Multisensor fusion for compiling battlespace tactical picture

This paper presents a modeling and simulation approach for a multisensor data fusion system to obtain a common tactical picture in defence survelliance applications. We explore an architecture for building a more accurate tactical picture. In addition it combines evidence to determine platform position, velocity and identity parameters. One of the advantages in our method is its ability to effectively combine the processing of position and velocity information with the processing of Class (vehicle type), ID (specific vehicle information) and thread type (friend/hostile) information. We define two types of fusion algorithms. The first one is based on the nearest neighbor clustering techniques for data association to determine more accurate position and velocity of targets. The second technique is the identity fusion based on the fuzzy rule based classifier.