Multiple Pedestrian Tracking Using Colour and Motion Models

This paper presents a method that combines colour and motion information to track pedestrians in video sequences captured by a fixed camera. Pedestrians are firstly detected using the human detector proposed by Dalal and Triggs which involves computing the histogram of oriented gradients descriptors and classification using a linear support vector machine. For the colour-based model, we extract a 4-dimensional colour histogram for each detected pedestrian window and compare these colour histograms between consecutive video frames using the Bhattacharyya coefficient. For the motion model, we use a Kalman filter which recursively predicts and updates the estimates of the positions of pedestrians in the video frames. We evaluate our tracking method using videos from two pedestrian video datasets from the web. Our experimental results show that our tracking method outperforms one that uses only colour information and can handle partial occlusion.