281documents trouvés
Underlayed landmarks initialization for monocular SLAM
J.SOLA, A.MONIN, M.DEVY
RAP, MRS
Rapport LAAS N°09071, Mars 2009, 15p.
Diffusable
116755A tuning strategy for face regognition in robotic application
T.GERMA, M.DEVY, R.RIOUX, F.LERASLE
RAP
Manifestation avec acte : International Conference on Computer Vision Theory and Applications (VISAPP 2009), Lisbone (Portugal), 5-8 Février 2009, 8p. , N° 09073
Diffusable
Plus d'informations
Mots-Clés / Keywords
Video-based face recognition; SVM; Tracking; Particle filtering;
Self-calibration constraints on Euclidean bundle adjustment parametrization. Application to the 2 views case
G.GELABERT, M.DEVY, F.LERASLE
RAP
Manifestation avec acte : International Conference on Computer Vision Theory and Applications (VISAPP 2009), Lisbone (Portugal), 5-8 Février 2009, 7p. , N° 09106
Diffusable
Plus d'informations
Mots-Clés / Keywords
Self-calibration; Focal estimation; 3D reconstruction; Bundle adjustment;
Appearance-based and active 3D object recognition using vision
F.J.TRUJILLO ROMERO, M.DEVY
RAP
Manifestation avec acte : International Conference on Computer Vision Theory and Applications (VISAPP 2009), Lisbonne (Portugal), 5-8 Février 2009, 8p. , N° 09107
Diffusable
Plus d'informations
Mots-Clés / Keywords
Recognition; Appearance-based model; active strategy; Robotics;
Registration by using a pseudo color attribute
F.J.TRUJILLO ROMERO, M.DEVY
RAP
Manifestation avec acte : 19th International Conference on Pattern Recognition (ICPR 2008), Tampa (USA), 8-11 Décembre 2008, 4p. , N° 08788
Diffusable
116860An MCMC-based particle filter for multiple person tracking
I.ZURIARRAIN, F.LERASLE, N.ARANA, M.DEVY
RAP, Mondragon
Manifestation avec acte : 19th International Conference on Pattern Recognition (ICPR 2008), Tampa (USA), 8-11 Décembre 2008, 4p. , N° 08361
Diffusable
Plus d'informations
Abstract
This paper presents a Markov Chain Monte Carlo (MCMC) based particle filter to track multiple persons dedicated to video surveillance applications. This hybrid tracker, devoted to networked intelligent cameras, takes benefit from the best properties of both MCMC and joint particle filter. A saliency map-based proposal distribution is shown to limit the well-known burst in terms of particles and MCMC iterations. Qualitative and quantitative results for real-world video data are presented.
Stereo matching and graph cuts
A.ZUREIKI, M.DEVY, R.CHATILA
RAP, RIS
Ouvrage (contribution) : Stereo Matching, N°ISBN 978-953-7619-22-0, Novembre 2008, Chapitre 21, pp.349-372 , N° 08787
Diffusable
116858Landmarks constellation based position estimation for spacecraft pinpoint landing
B.PHAM, S.LACROIX, M.DEVY
RIS, RAP
Manifestation sans acte : ESA Workshop on advanced Space Technologies for Robotics and Automation, Noordwijk (Pays Bas), 11-13 Novembre 2008, 9p. , N° 08831
Diffusable
117866Fusing monocular information in multi-camera SLAM
J.SOLA, A.MONIN, M.DEVY, T.VIDAL CALLEJA
MRS, RAP
Revue Scientifique : IEEE Transactions on Robotics, Vol.24, N°5, pp.958-968, Octobre 2008 , N° 08789
Diffusable
Plus d'informations
Abstract
This paper explores the possibilities of using monocular simultaneous localization and mapping (SLAM) algorithms in systems with more than one camera. The idea is to combine in a single system the advantages of both monocular vision (bearings-only, infinite range observations but no 3-D instantaneous information) and stereovision (3-D information up to a limited range). Such a system should be able to instantaneously map nearby objects while still considering the bearing information provided by the observation of remote ones. We do this by considering each camera as an independent sensor rather than the entire set as a monolithic supersensor. The visual data are treated by monocular methods and fused by the SLAM filter. Several advantages naturally arise as interesting possibilities, such as the desynchronization of the firing of the sensors, the use of several unequal cameras, self-calibration, and cooperative SLAM with several independently moving cameras. We validate the approach with two different applications: a stereovision SLAM system with automatic self-calibration of the rig's main extrinsic parameters and a cooperative SLAM system with two independent free-moving cameras in an outdoor setting.
Mots-Clés / Keywords
Machine vision; Robot vision systems; Stereo vision; Image sequence analysis; Kalman filter; Calibration;
Une architecture parallèle pour la rectification temps réel des images stéréoscopiques
Z.IRKI, M.DEVY
EMP, RAP
Manifestation avec acte : Conférence Internationale Francophone d'Automatique (CIFA 2008), Bucarest (Roumanie), 3-5 Septembre 2008, 6p. , N° 08411
Diffusable
Plus d'informations
Résumé
Dans ce papier on va présenter une architecture pour l'implémentation d'une approche de rectification temps réel des images stéréoscopiques. Cette architecture parallèle repose sur l'utilisation conjointe de plusieurs blocs mémoires dans lesquelles sont mémorisées des données pré calculées relatives aux caméras utilisées pour l'acquisition des images. La réduction des images s'avère indispensable dans l'approche utilisée, l'architecture proposée devra donc réaliser cette tâche en temps réel.
Mots-Clés / Keywords
Rectification des images stéréoscopiques; Temps réel; Réduction des images; Echantillonage; Architecture parallèle;