Joint Detection, Tracking and Recognition of Multi-targets Based on Narrowband Radar Measurement Information

On the basis of the jump Markov system model Gaussian mixture probability hypothesis density filtering (JMS-GMPHDF), ajoint detection, tracking and recognition method of the multi-targets for the narrowband radar is presented, using the attribute information such as the speed and acceleration in the radar measurement. In the process of the multi-model Gaussian mixture probability hypothesis density filtering process of the radar multi-target measurement information processing, this method numbers each Gaussian term and extracts the track, which can form a clear track with the track number and carry out the track management. Moreover, according to the target motion model, the target acceleration control input and speed estimation are combined for the multi-target recognition and classification. Simulation result verifies that the method can effectively identify the target track while detecting and tracking the targets.