Learning to Track 3D Human Motion from Silhouettes

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 : This paper describes a sparse Bayesian regression method for recovering 3D human body motion directly from silhouettes extracted from monocular video sequences. No detailed body shape model is needed, and realism is ensured by training on real human motion capture data. The tracker estimates 3D body pose by using Relevance Vector Machine regression to combine a learned autoregressive dynamical model with robust shape descriptors extracted automatically from image silhouettes. We studied several different combination methods, the most effective being to learn a nonlinear observation-update correction based on joint regression with respect to the predicted state and the observations. We demonstrate the method on a 54-parameter full body pose model, both quantitatively using motion capture based test sequences, and qualitatively on a test video sequence.
Type de document :
Communication dans un congrès
Carla E. Brodley. 21st International Conference on Machine Learning (ICML '04), Jul 2004, Banff, Canada. ACM Press, 69, pp.9--16, 2004, 〈http://portal.acm.org/citation.cfm?doid=1015330.1015343〉. 〈10.1145/1015330.1015343〉
Liste complète des métadonnées

Littérature citée [18 références]  Voir  Masquer  Télécharger


https://hal.inria.fr/inria-00548549
Contributeur : Thoth Team <>
Soumis le : lundi 20 décembre 2010 - 09:09:38
Dernière modification le : mercredi 11 avril 2018 - 01:53:38
Document(s) archivé(s) le : lundi 21 mars 2011 - 03:15:27

Identifiants

Collections

IMAG | INRIA | UGA

Citation

Ankur Agarwal, Bill Triggs. Learning to Track 3D Human Motion from Silhouettes. Carla E. Brodley. 21st International Conference on Machine Learning (ICML '04), Jul 2004, Banff, Canada. ACM Press, 69, pp.9--16, 2004, 〈http://portal.acm.org/citation.cfm?doid=1015330.1015343〉. 〈10.1145/1015330.1015343〉. 〈inria-00548549〉

Partager

Métriques

Consultations de la notice

275

Téléchargements de fichiers

564