Tsung-Han Tsai, Chih-Chi Huang, and Chih-Hao Chang, National Central University, Taiwan

Sensors on (or attached to) mobile phones can enable attractive sensing applications in different domains such as environmental monitoring, social networking, healthcare, etc. In this paper we propose a cloud computing system dedicated on smart home applications. We design the proposed wireless vision sensor network (WVSN) with its algorithm and hardware implementation. In WVSN, The partial-vision camera strategy is applied to allocate the computation task between the sensor node and the central server. Then we propose a high performance segmentation algorithm. Meanwhile, an efficient binary data compression method is proposed to cope with the result on labeling information. The proposed algorithm can provide high precision rate for the smart home applications such as the gesture recognition and humanoid tracking. To realize the physical system, we implement it on the embedded platform and the central server with their transmission work.