Application of the Particle Filter in IMM in Target Tracking Algorithm

Kalman filter has been widely used in the field of target tracking. It can get the optimal estimate in the linear Gauss model, but it can not achieved the good results in non-linear, non-gaussian models. The non-linear target tracking method has been extensive researched. Extend Kalman filter(EKF)based on local linearization of KF, for Taylor expansion, is simple, fast computation speed, and is suitable to applied to the nonlinear filter which is not Gauss. Particle filter is suitable for non-linear, non-gaussian system that could be represented with state model. For high speed, low flying and high maneuvering target tracking, good methods are needed in target tracking algorithm. Particle filter in IMM is demonstated that it has better performance when compared with the Extended Kalman filter in IMM to target tracking. When used in tracking algorithm, the new filter yields improved performance in the case of model uncertainties. The simulation results indicate that Particle filter in IMM algorithm can maintain track under severe correlates maneuvers, and it is better than Extended Kalman filter in IMM.