Easy Living in the Virtual World: A Noble Approach to Integrate Real World Activities to Virtual Worlds

摘要

Virtual worlds like “Second Life” are popular graphical representations of real (and fictitious) places, which are inhabited by real people in the form of personal avatars. The existence of people in these worlds is either (1) as avatars manipulated by users (to make them walk, fly, chat, etc), or (2) as pre-scripted agents, called “bots”, which are programmed to display some predefined behavior in the virtual world. Research that aims to bridge real life and these virtual worlds to simulate virtual living, while challenging and promising, is currently rare. Only very recently the mapping of real-world activities to virtual worlds has been attempted by processing multiple sensors data along with inference logic for real-world activities. Detecting or inferring human activity using such simple sensor data is often inaccurate and insufficient. Hence, this paper explains to infer human activity from environmental sound cues and common sense knowledge, which is an inexpensive alternative to other sensors (e.g., accelerometers). We discuss the challenges to implement such a system from the signal processing and agent based system point of view. To the best of our knowledge, this system pioneers the use of environmental sound based activity recognition in mobile computing to reflect one’s real-world activity in virtual worlds.