Performance Comparison of Hybrid GA-PSO Based Tuned IMMs for Maneuver Target Tracking

Target tracking is very important field of research as it has wider applications in defense as well as civilian applications. Kalman filter is generally used for such applications. When the process and measurements are non linear extensions of Kalman filters like Extended Kalman Filter, Unscented Kalman Filters are widely used. UKF can give estimations up to second order characteristics of random process. The target is maneuvering and switching among different models like constant velocity (CV), constant acceleration (CA) or constant turn (CT), Interactive Multiple Models (IMM) are employed. Implementation of IMM filters for any application is difficult because of initialization of Kalman filter i,e, tuning of filter has to be performed before applying to real time situations. It demands prior estimations of Noise covariance matrices which are left for engineering intuitions. This paper presents the nonlinear state estimation using IMM and tuning of the filter is done using bio-inspired algorithms like PSO GA and Hybrid GA-PSO.