A modified multi-target tracking algorithm based on joint probability data association and Gaussian particle filter

Abstract

The data association problem is the key point to realize multi-target tracking. In this paper, we employ a novel multi-target tracking algorithm that combines the suboptimal joint probabilistic data association (JPDA) algorithm and Gaussian particle filter (GPF). Unlike the traditional JPDA algorithm, the suboptimal JPDA algorithm is very fast and easy to implement, and GPF has much-improved performance and versatility over other Gaussian filters, especially when nontrivial nonlinearities are presented. So the paper employ the suboptimal JPDA and GPF to update each target state independently in multi-target bearings-only tracking. Finally the proposed method is applied to multi-target tracking. Simulation results show that the method can obtain better tracking performance than Monte Carlo JPDAF and illustrate the validity of this algorithm.