Suivi de gestes temps réel par traitement d’images couleur
Real Time tracking of human gestures using color image processing
OPEN ACCESS
This paper deals with areas detection and tracking using color based image processing. The application adressed concerns human head and hands tracking. We propose an original method in order to locate, for an foreground image, colored areas. Foreground image is provided by a probabilistic way using Gaussian Mixture Models (GMM) of probability density fonctions. The temporal tracking is then achieved by a particle filter, which is well adapted to partial occlusions and non gaussian models.
Résumé
Cet article adresse le problème de la détection et du suivi de zones colorées par traitement d'images couleur. L'application finale concerne le suivi 2D sans marqueurs de la tête et des deux mains d'une personne. Nous proposons une méthode originale de localisation de zones colorées, appliquée à l'issue d'une phase d'extraction de la personne par rapport au fond. L'appartenance d'un pixel de l'image au fond est modélisée par une densité de probabilités exprimée dans un espace couleur. Nous montrons que l'utilisation de mixtures de gaussiennes permet d'approcher cette densité de probabilités. La prise en compte de l'évolution temporelle du système est assurée par un filtre à particules, réputé robuste aux occultations partielles et aux modèles non gaussiens.
Colour image, colored patch tracking, background substraction, particle filter
Mots clés
Imagerie couleur, suivi de zones colorées, soustraction de fond, filtre à particules
[1] A.AGARWAL, B.TRIGGS, 3D Human pose from Silhouettes by Relivance Vector Regression, In To appear in IEEE Internationnal Conference on Computer Vision and Pattern Recognition, 2004.
[2] S.ARULAMPALAM, S.MASKELL, N.GORDON, T.CLAPP, A tutorial on particle filters for on-line non-linear/non-gaussian bayesian tracking, IEEE Transactions on Signal Processing, 50(2):174-188, February 2002.
[3] F.BARDET, T.CHATEAU, F.JURIE, M.NARANJO, Interactions geste-musique par vision artificielle, In Workshop Acquisition du geste humain par vision artificielle, dans RFIA04, Congrès sur la Reconnaissance des Formes et Intelligence Artificielle, Toulouse, January 2004, Actes sur CDROM.
[4] T.CHATEAU, F.JURIE, R.MARC, Reconnaissance de gestes par vision monoculaire en temps réel: application la formation des chargés de manoeuvres pour la conduite des ponts polaires, In Workshop Acquisition du geste humain par vision artificielle, dans RFIA04, Congrès sur la Reconnaissance des Formes et Intelligence Artificielle, Toulouse, January 2004, Actes sur CDROM.
[5] D. COMANICIU, V. RAMESH, P. MEER, Real-time tracking of nonrigid objects using mean shift, Conference on Computer Vision and Pattern Recognition, 2:142-149, 2000.
[6] D. CREMERS, T. KOHLBERGER, C. SCHNÖRR, Nonlinear Shape Statistics in Mumford-Shah Based Segmentation, In 7th European Conference on Computer Vision, volume2, 93-108, Copenhagen, Denmark, May 2002.
[7] D. DEMIRDJIAN, T. DARELL, 3-D Articulated Pose Tracking for Untethered Deictic Reference, In ICMI 2002, Pittsburgh, Pennsylvania, USA, October 2002.
[8] E. MEIER, F. ADE, Using the condensation algorithm to implement tracking for mobile robots, In Third European Workshop on Advanced Mobile Robots, Eurobot99, IEEE, 73-80, 1999.
[9] M.M. FLECK, D.A. FORSYTH, C.BREGLER, Finding naked people, In European Conference on Computer Vision, volume2, 592-602, 1996.
[10] D.M. GAVRILA, The Visual Analysis of Human Movement: A Survey, Computer Vision and Image Understanding, 73(1):82-98, January 1999.
[11] E. HAYMAN, Jan-Olof Eklundh, Statistical background subtraction for a mobile observer, In Int. Conf. Computer Vision, 67-74, Nice, France, 2003.
[12] F.JURIE, M.DHOME, Real time template matching, In Proc. IEEE International Conference on Computer vision, 544-549, Vancouver, Canada, July 2001.
[13] K. NUMMIARO, E. KOLLER-MEIER, L. VAN GOOL, Object Tracking with an Adaptive Color-Based Particle Filter, In Symposium for Pattern Recognition of the DAGM, September 2002.
[14] E.B. KOLLER-MEIER, L.VAN GOOL, Modeling, Recognition of Human Actions Using a Stochastic Approach, In 2nd European Workshop on Advanced Video-based Surveillance Systems AVBS'01, London, 4 September 2001.
[15] M. ISARD, A. BLAKE, Condensation – conditional density propagation for visual tracking, IJCV : International Journal of Computer Vision, 29(1):5-28, 1998.
[16] P. PEREZ, C. HUE, J. VERMAAK, M. GANGNET, Color-Based Probabilistic Tracking, In Computer Vision ECCV 2002, volume1, 661-675, May 2002.
[17] J.SOBOTTKA, I.PITTAS, Segmentation and tracking of faces in color images, In Proceedings of the Second International Conference on Automatic Face and Gesture Recognition, 236-241, 1996.
[18] C.STAUFFER, W.E.L. GRIMSON, Adaptative background mixture models for a real-time tracking, In Conference on Computer Vision and Patern Recognition, volumeII, 246-252, 1999.
[19] A. TRÉMEAU, C. MALOIGNE-FERNANDEZ, and P. BONTON, Image numérique couleur, Dunod, 2004.
[20] M.H. YANG, N.AHUJA, Mark. Tabb, Extraction of 2D Motion trajectories and Its Application to Hand gesture Recognition, IEEE Transactions on Pattern Analysis and Machine Intelligence, 24(8):1061-1074, August 2002.
[21] B.D. ZARIT, Skin detection in video images, Technical report, University of Illinois, Chicagi, 1998.
[22] B.D. ZARIT, B.J. SUPER, K.H. QUEK, Comparison of Five Color Models in Skin Pixel Classification, In ICCV'99 International Workshop on Recognition, Analysing, and Tracking of Faces and Gestures in Real-Time Systems, RATFG-RTS'99, 58-63, Corfu, Greece, September 1999.