HAL : inria-00590195, version 1

Voir la fiche détaillée

BibTeX,EndNote,... BibTeX - EndNote - TEI - RefWorks -

British Machine Vision Conference (BMVC '05), Oxford : Royaume-Uni (2005)

Articulated Motion Capture from 3-D Points and Normals

Matti Niskanen 1, Edmond Boyer 2, Radu Horaud 2

(2005)

In this paper we address the problem of tracking the motion of articulated objects from their 2-D silhouettes gathered with several cameras. The vast majority of existing approaches relies on a single camera or on stereo. We describe a new method which requires at least two cameras. The method relies on (i) building 3-D observations (points and normals) from image silhouettes and on (ii) fitting an articulated object model to these observations by minimizing their discrepancies. The objective function sums up these discrepancies while it takes into account both the scaled algebraic distance from data points to the model surface and the offset in orientation between observed normals and model normals. The combination of a feed-forward reconstruction technique with a robust model-tracking method results in a reliable and efficient method for articulated motion capture.

1 :	Machine Vision Group (MVG)
	University of Oulu
2 :	PERCEPTION (INRIA Grenoble Rhône-Alpes / LJK Laboratoire Jean Kuntzmann)
	INRIA – Laboratoire Jean Kuntzmann – CNRS : UMR5224 – Université Joseph Fourier - Grenoble I – Institut National Polytechnique de Grenoble (INPG) – Université Pierre-Mendès-France - Grenoble II

Domaine

:

Informatique/Synthèse d'image et réalité virtuelle

inria-00590195, version 1

http://hal.inria.fr/inria-00590195

oai:hal.inria.fr:inria-00590195

Contributeur : Team Perception <>

Déposé pour le compte de : Laure BENAC <>

Soumis le : Mardi 3 Mai 2011, 09:32:55

Dernière modification le : Vendredi 13 Mai 2011, 10:06:26