Research on information fusion of infrared and radar sensor based on SVM

The arithmetic idea of infrared sensor and radar tracking fusion is : getting solar by infrared image processing, time matching, synchronization fusion with radar data, updating object state by fusion data filtering. The fusion combines matching scores of individual obstacle recognition modules in order to improve the system´s final decision. The obtained bimodal feature vector is used as input to an SVM-based classification scheme. We can found from computer simulation results that the tracking precision improved by information fusion, and mobility was responded in short time.