Skip to Main Content
A novel framework named evidence filtering for processing information from multiple sensor modalities is presented. This approach is based on conditional belief notions in Dempster-Shafer (DS) evidence theory and enables one to directly process temporally and spatially distributed sensor data and infer on the ldquofrequencyrdquo characteristics of various events of interest. The method can accommodate partial and incomplete information from multiple sensor modalities during the process. Certain restrictions on the coefficients impose several challenges in the design of evidence filters suggesting that arbitrary frequency shaping is not possible. A design procedure and the analysis of nonrecursive evidence filters is presented. A threat assessment scenario is simulated and the results are presented to illustrate the applications of evidence filtering.