Maneuvering Multi-target Tracking Algorithm Based on Modified Generalized Probabilistic Data Association

Abstract

Aiming at the problem of strong nonlinear and effective echo confirm of multi-target tracking system in clutters environment, a novel maneuvering multi-target tracking algorithm based on modified generalized probabilistic data association is proposed in this paper. In view of the advantage of particle filter which can deal with the nonlinear and non-Gaussian system, it is introduced into the framework of generalized probabilistic data association to calculate the residual and residual covariance matrices, and the interconnection probability is further optimized. On that basis, the dynamic combination of particle filter and generalized probabilistic data association method is realized in the new algorithm. The theoretical analysis and experimental results show the filtering precision is obviously improved with respect to the tradition method using suboptimal filter.