Title :
Integrating crowd simulation for pedestrian tracking in a multi-camera system
Author :
Zhixing Jin ; Bhanu, Bir
Author_Institution :
Center for Res. in Intell. Syst., Univ. of California, Riverside, Riverside, CA, USA
fDate :
Oct. 30 2012-Nov. 2 2012
Abstract :
Multi-camera multi-target tracking is one of the most active research topics in computer vision. However, many challenges remain to achieve robust performance in real-world video networks. In this paper we extend the state-of-the-art single camera tracking method, with both detection and crowd simulation, to a multiple camera tracking approach that exploits crowd simulation and uses principal axis-based integration. The experiments are conducted on PETS 2009 data set and the performance is evaluated by multiple object tracking precision and accuracy (MOTP and MOTA) based on the position of each pedestrian on the ground plane. It is demonstrated that the information from crowd simulation can provide significant advantage for tracking multiple pedestrians through multiple cameras.
Keywords :
computer vision; object detection; object recognition; pedestrians; target tracking; traffic engineering computing; video surveillance; MOTA; MOTP; PETS 2009 data set; camera tracking method; computer vision; crowd simulation integration; multicamera multitarget tracking system; multiple object tracking accuracy; multiple object tracking precision; pedestrian detection; pedestrian tracking; principal axis-based integration; video network; Boosting; Cameras; Computational modeling; Detectors; Humans; Mathematical model; Tracking;
Conference_Titel :
Distributed Smart Cameras (ICDSC), 2012 Sixth International Conference on
Conference_Location :
Hong Kong
Print_ISBN :
978-1-4503-1772-6