmentation, Channel (digital image), Quantitative Biology::Tissues and Organs, Brain tumor, [SCCO.COMP]Cognitive science/Computer science, Article, Lesion, 03 medical and health sciences, symbols.namesake, Glioma, medicine, Humans, Electrical and Electronic Engineering, Tumors, Models, Statistical, Medical diagnostic imaging, business.industry, Probabilistic logic, Bayes Theorem, Pattern recognition, Magnetic resonance imaging, medicine.disease, Artificial intelligence, business, 030217 neurology & neurosurgery, Software
Abstract: We introduce a generative probabilistic model for segmentation of brain lesions in multi-dimensional images that generalizes the EM segmenter, a common approach for modelling brain images using Gaussian mixtures and a probabilistic tissue atlas that employs expectation-maximization (EM), to estimate the label map for a new image. Our model augments the probabilistic atlas of the healthy tissues with a latent atlas of the lesion. We derive an estimation algorithm with closed-form EM update equations. The method extracts a latent atlas prior distribution and the lesion posterior distributions jointly from the image data. It delineates lesion areas individually in each channel, allowing for differences in lesion appearance across modalities, an important feature of many brain tumor imaging sequences. We also propose discriminative model extensions to map the output of the generative model to arbitrary labels with semantic and biological meaning, such as “tumor core” or “fluid-filled structure”, but without a one-to-one correspondence to the hypo- or hyper-intense lesion areas identified by the generative model. We test the approach in two image sets: the publicly available BRATS set of glioma patient scans, and multimodal brain images of patients with acute and subacute ischemic stroke. We find the generative model that has been designed for tumor lesions to generalize well to stroke images, and the extended discriminative -discriminative model to be one of the top ranking methods in the BRATS evaluation., National Alliance for Medical Image Computing (U.S.) (NIH NIBIB NAMIC U54- EB005149), Neuroimaging Analysis Center (U.S.) (NIH NIBIB NAC P41EB015902), National Institute for Biomedical Imaging and Bioengineering (U.S.) (R01EB013565), Lundbeck Foundation (R141-2013-13117)
Published: 2016

13. Deep Learning Techniques for Automatic MRI Cardiac Multi-Structures Segmentation and Diagnosis: Is the Problem Solved?

Author: Frederick Cervenansky, Gerard Sanroma, Jay Patravali, Sandy Engelhardt, Pheng-Ann Heng, Georgios Tziritas, Clement Zotti, Elias Grinias, Paul F. Jäger, Mahendra Khened, Klaus H. Maier-Hein, Ganapathy Krishnamurthi, Karim Lekadir, Yoonmi Hong, Xin Yang, Steffen E. Petersen, Ivo Wolf, Christian F. Baumgartner, Xavier Pennec, Olivier Bernard, Sandy Napel, Jelmer M. Wolterink, Miguel Ángel González Ballester, Marc-Michel Rohé, Peter M. Full, Ivana Išgum, Lisa M. Koch, Fabian Isensee, Varghese Alex Kollerathu, Alain Lalande, Olivier Humbert, Yeonggul Jang, Maxime Sermesant, Irem Cetin, Oscar Camara, Shubham Jain, Pierre-Marc Jodoin, Images et Modèles, Centre de Recherche en Acquisition et Traitement de l'Image pour la Santé (CREATIS), Université Jean Monnet [Saint-Étienne] (UJM)-Hospices Civils de Lyon (HCL)-Institut National des Sciences Appliquées de Lyon (INSA Lyon), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Université de Lyon-Institut National des Sciences Appliquées (INSA)-Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-Centre National de la Recherche Scientifique (CNRS)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Université Jean Monnet [Saint-Étienne] (UJM)-Hospices Civils de Lyon (HCL)-Institut National des Sciences Appliquées de Lyon (INSA Lyon), Université de Lyon-Centre National de la Recherche Scientifique (CNRS)-Institut National de la Santé et de la Recherche Médicale (INSERM), Laboratoire d'Electronique, d'Informatique et d'Image [EA 7508] (Le2i), Université de Technologie de Belfort-Montbeliard (UTBM)-Université de Bourgogne (UB)-École Nationale Supérieure d'Arts et Métiers (ENSAM), Arts et Métiers Sciences et Technologies, HESAM Université (HESAM)-HESAM Université (HESAM)-Arts et Métiers Sciences et Technologies, HESAM Université (HESAM)-HESAM Université (HESAM)-AgroSup Dijon - Institut National Supérieur des Sciences Agronomiques, de l'Alimentation et de l'Environnement-Centre National de la Recherche Scientifique (CNRS), Département d'informatique [Sherbrooke] (UdeS), Faculté des sciences [Sherbrooke] (UdeS), Université de Sherbrooke (UdeS)-Université de Sherbrooke (UdeS), Service Informatique et développements, The Chinese University of Hong Kong [Hong Kong], Universitat Pompeu Fabra [Barcelona] (UPF), Institució Catalana de Recerca i Estudis Avançats (ICREA), Stanford School of Medicine [Stanford], Stanford Medicine, Stanford University-Stanford University, William Harvey Research Institute, Barts and the London Medical School, Computer Science Department [Crete] (CSD-UOC), School of Sciences and Engineering [Crete] (SSE-UOC), University of Crete [Heraklion] (UOC)-University of Crete [Heraklion] (UOC), Department of Engineering Design [Madras], Indian Institute of Technology Madras (IIT Madras), Analysis and Simulation of Biomedical Images (ASCLEPIOS), Inria Sophia Antipolis - Méditerranée (CRISAM), Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), E-Patient : Images, données & mOdèles pour la médeciNe numériquE (EPIONE), German Cancer Research Center - Deutsches Krebsforschungszentrum [Heidelberg] (DKFZ), Heidelberg University Hospital [Heidelberg], Hochschule Mannheim - University of Applied Sciences, Computer Vision Laboratory - ETHZ [Zurich], Eidgenössische Technische Hochschule - Swiss Federal Institute of Technology [Zürich] (ETH Zürich), University Medical Center [Utrecht], Yonsei University, Qure.ai company, Transporteurs et Imagerie, Radiothérapie en Oncologie et Mécanismes biologiques des Altérations du Tissu Osseux (TIRO-MATOs - UMR E4320), UMR E4320 (TIRO-MATOs), Université Nice Sophia Antipolis (... - 2019) (UNS), COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Côte d'Azur (UCA)-Université Nice Sophia Antipolis (... - 2019) (UNS), COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Côte d'Azur (UCA)-Service Hospitalier Frédéric Joliot (SHFJ), Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay, Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-Université de Lyon-Institut National des Sciences Appliquées de Lyon (INSA Lyon), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université Jean Monnet - Saint-Étienne (UJM)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)-Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université Jean Monnet - Saint-Étienne (UJM)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS), HESAM Université - Communauté d'universités et d'établissements Hautes écoles Sorbonne Arts et métiers université (HESAM)-HESAM Université - Communauté d'universités et d'établissements Hautes écoles Sorbonne Arts et métiers université (HESAM)-Arts et Métiers Sciences et Technologies, HESAM Université - Communauté d'universités et d'établissements Hautes écoles Sorbonne Arts et métiers université (HESAM)-HESAM Université - Communauté d'universités et d'établissements Hautes écoles Sorbonne Arts et métiers université (HESAM)-Centre National de la Recherche Scientifique (CNRS), Service Hospitalier Frédéric Joliot (SHFJ), Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-UMR E4320 (TIRO-MATOs), Université Nice Sophia Antipolis (1965 - 2019) (UNS), COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Côte d'Azur (UCA)-Université Nice Sophia Antipolis (1965 - 2019) (UNS), and COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Côte d'Azur (UCA)
Subjects: Male, Databases, Factual, Heart Diseases, Computer science, [SDV]Life Sciences [q-bio], Lleft and right ventricles, 030218 nuclear medicine & medical imaging, Task (project management), Cardiac segmentation and diagnosis, 03 medical and health sciences, 0302 clinical medicine, Deep Learning, Image Interpretation, Computer-Assisted, medicine, Medical imaging, Humans, Segmentation, Electrical and Electronic Engineering, Radiological and Ultrasound Technology, medicine.diagnostic_test, business.industry, Myocardium, Deep learning, Magnetic resonance imaging, Pattern recognition, Heart, Image segmentation, Magnetic Resonance Imaging, Computer Science Applications, Cardiac Imaging Techniques, medicine.anatomical_structure, Ventricle, Female, Artificial intelligence, business, Cardiac magnetic resonance, Left and right ventricles, 030217 neurology & neurosurgery, Software, MRI
Abstract: Delineation of the left ventricular cavity, myocardium, and right ventricle from cardiac magnetic resonance images (multi-slice 2-D cine MRI) is a common clinical task to establish diagnosis. The automation of the corresponding tasks has thus been the subject of intense research over the past decades. In this paper, we introduce the “Automatic Cardiac Diagnosis Challenge” dataset (ACDC), the largest publicly available and fully annotated dataset for the purpose of cardiac MRI (CMR) assessment. The dataset contains data from 150 multi-equipments CMRI recordings with reference measurements and classification from two medical experts. The overarching objective of this paper is to measure how far state-of-the-art deep learning methods can go at assessing CMRI, i.e., segmenting the myocardium and the two ventricles as well as classifying pathologies. In the wake of the 2017 MICCAI-ACDC challenge, we report results from deep learning methods provided by nine research groups for the segmentation task and four groups for the classification task. Results show that the best methods faithfully reproduce the expert analysis, leading to a mean value of 0.97 correlation score for the automatic extraction of clinical indices and an accuracy of 0.96 for automatic diagnosis. These results clearly open the door to highly accurate and fully automatic analysis of cardiac CMRI. We also identify scenarios for which deep learning methods are still failing. Both the dataset and detailed results are publicly available online, while the platform will remain open for new submissions.
Published: 2018

14. Simulation and Synthesis in Medical Imaging

Author: Ninon Burgos, Ipek Oguz, Orcun Goksel, Ali Gooya, Center for Computational Imaging and Simulation Technologies in Biomedicine [Sheffield] (CISTIB), University of Sheffield [Sheffield], Computer Vision Laboratory - ETHZ [Zurich], Eidgenössische Technische Hochschule - Swiss Federal Institute of Technology [Zürich] (ETH Zürich), Vanderbilt University [Nashville], Algorithms, models and methods for images and signals of the human brain (ARAMIS), Sorbonne Université (SU)-Inria de Paris, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Institut du Cerveau et de la Moëlle Epinière = Brain and Spine Institute (ICM), Institut National de la Santé et de la Recherche Médicale (INSERM)-CHU Pitié-Salpêtrière [AP-HP], Sorbonne Université (SU)-Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-Sorbonne Université (SU)-Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS)-Institut National de la Santé et de la Recherche Médicale (INSERM)-CHU Pitié-Salpêtrière [AP-HP], Sorbonne Université (SU)-Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS), Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Institut du Cerveau = Paris Brain Institute (ICM), Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-Institut National de la Santé et de la Recherche Médicale (INSERM)-CHU Pitié-Salpêtrière [AP-HP], Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-Sorbonne Université (SU)-Sorbonne Université (SU)-Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS)-Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-Institut National de la Santé et de la Recherche Médicale (INSERM)-CHU Pitié-Salpêtrière [AP-HP], Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-Sorbonne Université (SU)-Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS), Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS)-Institut National de la Santé et de la Recherche Médicale (INSERM)-CHU Pitié-Salpêtrière [AP-HP], Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS), Ali Gooya, Orcun Goksel, Ipek Oguz, and Ninon Burgos
Subjects: medicine.medical_specialty, Engineering, business.industry, Medical imaging, medicine, [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, Medical physics, business, ComputingMilieux_MISCELLANEOUS, Conjunction (grammar)
Abstract: International audience
Published: 2018

15. Visual Quality Assessment of 3D Models : on the Influence of Light-Material Interaction

Author: Guillaume Lavoué, Pierre Kraemer, Basile Sauvage, Kenneth Vanhoey, Computer Vision Laboratory - ETHZ [Zurich], Eidgenössische Technische Hochschule - Swiss Federal Institute of Technology [Zürich] (ETH Zürich), Laboratoire des sciences de l'ingénieur, de l'informatique et de l'imagerie (ICube), École Nationale du Génie de l'Eau et de l'Environnement de Strasbourg (ENGEES)-Université de Strasbourg (UNISTRA)-Institut National des Sciences Appliquées - Strasbourg (INSA Strasbourg), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Les Hôpitaux Universitaires de Strasbourg (HUS)-Centre National de la Recherche Scientifique (CNRS)-Matériaux et Nanosciences Grand-Est (MNGE), Université de Strasbourg (UNISTRA)-Université de Haute-Alsace (UHA) Mulhouse - Colmar (Université de Haute-Alsace (UHA))-Institut National de la Santé et de la Recherche Médicale (INSERM)-Institut de Chimie du CNRS (INC)-Centre National de la Recherche Scientifique (CNRS)-Université de Strasbourg (UNISTRA)-Université de Haute-Alsace (UHA) Mulhouse - Colmar (Université de Haute-Alsace (UHA))-Institut National de la Santé et de la Recherche Médicale (INSERM)-Institut de Chimie du CNRS (INC)-Centre National de la Recherche Scientifique (CNRS)-Réseau nanophotonique et optique, Université de Strasbourg (UNISTRA)-Université de Haute-Alsace (UHA) Mulhouse - Colmar (Université de Haute-Alsace (UHA))-Centre National de la Recherche Scientifique (CNRS)-Université de Strasbourg (UNISTRA)-Centre National de la Recherche Scientifique (CNRS), Geometry Processing and Constrained Optimization (M2DisCo), Laboratoire d'InfoRmatique en Image et Systèmes d'information (LIRIS), Université Lumière - Lyon 2 (UL2)-École Centrale de Lyon (ECL), Université de Lyon-Université de Lyon-Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-Institut National des Sciences Appliquées de Lyon (INSA Lyon), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Centre National de la Recherche Scientifique (CNRS)-Université Lumière - Lyon 2 (UL2)-École Centrale de Lyon (ECL), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Centre National de la Recherche Scientifique (CNRS), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Centre National de la Recherche Scientifique (CNRS)-Matériaux et nanosciences d'Alsace (FMNGE), Institut de Chimie du CNRS (INC)-Université de Strasbourg (UNISTRA)-Université de Haute-Alsace (UHA) Mulhouse - Colmar (Université de Haute-Alsace (UHA))-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)-Institut de Chimie du CNRS (INC)-Université de Strasbourg (UNISTRA)-Université de Haute-Alsace (UHA) Mulhouse - Colmar (Université de Haute-Alsace (UHA))-Institut National de la Santé et de la Recherche Médicale (INSERM)-Centre National de la Recherche Scientifique (CNRS)-Réseau nanophotonique et optique, Centre National de la Recherche Scientifique (CNRS)-Université de Strasbourg (UNISTRA)-Université de Haute-Alsace (UHA) Mulhouse - Colmar (Université de Haute-Alsace (UHA))-Centre National de la Recherche Scientifique (CNRS)-Université de Strasbourg (UNISTRA), Institut National des Sciences Appliquées de Lyon (INSA Lyon), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Université de Lyon-Institut National des Sciences Appliquées (INSA)-Centre National de la Recherche Scientifique (CNRS)-Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-École Centrale de Lyon (ECL), Université de Lyon-Université Lumière - Lyon 2 (UL2)-Institut National des Sciences Appliquées de Lyon (INSA Lyon), and Université de Lyon-Université Lumière - Lyon 2 (UL2)
Subjects: General Computer Science, business.industry, Quality assessment, Computer science, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, 020207 software engineering, Experimental and Cognitive Psychology, 3d model, 02 engineering and technology, [INFO.INFO-CG]Computer Science [cs]/Computational Geometry [cs.CG], [INFO.INFO-GR]Computer Science [cs]/Graphics [cs.GR], Theoretical Computer Science, Rendering (computer graphics), Perceived quality, [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, Polygon mesh, Computer vision, Artificial intelligence, business, Perceptual image, ComputingMilieux_MISCELLANEOUS, Perceptual study
Abstract: Geometric modifications of three-dimensional (3D) digital models are commonplace for the purpose of efficient rendering or compact storage. Modifications imply visual distortions that are hard to measure numerically. They depend not only on the model itself but also on how the model is visualized. We hypothesize that the model’s light environment and the way it reflects incoming light strongly influences perceived quality. Hence, we conduct a perceptual study demonstrating that the same modifications can be masked, or conversely highlighted, by different light-matter interactions. Additionally, we propose a new metric that predicts the perceived distortion of 3D modifications for a known interaction. It operates in the space of 3D meshes with the object’s appearance, that is, the light emitted by its surface in any direction given a known incoming light. Despite its simplicity, this metric outperforms 3D mesh metrics and competes with sophisticated perceptual image-based metrics in terms of correlation to subjective measurements. Unlike image-based methods, it has the advantage of being computable prior to the costly rendering steps of image projection and rasterization of the scene for given camera parameters.
Published: 2017

16. Static and Dynamic Objects Analysis as a 3D Vector Field

Author: Danda Pani Paudel, Cansen Jiang, Yohan Fougerolle, Cédric Demonceaux, David Fofi, Laboratoire Electronique, Informatique et Image [UMR6306] (Le2i), Université de Bourgogne (UB)-Centre National de la Recherche Scientifique (CNRS)-École Nationale Supérieure d'Arts et Métiers (ENSAM), Arts et Métiers Sciences et Technologies, HESAM Université (HESAM)-HESAM Université (HESAM)-Arts et Métiers Sciences et Technologies, HESAM Université (HESAM)-HESAM Université (HESAM)-AgroSup Dijon - Institut National Supérieur des Sciences Agronomiques, de l'Alimentation et de l'Environnement, Computer Vision Laboratory - ETHZ [Zurich], Eidgenössische Technische Hochschule - Swiss Federal Institute of Technology [Zürich] (ETH Zürich), ANR-15-CE23-0010,pLaTINUM,Cartographie Long Terme pour la Mobilité Urbaine(2015), Laboratoire Electronique, Informatique et Image ( Le2i ), Université de Bourgogne ( UB ) -AgroSup Dijon - Institut National Supérieur des Sciences Agronomiques, de l'Alimentation et de l'Environnement-Centre National de la Recherche Scientifique ( CNRS ), Eidgenössische Technische Hochschule [Zürich] ( ETH Zürich ), ANR-15-CE23-0010,Long Term MappINg for Urban Mobility,ANR pLaTINUM, Université de Bourgogne (UB)-École Nationale Supérieure d'Arts et Métiers (ENSAM), HESAM Université (HESAM)-HESAM Université (HESAM)-AgroSup Dijon - Institut National Supérieur des Sciences Agronomiques, de l'Alimentation et de l'Environnement-Centre National de la Recherche Scientifique (CNRS), JIANG, CANSEN, and Cartographie Long Terme pour la Mobilité Urbaine - - pLaTINUM2015 - ANR-15-CE23-0010 - AAPG2015 - VALID
Subjects: 0209 industrial biotechnology, Computer science, business.industry, [INFO.INFO-RB] Computer Science [cs]/Robotics [cs.RO], [ INFO.INFO-RB ] Computer Science [cs]/Robotics [cs.RO], ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Point cloud, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], Context (language use), Motion detection, 02 engineering and technology, [ INFO.INFO-CV ] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], [INFO.INFO-CV] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], 020901 industrial engineering & automation, Flow (mathematics), Motion estimation, 0202 electrical engineering, electronic engineering, information engineering, [INFO.INFO-RB]Computer Science [cs]/Robotics [cs.RO], 020201 artificial intelligence & image processing, Segmentation, Computer vision, Artificial intelligence, Cluster analysis, business, Euclidean vector
Abstract: International audience; In the context of scene modelling, understanding, and landmark-based robot navigation, the knowledge of static scene parts and moving objects with their motion behaviours plays a vital role. We present a complete framework to detect and extract the moving objects to reconstruct a high quality static map. For a moving 3D camera setup, we propose a novel 3D Flow Field Analysis approach which accurately detects the moving objects using only 3D point cloud information. Further, we introduce a Sparse Flow Clustering approach to effectively and robustly group the motion flow vectors. Experiments show that the proposed Flow Field Analysis algorithm and Sparse Flow Clustering approach are highly effective for motion detection and seg-mentation, and yield high quality reconstructed static maps as well as rigidly moving objects of real-world scenarios.
Published: 2017

17. High Quality Reconstruction of Dynamic Objects using 2D-3D Camera Fusion

Author: Cansen Jiang, Cédric Demonceaux, Danda Pani Paudel, Dennis Aprilla Christie, Laboratoire Electronique, Informatique et Image ( Le2i ), Université de Bourgogne ( UB ) -AgroSup Dijon - Institut National Supérieur des Sciences Agronomiques, de l'Alimentation et de l'Environnement-Centre National de la Recherche Scientifique ( CNRS ), Gunadarma University, Computer Vision Laboratory - ETHZ [Zurich], Eidgenössische Technische Hochschule [Zürich] ( ETH Zürich ), JIANG, CANSEN, Laboratoire Electronique, Informatique et Image [UMR6306] (Le2i), Université de Bourgogne (UB)-Centre National de la Recherche Scientifique (CNRS)-École Nationale Supérieure d'Arts et Métiers (ENSAM), Arts et Métiers Sciences et Technologies, HESAM Université (HESAM)-HESAM Université (HESAM)-Arts et Métiers Sciences et Technologies, HESAM Université (HESAM)-HESAM Université (HESAM)-AgroSup Dijon - Institut National Supérieur des Sciences Agronomiques, de l'Alimentation et de l'Environnement, and Eidgenössische Technische Hochschule - Swiss Federal Institute of Technology [Zürich] (ETH Zürich)
Subjects: 2D-3D Fusion, Point cloud, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, 02 engineering and technology, Iterative reconstruction, RANSAC, [ INFO.INFO-CV ] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], Vehicle dynamics, [INFO.INFO-CV] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], Robustness (computer science), Motion estimation, Point Cloud Registration, 0502 economics and business, [ INFO.INFO-TI ] Computer Science [cs]/Image Processing, 0202 electrical engineering, electronic engineering, information engineering, Computer vision, ComputingMethodologies_COMPUTERGRAPHICS, 050210 logistics & transportation, business.industry, 05 social sciences, 3D reconstruction, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], 020207 software engineering, ICP, Geography, [INFO.INFO-TI] Computer Science [cs]/Image Processing [eess.IV], [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], Artificial intelligence, business, 3D Reconstruction, Surface reconstruction
Abstract: International audience; In this paper, we propose a complete pipeline for high quality reconstruction of dynamic objects using 2D-3D camera setup attached to a moving vehicle. Starting from the segmented motion trajectories of individual objects, we compute their precise motion parameters, register multiple sparse point clouds to increase the density, and develop a smooth and textured surface from the dense (but scattered) point cloud. The success of our method relies on the proposed optimization framework for accurate motion estimation between two sparse point clouds. Our formulation for fusing it closest-point and it consensus based motion estimations, respectively in the absence and presence of motion trajectories, is the key to obtain such accuracy. Several experiments performed on both synthetic and real (KITTI) datasets show that the proposed framework is very robust and accurate.
Published: 2017

18. Incomplete 3D motion trajectory segmentation and 2D-to-3D label transfer for dynamic scene analysis

Author: Cédric Demonceaux, Danda Pani Paudel, Yohan Fougerolle, Cansen Jiang, David Fofi, Laboratoire Electronique, Informatique et Image ( Le2i ), Université de Bourgogne ( UB ) -AgroSup Dijon - Institut National Supérieur des Sciences Agronomiques, de l'Alimentation et de l'Environnement-Centre National de la Recherche Scientifique ( CNRS ), Computer Vision Laboratory - ETHZ [Zurich], Eidgenössische Technische Hochschule [Zürich] ( ETH Zürich ), Laboratoire Electronique, Informatique et Image [UMR6306] (Le2i), Université de Bourgogne (UB)-Centre National de la Recherche Scientifique (CNRS)-École Nationale Supérieure d'Arts et Métiers (ENSAM), Arts et Métiers Sciences et Technologies, HESAM Université (HESAM)-HESAM Université (HESAM)-Arts et Métiers Sciences et Technologies, HESAM Université (HESAM)-HESAM Université (HESAM)-AgroSup Dijon - Institut National Supérieur des Sciences Agronomiques, de l'Alimentation et de l'Environnement, Eidgenössische Technische Hochschule - Swiss Federal Institute of Technology [Zürich] (ETH Zürich), ANR-15-CE23-0010,pLaTINUM,Cartographie Long Terme pour la Mobilité Urbaine(2015), Université de Bourgogne (UB)-École Nationale Supérieure d'Arts et Métiers (ENSAM), HESAM Université (HESAM)-HESAM Université (HESAM)-AgroSup Dijon - Institut National Supérieur des Sciences Agronomiques, de l'Alimentation et de l'Environnement-Centre National de la Recherche Scientifique (CNRS), JIANG, CANSEN, and Cartographie Long Terme pour la Mobilité Urbaine - - pLaTINUM2015 - ANR-15-CE23-0010 - AAPG2015 - VALID
Subjects: Computer science, Scene Understanding, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, 02 engineering and technology, [ INFO.INFO-CV ] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], Motion (physics), [INFO.INFO-CV] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], 0502 economics and business, 0202 electrical engineering, electronic engineering, information engineering, [INFO.INFO-RB]Computer Science [cs]/Robotics [cs.RO], Computer vision, Segmentation, Motion Segmentation, 050210 logistics & transportation, business.industry, [INFO.INFO-RB] Computer Science [cs]/Robotics [cs.RO], [ INFO.INFO-RB ] Computer Science [cs]/Robotics [cs.RO], 05 social sciences, 3D reconstruction, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], 2D to 3D conversion, Feature (computer vision), Trajectory, Key (cryptography), Robot, 020201 artificial intelligence & image processing, Artificial intelligence, 3D Reconstruction, business
Abstract: International audience; The knowledge of the static scene parts and the moving objects in a dynamic scene plays a vital role for scene modelling, understanding, and landmark-based robot navigation. The key information for these tasks lies on semantic labels of the scene parts and the motion trajectories of the dynamic objects. In this work, we propose a method that segments the 3D feature trajectories based on their motion behaviours, and assigns them semantic labels using 2D-to-3D label transfer. These feature trajectories are constructed by using the proposed trajectory recovery algorithm which takes the loss of feature tracking into account. We introduce a complete framework for static-map and dynamic objects' reconstruction, as well as semantic scene understanding for a calibrated and moving 2D-3D camera setup. Our motion segmentation approach is faster by two orders of magnitude, while performing better than the state-of-the-art 3D motion segmentation methods, and successfully handles the previously discarded incomplete trajectory scenarios.
Published: 2017

19. Fully implicit methodology for the dynamics of biomembranes and capillary interfaces by combining the level set and Newton methods

Author: Chaouqi Misbah, Gábor Székely, Pierre Saramito, Aymen Laadhari, Computer Vision Laboratory - ETHZ [Zurich], Eidgenössische Technische Hochschule - Swiss Federal Institute of Technology [Zürich] (ETH Zürich), Equations aux Dérivées Partielles (EDP ), Laboratoire Jean Kuntzmann (LJK ), Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes [2016-2019] (UGA [2016-2019])-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes [2016-2019] (UGA [2016-2019]), Laboratoire Interdisciplinaire de Physique [Saint Martin d’Hères] (LIPhy), and Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes [2016-2019] (UGA [2016-2019])
Subjects: Finite element method, Physics and Astronomy (miscellaneous), Discretization, Canham–Helfrich–Evans model, Stability (learning theory), Signed distance function, 01 natural sciences, 010305 fluids & plasmas, Level set, 0103 physical sciences, Convergence (routing), Canham-Helfrich-Evans model, Inexact Newton method, Red blood cell, Vesicle, Surface tension, 0101 mathematics, Mathematics, Numerical Analysis, Applied Mathematics, Tangent, Computer Science Applications, 010101 applied mathematics, Computational Mathematics, Nonlinear system, Modeling and Simulation, Algorithm, [MATH.MATH-NA]Mathematics [math]/Numerical Analysis [math.NA]
Abstract: International audience; This framework is concerned with the numerical modeling of the dynamics of individual biomembranes and capillary interfaces in a surrounding Newtonian fluid. A level set approach helps to follow the interface motion. Our method features the use of high order fully implicit time integration schemes that enable to overcome stability issues related to the explicit discretization of the highly non-linear bending force or capillary force. At each time step, the tangent systems are derived and the resulting nonlinear problems are solved by a Newton–Raphson method. Based on the signed distance assumption, several inexact Newton strategies are employed to solve the capillary and vesicle problems and guarantee the second-order convergence behavior. We address in detail the main features of the proposed method, and we report several experiments in the two-dimensional case with the aim of illustrating its accuracy and efficiency. Comparative investigations with respect to the fully explicit scheme depict the stabilizing effect of the new method, which allows to use significantly larger time step sizes.
Published: 2017

20. An adaptive finite element method for the modeling of the equilibrium of red blood cells

Author: Laadhari, Aymen, Saramito, Pierre, Misbah, Chaouqi, Computer Vision Laboratory - ETHZ [Zurich], Eidgenössische Technische Hochschule - Swiss Federal Institute of Technology [Zürich] (ETH Zürich), Equations aux Dérivées Partielles (EDP ), Laboratoire Jean Kuntzmann (LJK ), Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes [2016-2019] (UGA [2016-2019])-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes [2016-2019] (UGA [2016-2019]), Laboratoire Interdisciplinaire de Physique [Saint Martin d’Hères] (LIPhy), and Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes [2016-2019] (UGA [2016-2019])
Subjects: Elastic bending energy, Lagrange multipliers, Canham and Helfrich model, Red Blood Cell, [PHYS.MPHY]Physics [physics]/Mathematical Physics [math-ph], Vesicle, Level set method, Numerical methods, Mesh adaptation, Finite element approximation, Minimization under constraints, [MATH.MATH-NA]Mathematics [math]/Numerical Analysis [math.NA]
Abstract: International audience; This contribution is concerned with a the numerical modeling of an isolated red blood cell (RBC), and more generally of phospholipid membranes. We propose an adaptive Eulerian finite element approximation, based on the level set method, of a shape optimization problem arising in the study of RBC's equilibrium. We simulate the equilibrium shapes that minimize the elastic bending energy under prescribed constraints of fixed volume and surface area. An anisotropic mesh adaptation technique is used in the vicinity of the cell's membrane to enhance the robustness of the method. Efficient time and spatial discretizations are considered and implemented. We address in detail the main features of the proposed method and finally we report several numerical experiments in the two-dimensional and the three-dimensional axisymmetric cases. The effectiveness of the numerical method is further demonstrated through numerical comparisons with semi-analytical solutions provided by a reduced order model.
Published: 2016

21. Confidence Bounds for the Estimation of the Volume Phase Fraction from a Single Image in a Nickel Base Superalloy

Author: Christian Germain, Pierre Baylou, Jean-Pierre da Costa, Rémi Blanc, Computer Vision Laboratory - ETHZ [Zurich], Eidgenössische Technische Hochschule - Swiss Federal Institute of Technology [Zürich] (ETH Zürich), Laboratoire de l'intégration, du matériau au système (IMS), and Université Sciences et Technologies - Bordeaux 1-Institut Polytechnique de Bordeaux-Centre National de la Recherche Scientifique (CNRS)
Subjects: Materials science, phase fraction, single section stereology, Context (language use), 02 engineering and technology, 01 natural sciences, spatial statistics, [SPI.MAT]Engineering Sciences [physics]/Materials, Image (mathematics), [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, measurement uncertainty, 0103 physical sciences, Forensic engineering, nickel base superalloy, Instrumentation, Spatial analysis, 010302 applied physics, 021001 nanoscience & nanotechnology, Confidence interval, Superalloy, Volume fraction, Measurement uncertainty, 0210 nano-technology, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing, Algorithm, scanning electron microscopy, Volume (compression)
Abstract: Microscopy and Microanalysis, 16 (3), ISSN:1431-9276, ISSN:1435-8115
Published: 2010

22. The Multimodal Brain Tumor Image Segmentation Benchmark (BRATS)

Author: Nicholas Ayache, Danial Lashkari, Yuliya Burren, Polina Golland, Duygu Sarikaya, Levente Lanczi, Florence Forbes, Binsheng Zhao, Michel Dojat, Brian B. Avants, Marcel Prastawa, Liang Zhao, Andac Hamamci, Jamie Shotton, Ben Glocker, Thomas J. Taylor, Joana Festa, Nicolas Cordier, Hervé Delingette, Johannes Slotboom, Doina Precup, Antonio Criminisi, Ezequiel Geremia, Lawrence H. Schwartz, Stephen J. Price, Gábor Székely, Carlos A. Silva, José Mariz, Owen M. Thomas, Tilak Das, Ender Konukoglu, Dong Hye Ye, Khan M. Iftekharuddin, Syed M. S. Reza, Xiaotao Guo, Koen Van Leemput, Raphael Meier, Senan Doyle, Christopher R. Durst, D. Louis Collins, Raj Jena, Tal Arbel, Elizabeth R. Gerstner, Darko Zikic, Çağatay Demiralp, Marc-André Weber, Keyvan Farahani, Nagesh K. Subbanna, Stefan Bauer, Nicholas J. Tustison, Sérgio Pereira, Bjoern H. Menze, Patricia Buendia, Jason J. Corso, Mauricio Reyes, Nuno Sousa, Max Wintermark, Jayashree Kalpathy-Cramer, Flor Vasseur, Justin Kirby, Gozde Unal, Andras Jakab, Roland Wiest, Tammy Riklin Raviv, Nigel M. John, N Porz, Michael Ryan, Hoo-Chang Shin, Analysis and Simulation of Biomedical Images (ASCLEPIOS), Inria Sophia Antipolis - Méditerranée (CRISAM), Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Computational Image Analysis and Radiology (CIR lab), Medizinische Universität Wien = Medical University of Vienna, Institute for Surgical Technology and Biomechanics [Bern] (ISTB), University of Bern, Massachusetts General Hospital [Boston], Department of Health and Human Services, National Institutes of Health [Bethesda] (NIH), Inselspital Bern, University of Debrecen Egyetem [Debrecen], Division of Medical Physics in Radiology [Heidelberg], German Cancer Research Center - Deutsches Krebsforschungszentrum [Heidelberg] (DKFZ), Diagnostic and Interventional Radiology [Heidelberg], Heidelberg University Hospital [Heidelberg], Centre for Intelligent Machines (CIM), McGill University = Université McGill [Montréal, Canada], Penn Image Computing & Science Lab [Philadelphia] (PICSL), University of Pennsylvania, INFOTECH Soft, McConnell Brain Imaging Centre (MNI), Montreal Neurological Institute and Hospital, McGill University = Université McGill [Montréal, Canada]-McGill University = Université McGill [Montréal, Canada], State University of New York (SUNY), Microsoft Research [Cambridge] (Microsoft), Microsoft Research, Cambridge University Hospitals - NHS (CUH), University of Cambridge [UK] (CAM), Computer Science Department [Stanford], Stanford University, Department of radiology and medical imaging [Charlottesville], University of Virginia, Grenoble Institut des Neurosciences (GIN), Université Joseph Fourier - Grenoble 1 (UJF)-Institut National de la Santé et de la Recherche Médicale (INSERM), Modelling and Inference of Complex and Structured Stochastic Systems (MISTIS), Inria Grenoble - Rhône-Alpes, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire Jean Kuntzmann (LJK), Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS)-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS), Universidade do Minho = University of Minho [Braga], Computer Science and Artificial Intelligence Laboratory [Cambridge] (CSAIL), Massachusetts Institute of Technology (MIT), Columbia University [New York], Faculty of Engineering and Natural Sciences (Sabanci University), Sabanci University [Istanbul], Old Dominion University [Norfolk] (ODU), Addenbrooke's Hospital, Cambridge University NHS Trust, Bangor University, Department of Surgery, Université de Genève = University of Geneva (UNIGE), Bristol Glaciology Centre, School of Geographical Sciences, Molecular Carcinogenesis [Sutton], Institute of cancer research, Center for Neuroscience and Cell Biology (CNC) (CNC), University of Coimbra [Portugal] (UC)-Neuroscience Research Domain, Computer Vision Laboratory - ETHZ [Zurich], Eidgenössische Technische Hochschule - Swiss Federal Institute of Technology [Zürich] (ETH Zürich), Department of Radiology [San Francisco], University of California [San Francisco] (UC San Francisco), University of California (UC)-University of California (UC), Purdue University [West Lafayette], Department of Computer Science [New York], Scientific Computing and Imaging Institute (SCI Institute), University of Utah, Department of radiology (Massachusetts General Hospital), European Project: 291080,EC:FP7:ERC,ERC-2011-ADG_20110209,MEDYMA(2012), Menze, Bjoern, Biophysical Modeling and Analysis of Dynamic Medical Images. - MEDYMA - - EC:FP7:ERC2012-04-01 - 2017-03-31 - 291080 - VALID, [et al.], University of Pennsylvania [Philadelphia], University of Virginia [Charlottesville], Universidade do Minho, University of Geneva [Switzerland], University of California [San Francisco] (UCSF), University of California-University of California, Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science, Golland, Polina, and Lashkari, Danial
Subjects: Computer science, Oncology/tumor, Brain tumor, [SCCO.COMP]Cognitive science/Computer science, Neuroimaging, Benchmark, computer.software_genre, Article, Set (abstract data type), [SCCO.COMP] Cognitive science/Computer science, Cut, medicine, Medical imaging, Humans, Electrical and Electronic Engineering, Image segmentation, Science & Technology, Radiological and Ultrasound Technology, business.industry, Brain, Pattern recognition, Glioma, medicine.disease, Magnetic Resonance Imaging, 3. Good health, Computer Science Applications, Benchmarking, Benchmark (computing), Data mining, Artificial intelligence, business, computer, Algorithms, Software, MRI
Abstract: In this paper we report the set-up and results of the Multimodal Brain Tumor Image Segmentation Benchmark (BRATS) organized in conjunction with the MICCAI 2012 and 2013 conferences. Twenty state-of-the-art tumor segmentation algorithms were applied to a set of 65 multi-contrast MR scans of low- and high-grade glioma patients - manually annotated by up to four raters - and to 65 comparable scans generated using tumor image simulation software. Quantitative evaluations revealed considerable disagreement between the human raters in segmenting various tumor sub-regions (Dice scores in the range 74%-85%), illustrating the difficulty of this task. We found that different algorithms worked best for different sub-regions (reaching performance comparable to human inter-rater variability), but that no single algorithm ranked in the top for all sub-regions simultaneously. Fusing several good algorithms using a hierarchical majority vote yielded segmentations that consistently ranked above all individual algorithms, indicating remaining opportunities for further methodological improvements. The BRATS image data and manual annotations continue to be publicly available through an online evaluation system as an ongoing benchmarking resource., National Center for Research Resources (U.S.) (P41-RR14075), National Institute of Biomedical Imaging and Bioengineering (U.S.) (R01EB013565), National Institute of Biomedical Imaging and Bioengineering (U.S.) (U54-EB005149), National Institutes of Health (U.S.) (P41-RR13218), National Institute of Biomedical Imaging and Bioengineering (U.S.) (P41-EB-015902), National Cancer Institute (U.S.) (R15CA115464)
Published: 2014

23. Sous-espaces de Mouvements Articulés ou Contraints et leurs Signatures

Author: Jacquet, Bastien, Angst, Roland, Pollefeys, Marc, Computer Vision Laboratory - ETHZ [Zurich], Eidgenössische Technische Hochschule - Swiss Federal Institute of Technology [Zürich] (ETH Zürich), and Adam, Sébastien
Subjects: intersection de sous espace, [INFO.INFO-CV] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], analyse de mouvement 3D, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], sous-espace de mouvement
Abstract: National audience; Les objets articulés ou à trajectoires contraintes représentent une grande part des objets de notre quotidien. La détection automatique de ces restrictions de mouvement entre objets et l'extraction des paramètres correspondant est donc importante, p. ex. pour augmenter une reconstruction 3D statique avec des paramètres dynamiques tels qu'axes de rotation, ou directions possibles de translation de certains objets. C'est pourquoi nous présentons ici une nouvelle théorie pour analyser le déplacement relatif de deux objets à trajectoire contrainte. L'analyse est basée sur les sous-espaces linéaires engendrés par les matrices relatives de déplacement. De plus, nous définissons une signature qui caractérise complètement la catégorie de contraintes encodée dans ces déplacements relatifs. Ce cadre théorique montre de nouvelles propriétés algébriques, comme la contrainte de bas-rang pour deux rotations consécutives autour de deux axes fixes. Enfin, pour chaque catégorie de contraintes prédite par la signature, cet article montre comment calculer tous les paramètres des contraintes par des manipulations simples d'algèbre linéaire. Notre approche est validée sur plusieurs jeux de données réelles, comme, parmi d'autre, un tableau roulant rotatif ou une roue roulant sur le sol.
Published: 2014

24. Merging Live and pre-Captured Data to support Full 3D Head Reconstruction for Telepresence

Author: Fleury, Cédric, Popa, Tiberiu, Cham, Tat Jen, Fuchs, Henry, Laboratoire de Recherche en Informatique (LRI), CentraleSupélec-Université Paris-Sud - Paris 11 (UP11)-Centre National de la Recherche Scientifique (CNRS), Situated interaction (IN-SITU), CentraleSupélec-Université Paris-Sud - Paris 11 (UP11)-Centre National de la Recherche Scientifique (CNRS)-CentraleSupélec-Université Paris-Sud - Paris 11 (UP11)-Centre National de la Recherche Scientifique (CNRS)-Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Department of Computer Science [Chapel Hill], University of North Carolina [Chapel Hill] (UNC), University of North Carolina System (UNC)-University of North Carolina System (UNC), Department of Computer Science and Software Engineering [Montreal] (CSE), Concordia University [Montreal], Computer Vision Laboratory - ETHZ [Zurich], Eidgenössische Technische Hochschule - Swiss Federal Institute of Technology [Zürich] (ETH Zürich), School of Computer Engineering [Singapore] (NTU), School of Computer Engineering, Nanyang Technological University, Université Paris-Sud - Paris 11 (UP11)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS), Université Paris-Sud - Paris 11 (UP11)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-Université Paris-Sud - Paris 11 (UP11)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-Inria Saclay - Ile de France, and Nanyang Technological University [Singapour]
Subjects: ACM: I.: Computing Methodologies/I.3: COMPUTER GRAPHICS/I.3.7: Three-Dimensional Graphics and Realism, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, ACM: H.: Information Systems/H.4: INFORMATION SYSTEMS APPLICATIONS/H.4.3: Communications Applications/H.4.3.1: Computer conferencing, teleconferencing, and videoconferencing, [INFO.INFO-HC]Computer Science [cs]/Human-Computer Interaction [cs.HC], [INFO.INFO-GR]Computer Science [cs]/Graphics [cs.GR], ComputingMethodologies_COMPUTERGRAPHICS
Abstract: International audience; This paper proposes a 3D head reconstruction method for low cost 3D telepresence systems that uses only a single consumer level hybrid sensor (color+depth) located in front of the users. Our method fuses the real-time, noisy and incomplete output of a hybrid sensor with a set of static, high-resolution textured models acquired in a calibration phase. A complete and fully textured 3D model of the users' head can thus be reconstructed in real-time, accurately preserving the facial expression of the user. The main features of our method are a mesh interpolation and a fusion of a static and a dynamic textures to combine respectively a better resolution and the dynamic features of the face.
Published: 2014

25. A Super-resolution Framework for High-Accuracy Multiview Reconstruction

Author: Daniel Cremers, Mathieu Aubry, Kalin Kolev, Bastian Goldlücke, Heidelberg Collaboratory for Image Processing (HCI), Universität Heidelberg [Heidelberg], École des Ponts ParisTech (ENPC), imagine [Marne-la-Vallée], Centre Scientifique et Technique du Bâtiment (CSTB)-École des Ponts ParisTech (ENPC)-Laboratoire d'Informatique Gaspard-Monge (LIGM), Centre National de la Recherche Scientifique (CNRS)-Fédération de Recherche Bézout-ESIEE Paris-École des Ponts ParisTech (ENPC)-Université Paris-Est Marne-la-Vallée (UPEM)-Centre National de la Recherche Scientifique (CNRS)-Fédération de Recherche Bézout-ESIEE Paris-Université Paris-Est Marne-la-Vallée (UPEM), Models of visual object recognition and scene understanding (WILLOW), Département d'informatique - ENS Paris (DI-ENS), Centre National de la Recherche Scientifique (CNRS)-Institut National de Recherche en Informatique et en Automatique (Inria)-École normale supérieure - Paris (ENS Paris), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Centre National de la Recherche Scientifique (CNRS)-Institut National de Recherche en Informatique et en Automatique (Inria)-École normale supérieure - Paris (ENS Paris), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Inria Paris-Rocquencourt, Institut National de Recherche en Informatique et en Automatique (Inria), Laboratoire d'Informatique Gaspard-Monge (LIGM), Centre National de la Recherche Scientifique (CNRS)-Fédération de Recherche Bézout-ESIEE Paris-École des Ponts ParisTech (ENPC)-Université Paris-Est Marne-la-Vallée (UPEM), Computer Vision Laboratory - ETHZ [Zurich], Eidgenössische Technische Hochschule - Swiss Federal Institute of Technology [Zürich] (ETH Zürich), Computer Vision and Pattern Recognition Group [Münster] (CVPR), Technische Universität Munchen - Université Technique de Munich [Munich, Allemagne] (TUM), Département d'informatique de l'École normale supérieure (DI-ENS), École normale supérieure - Paris (ENS Paris), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-École normale supérieure - Paris (ENS Paris), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Inria Paris-Rocquencourt, Centre National de la Recherche Scientifique (CNRS)-Inria Paris-Rocquencourt, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Département d'informatique - ENS Paris (DI-ENS), École normale supérieure - Paris (ENS-PSL), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-École normale supérieure - Paris (ENS-PSL), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL), Universität Heidelberg [Heidelberg] = Heidelberg University, Université Paris-Est Marne-la-Vallée (UPEM)-École des Ponts ParisTech (ENPC)-ESIEE Paris-Fédération de Recherche Bézout-Centre National de la Recherche Scientifique (CNRS)-Université Paris-Est Marne-la-Vallée (UPEM)-École des Ponts ParisTech (ENPC)-ESIEE Paris-Fédération de Recherche Bézout-Centre National de la Recherche Scientifique (CNRS)-Centre Scientifique et Technique du Bâtiment (CSTB), and Université Paris-Est Marne-la-Vallée (UPEM)-École des Ponts ParisTech (ENPC)-ESIEE Paris-Fédération de Recherche Bézout-Centre National de la Recherche Scientifique (CNRS)
Subjects: ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Conformal map, 02 engineering and technology, Camera calibration, Variational methods, Artificial Intelligence, Camera auto-calibration, 0202 electrical engineering, electronic engineering, information engineering, Computer vision, Mathematics, ComputingMethodologies_COMPUTERGRAPHICS, business.industry, Atlas (topology), Regular polygon, Multi-view 3D reconstruction, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], 020207 software engineering, Superresolution, Computer Science::Computer Vision and Pattern Recognition, Super-resolution, 020201 artificial intelligence & image processing, Computer Vision and Pattern Recognition, Artificial intelligence, Texture reconstruction, business, Texture mapping, Normal displacement, Software, Camera resectioning
Abstract: International audience; We present a variational framework to estimate super-resolved texture maps on a 3D geometry model of a surface from multiple images. Given the calibrated images and the reconstructed geometry, the proposed functional is convex in the super-resolution texture. Using a conformal atlas of the surface, we transform the model from the curved geometry to the flat charts and solve it using state-of-the-art and provably convergent primal-dual algorithms. In order to improve image alignment and quality of the texture, we extend the functional to also optimize for a normal displacement map on the surface as well as the camera calibration parameters. Since the sub-problems for displacement and camera parameters are non-convex, we revert to relaxation schemes in order to robustly estimate a minimizer via sequential convex programming. Experimental results confirm that the proposed super-resolution framework allows to recover textured models with significantly higher level-of-detail than the individual input images.
Published: 2014

26. Importance of patient DTI's to accurately model glioma growth using the reaction diffusion equation

Author: Ezequiel Geremia, N. Ayache, Erin Stretton, Hervé Delingette, Bjoern H. Menze, Analysis and Simulation of Biomedical Images (ASCLEPIOS), Inria Sophia Antipolis - Méditerranée (CRISAM), Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Computer Vision Laboratory - ETHZ [Zurich], Eidgenössische Technische Hochschule - Swiss Federal Institute of Technology [Zürich] (ETH Zürich), European Project: 291080,EC:FP7:ERC,ERC-2011-ADG_20110209,MEDYMA(2012), Asclepios, Project-Team, and Biophysical Modeling and Analysis of Dynamic Medical Images. - MEDYMA - - EC:FP7:ERC2012-04-01 - 2017-03-31 - 291080 - VALID
Subjects: Pathology, medicine.medical_specialty, Anisotropic diffusion, [INFO.INFO-TS] Computer Science [cs]/Signal and Image Processing, [INFO.INFO-IM] Computer Science [cs]/Medical Imaging, 02 engineering and technology, 030218 nuclear medicine & medical imaging, 03 medical and health sciences, 0302 clinical medicine, Nuclear magnetic resonance, Brain White Matter, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, Glioma, Reaction–diffusion system, 0202 electrical engineering, electronic engineering, information engineering, medicine, [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, Diffusion (business), [SPI.SIGNAL] Engineering Sciences [physics]/Signal and Image processing, Physics, Low resolution, Image segmentation, medicine.disease, [INFO.INFO-TI] Computer Science [cs]/Image Processing [eess.IV], [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], 020201 artificial intelligence & image processing, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing, Diffusion MRI
Abstract: International audience; Tumor growth models based on the FisherKolmogorov reactiondiffusion equation (FK) have shown convincing results in reproducing and predicting the invasion patterns of gliomas brain tumors. Diffusion tensor images (DTIs) were suggested to model the anisotropic diffusion of tumor cells in the brain white matter. However, clinical patient-DTIs are expensive and often acquired with low resolution, which compromises the accuracy of the tumor growth models. In this work, we used the traveling wave approximation model to describe the evolution of the visible boundary of the tumor modeled by the FK equation to investigate the impact of replacing the patient DTI by (i) an isotropic diffusion map or (ii) an anisotropic high-resolution DTI atlas formed by averaging DTIs of multiple patients. We quantify the impact of replacing the patient DTI using three metrics: the shape of the simulated glioma, the estimation of the tumor growth parameters, and the prediction performance on clinical cases.
Published: 2013
Full Text: View/download PDF

27. Patch-based Segmentation of Brain Tissues

Author: Cordier, Nicolas, Menze, Bjoern, Delingette, Hervé, Ayache, Nicholas, Cordier, Nicolas, Biophysical Modeling and Analysis of Dynamic Medical Images. - MEDYMA - - EC:FP7:ERC2012-04-01 - 2017-03-31 - 291080 - VALID, Bjoern Menze and Mauricio Reyes and Andras Jakab and Elisabeth Gerstner and Justin Kirby and Keyvan Farahani, Analysis and Simulation of Biomedical Images (ASCLEPIOS), Inria Sophia Antipolis - Méditerranée (CRISAM), Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Computer Vision Laboratory - ETHZ [Zurich], Eidgenössische Technische Hochschule - Swiss Federal Institute of Technology [Zürich] (ETH Zürich), and European Project: 291080,EC:FP7:ERC,ERC-2011-ADG_20110209,MEDYMA(2012)
Subjects: [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, [INFO.INFO-IM] Computer Science [cs]/Medical Imaging
Abstract: International audience; We describe our submission to the Brain Tumor Segmentation Challenge (BraTS) at MICCAI 2013. This segmentation approach is based on similarities between multi-channel patches. After patches are extracted from several MR channels for a test case, similar patches are found in training images for which label maps are known. These labels maps are then combined to result in a segmentation map for the test case. The labelling is performed, in a leave-one-out scheme, for each case of a publicly available training set, which consists of 30 real cases (20 high-grade gliomas, 10 low-grade gliomas) and 50 synthetic cases (25 high-grade gliomas, 25 low-grade gliomas). Promising results are shown on the training set, and we believe this algorithm would perform favourably well in comparison to the state of the art on a testing set.
Published: 2013

28. Spatially Adaptive Random Forest

Author: Nicholas Ayache, Ezequiel Geremia, Bjoern H. Menze, Analysis and Simulation of Biomedical Images (ASCLEPIOS), Inria Sophia Antipolis - Méditerranée (CRISAM), Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Computer Vision Laboratory - ETHZ [Zurich], Eidgenössische Technische Hochschule - Swiss Federal Institute of Technology [Zürich] (ETH Zürich), and European Project: 291080,EC:FP7:ERC,ERC-2011-ADG_20110209,MEDYMA(2012)
Subjects: Computer science, Feature vector, Feature extraction, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Scale-space segmentation, 02 engineering and technology, Machine learning, computer.software_genre, 030218 nuclear medicine & medical imaging, 03 medical and health sciences, 0302 clinical medicine, Discriminative model, Image texture, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, 0202 electrical engineering, electronic engineering, information engineering, [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, Segmentation, Feature detection (computer vision), Training set, Contextual image classification, Segmentation-based object categorization, business.industry, Pattern recognition, Image segmentation, Random forest, Feature (computer vision), [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], 020201 artificial intelligence & image processing, Artificial intelligence, business, computer, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing, Curse of dimensionality
Abstract: International audience; Medical imaging protocols produce large amounts of multi- modal volumetric images. The large size of the datasets contributes to the success of supervised discriminative methods for semantic image segmentation. Classifying relevant structures in medical images is challenging due to (a) the large size of data volumes, and (b) the severe class overlap in the feature space. Subsampling the training data addresses the first issue at the cost of discarding potentially useful image information. Increasing feature dimensionality addresses the second but requires dense sampling. We propose a general and efficient solution to these problems. "Spatially Adaptive Random Forests" (SARF) is a supervised learning algorithm. SARF aims at automatic semantic labelling of large medical volumes. During training, it learns the optimal image sampling associated to the classification task. During testing, the algorithm quickly handles the background and focuses challenging image regions to refine the classification. SARF demonstrated top performance in the context of multi-class gliomas segmentation in multi-modal MR images.
Published: 2013

29. Motion Control of the CyberCarpet Platform

Author: L. Van Gool, Paolo Robuffo Giordano, M. Schwaiger, M. Van den Bergh, Esther Koller-Meier, A. De Luca, H. Ulbrich, R. Mattone, Università degli Studi di Roma 'La Sapienza' = Sapienza University [Rome] (UNIROMA), Visual servoing in robotics, computer vision, and augmented reality (Lagadic), Inria Sophia Antipolis - Méditerranée (CRISAM), Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Inria Rennes – Bretagne Atlantique, Institut National de Recherche en Informatique et en Automatique (Inria)-SIGNAUX ET IMAGES NUMÉRIQUES, ROBOTIQUE (IRISA-D5), Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-Télécom Bretagne-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-Télécom Bretagne-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Télécom Bretagne-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS), Max Planck Institute for Biological Cybernetics, Max-Planck-Gesellschaft, Technische Universität Munchen - Université Technique de Munich [Munich, Allemagne] (TUM), Computer Vision Laboratory - ETHZ [Zurich], Eidgenössische Technische Hochschule - Swiss Federal Institute of Technology [Zürich] (ETH Zürich), Università degli Studi di Roma 'La Sapienza' = Sapienza University [Rome], CentraleSupélec-Télécom Bretagne-Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-Université de Rennes (UNIV-RENNES)-Institut National de Recherche en Informatique et en Automatique (Inria)-École normale supérieure - Rennes (ENS Rennes)-Université de Bretagne Sud (UBS)-Centre National de la Recherche Scientifique (CNRS)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-CentraleSupélec-Télécom Bretagne-Université de Rennes 1 (UR1), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Université de Rennes (UNIV-RENNES)-Université de Rennes (UNIV-RENNES)-École normale supérieure - Rennes (ENS Rennes)-Université de Bretagne Sud (UBS)-Centre National de la Recherche Scientifique (CNRS)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), and Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)
Subjects: input-output feedback linearization, 0209 industrial biotechnology, Engineering, motion control, disturbance observer, 02 engineering and technology, Kinematics, Motion (physics), 020901 industrial engineering & automation, Circular motion, Position (vector), Control theory, 0202 electrical engineering, electronic engineering, information engineering, [INFO.INFO-RB]Computer Science [cs]/Robotics [cs.RO], Electrical and Electronic Engineering, virtual reality (vr), Simulation, Nonholonomic system, business.industry, Feed forward, visual tracking, Motion control, locomotion platform, nonholonomic systems, Control and Systems Engineering, Video tracking, 020201 artificial intelligence & image processing, business
Abstract: International audience; The CyberCarpet is an actuated platform that allows unconstrained locomotion of a walking user for Virtual Reality exploration. The platform consists of a linear treadmill covered by a ball-array carpet and mounted on a turntable, and is equipped with two actuating devices for linear and angular motion. The main control objective is to keep the walker close to the platform center in the most natural way, counteracting his/her voluntary motion while satisfying perceptual constraints. The motion control problem for this platform is not trivial since the system kinematics is subject to a nonholonomic constraint. In the first part of the paper we describe the kinematic control design devised within the CyberWalk project, where the linear and angular platform velocities are used as input commands and feedback is based only on walker's position measurements obtained by an external visual tracking system. In particular, we present a globally stabilizing control scheme that combines a feedback and a feedforward action, based on a disturbance observer of the walker's intentional velocity. We also discuss possible extensions to acceleration-level control and the related assessment of dynamic issues affecting a walker during his/her motion. The second part of the paper is devoted to the actual implementation of the overall system. As a proof of concept of a final full-scale platform, the mechanical design and realization of a small-scale prototype of the CyberCarpet is presented, as well as the visual localization method used to obtain the human walker's position on the platform by an overhead camera. To validate the proposed motion control design, experimental results are reported and discussed for a series of motion tasks performed using a small tracked vehicle representative of a moving user.
Published: 2013

30. Classification Forests for Semantic Segmentation of Brain Lesions in Multi-channel MRI

Author: Darko Zikic, Bjoern H. Menze, Antonio Criminisi, Owen M. Thomas, Tilak Das, Nicholas Ayache, Ezequiel Geremia, Ender Konukoglu, Stephen J. Price, Olivier Clatz, Jamie Shotton, Ben Glocker, Raj Jena, Analysis and Simulation of Biomedical Images (ASCLEPIOS), Inria Sophia Antipolis - Méditerranée (CRISAM), Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Microsoft Research [Cambridge] (Microsoft), Microsoft Research, Computer Vision Laboratory - ETHZ [Zurich], Eidgenössische Technische Hochschule - Swiss Federal Institute of Technology [Zürich] (ETH Zürich), Cambridge University Hospitals - NHS (CUH), University of Cambridge [UK] (CAM), Criminisi, Antonio and Shotton, and J.
Subjects: Generalization, business.industry, Segmentation-based object categorization, Computer science, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Scale-space segmentation, 02 engineering and technology, Machine learning, computer.software_genre, Mixture model, 030218 nuclear medicine & medical imaging, 03 medical and health sciences, 0302 clinical medicine, Feature (computer vision), 0202 electrical engineering, electronic engineering, information engineering, [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, 020201 artificial intelligence & image processing, Segmentation, Artificial intelligence, business, computer, Block (data storage), Diffusion MRI
Abstract: International audience; Classification forests, as discussed in Chapter 2, have a series of advantageous properties which make them a very good choice for applications in medical image analysis. Classification forests are inherent multi-label classifiers (which allows for the simultaneous segmentation of different tissues), have good generalization properties (which is important as training data is often scarce in medical applications), and are able to deal with very high-dimensional feature spaces (which allows the use of non-local and context-aware features to describe the input data). In this chapter we demonstrate how classification forests can be used as a basic building block to develop state of the art systems for medical image analysis in two challenging applications. These applications perform the segmentation of two different types of brain lesions based on 3D multi-channel magnetic resonance images (MRI) as input. More specifically, we discuss (1) the segmentation of the individual tissues of high-grade brain tumor lesions, and (2) the segmentation of multiple-sclerosis lesions.
Published: 2013

31. Oblique Random Forests for 3-D Vessel Detection Using Steerable Filters and Orthogonal Subspace Filtering

Author: Bruno Weber, Bjoern H. Menze, Gábor Székely, Matthias Schneider, Sven Hirsch, Computer Vision Laboratory - ETHZ [Zurich], Eidgenössische Technische Hochschule - Swiss Federal Institute of Technology [Zürich] (ETH Zürich), Institute of Pharmacology and Toxicology [Zurich], Universität Zürich [Zürich] = University of Zurich (UZH), Analysis and Simulation of Biomedical Images (ASCLEPIOS), Inria Sophia Antipolis - Méditerranée (CRISAM), and Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)
Subjects: Hessian matrix, business.industry, Orientation (computer vision), ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Decision tree, [SCCO.COMP]Cognitive science/Computer science, Oblique case, Pattern recognition, 02 engineering and technology, Random forest, 03 medical and health sciences, symbols.namesake, 0302 clinical medicine, Feature (computer vision), 0202 electrical engineering, electronic engineering, information engineering, symbols, 020201 artificial intelligence & image processing, Segmentation, Artificial intelligence, business, Image resolution, 030217 neurology & neurosurgery, Mathematics
Abstract: International audience; We propose a machine learning-based framework using oblique random forests for 3-D vessel segmentation. Two different kinds of features are compared. One is based on orthogonal subspace filtering where we learn 3-D eigenspace filters from local image patches that return task optimal feature responses. The other uses a specific set of steerable filters that show, qualitatively,similarities to the learned eigenspace filters, but also allow for explicit parametrization of scale and orientation that we formally generalize to the 3-D spatial context. In this way, steerable filters allow to efficiently compute oriented features along arbitrary directions in 3-D. The segmentation performance is evaluated on four 3-D imaging datasets of the murine visual cortex at a spatial resolution of 0.7μm. Our experiments show that the learning-based approach is able to significantly improve the segmentation compared to conventional Hessian-based methods. Features computed based on steerable filters prove to be superior to eigenfilter-based features for the considered datasets. We further demonstrate that random forests using oblique split directions outperform decision tree ensembles with univariate orthogonal splits
Published: 2013

32. SAR-based Terrain Classification using Weakly Supervised Hierarchical Markov Aspect Models

Author: Bill Triggs, Gui-Song Xia, Dengxin Dai, Wen Yang, Signal Processing Lab (DSP), Wuhan University [China], Computer Vision Laboratory - ETHZ [Zurich], Eidgenössische Technische Hochschule - Swiss Federal Institute of Technology [Zürich] (ETH Zürich), Statistique Apprentissage Machine (SAM), Laboratoire Jean Kuntzmann (LJK), Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS)-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS), CEntre de REcherches en MAthématiques de la DEcision (CEREMADE), Centre National de la Recherche Scientifique (CNRS)-Université Paris Dauphine-PSL, and Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)
Subjects: Computer science, 0211 other engineering and technologies, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Markov process, Context (language use), 02 engineering and technology, symbols.namesake, [MATH.MATH-ST]Mathematics [math]/Statistics [math.ST], 0202 electrical engineering, electronic engineering, information engineering, Quadtree, Graphical model, 021101 geological & geomatics engineering, Ground truth, Training set, Markov chain, Probabilistic latent semantic analysis, business.industry, Pattern recognition, [STAT.TH]Statistics [stat]/Statistics Theory [stat.TH], Computer Graphics and Computer-Aided Design, Visualization, symbols, 020201 artificial intelligence & image processing, Artificial intelligence, business, Software, Smoothing
Abstract: International audience; We introduce the hierarchical Markov aspect model (HMAM), a computationally efficient graphical model for densely labeling large remote sensing images with their underlying terrain classes. HMAM resolves local ambiguities efficiently by combining the benefits of quadtree representations and aspect models--the former incorporate multiscale visual features and hierarchical smoothing to provide improved local label consistency, while the latter sharpen the labelings by focusing them on the classes that are most relevant for the broader local image context. The full HMAM model takes a grid of local hierarchical Markov quadtrees over image patches and augments it by incorporating a probabilistic latent semantic analysis aspect model over a larger local image tile at each level of the quadtree forest. Bag-of-word visual features are extracted for each level and patch, and given these, the parent-child transition probabilities from the quadtree and the label probabilities from the tile-level aspect models, an efficient forwards-backwards inference pass allows local posteriors for the class labels to be obtained for each patch. Variational expectation-maximization is then used to train the complete model from either pixel-level or tile-keyword-level labelings. Experiments on a complete TerraSAR-X synthetic aperture radar terrain map with pixel-level ground truth show that HMAM is both accurate and efficient, providing significantly better results than comparable single-scale aspect models with only a modest increase in training and test complexity. Keyword-level training greatly reduces the cost of providing training data with little loss of accuracy relative to pixel-level training.
Published: 2012

33. Brain tumor cell density estimation from multi-modal MR images based on a synthetic tumor growth model

Author: Marc-André Weber, Antonio Criminisi, Marcel Prastawa, Ezequiel Geremia, Bjoern H. Menze, Nicholas Ayache, Analysis and Simulation of Biomedical Images (ASCLEPIOS), Inria Sophia Antipolis - Méditerranée (CRISAM), Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Computer Vision Laboratory - ETHZ [Zurich], Eidgenössische Technische Hochschule - Swiss Federal Institute of Technology [Zürich] (ETH Zürich), Computer Science and Artificial Intelligence Laboratory [Cambridge] (CSAIL), Massachusetts Institute of Technology (MIT), Scientific Computing and Imaging Institute (SCI Institute), University of Utah, Diagnostic and Interventional Radiology [Heidelberg], Heidelberg University Hospital [Heidelberg], Division of Medical Physics in Radiology [Heidelberg], German Cancer Research Center - Deutsches Krebsforschungszentrum [Heidelberg] (DKFZ), Microsoft Research [Cambridge] (Microsoft), Microsoft Research, and European Project: 291080,EC:FP7:ERC,ERC-2011-ADG_20110209,MEDYMA(2012)
Subjects: Computer science, education, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Brain tumor, Latent variable, computer.software_genre, Machine learning, 030218 nuclear medicine & medical imaging, 03 medical and health sciences, 0302 clinical medicine, Discriminative model, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, Voxel, medicine, [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, Tumor growth, Ground truth, business.industry, Pattern recognition, medicine.disease, [INFO.INFO-MO]Computer Science [cs]/Modeling and Simulation, Random forest, ComputingMethodologies_PATTERNRECOGNITION, Modal, [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], Artificial intelligence, business, computer, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing, 030217 neurology & neurosurgery
Abstract: International audience; This paper proposes to employ a detailed tumor growth model to synthesize labelled images which can then be used to train an e cient data-driven machine learning tumor predictor. Our MR im- age synthesis step generates images with both healthy tissues as well as various tumoral tissue types. Subsequently, a discriminative algorithm based on random regression forests is trained on the simulated ground truth to predict the continuous latent tumor cell density, and the discrete tissue class associated with each voxel. The presented method makes use of a large synthetic dataset of 740 simulated cases for training and evalu- ation. A quantitative evaluation on 14 real clinical cases diagnosed with low-grade gliomas demonstrates tissue class accuracy comparable with state of the art, with added bene t in terms of computational e ciency and the ability to estimate tumor cell density as a latent variable un- derlying the multimodal image observations. The idea of synthesizing training data to train data-driven learning algorithms can be extended to other applications where expert annotation is lacking or expensive.
Published: 2012

34. Spatial Decision Forests for Glioma Segmentation in Multi-Channel MR Images

Author: Geremia, Ezequiel, Menze, Bjoern H., Ayache, Nicholas, Analysis and Simulation of Biomedical Images (ASCLEPIOS), Inria Sophia Antipolis - Méditerranée (CRISAM), Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Computer Vision Laboratory - ETHZ [Zurich], Eidgenössische Technische Hochschule - Swiss Federal Institute of Technology [Zürich] (ETH Zürich), European Project: 291080,EC:FP7:ERC,ERC-2011-ADG_20110209,MEDYMA(2012), Asclepios, Project-Team, and Biophysical Modeling and Analysis of Dynamic Medical Images. - MEDYMA - - EC:FP7:ERC2012-04-01 - 2017-03-31 - 291080 - VALID
Subjects: [INFO.INFO-TI] Computer Science [cs]/Image Processing [eess.IV], [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, [INFO.INFO-TS] Computer Science [cs]/Signal and Image Processing, [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], [INFO.INFO-IM] Computer Science [cs]/Medical Imaging, [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, [INFO.INFO-MO] Computer Science [cs]/Modeling and Simulation, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing, [INFO.INFO-MO]Computer Science [cs]/Modeling and Simulation, [SPI.SIGNAL] Engineering Sciences [physics]/Signal and Image processing
Abstract: International audience; A fully automatic algorithm is presented for the automatic segmentation of gliomas in 3D MR images. It builds on the discriminative random decision forest framework to provide a voxel-wise probabilistic classi cation of the volume. Our method uses multi-channel MR intensi- ties (T1, T1C, T2, Flair), spatial prior and long-range comparisons with 3D regions to discriminate lesions. A symmetry feature is introduced ac- counting for the fact that gliomas tend to develop in an asymmetric way. Quantitative evaluation of the data is carried out on publicly available labeled cases from the BRATS Segmentation Challenge 2012 dataset and demonstrates improved results over the state of the art.
Published: 2012

35. Statistical Model Based Shape Prediction from a Combination of Direct Observations and Various Surrogates

Author: Blanc, R., Seiler, Christof, Székely, G., Nolte, L., Reyes, Mauricio, Computer Vision Laboratory - ETHZ [Zurich], Eidgenössische Technische Hochschule - Swiss Federal Institute of Technology [Zürich] (ETH Zürich), Institute for Surgical Technology and Biomechanics [Bern] (ISTB), University of Bern, and Asclepios, Project-Team
Subjects: [INFO.INFO-TI] Computer Science [cs]/Image Processing [eess.IV], [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, [INFO.INFO-TS] Computer Science [cs]/Signal and Image Processing, [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], [INFO.INFO-IM] Computer Science [cs]/Medical Imaging, [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, [INFO.INFO-MO] Computer Science [cs]/Modeling and Simulation, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing, [INFO.INFO-MO]Computer Science [cs]/Modeling and Simulation, [SPI.SIGNAL] Engineering Sciences [physics]/Signal and Image processing
Abstract: International audience; In computer-assisted orthopaedic surgery, recovering three-dimensional patient-specific anatomy from incomplete information has been focus of interest due to several factors such as less invasive surgical procedures, reduced radiation doses, and rapid intra-operative updates of the anatomy. The aim of this paper is to report results obtained combining statistical shape modeling and multivariate regression techniques for predicting bone shape from clinically and surgically relevant predictors, including sparse observations of the bone surface but also morphometric and anthropometric information. Different state of the art methods such as partial least square regression, principal component regression, canonical correlation analysis, and non-parametric kernel-based regression are compared. Clinically relevant surrogate variables and combinations are investigated on a database of 142 femur and 154 tibia shapes obtained from CT images. The results are evaluated using cross validation to quantify the prediction error. The proposed approach enables to characterize the added value of different predictors in a quantitative and localized fashion. Results indicate that complementary sources of information can be efficiently exploited to improve the accuracy of shape prediction.
Published: 2012

36. Glioblastoma growth modeling for radiotherapy target delineation

Author: Unkelbach, J., Menze, Bjoern H., Motamedi, A., Dittmann, F., Konukoglu, Ender, Ayache, Nicholas, Shih, H., Massachusetts General Hospital [Boston], Analysis and Simulation of Biomedical Images (ASCLEPIOS), Inria Sophia Antipolis - Méditerranée (CRISAM), Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Computer Vision Laboratory - ETHZ [Zurich], Eidgenössische Technische Hochschule - Swiss Federal Institute of Technology [Zürich] (ETH Zürich), Machine learning and perception group [Cambridge], Microsoft Research Laboratory Cambridge, INRIA, and Wolfgang Birkfellner and Jamie R. Mcclelland and Simon Rit and Alexander Schlaefer
Subjects: [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing, [INFO.INFO-MO]Computer Science [cs]/Modeling and Simulation
Abstract: International audience; Radiotherapy treatment planning requires a localization of the tumor within the patient. This is challenging to accomplish for micro- scopic in ltrative spread of disease that is not visible on current imaging modalities. Prime examples for in ltrative tumors are gliomas. With the help of mathematical models, common growth characteristics of gliomas, which are known from histopathological studies, can be incorporated in radiotherapy target delineation. This requires an imaging based personal- ization of the model to the individual patient. We demonstrate use cases of the Fisher-Kolmogorov glioma growth model in radiotherapy planning of a clinical case. We further analyze the crucial input parameters to the model, in particular, the need for reliable segmentation of anatomical boundaries such as the falx cerebri and the tentorium cerebelli.
Published: 2012

37. Conditional Variability of Statistical Shape Models Based on Surrogate Variables

Author: Christof Seiler, Gábor Székely, Rémi Blanc, Mauricio Reyes, Computer Vision Laboratory - ETHZ [Zurich], Eidgenössische Technische Hochschule - Swiss Federal Institute of Technology [Zürich] (ETH Zürich), Institute for Surgical Technology and Biomechanics [Bern] (ISTB), University of Bern, Analysis and Simulation of Biomedical Images (ASCLEPIOS), Inria Sophia Antipolis - Méditerranée (CRISAM), Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), and Asclepios, Project-Team
Subjects: Models, Anatomic, Physics::Medical Physics, Tomography, X-Ray Computed/methods, [INFO.INFO-IM] Computer Science [cs]/Medical Imaging, Initialization, Femur/diagnostic imaging, 030218 nuclear medicine & medical imaging, Imaging, [INFO.INFO-CV] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], 0302 clinical medicine, Heat kernel signature, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, Models, Active shape model, Three-Dimensional/methods, Computer-Assisted/methods, Radiographic Image Enhancement/methods, Tomography, Mathematics, Anatomic, Radiographic Image Interpretation, Human femur, Statistical, X-Ray Computed/methods, Imaging, Three-Dimensional/methods, [INFO.INFO-TI] Computer Science [cs]/Image Processing [eess.IV], [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], [INFO.INFO-MO] Computer Science [cs]/Modeling and Simulation, Algorithm, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing, Algorithms, Shape analysis (digital geometry), Mathematical optimization, [INFO.INFO-TS] Computer Science [cs]/Signal and Image Processing, Quantitative Biology::Tissues and Organs, Kernel density estimation, Automated/methods, Pattern Recognition, Effect Modifier, Epidemiologic, Models, Biological, Sensitivity and Specificity, 03 medical and health sciences, Radiographic Image Interpretation, Computer-Assisted/methods, [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, Humans, [SPI.SIGNAL] Engineering Sciences [physics]/Signal and Image processing, Models, Statistical, Epidemiologic, Pattern Recognition, Automated/methods, Reproducibility of Results, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], Conditional probability distribution, Biological, [INFO.INFO-MO]Computer Science [cs]/Modeling and Simulation, Effect Modifier, Point distribution model, 030217 neurology & neurosurgery
Abstract: International audience; We propose to increment a statistical shape model with surrogate variables such as anatomical measurements and patient-related information, allowing conditioning the shape distribution to follow prescribed anatomical constraints. The method is applied to a shape model of the human femur, modeling the joint density of shape and anatomical parameters as a kernel density. Results show that it allows for a fast, intuitive and anatomically meaningful control on the shape deformations and an effective conditioning of the shape distribution, allowing the analysis of the remaining shape variability and relations between shape and anatomy. The approach can be further employed for initializing elastic registration methods such as Active Shape Models, improving their regularization term and reducing the search space for the optimization.
Published: 2009

38. Les fourmis pour la segmentation d'images médicales par résonance magnétique

Author: Nakib , A., Blanc , R., Oulhadj , H., Siarry , P., SIMO, Laboratoire Images, Signaux et Systèmes Intelligents (LISSI), Université Paris-Est Créteil Val-de-Marne - Paris 12 (UPEC UP12)-Université Paris-Est Créteil Val-de-Marne - Paris 12 (UPEC UP12), Computer Vision Laboratory - ETHZ [Zurich], Eidgenössische Technische Hochschule - Swiss Federal Institute of Technology [Zürich] (ETH Zürich), N. Monmarché, F. Guinand and P. Siarry, Amirat, Yacine, Laboratoire Images, Signaux et Systèmes Intelligents ( LISSI ), Université Paris-Est Créteil Val-de-Marne - Paris 12 ( UPEC UP12 ) -Université Paris-Est Créteil Val-de-Marne - Paris 12 ( UPEC UP12 ), and Eidgenössische Technische Hochschule [Zürich] ( ETH Zürich )
Subjects: [ MATH.MATH-OC ] Mathematics [math]/Optimization and Control [math.OC], [MATH.MATH-OC] Mathematics [math]/Optimization and Control [math.OC], [MATH.MATH-OC]Mathematics [math]/Optimization and Control [math.OC], ComputingMilieux_MISCELLANEOUS
Abstract: International audience; no abstract
Published: 2009

Catalog

Books, media, physical & digital resources

See catalog results

Searchworks

Select search scope, currently: Articles Catalog books, media & more in Jio Institute collections Articles journal articles & other e-resources

Search

Search Constraints

Refine your results

Search Limiters

Topic

Publication Year Range

Language

Journal

Database

Publisher

38 results on '"Computer Vision Laboratory - ETHZ [Zurich]"'

Search Results

Catalog

Select search scope, currently: Articles

Catalog

books, media & more in Jio Institute collections

Articles

journal articles & other e-resources