A knowledge-based approach to the detection, tracking and classification of target formations in infrared image sequences

A knowledge-based approach to the detection, tracking, and classification of ground-based formations of point targets in sequences of digitized forward-looking infrared (FLIR) image sequences is presented. The system has two components: a point target detector and tracker (PTD) which processes the image sequences and supplies candidate point targets to the knowledge-based target formation detector for clustering into formations, which are then classified as linear, V, and the like. The system has been implemented in software written in C and Common Lisp and evaluated on a variety of FLIR image sequences. The results indicate that, in all cases, the knowledge base improves system performance over that attained by the PTD alone