Filtering using a tree-based estimator
Björn Stenger, Arasanathan Thayananthan, PHS Torr, Roberto Cipolla, , · OpenGrey (Institut de l'Information Scientifique et Technique) · 2003
Within this paper a new framework for Bayesian tracking ispresented, which approximates the posterior distribution atmultiple resolutions. We propose a tree-based representationof the distribution, where the leaves define a partition ofthe state space with piecewise constant density. The advantageof this representation is that regions with low probabilitymass can be rapidly discarded in a hierarchical search,and the distribution can be approximated to arbitrary precision.We demonstrate the effectiveness of the technique byusing it for tracking 3D articulated and non-rigid motionin front of cluttered background. More specifically, we areinterested in estimating the joint angles, position and orientationof a 3D hand model in order to drive an avatar.