查看文章

Tracking and Surveillance methods and systems for monitor ing objects passing in front of non-overlapping cameras. Invention finds corresponding tracks from different cameras and works out which object passing in front of the camera (s) made the tracks, in order to track the object from camera to camera. The invention uses an algorithm to learninter-camera spatial temporal probability using Parzen windows, learns inter-camera appearance probabilities using distribution of Bhattacharyya distances between appearance models, estab lishes correspondences based on Maximum A Posteriori (MAP) framework combining both spatial temporal and appearance probabilities, and updates learned probabilities throughout the lifetime of the system.