Covariance Scaled Sampling for Monocular 3D Body Tracking

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 3D human body motion from monocular video sequences using robust image matching, 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: for reliable tracking at least 30 joint parameters need to be estimated, subject to highly nonlinear physical constraints; the problem is chronically ill conditioned as about 1/3 of the d.o.f. (the depth-related ones) are almost unobservable in any given monocular image; and matching an imperfect, highly flexible self-occluding model to cluttered image features is intrinsically hard. To reduce correspondence ambiguities we use a carefully designed robust matching-cost metric that combines robust optical flow, edge energy, and motion boundaries. Even so, the ambiguity, nonlinearity and non-observability make the parameter-space cost surface multi-modal, unpredictable and ill conditioned, so minimizing it is difficult. We discuss the limitations of CONDENSATION-like samplers, and introduce a novel hybrid search algorithm that combines inflated-covariance-scaled sampling and continuous optimization subject to physical constraints. Experiments on some challenging monocular sequences show that robust cost modelling, joint and self-intersection constraints, and informed sampling are all essential for reliable monocular 3D body tracking.
Type de document :
Communication dans un congrès
International Conference on Computer Vision & Pattern Recognition (CVPR '01), Dec 2001, Kauai, United States. IEEE Computer Society, 1, pp.447--454, 2001, 〈http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=990509〉. 〈10.1109/CVPR.2001.990509〉
Liste complète des métadonnées

Littérature citée [28 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/inria-00548273
Contributeur : Thoth Team <>
Soumis le : lundi 20 décembre 2010 - 08:42:38
Dernière modification le : mercredi 11 avril 2018 - 01:54:30
Document(s) archivé(s) le : jeudi 30 juin 2011 - 13:44:52

Fichier

Sminchisescu-cvpr01.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

IMAG | INRIA | UGA

Citation

Cristian Sminchisescu, Bill Triggs. Covariance Scaled Sampling for Monocular 3D Body Tracking. International Conference on Computer Vision & Pattern Recognition (CVPR '01), Dec 2001, Kauai, United States. IEEE Computer Society, 1, pp.447--454, 2001, 〈http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=990509〉. 〈10.1109/CVPR.2001.990509〉. 〈inria-00548273〉

Partager

Métriques

Consultations de la notice

285

Téléchargements de fichiers

277