PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Evaluation of Probabilistic Occupancy Map People Detection for Surveillance Systems
Jérôme Berclaz, Ali Shahrokni, Francois Fleuret, James Ferryman and Pascal Fua
In: IEEE International Workshop on Performance Evaluation of Tracking and Surveillance (PETS)(2009).


In this paper, we evaluate the Probabilistic Occupancy Map (POM) pedestrian detection algorithm on the PETS 2009 benchmark dataset. POM is a multi-camera generative detection method, which estimates ground plane occupancy from multiple background subtraction views. Occupancy probabilities are iteratively estimated by fitting a synthetic model of the background subtraction to the binary foreground motion. Furthermore, we test the integration of this algorithm into a larger framework designed for understanding human activities in real environments. We demonstrate accurate detection and localization on the PETS dataset, despite suboptimal calibration and foreground motion segmentation input.

EPrint Type:Conference or Workshop Item (Oral)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Machine Vision
ID Code:6242
Deposited By:Francois Fleuret
Deposited On:08 March 2010