PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Full Body Tracking from Multiple Views Using Stochastic Sampling
Roland Kehl, Matthieu Bray and Luc Van Gool
In: CVPR 2005, San Diego, USA(2005).

Abstract

We present a novel approach for full body pose tracking using stochastic sampling. A volumetric reconstruction of a person is extracted from silhouettes in multiple video images. Then, an articulated body model is fitted to the data with stochastic meta descent (SMD) optimization. By comparing even a simplified version of SMD to the commonly used Levenberg-Marquardt method, we demonstrate the power of stochastic compared to deterministic sampling, especially in cases of noisy and incomplete data. Moreover, color information is added to improve the speed and robustness of the tracking. Results are shown for several challenging sequences, with tracking of 24 degrees of freedom in less than 1 second per frame.

EPrint Type:Conference or Workshop Item (Poster)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Machine Vision
User Modelling for Computer Human Interaction
Learning/Statistics & Optimisation
ID Code:1755
Deposited By:Roland Kehl
Deposited On:28 November 2005