Multi-target joint detection, tracking and classification using radar information

Based on the jump Markov system model Gaussian mixture probability hypothesis density filtering (JMS-GMPHDF), a method is proposed for multi-target joint detection, tracking and classification by using the kinematic information of radar targets such as velocity and acceleration. This method applies track extraction technique and assigns tag to each Gaussian item during multi-model Gaussian mixture probability hypothesis density filtering in the process of radar multi-target measured information, which can form and manage the clear track with tracking number. Meanwhile, based on target kinematic models, the multi-target are classified by jointly using acceleration input control and velocity estimation of the target. Simulation results suggest that the proposed method can classify the target track effectively during the detection and tracking.