Comparing of several modified joint probabilistic data association algorithms

Abstract

The Joint Probabilistic Data Association algorithm is one of the most widely used Data Association algorithm which can effectively finish multi-target tracking in clutter environment. But it will cause track coalescence phenomenon in parallel neighboring or small-angle crossing scene. For avoiding track coalescence, four modified Joint Probabilistic Data Association algorithms are introduced in this paper. Through Monte Carlo simulations, it is confirmed that these algorithms all can avoid this problem, but the tracking performances of these algorithms are different. So tracking performances of them in tracking precision, computation and anti-jamming ability are compared through simulation test, which can provide the basis for applying these new algorithms in practical.