Study of maneuvering target tracking algorithm based on Kalman filter and ANFIS
Zengqiang Ma1,2 , Yacong Zheng1, Sha Zhong1, Xingxing Zou1
COMPUTER MODELLING & NEW TECHNOLOGIES 2014 18(1) 31-37
1 School of Electrical and Electronics Engineering, Shijiazhuang Tiedao University, 17 Northeast, Second Inner Ring, Shijiazhuang, China
2 Key Laboratory of Traffic Safety and Control in Hebei, 17 Northeast, Second Inner Ring, Shijiazhuang, China
Although Kalman filtering algorithm has been widely used in the maneuvering target tracking, conventional Kalman filtering algorithm always fails to track the maneuvering target as the target changes its movement state suddenly. In order to overcome its disadvantages, an improved Kalman filtering algorithm that based on the adaptive neural fuzzy inference system (ANFIS) is proposed in this paper. In the improved algorithm, the covariance matrix of Kalman residual is gainer and the measurement noise covariance can be updated in real-time by ANFIS module. Finally, the comparison and analysis of the experiment results between the original Kalman filtering algorithm and the improved one has been carried out. The experiment results show that the tracking error is obviously reduced and the accuracy is significantly boosted after the original Kalman filtering algorithm was substituted by the improved one.