Multi-target tracking in clutter using a high pulse repetition frequency radar

In this study, two algorithms of single-target tracking in clutter using a high pulse repetition frequency radar are extended: the Gaussian mixture measurement likelihood-integrated track splitting (GMM-ITS) algorithm and the enhanced multiple models (MM) to multi-target tracking algorithm, that is, the GMM-joint ITS algorithm and the enhanced MM-joint probabilistic data association algorithm, respectively. Both algorithms are extended on the basis of the optimal Bayes approach that creates track clusters for determining the nearby tracks that share measurements by enumerating and evaluating all the feasible joint measurement allocations. In all cases, the track trajectory probability density function is a Gaussian mixture, and both algorithms enable false track discrimination using the probability of target existence.