Integration of Bayes detection with target tracking

Existing detection systems generally are operated using a fixed threshold a nd optimized to the Neyman-Pearson criterion. An alternative is Bayes detec tion, in which the threshold varies according to the ratio of prior probabi lities, In a recursive target tracker such as the probabilistic data associ ation filter (PDAF), such priors are available in the Form of a predicted l ocation and associated covariance; however, the information is not at prese nt made available to the detector. Put another way, in a standard detection /tracking implementation, information flows only one way: from detector to tracker. Here, we explore the idea of two-way information flow, in which th e tracker instructs the detector where to look for a target, and the detect or returns what it has found, More specifically, we show that the Bayesian detection threshold is lowered in the vicinity of the predicted measurement , and we explain the appropriate modification to the PDAF, The implementati on is simple, and the performance is remarkably good.