A new approach based on particle filter for target tracking with glint noise

In radar target tracking application, the observation noise is usually non-Gaussian, which is also referred to as glint noise. The performances of conventional trackers degrade severely in the presence of glint noise. An improved particle filter, Markov chain Monte Carlo iterated extended Kalman particle filter (MCMC-IEKPF), is applied to this problem. The tracking performance of the filter is evaluated and compared to the particle filter (PF) and the Markov chain Monte Carlo particle filter (MCMC-PF) via simulations. It is shown that the MCMC-IEKPF has better tracking performance.