Two-stage Kalman estimator using advanced circular prediction for maneuvering target tracking

Maneuvering targets are difficult to track with the Kalman filter since the target model of the tracking filter might not fit the real target trajectory and the statistical characteristics of the target maneuver are unknown in advance. In order to track such a heavy maneuvering target, the estimation of the target turn-direction is necessary. A two-stage estimator using advanced circular prediction which considers the target turn-direction is proposed for maneuvering target tracking. Simulation results are given for a comparison of the performance of our proposed scheme with that of conventional tracking filters.