Comparison of Nonlinear Filtering Algorithms in Ground Moving Target Indicator (GMTI) Tracking

The ground moving target indicator (GMTI) radar sensor plays an important role in situation awareness of the battlefield, surveillance, and precision tracking of ground targets. The extended Kalman filter (EKF) is usually used either alone or in the Interacting Multiple Model (IMM) framework to solve nonlinear filtering problems. Since the GMTI measurement model is nonlinear, the use of an EKF is not the best solution. The particle filter (PF) has been shown recently as a robust algorithm for a wide range of nonlinear estimation problems. The disadvantage of particle filters is the high computational load. In this paper, we compare the performance of the EKF and PF for the GMTI measurement problem using the nearly constant velocity (NCV) model in two dimensions. We analyze the differences in the performance of the EKF and PF using simulated data..