Abstract:

For recognizing the multi-target simultaneously with those targets detected and tracked in modern early warning and surveillance system, based on the jump Markov system model Gaussian mixture probability hypothesis density filtering (JMS-GMPHDF), a method is proposed for multi-target detection, tracking and recognition by fusion of radar and electronic support measures （ESM） sensors. First, the independent multi-target multi-model Gaussian mixture probability hypothesis density filter for each class of targets is designed, and Gaussian terms labels in each filtering process are given. Then, the Gaussian terms are merged and the class is estimated by targets velocity and acceleration model, and the type is estimated by ESM measurement. Finally, by managing tracks, determinate tracks with kinematic states, class, type, and track number are formed. Simulation results suggest that the proposed method can recognize the targets effectively and formulate correct tracks during the detecting and tracking process.