Trajectory probability hypothesis density filter
This work addresses trajectory estimation in multi-target tracking, which is incremental as it extends existing PHD filter concepts to trajectories.
The paper tackles the problem of estimating multiple target trajectories without evaluating all measurement-to-target associations by proposing the trajectory probability hypothesis density (TPHD) filter, which recursively approximates the multitrajectory filtering density using a Poisson approximation and includes a Gaussian mixture implementation with simulation results demonstrating performance.
This paper presents the probability hypothesis density (PHD) filter for sets of trajectories: the trajectory probability density (TPHD) filter. The TPHD filter is capable of estimating trajectories in a principled way without requiring to evaluate all measurement-to-target association hypotheses. The TPHD filter is based on recursively obtaining the best Poisson approximation to the multitrajectory filtering density in the sense of minimising the Kullback-Leibler divergence. We also propose a Gaussian mixture implementation of the TPHD recursion. Finally, we include simulation results to show the performance of the proposed algorithm.