Gaussian mixture PHD smoother for jump Markov models in multiple maneuvering targets tracking

Abstract

This paper presents a Gaussian mixture probability hypothesis density (GM-PHD) smoother for tracking multiple maneuvering targets that follow jump Markov models. Unlike the generalization of the multiple model GM-PHD filters, our aim is to approximate the dynamics of the linear Gaussian jump Markov system (LGJMS) by a best-fitting Gaussian (BFG) distribution so that the GM-PHD smoother can be carried out with respect to an approximated linear Gaussian system. Our approach is inspired by the recognition that the BFG approximation provides an accurate performance measure for the LGJMS. Furthermore, the multiple model estimation is avoided and less computational cost is required. The effectiveness of the proposed smoother is verified with a numerical simulation.

Promotion of GM-PHD Filtering Approach for Single-Target Tracking in Raw Data of Synthetic Aperture Radar in Spotlight Imaging Mode

“…For tracking multiple maneuvering targets, similar results have been extended to handle jump Markov models [7][8][9][10]. To derive PHD smoothers, the particle and Gaussian mixture techniques have also been used [11][12][13][14][15][16][17][18]. In [19], the GM-PHD filter is extended to multi-sensor tracking system and the target state estimates are obtained sequentially at each sensor.…”