MULTISENSOR DATA FUSION AND DECISION SUPPORT FOR AIRBORNE TARGET IDENTIFICATION

A knowledge-based approach and a reasoning system for multisensor data fusion (MSF) is presented. The scenario taken for the example is an air-land battlefield situation. A data fusion system obtains data from a variety of sensors. This is an essential step in a Command, Control, Communication and Intelligence (C3I) system. Automatic processing of sensor data has become essential due to the volume of evidence available in real-time and to support higher level decision making processes. When several varieties of sensors are involved in the process of fusion, each contributing information at its own level of detail, we need to have a way to combine uncertain information from these disparate sensor sources at different levels of abstraction. Dempster-Shafer approach to represent and combine data is found appropriate for this, as this offers a way to combine uncertain information from several sources, each contributing in their own way. Evidential reasoning allows confidences to be assigned to sets of propositions rather than to just N mutually exclusive propositions. The software has been developed in LISP language and tested on the IBM personal computer. The results illustrate the advantages of using multiple sensors in terms of increase in detection probability, increased spatial and temporal coverage and increased reliability that are very important in a battle-field/air-defense/naval-warfare situation.