Evidential Data Association Filter

Abstract

The problem of multi-target tracking in clutter environment has been shown to be very challenging for both the measurement to track association and the targets' state estimation. Several approaches have been put forward to deal with such issue. Especially, the family of joint probabilistic data association and its modified versions has been very popular in the field. This paper advocates the use of the theory of belief function to tackle the measurement-to-track association as well as the estimation problems. The proposal generates the basic belief mass assignment using a Bayesian approach, while the decision making process is based on the extension of the frame of hypotheses. Our method has been tested for a nearly constant velocity target and compared to both the nearest neighbor filter and the joint probabilistic data associations filter in a highly ambiguous cases. The results demonstrate the feasibility of the proposal and show improved performances compared to the aforementioned alternative commonly used methods. © Springer-Verlag Berlin Heidelberg 2010.