Particle Filter-Based Object Tracking Using Adaptive Histogram

Object tracking is a difficult and primary task inmany video processing applications. Because of the diversity ofvarious video processing tasks, there exists no optimum methodthat can perform properly for all applications. Histogram-basedparticle filtering is one of the most successfu1 object trackingmethods. However, for dealing with visual tracking in realworld conditions (such as changes in illumination and pose) isstill a challenging task. In this paper, we have proposed acolor-based adaptive histogram particle filtering method thatcan update the target model. We have used the Bhattacharyyacoefficients to measure the likelihood between two colorhistograms. Our experimental results show that the proposedmethod is robust against partial occlusion, rotation, scaling,object deformation, and changes in illumination and pose. It isalso fast enough to be used in real-time applications.

Keywords:

Object tracking , Particle filter , Adaptivehistogram , Bhattacharyya coefficient