Multiple Collaborative Cameras for Multi-Target Tracking Using Color-Based Particle Filter and Contour Information

Abstract

Multi-target tracking is a active research field nowadays due to its wide practical applicability in video processing. While talking about Multi-target tracking, 'multi-target occlusion' is a common problem that needs to be addressed. Lots of work has been done using multiple cameras for handling 'multitarget occlusion'; however most of them require camera calibration parameters that make them impractical for outdoor video surveillance applications. The main focus of this paper is to reduce the dependency on camera calibration for multiple camera collaboration. In this perspective Gale-Shapley algorithm (GSA) has been used for finding stable matching between two or more camera views, while more robustness on tracking of objects has been ensured by combining multiple cues such object's boundary information of the object with color histogram. Efficient tracking of object ensures proficient reckoning of target depicting parameter (i.e. apparent color, height and width information of the object) as a consequence better camera collaboration. The simulation results prove the validity of our approach.