Back to Tao Zhao's Research Page

Stochastic Human Segmentation from a Static Camera

Tao Zhao and Ram Nevatia
{taozhao|nevatia} (at) iris (o) usc (o) edu
WMVC 2002 (IEEE Workshop on Motion and Video Computing), Orlando, Florida, Dec., 2002.

Abstract

Segmenting individual humans in a high-density scene (e.g., a crowd) acquired from a static camera is challenging mainly due to object inter-occlusion. We define this problem as a ”°model-based segmentation”± problem and the solution is obtained using a Markov chain Monte Carlo (MCMC) approach. Knowledge of various aspects including human shape, human height, camera model, and image cues including human head candidates, foreground/background separation are integrated in a Bayesian framework. We show promising results on some challenging data.

Input frame
Foreground blobs by background subtraction
Result after segmentation
Download PDF file