Emitter group targets tracking using GM-PHD filter combined with clustering

Group targets tracking is a more complex problem of multi-target tracking. Because the military emitter targets often turn off the radar, the traditional tracking methods do not perform well for these emitter group targets. A modified Gaussian mixture-probability hypothesis density (GM-PHD) filter combined with clustering technology is proposed. In the update process of the GM-PHD filter, the proposed method introduces the dummy measurements generated by the group centers to improve the tracking performance, rather than partitions the measurement set. After estimating the single target statements, the Jensen-Shannon divergence is used to compute their similarities. Then, the estimated targets are clustered to achieve the group tracking. Finally, the track points of the group centers in adjacent time are connected to obtain the entire trajectories of the group targets. Experiment results show that the proposed method can effectively track the emitter group targets and performs better in the simulated scenarios.