Tracking pedestrians using smoothed colour histograms in an interacting multiple model framework

In this paper, we present a method for tracking pedestrians in video sequences captured by a fixed camera. Pedestrians are detected in every video frame using the human detector proposed by Dalal and Triggs. An interacting multiple model method is used to predict and update pedestrian trajectories from current frame to the next one. We employ a stationary model and a constant velocity model in our method to handle cases such as when a pedestrian suddenly stops or changes walking direction. We smooth the colour histogram that describes the appearance of each detected pedestrian using kernel density estimation. Our experimental results show that our tracking method outperforms one that uses the Kalman filter and colour histograms.