Comparison of Filtering Algorithms for Ground Target Tracking Using Space-based GMTI Radar

Space-based radar (SBR) systems have received a great deal of attention, since they can provide all-weather, day-night, and continuous world-wide surveillance and tracking of ground, air, and sea-surface targets. The ground moving target indicator (GMTI) mode is an important operating mode for such systems. GMTI radar measurements are the range, azimuth and range-rate, which are nonlinear functions of the target state. We consider the extended Kalman filter (EKF), unscented Kalman filter (UKF), and particle filter (PF) for the SBR GMTI nonlinear filtering problem and present a new track initiation algorithm. We compare the mean square errors (MSEs) and computational times using simulated data generated by Monte Carlo simulations. Although the cross-range errors are large, our results show that the MSEs of the filters are nearly the same. Our results show that the EKF performs the best for the scenario considered based on the MSE and computational time.