PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Stochastic Meta-Descent for Tracking Articulated Structures
Matthieu Bray, Esther Koller-Meier, Nicol N. Schraudolph and Luc Van Gool
In: IEEE Workshop on Articulated and Nonrigid Motion, 27 June 2004, Washington, USA.

Abstract

Recently, an optimization approach for fast visual tracking of articulated structures based on Stochastic Meta-Descent (SMD) has been presented (Bray et al. 2004). SMD is a gradient descent with local step size adaptation that combines rapid convergence with excellent scalability. Stochastic sampling helps to avoid local minima in the optimization process. We have extended the SMD algorithm with new features for fast and accurate tracking by adapting the different step sizes between as well as within video frames and by introducing a robust likelihood function which incorporates both depths and surface orientations. A realistic deformable hand model reinforces the accuracy of our tracker. The advantages of the resulting tracker over state-of-the-art methods are corroborated through experiments.

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:172
Deposited By:Matthieu Bray
Deposited On:03 June 2004