Broadband Communications, Networks, and Systems. 10th EAI International Conference, Broadnets 2019, Xi’an, China, October 27-28, 2019, Proceedings

Research Article

Device-Free Gesture Recognition Using Time Series RFID Signals

  • @INPROCEEDINGS{10.1007/978-3-030-36442-7_10,
        author={Han Ding and Lei Guo and Cui Zhao and Xiao Li and Wei Shi and Jizhong Zhao},
        title={Device-Free Gesture Recognition Using Time Series RFID Signals},
        proceedings={Broadband Communications, Networks, and Systems. 10th EAI International Conference, Broadnets 2019, Xi’an, China, October 27-28, 2019, Proceedings},
        proceedings_a={BROADNETS},
        year={2019},
        month={12},
        keywords={Gesture recognition RFID Device free},
        doi={10.1007/978-3-030-36442-7_10}
    }
    
  • Han Ding
    Lei Guo
    Cui Zhao
    Xiao Li
    Wei Shi
    Jizhong Zhao
    Year: 2019
    Device-Free Gesture Recognition Using Time Series RFID Signals
    BROADNETS
    Springer
    DOI: 10.1007/978-3-030-36442-7_10
Han Ding1,*, Lei Guo1,*, Cui Zhao1,*, Xiao Li1,*, Wei Shi1,*, Jizhong Zhao1,*
  • 1: Xi’an Jiaotong University
*Contact email: dinghan@xjtu.edu.cn, gl0103@stu.xjtu.edu.cn, zhaocui@stu.xjtu.edu.cn, lixiao0906@stu.xjtu.edu.cn, weishi0103@sina.com, zjz@xjtu.edu.cn

Abstract

A wide range of applications can benefit from the human motion recognition techniques that utilize the fluctuation of time series wireless signals to infer human gestures. Among which, device-free gesture recognition becomes more attractive because it does not need human to carry or wear sensing devices. Existing device-free solutions, though yielding good performance, require heavy crafting on data preprocessing and feature extraction. In this paper, we propose RF-Mnet, a deep-learning based device-free gesture recognition framework, which explores the possibility of directly utilizing time series RFID tag signal to recognize static and dynamic gestures. We conduct extensive experiments in three different environments. The results demonstrate the superior effectiveness of the proposed RF-Mnet framework.