An improved 2-D assignment algorithm for track-to-track association

Binary hypothesis testing and 2-D linear assignment algorithm are combined to solve track-to-track association problem in circumstance of two sensors tracking multiple targets. According the processing sequence of testing and assigning, track-to-track association approaches can be roughly divided into two types, the assignment first algorithm (AFA) and the test first algorithm (TFA). An improved 2-D assignment algorithm is proposed in this paper. Using the Squared Mahalanobis Distance of state estimates as the assignment cost for the sake of briefness, performance of typical algorithms including the proposed algorithm has been evaluated through Monte Carlo simulations. It is shown that the proposed algorithm performance is more desirable than other algorithms both in terms of correct and false association rate under multiple targets scenario.