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.