An adaptive non-linear estimate for radar target tracking

The detection of targets with a radar system is inherently a nonlinear stochastic process. Thus the application of nonlinear estimation becomes inevitable. This paper reviews four approaches: the extended Kalman filter (EKF), the Gaussian second-order filter (GSF), the iterative filter (IF), and the adaptive filter (AF). The superiority of AF in tracking maneuvering targets is quite clear in comparison with the other filters.