Search

Your search keyword '"Laure Tougne"' showing total 48 results
Start Over Author "Laure Tougne" Topic 020201 artificial intelligence & image processing
48 results on '"Laure Tougne"'

1. CTIS-Net: A Neural Network Architecture for Compressed Learning Based on Computed Tomography Imaging Spectrometers

Author

Carlos Crispim-Junior, Gérald Germain, Clément Douarre, David Rousseau, Laure Tougne, Anthony Gelibert, Laboratoire d'InfoRmatique en Image et Systèmes d'information (LIRIS), Institut National des Sciences Appliquées de Lyon (INSA Lyon), Institut National des Sciences Appliquées (INSA)-Université de Lyon-Institut National des Sciences Appliquées (INSA)-Université de Lyon-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), Laboratoire Angevin de Recherche en Ingénierie des Systèmes (LARIS), Université d'Angers (UA), and 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)

Subjects
Computer science, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Imaging spectrometer, 02 engineering and technology, Iterative reconstruction, 01 natural sciences, Convolutional neural network, Image (mathematics), [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], 010309 optics, 0103 physical sciences, 0202 electrical engineering, electronic engineering, information engineering, Computer vision, ComputingMilieux_MISCELLANEOUS, [PHYS.PHYS.PHYS-OPTICS]Physics [physics]/Physics [physics]/Optics [physics.optics], Spectrometer, business.industry, Hyperspectral imaging, Computer Science Applications, Computational Mathematics, Signal Processing, Snapshot (computer storage), 020201 artificial intelligence & image processing, Artificial intelligence, Cube, business
Abstract

The Computed Tomography Imaging Spectrometer (CTIS) permits a snapshot acquisition of a hyperspectral cube, through the creation of an image of indirect measurements which is then traditionally used for reconstruction of the cube. This reconstruction step is time-consuming and only yields an approximation of the original cube. Following a compressed learning framework, we compare the performance of a classification task carried out on reconstructed cubes on one hand, directly on the raw images on the other. Regarding the latter case, we propose in particular the use of a new Convolutional Neural Network (CNN) architecture called CTIS-Net, whose architecture is tailored to benefit from the specific structure of CTIS images. Results show a sizable increase compared to classification with a standard architecture and compared to a conventional classification on the reconstructed cubes.

Published
2021

2. Registering Unmanned Aerial Vehicle Videos in the Long Term

Author

Carlos Crispim-Junior, Laure Tougne, Lionel Robinault, Pierre Lemaire, Extraction de Caractéristiques et Identification (imagine), Laboratoire d'InfoRmatique en Image et Systèmes d'information (LIRIS), 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), Université de Lyon-Université Lumière - Lyon 2 (UL2), and Foxstream

Subjects
0209 industrial biotechnology, Computer science, 02 engineering and technology, drone, lcsh:Chemical technology, Biochemistry, Article, Analytical Chemistry, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], 020901 industrial engineering & automation, Data acquisition, registration, 0202 electrical engineering, electronic engineering, information engineering, unmanned aerial vehicle, lcsh:TP1-1185, Computer vision, Electrical and Electronic Engineering, Instrumentation, ComputingMilieux_MISCELLANEOUS, Jitter, Background subtraction, business.industry, Perspective (graphical), [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], Video processing, Atomic and Molecular Physics, and Optics, Term (time), stabilization, [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], 020201 artificial intelligence & image processing, Artificial intelligence, business
Abstract

International audience; Unmanned aerial vehicles (UAVs) have become a very popular way of acquiring video within contexts such as remote data acquisition or surveillance. Unfortunately, their viewpoint is often unstable, which tends to impact the automatic processing of their video flux negatively. To counteract the effects of an inconsistent viewpoint, two video processing strategies are classically adopted, namely registration and stabilization, which tend to be affected by distinct issues, namely jitter and drifting. Following our prior work, we suggest that the motion estimators used in both situations can be modeled to take into account their inherent errors. By acknowledging that drifting and jittery errors are of a different nature, we propose a combination that is able to limit their influence and build a hybrid solution for jitter-free video registration. In this work, however, our modeling was restricted to 2D-rigid transforms, which are rather limited in the case of airborne videos. In the present paper, we extend and refine the theoretical ground of our previous work. This addition allows us to show how to practically adapt our previous work to perspective transforms, which our study shows to be much more accurate for this problem. A lightweight implementation enables us to automatically register stationary UAV videos in real time. Our evaluation includes traffic surveillance recordings of up to 2 h and shows the potential of the proposed approach when paired with background subtraction tasks.

Published
2021

3. Spatio-Temporal Convolutional Autoencoders for Perimeter Intrusion Detection

Author

Quentin Barthélemy, Lionel Robinault, Laure Tougne, Sarah Bertrand, Carlos Crispim-Junior, Devashish Lohani, Extraction de Caractéristiques et Identification (imagine), Laboratoire d'InfoRmatique en Image et Systèmes d'information (LIRIS), 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), Université de Lyon-Université Lumière - Lyon 2 (UL2), and Foxstream

Subjects
Scheme (programming language), Source code, Computer science, media_common.quotation_subject, Context (language use), 02 engineering and technology, Intrusion detection system, 010501 environmental sciences, Unsupervised learning, 01 natural sciences, Spatio-temporal data, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], Task (project management), [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], 0202 electrical engineering, electronic engineering, information engineering, Perimeter intrusion detection, [INFO]Computer Science [cs], 0105 earth and related environmental sciences, computer.programming_language, media_common, 3D convolutions, business.industry, Supervised learning, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], Pattern recognition, Autoencoder, Convolutional autoencoder, 020201 artificial intelligence & image processing, Artificial intelligence, business, computer
Abstract

In the video surveillance context, a perimeter intrusion detection system (PIDS) aims to detect the presence of an intrusion in a secured perimeter. Existing camera based approaches relies on hand crafted rules, image based classification and supervised learning. In a real world intrusion detection system, we need to learn spatio-temporal features unsupervisely (as annotated data are very difficult to obtain) and use these features to detect intrusions. To tackle this problem, we propose to use a 3D convolutional autoencoder. It is inspired from the DeepFall paper where they use it for an unsupervised fall detection task. In this paper, we reproduce their results on the fall detection task and further extend this model to detect intrusions in a perimeter intrusion dataset. We also provide an extended evaluation scheme which helps to draw essential insights from the results. Our results (The source code is available at https://gitlab.liris.cnrs.fr/dlohani/stcae_pids.) show that we correctly reproduce the results of fall detection task and furthermore our model shows competitive performance in perimeter intrusion detection task. To our knowledge, it is the first time when a PIDS is made in a fully unsupervised manner while jointly learning the spatio-temporal features from a video-stream.

Published
2021

4. Semantic Segmentation Post-processing with Colorized Pairwise Potentials and Deep Edges

Author

Laure Tougne, Elodie Faure, Rémi Ratajczak, Carlos Crispim, Béatrice Fervers, Extraction de Caractéristiques et Identification (imagine), Laboratoire d'InfoRmatique en Image et Systèmes d'information (LIRIS), 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), Université de Lyon-Université Lumière - Lyon 2 (UL2), Département cancer environnement (Centre Léon Bérard - Lyon), Centre Léon Bérard [Lyon], Agence de l'Environnement et de la Maîtrise de l'Energie (ADEME), LABEX IMU (ANR-10-LABX-0088/ ANR-11-IDEX-0007)., ADEME (N TEZ17-42), Centre Léon Bérard, IEEE, TESTIS, and IMU GOURAMIC

Subjects
Conditional random field, Computer science, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, 0211 other engineering and technologies, 02 engineering and technology, Grayscale, Deep Edges, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], Segmentation, Deep Learning, Land Use, 0202 electrical engineering, electronic engineering, information engineering, 021101 geological & geomatics engineering, Pixel, business.industry, Deep learning, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], Pattern recognition, Object (computer science), [SDE.ES]Environmental Sciences/Environmental and Society, Panchromatic film, [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], 020201 artificial intelligence & image processing, Pairwise comparison, Artificial intelligence, business
Abstract

International audience; Semantic segmentation is the task of assigning a label to each pixel in an image, providing high level insights to a wide range of end-user applications like autonomous driving, medical imaging and land use mapping. However, semantic segmentation results are not always consistent with the object boundaries and may sometimes lack of spatial consistency. To solve these problems, post-processing algorithms have been proposed, paving the way for more robust pipelines. In this work, we study a novel post-processing approach to enhance semantic segmentation of panchromatic aerial images based on unsupervised colorization and deep edge superpixels. In particular, we propose to assess whether applying a colorization algorithm could enhance the strength of the pairwise potentials used in an extended dense conditional random field. We present experiments on recent aerial color images that we convert to grayscale before colorization, allowing us to assess how colorized representations impact post-processing when compared to real color and panchromatic representations.

Published
2020

5. Patch-based CNN evaluation for bark classification

Author

Debaleena Misra, Laure Tougne, Carlos Crispim-Junior, 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-Centre National de la Recherche Scientifique (CNRS)-Institut National des Sciences Appliquées de Lyon (INSA Lyon), Institut National des Sciences Appliquées (INSA)-Université de Lyon-Institut National des Sciences Appliquées (INSA), Extraction de Caractéristiques et Identification (imagine), 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), Université de Lyon-Université Lumière - Lyon 2 (UL2), ANR-15-CE38-0004,ReVeRIES,Reconnaissance de Végétaux Récréative, Interactive et Educative sur Smartphone(2015), Misra, Debaleena, and Reconnaissance de Végétaux Récréative, Interactive et Educative sur Smartphone - - ReVeRIES2015 - ANR-15-CE38-0004 - AAPG2015 - VALID

Subjects
0106 biological sciences, Majority rule, Computer science, media_common.quotation_subject, 02 engineering and technology, [INFO] Computer Science [cs], transfer learning, 010603 evolutionary biology, 01 natural sciences, Convolutional neural network, Voting, convolutional neural networks, 0202 electrical engineering, electronic engineering, information engineering, bicubic interpolation, super-resolution networks, [INFO]Computer Science [cs], media_common, Bark classification, majority voting, business.industry, Deep learning, Process (computing), patch-based CNNs, image re-scaling, Pattern recognition, Identification (information), Bicubic interpolation, 020201 artificial intelligence & image processing, Artificial intelligence, business, Transfer of learning
Abstract

International audience; The identification of tree species from bark images is a challenging computer vision problem. However, even in the era of deep learning today, bark recognition continues to be explored by traditional methods using time-consuming handcrafted features, mainly due to the problem of limited data. In this work, we implement a patch-based convolutional neural network alternative for analyzing a challenging bark dataset Bark-101, comprising of 2587 images from 101 classes. We propose to apply image re-scaling during the patch extraction process to compensate for the lack of sufficient data. Individual patch-level predictions from fine-tuned CNNs are then combined by classical majority voting to obtain image-level decisions. Since ties can often occur in the voting process, we investigate various tie-breaking strategies from ensemble-based classifiers. Our study outperforms the classification accuracy achieved by traditional methods applied to Bark-101, thus demonstrating the feasibility of applying patch-based CNNs to such challenging datasets.

Published
2020

6. Semantic Segmentation Refinement with Deep Edge Superpixels to Enhance Historical Land Cover

Author

Laure Tougne, Rémi Ratajczak, Béatrice Fervers, Carlos Crispim-Junior, Elodie Faure, Extraction de Caractéristiques et Identification (imagine), Laboratoire d'InfoRmatique en Image et Systèmes d'information (LIRIS), 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), Université de Lyon-Université Lumière - Lyon 2 (UL2), Département cancer environnement (Centre Léon Bérard - Lyon), Centre Léon Bérard [Lyon], Agence de l'Environnement et de la Maîtrise de l'Energie (ADEME), LABEX IMU (ANR-10-LABX-0088/ ANR-11-IDEX-0007)., ADEME (N TEZ17-42), Centre Léon Bérard, IEEE, TESTIS, IMU GOURAMIC, 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-Centre National de la Recherche Scientifique (CNRS)-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 Lumière - Lyon 2 (UL2)-École Centrale de Lyon (ECL), and Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)

Subjects
Conditional random field, Computer science, 02 engineering and technology, Land cover, 010501 environmental sciences, 01 natural sciences, Deep Edges, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], Segmentation, Deep Learning, Land Use, 0202 electrical engineering, electronic engineering, information engineering, ComputingMilieux_MISCELLANEOUS, 0105 earth and related environmental sciences, business.industry, Deep learning, Land use land cover, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], Pattern recognition, Image segmentation, 15. Life on land, Classification, [SDE.ES]Environmental Sciences/Environmental and Society, Historical Land Use, Kernel (image processing), [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], 020201 artificial intelligence & image processing, Artificial intelligence, business
Abstract

International audience; In this work, we explore a post-processing method to enhance coarse semantic segmentation of historical aerial images. We propose to use deep edges to generate semantically meaningful superpixels that we integrate as additional pairwise potentials in a dense conditional random field. We apply our approach on very high resolution images acquired between 1975 and 1995 and annotated with land use land cover labels. Results show the interest of our approach compared to other post-processing methods.

Published
2020

7. CAD-based Learning for Egocentric Object Detection in Industrial Context

Author

Céline Grange-Faivre, Julia Cohen, Laure Tougne, Carlos Crispim-Junior, Extraction de Caractéristiques et Identification (imagine), Laboratoire d'InfoRmatique en Image et Systèmes d'information (LIRIS), 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), Université de Lyon-Université Lumière - Lyon 2 (UL2), and CIFRE n°2018/0872

Subjects
business.industry, Computer science, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Image content, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], 020207 software engineering, Context (language use), CAD, 02 engineering and technology, [INFO.INFO-NE]Computer Science [cs]/Neural and Evolutionary Computing [cs.NE], Real image, Convolutional neural network, Object detection, Task (project management), Database Generation, Object Detection, 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, Computer vision, Egocentric, [INFO]Computer Science [cs], Artificial intelligence, business, Set (psychology)
Abstract

International audience; Industries nowadays have an increasing need of real-time and accurate vision-based algorithms. Although the performance of object detection methods improved a lot thanks to massive public datasets, instance detection in industrial context must be approached differently, since annotated images are usually unavailable or rare. In addition, when the video stream comes from a head-mounted camera, we observe a lot of movements and blurred frames altering the image content. For this purpose, we propose a framework to generate a dataset of egocentric synthetic images using only CAD models of the objects of interest. To evaluate different strategies exploiting synthetic and real images, we train a Convolutional Neural Network (CNN) for the task of object detection in egocentric images. Results show that training a CNN on synthetic images that reproduce the characteristics of egocentric vision may perform as well as training on a set of real images, reducing, if not removing, the need to manually annotate a large quantity of images to achieve an accurate performance.

Published
2020

8. Pseudo-Cyclic Network for Unsupervised Colorization with Handcrafted Translation and Output Spatial Pyramids

Author

Rémi Ratajczak, Laure Tougne, Béatrice Fervers, Carlos Crispim-Junior, Elodie Faure, Agence de l'Environnement et de la Maîtrise de l'Energie (ADEME), Extraction de Caractéristiques et Identification (imagine), Laboratoire d'InfoRmatique en Image et Systèmes d'information (LIRIS), 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), Université de Lyon-Université Lumière - Lyon 2 (UL2), Département cancer environnement (Centre Léon Bérard - Lyon), and Centre Léon Bérard [Lyon]

Subjects
Artificial neural network, Computer science, business.industry, [INFO.INFO-MM]Computer Science [cs]/Multimedia [cs.MM], ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Pattern recognition, 02 engineering and technology, [INFO.INFO-NE]Computer Science [cs]/Neural and Evolutionary Computing [cs.NE], 010501 environmental sciences, Color space, Translation (geometry), 01 natural sciences, Grayscale, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, State (computer science), Artificial intelligence, business, 0105 earth and related environmental sciences, Generator (mathematics), Complement (set theory)
Abstract

International audience; We present a novel pseudo-cyclic adversarial learning approach for unsupervised colorization of grayscale images. We investigate the use of a non-trainable, lightweight and well-defined Handcrafted Translation to enforce the generation of realistic images and replace one of the two deep convolutional generative adversarial neural networks classically used in cyclic models. Additionally, we propose to use Output Spatial Pyramids to jointly constrain the deep latent spaces of an encoder-decoder generator to preserve spatial structures and improve the quality of the generated images. We demonstrate the interest of our approach compared with the state of the art on standard datasets (paintings, landscapes, aerial, thumbnails) that we modified for the purpose of colorization. We evaluate colorization quality of the generated images along the training with deterministic and reproducible criteria. In complement, we demonstrate the ability of our method to generate representations that are prone to make a classification network generalize well to slightly different color spaces. We believe our approach has potential applications in arts and cultural heritage to produce alternative representations without requiring paired data.

Published
2019

9. Toward An Unsupervised Colorization Framework for Historical Land Use Classification

Author

Béatrice Fervers, Laure Tougne, Rémi Ratajczak, Carlos Crispim-Junior, Elodie Faure, Extraction de Caractéristiques et Identification (imagine), Laboratoire d'InfoRmatique en Image et Systèmes d'information (LIRIS), 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), Université de Lyon-Université Lumière - Lyon 2 (UL2), Département cancer environnement (Centre Léon Bérard - Lyon), Centre Léon Bérard [Lyon], Agence de l'Environnement et de la Maîtrise de l'Energie (ADEME), LABEX IMU (ANR-10-LABX-0088/ ANR-11-IDEX-0007)., ADEME (N TEZ17-42), Centre Léon Bérard, IEEE, TESTIS, and IMU GOURAMIC

Subjects
Computer science, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, 02 engineering and technology, Texture (geology), [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], Deep Learning, Land Use, 0202 electrical engineering, electronic engineering, information engineering, Colorization, Land use, Artificial neural network, Texture filters, business.industry, Deep learning, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], Pattern recognition, 15. Life on land, Index Terms-Colorization, Classification, [SDE.ES]Environmental Sciences/Environmental and Society, GAN, Visualization, Historical Land Use, [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], 020201 artificial intelligence & image processing, Artificial intelligence, business
Abstract

International audience; We present an unsupervised colorization framework to improve both the visualization and the automatic land use classification of historical aerial images. We introduce a novel algorithm built upon a cyclic generative adversarial neural network and a texture replacement method to homogeneously and automatically colorize unpaired VHR images. We apply our framework on historical aerial images acquired in France between 1970 and 1990. We demonstrate that our approach helps to disentangle hard to classify land use classes and hence improves the overall land use classification.

Published
2019

10. Automatic Land Cover Reconstruction From Historical Aerial Images: An Evaluation of Features Extraction and Classification Algorithms

Author

Rémi Ratajczak, Laure Tougne, Béatrice Fervers, Elodie Faure, Carlos Crispim-Junior, Extraction de Caractéristiques et Identification (imagine), Laboratoire d'InfoRmatique en Image et Systèmes d'information (LIRIS), Institut National des Sciences Appliquées de Lyon (INSA Lyon), Institut National des Sciences Appliquées (INSA)-Université de Lyon-Institut National des Sciences Appliquées (INSA)-Université de Lyon-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), Université de Lyon-Université Lumière - Lyon 2 (UL2), Agence de l'Environnement et de la Maîtrise de l'Energie (ADEME), Département cancer environnement (Centre Léon Bérard - Lyon), Centre Léon Bérard [Lyon], ADEME (N TEZ17-42), ENVITERA, CENTRE LEON BERARD, LABEX IMU (ANR-10-LABX-0088/ ANR11-IDEX-0007), TESTIS, and IMU GOURAMIC

Subjects
Local binary patterns, Feature vector, Index Terms-Features extraction, Feature extraction, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, 02 engineering and technology, [INFO.INFO-NE]Computer Science [cs]/Neural and Evolutionary Computing [cs.NE], Convolutional neural network, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], Machine Learning, Deep Learning, [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], 0202 electrical engineering, electronic engineering, information engineering, Deep Con- volutional Neural Networks, business.industry, Texture filters, Deep learning, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], Pattern recognition, Image segmentation, [SHS.GEO]Humanities and Social Sciences/Geography, 15. Life on land, Land Cover, Computer Graphics and Computer-Aided Design, Historical Aerial Images, Statistical classification, Filter (video), [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], 020201 artificial intelligence & image processing, Artificial intelligence, business, Software
Abstract

International audience; The land cover reconstruction from monochromatic historical aerial images is a challenging task that has recently known an increasing interest from the scientific community with the proliferation of large scale epidemiological studies involving retrospective analysis of spatial pattern. However, the efforts engaged by the computer vision community in remote sensing applications are mostly focused on prospective approaches through the analysis of high resolution multi-spectral data acquired by advanced spatial programs. Hence, four contributions are proposed in this article. They aim at providing a comparison basis for the future development of computer vision algorithms applied to the automation of the land cover reconstruction from monochromatic historical aerial images. Firstly, a new multiscale multi-date dataset composed of 4.9 million non-overlapping annotated patches of the France territory between 1970 and 1990 has been created with the help of Geography experts. This dataset has been named HistAerial (http://eidolon.univ-lyon2.fr/~remi1/HistAerialDataset/). Secondly, an extensive comparison study of state-of-the-art texture features extraction and classification algorithms including deep convolutional neural networks (DCNNs) has been performed. It is presented in the form of an evaluation. Thirdly, a novel low-dimensional local texture filter named Rotated-CorneR Local Binary Pattern (RCRLBP) is presented as a simplification of the Binary Gradient Contours filter through the use of an orthogonal combination representation. Finally, a novel combination of low-dimensional texture descriptors, including the R-CRLBP filter, is introduced as a Light Combination of Local Binary Patterns (LCoLBP). The LCoLBP filter achieved state-of-the-art results on the HistAerial dataset while conserving a relatively low-dimensional feature vector space compared with the DCNN approaches (17 times shorter).HistAerial : http://eidolon.univ-lyon2.fr/~remi1/HistAerialDataset/

Published
2019

11. Euclidean Distance-Based Skeletons: A Few Notes on Average Outward Flux and Ridgeness

Author

Aurélie Leborgne, Julien Mille, Laure Tougne, Laboratoire d'Informatique Fondamentale et Appliquée de Tours (LIFAT), Université de Tours (UT)-Institut National des Sciences Appliquées - Centre Val de Loire (INSA CVL), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Centre National de la Recherche Scientifique (CNRS), Institut Pascal (IP), SIGMA Clermont (SIGMA Clermont)-Université Clermont Auvergne [2017-2020] (UCA [2017-2020])-Centre National de la Recherche Scientifique (CNRS), Extraction de Caractéristiques et Identification (imagine), 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), Centre National de la Recherche Scientifique (CNRS)-Université de Tours-Institut National des Sciences Appliquées - Centre Val de Loire (INSA CVL), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA), 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), Université de Lyon-Université Lumière - Lyon 2 (UL2), and Institut National des Sciences Appliquées (INSA)-Université de Lyon-Institut National des Sciences Appliquées (INSA)-Université de Lyon-Centre National de la Recherche Scientifique (CNRS)-Université Claude Bernard Lyon 1 (UCBL)

Subjects
Statistics and Probability, geography, geography.geographical_feature_category, Applied Mathematics, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], Geometry, Context (language use), 02 engineering and technology, Skeleton (category theory), Condensed Matter Physics, Measure (mathematics), Euclidean distance, Maxima and minima, Ridge, Modeling and Simulation, [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, Geometry and Topology, Computer Vision and Pattern Recognition, Focus (optics), Distance transform, Mathematics
Abstract

International audience; Among the various existing and mathematically equivalent definitions of the skeleton, we consider the set of critical points of the Euclidean distance transform of the shape. The problem of detecting these points and using them to generate a skeleton that is stable , thin and homotopic to the shape has been the focus of numerous papers. Skeleton branches correspond to ridges of the distance map, i.e. continuous lines of points that are local maxima of the distance in at least one direction. Extracting these ridges is a non-trivial task on a discrete grid. In this context, the average outward flux, used in the Hamilton-Jacobi skeleton [43], and the ridgeness measure [28] have been proposed as ridge detectors. We establish the mathematical relation between these detectors and, extending the work in [18], we study various local shape configurations, on which closed-form expressions or approximations of the average outward flux and ridgeness can be derived. In addition , we conduct experiments to assess the accuracy of skeletons generated using these measures, and study the influence of their respective parameters.

Published
2019

12. Jitter-Free Registration for Unmanned Aerial Vehicle Videos

Author

Lionel Robinault, Carlos Crispim-Junior, Pierre Lemaire, Laure Tougne, Extraction de Caractéristiques et Identification (imagine), Laboratoire d'InfoRmatique en Image et Systèmes d'information (LIRIS), 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
0209 industrial biotechnology, Computer science, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Video Registration, 02 engineering and technology, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], 020901 industrial engineering & automation, Motion estimation, 0202 electrical engineering, electronic engineering, information engineering, Hybrid solution, Computer vision, Unmanned Aerial Vehicles, Jitter, business.industry, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], Drone, Image stabilization, Variable (computer science), Video registration, [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], 020201 artificial intelligence & image processing, Artificial intelligence, Constant (mathematics), business, Motion Estimation, Video Stabiliza- tion
Abstract

International audience; Unmanned Aerial Vehicles (UAVs), such as tethered drones, become increasingly popular for video acquisition, within video surveillance or remote, scientific measurement contexts. However, UAV recordings often present an unstable, variable viewpoint that is detrimental to the automatic exploitation of their content. This is often countered by one amongst two strategies, video registration and video stabilization, which are usually affected by distinct issues, namely jitter and drifting. This paper proposes a hybrid solution between both techniques that produces a jitter-free registration. A lightweight implementation enables real time, automatic generation of videos with a constant viewpoint from unstable video sequences acquired with stationary UAVs. Performance evaluation is carried out using video recordings from traffic surveillance scenes up to 15 minutes long, including multiple mobile objects.

Published
2019

13. Bark and Leaf Fusion Systems to Improve Automatic Tree Species Recognition

Author

Lionel Valet, Didier Coquin, Guillaume Cerutti, Sarah Bertrand, Rihab Ben Ameur, Laure Tougne, Extraction de Caractéristiques et Identification ( imagine ), 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-Centre National de la Recherche Scientifique ( CNRS ) -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 Lumière - Lyon 2 ( UL2 ) -École Centrale de Lyon ( ECL ), Université de Lyon-Institut National des Sciences Appliquées ( INSA ) -Institut National des Sciences Appliquées ( INSA ), Modeling plant morphogenesis at different scales, from genes to phenotype ( VIRTUAL PLANTS ), 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 ) -Institut National de la Recherche Agronomique ( INRA ) -Centre de coopération internationale en recherche agronomique pour le développement [CIRAD] : UMR51, ANR-15-CE38-0004,ReVeRIES,Reconnaissance de Végétaux Récréative, Interactive et Educative sur Smartphone, Extraction de Caractéristiques et Identification (imagine), 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-Centre National de la Recherche Scientifique (CNRS)-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 Lumière - Lyon 2 (UL2)-École Centrale de Lyon (ECL), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA), Laboratoire d'Informatique, Systèmes, Traitement de l'Information et de la Connaissance (LISTIC), Université Savoie Mont Blanc (USMB [Université de Savoie] [Université de Chambéry]), Simulation et Analyse de la morphogenèse in siliCo (MOSAIC), Inria Grenoble - Rhône-Alpes, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Reproduction et développement des plantes (RDP), École normale supérieure - Lyon (ENS Lyon)-Institut National de la Recherche Agronomique (INRA)-Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-Université de Lyon-Centre National de la Recherche Scientifique (CNRS), 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), École normale supérieure de Lyon (ENS de Lyon)-Institut National de la Recherche Agronomique (INRA)-Université Claude Bernard Lyon 1 (UCBL), ANR-15-CE38-0004,ReVeRIES,Reconnaissance de Végétaux Récréative, Interactive et Educative sur Smartphone(2015), Institut National des Sciences Appliquées de Lyon (INSA Lyon), Institut National des Sciences Appliquées (INSA)-Université de Lyon-Institut National des Sciences Appliquées (INSA)-Université de Lyon-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), Université de Lyon-Université Lumière - Lyon 2 (UL2), Centre National de la Recherche Scientifique (CNRS)-Université Claude Bernard Lyon 1 (UCBL), and Université de Lyon-Université de Lyon-Institut National de la Recherche Agronomique (INRA)-École normale supérieure - Lyon (ENS Lyon)

Subjects
[ INFO.INFO-IR ] Computer Science [cs]/Information Retrieval [cs.IR], [ INFO ] Computer Science [cs], Computer science, 02 engineering and technology, 01 natural sciences, Bark, Tree recognition, [ INFO.INFO-TI ] Computer Science [cs]/Image Processing, 0202 electrical engineering, electronic engineering, information engineering, [INFO]Computer Science [cs], Fusion, Ecology, Evolution, Behavior and Systematics, Ecology, business.industry, Applied Mathematics, Ecological Modeling, 010401 analytical chemistry, Confusion matrix, Pattern recognition, Distinctive feature, 15. Life on land, 0104 chemical sciences, Computer Science Applications, Tree (data structure), Leaf, Computational Theory and Mathematics, Modeling and Simulation, visual_art, [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], [INFO.INFO-IR]Computer Science [cs]/Information Retrieval [cs.IR], Combination, visual_art.visual_art_medium, 020201 artificial intelligence & image processing, Identification (biology), Artificial intelligence, business, Tree species
Abstract

International audience; For everyone, the identification of tree is a difficult task. The main organ of the plant used generally to identify a tree is the leaf. However, due to the large variability of the shapes of leaves, it is difficult to obtain good recognition results. Moreover, sometimes the bark is a very distinctive feature and we think it may be possible to improve the recognition rate by considering it. The main purpose of this article is to investigate how we can combine the features extracted respectively from the leaf and the bark images to recognize the tree the photos come from. An important point is the consideration of the confusion matrix that can be constructed between several species, when the form of a leaf or the shape of a bark is common to a number of tree species. So, we present various strategies of fusion including belief functions and compare them on a public database of 72 species of trees and shrubs, which can be find in metropolitan France.

Published
2018

14. A New Database of Digits Extracted from Coins with Hard-to-Segment Foreground for Optical Character Recognition Evaluation

Author

Xingyu Pan and Laure Tougne

Subjects
Computer Networks and Communications, Computer science, character recognition, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, 02 engineering and technology, computer.software_genre, 01 natural sciences, lcsh:QA75.5-76.95, test database, Artificial Intelligence, 0103 physical sciences, 0202 electrical engineering, electronic engineering, information engineering, Segmentation, coin, digits, 010306 general physics, Recognition algorithm, Database, Optical character recognition, Numerical digit, 13. Climate action, Hardware and Architecture, ICT, Release date, date, 020201 artificial intelligence & image processing, lcsh:Electronic computers. Computer science, Digit recognition, computer, Software, Character recognition, Information Systems
Abstract

Since the release date struck on a coin is important information of its monetary type, recognition of extracted digits may assist in identification of monetary types. However, digit images extracted from coins are challenging for conventional optical character recognition methods because the foreground of such digits has very often the same color as their background. In addition, other noises, including the wear of coin metal, make it more difficult to obtain a correct segmentation of the character shape. To address those challenges, this article presents the CoinNUMS database for automatic digit recognition. The database CoinNUMS, containing 3,006 digit images, is divided into three subsets. The first subset CoinNUMS_geni consists of 606 digit images manually cropped from high-resolution photographs of well-conserved coins from GENI coin photographs; the second subset CoinNUMS_pcgs_a consists of 1,200 digit images automatically extracted from a subset of the USA_Grading numismatic database containing coins in different quality; the last subset CoinNUMS_pcgs_m consists of 1,200 digit images manually extracted from the same coin photographs as CoinNUMS_pcgs_a. In CoinNUMS_pcgs_a and CoinNUMS_pcgs_m, the digit images are extracted from the release date. In CoinNUMS_geni, the digit images can come from the cropped date, the face value, or any other legends containing digits in the coin. To show the difficulty of these databases, we have tested recognition algorithms of the literature. The database and the results of the tested algorithms will be freely available on a dedicated website.1

Published
2017

15. Adding a rigid motion model to foreground detection: application to moving object detection in rivers

Author

Imtiaz Ali, Laure Tougne, Julien Mille, Extraction de Caractéristiques et Identification (imagine), Laboratoire d'InfoRmatique en Image et Systèmes d'information (LIRIS), 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), Université de Lyon-Université Lumière - Lyon 2 (UL2), and Geometry Processing and Constrained Optimization (M2DisCo)

Subjects
Foreground detection, Background subtraction, Computer science, business.industry, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Motion detection, 0102 computer and information sciences, 02 engineering and technology, 01 natural sciences, Object detection, Object-class detection, 010201 computation theory & mathematics, Artificial Intelligence, Motion estimation, 0202 electrical engineering, electronic engineering, information engineering, Structure from motion, [INFO]Computer Science [cs], 020201 artificial intelligence & image processing, Computer vision, Viola–Jones object detection framework, Computer Vision and Pattern Recognition, Artificial intelligence, business
Abstract

International audience; Object detection in a dynamic backgroundis a challenging task in many computer vision applica-tions. In some situations, the motion of objects can bepredicted thanks to its regularity (e.g. vehicle motion,pedestrian motion). In this article, we propose to modelsuch motion knowledge and to use it as additional infor-mation to help in foreground detection. The inclusionof object motion information provides a measure fordistinguishing moving objects from a background thathas similar sizes and brightness levels. This informationis obtained by applying statistical methods on data ob-tained during the training period.When available, priorknowledge can be incorporated into the foreground de-tection process to improve robustness and to decreasefalse detection. We apply this framework to moving ob-ject detection in rivers, one of the situations in whichclassic background subtraction algorithms fail. Our ex-periments show that the incorporation of prior motiondata into background subtraction improves object de-tection.

Published
2013

16. Noise-resistant Digital Euclidean Connected Skeleton for graph-based shape matching

Author

Laure Tougne, Julien Mille, Aurélie Leborgne, Extraction de Caractéristiques et Identification (imagine), Laboratoire d'InfoRmatique en Image et Systèmes d'information (LIRIS), Institut National des Sciences Appliquées de Lyon (INSA Lyon), Institut National des Sciences Appliquées (INSA)-Université de Lyon-Institut National des Sciences Appliquées (INSA)-Université de Lyon-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
ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], 020207 software engineering, 02 engineering and technology, Blob detection, Topology, Skeletonization, Medial axis, Robustness (computer science), [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], Signal Processing, 0202 electrical engineering, electronic engineering, information engineering, Media Technology, 020201 artificial intelligence & image processing, Topological skeleton, Computer Vision and Pattern Recognition, Electrical and Electronic Engineering, Representation (mathematics), Distance transform, Algorithm, Pruning (morphology), Mathematics, ComputingMethodologies_COMPUTERGRAPHICS
Abstract

We propose a propagation algorithm to obtain a skeleton with "good properties".Our algorithm combines RDMA and Laplacian of Gaussian filtering.The complexity is linearly proportional to the number of pixels of image.Our method is compared to three existing methods. The skeleton is an essential shape descriptor providing a compact representation of a shape that can be used in the context of real object recognition. However, due to the discretization, the required properties to use it for graph matching (homotopy to the shape, consequently connectivity, thinness, robustness to noise) may be difficult to obtain simultaneously. In this paper, we propose a new skeletonization algorithm having all these properties, based on the Euclidean distance map. More precisely, the algorithm cleverly combines the centers of maximal balls included in the shape and the ridges of the distance map. Post-processing is then applied to thin and prune the resulting skeleton. We compare the proposed method to three fairly recent methods and demonstrate its good properties.

Published
2015

17. Leaf margins as sequences: A structural approach to leaf identification

Author

Guillaume Cerutti, Laure Tougne, Antoine Vacavant, Didier Coquin, Extraction de Caractéristiques et Identification (imagine), 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), Laboratoire d'Informatique, Systèmes, Traitement de l'Information et de la Connaissance (LISTIC), Université Savoie Mont Blanc (USMB [Université de Savoie] [Université de Chambéry]), Image Science for Interventional Techniques (ISIT), Université d'Auvergne - Clermont-Ferrand I (UdA)-Clermont Université-Centre National de la Recherche Scientifique (CNRS), ANR-10-CORD-0005,REVES,REconnaissance de VEgétaux pour des interfaces Smartphones(2010), 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
Multivariate sequences, Edit distance, Context (language use), 02 engineering and technology, Consistency (database systems), [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, Artificial Intelligence, 0202 electrical engineering, electronic engineering, information engineering, Representation (mathematics), Mathematics, Sequence, Interpretation (logic), business.industry, 020207 software engineering, Pattern recognition, Classification, Identification (information), Tree (data structure), Signal Processing, 020201 artificial intelligence & image processing, Leaf recognition, Computer Vision and Pattern Recognition, Artificial intelligence, business, Software
Abstract

We propose a high-level interpretation of leaf contours through CSS analysis.Leaf margins are described by an original string representation of vectorial symbols.Methods inspired from string processing are adapted to this objects.We use this spatially-rich descriptor to perform species classification.Performance is compared with state-of-the-art shape descriptors, and shows competitive results. In the context of an automated leaf identification process, the use of thorough leaf margin descriptors is essential given the importance of this criterion in the determination of the species. The spatial properties of teeth along the leaf contour are something to keep track of, which is made possible through the use of structured representations. This paper introduces a sequence representation of leaf margins where teeth are viewed as symbols of a multivariate real valued alphabet. It presents the methods developed to make use of this description for classification and implementation in a mobile tree identifying application. The results of various classification methods are compared and discussed, both in terms of species recognition and of consistency with botanical concepts.

Published
2014

18. A New Coin Segmentation and Graph-Based Identification Method for Numismatic Application

Author

Kitti Puritat, Laure Tougne, Xingyu Pan, Extraction de Caractéristiques et Identification (imagine), Laboratoire d'InfoRmatique en Image et Systèmes d'information (LIRIS), Institut National des Sciences Appliquées de Lyon (INSA Lyon), Institut National des Sciences Appliquées (INSA)-Université de Lyon-Institut National des Sciences Appliquées (INSA)-Université de Lyon-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), Université de Lyon-Université Lumière - Lyon 2 (UL2), and Chiang Mai University (CMU)

Subjects
TheoryofComputation_COMPUTATIONBYABSTRACTDEVICES, Computer science, Graph based, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], 02 engineering and technology, computer.software_genre, 01 natural sciences, Two stages, Identification system, [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], 0103 physical sciences, 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, Segmentation, Model based segmentation, Data mining, InformationSystems_MISCELLANEOUS, 010306 general physics, computer
Abstract

International audience; The automatic identification of coins from photos helps coin experts to accelerate their study of coins and to reduce the associated expenses. To address this challenging problem for numismatic applications , we propose a novel coin identification system that consists of two stages. In the first stage, an active model based segmentation approach extracts precisely the coin from the photo with its shape features; in the second stage, the coin is identified to a monetary class represented by a template coin. The similarity score of two coins is computed from graphs constructed by feature points. Validation on the USA Grading dataset demonstrates that the proposed method obtains promising results with an identification accuracy of 94.4% on 2450 coins of 148 classes.

Published
2014

19. An Approach for the Estimation of the Precision of a Real Object from its Digitization

Author

Fabien Feschet, Laure Tougne, TOUGNE, Laure, Laboratoire de Logique, Algorithmique et Informatique (LLAIC1), Université d'Auvergne - Clermont-Ferrand I (UdA), Laboratoire d'InfoRmatique en Image et Systèmes d'information (LIRIS), 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), 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), and Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Centre National de la Recherche Scientifique (CNRS)

Subjects
Mathematical optimization, General Computer Science, 02 engineering and technology, Computer Science::Computational Geometry, Theoretical Computer Science, Set (abstract data type), Error estimation, [INFO.INFO-CV] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], 020204 information systems, 0202 electrical engineering, electronic engineering, information engineering, Discrete Mathematics and Combinatorics, discretization, Rigid transformation, Digitization, ComputingMilieux_MISCELLANEOUS, ComputingMethodologies_COMPUTERGRAPHICS, Mathematics, Simplex, Discrete curve, Applied Mathematics, Representation (systemics), [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], Object (computer science), polygonalisation, Transformation (function), Preimages of lines, Polygon, 020201 artificial intelligence & image processing, Algorithm, Computer Science(all)
Abstract

In this article, we study the problem of the estimation of the rigid transformations, composed by translations and rotations, of a real object such that the discretizations before and after the transformation are the same. Our method is based on the polyhedral simplex representation associated to the set of lines compatible with each border of a real polygon. We give some algorithms that allow to decide whether a transformation is “valid” for a polygon and to compute the “maximal possible transformations”.

Published
2001
Full Text
View/download PDF

20. Understanding Leaves in Natural Images - A Model-Based Approach for Tree Species Identification

Author

Guillaume Cerutti, Julien Mille, Laure Tougne, Didier Coquin, Antoine Vacavant, Geometry Processing and Constrained Optimization (M2DisCo), Laboratoire d'InfoRmatique en Image et Systèmes d'information (LIRIS), 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), Université de Lyon-Université Lumière - Lyon 2 (UL2), Extraction de Caractéristiques et Identification (imagine), Image Science for Interventional Techniques (ISIT), Université d'Auvergne - Clermont-Ferrand I (UdA)-Clermont Université-Centre National de la Recherche Scientifique (CNRS), Laboratoire d'Informatique, Systèmes, Traitement de l'Information et de la Connaissance (LISTIC), Université Savoie Mont Blanc (USMB [Université de Savoie] [Université de Chambéry]), 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), and Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Centre National de la Recherche Scientifique (CNRS)

Subjects
geometric features, Process (engineering), Semantic interpretation, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Scale-space segmentation, 02 engineering and technology, Image (mathematics), plant recognition, 0202 electrical engineering, electronic engineering, information engineering, tree leaf, Segmentation, image segmentation, Mathematics, Active contour model, business.industry, Pattern recognition, 04 agricultural and veterinary sciences, Image segmentation, 15. Life on land, active contours, Identification (information), classification, [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], Signal Processing, 040103 agronomy & agriculture, 0401 agriculture, forestry, and fisheries, 020201 artificial intelligence & image processing, Computer Vision and Pattern Recognition, Artificial intelligence, business, Software, natural background
Abstract

International audience; With the aim of elaborating a mobile application, accessible to anyone and with educational purposes, we present a method for tree species identification that relies on dedicated algorithms and explicit botany-inspired descriptors. Focusing on the analysis of leaves, we developed a working process to help recognize species, starting from a picture of a leaf in a complex natural background. A two-step active contour segmentation algorithm based on a polygonal leaf model processes the image to retrieve the contour of the leaf. Features we use afterwards are high-level geometrical descriptors that make a semantic interpretation possible, and prove to achieve better performance than more generic and statistical shape descriptors alone. We present the results, both in terms of segmentation and classification, considering a database of 50 European broad-leaved tree species, and an implementation of the system is available in the iPhone application Folia.

Published
2013

21. Comparative Study of Segmentation Methods for Tree Leaves Extraction

Author

Kevin Bianchi, Antoine Vacavant, Guillaume Cerutti, Manuel Grand-Brochier, Laure Tougne, Laboratoire d'InfoRmatique en Image et Systèmes d'information (LIRIS), 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), Image Science for Interventional Techniques (ISIT), Université d'Auvergne - Clermont-Ferrand I (UdA)-Clermont Université-Centre National de la Recherche Scientifique (CNRS), Geometry Processing and Constrained Optimization (M2DisCo), Université de Lyon-Université Lumière - Lyon 2 (UL2)-Institut National des Sciences Appliquées de Lyon (INSA Lyon), 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), and 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)

Subjects
Segmentation-based object categorization, Computer science, business.industry, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Scale-space segmentation, 020207 software engineering, Pattern recognition, 02 engineering and technology, Image segmentation, Thresholding, Tree (data structure), 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, Segmentation, Computer vision, [INFO]Computer Science [cs], Artificial intelligence, Cluster analysis, business, Hamming code
Abstract

International audience; In this paper, we present a comparative study of segmentation methods, tested for an issue of tree leaves extraction. Approaches implemented include processes using thresholding, clustering, or even active contours. The observation criteria, such as the Dice index, Hamming measure or SSIM for example, allow us to highlight the performance obtained by our guided active coutour algorithm that is specially dedicated to tree leaf segmentation (G. Cerutti et al., Guiding Active Contours for Tree Leaf Segmentation and Identification. ImageCLEF2011). We currently offer a dedicated segmentation tree leaf benchmark, comparing fourteen segmentation methods (ten unsupervised and four supervised) following twenty evaluation criteria.

Published
2013

22. A Testing Framework for Background Subtraction Algorithms Comparison inIntrusion Detection Context

Author

Lionel Robinault, Emanuelle Reynaud, Corentin Lallier, Laure Tougne, Geometry Processing and Constrained Optimization (M2DisCo), Laboratoire d'InfoRmatique en Image et Systèmes d'information (LIRIS), 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), Université de Lyon-Université Lumière - Lyon 2 (UL2), Laboratoire d'Etude des Mécanismes Cognitifs (EMC), and Université Lumière - Lyon 2 (UL2)

Subjects
Background subtraction, Pixel, Computer science, business.industry, Frame (networking), ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, 020206 networking & telecommunications, Context (language use), Pattern recognition, 02 engineering and technology, Image segmentation, Intrusion detection system, Similarity measure, 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, Segmentation, Computer vision, [INFO]Computer Science [cs], Artificial intelligence, business, Algorithm
Abstract

International audience; Identifying objects from a video stream is a fundamentaland critical task in many computer-vision applications.A popular approach is the background subtraction, whichconsists in separating foreground (moving objects) frombackground. Many methodologies have been developed forautomatic background segmentation but this fundamentaltask is still challenging. We focus here on a particular applicationof computer vision: intrusion detection in videosurveillance.We propose in this paper a multi-level methodology forevaluating and comparing background subtraction algorithms.Three levels are studied: first, pixel level to evaluatethe accuracy of the segmentation algorithm to attribute theright class to each pixel. Second, image level, measuringthe rate of right decision on each frame (intrusion vs nointrusion) and finally sequence level, measuring the accordancewith the time span where objects appear. Moreover,we also propose a new similarity measure, called D-Score,adapted to the context of intrusion detection.

Published
2011

23. A Parametric Active Polygon for Leaf Segmentation and Shape Estimation

Author

Guillaume Cerutti, Didier Coquin, Laure Tougne, Antoine Vacavant, Geometry Processing and Constrained Optimization (M2DisCo), Laboratoire d'InfoRmatique en Image et Systèmes d'information (LIRIS), 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), Université de Lyon-Université Lumière - Lyon 2 (UL2), Image Science for Interventional Techniques (ISIT), Université d'Auvergne - Clermont-Ferrand I (UdA)-Clermont Université-Centre National de la Recherche Scientifique (CNRS), Laboratoire d'Informatique, Systèmes, Traitement de l'Information et de la Connaissance (LISTIC), Université Savoie Mont Blanc (USMB [Université de Savoie] [Université de Chambéry]), Cerutti, Guillaume, 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), and Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Centre National de la Recherche Scientifique (CNRS)

Subjects
Active contour model, Basis (linear algebra), business.industry, Computer science, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Process (computing), Scale-space segmentation, 020207 software engineering, 02 engineering and technology, 15. Life on land, Leaf identification, Tree (data structure), Segmentation, [INFO.INFO-TI] Computer Science [cs]/Image Processing [eess.IV], [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], Polygon, 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, Computer vision, Artificial intelligence, business, ComputingMethodologies_COMPUTERGRAPHICS, Parametric statistics
Abstract

International audience; The identication of tree leaves from photographs taken in a natural environment is a di cult task where the quality of the seg- mentation is of primary importance. In this paper we present a system that combines a rst, unre ned segmentation step, with an estimation of descriptors depicting the general shape of a simple leaf. It is based on a light polygonal model, built to represent most of the leaf shapes, that will be deformed to t the leaf in the image. Avoiding some classic obstacles of active contour models, this approach gives promising results, even on complex natural photographs, and constitutes a solid basis for a leaf recognition process.

Published
2011

24. Wood Detection and Tracking in Videos of Rivers

Author

Imtiaz Ali, Julien Mille, Laure Tougne, Extraction de Caractéristiques et Identification (imagine), Laboratoire d'InfoRmatique en Image et Systèmes d'information (LIRIS), 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), Université de Lyon-Université Lumière - Lyon 2 (UL2), and Geometry Processing and Constrained Optimization (M2DisCo)

Subjects
Rest (physics), 010504 meteorology & atmospheric sciences, Computer science, business.industry, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, 02 engineering and technology, Image segmentation, Tracking (particle physics), 01 natural sciences, Debris, GeneralLiterature_MISCELLANEOUS, Consecutive frame, Representative point, 0202 electrical engineering, electronic engineering, information engineering, [INFO]Computer Science [cs], 020201 artificial intelligence & image processing, Computer vision, Artificial intelligence, business, ComputingMethodologies_COMPUTERGRAPHICS, 0105 earth and related environmental sciences
Abstract

International audience; Rivers during floods bring a lot of fallen trees and debris. Video surveillance systems are installed on strategically important places on the rivers. To protect these places from destructions due to accumulation of wood, such systems must be able to automatically detect wood. Image segmentation is performed to separate wood and other moving elements from the rest of the water. Moving objects are detected with respect to brightness and temporal variation features. The floating wood is then tracked in the sequence of frames by temporal linking of the segments generated in the detection step. Our algorithm is tested on multiple videos of floods and the results are evaluated both qualitatively and quantitatively.

Published
2011

25. Measure of circularity for parts of digital boundaries and its fast computation

Author

Laure Tougne, Tristan Roussillon, Isabelle Sivignon, Laboratoire d'InfoRmatique en Image et Systèmes d'information (LIRIS), Institut National des Sciences Appliquées de Lyon (INSA Lyon), Institut National des Sciences Appliquées (INSA)-Université de Lyon-Institut National des Sciences Appliquées (INSA)-Université de Lyon-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), and ANR-06-BLAN-0225,GEODIB,Géométrie des Objets Discrets Bruités(2006)

Subjects
Computation, Digital data, Boundary (topology), Discrete geometry, 0102 computer and information sciences, 02 engineering and technology, Computational geometry, 01 natural sciences, Measure (mathematics), 010201 computation theory & mathematics, Artificial Intelligence, [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], Signal Processing, 0202 electrical engineering, electronic engineering, information engineering, Digital geometry, 020201 artificial intelligence & image processing, Digital signal, Computer Vision and Pattern Recognition, Algorithm, Software, Mathematics
Abstract

International audience; This paper focuses on the design of an effective method that computes the measure of circularity of a part of a digital boundary. An existing circularity measure of a set of discrete points, which is used in computational metrology, is extended to the case of parts of digital boundaries. From a single digital boundary, two sets of points are extracted so that the circularity measure computed from these sets is representative of the circularity of the digital boundary. Therefore, the computation consists of two steps. First, the inner and outer sets of points are extracted from the input part of a digital boundary using digital geometry tools. Next, the circularity measure of these sets is computed using classical tools of computational geometry. It is proved that the algorithm is linear in time in the case of convex parts thanks to the specificity of digital data, and is in O(n log n) otherwise. Experiments done on synthetic and real images illustrate the interest of the properties of the circularity measure.

Published
2010

26. Unsupervised video analysis for counting of wood in river during floods

Author

Laure Tougne, Imtiaz Ali, Laboratoire d'InfoRmatique en Image et Systèmes d'information (LIRIS), 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), Geometry Processing and Constrained Optimization (M2DisCo), and Université de Lyon-Université Lumière - Lyon 2 (UL2)-Institut National des Sciences Appliquées de Lyon (INSA Lyon)

Subjects
010504 meteorology & atmospheric sciences, business.industry, Computer science, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Unsupervised segmentation, 02 engineering and technology, Image segmentation, Mixture model, 01 natural sciences, Debris, GeneralLiterature_MISCELLANEOUS, False detection, 0202 electrical engineering, electronic engineering, information engineering, Automatic segmentation, 020201 artificial intelligence & image processing, Computer vision, [INFO]Computer Science [cs], Artificial intelligence, business, Monocular vision, ComputingMethodologies_COMPUTERGRAPHICS, 0105 earth and related environmental sciences
Abstract

International audience; This paper presents a framework for counting the fallen trees,bushes and debris passing in the river by monocular vision. Automaticsegmentation and recognition of wood in the river is relatively new fieldof research. Unsupervised segmentation of the wooden objects movingin the river has been developed. A novel method is developed for theseparation of wood from water waves. The counting of number of fallentrees in the river is realized by tracking them in the consecutive continuousframes. The algorithm is tested on multiple videos of floods and theresults are evaluated both qualitatively and quantitatively.

Published
2009

27. A Novel Algorithm for Distance Transformation on Irregular Isothetic Grids

Author

Antoine Vacavant, David Coeurjolly, Laure Tougne, Geometry Processing and Constrained Optimization (M2DisCo), Laboratoire d'InfoRmatique en Image et Systèmes d'information (LIRIS), 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
020207 software engineering, 02 engineering and technology, Regular grid, Separable space, Octree, Transformation (function), Medial axis, 0202 electrical engineering, electronic engineering, information engineering, Quadtree, 020201 artificial intelligence & image processing, [INFO]Computer Science [cs], Voronoi diagram, Representation (mathematics), Algorithm, Mathematics
Abstract

In this article, we propose a new definition of the E2DT (Squared Euclidean Distance Transformation) on irregular isothetic grids such as quadtree/octree or run-length encoded d-dimensional images. We describe a new separable algorithm to compute this transformation on every grids, which is independent of the background representation. We show that our proposal is able to efficiently handle various kind of classical irregular two-dimensional grids in imagery, and that it can be easily extended to higher dimensions.

Published
2009

28. A framework for dynamic implicit curve approximation by an irregular discrete approach

Author

Antoine Vacavant, Laure Tougne, David Coeurjolly, SI LIRIS, Équipe gestionnaire des publications, Geometry Processing and Constrained Optimization (M2DisCo), Laboratoire d'InfoRmatique en Image et Systèmes d'information (LIRIS), 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
Process (computing), Discrete geometry, 020207 software engineering, 02 engineering and technology, [INFO] Computer Science [cs], Topology, Computer Graphics and Computer-Aided Design, Interval arithmetic, Planar, Line segment, Modeling and Simulation, 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, [INFO]Computer Science [cs], Geometry and Topology, Representation (mathematics), Reeb graph, Algorithm, Software, Topology (chemistry), Mathematics
Abstract

International audience; The approximation of implicit planar curves by line segments is a very classical problem.Many algorithms use interval analysis to approximate this curve, and to handle the topology of thefinal reconstruction. In this article, we use discrete geometry tools to build an original geometricaland topological representation of the implicit curve. The polygonal approximation contains fewsegments, and the Reebgraph permits to sum up efficiently the shape and the topology of the curve.Furthermore, we propose two algorithms to process local cells refinement and local cells groupingschemes.We illustrate these schemes with a global system thatefficiently handles manual or automatic fast updates on the global reconstruction, by consideringtopological or geometrical constraints.We also compare the speed and the quality of our approach with two classical methods.

Published
2009

29. On Three Constrained Versions of the Digital Circular Arc Recognition Problem

Author

Isabelle Sivignon, Laure Tougne, Tristan Roussillon, Geometry Processing and Constrained Optimization (M2DisCo), Laboratoire d'InfoRmatique en Image et Systèmes d'information (LIRIS), 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), Université de Lyon-Université Lumière - Lyon 2 (UL2), and Sivignon, Isabelle

Subjects
Mathematical optimization, Boundary (topology), 0102 computer and information sciences, 02 engineering and technology, Radius, 01 natural sciences, Arc (geometry), [INFO.INFO-TI] Computer Science [cs]/Image Processing [eess.IV], 010201 computation theory & mathematics, Simple (abstract algebra), [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, Center (algebra and category theory), Point (geometry), Algorithm, Digitization, MathematicsofComputing_DISCRETEMATHEMATICS, Mathematics
Abstract

International audience; This paper focuses on the on-line recognition of digital arcs. The main contribution is to propose a simple and linear algorithm for three subproblems: on-line recognition of digital arcs coming from the digitization of a disk having (i) a fixed radius, (ii) a boundary that con- tacts a fixed point and (iii) a center that belongs to a fixed straight line. Solving such subproblems is interesting in itself, but also for the recog- nition of digital arcs. Indeed the proposed algorithm can be used as an oracle in multidimensional search techniques or can be iteratively used in a naive manner. Moreover, since the algorithm is on-line, it is a means of segmenting digital curves in a very fast way.

Published
2009

30. What Does Digital Straightness Tell About Digital Convexity ?

Author

Laure Tougne, Isabelle Sivignon, Tristan Roussillon, Sivignon, Isabelle, Geometry Processing and Constrained Optimization (M2DisCo), Laboratoire d'InfoRmatique en Image et Systèmes d'information (LIRIS), 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
Computer science, Regular polygon, Boundary (topology), 0102 computer and information sciences, 02 engineering and technology, Edge (geometry), 01 natural sciences, Convexity, Combinatorics, Set (abstract data type), [INFO.INFO-TI] Computer Science [cs]/Image Processing [eess.IV], 010201 computation theory & mathematics, [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], TheoryofComputation_ANALYSISOFALGORITHMSANDPROBLEMCOMPLEXITY, 0202 electrical engineering, electronic engineering, information engineering, Digital geometry, 020201 artificial intelligence & image processing, Point (geometry), Segmentation, Algorithm
Abstract

International audience; The paper studies local convexity properties of parts of dig- ital boundaries. An online and linear-time algorithm is introduced for the decomposition of a digital boundary into convex and concave parts. In addition, other data are computed in the same time without any extra cost: the hull of each convex or concave part as well as the Bezout points of each edge of those hulls. The proposed algorithm involves well- understood algorithms: adding a point to the front or removing a point from the back of a digital straight segment and computing the set of maximal segments. The output of the algorithm is useful either for a polygonal representation of digital boundaries or for a segmentation into circular arcs.

Published
2009

31. Robust Decomposition of a Digital Curve into Convex and Concave Parts

Author

Laure Tougne, Tristan Roussillon, Isabelle Sivignon, Geometry Processing and Constrained Optimization (M2DisCo), Laboratoire d'InfoRmatique en Image et Systèmes d'information (LIRIS), 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), Université de Lyon-Université Lumière - Lyon 2 (UL2), and SI LIRIS, Équipe gestionnaire des publications

Subjects
Convex hull, Mathematical optimization, Convex geometry, business.industry, Computation, 0102 computer and information sciences, 02 engineering and technology, [INFO] Computer Science [cs], 01 natural sciences, 010201 computation theory & mathematics, TheoryofComputation_ANALYSISOFALGORITHMSANDPROBLEMCOMPLEXITY, 0202 electrical engineering, electronic engineering, information engineering, Curve fitting, 020201 artificial intelligence & image processing, Convex combination, Output-sensitive algorithm, [INFO]Computer Science [cs], Artificial intelligence, Gift wrapping algorithm, business, Algorithm, Alpha shape, Mathematics
Abstract

International audience; We propose a linear in time and easy-to-implement algorithm that robustly decomposes a digital curve into convex and concave parts. This algorithm is based on classical tools in discrete and computational geometry: convex hull computation and Pick's formula.

Published
2008

32. Two dimensional discrete statistical shape models construction

Author

Serge Miguet, Isameddine Boukhriss, Laure Tougne, Laboratoire d'InfoRmatique en Image et Systèmes d'information (LIRIS), 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), and TOUGNE, Laure

Subjects
Active contour model, Computer science, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], 0102 computer and information sciences, 02 engineering and technology, Landmark point, Curvature, 01 natural sciences, [INFO.INFO-CV] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], [INFO.INFO-TI] Computer Science [cs]/Image Processing [eess.IV], 010201 computation theory & mathematics, Position (vector), [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], Active shape model, Principal component analysis, 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, Point (geometry), Algorithm, Normal, ComputingMilieux_MISCELLANEOUS, ComputingMethodologies_COMPUTERGRAPHICS
Abstract

In this paper, we present a discrete approach to 2D statistical shape models construction. An object is modeled in terms of landmark points on its contour. An optimized process of intrinsic discrete properties computes then curvilinear position, curvature and normal vector for each point. The approach uses after a dynamic programming process to match points of different shapes. By identifying matched points on a set of training examples, a statistical approach with principal component analysis, computes the mean object shape, the major modes of shape variation and extracts a compact and generic model.

Published
2007

33. Computation of Binary Objects Sides Number using Discrete Geometry, Application to Automatic Pebbles Shape Analysis

Author

Tristan Roussillon, Laure Tougne, Isabelle Sivignon, Geometry Processing and Constrained Optimization (M2DisCo), Laboratoire d'InfoRmatique en Image et Systèmes d'information (LIRIS), 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
[INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], 0202 electrical engineering, electronic engineering, information engineering, 020207 software engineering, 020201 artificial intelligence & image processing, 02 engineering and technology, [INFO.INFO-CG]Computer Science [cs]/Computational Geometry [cs.CG]
Abstract

International audience; We are working in collaboration with geographers to study a set of pebbles digital images. Among the features geographers want to get automatically, pebble sides number is intuitively defined as shown in Fig 1. It is merely computed after a thick polygonalisation of pebble contour. We propose an incremental and linear algorithm, free of restrictive hypothesis, which relies on previous works of Debled et al. [DRFRD05, DRFRD06, DRRRD05]. We give some results on synthetical and real images.

Published
2007

34. Dynamic Reconstruction of Complex Planar Objects on Irregular Isothetic Grids

Author

Antoine Vacavant, David Coeurjolly, Laure Tougne, Geometry Processing and Constrained Optimization (M2DisCo), Laboratoire d'InfoRmatique en Image et Systèmes d'information (LIRIS), 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), Université de Lyon-Université Lumière - Lyon 2 (UL2), Laboratoire des sciences et matériaux pour l'électronique et d'automatique (LASMEA), Université Blaise Pascal - Clermont-Ferrand 2 (UBP)-Centre National de la Recherche Scientifique (CNRS), 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), and Coeurjolly, David

Subjects
ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, 020207 software engineering, Reconstruction algorithm, Image processing, 02 engineering and technology, Iterative reconstruction, Grid, Interval arithmetic, [INFO.INFO-TI] Computer Science [cs]/Image Processing [eess.IV], [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], Vectorization (mathematics), 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, Representation (mathematics), Algorithm, Reeb graph, Mathematics
Abstract

International audience; The vectorization of discrete regular images has been widely developed in many image processing and synthesis applications, where images are considered as a regular static data. Regardless of final application, we have proposed in [14] a reconstruction algorithm of planar graphical elements on irregular isothetic grids. In this paper, we present a dynamic version of this algorithm to control the reconstruction. Indeed, we handle local refinements to update efficiently our complete shape representation. We also illustrate an application of our contribution for interactive approximation of implicit curves by lines, controlling the topology of the reconstruction.

Published
2006

35. On the min DSS problem of the closed discrete curves

Author

Laure Tougne, Fabien Feschet, Laboratoire de Logique, Algorithmique et Informatique (LLAIC1), Université d'Auvergne - Clermont-Ferrand I (UdA), Laboratoire d'InfoRmatique en Image et Systèmes d'information (LIRIS), 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), 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), and TOUGNE, Laure

Subjects
Mathematical optimization, Optimal complexity, 0102 computer and information sciences, 02 engineering and technology, 01 natural sciences, Discrete system, [INFO.INFO-CV] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], Quadratic equation, Min DSS problem, 0202 electrical engineering, electronic engineering, information engineering, Discrete Mathematics and Combinatorics, Point (geometry), Representation (mathematics), Time complexity, ComputingMilieux_MISCELLANEOUS, Computer Science::Databases, Mathematics, Series (mathematics), Applied Mathematics, Tangent, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], Tangential cover, 020202 computer hardware & architecture, Cover (topology), 010201 computation theory & mathematics, 020201 artificial intelligence & image processing, Algorithm, Discrete curves and segments
Abstract

International audience; Given a discrete eight-connected curve, it can be represented by discrete eight connected segments. In this paper, we try to determine the minimal number of necessary discrete segments. This problem is known as the min DSS problem. We propose to use a generic curve representation by discrete tangents, called a tangential cover which can be computed in linear time. We introduce a series of criteria each having a linear-time complexity to progressively solve the min DSS problem. This results in an optimal algorithm both from the point of view of optimization and of complexity, outperforming the previous quadratic bound.

Published
2005

36. Two-Dimensional Discrete Morphing

Author

Isameddine Boukhriss, Serge Miguet, Laure Tougne, Laboratoire d'InfoRmatique en Image et Systèmes d'information (LIRIS), 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), and Université de Lyon-Université Lumière - Lyon 2 (UL2)

Subjects
Pixel, Geodesic, Atlas (topology), Computer science, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Discrete geometry, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], Image processing, 0102 computer and information sciences, 02 engineering and technology, Topology, 01 natural sciences, Morphing, Operator (computer programming), 010201 computation theory & mathematics, Approximation error, 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, Algorithm, Rigid transformation, ComputingMilieux_MISCELLANEOUS, ComputingMethodologies_COMPUTERGRAPHICS, Interpolation
Abstract

In this article we present an algorithm for discrete object deformation. This algorithm is a first step for computing an average shape between two discrete objects and may be used for building a statistical atlas of shapes. The method we develop is based on discrete operators and works only on digital data. We do not compute continuous approximations of objects so that we have neither approximations nor interpolation errors. The first step of our method performs a rigid transformation that aligns the shapes as best as possible and decreases geometrical differences between them. The next step consists in searching the progressive transformations of one object toward the other one, that iteratively adds or suppresses pixels. These operations are based on geodesic distance transformation and lead to an optimal (linear) algorithm.

Published
2004

37. 2D and 3D Visibility in Discrete Geometry : an Application to Discrete Geodesic Paths

Author

David Coeurjolly, Serge Miguet, Laure Tougne, Laboratoire d'InfoRmatique en Image et Systèmes d'information (LIRIS), 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), and Université de Lyon-Université Lumière - Lyon 2 (UL2)

Subjects
Convex geometry, Geodesic, Visibility (geometry), Discrete geometry, 0102 computer and information sciences, 02 engineering and technology, Computational geometry, Topology, 01 natural sciences, Discrete system, 010201 computation theory & mathematics, Artificial Intelligence, [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], Signal Processing, 0202 electrical engineering, electronic engineering, information engineering, Digital geometry, 020201 artificial intelligence & image processing, Computer Vision and Pattern Recognition, Discrete differential geometry, Software, Mathematics, ComputingMethodologies_COMPUTERGRAPHICS
Abstract

International audience; In this article, we present a discrete definition of the classical visibility in computational geometry based on digital straight lines. We present efficient algorithms to compute the set of pixels in a non-convex domain that are visible from a source pixel. Based on these definitions, we define discrete geodesic paths in discrete domain with obstacles. This allows us to introduce a new geodesic metric in discrete geometry.

Published
2004

38. Multigrid Convergence and Surface Area Estimation

Author

David Coeurjolly, Laure Tougne, Olivier Teytaud, Frédéric Flin, Laboratoire d'InfoRmatique en Image et Systèmes d'information (LIRIS), 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), Météo-France [Paris], Météo France, Algorithmic number theory for cryptology (TANC), 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)-Laboratoire d'informatique de l'École polytechnique [Palaiseau] (LIX), Centre National de la Recherche Scientifique (CNRS)-École polytechnique (X)-Centre National de la Recherche Scientifique (CNRS)-École polytechnique (X), Laboratoire de Recherche en Informatique (LRI), Université Paris-Sud - Paris 11 (UP11)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS), 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), Météo-France, Laboratoire d'informatique de l'École polytechnique [Palaiseau] (LIX), École polytechnique (X)-Centre National de la Recherche Scientifique (CNRS)-École polytechnique (X)-Centre National de la Recherche Scientifique (CNRS)-Inria Saclay - Ile de France, and Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)

Subjects
Multigrid convergence, Mathematical optimization, Computer science, Computation, Estimator, 020207 software engineering, Image processing, 02 engineering and technology, Multigrid method, [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, Algorithm, Normal, ComputingMilieux_MISCELLANEOUS, Shape analysis (digital geometry)
Abstract

Surface area of discrete objects is an important feature for model-based image analysis. In this article, we present a theoretical framework in order to prove multigrid convergence of surface area estimators based on discrete normal vector field integration. The paper details an algorithm which is optimal in time and multigrid convergent to estimate the surface area and a very efficient algorithm based on a local but adaptive computation.

Published
2003

39. Discrete parabolas and circles on 2D cellular automata

Author

Laure Tougne, Marianne Delorme, Jacques Mazoyer, Laboratoire de l'Informatique du Parallélisme (LIP), École normale supérieure de Lyon (ENS de Lyon)-Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-Université de Lyon-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS), École normale supérieure - Lyon (ENS Lyon)-Université Claude Bernard Lyon 1 (UCBL), Centre National de la Recherche Scientifique (CNRS)-Université de Lyon-Institut National de Recherche en Informatique et en Automatique (Inria)-Université Claude Bernard Lyon 1 (UCBL), and Université de Lyon-École normale supérieure - Lyon (ENS Lyon)

Subjects
Discrete mathematics, Vertex (graph theory), General Computer Science, Algorithm complexity, [INFO.INFO-DS]Computer Science [cs]/Data Structures and Algorithms [cs.DS], [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], 02 engineering and technology, State (functional analysis), Cellular automaton, Whole systems, Automaton, Theoretical Computer Science, Combinatorics, 020204 information systems, 0202 electrical engineering, electronic engineering, information engineering, Automata theory, 020201 artificial intelligence & image processing, ComputingMilieux_MISCELLANEOUS, Mathematics, Computer Science(all)
Abstract

andpossiblythehexagonalnetwork. Wecallcell each pair {vertex,automaton A}.Such a system can be considered as a dynamical one. At one time t,the global state of the system is given by an application Γ −→ S,whichassigns to each cell a state of A.And,startingfromaninitialconfiguration,the whole system synchronously evolves, at discrete times, from one config-uration to the next one. This behavior is formalized through asequenceofconfigurations (Γ

Published
1999

40. Circle digitization and cellular automata

Author

Laure Tougne, Laboratoire de l'Informatique du Parallélisme (LIP), École normale supérieure de Lyon (ENS de Lyon)-Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-Université de Lyon-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS), Centre National de la Recherche Scientifique (CNRS)-Université de Lyon-Institut National de Recherche en Informatique et en Automatique (Inria)-Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-École normale supérieure - Lyon (ENS Lyon), and École normale supérieure - Lyon (ENS Lyon)-Université Claude Bernard Lyon 1 (UCBL)

Subjects
060201 languages & linguistics, Diagonal, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], 06 humanities and the arts, 02 engineering and technology, Construct (python library), Nonlinear Sciences::Cellular Automata and Lattice Gases, Grid, Cellular automaton, Mobile automaton, Algebra, 0602 languages and literature, 0202 electrical engineering, electronic engineering, information engineering, Arithmetic function, 020201 artificial intelligence & image processing, Digitization, Beam (structure), ComputingMilieux_MISCELLANEOUS, Mathematics
Abstract

The article studies the discrete circles with the help of cellular automata. It is shown that if we consider a discrete circle as a succession of horizontal, diagonal and vertical segments which lean on a beam of parabolas, we can describe it by local properties and so, construct it by cellular automata. In fact, two algorithms are examined. The first one localizes the intersections between a given real circle and the grid. The second one constructs a well-known discrete circle: the arithmetical circle.

Published
1996

41. An elementary algorithm for digital arc segmentation

Author

Yan Gerard, Laure Tougne, David Coeurjolly, Jean-Pierre Reveillès, Coeurjolly, David, 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), Laboratoire de Logique, Algorithmique et Informatique (LLAIC1), Université d'Auvergne - Clermont-Ferrand I (UdA), Entrepôts, Représentation et Ingénierie des Connaissances (ERIC), Université Lumière - Lyon 2 (UL2)-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)-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), and Université de Lyon-Université Lumière - Lyon 2 (UL2)

Subjects
digital circle, General Computer Science, Linear programming, Arc segmentation, digital arc recognition, 0102 computer and information sciences, 02 engineering and technology, [INFO.INFO-CG]Computer Science [cs]/Computational Geometry [cs.CG], 01 natural sciences, Theoretical Computer Science, Arc (geometry), arc separability, 0202 electrical engineering, electronic engineering, information engineering, Discrete Mathematics and Combinatorics, Incremental algorithm, Meaning (existential), ComputingMilieux_MISCELLANEOUS, Separation problem, Mathematics, Discrete curve, Applied Mathematics, Computational geometry, Midpoint circle algorithm, digital curvature, [INFO.INFO-TI] Computer Science [cs]/Image Processing [eess.IV], 010201 computation theory & mathematics, [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], 020201 artificial intelligence & image processing, Algorithm, Computer Science(all)
Abstract

This paper is concerned with the digital circle recognition problem and more precisely with the circular separating algorithm . It tries to go further in implementation details, giving pseudo-code algorithms for the main points, and avoids using the sophisticated machinery coming either from Computational Geometry or from Linear Programming found in previous papers on this subject. After recalling the geometrical meaning of the separating circle problem, we present an incremental algorithm to segment a discrete curve into digital arc.

42. Separable algorithms for distance transformations on irregular grids

Author

David Coeurjolly, Antoine Vacavant, Laure Tougne, SI LIRIS, Équipe gestionnaire des publications, Geometry Processing and Constrained Optimization (M2DisCo), Laboratoire d'InfoRmatique en Image et Systèmes d'information (LIRIS), 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
Minkowski distance, 020207 software engineering, 02 engineering and technology, Euclidean distance matrix, [INFO] Computer Science [cs], Topology, Weighted Voronoi diagram, Euclidean distance, Octree, Transformation (function), Artificial Intelligence, Signal Processing, 0202 electrical engineering, electronic engineering, information engineering, Quadtree, 020201 artificial intelligence & image processing, [INFO]Computer Science [cs], Computer Vision and Pattern Recognition, Voronoi diagram, Algorithm, Software, Mathematics
Abstract

International audience; In this article, we propose to investigate two extensions of the E2DT (squared Euclidean Distance Transformation) on irregular isothetic grids (or I-grids), such as quadtree/octree or run-length encoded d-dimensional images. We enumerate the advantages and drawbacks of the I-CDT, based on the cell centres, and the ones of the I-BDT, which uses the cell borders. One of the main problem we mention is that no efficient algorithm has been designed to compute both transforms in arbitrary dimensions. To tackle this problem, we describe in this paper two algorithms, separable in dimension, to compute these distance transformations in the two-dimensional case, and we show that they can be easily extended to higher dimensions.

43. A Model-Based Approach for Compound Leaves Understanding and Identification

Author

Guillaume Cerutti, Antoine Vacavant, Julien Mille, Didier Coquin, Laure Tougne, 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), Extraction de Caractéristiques et Identification (imagine), Image Science for Interventional Techniques (ISIT), Université d'Auvergne - Clermont-Ferrand I (UdA)-Clermont Université-Centre National de la Recherche Scientifique (CNRS), Laboratoire d'Informatique, Systèmes, Traitement de l'Information et de la Connaissance (LISTIC), Université Savoie Mont Blanc (USMB [Université de Savoie] [Université de Chambéry]), 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), Université de Lyon-Université Lumière - Lyon 2 (UL2), and Cerutti, Guillaume

Subjects
Computer science, Semantic interpretation, compound leaf, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, 02 engineering and technology, Interpretation (model theory), Set (abstract data type), plant recognition, 0202 electrical engineering, electronic engineering, information engineering, Segmentation, image segmentation, deformable templates, Contextual image classification, business.industry, 020207 software engineering, Pattern recognition, Image segmentation, 15. Life on land, active contours, Identification (information), [INFO.INFO-TI] Computer Science [cs]/Image Processing [eess.IV], classification, [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], 020201 artificial intelligence & image processing, Artificial intelligence, business
Abstract

International audience; In this paper, we propose a specific method for the identification of compound-leaved tree species, with the aim of integrating it in an educational smartphone application. Our work is based on dedicated shape models for compound leaves, designed to estimate the number and shape of leaflets. A deformable template approach is used to fit these models and produce a high-level interpretation of the image content. The resulting models are later used for the segmentation of leaves in both plain and natural background images, by the use of multiple region-based active contours. Combined with other botany-inspired descriptors accounting for the morphological properties of the leaves, we propose a classification method that makes a semantic interpretation possible. Results are presented over a set of more than 1000 images from 17 European tree species, and an integration in the existing mobile application Folia is considered.

44. Hierarchical skeleton for shape matching

Author

Julien Mille, Aurélie Leborgne, Laure Tougne, LEBORGNE, Aurélie, Reconnaissance de Végétaux Récréative, Interactive et Educative sur Smartphone - - ReVeRIES2015 - ANR-15-CE38-0004 - AAPG2015 - VALID, Extraction de Caractéristiques et Identification (imagine), Laboratoire d'InfoRmatique en Image et Systèmes d'information (LIRIS), Institut National des Sciences Appliquées de Lyon (INSA Lyon), Institut National des Sciences Appliquées (INSA)-Université de Lyon-Institut National des Sciences Appliquées (INSA)-Université de Lyon-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), Université de Lyon-Université Lumière - Lyon 2 (UL2), Laboratoire d'Informatique Fondamentale et Appliquée de Tours (LIFAT), Université de Tours (UT)-Institut National des Sciences Appliquées - Centre Val de Loire (INSA CVL), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Centre National de la Recherche Scientifique (CNRS), ANR-15-CE38-0004,ReVeRIES,Reconnaissance de Végétaux Récréative, Interactive et Educative sur Smartphone(2015), Centre National de la Recherche Scientifique (CNRS)-Université de Tours-Institut National des Sciences Appliquées - Centre Val de Loire (INSA CVL), and Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)

Subjects
Matching (graph theory), business.industry, hierarchical skeleton, matching, pruning, pattern recognition, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], 020207 software engineering, Pattern recognition, 02 engineering and technology, Skeleton (category theory), Euclidean distance, [INFO.INFO-CV] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], Pattern recognition (psychology), Morphological skeleton, 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, Topological skeleton, Artificial intelligence, business, Pruning (morphology), Smoothing, Mathematics, ComputingMethodologies_COMPUTERGRAPHICS
Abstract

International audience; The skeleton is an efficient and complete shape descriptor often used for matching. However, existing skeleton-based shape matching methods are computationally intensive. To reduce the algorithmic complexity, we propose to exploit the natural hierarchy of the skeleton. The aim is to quantify the importance of skeleton branches to guide the shape matching algorithm, in order to match branches having the same order of importance. Our method is based on successive shape smoothing operations and on the deformability of the skeleton to adapt it to each smoothed shape. Moreover, we show that our method is independent from the initial skeleton.

45. Discrete Average of Two-Dimensional Shapes

Author

Laure Tougne, Isameddine Boukhriss, Serge Miguet, Laboratoire d'InfoRmatique en Image et Systèmes d'information (LIRIS), 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), and Université de Lyon-Université Lumière - Lyon 2 (UL2)

Subjects
Pixel, Geodesic, Computer science, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], Discrete geometry, Image processing, 0102 computer and information sciences, 02 engineering and technology, Topology, 01 natural sciences, Weighting, 010201 computation theory & mathematics, 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, ComputingMilieux_MISCELLANEOUS, Rigid transformation, Shape analysis (digital geometry)
Abstract

In this article we present an algorithm for computing discrete average of n two-dimensional shapes. Our previous work was limited to two shapes, we generalize it to an arbitrary number of objects with consideration of increasing inter-individual variability. The first step of our approach performs a rigid transformation that aligns the shapes as best as possible. The next step consists in searching the progressive metamorphosis of one object toward the other one, that iteratively adds or suppresses pixels. This process is then iterated between the last average shape obtained and the new object from the set according to weighting consideration. It considers the rank in which each shape is added and gives criteria of optimization in variability and global topology preservation. The basic operations are based on geodesic distance transformations and lead to an optimal (linear) algorithm.

46. A first look into a formal and constructive approach for discrete geometry using nonstandard analysis

Author

Guy Wallet, Gaëlle Largeteau-Skapin, Laurent Fuchs, Eric Andres, Agathe Chollet, SIC, XLIM (XLIM), Université de Limoges (UNILIM)-Centre National de la Recherche Scientifique (CNRS)-Université de Limoges (UNILIM)-Centre National de la Recherche Scientifique (CNRS)-Université de Poitiers, Mathématiques, Image et Applications - EA 3165 (MIA), Université de La Rochelle (ULR), David Coeurjolly, Isabelle Sivignon, Laure Tougne, Florent Dupont, Largeteau-Skapin, Gaëlle, and David Coeurjolly, Isabelle Sivignon, Laure Tougne, Florent Dupont

Subjects
Discrete mathematics, Basis (linear algebra), Continuum (measurement), 010102 general mathematics, Discrete geometry, 02 engineering and technology, [INFO.INFO-DM]Computer Science [cs]/Discrete Mathematics [cs.DM], 01 natural sciences, Constructive, Algebra, [INFO.INFO-DM] Computer Science [cs]/Discrete Mathematics [cs.DM], Analytic geometry, 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, Constructive analysis, 0101 mathematics, Axiom, Differential (mathematics), ComputingMilieux_MISCELLANEOUS, Mathematics
Abstract

In this paper, we recall the origins of discrete analytical geometry developed by J-P. Reveilles [1] in the nonstandard model of the continuum based on integers proposed by Harthong and Reeb [2,3]. We present some basis on constructive mathematics [4] and its link with programming [5,6]. We show that a suitable version of this new model of the continuum partly fits with the constructive axiomatic of R proposed by Bridges [7]. The aim of this paper is to take a first look at a possible formal and constructive approach to discrete geometry. This would open the way to better algorithmic definition of discrete differential concepts.

Published
2008

47. Generation and Recognition of Digital Plane using Multi-dimensional Continued Fractions

Author

Thomas Fernique, Arithmétique informatique (ARITH), Laboratoire d'Informatique de Robotique et de Microélectronique de Montpellier (LIRMM), Centre National de la Recherche Scientifique (CNRS)-Université de Montpellier (UM)-Centre National de la Recherche Scientifique (CNRS)-Université de Montpellier (UM), and David Coeurjolly and Isabelle Sivignon and Laure Tougne and Florent Dupont

Subjects
Discrete mathematics, digital plane recognition, continued fractions, 0102 computer and information sciences, 02 engineering and technology, [INFO.INFO-DM]Computer Science [cs]/Discrete Mathematics [cs.DM], Brun algorithm, 01 natural sciences, Connection (mathematics), Hyperplane, Chain (algebraic topology), 010201 computation theory & mathematics, [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], Pattern recognition (psychology), 0202 electrical engineering, electronic engineering, information engineering, Multi dimensional, 020201 artificial intelligence & image processing, generalized substitution, Mathematics
Abstract

International audience; This paper extends, in a multi-dimensional framework, pattern recognition technics for generation or recognition of digital lines. More precisely, we show how the connection between chain codes of digital lines and continued fractions can be generalized by a connection between tilings and multi-dimensional continued fractions. This leads to a new approach for generating and recognizing digital hyperplanes.

Published
2008

48. Geometric Feature Estimators for Noisy Discrete Surfaces

Author

I. Debled-Rennesson, L. Provot, Applying Discrete Algorithms to Genomics and Imagery (ADAGIO), Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Institut National de Recherche en Informatique et en Automatique (Inria)-Université Henri Poincaré - Nancy 1 (UHP)-Université Nancy 2-Institut National Polytechnique de Lorraine (INPL)-Centre National de la Recherche Scientifique (CNRS)-Institut National de Recherche en Informatique et en Automatique (Inria)-Université Henri Poincaré - Nancy 1 (UHP)-Université Nancy 2-Institut National Polytechnique de Lorraine (INPL)-Centre National de la Recherche Scientifique (CNRS), David Coeurjolly, Isabelle Sivignon, Laure Tougne and Florent Dupont, and ANR-06-BLAN-0225,GEODIB,Géométrie des Objets Discrets Bruités(2006)

Subjects
Geometric feature estimators, business.industry, Digital geometry, Regular polygon, Estimator, 020207 software engineering, Pattern recognition, 02 engineering and technology, [INFO.INFO-DM]Computer Science [cs]/Discrete Mathematics [cs.DM], Object (computer science), Feature (computer vision), 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, Point (geometry), 3D discrete objects, Artificial intelligence, Noise (video), business, Normal, Algorithm, Mathematics
Abstract

International audience; We present in this paper robust geometric feature estimators on the border of a possibly noisy discrete object. We introduce the notion of patch centered at a point of this border. Thanks to a width parameter, attached to a patch, the noise on the border of the discrete object can be considered, and an extended flat neighborhood of a border point is computed. Stable geometric features are then extracted around this point. A normal vector estimator is proposed as well as a detector of convex and concave parts on the border of a discrete object.

Published
2008

Catalog

Books, media, physical & digital resources
See catalog results