Monocular Human Motion Capture with a Mixture of Regressors

Ankur Agarwal 1 Bill Triggs 1
1 LEAR - Learning and recognition in vision
GRAVIR - IMAG - Graphisme, Vision et Robotique, Inria Grenoble - Rhône-Alpes, CNRS - Centre National de la Recherche Scientifique : FR71
Abstract : We address 3D human motion capture from monocular images, taking a learning based approach to construct a probabilistic pose estimation model from a set of labelled human silhouettes. To compensate for ambiguities in the pose reconstruction problem, our model explicitly calculates several possible pose hypotheses. It uses locality on a manifold in the input space and connectivity in the output space to identify regions of multi-valuedness in the mapping from silhouette to 3D pose. This information is used to fit a mixture of regressors on the input manifold, giving us a global model capable of predicting the possible poses with corresponding probabilities. These are then used in a dynamicalmodel based tracker that automatically detects tracking failures and re-initializes in a probabilistically correct manner. The system is trained on conventional motion capture data, using both the corresponding real human silhouettes and silhouettes synthesized artificially from several different models for improved robustness to inter-person variations. Static pose estimation is illustrated on a variety of silhouettes. The robustness of the method is demonstrated by tracking on a real image sequence requiring multiple automatic re-initializations.
Type de document :
Communication dans un congrès
Cordelia Schmid and Stefano Soatto and Carlo Tomasi. IEEE Workshop on Vision for Human Computer Interaction at Computer Vision and Pattern Recognition (CVPR '05), Jun 2005, San Diego, United States. IEEE Computer Society, pp.72, 2005, 〈http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1565379〉. 〈10.1109/CVPR.2005.496〉
Liste complète des métadonnées


https://hal.inria.fr/inria-00548522
Contributeur : Thoth Team <>
Soumis le : lundi 20 décembre 2010 - 09:09:02
Dernière modification le : jeudi 11 janvier 2018 - 06:20:04
Document(s) archivé(s) le : lundi 21 mars 2011 - 03:08:41

Identifiants

Collections

IMAG | INRIA | UGA

Citation

Ankur Agarwal, Bill Triggs. Monocular Human Motion Capture with a Mixture of Regressors. Cordelia Schmid and Stefano Soatto and Carlo Tomasi. IEEE Workshop on Vision for Human Computer Interaction at Computer Vision and Pattern Recognition (CVPR '05), Jun 2005, San Diego, United States. IEEE Computer Society, pp.72, 2005, 〈http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1565379〉. 〈10.1109/CVPR.2005.496〉. 〈inria-00548522〉

Partager

Métriques

Consultations de la notice

308

Téléchargements de fichiers

616