Particle Filter with Analytical Inference for Human Body Tracking

  • Authors:
  • Mun Wai Lee;Isaac Cohen;Soon Ki Jung

  • Affiliations:
  • -;-;-

  • Venue:
  • MOTION '02 Proceedings of the Workshop on Motion and Video Computing
  • Year:
  • 2002

Quantified Score

Hi-index 0.00

Visualization

Abstract

This paper introduces a framework that integratesanalytical inference into the particle filtering scheme forhuman body tracking. The analytical inference isprovided by body parts detection, and is used to updatesubsets of state parameters representing the human pose.This reduces the degree of randomness and decreases therequired number of particles. This new technique is asignificant improvement over the standard particlefiltering with the advantages of performing automatictrack initialization, recovering from tracking failures, andreducing the computational load.