People tracking by integrating multiple features

Because a people detection system that considers only a single feature tends to be unstable, many people detection systems that consider multiple features simultaneously have been proposed. These detection systems usually integrate features using a heuristic method based on the designers´ observations and induction. Whenever the number of features to be considered is changed, the designer must change and adjust the integration mechanism accordingly. To avoid this tedious process, we propose a multi-modal fusion system that can detect and track people in a scalable, accurate, robust and flexible manner. Each module considers a single feature and all modules operate independently at the same time. The outputs from the individual modules are integrated together and tracked using a Kalman filter.