Ruan, Wenjie and Sheng, Quan Z. and Yao, Lina and Yang, Lei and Gu, Tao (2016) HOI-Loc:Towards unobstructive human localization with probabilistic multi-sensor fusion. In: 2016 IEEE International Conference on Pervasive Computing and Communication Workshops, PerCom Workshops 2016. IEEE, AUS, pp. 1-4. ISBN 9781509019410
Full text not available from this repository.Abstract
Unobtrusive indoor localization aims to localize people without requiring them to carry any devices or being actively involved with the localizing process. It underpins a wide range of applications including older people surveillance, intruder detection and indoor navigation. However, in a residential home, the Received Signal Strength Indicator (RSSI) is heavily obstructed by furniture or domestic appliances, reducing the localization accuracy. This environment is important to observe as human-object interaction (HOI) events, detected by pervasive sensors, can reveal people's interleaved locations during daily living activities. Thus, this paper aims to enhance the performance of the RFID-based localization system by fusing human-object interactions. Specifically, we propose a general Bayesian probabilistic multi-sensor fusion framework to integrate both RSSI signals and human-object interaction events to infer the most likely location and trajectory. Unlike other RFID-based unobtrusive localization systems, which are limited to deployment and testing in cleared spacial areas, our system can work in a furnished environment. The extensive experiments with this system have a localization accuracy up to 96.7%, and average 0.58m tracking error.