The Aware Home: A Living Laboratory for Ubiquitous Computing Research
CoBuild '99 Proceedings of the Second International Workshop on Cooperative Buildings, Integrating Information, Organization, and Architecture
Adaptive Temporal Radio Maps for Indoor Location Estimation
PERCOM '05 Proceedings of the Third IEEE International Conference on Pervasive Computing and Communications
EURASIP Journal on Applied Signal Processing
Location Fingerprint Analyses Toward Efficient Indoor Positioning
PERCOM '08 Proceedings of the 2008 Sixth Annual IEEE International Conference on Pervasive Computing and Communications
Autonomous Ultrasonic Indoor Tracking System
ISPA '08 Proceedings of the 2008 IEEE International Symposium on Parallel and Distributed Processing with Applications
Lightweight object localization with a single camera in wireless multimedia sensor networks
GLOBECOM'09 Proceedings of the 28th IEEE conference on Global telecommunications
Indoor localization using improved RSS-based lateration methods
GLOBECOM'09 Proceedings of the 28th IEEE conference on Global telecommunications
| Hi-index | 0.01 |
Ubiquitous computing technology has brought great attentions in recent years since it promises a simple operation to an ever increasing comprehensive digital world. For a networked home supporting advanced applications, ubiquitous media access becomes a must to offer enjoyable experience for home users. The first step of ubiquitous computing is the seamless detection of user activities in order to offer services correspondingly. The challenge of user activity detection in a home is multi folds, which includes constraints on cost, privacy, energy and health concerns. This paper proposes an indoor location detection solution based on a multi modal sensor network with radio signal and cameras. With an adaptive learning estimation algorithm for noise and radio signal, by processing the combination of radio signal and image from camera, radio signal detection thresholds which controls the camera power on and cut off are generated and updated, reflecting the dynamic environment change. In this processing, no manual explicit training is needed. Simulation results show our method is very effective in terms of the determination of when to power on/off the camera.