期刊
IEEE TRANSACTIONS ON MOBILE COMPUTING
卷 16, 期 2, 页码 381-393出版社
IEEE COMPUTER SOC
DOI: 10.1109/TMC.2016.2549518
关键词
Gesture Recognition; COTS RFID; phase
资金
- Guangdong Natural Science Funds for Distinguished Young Scholar [S20120011468]
- Shenzhen Science and Technology Foundation [JCYJ20140509172719309, KQCX2015032416 0536457]
- China NSFC [61472259]
- Guangdong Young Talent Project [2014TQ01X238]
- Hong Kong RGC Grant [HKUST16207714]
- University of Macau Grant [SRG2015-00050-FST]
- Guangdong ST Project [2013B051000003]
- GDUPS
- National Basic Research Program of China (973 Program) [2015CB351705]
- NSFC [61572396, 61325013]
Gesture recognition has emerged recently as a promising application in our daily lives. Owing to low cost, prevalent availability, and structural simplicity, RFID shall become a popular technology for gesture recognition. However, the performance of existing RFID-based gesture recognition systems is constrained by unfavorable intrusiveness to users, requiring users to attach tags on their bodies. To overcome this, we propose GRfid, a novel device-free gesture recognition system based on phase information output by COTS RFID devices. Our work stems from the key insight that the RFID phase information is capable of capturing the spatial features of various gestures with low-cost commodity hardware. In GRfid, after data are collected by hardware, we process the data by a sequence of functional blocks, namely data preprocessing, gesture detection, profiles training, and gesture recognition, all of which are well-designed to achieve high performance in gesture recognition. We have implemented GRfid with a commercial RFID reader and multiple tags, and conducted extensive experiments in different scenarios to evaluate its performance. The results demonstrate that GRfid can achieve an average recognition accuracy of 96.5 and 92.8 percent in the identical-position and diverse-positions scenario, respectively. Moreover, experiment results show that GRfid is robust against environmental interference and tag orientations.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据