An estimating algorithm for highly maneuvering target tracking

A novel estimating method for highly-maneuvering target tracking using the Interacting Multiple-Model (IMM) algorithm with Kalman Filter (KF) based on "current" statistical model is presented in this paper. The IMM algorithm remedies the shortcoming of narrow coverage and poor generality of utilizing the single dynamic model to realize the precision tracking. Since the "current" statistical model of the proposed method can estimate the acceleration from all available online information, adaptability of IMM algorithm can be enhanced. For evaluating the performance of the novel algorithm, two highly-maneuvering motions scenarios are included. Results of the simulation validated the superiority of the IMM algorithm .The Root Mean-Square Error (RMSE) for position and acceleration estimating by using the proposed method is lower than the traditional IMM method. And the performance is evidently better than the traditional KF algorithm based on single dynamic model.