An Activity-Centered Wearable Computing Infrastructure for Intelligent Environment Applications

There are many research efforts that focus on converting everyday environments into intelligent and computationally active environments that support and enhance the abilities of its occupants in executing their activities. Such environments must have the ability to recognize the activities performed by its occupant, maintain a real-time model of the environment, address the occupant’s privacy and personalization issues, and provide interaction capabilities in a way the occupant would with other people. In this paper we present an activity-centered wearable computing infrastructure for designing intelligent environment applications based on the occupant’s usage and storage of everyday objects in that environment. Four components namely object manager, situative space monitor, activity recognizer and egocentric interaction manager are introduced and described in detail. A prototypical intelligent home environment capable of supporting 15 Activities of Daily Living with an activity recognition precision of 92% is presented as a “proof of concept” in a virtual reality (VR) simulated home environment.