GMLB Filter With Uncorrelated Conversion for Multi Nonlinear Targets Tracking

Abstract

In the process of multi-target tracking, error observation and noise should be excluded and associated with the actual target observation value. Especially in the case of nonlinear motion, the difficulty of correlation rises sharply. To solve the decreasing correlation accuracy in nonlinear motion, a Generalized Labeled Multi-Bernoulli (GLMB) filter based on an Uncorrelated Conversion (UC) named UC-GLMB filter was proposed in this paper. Firstly, this method can effectively obtain more measurement information and is applied to the linear estimator. Secondly, it is an effective solution for multiple nonlinear moving target tracking problems based on random finite sets (RFS). Thus, the performance of the UC-GLMB filter may be continually improved. Simulation results demonstrate the effectiveness of the proposed estimator compared with some popular multi-target tracking algorithms.