Particle Filter with improved MSV Resample for Manoeuvring Target Tracking
Pei Wang, Wang Min-gang, Yang Yao · 2020
Aiming at the shortcomings of traditional resampling method in particle filtering, such as unstable filter performance, which is greatly affected by simulation parameters and lack of particles, the paper proposes an improved MSV resampling particle filter algorithm and applies it to the tracking problem of maneuvering targets under flicker noise for the first time. Compared with the traditional resampling, the improved MSV resampling is based on the same distribution characteristics for sampling, and the resampling loses less information, which can improve the stability and accuracy of filtering and improve the phenomenon of particle scarcity. Simulation results show that the proposed algorithm overcomes the shortcomings of traditional resampling without reducing computational efficiency.