Articulated-Body Tracking Through Anisotropic Edge Detection

David Knossow 1 Joost Van de Weijer 2 Radu Horaud 1 Rémi Ronfard 2
1 PERCEPTION - Interpretation and Modelling of Images and Videos
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
2 LEAR - Learning and recognition in vision
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
Abstract : This paper addresses the problem of articulated motion tracking from image sequences. We describe a method that relies on both an explicit parameterization of the extremal contours and on the prediction of the human boundary edges in the image. We combine extremal contour prediction and edge detection in a non linear minimization process. The error function that measures the discrepancy between observed image edges and predicted model contours is minimized using an analytical expression of the Jacobian that maps joint velocities onto extremal contour velocities. In practice, we model people both by their geometry (truncated elliptic cones) and their articulated structure - a kinematic model with 40 rotational degrees of freedom. To overcome the flaws of standard edge detection, we introduce a model-based anisotropic Gaussian filter. The parameters of the anisotropic Gaussian are automatically derived from the kinematic model through the prediction of the extremal contours. The theory is validated by performing full body motion capture from six synchronized video sequences at 30 fps without markers.
Type de document :
Communication dans un congrès
René Vidal and Anders Heyden and Yi Ma. Workshop on Dynamical Vision, May 2006, Graz, Austria. Springer, 4358, pp.86-99, 2007, Lecture Notes in Computer Science. 〈10.1007/978-3-540-70932-9_7〉
Liste complète des métadonnées

Littérature citée [22 références]  Voir  Masquer  Télécharger


https://hal.inria.fr/inria-00544742
Contributeur : Rémi Ronfard <>
Soumis le : samedi 11 décembre 2010 - 08:24:04
Dernière modification le : mercredi 11 avril 2018 - 01:58:29
Document(s) archivé(s) le : samedi 12 mars 2011 - 02:23:12

Fichiers

Identifiants

Citation

David Knossow, Joost Van de Weijer, Radu Horaud, Rémi Ronfard. Articulated-Body Tracking Through Anisotropic Edge Detection. René Vidal and Anders Heyden and Yi Ma. Workshop on Dynamical Vision, May 2006, Graz, Austria. Springer, 4358, pp.86-99, 2007, Lecture Notes in Computer Science. 〈10.1007/978-3-540-70932-9_7〉. 〈inria-00544742〉

Partager

Métriques

Consultations de la notice

812

Téléchargements de fichiers

919