Robust pedestrian tracking using a model-based approach

This paper presents a real-time system for pedestrian tracking in sequences of grayscale images acquired by a stationary CCD camera. The objective is to integrate this system with a pedestrian control scheme for intersections. The system outputs the spatio-temporal coordinates of each pedestrian during the period the pedestrian is in the scene. Processing is done at three levels: raw images, blobs, and pedestrians. Our method models pedestrians as rectangular patches with a certain dynamic behavior. Kalman filtering is used to estimate pedestrian parameters. The system was implemented on a Datacube MaxVideo 20 equipped with a Datacube Max860 and was able to achieve a peak performance of over 20 frames per second. Experimental results based on indoor and outdoor scenes demonstrated the system´s robustness under many difficult situations such as partial and full occlusions of pedestrians