Distributed tracking with probabilistic data association

This paper presents a distributed tracking version of the centralized probabilistie data association (PDA) algorithm. In this algorithm, the sensors´ observations of a target in a cluttered environment are processed locally. The results of the local estimation algorithms are communicated to a coordinator. The coordinator reconstructs the target´s statistics based on the validated observations of all the sensors, using only the communicated statistics. The local processors assume local models which may be different from the true target´s model, available to the coordinator, and from each other.