A Multi-Sensor Multi-Target Tracker Based on Labeled MS-CPHD Filter

Abstract

The multi-sensor cardinalized probability hypothesis density (MS-CPHD) filter based on the random finite set (RFS) have been developed in the literature for multi-sensor multitarget tracking. However, this filter is not strictly a multi-target tracker as it cannot estimate identities of individual target states. To form the target tracks, a multiple target tracker based on the MS-CPHD filter is given in this paper. Specifically, in the Gaussian mixture recursion of the MS-CPHD filter, each Gaussian component is identify identified with a unique label for separating different targets. Then the target tracks can be determined from the calculation of the Gaussian component with a corresponding label. Furthermore, we also propose a track management mechanism to determine the creation, maintenance, and termination of tracks. Numerical results from simulations show that, our proposed method can obtain target tracks and has higher filtering accuracy compared with the original MS-CPHD filter, especially in scenarios with high clutter intensity.