uEyes: A Ubiquitous Care-Support Service Based on Multiple Contexts Coordination

Abstract

In this paper we propose a gentle system for watching over for ubiquitous care-support services that fulfill users' actual requirements. In traditional systems of this domain, only the location information of a user on "one" side of the watching site or the watched site is considered. In this work, we cope not only with the user's location but also all the detailed situations (contexts) of associated entities such as devices, software, networks, and users, in "both" sides. To do this, we propose a ubiquitous watching over system "uEyes". In uEyes, autonomous decision making ability and cooperative behavior are introduced to each entity. Based on the advanced feature of the entities, live video streaming system is dynamically constructed according to the contexts of the entities, on both sides in runtime. As a result, watching over service that fulfills detailed users' requirements can be effectively provided. We implemented a prototype of uEyes for watching over elderly people, and performed some experiments based on several scenarios. For instance, we assumed a scenario that a son, who is taking care of his ailing father, wanted to see his facial color and expression in high quality video. We confirmed that the live video streaming system involving high resolution camera and display devices is dynamically configured in run-time