Label-PHD Particle Filter for Multitarget Tracking

摘要

In multiple targets tracking problem, Probability Hypothesis Density(PHD) particle filter can be used to estimate the multi-target state and the number at each time step, however, the tracks of multi-target can not be given at each time step. In this paper, label was assigned to the posterior intensity particles to get the identifier of a track, and to associate the estimate and the track. Simulations show that the "Label-PHD" program can associate estimate with track to construct the tracks of targets.