PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

3D Hand Tracking in a Stochastic Approximation Setting
Desmond Chik, Jochen Trumpf and Nicol Schraudolph
In: 2nd Workshop on Human Motion: Understanding, Modeling, Capture and Animation, 11th IEEE International Conference on Computer Vision Lecture Notes in Computer Science , 4814 . (2007) Springer Verlag, Berlin , Rio de Janeiro, Brazil , pp. 136-151. ISBN 978-3-540-75702-3

Abstract

This paper introduces a hand tracking system with a theoretical proof of convergence. The tracking system follows a model-based approach and uses image-based cues, namely silhouettes and colour constancy. We show that, with the exception of a small set of parameter configurations, the cost function of our tracker has a well-behaved unique minimum. The convergence proof for the tracker relies on the convergence theory in stochastic approximation. We demonstrate that our tracker meets the sufficient conditions for stochastic approximation to hold locally. Experimental results on synthetic images generated from real hand motions show the feasibility of this approach.

PDF - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Book Section
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Computational, Information-Theoretic Learning with Statistics
Learning/Statistics & Optimisation
ID Code:3991
Deposited By:S V N Vishwanathan
Deposited On:25 February 2008