Target recognition based on modified combination rule

Evidence theory is widely used in the field of t arget recognition. The invalidation problem of this theory when dealing with hig hly conflict evidences is a research hotspot. Several alternatives of the combin ation rule are analyzed and compared. A new combination approach is proposed. Ca lculate the reliabilities of evidence sources using existing evidences. Construc t reliabilities judge matrixes and get the weights of each evidence source. Weig ht average all inputted evidences. Combine processed evidences with D-S combina tion rule repeatedly to identify a target. The application in multi-sensor targ et recognition as well as the comparison with typical alternatives all validated that this approach can dispose highly conflict evidences efficiently and get re asonable recognition results rapidly.