Joint tracking and classification of nonlinear trajectories of multiple objects using the transferable belief model and multi-sensor fusion framework

In this paper, we present our findings of investigating non-linear multi-target tracking techniques when jointly used with object classification. The transferable belief model (TBM) is utilized in the multi-target evaluation, data association, and target classification stages. A particle filter is used to track each of the targets and uses a motion model that is relevant to the classification given to that target. The targets are classified based upon their motion throughout the scene and their land based position. We show how this system can deal with prior knowledge and lack of knowledge. Situations, with data of this type, regularly occur in real world scenarios and we think it is very important that any system must be able to cope well to such situations. Bayesian and regular DST methods have shortcomings when dealing with such scenarios. We show that the TBM approach can be generally more computational tractable and more robust.