Research Of Maneuvering Target Tracking Based On Interacting Multiple Models Algorithm

With the rapid development of modern shipping industry,the situation of water traffic becomes more and more serious,and the problem of ship safety navigation becomes more and more prominent,so the ship tracking performance is more demanding,especially the stable tracking of maneuvering target.In order to improve the tracking stability and improve the accuracy of maneuvering target tracking,this paper studies the maneuvering target tracking algorithm based on the interactive multiple model algorithm.Firstly,this paper introduces the basic principle of maneuvering target tracking and analyzes the commonly used target motion model.Then,based on Kalman filter,two kinds of main nonlinear filtering algorithms,extended Kalman filter(EKF)and unscented Kalman filter(UKF),are studied emphatically.The target maneuvering scene is designed and the maneuvering target tracking performance of EKF algorithm and UKF algorithm is compared and analyzed,which provides the theoretical basis for the improved algorithm.Secondly,in order to adapt to the maneuvering change of the target,based on the analysis of the principle and advantages and disadvantages of the interactive multiple model algorithm,the interactive multiple model algorithm is combined with the two nonlinear filtering algorithms such as EKF and UKF respectively.Then,this paper researches and designs interactive multiple model algorithm base on EKF(IMM-EKF)and interactive multiple model algorithm UKF(IMM-UKF).The target tracking algorithm of EKF,UKF,IMM-EKF and IMM-UKF are simulated and analyzed for the moving scene with constant speed and turning motion.Compared with the traditional algorithms,the interactive multiple model algorithm based on nonlinear filtering improves the tracking accuracy of maneuvering targets.Finally,in order to improve the accuracy of the model probability,the existing multiple model algorithm based on the probability correction of the model is studied,and the correction process of the model's probability is analyzed in this paper.Then,according to the idea of introducing the current covariance information into the model probability,this paper proposes an interactive multiple model algorithm based on the modified probability of covariance matrix.The simulation and comparison of this algorithm and IMM algorithm show that the algorithm is effective and superior.