Multi-sensor fusion recognition method based on improved D-S evidence theory

Abstract

A multi-sensor fusion recognition method based on improved D-S evidence theory is presented in this paper to solve the problem of highly conflictive multi-sensor fusion recognition in the decision fusion of target comprehensive recognition system which D-S evidence theory can't solve. The method modifies evidence sources by calculating the weights using the resemblance degree of single characteristic recognition results, then handle the fusion processing of the modified evidence sources to get comprehensive recognition results. The numerical example analyses demonstrate the superiority of the method proposed in this paper that it can effectively improve the accuracy and reliability of the combination. And the last simulation results of the missile target integrated recognition indicate that this method can effectively solve the problem of high conflictive data fusion error existing in the decision fusion process and improve the recognition performance of the recognition system perfectly.