CN103941859A - 一种利用信号功率区分不同手势的算法 - Google Patents

一种利用信号功率区分不同手势的算法 Download PDF

Info

Publication number
CN103941859A
CN103941859A CN201410106117.8A CN201410106117A CN103941859A CN 103941859 A CN103941859 A CN 103941859A CN 201410106117 A CN201410106117 A CN 201410106117A CN 103941859 A CN103941859 A CN 103941859A
Authority
CN
China
Prior art keywords
signal
algorithm
signals
hit
gestures
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201410106117.8A
Other languages
English (en)
Inventor
不公告发明人
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
SHANGHAI WEIPU ELECTRON TECHNOLOGY Co Ltd
Original Assignee
SHANGHAI WEIPU ELECTRON TECHNOLOGY Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by SHANGHAI WEIPU ELECTRON TECHNOLOGY Co Ltd filed Critical SHANGHAI WEIPU ELECTRON TECHNOLOGY Co Ltd
Priority to CN201410106117.8A priority Critical patent/CN103941859A/zh
Publication of CN103941859A publication Critical patent/CN103941859A/zh
Pending legal-status Critical Current

Links

Landscapes

  • User Interface Of Digital Computer (AREA)

Abstract

本发明涉及一种通过计算手臂肌肉电流信号平均功率的方法来进行手势区分的算法。算法说明如下:设有L个通道的肌肉电流信号分别为,其中是通道数目,是时间上的采样点,设有效信号起始点为,信号持续时间为N,则首先计算每路信号的平均功率,然后根据计算出的每路信号的平均功率与预先设定好的阈值进行比较,即可进行手势的判断。以,识别握拳(G1),伸掌(G2),握拳前勾(G3)和握拳后摆(G4)四种手势为例,首先检测信号的起始点和终止点,得出有效信号的长度,然后计算每路信号的平均功率,分别为

Description

一种利用信号功率区分不同手势的算法
技术领域
本发明采用计算手臂肌肉电流信号(EMG)平均功率的方法来进行手势识别,它相较于其它手势识别算法,优点在于: 
计算复杂度低,只需计算每路手臂肌肉电流信号(EMG)的平均功率,与相应的阈值进行比较即可进行手势识别;计算延迟小,基本能够实时给出信号对应的手势。
背景技术
信号分析中,频谱和功率分析是一种常用方法。我们采用功率分析方法对手臂肌肉电流信号(EMG)做特征参数分析,以此来区别各个手势。 
发明内容
设有L个通道的手臂肌肉电流信号(EMG)分别为 ,其中是通道数目,是时间上的采样点,设有效信号起始点为,信号持续时间为。则首先计算每路信号的平均功率为 
    (公式1)
根据计算出的每路信号的平均功率与预先设定好的阈值进行比较,并做一定的相关性限制,即可进行手势的判断。
  
,识别握拳(G1),伸掌(G2),握拳前勾(G3)和握拳后摆(G4)四种手势为例。首先检测信号的起始点和终止点,计算出有效信号的长度,根据公式1计算出每路信号的功率,分别为,根据每种手势对每路信号设置的相应的最大和最小阈值,分别为
根据设置的阈值,即可进行手势判断,算法伪代码描述如下:
G1_hit=G2_hit=G3_hit=G4_hit=0;
If P1>=G1_CH1_MIN_TH && P1<=G1_CH1_MAX_TH
    G1_hit++;
End
If P2>=G1_CH2_MIN_TH && P2<=G1_CH2_MAX_TH
    G1_hit++;
End
If P3>=G1_CH3_MIN_TH && P1<=G1_CH3_MAX_TH
    G1_hit++;
End
If P4>=G1_CH4_MIN_TH && P1<=G1_CH4_MAX_TH
    G1_hit++;
End
If P1>=G2_CH1_MIN_TH && P1<=G2_CH1_MAX_TH
    G2_hit++;
End
If P2>=G2_CH2_MIN_TH && P2<=G2_CH2_MAX_TH
    G2_hit++;
End
If P3>=G2_CH3_MIN_TH && P1<=G2_CH3_MAX_TH
    G2_hit++;
End
If P4>=G2_CH4_MIN_TH && P1<=G2_CH4_MAX_TH
    G2_hit++;
End
If P1>=G3_CH1_MIN_TH && P1<=G3_CH1_MAX_TH
    G3_hit++;
End
If P2>=G3_CH2_MIN_TH && P2<=G3_CH2_MAX_TH
    G3_hit++;
End
If P3>=G3_CH3_MIN_TH && P1<=G3_CH3_MAX_TH
    G3_hit++;
End
If P4>=G3_CH4_MIN_TH && P1<=G3_CH4_MAX_TH
    G3_hit++;
End
If P1>=G4_CH1_MIN_TH && P1<=G4_CH1_MAX_TH
    G4_hit++;
End
If P2>=G4_CH2_MIN_TH && P2<=G4_CH2_MAX_TH
    G4_hit++;
End
If P3>=G4_CH3_MIN_TH && P1<=G4_CH3_MAX_TH
    G4_hit++;
End
If P4>=G4_CH4_MIN_TH && P1<=G4_CH4_MAX_TH
    G4_hit++;
End
If G4_hit==4
    Return gesture is G4;
Else if G3_hit==4
    Return gesture is G3;
Else if G2_hit>G1_hit && G2_hit>=3
    Return gesture is G2;
Else if G1_hit>=3
    Return gesture is G1;
Else
    Return no gesture is detected;
End。

Claims (3)

1.一种利用信号功率进行不同手势区分的算法,其特征为,计算每路有效肌肉电流信号(EMG)的平均功率,根据预先设定的阈值进行手势判断。
2.如公式                                                 给出的计算每路信号的平均功率的算法。
3.当每路信号的阈值设定好后,如说明书伪代码给出的判断手势的算法。
CN201410106117.8A 2014-03-21 2014-03-21 一种利用信号功率区分不同手势的算法 Pending CN103941859A (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201410106117.8A CN103941859A (zh) 2014-03-21 2014-03-21 一种利用信号功率区分不同手势的算法

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201410106117.8A CN103941859A (zh) 2014-03-21 2014-03-21 一种利用信号功率区分不同手势的算法

Publications (1)

Publication Number Publication Date
CN103941859A true CN103941859A (zh) 2014-07-23

Family

ID=51189555

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201410106117.8A Pending CN103941859A (zh) 2014-03-21 2014-03-21 一种利用信号功率区分不同手势的算法

Country Status (1)

Country Link
CN (1) CN103941859A (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106980367A (zh) * 2017-02-27 2017-07-25 浙江工业大学 一种基于肌电地形图的手势识别方法

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101987048A (zh) * 2009-08-03 2011-03-23 深圳先进技术研究院 假肢控制方法和系统
WO2011055326A1 (en) * 2009-11-04 2011-05-12 Igal Firsov Universal input/output human user interface
CN102349037A (zh) * 2009-03-13 2012-02-08 微软公司 用于人机接口的基于肌电图的可佩戴控制器
CN102729254A (zh) * 2012-07-04 2012-10-17 杭州电子科技大学 基于触觉临场感的遥操作机器人肌电控制方法
CN103558918A (zh) * 2013-11-15 2014-02-05 上海威璞电子科技有限公司 智能手表基于手臂肌肉电流信号做手势识别的方案

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102349037A (zh) * 2009-03-13 2012-02-08 微软公司 用于人机接口的基于肌电图的可佩戴控制器
CN101987048A (zh) * 2009-08-03 2011-03-23 深圳先进技术研究院 假肢控制方法和系统
WO2011055326A1 (en) * 2009-11-04 2011-05-12 Igal Firsov Universal input/output human user interface
CN102729254A (zh) * 2012-07-04 2012-10-17 杭州电子科技大学 基于触觉临场感的遥操作机器人肌电控制方法
CN103558918A (zh) * 2013-11-15 2014-02-05 上海威璞电子科技有限公司 智能手表基于手臂肌肉电流信号做手势识别的方案

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106980367A (zh) * 2017-02-27 2017-07-25 浙江工业大学 一种基于肌电地形图的手势识别方法
CN106980367B (zh) * 2017-02-27 2020-08-18 浙江工业大学 一种基于肌电地形图的手势识别方法

Similar Documents

Publication Publication Date Title
WO2015179868A3 (en) Automated health data acquisition, processing and communication system
WO2015101698A3 (en) A method and system for measuring stress and recovery
WO2014113892A3 (en) Computer-aided localization of site of origin of cardiac activation with discriminator leads
WO2013013646A3 (zh) 一种提高胎心率数据加速识别准确性的装置和方法
HRP20131207T1 (hr) Sustav i metoda za praćenje ili predviđanje
GB201202344D0 (en) Method of locating a sensor and related apparatus
RU2016124465A (ru) Устройство управления отображением, способ управления отображением и программа
WO2014066678A3 (en) Using user and device behavioral context models
WO2015036517A3 (en) Triggering an action in a computer device
MX2016000599A (es) Metodo y dispositivo para activar un elemento.
WO2015025187A8 (en) Method and device for improving prediction and detection of change in a physiological condition
AU2013217913A8 (en) Method for determining and comparing users&#39; paths in a building
MX341376B (es) Dispositivo de deteccion de objetos tridimensionales.
MX359535B (es) Ubicacion de dispositivo con base en un modelo de aprendizaje.
MX359360B (es) Pronóstico de producción de recursos.
RU2015137788A (ru) Расширение игрового процесса с использованием устройства отслеживания физической активности
US20220296157A1 (en) Motion speed analysis method and apparatus, and wearable device
WO2012047036A3 (en) Apparatus and method for adaptive gesture recognition in portable terminal
EP4268713A3 (en) Method and system for adjusting audio signals based on motion deviation
MX2018001483A (es) Sistemas y metodos para detectar tornados.
MX2013010466A (es) Aparato de reconocimiento de persona y metodo del mismo.
WO2016157217A3 (en) Technological device to assist user in workouts and healthy living
CN103810393A (zh) 一种基于心电向量的心电波形特征点定位方法
WO2015153503A3 (en) Systems and methods for detecting and identifying arcing based on numerical analysis
CN105344086A (zh) 足球技进攻与防守战术智能教学、训练和比赛系统的设置方法及其设备

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20140723