Distributed Vision-Based Reasoning for Smart Home Care

In this paper we develop a distributed vision-based smart home care system aimed for monitoring elderly persons remotely. The cameras are triggered by a broadcast from the user badge when accelerometers on the badge detect a signal indicating an accidental fall. Tracking the approximate position of the user by the network allows for triggering cameras with the best views. Distributed scene analysis modules analyze the user’s posture and head location; these information are merged through a collaborative reasoning module, which makes a final decision about the type of the report that needs to be prepared. The developed prototype also allows for a voice channel to be established between the user badge and a call center over the phone line. A description of the developed network and several examples of the vision-based reasoning algorithm are presented in the paper.