CN104423549A - Virtual body feeling mouse technology applied to computer - Google Patents
Virtual body feeling mouse technology applied to computer Download PDFInfo
- Publication number
- CN104423549A CN104423549A CN201310388473.9A CN201310388473A CN104423549A CN 104423549 A CN104423549 A CN 104423549A CN 201310388473 A CN201310388473 A CN 201310388473A CN 104423549 A CN104423549 A CN 104423549A
- Authority
- CN
- China
- Prior art keywords
- signal
- cursor
- semg
- gesture
- recognition
- 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
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/011—Arrangements for interaction with the human body, e.g. for user immersion in virtual reality
- G06F3/015—Input arrangements based on nervous system activity detection, e.g. brain waves [EEG] detection, electromyograms [EMG] detection, electrodermal response detection
Abstract
The invention discloses a virtual body feeling mouse technology applied to a computer. According to the technology, adopting a band-pass filter for pre-processing the collected original SEMG signal for restraining the noise; adopting the moving average algorithm for detecting the active section and judging the start point and the end point of the effective action signal; extracting the mean value of the range absolute value, zero-crossing rate and three-step AR model parameter as the characteristics of the SEMG signal; and adopting BP neural network and SOFM network for classifying the action SEMG signal. Shown by the experimental result, the higher recognition accuracy for the recognition on the gesture can be obtained by two types of neural network. The design and implementation for virtual mouse (cursor) base on the VB platform. The self API function of the Windows is used for controlling the cursor utilizing the results of the gesture electromyographic signal pattern recognition.
Description
Surface electromyogram signal (Surface Electromyography) SEMG, as a kind of important bioelectrical signals, has been widely used in bionics, biofeedback, sports medical science and rehabilitation project.In recent years, based on the Gesture Recognition of action SEMG signal as a study hotspot, the control signal as man-machine interaction is developed, for controlling myoelectric limb, servicing unit and other electronic equipments.The research contents of paper has the following aspects.
Based on the pattern-recognition of the gesture motion electromyographic signal of neural network, comprise the pre-service of signal, active segment detection, feature extraction and classification.
Bandpass filter is utilized to carry out pre-service, with restraint speckle to the original SEMG signal collected; Moving average algorithm is adopted to detect active segment, to judge the starting point and ending point of effective action signal; Extraction amplitude absolute value average, zero-crossing rate and 3 rank AR model coefficients are as the feature of SEMG signal; BP neural network and SOFM network is adopted to classify to action SEMG signal.Experimental result shows, two kinds of neural networks all obtain higher recognition correct rate to the identification of gesture.Based on the Design and implementation that the virtual mouse (cursor) of VB platform controls.Utilize the result of gesture motion electromyographic signal pattern-recognition, the api function adopting Windows to carry realizes the control to cursor.
Claims (4)
1. utilize bandpass filter to carry out pre-service, with restraint speckle to the original SEMG signal collected; Moving average algorithm is adopted to detect active segment, to judge the starting point and ending point of effective action signal; Extraction amplitude absolute value average, zero-crossing rate and 3 rank AR model coefficients are as the feature of SEMG signal; BP neural network and SOFM network is adopted to classify to action SEMG signal.
2. experimental result shows, two kinds of neural networks all obtain higher recognition correct rate to the identification of gesture.
3. based on the Design and implementation that the virtual mouse (cursor) of VB platform controls.
4. utilize the result of gesture motion electromyographic signal pattern-recognition, the api function adopting Windows to carry realizes the control to cursor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310388473.9A CN104423549A (en) | 2013-09-02 | 2013-09-02 | Virtual body feeling mouse technology applied to computer |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310388473.9A CN104423549A (en) | 2013-09-02 | 2013-09-02 | Virtual body feeling mouse technology applied to computer |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104423549A true CN104423549A (en) | 2015-03-18 |
Family
ID=52972839
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310388473.9A Pending CN104423549A (en) | 2013-09-02 | 2013-09-02 | Virtual body feeling mouse technology applied to computer |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104423549A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111714123A (en) * | 2020-07-22 | 2020-09-29 | 华南理工大学 | System and method for detecting human body waist and back surface electromyographic signals |
| CN115299950A (en) * | 2022-08-12 | 2022-11-08 | 歌尔股份有限公司 | Electromyographic signal acquisition circuit, wearable device and control method |
-
2013
- 2013-09-02 CN CN201310388473.9A patent/CN104423549A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111714123A (en) * | 2020-07-22 | 2020-09-29 | 华南理工大学 | System and method for detecting human body waist and back surface electromyographic signals |
| CN115299950A (en) * | 2022-08-12 | 2022-11-08 | 歌尔股份有限公司 | Electromyographic signal acquisition circuit, wearable device and control method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Manimegalai | Hand gesture recognition based on EMG signals using ANN | |
| Fang et al. | A multichannel surface EMG system for hand motion recognition | |
| Aungsakul et al. | Evaluating feature extraction methods of electrooculography (EOG) signal for human-computer interface | |
| US20170143226A1 (en) | Action Recognition Method and Device Based on Surface Electromyography Signal | |
| Nurhanim et al. | Classification of human activity based on smartphone inertial sensor using support vector machine | |
| WO2015103330A3 (en) | Real-time fatigue, personal effectiveness, injury risk device(s) | |
| Ryu et al. | Real-time gait subphase detection using an EMG signal graph matching (ESGM) algorithm based on EMG signals | |
| KR20140124377A (en) | Device and method for continuous biometric recognition based on electrocardiographic signals | |
| Oh et al. | Classification of hand gestures based on multi-channel EMG by scale Average wavelet transform and convolutional neural network | |
| KR102057705B1 (en) | A smart hand device for gesture recognition and control method thereof | |
| Oweis et al. | ANN-based EMG classification for myoelectric control | |
| CN104423549A (en) | Virtual body feeling mouse technology applied to computer | |
| Kim et al. | Arm motion estimation algorithm using MYO armband | |
| Oh et al. | EMG-based hand gesture classification by scale average wavelet transform and CNN | |
| Geng et al. | A novel design of 4-class BCI using two binary classifiers and parallel mental tasks | |
| Wang et al. | Emg based rehabilitation systems-approaches for als patients in different stages | |
| Liu et al. | A new feature extraction method based on autoregressive power spectrum for improving sEMG classification | |
| Ruiz-Olaya et al. | EMG-based pattern recognition with kinematics information for hand gesture recognition | |
| Tomczyński et al. | Hand gesture-based interface with multichannel sEMG band enabling unknown gesture discrimination | |
| Zhang et al. | The analysis of hand movement distinction based on relative frequency band energy method | |
| CN108268818A (en) | Gesture identification method based on surface electromyogram signal and acceleration | |
| Anam et al. | Index Finger Motion Recognition using self-advise support vector machine | |
| KR101520462B1 (en) | Apparatus for interface with disabled upper limbs | |
| Li et al. | A single smartwatch-based segmentation approach in human activity recognition | |
| Yu et al. | Classification of nine directions using the maximum likelihood estimation based on electromyogram of both forearms |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20150318 |
|
| WD01 | Invention patent application deemed withdrawn after publication |