An adaptive resampling strategy in particle filter
Jinxia Yu, Yongli Tang, Xian-Cha Chen, Qian Zhao · 2011
Particle filter has been widely applied into many fields in recent years. Combined with the deficiency analysis of particle filter, an adaptive resampling strategy based on diversity guidance is proposed. Firstly, the adaptive resampling step in particle filter is tuned based on two diversity measures which are effective sample size and population diversity factor. Moreover, the operation of particle mutation after resampling is integrated into PF so as to assure the diversity of particle sets. Then, an optimized resampling strategy in PF is presented. It drew from the advantage that resampling is done faster in partial stratified resampling algorithm. At the same time, aimed at the disadvantage of PSR algorithm in PF, it used the weights optimal idea to improve the performance of PF. With the simulation program using matlab 7.0 to track a single target motion from a fixed visual observation points, the validity of the proposed method is verified.