A unifying approach to track-to-track correlation for multisensor fusion for multiple targets

Abstract

In this paper, a global modeling approach was proposed for multi sensor fusion problems. Once the global model was investigated considering the data association and fusion, it is adapted to track to track correlation problem by a new approach. The key development of the approach is that a decentralized filtering algorithm is used for data fusion and state estimation problems in a multi-target tracking system. The use of a global mapping matrix for the track to track correlation is key element of our technique. Via the presented mathematical models, the sensor fusion and track to track correlation problems can be solved in a global way.