Skip to Main Content
A new target detection architecture, designated as cognitive detector, is proposed. This method aims at solving the problems arising from simultaneous detecting and tracking targets in various non-stationary and time-variant clutter environment. Image character of detection background and the scene analysis result, which is the information that hasnÂ¿t been exploited in any existing integrated detection and tracking system, can help adjust the detection algorithm adapting for the various background and add more information about the target/clutter for data association or tracking to enhance the systemÂ¿s performance. Cognitive detector partitions the radar detection scene using the statistical and image character of the detection background. Then, multipolicy detection algorithm and detection oriented data association method operate based on the former output. At last, feedback structure between detection and tracking algorithm is used to optimize the detection policy. As describing the definition of cognitive detection and its operation processes, the paper focuses on the specific application of high frequency surface wave radar, for which the cognitive detector is rather well suitable.