not logged in. (login)

Document Information

Monocular Tracking of 3D Human Motion with a Coordinated Mixture of Factor Analyzers (2006) Rui Li,Ming-Hsuan Yang,Stan Sclaroff and Tai-Peng Tian	Download pdf
Abstract: Filtering based algorithms have become popular in tracking human body pose. Such algorithms can suffer the curse of dimensionality due to the high-dimensionality of the pose state space; therefore, efforts have been dedicated to either smart sampling or reducing the dimensionality of the original pose state space. In this paper, a novel formulation that employs dimensionality reduced state space multi-hypothesis tracking algorithm is proposed. During off-line training, a mixture of factor analyzers is learned. Each factor analyzer can be thought of as a ``local dimensionality reducer" that locally approximates the pose manifold. Global coordination between local factor analyzers is achieved by learning a set of linear mixture functions that enforces agreement between local factor analyzers. The formulation allows easy bidirectional mapping between the original body pose space and the lower-dimension space. During online tracking, the clusters of factor analyzers are utilized in a multiple hypothesis tracking framework. Experiments demonstrate that the proposed framework is able to efficiently and accurately track 3D body pose, even when self-occlusion, motion blur and large limb movements occur. Quantitative comparison shows that the proposed formulation produces more accurate 3D pose estimates over time than those that can be obtained via a number of previously-proposed particle filtering based tracking algorithms.
Published in: Proceedings of the European Conference on Computer Vision (ECCV), pp 137-150, 2006.