Stochastic human segmentation from a static camera

Author

Zhao, Tao ; Nevatia, Ram

Author_Institution

Inst. for Robotics & Intelligent Syst., Univ. of Southern California, Los Angeles, CA, USA

fYear

2002

fDate

5-6 Dec. 2002

Firstpage

9

Lastpage

14

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.

Keywords

Bayes methods; Markov processes; Monte Carlo methods; image segmentation; object recognition; Bayesian framework; Markov chain; Monte Carlo approach; camera model; foreground/background separation; high-density scene; human head candidates; human height; human shape; image cues; model-based segmentation; object inter-occlusion; static camera; stochastic human segmentation; Cameras; Head; Humans; Image segmentation; Intelligent robots; Intelligent systems; Layout; Robot vision systems; Shape; Stochastic processes;

fLanguage

English

Publisher

ieee

Conference_Titel

Motion and Video Computing, 2002. Proceedings. Workshop on

Print_ISBN

0-7695-1860-5

Type

conf

DOI

10.1109/MOTION.2002.1182207

Filename

1182207