CN108268818A - Gesture identification method based on surface electromyogram signal and acceleration - Google Patents
Gesture identification method based on surface electromyogram signal and acceleration Download PDFInfo
- Publication number
- CN108268818A CN108268818A CN201611259620.2A CN201611259620A CN108268818A CN 108268818 A CN108268818 A CN 108268818A CN 201611259620 A CN201611259620 A CN 201611259620A CN 108268818 A CN108268818 A CN 108268818A
- Authority
- CN
- China
- Prior art keywords
- acceleration
- feature
- gesture
- signal
- myoelectricity
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/20—Movements or behaviour, e.g. gesture recognition
- G06V40/28—Recognition of hand or arm movements, e.g. recognition of deaf sign language
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/253—Fusion techniques of extracted features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
Abstract
The present invention proposes a kind of gesture identification method based on surface electromyogram signal and acceleration, is extracted including S1 active segments, active segment is found out according to signal strength amplitude, by gesture motion rough segmentation by a small margin and significantly two class;Acceleration and myoelectricity feature are extracted in S2 feature extractions;S3 Classification and Identifications operate, and according to the feature of extraction, by myoelectricity feature and acceleration signature fusion under same dimension, are realized and classified using template matches.The present invention program is using surface myoelectric sensor and the motion gesture of acceleration transducer acquisition user, gesture motion by a small margin is identified using surface electromyogram signal, it is significantly acted using acceleration signal identification, the identification of gesture motion is realized using the mode of signal fused, action recognition range is big, accuracy rate is high and strong interference immunity.
Description
Technical field
The present invention relates to field of human-computer interaction, and in particular to a kind of gesture identification based on surface electromyogram signal and acceleration
Method.
Background technology
In order to help disabled person/the elderly keep with the exchanging of the external world, link up, improve their independent living ability, subtract
Light family, the burden of society, all over the world many scientists start the novel man-machine interaction mode of exploratory development.So-called interaction
Technology includes people and the interaction of executing agency (such as robot) and the interaction of executing agency and environment.The former meaning is can
It is gone to realize the planning and decision that executing agency is difficult in unknown or uncertain condition by people;And be can for the meaning of the latter
By robot go to complete people job task in inaccessiable adverse circumstances or long distance environment.
Traditional human-computer interaction device mainly has keyboard, mouse, handwriting pad, touch screen, game console etc., these equipment
The function of human-computer interaction is realized using the hand exercise of user.Gesture interaction supports more more natural interactive modes, carries
Human-centred rather than facility center management interaction technique is supplied, being primarily focused on original this thereby using family does
In thing and content rather than concentrate in equipment.
Common gesture interaction technology is divided into the gesture interaction technology based on data glove sensor and is regarded based on computer
Two kinds of the gesture interaction technology of feel.
Gesture interaction technology based on computer vision by machine vision to camera collected gesture image sequence
Processing identification, so as to be interacted with computer, this method acquires gesture information using camera, then utilizes complexion model
Human hand part is split, so as to fulfill gestures detection and identification, the tracking of motion gesture is finally realized using frame-to-frame differences method.
The effect of this method depends on the accuracy rate of complexion model, however the skin color of people differs, it is difficult to obtain general, efficient skin
Color model;In addition, when human hand movement speed is uneven, disruption will appear using frame-to-frame differences method tracking gesture, so as to lose
It loses and is tracked gesture.
Gesture interaction technology based on data glove sensor needs user to wear data glove or position sensor etc.
Hardware device acquires the information such as finger state and movement locus using sensor, computer is allowed to identify so as to carry out calculation process
Gesture motion realizes various interactive controllings.This mode advantage is to identify that accurate robust performance is good, algorithm is relatively easy, operation
Data are few and quick, can precisely obtain the solid space action of hand, change without the ambient lighting of vision system and carry on the back completely
The problems such as scape is complicated interferes.Shortcoming is that equipment wearing is complicated, of high cost, user's operation is inconvenient for use and gesture motion is by certain
Restrict, therefore, it is difficult to largely put into actual production to use.
Invention content
The purpose of the present invention is to overcome the deficiency in the prior art, especially solves the existing gesture based on data glove sensor
In interaction technique, equipment dresses the problem of complicated, of high cost, user's operation is inconvenient for use.
In order to solve the above technical problems, the present invention provides a kind of gesture identification side based on surface electromyogram signal and acceleration
Method, this method include the extraction of S1 active segments, S2 feature extractions, the operation of S3 Classification and Identifications, wherein:
S1 active segments extract, and active segment is found out, and reject user according to the length of active segment according to signal strength amplitude
The mild action performed unintentionally and the action long lasting for execution, by gesture motion rough segmentation by a small margin and significantly two
Class;
S2 feature extractions for acting by a small margin, only extract myoelectricity feature, for significantly acting, while extract acceleration
Degree and myoelectricity feature;
S3 Classification and Identifications operate, and according to the feature of extraction, myoelectricity feature and acceleration signature are merged under same dimension,
It is realized and classified using template matches.
The present invention has following advantageous effect compared with prior art:
The present invention program uses surface using surface myoelectric sensor and the motion gesture of acceleration transducer acquisition user
Electromyography signal identifies gesture motion by a small margin, is significantly acted using acceleration signal identification, and the mode for using signal fused is real
The identification of existing gesture motion, action recognition range is big, accuracy rate is high and strong interference immunity.
Description of the drawings
Fig. 1 is a kind of stream of one embodiment of the gesture identification method based on surface electromyogram signal and acceleration of the present invention
Cheng Tu.
Specific embodiment
Below in conjunction with the accompanying drawings and specific embodiment the present invention is carried out in further detail with complete explanation.It is appreciated that
It is that specific embodiment described herein is only used for explaining the present invention rather than limitation of the invention.
Referring to Fig. 1, a kind of gesture identification method based on surface electromyogram signal and acceleration of the embodiment of the present invention, the party
Method includes the extraction of S1 active segments, S2 feature extractions, the operation of S3 Classification and Identifications, wherein:
S1 active segments extract, and active segment is found out, and reject user according to the length of active segment according to signal strength amplitude
The mild action performed unintentionally and the action long lasting for execution, by gesture motion rough segmentation by a small margin and significantly two
Class;It is described in detail below:
When active segment extracts, myoelectrical activity section is first found according to surface electromyogram signal, then finds and accelerates in its vicinity
Spend active segment.Then the start-stop position of the active segment at t-th of time point can by the parameter sp (t, L) defined in following formula and two users
With customized threshold value tonAnd toffIt determines.
Wherein, L represents the time span of active segment, and m and n represent the signal of myoelectric sensor and acceleration transducer respectively
Quantity, Sic(i) signal value of i-th of moment, c-th of sampled point is represented.
If oneself continuous l sampled point of the value of sp (p+t, L) is more than ton, then active segment start from p-th of sampled point.If
Continuous l sampled point is less than t to the value of sp (q+t, L)off, then active segment end at q-th of sampled point.In the present embodiment, when
The length of active segment be 0.3~1.0 between when, to act by a small margin;When active segment is between 0.3~2.5, significantly to move
Make, remaining is inactive section.
S2 feature extractions for acting by a small margin, only extract myoelectricity feature, for significantly acting, while extract acceleration
Degree and myoelectricity feature;It is described in detail below:
Using absolute value mean value (MAV) as the myoelectricity feature acted by a small margin, the present embodiment is using the MAV in 200ms
As myoelectricity characteristic signal;
Using down-sampled acceleration signal as the acceleration signature significantly acted, down-sampled signal DSA is expressed as:
Wherein, Nd is deviation factor, s, t, spiRepresent sampling instant,Represent the mean value of signal in specified time.
S3 Classification and Identifications operate, and according to the feature of extraction, myoelectricity feature and acceleration signature are merged under same dimension,
It is realized and classified using template matches.It is described in detail below:
The electromyography signal feature MAV and acceleration signature DSA of extraction are linked up to the mould for having action with oneself as feature x
Plate matches one by one, and is identified as the action with highest matching degree.Feature vector x and the i-th class action matching degree P (x,
I) it is defined as
Wherein, ΣiAnd μiRepresent the covariance variance and mean vector of category motion characteristic, the training from sample data
It obtains.The final highest type of action of matching degree is identified action.
Claims (1)
1. a kind of gesture identification method based on surface electromyogram signal and acceleration, which is characterized in that extracted including S1 active segments,
S2 feature extractions, the operation of S3 Classification and Identifications, wherein:
S1 active segments extract, and active segment is found out, and reject user according to the length of active segment and be not intended to according to signal strength amplitude
The mild action of middle execution and the action long lasting for execution, by gesture motion rough segmentation by a small margin and significantly two class;
S2 feature extractions, for acting by a small margin, only extract myoelectricity feature, for significantly acting, at the same extract acceleration and
Myoelectricity feature;
S3 Classification and Identifications operate, and according to the feature of extraction, by myoelectricity feature and acceleration signature fusion under same dimension, use
Template matches realize classification.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611259620.2A CN108268818A (en) | 2016-12-31 | 2016-12-31 | Gesture identification method based on surface electromyogram signal and acceleration |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611259620.2A CN108268818A (en) | 2016-12-31 | 2016-12-31 | Gesture identification method based on surface electromyogram signal and acceleration |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108268818A true CN108268818A (en) | 2018-07-10 |
Family
ID=62754862
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201611259620.2A Pending CN108268818A (en) | 2016-12-31 | 2016-12-31 | Gesture identification method based on surface electromyogram signal and acceleration |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108268818A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109558911A (en) * | 2018-12-26 | 2019-04-02 | 杭州电子科技大学 | Electromyography signal Feature fusion based on genetic algorithm broad sense canonical correlation analysis |
CN113970968A (en) * | 2021-12-22 | 2022-01-25 | 深圳市心流科技有限公司 | Intelligent bionic hand action pre-judging method |
CN117238037A (en) * | 2023-11-13 | 2023-12-15 | 中国科学技术大学 | Dynamic action recognition method, device, equipment and storage medium |
-
2016
- 2016-12-31 CN CN201611259620.2A patent/CN108268818A/en active Pending
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109558911A (en) * | 2018-12-26 | 2019-04-02 | 杭州电子科技大学 | Electromyography signal Feature fusion based on genetic algorithm broad sense canonical correlation analysis |
CN113970968A (en) * | 2021-12-22 | 2022-01-25 | 深圳市心流科技有限公司 | Intelligent bionic hand action pre-judging method |
CN113970968B (en) * | 2021-12-22 | 2022-05-17 | 深圳市心流科技有限公司 | Intelligent bionic hand action pre-judging method |
CN117238037A (en) * | 2023-11-13 | 2023-12-15 | 中国科学技术大学 | Dynamic action recognition method, device, equipment and storage medium |
CN117238037B (en) * | 2023-11-13 | 2024-03-29 | 中国科学技术大学 | Dynamic action recognition method, device, equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Kumar et al. | A multimodal framework for sensor based sign language recognition | |
Gu et al. | Human gesture recognition through a kinect sensor | |
Zheng et al. | Recent advances of deep learning for sign language recognition | |
Chen et al. | A real-time dynamic hand gesture recognition system using kinect sensor | |
Pan et al. | Real-time sign language recognition in complex background scene based on a hierarchical clustering classification method | |
Agrawal et al. | A survey on manual and non-manual sign language recognition for isolated and continuous sign | |
Badi et al. | Hand posture and gesture recognition technology | |
Alrubayi et al. | A pattern recognition model for static gestures in malaysian sign language based on machine learning techniques | |
Joshi et al. | American sign language translation using edge detection and cross correlation | |
Kumar et al. | A hybrid gesture recognition method for American sign language | |
CN108268818A (en) | Gesture identification method based on surface electromyogram signal and acceleration | |
Xue et al. | A Chinese sign language recognition system using leap motion | |
Farooq et al. | A comparison of hardware based approaches for sign language gesture recognition systems | |
Elakkiya et al. | Intelligent system for human computer interface using hand gesture recognition | |
Vasanthan et al. | Facial expression based computer cursor control system for assisting physically disabled person | |
Sokhib et al. | A combined method of skin-and depth-based hand gesture recognition. | |
CN109901700A (en) | A kind of new gesture identification method | |
Zhu et al. | Near infrared hand vein image acquisition and ROI extraction algorithm | |
Dhamanskar et al. | Human computer interaction using hand gestures and voice | |
Jeyasheeli et al. | IoT based sign language interpretation system | |
Pansare et al. | 2D hand gesture for numeric devnagari sign language analyzer based on two cameras | |
Proenca et al. | A gestural recognition interface for intelligent wheelchair users | |
Singh et al. | Computer vision based hand gesture recognition: A survey | |
Fan et al. | A method of hand gesture recognition based on multiple sensors | |
Rokade et al. | Paint using hand gesture |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20180710 |
|
WD01 | Invention patent application deemed withdrawn after publication |