An Adaptive Indoor Location Detection Method Using Hybrid of Radio Signal and Image Sensors

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.