基于静电信号的人体动作识别

doi:10.13973/j.cnki.robot.180170

摘要
图/表
参考文献
相关文章 (15)

全文: PDF (790 KB) HTML ( ) 输出: BibTeX \| EndNote (RIS)
引用本文:
王以飞, 王伟, 田姗姗, 李孟轩, 李鹏斐, 陈曦. 基于静电信号的人体动作识别[J]. 机器人, 2018, 40(4): 423-430.DOI: 10.13973/j.cnki.robot.180170. WANG Yifei, WANG Wei, TIAN Shanshan, LI Mengxuan, LI Pengfei, CHEN Xi. Human Motion Recognition Based on Electrostatic Signals. ROBOT, 2018, 40(4): 423-430. DOI: 10.13973/j.cnki.robot.180170.

摘要提出一种通过检测人体行为动作产生的静电信号进行人体动作识别的方法.在分析人体荷电特性的基础上，设计静电信号检测系统采集被测人员的5种典型动作（行走、踏步、坐下、拿取物品、挥手）的静电感应信号.对采集的5种动作的静电信号进行特征参量提取和显著性差异分析，优化用于分类的特征参数.基于Weka平台使用3种分类算法（支持向量机、决策树C4.5和随机森林）分别对采集到的250组样本数据通过10折交叉验证进行了分类识别，结果显示随机森林算法的识别效果最好，正确率可达99.6%.研究表明本文提出的单人环境下基于人体静电信号的动作分类识别方法能够有效地对典型人体动作进行识别.

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	王以飞
	王伟
	田姗姗
	李孟轩
	李鹏斐
	陈曦

关键词 ：人机交互, 人体动作识别, 静电信号, 特征提取, 分类识别

Abstract：A human motion recognition method by detecting electrostatic signals generated by human behaviors is proposed. Based on the analysis of the charge characteristics of human body, a static electricity detection system is designed to collect the electrostatic induction signals of 5 typical actions of the tested persons, i.e. walking, stepping, sitting down, taking the goods, and waving hand. The characteristic parameters of the collected 5 kinds of human body electrostatic signals are extracted, their significant differences are analyzed, and the characteristic parameters for classification are optimized. 3 kinds of classification algorithms including support vector machine, decision tree-C4.5 and random forest, are used based on Weka platform to classify the 250 collected signal samples by 10-fold cross-validation. The results show that the random forest algorithm obtains the best recognition effect with the accuracy of 99.6%. The research shows that the proposed action classification method based on human electrostatic signals for single environment can effectively identify typical human actions.

Key words： human-computer interaction human motion recognition electrostatic signal feature extraction classification and recognition

收稿日期: 2018-02-17 录用日期: 2018-06-13

TP242

基金资助:国家自然科学基金（51777010，51407009，U1630130，51707008）

通讯作者: 李鹏斐,pfli@bit.edu.cn E-mail: pfli@bit.edu.cn

作者简介: 王以飞(1992-),男,硕士生.研究领域:静电传感器,人机交互.
王伟(1975-),男,博士,副研究员.研究领域:静电感知与测量,智能控制.
田姗姗(1992-),女,硕士.研究领域:静电感知与测量,步态识别.

链接本文:

https://robot.sia.cn/CN/10.13973/j.cnki.robot.180170 或 https://robot.sia.cn/CN/Y2018/V40/I4/423

[1] 袁保宗,阮秋琦,王延江,等.新一代(第四代)人机交互的概念框架特征及关键技术[J].电子学报,2003,31(12A):1945-1954.Yuan B Z, Ruan Q Q, Wang Y J, et al. A conceptual model and features of new generation (fourth generation) human-computer interactive systems[J]. Acta Electronica Sinica, 2003, 31(12A):1945-1954.
[2] 王鑫,沃波海,管秋,等.基于流形学习的人体动作识别[J].中国图象图形学报,2014,19(6):914-923.Wang X, Wo B H, Guan Q, et al. Human action recognition based on manifold learning[J]. Journal of Image and Graphics, 2014, 19(6):914-923.
[3] Xu G Y, Cao Y. Action recognition and activity understanding:A review[J]. Journal of Image and Graphics, 2009, 14(2):189-195.
[4] 胡成全,王凯,何丽莉,等.基于MEMS六轴传感器的上肢运动识别系统[J].大连理工大学学报,2017,57(1):92-99.Hu C Q, Wang K, He L L, et al. Arm motion detection system based on six-axis MEMS sensor[J]. Journal of Dalian Universityof Technology, 2017, 57(1):92-99.
[5] Orphomma S, Swangmuang N. Exploiting the wireless RFfading for human activity recognition[C]//10th International Conference on Electrical Engineering/Electronics, Computer,Telecommunications and Information Technology. Piscataway,USA:IEEE, 2013.
[6] Sigg S, Scholz M, Shi S, et al. RF-sensing of activities from non-cooperative subjects in device-free recognition systems using ambient and local signals[J]. IEEE Transactions on Mobile Computing, 2014, 13(4):907-920.
[7] 王钰翔,李晟洁,王皓,等.基于Wi-Fi的非接触式行为识别研究综述[J].浙江大学学报(工学版),2017,51(4):648-654,690.Wang Y X, Li S J, Wang H, et al. Survey on Wi-Fi based contactless activity recognition[J]. Journal of Zhejiang University (Engineering Science), 2017, 51(4):648-654,690.
[8] Takiguchi K, Wada T, Toyama S. Human body detection that uses electric field by walking[J]. Journal of Advanced Mechanical Design Systems and Manufacturing, 2007, 1(3):294-305.
[9] Kurita K. Note:Human heartbeat measurement on the basis of current generated by electrostatic induction[J]. Review of Scientific Instruments, 2011, 82:No.026105.
[10] Kurita K. Novel non-contact and non-attached technique for detecting sports motion[J]. Measurement, 2011, 44(8):1361-1366.
[11] Kurita K, Ueta S. A new control method for bipedal robot based on noncontact and nonattached human motion sensing technique[J]. IEEE Transactions on Industry Applications, 2011, 47(2):1022-1027.
[12] Han Q W, Chen X, Tang K, et al. A non-contact human-computer interaction application design based on electrostatic current of human body[J]. International Journal of Computer Applications in Technology, 2016, 53(1):23-31.
[13] 唐凯.基于人体静电的人机交互技术研究[D].北京:北京理工大学,2016.Tang K. Research on human-computer interaction technology based on human body static electricity[D]. Beijing:Beijing Institute of Technology, 2016.
[14] Zheng W, Cui Z, Zheng Z, et al. Remote monitoring of human hand motion using induced electrostatic signals[J]. Journal of Electrostatics, 2011, 69(6):571-577.
[15] Chubb J N. Comments on methods for charge decay measurement[J]. Journal of Electrostatics, 2004, 62(1):73-80.
[16] Chubb J N. A standard proposed for assessing the electrostatic suitability of materials[J]. Journal of Electrostatics, 2007, 65(9):607-610.
[17] Chubb J N. Tribocharging studies on inhabited cleanroom garments[J]. Journal of Electrostatics, 2008, 66(9-10):531-537.
[18] Chubb J N. Letter to the editor:Assessing the suitability of garments for use in electrostatically sensitive work areas[J]. Journal of Electrostatics, 2010, 68(4):404.
[19] Ficker T. Electrification of human body by walking[J]. Journal of Electrostatics, 2006, 64(1):10-16.
[20] Kurita K. Non-contact physical activity estimation method based on electrostatic induction technique[J]. Artificial Life & Robotics, 2012, 17(1):97-101.
[21] 杜友田,陈峰,徐文立,等.基于视觉的人的运动识别综述[J].电子学报,2007,35(1):84-90.Du Y T, Chen F, Xu W L, et al. A survey on the vision-based human motion recognition[J]. Acta Electronica Sinica, 2007, 35(1):84-90.
[22] Grzegorzewski P, ?piewak M. The Mann-Whitney test for interval-valued data[C]//10th Conference of the European-Society-for-Fuzzy-Logic-and-Technologyi. Cham, Switzerland:Springer, 2017:188-199.
[23] Xia Y, Gao Q W, Ye Q. Classification of gait rhythm signals between patients with neuro-degenerative diseases and normal subjects:Experiments with statistical features and different classification models[J]. Biomedical Signal Processing and Control, 2015, 18:254-262.