Title :
Adaptive Evolutionary Particle Filter Based Object Tracking with Occlusion Handling
Author :
Duan, Zhuohua ; Cai, Zixing
Author_Institution :
Sch. of Comput. Sci., Shaoguan Univ., Shaoguan, China
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.
Keywords :
evolutionary computation; nonlinear estimation; object detection; particle filtering (numerical methods); adaptive evolutionary particle filter; adaptive transition function; nonGaussian estimation problems; nonlinear estimation; normalization factor; object occlusion detection; object tracking; occlusion detection method; occlusion handling; Filtering; Noise measurement; Object detection; Particle filters; Particle measurements; Particle tracking; Proposals; Robustness; Target tracking; Time measurement; adaptive evolutionary particle filter; object tracking; occlusion detection;
Conference_Titel :
Natural Computation, 2009. ICNC '09. Fifth International Conference on
Conference_Location :
Tianjin
Print_ISBN :
978-0-7695-3736-8
DOI :
10.1109/ICNC.2009.623
