A dynamic multiple-model estimator and neural algorithm for radar system

Target maneuvering situations are usually existed in radar tracking systems. The maneuvering will cause severe tracking error in a radar tracking system. Therefore accurately detecting and estimating maneuvering status of targets is one essential step in the reduction of tracking errors. In this paper, we develop a dynamic multiple-model estimator to track multiple maneuvering targets for a radar system. In this dynamic multiple-model estimator, an equivalent filter bank structure is designed to estimate the status of target maneuvering situations. Moreover an adaptive procedure is applied in this system to adjust the filtering gain in real time to obtain faster response for tracking filters. Therefore, applying the proposed approach, the system will quickly and efficiently to obtain th more accurate tracking results even under various targets' situations.