Adaptive Evolutionary Particle Filter Based Object Tracking with Occlusion Handling

Abstract

Fast and robust object tracking with occlusion handling is a challenging task. Particle filtering has proven very successful for non-linear and non-Gaussian estimation problems. The paper presents a method for occlusion detection for object tracking with adaptive evolutionary particle filter. Firstly, object occlusion is detected with normalization factor. Secondly, adaptive transition function is employed to recovery from occlusion. Thirdly, an adaptive evolutionary method is employed to handle particle degeneracy problem. Experimental results show the presented method can track object fast and accurate in occluded situation.