Model-based Human Pose Estimation and Tracking

Mun Wai Lee


Abstract

Estimating human body poses in static images and tracking poses in monocular video are important for many image and video understanding applications including video surveillance. The problem is difficult due to the presence of image noise, ambiguities in image observation, high dimensional state space and partial occlusion of the human body. Human pose estimation and tracking can be made more robust by integrating the detection of components such as face and limbs. An approach based on data-driven Markov chain Monte Carlo (DD-MCMC) is used, where component detection results generate state proposals for pose estimation and initialization.  Experimental results on a set of test images and indoor video sequences show that the method is able to estimate the pose in realistic scenarios.


Maintained by Philippos Mordohai