Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review
Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review
}
TY - GEN
T1 - HOI-Loc
T2 - 13th IEEE International Conference on Pervasive Computing and Communication Workshops, PerCom Workshops 2016
AU - Ruan, Wenjie
AU - Sheng, Quan Z.
AU - Yao, Lina
AU - Yang, Lei
AU - Gu, Tao
PY - 2016/3/14
Y1 - 2016/3/14
N2 - 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.
AB - 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.
U2 - 10.1109/PERCOMW.2016.7457055
DO - 10.1109/PERCOMW.2016.7457055
M3 - Conference contribution/Paper
AN - SCOPUS:84966549625
SP - 1
EP - 4
BT - 2016 IEEE International Conference on Pervasive Computing and Communication Workshops, PerCom Workshops 2016
PB - IEEE
Y2 - 14 March 2016 through 18 March 2016
ER -