Multiple Model CPHD Filter for Tracking Maneuvering Targets

A multiple model cardinalized probability hypothesis density (CPHD) filter is proposed for tracking multiple maneuvering targets. The augmented state is established by combining the target motion mode with the kinematic state. Both the posterior cardinality distribution of the targets and the posterior probability hypothesis density (PHD) of the augmented state are jointly propagated by using CPHD recursion. Simulation results show that the proposed filter improves the estimation accuracy of target number and target states over the multiple model PHD filter and single model CPHD filter respectively.