Estimating Articulated Human Motion With Covariance Scaled Sampling

Cristian Sminchisescu 1 Bill Triggs 1
1 MOVI - Modeling, localization, recognition and interpretation in computer vision
GRAVIR - IMAG - Graphisme, Vision et Robotique, Inria Grenoble - Rhône-Alpes, CNRS - Centre National de la Recherche Scientifique : FR71
Abstract : We present a method for recovering three-dimensional (3D) human body motion from monocular video sequences based on a robust image matching metric, incorporation of joint limits and non-self-intersection constraints, and a new sample-and-refine search strategy guided by rescaled cost-function covariances. Monocular 3D body tracking is challenging: besides the difficulty of matching an imperfect, highly flexible, self-occluding model to cluttered image features, realistic body models have at least 30 joint parameters subject to highly nonlinear physical constraints, and at least a third of these degrees of freedom are nearly unobservable in any given monocular image. For image matching we use a carefully designed robust cost metric combining robust optical flow, edge energy, and motion boundaries. The nonlinearities and matching ambiguities make the parameter-space cost surface multimodal, ill-conditioned and highly nonlinear, so searching it is difficult. We discuss the limitations of CONDENSATION-like samplers, and describe a novel hybrid search algorithm that combines inflated-covariance-scaled sampling and robust continuous optimization subject to physical constraints and model priors. Our experiments on challenging monocular sequences show that robust cost modeling, joint and self-intersection constraints, and informed sampling are all essential for reliable monocular 3D motion estimation.
Type de document :
Article dans une revue
International Journal of Robotics Research, SAGE Publications, 2003, 22 (6), pp.371--391
Liste complète des métadonnées

Littérature citée [53 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/inria-00548242
Contributeur : Thoth Team <>
Soumis le : lundi 20 décembre 2010 - 08:42:14
Dernière modification le : jeudi 11 janvier 2018 - 06:20:04
Document(s) archivé(s) le : lundi 21 mars 2011 - 02:47:55

Fichier

Sminchisescu-ijrr03.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : inria-00548242, version 1

Collections

IMAG | INRIA | UGA

Citation

Cristian Sminchisescu, Bill Triggs. Estimating Articulated Human Motion With Covariance Scaled Sampling. International Journal of Robotics Research, SAGE Publications, 2003, 22 (6), pp.371--391. 〈inria-00548242〉

Partager

Métriques

Consultations de la notice

162

Téléchargements de fichiers

166