Abstract:

A cubature Kalman particle probability hypothesis density (CP-PHD) filter is proposed to solve the problems of the low state estimation accuracy and the serious particles degradation in standard particle probability hypothesis density (SP-PHD) filter because of unused the most recent observation. CP-PHD uses cubature Kalman filter based on spherical radial cubature rule to generate the proposal density function and obtains the present particles states by sampling from the proposal density function, so that particle distribution is closer to the real multi-target posterior probability density function. Otherwise, the performance of CP-PHD is not affected by the dimension of target state, so CP-PHD has stronger adaptive and better tracking performance than unscented Kalman particle probability hypothesis density (UP-PHD) filter. Simulation results show that the tracking accuracy of CP-PHD algorithm is superior to SP-PHD and UP-PHD.