Applying image processing and neural network techniques to data association algorithm

Multiple-target tracking (MTT) is a prerequisite step for radar surveillance systems. Data association is the key technique used in radar MTT systems. This paper presents a new approach for data association that uses both quantity data and image information. In order to combine these two attributes, a fusion algorithm based on the competitive Hopfield neural network (CHNN) is developed to match radar measurements with existing target tracks. When target maneuvering problems are detected, an adaptive maneuvering estimator is applied. Computer simulation results indicate that the proposed approach is suitable for multiple-target tracking problems and has good performance.