Anti-occlusion particle filter target tracking method based on chicken swarm optimization

In order to solve the poor target tracking accuracy problem caused by particle impoverishment in particle filter (PF) algorithm under the occlusion condition, an Anti-occlusion Chicken Swarm Optimization-based particle filter target tracking method is proposed. Firstly, the weight of particles is as the fitness and the type of each particle in the population and interrelation among particles is determined, and various movement mechanism of different types of particles are introduced to update the position. Then individual learning for food are adjusted through linear decrementing weight strategy and guided by the optimal individual of the population to overcome local optimal problems, and we define the area which has the biggest likelihood function value as the target. Finally, the tracking is continued by the updating templates under the occlusion condition. Theoretical analysis and experimental results show that the proposed algorithm has better robustness and higher tracking accuracy for occlusion targets than the chicken swarm optimization-based particle filter (CSO-PF) and the particle filter tracking methods.