PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Smart Particle Filtering for 3D Hand Tracking
Matthieu Bray, Esther Koller-Meier and Luc Van Gool
In: International Conference on Automatic Face and Gesture Recognition, 17-19 May 2004, Seoul, Korea.


Solving the tracking of an articulated structure in a reasonable time is a complex task mainly due to the high dimensionality of the problem. A new optimization method, called Stochastic Meta-Descent (SMD), based on gradient descent with adaptive and parameter specific step sizes was introduced recently (Bray et al. 2004) to solve this challenging problem. While the local optimization works very well, reaching the global optimum is not guaranteed. We therefore propose a novel algorithm which combines the SMD optimization with a particle filter to form `smart particles`. After propagating the particles, SMD is performed and the resulting new particle set is included such that the original Bayesian distribution is not altered. The resulting `smart particle filter` (SPF) tracks high dimensional articulated structures with far fewer samples than previous methods.

PDF - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Conference or Workshop Item (Paper)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Learning/Statistics & Optimisation
Theory & Algorithms
ID Code:173
Deposited By:Matthieu Bray
Deposited On:03 June 2004