CN106681496A - Control method and device based on multiple detecting faces - Google Patents
Control method and device based on multiple detecting faces Download PDFInfo
- Publication number
- CN106681496A CN106681496A CN201611120551.7A CN201611120551A CN106681496A CN 106681496 A CN106681496 A CN 106681496A CN 201611120551 A CN201611120551 A CN 201611120551A CN 106681496 A CN106681496 A CN 106681496A
- Authority
- CN
- China
- Prior art keywords
- gesture
- human body
- many
- detecting faces
- identification
- 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
- G06F3/017—Gesture based interaction, e.g. based on a set of recognized hand gestures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- 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
Abstract
The invention relates to a control method and device based on multiple detecting faces. The method comprises the steps that human gestures in front of the multiple detecting faces are tracked and identified; corresponding detecting face controlling operations are executed through the identified human gestures. The operation problem that multiple persons operate the contents of one or more computers in the prior art is solved, and the method makes man-machine interaction have good flexibility and usability.
Description
Technical field
The present invention relates to touch control device detection technique field, more particularly to a kind of control method and dress based on many detecting faces
Put.
Background technology
At present, polylith screen can be spliced in existing large-size screen monitors Display Technique, reaches one piece of polylith screen and show jointly
The purpose of multiple main frames content or each screen display difference content host.But it is also real on the basis of this large-size screen monitors show
The effect for interacting for now allowing large-size screen monitors outrunner more flexible with computer more freely.
The content of the invention
In consideration of it, being necessary the problem existed for conventional art, there is provided a kind of control method based on many detecting faces
And device, can by being shown in this large-size screen monitors on the basis of place camera collection image, then pass through gathered image to people
Body gesture is identified, thus more freely allow large-size screen monitors outrunner more flexible with computer and have controlled accuracy with it is easy
The property used.
To reach goal of the invention, there is provided a kind of control method based on many detecting faces, methods described includes:Detectd to described more
Human body gesture in face of survey is tracked and identification;Corresponding control is performed by the human body gesture after identification described many
The operation in detecting face.
Wherein in one embodiment, the human body gesture to many detecting faces is tracked to be included with identification:Obtain
The each two field picture gathered by image-taking device in image is taken, and many detecting faces do not have the background in the state of user
Image;The right-hand gesture of many detecting face users is divided into by image detection.
Wherein in one embodiment, the human body gesture in face of many detectings is tracked also wraps with identification
Include:The institute in feature database of the human body gesture with the target gesture for pre-setting in face of the described many detectings for obtaining will be tracked
The motion characteristic for stating human body gesture is matched;If matching degree is more than predetermined threshold value, complete described in face of many detectings
The identification operation of human body gesture.
Wherein in one embodiment, the human body gesture that will be tracked in face of the described many detectings for obtaining with it is advance
The motion characteristic of the human body gesture in the feature database of the target gesture of setting carries out matching to be included:By real-time detection in image
To the image segmentation of right-hand gesture of many people out carry out feature extraction afterwards, and with the feature database of the target gesture in
The feature of multiple described target gesture matched.
Wherein in one embodiment, the feature database of the target gesture for pre-setting includes:By nerve net
Network training simultaneously extracts the motion characteristic of various human body gestures, and according to the motion characteristic of various human body gestures
Generate the feature database of the target gesture.
A kind of control device based on many detecting faces based on same inventive concept, described device includes:Tracking and identification
Module, for being tracked and identification to the human body gesture in face of many detectings;Control module, for by the institute after identification
State the operation that human body gesture performs corresponding control many detecting faces.
Wherein in one embodiment, the tracking includes with identification module:Acquisition module, is filled for obtaining by capture
The each two field picture in collection image is put, and many detecting faces do not have the background image in the state of user;Segmentation mould
Block, the right-hand gesture for being divided into many detecting face users by image detection.
Wherein in one embodiment, the tracking also includes with identification module:Matching module, for will track what is obtained
The human body gesture in the human body gesture in face of many detectings and the feature database of the target gesture for pre-setting it is dynamic
Matched as feature;Identification module, if being more than predetermined threshold value for matching degree, completes the people in face of many detectings
The identification operation of body gesture.
Wherein in one embodiment, the matching module is additionally operable to the right hand of many people for arriving real-time detection in image
The image segmentation of gesture out carries out feature extraction afterwards, and with the feature database of the target gesture in multiple described target
The feature of gesture is matched.
Wherein in one embodiment, the matching module includes:Feature database generation module, for being instructed by neutral net
Practice and extract the motion characteristic of various human body gestures, and generated according to the motion characteristic of various human body gestures
The feature database of the target gesture.
A kind of control method and device based on many detecting faces that the present invention is provided.Human body gesture in face of many detectings is entered
Line trace and identification;The operation that face is detected corresponding control is performed by human body gesture after identification more.This method solve
The problem of operation of many people with one to single or multiple computer contents in conventional art, has more preferable with man-machine interaction
Flexibility and ease for use.
Brief description of the drawings
The step of Fig. 1 is a kind of control method of in one embodiment of the invention based on many detecting faces flow chart;And
Fig. 2 is a kind of structural representation of the control device based on many detecting faces in one embodiment of the invention.
Specific embodiment
In order to make the purpose , technical scheme and advantage of the present invention be clearer, below in conjunction with drawings and Examples pair
Control method and device of the present invention based on many detecting faces are further elaborated.It should be appreciated that tool described herein
Body embodiment is only used to explain the present invention, is not intended to limit the present invention.
As shown in figure 1, a kind of the step of control method of in for one embodiment based on many detecting faces flow chart.Specifically
Comprise the following steps:
Step 102, is tracked and identification to the human body gesture in face of many detectings.
In the present embodiment, the human body gestures for detecting faces are tracked more to be included with identification:Acquisition is adopted by image-taking device
Each two field picture in collection image, and many detecting faces do not have the background image in the state of user;By image detection point
Cut the right-hand gesture of many detecting face users.
Further, the human body gesture in face of many detectings is tracked also includes with identification:Acquisition will be tracked to detect more
Human body gesture in face of survey is matched with the motion characteristic of the human body gesture in the feature database of the target gesture for pre-setting;If
Matching degree is more than predetermined threshold value, then complete the identification operation of the human body gesture in face of many detectings.
Wherein, in feature database of the human body gesture with the target gesture for pre-setting in face of many detectings for tracking being obtained
The motion characteristic of human body gesture carries out matching to be included:By real-time detection in image to the image segmentation of right-hand gesture of many people go out
Feature extraction is carried out after coming, and is matched with the feature of the multiple target gestures in the feature database of target gesture.
It should be noted that the feature database of the target gesture for pre-setting includes:By neural metwork training and extract
The motion characteristic of various human body gestures, and the feature database of target gesture is generated according to the motion characteristic of various human body gestures.
Step 104, the operation that face is detected corresponding control is performed by human body gesture after identification more.
A kind of control method based on many detecting faces that the present invention is provided.Human body gesture in face of many detectings is tracked
With identification;The operation that face is detected corresponding control is performed by human body gesture after identification more.This method solve traditional skill
The problem of operation of many people with one to single or multiple computer contents in art, has preferably flexibly with man-machine interaction
Property and ease for use.
Based on same inventive concept, a kind of control device based on many detecting faces is additionally provided.Because this device solves to ask
The principle of topic is similar to a kind of foregoing control method based on many detecting faces, therefore, the implementation of the device can be according to foregoing side
The specific steps of method are realized, repeat part and repeat no more.
As shown in Fig. 2 a kind of structural representation of the control device based on many detecting faces in for one embodiment.The base
Control device 10 in many detecting faces includes:Tracking and identification module 200 and control module 400.
Wherein, tracking is used to be tracked and identification the human body gesture in face of many detectings with identification module 200;Control mould
Block 400 is used to be detected by the corresponding control of the human body gesture execution after identification the operation in face more.
In the present embodiment, tracking includes with identification module 200:The (not shown) of acquisition module 210 passes through for acquisition
Each two field picture in image-taking device collection image, and many detecting faces do not have the background image in the state of user;Segmentation
The (not shown) of module 220 is used to be divided into by image detection the right-hand gesture of many detecting face users;Tracking and identification
Module 200 also includes:The (not shown) of matching module 230 be used for will track obtain many detectings in face of human body gesture with it is pre-
The motion characteristic of the human body gesture in the feature database of the target gesture for first setting is matched;Identification module 240 (does not show in figure
Go out) if for matching degree more than predetermined threshold value, completing the identification operation of the human body gesture in face of many detectings.
Further, the (not shown) of matching module 230 is additionally operable to the right hand of many people for arriving real-time detection in image
The image segmentation of gesture out carries out feature extraction afterwards, and enters with the feature of multiple target gestures in the feature database of target gesture
Row matching.
Further, the (not shown) of matching module 230 includes:The (not shown) of feature database generation module 231
It is for by neural metwork training and extracting the motion characteristic of various human body gestures and special according to the action of various human body gestures
Levy the feature database of generation target gesture.
A kind of control device based on many detecting faces that the present invention is provided.Being detected 200 pairs with identification module by tracking more
Human body gesture in front is tracked and identification;Performed by the human body gesture after identification by control module 400 again corresponding
Control more detect face operation.Which solves many people in conventional art with one to single or multiple computer contents
Operation problem, there is more preferable flexibility and ease for use with man-machine interaction.
One of ordinary skill in the art will appreciate that all or part of flow in realizing above-described embodiment method, can be
The hardware of correlation is instructed to complete by computer program, described program can be stored in a computer read/write memory medium
In, the program is upon execution, it may include such as the flow of the embodiment of above-mentioned each method.Wherein, described storage medium can be magnetic
Dish, CD, read-only memory (Read-Only Memory, ROM) or random access memory (Random Access
Memory, RAM) etc..
Each technical characteristic of embodiment described above can be combined arbitrarily, to make description succinct, not to above-mentioned reality
Apply all possible combination of each technical characteristic in example to be all described, as long as however, the combination of these technical characteristics is not deposited
In contradiction, the scope of this specification record is all considered to be.
Embodiment described above only expresses several embodiments of the invention, and its description is more specific and detailed, but simultaneously
Therefore the limitation to the scope of the claims of the present invention can not be interpreted as.It should be pointed out that for one of ordinary skill in the art
For, without departing from the inventive concept of the premise, various modifications and improvements can be made, these belong to guarantor of the invention
Shield scope.Therefore, the protection domain of patent of the present invention should be determined by the appended claims.
Claims (10)
1. it is a kind of based on the control methods for detecting faces, it is characterised in that methods described includes more:
Human body gesture in face of many detectings is tracked and identification;
The operation in corresponding control many detecting faces is performed by the human body gesture after identification.
2. it is according to claim 1 based on the control methods for detecting faces, it is characterised in that described to many detecting faces more
Human body gesture be tracked and include with identification:
Obtain each two field picture gathered by image-taking device in image, and described detect in the state of face do not have a user more
Background image;
The right-hand gesture of many detecting face users is divided into by image detection.
3. it is according to claim 1 based on the control methods for detecting faces, it is characterised in that described to many detecting faces more
Preceding human body gesture is tracked also to be included with identification:
In feature database of the human body gesture with the target gesture for pre-setting in face of described many detectings that tracking is obtained
The motion characteristic of the human body gesture is matched;
If matching degree is more than predetermined threshold value, the identification operation of the human body gesture in face of many detectings is completed.
4. it is according to claim 3 based on the control methods for detecting faces, it is characterised in that described to track the institute for obtaining more
State the action of the human body gesture in the human body gesture in face of many detectings and the feature database of the target gesture for pre-setting
Feature carries out matching to be included:By real-time detection in image to the image segmentation of right-hand gesture of many people out carry out feature afterwards and carry
Take, and matched with the feature of the multiple described target gesture in the feature database of the target gesture.
5. it is according to claim 3 based on the control methods for detecting faces, it is characterised in that the target for pre-setting more
The feature database of gesture includes:By neural metwork training and extract the motion characteristic of various human body gestures, and root
The feature database of the target gesture is generated according to the motion characteristic of various human body gestures.
6. it is a kind of based on the control devices for detecting faces, it is characterised in that described device includes more:
Tracking and identification module, for being tracked and identification to the human body gesture in face of many detectings;
Control module, the operation for performing corresponding control many detecting faces by the human body gesture after identification.
7. it is according to claim 6 based on the control devices for detecting faces, it is characterised in that the tracking and identification module more
Including:
Acquisition module, for obtaining each two field picture gathered by image-taking device in image, and many detecting faces do not have
Background image in the state of user;
Segmentation module, the right-hand gesture for being divided into many detecting face users by image detection.
8. it is according to claim 6 based on the control devices for detecting faces, it is characterised in that the tracking and identification module more
Also include:
Matching module, for the human body gesture and the target gesture for pre-setting in face of the described many detectings for obtaining will to be tracked
Feature database in the motion characteristic of the human body gesture matched;
Identification module, if being more than predetermined threshold value for matching degree, completes the knowledge of the human body gesture in face of many detectings
Do not operate.
9. it is according to claim 8 based on the control devices for detecting faces, it is characterised in that the matching module more, also use
In by real-time detection in image to the image segmentation of right-hand gesture of many people out carry out feature extraction afterwards, and with the target
The feature of the multiple described target gesture in the feature database of gesture is matched.
10. it is according to claim 8 based on the control devices for detecting faces, it is characterised in that the matching module includes more:
Feature database generation module, for by neural metwork training and extracting the motion characteristic of various human body gestures, and according to
The motion characteristic of various human body gestures generates the feature database of the target gesture.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611120551.7A CN106681496A (en) | 2016-12-07 | 2016-12-07 | Control method and device based on multiple detecting faces |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611120551.7A CN106681496A (en) | 2016-12-07 | 2016-12-07 | Control method and device based on multiple detecting faces |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106681496A true CN106681496A (en) | 2017-05-17 |
Family
ID=58867762
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201611120551.7A Pending CN106681496A (en) | 2016-12-07 | 2016-12-07 | Control method and device based on multiple detecting faces |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106681496A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108815845A (en) * | 2018-05-15 | 2018-11-16 | 百度在线网络技术(北京)有限公司 | The information processing method and device of human-computer interaction, computer equipment and readable medium |
CN109325456A (en) * | 2018-09-29 | 2019-02-12 | 佳都新太科技股份有限公司 | Target identification method, device, target identification equipment and storage medium |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20090211817A1 (en) * | 2008-02-26 | 2009-08-27 | Egalax_Empia Technology Inc. | Touch panel device operable by multiple users and a method for controlling the touch panel |
WO2010030296A1 (en) * | 2008-09-15 | 2010-03-18 | Hewlett-Packard Development Company, L.P. | Touchscreen display with plural cameras |
CN102685581A (en) * | 2012-05-24 | 2012-09-19 | 尹国鑫 | Multi-hand control system for intelligent television |
CN103105928A (en) * | 2012-12-11 | 2013-05-15 | 渭南高新区晨星专利技术咨询有限公司 | Gesture remote control system |
CN104932668A (en) * | 2014-03-20 | 2015-09-23 | 冠捷投资有限公司 | Play content driving device and method for display system |
CN105074620A (en) * | 2013-03-15 | 2015-11-18 | 英特尔公司 | System and method for assigning voice and gesture command areas |
-
2016
- 2016-12-07 CN CN201611120551.7A patent/CN106681496A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20090211817A1 (en) * | 2008-02-26 | 2009-08-27 | Egalax_Empia Technology Inc. | Touch panel device operable by multiple users and a method for controlling the touch panel |
WO2010030296A1 (en) * | 2008-09-15 | 2010-03-18 | Hewlett-Packard Development Company, L.P. | Touchscreen display with plural cameras |
CN102685581A (en) * | 2012-05-24 | 2012-09-19 | 尹国鑫 | Multi-hand control system for intelligent television |
CN103105928A (en) * | 2012-12-11 | 2013-05-15 | 渭南高新区晨星专利技术咨询有限公司 | Gesture remote control system |
CN105074620A (en) * | 2013-03-15 | 2015-11-18 | 英特尔公司 | System and method for assigning voice and gesture command areas |
CN104932668A (en) * | 2014-03-20 | 2015-09-23 | 冠捷投资有限公司 | Play content driving device and method for display system |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108815845A (en) * | 2018-05-15 | 2018-11-16 | 百度在线网络技术(北京)有限公司 | The information processing method and device of human-computer interaction, computer equipment and readable medium |
CN108815845B (en) * | 2018-05-15 | 2019-11-26 | 百度在线网络技术(北京)有限公司 | The information processing method and device of human-computer interaction, computer equipment and readable medium |
CN109325456A (en) * | 2018-09-29 | 2019-02-12 | 佳都新太科技股份有限公司 | Target identification method, device, target identification equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US20170161555A1 (en) | System and method for improved virtual reality user interaction utilizing deep-learning | |
Hsieh et al. | A real time hand gesture recognition system using motion history image | |
CN105425964B (en) | A kind of gesture identification method and system | |
CN103336576A (en) | Method and device for operating browser based on eye-movement tracking | |
CN105426827A (en) | Living body verification method, device and system | |
CN104317391A (en) | Stereoscopic vision-based three-dimensional palm posture recognition interactive method and system | |
CN105631399A (en) | Fast object tracking framework for sports video recognition | |
CN104123007A (en) | Multidimensional weighted 3D recognition method for dynamic gestures | |
CN103440033B (en) | A kind of method and apparatus realizing man-machine interaction based on free-hand and monocular cam | |
CN104346816A (en) | Depth determining method and device and electronic equipment | |
CN103207709A (en) | Multi-touch system and method | |
Chaudhary et al. | Deep network for human action recognition using Weber motion | |
DE112013004801T5 (en) | Multimodal touch screen emulator | |
US9152857B2 (en) | System and method for detecting object using depth information | |
CN104821010A (en) | Binocular-vision-based real-time extraction method and system for three-dimensional hand information | |
CN105892635A (en) | Image capture realization method and apparatus as well as electronic device | |
CN103985137A (en) | Moving object tracking method and system applied to human-computer interaction | |
CN102222342A (en) | Tracking method of human body motions and identification method thereof | |
KR20200056602A (en) | Apparatus and method for recognizing movement of object | |
CN104111733A (en) | Gesture recognition system and method | |
CN105159537A (en) | Multiscreen-based real-time independent interaction system | |
CN103105924A (en) | Man-machine interaction method and device | |
CN104978074B (en) | A kind of formula input method and device | |
CN106681496A (en) | Control method and device based on multiple detecting faces | |
CN103761011B (en) | A kind of method of virtual touch screen, system and the equipment of calculating |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
WD01 | Invention patent application deemed withdrawn after publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20170517 |