Moving target classi cation and tracking from real - time videoAlan

This paper describes an end-to-end method for extracting moving targets from a real-time video stream, classifying them into predeened categories according to image-based properties, and then robustly tracking them. Moving targets are detected using the pixelwise diierence between consecutive image frames. A classi-catoin metric is applied these targets with a temporal consistency constraint to classify them into three categories: human, vehicle or background clutter. Once classiied, targets are tracked by a combination of temporal diierencing and template matching. The resulting system robustly identiies targets of interest, rejects background clutter, and continually tracks over large distances and periods of time despite occlusions, appearance changes and cessation of target motion.