METHOD AND DEVICE FOR TRACKING MANEUVERING TARGET

摘要

A method and device for tracking a maneuvering target, which is applied to the technical field of target tracking. The method comprises: representing target feature information of a maneuvering target as multiple semantically fuzzy sets, and on the basis of the multiple semantically fuzzy sets, constructing a T-S semantic fuzziness multi-model, the T-S semantic fuzziness multi-model comprising multiple sub-models (101); identifying consequent parameters on the basis of the unscented Kalman filter algorithm to determine the target state and the covariance of the target state of each sub-model (102); identifying antecedent parameters on the basis of a fuzzy C-regression clustering algorithm to determine a target fuzzy membership function for the antecedent parameters of each sub-model (103); on the basis of the target state, the covariance of the target state and the target fuzzy membership function for the antecedent parameters for each sub-model, obtaining a state estimation and covariance estimation for the maneuvering target (104); and on the basis of the state estimation and covariance estimation for the maneuvering target, predicting the track of the maneuvering target (105). The described method may improve accuracy in target tracking.