IMMJPDA VERSUS MHT AND KALMAN FILTER WITH NN CORRELATION - PERFORMANCE COMPARISON

Multitarget tracking systems in operational use today generally adopt Kalman filter (KF) techniques (coupled with a manoeuvre detector to in troduce some kind of adaptivity), and nearest neighbour (NN) correlati on. Today there are two new approaches to the tracking problem, namely : interacting multiple model joint probabilistic data association (IMM JPDA) and multiple hypothesis tracking (MHT) which promise improved tr acking performance. The paper provides a performance comparison betwee n these three tracking algorithms in terms of track maintenance probab ility and tracking errors. The NN + KF algorithm is used as reference because of its widespread use. Results show that MHT is superior to IM MJPDA and, as expected, both perform better than NN + KF; the cost of additional performance is increased, yet feasible, computing power.