Study On Infrared Small Target Detection And Tracking Algorithm Under Complex Backgrounds

As key techniques in infrared (IR) homing guidance, target search and tracking, warning and so on, IR small target detection and tracking have been regarded as old-line and attractive research topics in the field of IR image processing. As for the real weapon systems, how to make the best of IR target detection techniques to increase the distance of target detection and to obtain the related information about the invading targets, have become important factors to decide the victory or defeat of modern warfare. The longer the distance of targets, the less the imaging area of targets and the larger the probabilities of targets influenced by backgrounds and clutter will be. Therefore, comparing with other topics in the field of IR target detection and tracking, how small targets can be robustly detected and tracked under complex backgrounds have become the more realistic and challenging research topics.The problems of small targets detection and tracking under IR complex backgrounds have been discussed in this dissertation within a novel theory framework. It can provide a new train of thoughts for other researchers. Following with traditional research steps, we decompose the problems of small target detection and tracking into three sub-topics: image preprocessing, small target detection and small target tracking. We firstly propose the concept of'complex degree of IR background', then identify and discuss a quantitative criterion to evaluate the complex degree of IR backgrounds. To implement an IR image preprocessing algorithm with some universality, an adaptive Butterworth high pass filter based on evaluating the complex degree of real backgrounds is proposed. Subsequently, we construct and implement a practical DBT (detect before track) small target detection algorithm. Thus, two sub-topics, image preprocessing and small target detection are realized in an integrated adaptive framework. Finally, an IR small target tracking algorithm which combines the merits of'filtering and data association'tracking framework and'target representation and localization'tracking framework is proposed. We spread the whole discussing process of this dissertation out based on the proposed...