Joint Probabilistic Data Association in Distributed Sensor Networks

A distributed multitarget tracking problem is considered. The Joint Probabilistic Data Association (JPDA) algorithm has been applied successfully for tracking under the multiple-target and clutter environment. However, it assumes a centralized processing architecture in which all the sensors' measurements are transmitted to a single processor and processed. In many applications, however, a set of local processors are present and each processor processes the local sensors' measurements instead of transmitting them to the central processor. The locally processed results are then interchanged and fused together through the communication network. A distributed version of JPDA algorithm which handles the fusion problem from multiple processors is presented.