An adaptive particle filter based on posterior distribution

To address the contradiction between efficiency and precision in the particle filter, this paper propose an adaptive particle filter based on posterior distribution, which takes advantage of that the variance of measure is not more than the process variance in the dynamic system. The prior knowledge is used to set the confidence interval of likelihood, and the number of particles is adjusted by the posterior estimation in the confidence interval. The result of experiments shows that the method is not only more efficiently, but also keeps a good performance.