Analytic performance prediction of feature-aided global nearest neighbour algorithm in dense target scenarios

An analytic performance prediction method for the feature-aided global nearest neighbour tracking algorithm in multi-target tracking (MTT) scenarios is proposed. The approach serves as an alternative to the costly Monte Carlo simulation method. In MTT, evaluation of interference among multiple targets remains a crucial issue on tracking performance study. This issue is investigated in dense target scenarios with feature information and unrestrictive motion. Analytic expressions are developed for tracking performance in terms of the probability of correct association and estimation accuracy. Feature information of targets is incorporated in the formulation which provides us an insight on how the tracking performance is impacted by features. In the derivations, a series of simplification assumptions are made and the results are not intended to be used directly in practical tracking applications. The major contribution of the paper is to provide a theoretical exploration and a methodology for analytic performance prediction of MTT.