An Efficient Multi-Target Tracking Algorithm Using Gaussian Mixture Probability Hypothesis Density Filter

Abstract

For the problem that the standard probability hypothesis density is unable to estimate the states of targets when tracking multiple targets in possible missed detection environments, a Gaussian mixture probability hypothesis density filter based multi-target tracking algorithm is proposed. Two assisted parameters, namely label and existence probability, are introduced to expand the standard target state in the proposed algorithm which includes three robust schemes compared with the Gaussian mixture probability hypothesis density filter. Firstly, the extended parameter set of target states representing the target intensity can be correctly updated in the proposed target intensity update scheme. Secondly, by optimizing the component set that approximates the target posterior intensity, the invalid components are effectively reduced in the improved component fusion scheme. Lastly, the new target state extraction scheme can accurately estimate the states of targets by extracting the components that can better represent the real targets by comprehensively utilizing both the weight and existence probability of the target. Simulation results show that the proposed algorithm not only provides relatively accurate multi-target estimates, but also has a relatively low computational burden.