Tracking multiple people with a multi-camera system

Abstract

We present a multi-camera system based on Bayesian modality fusion to track multiple people in an indoor environment. Bayesian networks are used to combine multiple modalities for matching subjects between consecutive image frames and between multiple camera views. Unlike other occlusion reasoning methods, we use multiple cameras in order to obtain continuous visual information of people in either or both cameras so that they can be tracked through interactions. Results demonstrate that the system can maintain people's identities by using multiple cameras cooperatively.