Skip to Main Content
Most existing video-based target detection systems employ state-space models to keep track of an explicit number of individual targets. We introduce a framework for enhancing target detection in video by applying probabilistic models to the soft information in correlation outputs before thresholding. We show how to efficiently compute arrays of posterior target probabilities for every position in the scene conditioned on all current and past frames of a video sequence. These arrays can then be thresholded in the typical manner to yield more reliable target detections. Because the framework avoids the formation of explicit tracks, it is well suited for handling scenes with unknown numbers of targets at unknown positions. Simulation results on forward-looking infrared (FLIR) video sequences show that our proposed framework can significantly reduce the false-alarm rate of a bank of correlation filters while requiring only a marginal increase in computation.