Search

Your search keyword '"LAGIS-SI"' showing total 302 results
Start Over Author "LAGIS-SI"
302 results on '"LAGIS-SI"'

151. Comparison of color demosaicing methods

Author

Losson, Olivier, Macaire, Ludovic, Yang, Yanqin, LAGIS-SI, Laboratoire d'Automatique, Génie Informatique et Signal (LAGIS), and Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)

Subjects
Demosaicing, Color image, Comparison criteria, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Quality evaluation, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing, ComputingMethodologies_COMPUTERGRAPHICS
Abstract

International audience; Mono-CCD color cameras acquire only one color component at each pixel by means of their color filter array (CFA) covering the CCD sensor. To obtain a color image, a procedure - called demosaicing - is then necessary to estimate the other two missing color components at each pixel. This chapter deals with the quality of color images generated in such a way. We attempt to determine which demosaicing method provides the best results according to several comparison criteria, particularly for subsequent needs of color image analyses like edge detection.

Published
2010

152. A visual attention focusing system using an active stereoscopic vision sensor

Author

Luc Duvieubourg, François Cabestaing, Shahram Bahrami, Yann Ducrocq, Département Automatique, Ecole d'Ingénieurs du Pas-de-Calais (EIPC), LAGIS-SI, Laboratoire d'Automatique, Génie Informatique et Signal (LAGIS), Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS), Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 (CRIStAL), Centrale Lille-Université de Lille-Centre National de la Recherche Scientifique (CNRS), Ecole d'Ingénieurs du Pas-de-Calais, and IEEE

Subjects
active vision, Visual perception, Computer science, Machine vision, media_common.quotation_subject, Stereoscopy, 010501 environmental sciences, 01 natural sciences, 050105 experimental psychology, law.invention, [SPI]Engineering Sciences [physics], [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, Salience (neuroscience), law, Perception, Visual attention, 0501 psychology and cognitive sciences, Computer vision, Active vision, ComputingMilieux_MISCELLANEOUS, 0105 earth and related environmental sciences, media_common, stereoscopic catadioptric sensor, saliency, Orientation (computer vision), business.industry, 05 social sciences, Gaze, orientable field of view, Stereopsis, visual attention, Artificial intelligence, business, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing
Abstract

International audience; Humans have the capacity to move their eyes. Thanks to this capacity, they can orient their gaze to look at a relevant object inside a complex scene. In this paper, we have implemented a driver assistance application which tries to mimic this human capacity. We focus specially on highway driving situations, where the detection of obstacles must be done far away in front of the car. The implementation of the gaze control and orientation is obtained by an active vision system. We know that the human gaze is related to the visual attention which is a result of human perception and cognitive phenomenon. Several studies have shown that human perception and more specially the visual perception can be decomposed into a bottom-up process and a top-down process. Most of researches focused on the bottom-up process. In this work, in order to mimic the human behavior or at least improve vision systems, we use a new active stereovision setup and a model of the human visual perception based on the two previous approaches. Moreover, in a bottom-up approach, we add the depth information obtained with the stereoscopic sensor to the classical features used by other works. The topdown process is computed by the global knowledge of the scene and its features. Some results obtained by mean of a virtual road sequence, show the orientation of the field of view of the stereoscopic sensor toward relevant objects, given our criteria.

Published
2010

153. Consonant Continuous Belief Functions Conflicts Calculation

Author

Jean-Marc Vannobel, LAGIS-SI, Laboratoire d'Automatique, Génie Informatique et Signal (LAGIS), Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS), E. Hüllermeier, R. Kruse, F. Hoffmann, Vannobel, Jean-Marc, and E. Hüllermeier, R. Kruse, F. Hoffmann

Subjects
Consonant, 0209 industrial biotechnology, Gaussian, Probability density function, 02 engineering and technology, 16. Peace & justice, Calculation methods, [SPI.AUTO]Engineering Sciences [physics]/Automatic, symbols.namesake, [SPI.AUTO] Engineering Sciences [physics]/Automatic, 020901 industrial engineering & automation, 0202 electrical engineering, electronic engineering, information engineering, symbols, Conflict management, 020201 artificial intelligence & image processing, Merge (version control), Algorithm, Continuous belief functions Conjunctive combination Disjunctive combination Partial and global conflict calculation, Real number, Mathematics
Abstract

International audience; Much information sources model imprecision by the way of unimodal, consonant and continuous probability density functions (pdfs). We consider here in the framework of belief functions on real numbers, agents of evidence deduced from such pdfs. First are singletons plausibilities in conjunctive and disjunctive combinations proposed to basically merge agents of evidence with consonant focal elements. Second are partial and global conflict calculation methods provided. An application shows the plausibility curves and conflict values obtained in case of combination operations done on Gaussian based agents and at last, an example of conflict management based on an RCR-S adaptive rule of combination is given.

Published
2010

154. Using High-Dimensional Image Models to Perform Highly Undetectable Steganography

Author

Tomáš Pevný, Patrick Bas, Tomas Filler, Czech Technical University in Prague (CTU), Binghamton University [SUNY], State University of New York (SUNY), LAGIS-SI, Laboratoire d'Automatique, Génie Informatique et Signal (LAGIS), Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS), and ANR-06-SETI-0009,NEBIANNO,Sécurité et fiabilité des techniques de tatouages(2006)

Subjects
Steganalysis, Steganography, business.industry, Computer science, Feature vector, 020207 software engineering, Pattern recognition, 02 engineering and technology, LNCS, Digital media, Image (mathematics), Digital image, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, Distortion, 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, Computer vision, Artificial intelligence, business, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing, Curse of dimensionality
Abstract

International audience; This paper presents a complete methodology for designing practical and highly-undetectable stegosystems for real digital media. The main design principle is to minimize a suitably-defined distortion by means of efficient coding algorithm. The distortion is defined as a weighted difference of extended state-of-the-art feature vectors already used in steganalysis. This allows us to "preserve" the model used by steganalyst and thus be undetectable even for large payloads. This framework can be efficiently implemented even when the dimensionality of the feature set used by the embedder is larger than 10^{7}. The high dimensional model is necessary to avoid known security weaknesses. Although high-dimensional models might be problem in steganalysis, we explain, why they are acceptable in steganography. As an example, we introduce HUGO, a new embedding algorithm for spatial-domain digital images and we contrast its performance with LSB matching. On the BOWS2 image database and in contrast with LSB matching, HUGO allows the embedder to hide 7\times longer message with the same level of security level.

Published
2010

155. Intégration des facteurs humains dans l'expérimentation des interfaces cerveau machine

Author

Leclercq, Stéphanie, Bekaert, Marie-Hélène, Lecocq, Claudine, Service d'ergothérapie, Hôpital Swynghedauw, Centre Hospitalier Régional Universitaire [Lille] (CHRU Lille), LAGIS-SI, Laboratoire d'Automatique, Génie Informatique et Signal (LAGIS), Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS), IFRATH, P. G. J. Lopez Krahe, C. Berger-Vachon, Ed, Bekaert, Marie-Hélène, and IFRATH, P. G. J. Lopez Krahe, C. Berger-Vachon, Ed

Subjects
BMI, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, [INFO.INFO-TS] Computer Science [cs]/Signal and Image Processing, ergonomie des systèmes d'assistance, [SCCO.NEUR]Cognitive science/Neuroscience, [SCCO.NEUR] Cognitive science/Neuroscience, salle d'expérimentation, [INFO.INFO-HC]Computer Science [cs]/Human-Computer Interaction [cs.HC], [INFO.INFO-HC] Computer Science [cs]/Human-Computer Interaction [cs.HC], aménagement, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing, [SPI.SIGNAL] Engineering Sciences [physics]/Signal and Image processing
Abstract

National audience; La recherche sur les interfaces cerveau machine (Brain Machines Interfaces : BMIs), en plein essor, reste encore aujourd'hui au niveau expérimental et ne permet pas une utilisation efficace des applications BMIs dans la vie quotidienne des personnes handicapées. Pour que le transfert des BMIs, des laboratoires de recherche vers les services cliniques et à plus long terme chez le patient, puisse se faire dans les meilleures conditions, il est non seulement indispensable d'intégrer les facteurs humains lors des expérimentations mais aussi, beaucoup plus en amont, dès la phase d'aménagement des locaux. Notre article présente une étude des différents critères à prendre en compte lors de la création d'une salle d'expérimentation BMI et lors de la définition des protocoles expérimentaux. Le travail présenté met en évidence la complexité et la nécessité d'une approche globale et pluridisciplinaire afin de placer les facteurs humains au centre de la réflexion.

Published
2010

156. Mueller matrix interpolation in polarization optics

Author

Vincent Devlaminck, LAGIS-SI, Laboratoire d'Automatique, Génie Informatique et Signal (LAGIS), and Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)

Subjects
010302 applied physics, Physical model, business.industry, Computer science, Polarimetry, Image processing, Optical polarization, Polarization (waves), 01 natural sciences, Atomic and Molecular Physics, and Optics, Electronic, Optical and Magnetic Materials, 010309 optics, Optics, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, 0103 physical sciences, Euclidean geometry, Computer Vision and Pattern Recognition, Mueller calculus, OCIS codes: 260.5430, 120.5410, 100.4995, business, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing
Abstract

International audience; The question of the physical significance of the Mueller matrix average is addressed by means of an analysis of interpolation processes. We draw a comparison between two interpolation processes. The first one is related to the classical Euclidean metrics and the second one is based on the log-Euclidean metrics. Both the associated interpolation procedures are depicted with their underlying physical models. Addressing the question of the physical meaning of the log-Euclidean process of interpolation is founded on a very similar approach to the layered-medium interpretation proposed by Jones [J. Opt. Soc. Am. 38, 671 (1948)] in the seventh paper of his series. Based on the analysis of their respective properties, we eventually show that the choice between both these interpolation processes may depend on what statistical situation is considered or what underlying physical model is assumed.

Published
2010

157. System and method for partial LCVR Stokes polarimeter thermal drift compensation

Author

Vincent Devlaminck, Jean-Michel Charbois, Patrick Terrier, LAGIS-SI, Laboratoire d'Automatique, Génie Informatique et Signal (LAGIS), Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS), and EPJ Web of Conferences

Subjects
Physics, business.industry, QC1-999, Polarimeter, 02 engineering and technology, 01 natural sciences, Ray, Compensation (engineering), 010309 optics, symbols.namesake, 020210 optoelectronics & photonics, Optics, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, Liquid crystal, 0103 physical sciences, Thermal, 0202 electrical engineering, electronic engineering, information engineering, symbols, Reflection (physics), Stokes parameters, Charge-coupled device, business, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing, ComputingMilieux_MISCELLANEOUS
Abstract

In this paper we deal with the problem of thermal drift when using a LCVR (liquid crystal variable retarder) Stokes polarimeter. We address this problem in the restricted case of using a polarimeter to estimate partially linearly polarized light (that corresponds for example to the reflection of an unpolarized incident light on manufactured objects). Usually, the three parameters (S0, S1 and S2) are estimated by observing the reflected light wave, with a CCD sensor, through the LCVR polarimeter. The accuracy of the Stokes parameters estimate is then directly related to precise adjustment of the retardation. The problem is that the retardation introduced by a liquid crystal, variable retarder is strongly dependent on external factors (i.e. temperature). So, it is almost impossible to guarantee the reliability of the retardation in time and in practice it is either necessary to calibrate the LCVR just before carrying out measurement or use a thermostatic control. So, in this paper we propose a solution that does not care about the thermal drift of the LCVR to estimate accurately partially linearly polarized light without thermostatic control.

Published
2010

158. The BCI group in LAGIS at Lille university

Author

Cabestaing, François, Bekaert, Marie-Hélène, Botte-Lecocq, Claudine, LAGIS-SI, Laboratoire d'Automatique, Génie Informatique et Signal (LAGIS), Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS), and Cabestaing, François

Subjects
[INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, [INFO.INFO-TS] Computer Science [cs]/Signal and Image Processing, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing, [SPI.SIGNAL] Engineering Sciences [physics]/Signal and Image processing
Abstract

id:166; Since 2005, when BCI research activities started in our lab -- dealing with classification methods for the P300 Speller [1] -- we have mostly focused our attention on the development of palliative communication interfaces. Like in many labs our BCIs are based on EEG signal analysis, as much from the experimental point of view as from the scientific one. First, we will present the experimental goals of our group in terms of palliation of motor handicap. Then, we will present our scientific contribution to the development of BCI interfaces. These studies have been started thanks to several partners involved in different projects that we will finally clarify.

Published
2010

159. Studies on DPM for the density estimation of pseudorange noises and evaluations on real data

Author

Emmanuel Duflos, Nicolas Viandier, Juliette Marais, Asma Rabaoui, Laboratoire Électronique Ondes et Signaux pour les Transports (IFSTTAR/LEOST), Institut Français des Sciences et Technologies des Transports, de l'Aménagement et des Réseaux (IFSTTAR)-PRES Université Lille Nord de France, Laboratoire de l'intégration, du matériau au système (IMS), Université Sciences et Technologies - Bordeaux 1-Institut Polytechnique de Bordeaux-Centre National de la Recherche Scientifique (CNRS), Sequential Learning (SEQUEL), Laboratoire d'Informatique Fondamentale de Lille (LIFL), Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Laboratoire d'Automatique, Génie Informatique et Signal (LAGIS), Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Inria Lille - Nord Europe, Institut National de Recherche en Informatique et en Automatique (Inria), LAGIS-SI, Laboratoire d'Automatique, Génie Informatique et Signal (LAGIS), Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS), Université Sciences et Technologies - Bordeaux 1 (UB)-Institut Polytechnique de Bordeaux-Centre National de la Recherche Scientifique (CNRS), Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Inria Lille - Nord Europe, Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire d'Automatique, Génie Informatique et Signal (LAGIS), and Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)

Subjects
Sequential estimation, Computer science, GPS, Pseudorange, 020206 networking & telecommunications, 02 engineering and technology, Density estimation, 01 natural sciences, Bayes Non Parametric, 010104 statistics & probability, Noise, symbols.namesake, Additive white Gaussian noise, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, GNSS applications, Dirichlet Process Mixture, 11. Sustainability, 0202 electrical engineering, electronic engineering, information engineering, symbols, Electronic engineering, Satellite navigation, 0101 mathematics, Particle filter, Algorithm, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing
Abstract

International audience; GNSS localization is accurate in clear environment where the pseudorange noise distributions are assumed white- Gaussian. But in constricted environment, e.g. dense urban environment, because of the signal reflections on the surrounding obstacles, this assumption cannot be used and accuracy and continuity of service of GNSS receivers are strongly degraded. To enhance the localization performances, we propose to use Dirichlet Process Mixtures to model the pseudorange error density at each acquisition step. Next, this estimation will be used in Rao-Blackwellized Particle Filter to compute the position. This sequential estimation is adapted when the noise is non-stationary. This approach will be tested on real data acquired by a single frequency receiver.

Published
2010

160. Belief Function Based Algorithm for Material Detection and Tracking in Construction

Author

Duflos, Emmanuel, Vanheeghe, Philippe, Razavi, Saiedeh, Haas, Carl, Sequential Learning (SEQUEL), Laboratoire d'Informatique Fondamentale de Lille (LIFL), Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Laboratoire d'Automatique, Génie Informatique et Signal (LAGIS), Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Inria Lille - Nord Europe, Institut National de Recherche en Informatique et en Automatique (Inria), LAGIS-SI, Laboratoire d'Automatique, Génie Informatique et Signal (LAGIS), Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS), Department of Civil and Environmental Engineering [Waterloo], University of Waterloo [Waterloo], Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Inria Lille - Nord Europe, Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire d'Automatique, Génie Informatique et Signal (LAGIS), and Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)

Subjects
Belief Functions, RFID, Construction Materials, GPS, [INFO.INFO-AU]Computer Science [cs]/Automatic Control Engineering, Sensors Network, Dislocation Tracking, Dislocation Detection
Abstract

International audience; Dislocation is defined as the change between discrete sequential locations of critical materials such as special valves or fabricated items, on a large construction project. Dislocations of construction materials on large sites represent critical state changes. Detecting these dislocations in a noisy information environment where low cost Radio Frequency Identification tags are attached to each piece of material, and the material is moved sometimes only a few meters, is the main focus of this study. We propose in this paper a method based on the Transferable Belief Model (TBM) to estimate materials locations and detect dislocations. This method has been implemented and real experiments were carried out. The results of these experiments show the ability of the proposed method to track the materials.

Published
2010

161. Continuous belief functions: singletons plausibility function in conjunctive and disjunctive combination operations of consonant bbds

Author

Vannobel, Jean-Marc, LAGIS-SI, Laboratoire d'Automatique, Génie Informatique et Signal (LAGIS), Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS), and Vannobel, Jean-Marc

Subjects
[SPI.AUTO] Engineering Sciences [physics]/Automatic, [SPI.AUTO]Engineering Sciences [physics]/Automatic
Abstract

International audience; We propose in this paper to reconstruct the plausibility function curve in combination operations on continuous consonant basic belief densities (bbd). First are presented properties of nested focal elements that lead to a set based graphical representation of focal sets. Examples of belief functions for classical pdfs precedes then a proposal of simplification of the plausibility formulation. This is done for singletons in conjunctive and disjunctive combination operations with help of the focal elements properties. Conflict existing between information sources is then evoked with at last some tracks to follow for conflict management.

Published
2010

162. Automatic discounting rate computation using a dissent criterion

Author

Klein, John, Colot, Olivier, LAGIS-SI, Laboratoire d'Automatique, Génie Informatique et Signal (LAGIS), Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS), and Klein, John

Subjects
discounting, ComputerApplications_GENERAL, belief functions, [PHYS.PHYS.PHYS-DATA-AN] Physics [physics]/Physics [physics]/Data Analysis, Statistics and Probability [physics.data-an], [PHYS.PHYS.PHYS-DATA-AN]Physics [physics]/Physics [physics]/Data Analysis, Statistics and Probability [physics.data-an]
Abstract

International audience; An iterative method for automatic discounting rate computation is introduced in this paper. As part of a conjunctive combination of sources, discounting reduces the impact of a source on the result of the fusion. The key problems related to discounting are: what sources must be discounted and up to what degree. We propose a method that jointly tackles these two issues by computing rates using a dissent measure. The dissension of the sources is evaluated by comparing them to the average of their mass functions. Sources very different from others (like sources resulting from outliers) are thus heavily discounted. This discounting process is iterated so as to obtain a minimum distance between the conjunctive combination of the discounted sources and a categorical mass function. The efficiency of the method is evaluated through several simulations.

Published
2010

163. Distance géodésique sur l'espace des matrices de cohérence non singulières en optique de polarisation

Author

Devlaminck, Vincent, Terrier, Patrick, LAGIS-SI, Laboratoire d'Automatique, Génie Informatique et Signal (LAGIS), and Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)

Subjects
[INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing
Published
2010

164. Relations entre posturologie et score EDSS

Author

Antonio Pinti, F. Cavillon, Philippe Gallois, Laurent Peyrodie, Olivier Agnani, Samuel Boudet, LAGIS-SI, Laboratoire d'Automatique, Génie Informatique et Signal (LAGIS), Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS), Faculté Libre de Médecine de Lille (FLM), Université catholique de Lille (UCL), Laboratoire d'Automatique, de Mécanique et d'Informatique industrielles et Humaines - UMR 8201 (LAMIH), Université de Valenciennes et du Hainaut-Cambrésis (UVHC)-Centre National de la Recherche Scientifique (CNRS)-INSA Institut National des Sciences Appliquées Hauts-de-France (INSA Hauts-De-France), Faculté Libre de Médecine (FLM), and Groupe Hospitalier de l'institut Catholique de Lille (GHICL)

Subjects
03 medical and health sciences, signal posturométrique, 0302 clinical medicine, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, 0206 medical engineering, Genetics, Animal Science and Zoology, 02 engineering and technology, EDSS, 020601 biomedical engineering, RQA, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing, 030217 neurology & neurosurgery
Abstract

National audience; Le but de cette étude est d'établir la corrélation entre le niveau de handicap évalué par l'Expanded Disability Status Scale (EDSS) et les données issues d'une plateforme de mesure d'équilibre pour des sujets atteints de Sclérose En Plaques (SEP).La base de données est constituée de 96 patients et de 90 sujets sains appariés par age et sexe. Aucun n'est atteint de troubles orthopédiques. Pour chaque patient le score EDSS a été calculé par le praticien. Pour chaque personne un ensemble d'indices linéaire et non linéaires sont calculés à partir des mesures posturométriques. Résultats : Le test statistique objective des corrélations significatives (p

Published
2010

165. Alpha-stable interference modeling and Cauchy receiver for an IR-UWB ad hoc network

Author

Laurent Clavier, Hamza El Ghannudi, François Septier, Paul-Alain Rolland, Nourddine Azzaoui, Institut d’Électronique, de Microélectronique et de Nanotechnologie - UMR 8520 [IEMN], Institut d’Électronique, de Microélectronique et de Nanotechnologie - UMR 8520 (IEMN), Centrale Lille-Institut supérieur de l'électronique et du numérique (ISEN)-Université de Valenciennes et du Hainaut-Cambrésis (UVHC)-Université de Lille-Centre National de la Recherche Scientifique (CNRS)-Université Polytechnique Hauts-de-France (UPHF), Laboratoire Modélisation et Sûreté des Systèmes (LM2S), Institut Charles Delaunay (ICD), Université de Technologie de Troyes (UTT)-Centre National de la Recherche Scientifique (CNRS)-Université de Technologie de Troyes (UTT)-Centre National de la Recherche Scientifique (CNRS), Institut TELECOM/TELECOM Lille1, Institut Mines-Télécom [Paris] (IMT), LAGIS-SI, Laboratoire d'Automatique, Génie Informatique et Signal (LAGIS), and Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)

Subjects
Wireless ad hoc network, Gaussian, 020208 electrical & electronic engineering, Cauchy distribution, Ultra-wideband, 020206 networking & telecommunications, 02 engineering and technology, Impulse (physics), Topology, symbols.namesake, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, Heavy-tailed distribution, 0202 electrical engineering, electronic engineering, information engineering, Bit error rate, symbols, Electronic engineering, Electrical and Electronic Engineering, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing, Random variable, Computer Science::Information Theory, Mathematics
Abstract

International audience; In this paper we investigate ad hoc networks based on impulse radio ultra wideband. Due to multiple access, the interference distribution is not Gaussian. One important reason for errors is the presence of close interferers generating pulse collision. However such events are rare and we propose an α-stable model compatible with this fact due to its heavy tailed distribution. We derive the analytical expression of the two significant parameters. They depend on the attenuation coefficient, the users' density, the pulse collision probability and the pulse shape. We finally propose receiver strategies (Cauchy receiver and p-norm) that outperforms the classical Gaussian receiver.

Published
2010

166. Pilot-aided sequential Monte Carlo estimation of phase distortions and transmitted symbols in multicarrier systems

Author

Christelle Garnier, Yves Delignon, Atika Menhaj-Rivenq, François Septier, Institut d’Électronique, de Microélectronique et de Nanotechnologie - UMR 8520 (IEMN), Centrale Lille-Institut supérieur de l'électronique et du numérique (ISEN)-Université de Valenciennes et du Hainaut-Cambrésis (UVHC)-Université de Lille-Centre National de la Recherche Scientifique (CNRS)-Université Polytechnique Hauts-de-France (UPHF), Signal Processing Laboratory, University of Cambridge, University of Cambridge [UK] (CAM), LAGIS-SI, Laboratoire d'Automatique, Génie Informatique et Signal (LAGIS), Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS), Institut TELECOM/TELECOM Lille1, Institut Mines-Télécom [Paris] (IMT), Institut d’Électronique, de Microélectronique et de Nanotechnologie - UMR 8520 [IEMN], and Apollo - University of Cambridge Repository

Subjects
Computer engineering. Computer hardware, General Computer Science, Mean squared error, Article Subject, Orthogonal frequency-division multiplexing, Computer science, 02 engineering and technology, Data_CODINGANDINFORMATIONTHEORY, TK7885-7895, 0203 mechanical engineering, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, Robustness (computer science), 0202 electrical engineering, electronic engineering, information engineering, Electronic engineering, Electrical and Electronic Engineering, 40 Engineering, Computer Science::Information Theory, Estimator, 020302 automobile design & engineering, 020206 networking & telecommunications, 3. Good health, Nonlinear system, Autoregressive model, Signal Processing, Bit error rate, Particle filter, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing, 4006 Communications Engineering
Abstract

International audience; We address the challenging problem of the joint estimation of transmitted symbols and phase distortions in standardized multicarrier systems, including pilot or virtual subcarriers. These subcarriers create time correlation on the useful transmitted OFDM signal that we propose to take into account by an autoregressive model. Because the phase distortions are nonlinear, we set the joint estimation algorithm on the framework of the Sequential Monte Carlo methods. Simulation results are provided in terms of bit error rate (BER) and mean square error (MSE); they highlight the efficiency and the robustness of the estimator.

Published
2010

167. Nonlinear functional regression: a functional RKHS approach

Author

Kadri, H., Duos, E., Preux, P., Stéphane Canu, Davy, M., KADRI, Hachem, Programme 'blanc' - Apprentissage et noyaux pour la représentation et la décision en traitement du signal - - KERNSIG2006 - ANR-06-BLAN-0078 - BLANC - VALID, Sequential Learning (SEQUEL), Laboratoire d'Informatique Fondamentale de Lille (LIFL), Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Laboratoire d'Automatique, Génie Informatique et Signal (LAGIS), Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Inria Lille - Nord Europe, Institut National de Recherche en Informatique et en Automatique (Inria), LAGIS-SI, Laboratoire d'Automatique, Génie Informatique et Signal (LAGIS), Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS), Groupe de Recherche en Apprentissage Automatique (GRAppA - LIFL), Université de Lille, Sciences et Technologies-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS), Laboratoire d'Informatique, de Traitement de l'Information et des Systèmes (LITIS), Université Le Havre Normandie (ULH), Normandie Université (NU)-Normandie Université (NU)-Université de Rouen Normandie (UNIROUEN), Normandie Université (NU)-Institut national des sciences appliquées Rouen Normandie (INSA Rouen Normandie), Institut National des Sciences Appliquées (INSA)-Normandie Université (NU)-Institut National des Sciences Appliquées (INSA), ANR-06-BLAN-0078,KERNSIG,Apprentissage et noyaux pour la représentation et la décision en traitement du signal(2006), Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Inria Lille - Nord Europe, Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire d'Automatique, Génie Informatique et Signal (LAGIS), and Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)

Subjects
[INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, [INFO.INFO-TS] Computer Science [cs]/Signal and Image Processing, [INFO.INFO-LG] Computer Science [cs]/Machine Learning [cs.LG], [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing, [SPI.SIGNAL] Engineering Sciences [physics]/Signal and Image processing
Abstract

International audience; This paper deals with functional regression, in which the input attributes as well as the response are functions. To deal with this problem, we develop a functional reproducing kernel Hilbert space approach; here, a kernel is an operator acting on a function and yielding a function. We demonstrate basic properties of these functional RKHS, as well as a representer theorem for this setting; we investigate the construction of kernels; we provide some experimental insight.

Published
2010

168. Fuzzy filter based on interval-valued fuzzy sets for image filtering

Author

André Bigand, Olivier Colot, Laboratoire d'Informatique Signal et Image de la Côte d'Opale (LISIC), Université du Littoral Côte d'Opale (ULCO), LAGIS-SI, Laboratoire d'Automatique, Génie Informatique et Signal (LAGIS), and Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)

Subjects
0209 industrial biotechnology, Mathematical optimization, Logic, Fuzzy set, Image processing, 02 engineering and technology, Impulse noise, Fuzzy logic, Composite image filter, symbols.namesake, 020901 industrial engineering & automation, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, Artificial Intelligence, 0202 electrical engineering, electronic engineering, information engineering, Median filter, ComputingMilieux_MISCELLANEOUS, Mathematics, business.industry, Pattern recognition, Filter (signal processing), Gaussian noise, symbols, 020201 artificial intelligence & image processing, Artificial intelligence, business, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing
Abstract

A new fuzzy image filter controlled by interval-valued fuzzy sets (IVFS) is proposed for removing noise from images. The proposed approach is based on IVFS entropy application. IVFS makes it possible to take into account the total uncertainty inherent to image processing, and particularly noise removal is considered. Interval-valued fuzzy sets entropy is used as a tool to perform histogram analysis in order to find all major homogeneous regions at the first stage. Then, an efficient peak-finding algorithm is employed to identify the most significant peaks of the histogram (1) and a noise filtering process (2) that estimates the original value of each noisy pixel (utilizing the global information from (1) and the local information of the image pixels) is proposed. Experimental results have demonstrated that the proposed filter can outperform some well-known classical and fuzzy filters in preserving image details while suppressing impulse noise and reducing Gaussian noise. The main advantage of the proposed technique is to restrict the number of thresholds or parameters which have to be tuned.

Published
2010

169. Corpus Callosum deformation analysis in Multiple Sclerosis

Author

Derraz, Foued, Pinti, Antonio, Lenne, Bruno, Peyrodie, Laurent, Chikh, Azzeddine, Taleb-Ahmed, Abdelmalik, Hautecoeur, Patrick, Groupe Hospitalier de l'institut Catholique de Lille (GHICL), Université catholique de Lille (UCL), Laboratoire d'Automatique, de Mécanique et d'Informatique industrielles et Humaines - UMR 8201 (LAMIH), Université de Valenciennes et du Hainaut-Cambrésis (UVHC)-Centre National de la Recherche Scientifique (CNRS)-INSA Institut National des Sciences Appliquées Hauts-de-France (INSA Hauts-De-France), LAGIS-SI, Laboratoire d'Automatique, Génie Informatique et Signal (LAGIS), Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS), and Laboratoire de recherches Génie Biomédicale (GBM Lab)

Subjects
Image processing, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing
Abstract

nombre de pages : 15; International audience; In this paper, we propose a new methodology for analyzing the deformations of the Corpus Callosum (CC) volume associated to Multiple Sclerosis (MS) lesion. We propose an approach for 3D segmentation of the volume of interest based on deformable models method. The measures are carried from the segmented brain volume obtained from MR and the deformation of the geometric shape is quantified. The deformations of the two ends as well as the thickness of the CC were retained to validate the method. The results allow evaluating the rate of deformation of the CC among patients from MRI sequences of patients with different level from handicap using the criterion established in this paper.

Published
2010

170. Focusing on human factors while designing a BMI room

Author

Leclercq, Stéphanie, Bekaert, Marie-Hélène, Botte-Lecocq, Claudine, Cabestaing, François, Bekaert, Marie-Hélène, Service d'ergothérapie, Hôpital Swynghedauw, Centre Hospitalier Régional Universitaire [Lille] (CHRU Lille), LAGIS-SI, Laboratoire d'Automatique, Génie Informatique et Signal (LAGIS), and Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)

Subjects
BMI, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, [INFO.INFO-TS] Computer Science [cs]/Signal and Image Processing, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing, Assisting system ergonomics, experimentation room fitting, [SPI.SIGNAL] Engineering Sciences [physics]/Signal and Image processing
Abstract

International audience; The research in Brain Machine Interfaces (BMIs), although in rapid expansion, must still be considered at the experimental level since no widely available BMI system exists for helping people with motor disabilities in everyday life. Transferring BMI applications from laboratories to dedicated clinical services - and later to patient homes - implies, first of all, the specification of perfectly adapted experimental conditions including all the human factors. Our paper surveys various criteria that must be taken into account while designing a room dedicated to BMI experimentation from the ergonomic point of view, as well as adapted experimental protocols. This related work emphasizes the need and the complexity of a global and multidisciplinary approach which places human factors at the centre of the concerns.

Published
2010

171. User-focused design of a BCI experimentation room

Author

Botte-Lecocq, Claudine, Leclercq, Stéphanie, Bekaert, Marie-Hélène, Cabestaing, François, Cabestaing, François, LAGIS-SI, Laboratoire d'Automatique, Génie Informatique et Signal (LAGIS), Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS), and Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)

Subjects
[INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, [INFO.INFO-TS] Computer Science [cs]/Signal and Image Processing, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing, [SPI.SIGNAL] Engineering Sciences [physics]/Signal and Image processing
Abstract

id:198; Today, various experimental BCI systems offer many types of applications to help users overcome a major physical disability by restoring communication, mobility, object handling... Although in rapid expansion, this research field must still be considered at the experimental level, since no widely available BCI system exists for helping people with motor disabilities.

Published
2010

172. On the use of Dirichlet process mixtures for the modelling of pseudorange errors in multi-constellation based localisation

Author

Emmanuel Duflos, Nicolas Viandier, Juliette Marais, Asma Rabaoui, Laboratoire de l'intégration, du matériau au système (IMS), Université Sciences et Technologies - Bordeaux 1 (UB)-Institut Polytechnique de Bordeaux-Centre National de la Recherche Scientifique (CNRS), Laboratoire Électronique Ondes et Signaux pour les Transports (IFSTTAR/LEOST), Institut Français des Sciences et Technologies des Transports, de l'Aménagement et des Réseaux (IFSTTAR)-PRES Université Lille Nord de France, Sequential Learning (SEQUEL), Laboratoire d'Informatique Fondamentale de Lille (LIFL), Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Inria Lille - Nord Europe, Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire d'Automatique, Génie Informatique et Signal (LAGIS), Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Centrale Lille-Centre National de la Recherche Scientifique (CNRS), LAGIS-SI, Laboratoire d'Automatique, Génie Informatique et Signal (LAGIS), Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS), Université Sciences et Technologies - Bordeaux 1-Institut Polytechnique de Bordeaux-Centre National de la Recherche Scientifique (CNRS), Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Laboratoire d'Automatique, Génie Informatique et Signal (LAGIS), Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Inria Lille - Nord Europe, and Institut National de Recherche en Informatique et en Automatique (Inria)

Subjects
business.industry, Computer science, GPS, Pseudorange, 020206 networking & telecommunications, 02 engineering and technology, 01 natural sciences, Bayes Non Parametric, Dirichlet process, 010104 statistics & probability, Noise, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, GNSS applications, Dirichlet Process Mixture, Statistics, 0202 electrical engineering, electronic engineering, information engineering, Global Positioning System, Satellite navigation, 0101 mathematics, business, Particle filter, Algorithm, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing, Multipath propagation
Abstract

International audience; In Global Navigation Satellite Systems (GNSS) positioning, the receiver measures the pseudoranges with respect to each observable navigation satellite and determines the user position. The use of many constellations should lead to highly available, highly accurate navigation anywhere. However, it is important to notice that even if modern receivers achieve high position accuracy in line-of-sight (LOS) conditions, multipath propagation highly degrades positioning performances even in multi-constellation based localisation (¿GPS + Galileo¿ for instance). In urban area, some obstacles (cars, pedestrians, etc) can appear suddenly and thus can induce a random error in the pseudorange measure. We address here the case where the noise probability density functions are of unknown functional form. A flexible Bayesian nonparametric noise model based on Dirichlet process mixtures (DPM) is introduced. Hence, the paper will contain two main parts. The first part focuses on the modelling of the pseudorange noises using DPMs and its suitability in the estimation problem handled by an efficient particle filter. The other part contains interesting validation schemes.

Published
2009

173. Enhancement of Galileo and multi-constellation accuracy by modeling pseudorange noises

Author

Nicolas Viandier, Emmanuel Duflos, Asma Rabaoui, Juliette Marais, Laboratoire Électronique Ondes et Signaux pour les Transports (IFSTTAR/LEOST), Institut Français des Sciences et Technologies des Transports, de l'Aménagement et des Réseaux (IFSTTAR)-PRES Université Lille Nord de France, Laboratoire de l'intégration, du matériau au système (IMS), Université Sciences et Technologies - Bordeaux 1-Institut Polytechnique de Bordeaux-Centre National de la Recherche Scientifique (CNRS), Sequential Learning (SEQUEL), Laboratoire d'Informatique Fondamentale de Lille (LIFL), Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Laboratoire d'Automatique, Génie Informatique et Signal (LAGIS), Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Inria Lille - Nord Europe, Institut National de Recherche en Informatique et en Automatique (Inria), LAGIS-SI, Laboratoire d'Automatique, Génie Informatique et Signal (LAGIS), Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS), Université Sciences et Technologies - Bordeaux 1 (UB)-Institut Polytechnique de Bordeaux-Centre National de la Recherche Scientifique (CNRS), Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Inria Lille - Nord Europe, Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire d'Automatique, Génie Informatique et Signal (LAGIS), and Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)

Subjects
Computer science, GPS, Real-time computing, 02 engineering and technology, 01 natural sciences, 010104 statistics & probability, symbols.namesake, Extended Kalman filter, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, Pseudorange, 11. Sustainability, 0202 electrical engineering, electronic engineering, information engineering, Galileo (satellite navigation), Computer vision, 0101 mathematics, business.industry, 020206 networking & telecommunications, Kalman filter, Noise, GNSS applications, Physics::Space Physics, symbols, Global Positioning System, Satellite navigation, Artificial intelligence, business, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing
Abstract

International audience; Satellite-based positioning systems do not offer accurate solutions in urban environments because of propagation disturbances noising measurements. Furthermore, usual positioning computation, like extended Kalman filter, relies on considering the noise as a Gaussian centered distribution, which is unrealistic in constrained area. Moreover, today only the US system (GPS) is fully operational. Available satellite signals are not always sufficient to guarantee a continuity of service in all environments and more particularly in urban environment. However, new satellite navigation systems will appear in a couple of years. These new constellations will provide more satellites and signals. In this paper, at first, we highlight the improvement using GPS in complement with Galileo. Next, we propose a modeling of propagation noises function of the satellite state of reception, and we explain its use in the filtering process. And finally, we show some simulations results.

Published
2009

174. Modélisation de visages par un réseau d'ondelettes de Gabor

Author

Chaari, Ahmed, Cabestaing, François, Sellami-Masmoudi, Dorra, Intelligent Control, design & Optimization of complex Systems (ICOS), Université de Sfax - University of Sfax-École Nationale d'Ingénieurs de Sfax | National School of Engineers of Sfax (ENIS), LAGIS-SI, Laboratoire d'Automatique, Génie Informatique et Signal (LAGIS), Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS), and GRETSI, Groupe d'Etudes du Traitement du Signal et des Images

Subjects
[INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing
Abstract

International audience; Nous proposons une nouvelle méthode de codage d'une image d'un visage par un réseau d'ondelettes de Gabor. Ce type de réseau permet d'approcher toute fonction par une combinaison linéaire d'ondelettes de Gabor auxquelles sont associées des poids. Les paramètres du réseau, à savoir les poids et les coefficients intervenant dans la définition des ondelettes de Gabor, sont déterminés par apprentissage. Dans notre méthode, nous associons un indice de confiance à chaque ondelette, lequel permet d'accorder plus d'importance aux ondelettes les plus signicatives. Le coefficient de confiance est déterminé en étudiant les évolutions des paramètres de l'ondelette au cours de l'apprentissage, étape qui dans notre cas fait intervenir plusieurs images du visage d'un même individu avec différentes expressions faciales. Le masque obtenu par combinaison des amplitudes des ondelettes pondérées par les coefficients de confiance indique les zones du visage contenant des indices caractéristiques fiables pour la reconnaissance.

Published
2009

175. Steganalysis by Subtractive Pixel Adjacency Matrix

Author

Jessica Fridrich, Tomáš Pevný, Patrick Bas, GIPSA - Communication, Signal et Sécurité (GIPSA-C2S), Département Images et Signal (GIPSA-DIS), Grenoble Images Parole Signal Automatique (GIPSA-lab), Université Stendhal - Grenoble 3-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS)-Université Stendhal - Grenoble 3-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS)-Grenoble Images Parole Signal Automatique (GIPSA-lab), Université Stendhal - Grenoble 3-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS)-Université Stendhal - Grenoble 3-Université Pierre Mendès France - Grenoble 2 (UPMF)-Université Joseph Fourier - Grenoble 1 (UJF)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP )-Centre National de la Recherche Scientifique (CNRS), Binghamton University [SUNY], State University of New York (SUNY), ANR-06-SETI-0009,NEBIANNO,Sécurité et fiabilité des techniques de tatouages(2006), Czech Technical University in Prague (CTU), LAGIS-SI, Laboratoire d'Automatique, Génie Informatique et Signal (LAGIS), Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS), Bas, Patrick, and Programme 'Sécurité et Informatique - Sécurité et fiabilité des techniques de tatouages - - NEBIANNO2006 - ANR-06-SETI-0009 - SETI - VALID

Subjects
Matching (graph theory), [INFO.INFO-TS] Computer Science [cs]/Signal and Image Processing, Computer Networks and Communications, Computer science, Feature extraction, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Feature selection, 02 engineering and technology, Least significant bit, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, Histogram, Computer Science::Multimedia, 0202 electrical engineering, electronic engineering, information engineering, Adjacency matrix, Safety, Risk, Reliability and Quality, [SPI.SIGNAL] Engineering Sciences [physics]/Signal and Image processing, Mathematics, Steganalysis, Markov chain, Pixel, Steganography, business.industry, 020207 software engineering, Pattern recognition, computer.file_format, JPEG, Support vector machine, 020201 artificial intelligence & image processing, Artificial intelligence, business, computer, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing, Curse of dimensionality
Abstract

This paper presents a method for detection of steganographic methods that embed in the spatial domain by adding a low-amplitude independent stego signal, an example of which is least significant bit (LSB) matching. First, arguments are provided for modeling the differences between adjacent pixels using first-order and second-order Markov chains. Subsets of sample transition probability matrices are then used as features for a steganalyzer implemented by support vector machines. The major part of experiments, performed on four diverse image databases, focuses on evaluation of detection of LSB matching. The comparison to prior art reveals that the presented feature set offers superior accuracy in detecting LSB matching. Even though the feature set was developed specifically for spatial domain steganalysis, by constructing steganalyzers for ten algorithms for JPEG images, it is demonstrated that the features detect steganography in the transform domain as well.

Published
2009

176. An approach for the discrimination of moving textures

Author

Boujiha, Tarik, Postaire, Jack-Gérard, Sbihi, Abderrahmane, Mouradi, Aziza, Macaire, Ludovic, LAGIS-SI, Laboratoire d'Automatique, Génie Informatique et Signal (LAGIS), and Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)

Subjects
[INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], ComputingMilieux_MISCELLANEOUS
Abstract

International audience

Published
2009

177. Real world implementation of belief function theory to detect dislocation of materials in construction

Author

Razavi, Saiedeh, Haas, Carl, Vanheeghe, Philippe, Duflos, Emmanuel, Department of Civil and Environmental Engineering [Waterloo], University of Waterloo [Waterloo], Sequential Learning (SEQUEL), Laboratoire d'Informatique Fondamentale de Lille (LIFL), Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Inria Lille - Nord Europe, Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire d'Automatique, Génie Informatique et Signal (LAGIS), Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Centrale Lille-Centre National de la Recherche Scientifique (CNRS), LAGIS-SI, Laboratoire d'Automatique, Génie Informatique et Signal (LAGIS), Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS), Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Laboratoire d'Automatique, Génie Informatique et Signal (LAGIS), Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Inria Lille - Nord Europe, and Institut National de Recherche en Informatique et en Automatique (Inria)

Subjects
Belief Functions, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, GPS, 021105 building & construction, 0211 other engineering and technologies, 0202 electrical engineering, electronic engineering, information engineering, locating, 020201 artificial intelligence & image processing, Proximity Measure, 02 engineering and technology, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing, Dislocation Detection
Abstract

International audience; Dislocations of construction materials on large sites represent critical state changes. The ability to detect dislocations automatically for tens of thousands of items can ultimately improve project performance significantly. A belief function based data fusion algorithm was developed to estimate materials locations and detect dislocations. Dislocation is defined as the change between discrete sequential locations of critical materials such as special valves or fabricated items, on a large construction project. Detecting these dislocations in a noisy information environment where low cost radio frequency identification tags are attached to each piece of material, and the material is moved sometimes only a few meters, is the main focus of this study. This work is a continuation of previous research, in which we tackled the location estimation problem by fusing the data from a simulation model. The results indicate the potential of the belief function based algorithm to detect object dislocation.

Published
2009

178. Radar Optimal Times Detection Allocation in Multitarget Environment

Author

Philippe Vanheeghe, Emmanuel Duflos, M. de Vilmorin, Laboratoire de Génie Informatique et d'Automatique de l'Artois (LGI2A), Université d'Artois (UA), Sequential Learning (SEQUEL), Laboratoire d'Informatique Fondamentale de Lille (LIFL), Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Laboratoire d'Automatique, Génie Informatique et Signal (LAGIS), Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Inria Lille - Nord Europe, Institut National de Recherche en Informatique et en Automatique (Inria), LAGIS-SI, Laboratoire d'Automatique, Génie Informatique et Signal (LAGIS), Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS), Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Inria Lille - Nord Europe, Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire d'Automatique, Génie Informatique et Signal (LAGIS), and Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)

Subjects
Sensor Management, Computer Networks and Communications, Computer science, 0211 other engineering and technologies, Context (language use), 02 engineering and technology, law.invention, Nonlinear programming, Radar Management, law, [INFO.INFO-AU]Computer Science [cs]/Automatic Control Engineering, 0202 electrical engineering, electronic engineering, information engineering, Computer vision, Electrical and Electronic Engineering, Radar, Context model, 021103 operations research, business.industry, Probabilistic logic, 020206 networking & telecommunications, Sensor fusion, Object detection, Computer Science Applications, Detection, Search theory, Control and Systems Engineering, Optimal Temporal Allocation, Artificial intelligence, business, Algorithm, Information Systems
Abstract

International audience; This paper deals with the problem of the management of Electronically Steered Antenna (ESA) in multitarget environments. Radars are used to detect, locate and identify targets. In this paper we focus on the detection of several aerial targets in a fixed given time. The difficulty of such detection lies in the fact that targets may be located anywhere in the space, but radars can only observe a limited part of it at a time. As a result, it is necessary to change their axis position over time. This paper describes the main steps to derive an optimal radar management in this context: the modeling of the radar, the determination of a criterion based on the target detection probability and the temporal optimization process leading to sensor management strategy. An optimization solution is presented for several contexts and several hypotheses about prior knowledge concerning the targets' locations. First, we propose a method for the optimization of the radar detection probability in a single target environment. It consists in the decomposition of the detection step into an optimal number of independent elementary detections. Then, in a multitarget context with deterministic prior knowledge, we present an optimal time allocation method which is based on the results of non linear programming. Finally, in a multitarget context with probabilistic prior knowledge, results in Search Theory are used to determine an optimal temporal allocation.

Published
2009

179. Exploitation de la couleur pour la reconnaissance d'objets

Author

Muselet, Damien, Song, Xiaohu, Macaire, Ludovic, Laboratoire Hubert Curien [Saint Etienne] (LHC), Institut d'Optique Graduate School (IOGS)-Université Jean Monnet [Saint-Étienne] (UJM)-Centre National de la Recherche Scientifique (CNRS), LAGIS-SI, Laboratoire d'Automatique, Génie Informatique et Signal (LAGIS), and Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)

Subjects
[INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing
Published
2009

180. Fusion d'informations dans le cadre de la théorie des fonctions de croyance : applications en imagerie

Author

Colot, Olivier, LAGIS-SI, Laboratoire d'Automatique, Génie Informatique et Signal (LAGIS), Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS), and Colot, Olivier

Subjects
[INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, [INFO.INFO-TS] Computer Science [cs]/Signal and Image Processing, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing, ComputingMilieux_MISCELLANEOUS, [SPI.SIGNAL] Engineering Sciences [physics]/Signal and Image processing
Abstract

National audience

Published
2009

181. Color space selection for color image segmentation by spectral clustering

Author

J. Shi, L. Busin, Ludovic Macaire, Nicolas Vandenbroucke, LAGIS-SI, Laboratoire d'Automatique, Génie Informatique et Signal (LAGIS), and Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)

Subjects
Color histogram, Computer science, Color normalization, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Color balance, 02 engineering and technology, False color, Color space, 03 medical and health sciences, Color depth, 0202 electrical engineering, electronic engineering, information engineering, [INFO]Computer Science [cs], Computer vision, ComputingMilieux_MISCELLANEOUS, ComputingMethodologies_COMPUTERGRAPHICS, 030307 microscopy, 0303 health sciences, Color image, business.industry, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], Pattern recognition, Color quantization, ComputingMethodologies_PATTERNRECOGNITION, Computer Science::Computer Vision and Pattern Recognition, 020201 artificial intelligence & image processing, Artificial intelligence, business
Abstract

In this paper, we propose to segment color images by pixel clustering in a selected color space. This color space is selected among a set of classical color spaces according to a specific criterion based on a spectral clustering analysis. The clusters are determined by analyzing the 3D-histogram of the image coded in the selected color space thanks to a spectral clustering method. This scheme can identify clusters with complex shapes in the color space without any other post/pre-processing stages.

Published
2009

182. Color Stereo Matching Cost Applied to CFA Images

Author

François Cabestaing, Ludovic Macaire, Hachem Halawana, LAGIS-SI, Laboratoire d'Automatique, Génie Informatique et Signal (LAGIS), Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS), Tremeau, A and Schettini, and R and Tominaga

Subjects
Color histogram, Demosaicing, Color image, business.industry, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], Color balance, 020206 networking & telecommunications, 02 engineering and technology, Color co-site sampling, Color depth, 0202 electrical engineering, electronic engineering, information engineering, RGB color model, 020201 artificial intelligence & image processing, Color filter array, Computer vision, Artificial intelligence, business, ComputingMilieux_MISCELLANEOUS, ComputingMethodologies_COMPUTERGRAPHICS, Mathematics
Abstract

Most color stereovision setups include single-sensor cameras which provide Color Filter Array (CFA) images. In those, a single color component is sampled at each pixel rather than the three required ones (R,G,B). We show that standard demosaicing techniques, used to interpolate missing components, are not well adapted when the resulting color pixels are matched for estimating image disparities. In order to avoid this problem while exploiting color information, we propose a new matching cost designed for dense stereovision based on pairs of CFA images.

Published
2009

183. Estimation séquentielle et conjointe du bruit de phase, de l'offset en fréquence et des symboles émis dans les systèmes OFDM

Author

Septier, François, Delignon, Yves, Rivenq, Atika, Garnier, Christelle, Institut d’Électronique, de Microélectronique et de Nanotechnologie - UMR 8520 (IEMN), Centrale Lille-Institut supérieur de l'électronique et du numérique (ISEN)-Université de Valenciennes et du Hainaut-Cambrésis (UVHC)-Université de Lille-Centre National de la Recherche Scientifique (CNRS)-Université Polytechnique Hauts-de-France (UPHF), Signal Processing Laboratory, University of Cambridge [UK] (CAM), LAGIS-SI, Laboratoire d'Automatique, Génie Informatique et Signal (LAGIS), Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS), and Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)

Subjects
[INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing, ComputingMilieux_MISCELLANEOUS
Abstract

International audience

Published
2009

184. Color spaces and image segmentation

Author

Busin, Laurent, Vandenbroucke, Nicolas, Macaire, Ludovic, LAGIS-SI, Laboratoire d'Automatique, Génie Informatique et Signal (LAGIS), and Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)

Subjects
[INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing, ComputingMilieux_MISCELLANEOUS
Abstract

International audience

Published
2008

185. An Effective Active Vision System for Gaze Control

Author

François Cabestaing, Luc Duvieubourg, Yann Ducrocq, Shahram Bahrami, Département Automatique, Ecole d'Ingénieurs du Pas-de-Calais, LAGIS-SI, Laboratoire d'Automatique, Génie Informatique et Signal (LAGIS), Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS), George Bebis et al., Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 (CRIStAL), Centrale Lille-Université de Lille-Centre National de la Recherche Scientifique (CNRS), and Ecole d'Ingénieurs du Pas-de-Calais (EIPC)

Subjects
business.industry, Computer science, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, 020207 software engineering, Field of view, 02 engineering and technology, Gaze, Signal, Saccadic masking, Smooth pursuit, [SPI]Engineering Sciences [physics], [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, 0202 electrical engineering, electronic engineering, information engineering, Eye tracking, 020201 artificial intelligence & image processing, Computer vision, Prism, Artificial intelligence, Active vision, business, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing, ComputingMilieux_MISCELLANEOUS
Abstract

International audience; This paper presents the performances of an active vision system that mimic the human gaze control. A human can shift his gaze either by quickly moving his fixation point or by keeping a moving target in the fovea (high resolution). These two visual phenomena are called saccadic and smooth pursuit eye movements respectively. In order to mimic this human behavior, we have developed a novel active vision system based on a particular stereo-vision setup. It is composed with one camera, one prism and a set of mirrors. To point the field of view of the sensor at a target, the prism is rotated about its axis by a motorized stage. The system is designed for fast and accurate dynamical adjustments of gaze. To study the mechanical performances of our active vision system we have used three different but classical input signals. A step signal that simulates a change of target (saccadic eye movement), a velocity ramp and a sinusoidal signal that simulate a moving target (smooth pursuit). Whatever the input signal, the objective is to maintain the target in the middle of the image. The experiments demonstrate the efficiency of our vision sensor, in term of dynamical properties and measurement accuracy.

Published
2008

186. Using One-Class SVMs and Wavelets for Audio Surveillance

Author

Manuel Davy, Stéphane Rossignol, Asma Rabaoui, Noureddine Ellouze, Ecole Nationale d'Ingénieurs de Tunis (ENIT), Université de Tunis El Manar (UTM), Sequential Learning (SEQUEL), Laboratoire d'Informatique Fondamentale de Lille (LIFL), Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Inria Lille - Nord Europe, Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire d'Automatique, Génie Informatique et Signal (LAGIS), Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Centrale Lille-Centre National de la Recherche Scientifique (CNRS), LAGIS-SI, Laboratoire d'Automatique, Génie Informatique et Signal (LAGIS), Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS), SUPELEC-Campus Metz, Ecole Supérieure d'Electricité - SUPELEC (FRANCE), Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Laboratoire d'Automatique, Génie Informatique et Signal (LAGIS), Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Inria Lille - Nord Europe, and Institut National de Recherche en Informatique et en Automatique (Inria)

Subjects
[SPI.ACOU]Engineering Sciences [physics]/Acoustics [physics.class-ph], Computer Networks and Communications, business.industry, Computer science, Speech recognition, Feature extraction, Word error rate, Wavelet transform, 020206 networking & telecommunications, Pattern recognition, 02 engineering and technology, computer.software_genre, [PHYS.MECA.ACOU]Physics [physics]/Mechanics [physics]/Acoustics [physics.class-ph], Support vector machine, Multiclass classification, Wavelet, 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, Artificial intelligence, Safety, Risk, Reliability and Quality, business, Audio signal processing, Hidden Markov model, computer
Abstract

International audience; This paper presents a method aimed at recognizing environmental sounds for surveillance and security applications. We propose to apply one-class support vector machines (1-SVMs) together with a sophisticated dissimilarity measure in order to address audio classification, and more specifically, sound recognition. We illustrate the performance of this method on an audio database, which consists of 1015 sounds belonging to nine classes. The database used presents high intraclass diversity in temps of signal properties and some kind of interclass similarities. A large discrepancy in the number of items in each class implies nonuniform probability of sound appearances. The method proceeds as follows: first, the use of a set of state-of-the-art audio features is studied. Then, we introduce a set of novel features obtained by combining elementary features. Experiments conducted on a nine-class classification problem show the superiority of this novel sound recognition method. The best recognition accuracy (96.89%) is obtained when combining wavelet-based features, MFCCs, and individual temporal and frequency features. Our 1-SVM-based multiclass classification approach overperforms the conventional hidden Markov model-based system in the experiments conducted, the improvement in the error rate can reach 50%. Besides, we provide empirical results showing that the single-class SVM outperforms a combination of binary SVMs. Additional experiments demonstrate our method is robust to environmental noise.

Published
2008

187. Les interfaces cerveau-ordinateur

Author

Cabestaing, François, LAGIS-SI, Laboratoire d'Automatique, Génie Informatique et Signal (LAGIS), and Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)

Subjects
[INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing
Abstract

International audience; Une interface cerveau-ordinateur est un système qui permet d'instaurer un canal de communication direct entre une personne et un ordinateur, soit en analysant l'activité cérébrale de l'individu (communication homme-machine), soit en stimulant ses canaux sensoriels (communication machine-homme). Dans cette communication, les deux approches seront décrites très brièvement, mais l'accent sera mis sur les interfaces permettant la communication homme-machine. Le domaine d'application privilégié qui sera abordé est celui de la palliation du handicap sévère, notamment des personnes atteintes du syndrome d'enfermement (Locked-In Syndrom). Au niveau physique, le contact entre l'humain et la machine est le plus souvent établi directement ou indirectement par le biais d'une liaison électrique. Par exemple, l'activité corticale d'un individu est mesurable par l'intermédiaire des champs ou des potentiels électriques créés par la propagation des influx nerveux le long des axones des neurones du cortex. Le contact peut être réalisé soit au niveau d'un neurone isolé, soit en plaçant l'électrode à proximité d'un petit groupe de neurones, soit encore en mesurant la combinaison des activités d'un nombre important de neurones en surface du cortex ou sur le scalp. Au niveau logique, il s'agit de transformer les informations brutes issues des mesures de l'activité électrique en caractéristiques plus riches permettant la communication. Dans les interfaces homme-machine, on distingue deux approches particulières, qualifiées de synchrone et d'asynchrone. Dans une interface synchrone, l'utilisateur est soumis à des stimuli envoyés par la machine qui analyse ensuite les propriétés des réponses. Dans une interface asynchrone, l'utilisateur reste le seul maître du processus de communication, la machine se contentant d'analyser les variations, supposées contrôlées par l'individu, de son activité cérébrale. A la fin de cette communication, les travaux menés actuellement au LAGIS (Laboratoire d'Automatique, Génie Informatique et Signal) dans cette thématique seront présentés. L'interface portative assemblée au laboratoire a tout d'abord été utilisée pour la réadaptation fonctionnelle de patients souffrant de douleurs neuropathiques sévères. Il s'agit d'utiliser le neurofeedback afin de permettre au patient de récupérer sa motricité en lui permettant de déporter son attention des mouvements effectivement réalisés par son membre douloureux. Ensuite, le projet de constitution d'une interface non-invasive utilisant des techniques récentes de modélisation floue et de fusion de données sera présenté.

Published
2008

188. Definition of a parametric form of nonsingular Mueller matrices

Author

Vincent Devlaminck, Patrick Terrier, LAGIS-SI, Laboratoire d'Automatique, Génie Informatique et Signal (LAGIS), and Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)

Subjects
02 engineering and technology, 01 natural sciences, law.invention, 010309 optics, Optics, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, Transformation group, law, 0103 physical sciences, Minkowski space, Mueller calculus, Parametric equation, OCIS codes: 260.5430, 120.2130, 120.5410, Mathematics, [PHYS.PHYS.PHYS-OPTICS]Physics [physics]/Physics [physics]/Optics [physics.optics], business.industry, Optical polarization, 021001 nanoscience & nanotechnology, 16. Peace & justice, Polarization (waves), Atomic and Molecular Physics, and Optics, Electronic, Optical and Magnetic Materials, Invertible matrix, Orthogonal group, Computer Vision and Pattern Recognition, 0210 nano-technology, business, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing
Abstract

International audience; The goal of this paper is to propose a mathematical framework to define and analyze a general parametric form of an arbitrary nonsingular Mueller matrix. Starting from previous results about nondepolarizing matrices, we generalize the method to any nonsingular Mueller matrix. We address this problem in a six-dimensional space in order to introduce a transformation group with the same number of degrees of freedom and explain why subsets of O 5,1 , the orthogonal group associated with six-dimensional Minkowski space, is a physically admissible solution to this question. Generators of this group are used to define possible expressions of an arbitrary nonsingular Mueller matrix. Ultimately, the problem of decomposition of these matrices is addressed, and we point out that the "reverse" and "forward" decomposition concepts recently introduced may be inferred from the formalism we propose.

Published
2008

189. An Altered Image Alignment Technique for 3D Motion Estimation of a Reflective Sphere

Author

Y. Bachalany, François Cabestaing, Christophe Vieren, Sébastien Ambellouis, Laboratoire d'Automatique, Génie Informatique et Signal (LAGIS), Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS), LAGIS-SI, Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS), Laboratoire Electronique, Ondes et Signaux pour les Transports (INRETS/LEOST), Institut National de Recherche sur les Transports et leur Sécurité (INRETS), and IEEE

Subjects
business.industry, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, 02 engineering and technology, Tracking (particle physics), Motion (physics), 03 medical and health sciences, 0302 clinical medicine, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, Image texture, Motion field, Computer Science::Computer Vision and Pattern Recognition, Motion estimation, 0202 electrical engineering, electronic engineering, information engineering, Specular highlight, 020201 artificial intelligence & image processing, Computer vision, Artificial intelligence, Specular reflection, business, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing, 030217 neurology & neurosurgery, Image restoration, ComputingMethodologies_COMPUTERGRAPHICS, Mathematics
Abstract

International audience; Recovering 3D motion of reflective objects in image sequences is still a cumbersome problem for computer vision. One common approach is to track geometric features of the object such as contours and edges since they are rather insensitive to light reflections. However, such basic features fail to recover the actual 3D motion in some cases. For example, the external contour of a sphere rotating about one of its axes remains static in the image. In this paper, we propose a new approach to 3D motion recovery of a reflective sphere visible in an image sequence. Instead of tracking only geometric features, our technique makes use of texture information in a slightly modified image alignment method. Unlike in classical image alignment methods, texture information is processed differently whether it comes from a diffuse or a specular light component. Using this technique, we show that motion estimation is not only possible when dealing with reflective objects, but also that specular components can offer information about the 3D motion. Finally, we present some results obtained from the analysis of image sequences.

Published
2008

190. A New Approach to Face Image Coding using Gabor Wavelet Networks

Author

D. Sellami-Masmoudi, A. Chaari, François Cabestaing, Laboratoire d'Automatique, Génie Informatique et Signal (LAGIS), Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS), Intelligent Control, design & Optimization of complex Systems (ICOS), Université de Sfax - University of Sfax-École Nationale d'Ingénieurs de Sfax | National School of Engineers of Sfax (ENIS), LAGIS-SI, Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS), and IEEE

Subjects
Artificial neural network, business.industry, Gabor wavelet, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Wavelet transform, Pattern recognition, 02 engineering and technology, 01 natural sciences, Facial recognition system, Image (mathematics), 010309 optics, Wavelet, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, Face (geometry), 0103 physical sciences, 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, Computer vision, Artificial intelligence, Representation (mathematics), business, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing, Mathematics
Abstract

International audience; In this paper, we describe a new approach to face image coding using Gabor Wavelet Networks (GWN). This type of network yields good results in many signal coding applications and was already used for face representation by Kruger in 2001. The main idea is to approximate the face image, considered as a two dimensional function, with a set of Gabor wavelets. We describe an improved network training technique, which uses several face images of the same person rather than a single one. This technique yields the model of the face image, but also statistical criteria defining the significance of each Gabor wavelet in this model.

Published
2008

191. Gaze control of an active vision system in dynamic scenes

Author

Ducrocq, Yann, Bahrami, Shahram, Duvieubourg, Luc, Cabestaing, François, Département Automatique, Ecole d'Ingénieurs du Pas-de-Calais, LAGIS-SI, Laboratoire d'Automatique, Génie Informatique et Signal (LAGIS), Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS), and Markus Vincze and Danica Kragic and Darius Burschka and Antonis Argyros

Subjects
ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], ComputingMethodologies_COMPUTERGRAPHICS
Abstract

International audience; In this paper, we present an active vision system that imitates the human viewing strategy. We know that gaze control is a major activity in scene observation. In fact, a person instinctively directs his visual fixation point toward regions of interest containing salient information. This information is then acquired by the region of the retina near the center of the field of view, i.e. the fovea. In this region, the acuity and the color sensitivity are higher. In order to mimic this human behavior, we have developed a novel active vision system based on a particular stereovision rig. It is composed with one camera, one prism and a set of mirrors. To direct the fixation point, the prism is rotated about its axis by a motorized stage. The system is designed for accurate dynamical adjustments of gaze and for operating at video rate. To validate our approach to active perception, we have developed a simple observation strategy for a real scene with dynamic objects. We present an experiment on real videos, which show its efficiency.

Published
2008

192. Using a brain-computer interface for rehabilitation : a case study on a patient with implanted electrodes

Author

van Langhenhove, Aurélien, Bekaert, Marie-Hélène, N'Guyen, Jean-Paul, LAGIS-SI, Laboratoire d'Automatique, Génie Informatique et Signal (LAGIS), Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS), Service de neurochirurgie [Nantes], TU Graz/Büroservice, Graz, Austria, Bekaert, Marie-Hélène, and TU Graz/Büroservice, Graz, Austria

Subjects
[INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, [INFO.INFO-TS] Computer Science [cs]/Signal and Image Processing, functional recovery, [SCCO.NEUR]Cognitive science/Neuroscience, [SCCO.NEUR] Cognitive science/Neuroscience, motor rehabilitation, invasive BCI, [INFO.INFO-HC]Computer Science [cs]/Human-Computer Interaction [cs.HC], [INFO.INFO-HC] Computer Science [cs]/Human-Computer Interaction [cs.HC], [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing, [SPI.SIGNAL] Engineering Sciences [physics]/Signal and Image processing
Abstract

International audience; Brain-computer interfaces (BCIs) allow direct communication between men and computers thanks to the analysis of brain activity. Current applications of BCIs in assistive technologies are: palliative communication systems for patients with complete muscular paralysis and restoration of movement for people with a motor in firmity (orthetic or prosthetic devices controlled by the thought). It appears today that brain-computer interfaces can also be used in therapeutic approaches to rehabilitation or functional recovery through neurofeedback. In this paper we briefly review several therapeutic uses of brain-computer interfaces and present a clinical experiment with an hemiparetic patient who has used a BCI as a motor rehabilitation tool.

Published
2008

193. Optimal Policies Search for Sensor Management

Author

Br��hard, Thomas, Duflos, Emmanuel, Vanheeghe, Philippe, Coquelin, Pierre-Arnaud, Sequential Learning (SEQUEL), Laboratoire d'Informatique Fondamentale de Lille (LIFL), Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Laboratoire d'Automatique, Génie Informatique et Signal (LAGIS), Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Inria Lille - Nord Europe, Institut National de Recherche en Informatique et en Automatique (Inria), LAGIS-SI, Laboratoire d'Automatique, Génie Informatique et Signal (LAGIS), Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS), Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Inria Lille - Nord Europe, Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire d'Automatique, Génie Informatique et Signal (LAGIS), and Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)

Subjects
FOS: Computer and information sciences, ACM: G.: Mathematics of Computing/G.3: PROBABILITY AND STATISTICS/G.3.7: Probabilistic algorithms (including Monte Carlo), [STAT.AP]Statistics [stat]/Applications [stat.AP], Stochastic Gradient Estimation, Statistics - Applications, Partially Observable Markov Decision Process, Machine Learning (cs.LG), Computer Science - Learning, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], AESA Radar, Applications (stat.AP), Sensor(s) Management, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing
Abstract

International audience; This paper introduces a new approach to solve sensor management problems. Classically sensor management problems can be well formalized as Partially-Observed Markov Decision Processes (POMPD). The original approach developped here consists in deriving the optimal parameterized policy based on a stochastic gradient estimation. We assume in this work that it is possible to learn the optimal policy off-line (in simulation ) using models of the environement and of the sensor(s). The learned policy can then be used to manage the sensor(s). In order to approximate the gradient in a stochastic context, we introduce a new method to approximate the gradient, based on Infinitesimal Perturbation Approximation (IPA). The effectiveness of this general framework is illustrated by the managing of an Electronically Scanned Array Radar. First simulations results are finally proposed.

Published
2008

194. About the combination of belief functions on real numbers and the fusion based on maximal coherent sets

Author

Vannobel, Jean-Marc, Madiomanana, Ilaitsivery Jacques, Colot, Olivier, LAGIS-SI, Laboratoire d'Automatique, Génie Informatique et Signal (LAGIS), Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS), and Colot, Olivier

Subjects
[INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, [INFO.INFO-TS] Computer Science [cs]/Signal and Image Processing, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing, ComputingMilieux_MISCELLANEOUS, [SPI.SIGNAL] Engineering Sciences [physics]/Signal and Image processing
Abstract

International audience

Published
2008

195. Optimal policies search for sensor management : Application to the ESA radar

Author

Bréhard, Thomas, Coquelin, Pierre-Arnaud, Duflos, Emmanuel, Vanheeghe, Philippe, Sequential Learning (SEQUEL), Laboratoire d'Informatique Fondamentale de Lille (LIFL), Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Inria Lille - Nord Europe, Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire d'Automatique, Génie Informatique et Signal (LAGIS), Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Centrale Lille-Centre National de la Recherche Scientifique (CNRS), LAGIS-SI, Laboratoire d'Automatique, Génie Informatique et Signal (LAGIS), Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS), Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Laboratoire d'Automatique, Génie Informatique et Signal (LAGIS), Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Inria Lille - Nord Europe, and Institut National de Recherche en Informatique et en Automatique (Inria)

Subjects
[INFO.INFO-AU]Computer Science [cs]/Automatic Control Engineering, AESA Radar, Stochastic Gradient Estimation, Sensor(s) Management, Partially Observable Markov Decision Process
Abstract

International audience; This paper introduces a new approach to solve sensor management problems. Classically sensor management problems can be well formalized as partially-observed Markov decision processes (POMPD). The original approach developped here consists in deriving the optimal parameterized policy based on a stochastic gradient estimation. We assume in this work that it is possible to learn the optimal policy off-line (in simulation) using models of the environement and of the sensor(s). The learned policy can then be used to manage the sensor(s). In order to approximate the gradient in a stochastic context, we introduce a new method to approximate the gradient, based on infinitesimal perturbation approximation (IPA). The effectiveness of this general framework is illustrated by the managing of an electronically scanned array radar. First simulations results are finally proposed.

Published
2008

196. Utilisations thérapeutiques des interfaces cerveau-ordinateur

Author

van Langhenhove, Aurélien, Bekaert, Marie-Hélène, N'Guyen, Jean-Paul, LAGIS-SI, Laboratoire d'Automatique, Génie Informatique et Signal (LAGIS), Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS), Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS), Service de neurochirurgie [Nantes], P. G. N. Vigouroux, Ed. Paris : Cépaduès, and Bekaert, Marie-Hélène

Subjects
Interface Cerveau Ordinateur, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, [INFO.INFO-TS] Computer Science [cs]/Signal and Image Processing, [SCCO.NEUR]Cognitive science/Neuroscience, [SCCO.NEUR] Cognitive science/Neuroscience, récupération fonctionnelle, neurofeedback, [INFO.INFO-HC]Computer Science [cs]/Human-Computer Interaction [cs.HC], [INFO.INFO-HC] Computer Science [cs]/Human-Computer Interaction [cs.HC], [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing, [SPI.SIGNAL] Engineering Sciences [physics]/Signal and Image processing
Abstract

National audience; Les interfaces cerveau-ordinateur (BCI : Brain-Computer Interfaces) permettent une communication directe entre l'homme et l'ordinateur. L'activité cérébrale de l'individu est enregistrée, analysée et traduite en commandes destinées à l'ordinateur. Les principales applications actuelles des BCI dans le domaine des technologies de l'assistance sont : l'aide à la communication pour les patients atteints de paralysie musculaire complète et la récupération du mouvement pour les personnes présentant une infirmité motrice (contrôle par la pensée d'une orthèse, d'une prothèse ou d'un robot). Il apparaît aujourd'hui que les interfaces cerveau-ordinateur peuvent également être utilisées dans une approche thérapeutique par neurofeedback dans le cadre d'une rééducation ou d'une récupération fonctionnelle. Dans cette communication, nous passons en revue les diverses utilisations thérapeutiques des systèmes d'interface cerveau-ordinateur. Nous retraçons également une expérience clinique durant laquelle une BCI a été utilisée comme outil d'aide à la rééducation motrice par un patient atteint d'une hémiplégie du coté droit

Published
2008

197. Les interfaces cerveau-machine pour la palliation du handicap moteur sévère

Author

Botte-Lecocq, Claudine, Cabestaing, François, LAGIS-SI, Laboratoire d'Automatique, Génie Informatique et Signal (LAGIS), Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS), and Nadine Vigouroux et Philippe Gorce

Subjects
[INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing
Abstract

National audience; Dans cette communication, nous décrivons le principe des interfaces cerveau-machine et passons en revue leurs domaines d'application pour la palliation d'un handicap moteur sévère. Les interfaces cerveau-machine permettent à un utilisateur d'interagir directement avec une machine sans nécessiter d'action musculaire. De ce fait, elles sont bien adaptées à la palliation des handicaps moteurs, lesquels interdisent au patient tout mouvement volontaire. L'activité cérébrale du patient est enregistrée, analysée puis transformée en commandes. Ces dernières peuvent être utilisées par un système de communication palliative, en général de type clavier virtuel. Ces commandes peuvent également être destinées à un fauteuil roulant permettant à la personne handicapée de récupérer une autonomie partielle.

Published
2008

198. Least committed basic belief density induced by a multivariate Gaussian: Formulation with applications

Author

Philippe Vanheeghe, Branko Ristic, Emmanuel Duflos, François Caron, Advanced Learning Evolutionary Algorithms (ALEA), Inria Bordeaux - Sud-Ouest, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Bordeaux (UB)-Centre National de la Recherche Scientifique (CNRS), Institut de Mathématiques de Bordeaux (IMB), Université Bordeaux Segalen - Bordeaux 2-Université Sciences et Technologies - Bordeaux 1-Université de Bordeaux (UB)-Institut Polytechnique de Bordeaux (Bordeaux INP)-Centre National de la Recherche Scientifique (CNRS), Defence Science and Technology Organisation (DSTO), Defence Science and Technology Organisation, Sequential Learning (SEQUEL), Laboratoire d'Informatique Fondamentale de Lille (LIFL), Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Laboratoire d'Automatique, Génie Informatique et Signal (LAGIS), Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Inria Lille - Nord Europe, Institut National de Recherche en Informatique et en Automatique (Inria), LAGIS-SI, Laboratoire d'Automatique, Génie Informatique et Signal (LAGIS), Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS), Université Bordeaux Segalen - Bordeaux 2-Université Sciences et Technologies - Bordeaux 1 (UB)-Université de Bordeaux (UB)-Institut Polytechnique de Bordeaux (Bordeaux INP)-Centre National de la Recherche Scientifique (CNRS), Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Inria Lille - Nord Europe, Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire d'Automatique, Génie Informatique et Signal (LAGIS), and Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)

Subjects
Target classification, Feature vector, Gaussian, Multivariate normal distribution, Probability density function, Target tracking, 02 engineering and technology, Transferable belief model, Theoretical Computer Science, symbols.namesake, Artificial Intelligence, [INFO.INFO-AU]Computer Science [cs]/Automatic Control Engineering, 0202 electrical engineering, electronic engineering, information engineering, Gaussian process, Multivariate Gaussian pdf, Mathematics, business.industry, Basic belief, Applied Mathematics, 020206 networking & telecommunications, Evidential theory, Belief function theory, symbols, 020201 artificial intelligence & image processing, Artificial intelligence, business, Particle filter, Algorithm, Particle filtering, Software
Abstract

International audience; We consider here the case where our knowledge is partial and based on a betting density function which is n-dimensional Gaussian. The explicit formulation of the least committed basic belief density (bbd) of the multivariate Gaussian pdf is provided in the transferable belief model (TBM) framework. Beliefs are then assigned to hyperspheres and the bbd follows a khi-2 distribution. Two applications are also presented. The first one deals with model based classification in the joint speed-accel- eration feature space. The second is devoted to joint target tracking and classification: the tracking part is performed using a Rao-Blackwellized particle filter, while the classification is carried out within the developed TBM scheme.

Published
2008

199. A Robust Method to Filter Various Types of Artifacts on Long Duration EEG Recordings

Author

Samuel Boudet, Laurent Peyrodie, Christian Vasseur, Philippe Gallois, Equipe de Recherche en Automatique et Systèmes Microélectronique (HEI-ERASM), HEI, LAGIS-SI, Laboratoire d'Automatique, Génie Informatique et Signal (LAGIS), Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS), Saint Philibert (GHICL), Université catholique de Lille (UCL), and Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)

Subjects
genetic structures, Computer science, 02 engineering and technology, Electroencephalography, Signal, 03 medical and health sciences, 0302 clinical medicine, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, adaptive filtering, 0202 electrical engineering, electronic engineering, information engineering, medicine, EEG recordings, Computer vision, Projection (set theory), Short duration, Artifact (error), cerebral signal electrical brain activity, medicine.diagnostic_test, business.industry, Eye movement, 020206 networking & telecommunications, Filter (signal processing), Adaptive filter, Artificial intelligence, business, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing, 030217 neurology & neurosurgery
Abstract

International audience; EEG is a system used to measure electrical brain activity using multiple electrodes placed on the scalp. Unfortunately, the signals can be easily contaminated by noises called artifacts. These can be generated by various actions such as eye blinks, eye movements, muscle activities or small electrode movements. This paper presents a global artifact removal method corresponding to an evolution of the AFOP method (Adaptive Filtering by Optimal Projection) in order to improve its stability. This evolution automatically filters ocular, muscular and heart beat artifacts. The results are validated on long duration EEG recordings containing pathological activities. An expert analysis shows that the cerebral signal is well conserved while a lot of artifacts are removed.

Published
2008

200. Speech recognition with speech density estimation by the dirichlet process mixture

Author

Philippe Vanheeghe, Emmanuel Duflos, K. Ota, M. Yanagida, Laboratoire d'Automatique, Génie Informatique et Signal (LAGIS), Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS), Sequential Learning (SEQUEL), Laboratoire d'Informatique Fondamentale de Lille (LIFL), Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Inria Lille - Nord Europe, Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire d'Automatique, Génie Informatique et Signal (LAGIS), Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Centrale Lille-Centre National de la Recherche Scientifique (CNRS), LAGIS-SI, Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS), Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Université de Lille, Sciences et Technologies-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lille, Sciences Humaines et Sociales-Centre National de la Recherche Scientifique (CNRS)-Laboratoire d'Automatique, Génie Informatique et Signal (LAGIS), Université de Lille, Sciences et Technologies-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Centrale Lille-Centre National de la Recherche Scientifique (CNRS)-Inria Lille - Nord Europe, and Institut National de Recherche en Informatique et en Automatique (Inria)

Subjects
Signal processing, Computer science, Speech recognition, Speech enhancement, 01 natural sciences, 010104 statistics & probability, Extended Kalman filter, symbols.namesake, Stochastic processes, [INFO.INFO-AU]Computer Science [cs]/Automatic Control Engineering, 0101 mathematics, Environmental noise, Gaussian process, Noise (signal processing), 010401 analytical chemistry, Kalman filter, Covariance, Mixture model, 0104 chemical sciences, Dirichlet process, Computer Science::Sound, symbols, Particle filter, Kalman filtering
Abstract

International audience; This paper shows a method for the modeling of speech signal distributions based on Dirichlet process mixtures (DPM) and the estimation of noise sequences based on particle filtering. In real situations, the speech recognition rate degrades miser ably because of the effect of environmental noises, reflected waves and so on. To improve the speech recognition rate, a technique for the estimation of noise sequences is necessary. In this paper, the distribution of the clean speech is modeled using the DPM instead of the traditional model, which is a Gaussian mixture model (GMM). Speech signal sequences are generated according to the mean and covariance generated from the DPM. Then, noise signal sequences are estimated with a particle filter. The proposed method using extended Kalman filter (EKF) can improve the speech recognition rate significantly in the low SNR region. Applying unscented Kalman filter (UKF), better results can be obtained in also the high SNR.

Published
2008

Catalog

Books, media, physical & digital resources
See catalog results