Estimation of articulated motion using kinematically constrained mixture densities

Abstract
We address the problem of articulated posture estimation in it's general form. Namely, the recovery of full 3D posture parameters from an uncontrolled scene. Stochastic modeling of low-level image data is unified with models of object kinematic structure through a constrained mixture of observation processes. A modified Expectation-Maximization algorithm is proposed for this purpose. Early experiments qualitatively demonstrate the efficacy of our approach.

This publication has 17 references indexed in Scilit: