Multitarget tracking performance based on the quality assessment of data association

The main objective of this paper is to present, to apply, and to test the effectiveness of the new method, based on belief functions, proposed by Dezert et al. in order to evaluate the quality of the individual association pairings provided in the classical optimal data association solution for improving the performances of multitarget tracking systems in clutter, when some of the association decisions given in the optimal assignment solution are unreliable and doubtful and lead to potentially critical mistake. This evaluation is based on a Monte Carlo simulation for particular difficult maneuvering and non-maneuvering MTT problems in clutter. A comparison with the results obtained on the base of Kinematic only Data Association and Generalized Data Association is made.