CN110096166A - A kind of virtual input method - Google Patents
A kind of virtual input method Download PDFInfo
- Publication number
- CN110096166A CN110096166A CN201910332812.9A CN201910332812A CN110096166A CN 110096166 A CN110096166 A CN 110096166A CN 201910332812 A CN201910332812 A CN 201910332812A CN 110096166 A CN110096166 A CN 110096166A
- Authority
- CN
- China
- Prior art keywords
- input
- image
- user
- input equipment
- identification model
- 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
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- 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
- G06F3/02—Input arrangements using manually operated switches, e.g. using keyboards or dials
- G06F3/023—Arrangements for converting discrete items of information into a coded form, e.g. arrangements for interpreting keyboard generated codes as alphanumeric codes, operand codes or instruction codes
- G06F3/0233—Character input methods
Abstract
The present invention relates to input equipment fields, and in particular to a kind of virtual input method, which comprises the 3D rendering for generating input equipment obtains 3D input equipment;Using the image of camera shooting user's operation 3D input equipment;By the image input picture identification model of camera shooting user's operation 3D input equipment, the input content of the described image identification model user's operation 3D input equipment for identification;The input content is shown in display equipment.The present invention provides a kind of new input modes, and input can be realized by not needing physical keyboard.
Description
Technical field
The present invention relates to input equipment fields, more particularly to a kind of virtual input method.
Background technique
Keyboard is most common most important computer input device, it is widely used in robot, mobile phone, computer, security protection
On the mobile terminals such as the instrument and meter that gate inhibition, monitoring and every profession and trade use, but these input equipments such as mouse, all kinds of at present
Keyboard is all the physical equipments such as key, touch screen.
Existing gap is bigger between the key of some key boards, is easy to shelter evil people and countenance evil practices, it is difficult to clean, be easy to cause
Button malfunction.In addition, fixed on the key of some keyboards be printed on the label such as character code and symbol of required national language, these labels
It cannot be changed and be easy to be worn.
Summary of the invention
To solve the above-mentioned problems, the object of the present invention is to provide a kind of virtual input methods, do not need physical keyboard just
It may be implemented to input, be a kind of new input mode.
Based on this, the present invention provides a kind of virtual input methods, which comprises a kind of virtual input method,
It is characterized in that, comprising:
The 3D rendering for generating input equipment, obtains 3D input equipment;
Using the image of camera shooting user's operation 3D input equipment;
By the image input picture identification model of camera shooting user's operation 3D input equipment, described image identification
The input content of the model user's operation 3D input equipment for identification;
The input content is shown in display equipment.
The method of the 3D rendering for generating input equipment includes persistence of vision technology or hologram technology.
The persistence of vision technology includes fan, and evenly distributed LED on the blade of the fan, the fan is with default
Speed rotation, obtains 3D rendering.
The line holographic projections technology includes:
Using laser as lighting source, and the light that the lighting source issues is divided into two bundles, a branch of directive sensitive film,
Another beam sensitive film described in directive again after the reflection of object;
The two-beam is superimposed generation interference on the sensitive film;
It is further processed using the hologram that digital picture basic principle reproduces, removes digital interference, obtain 3D rendering.
The image input picture identification model of the user's operation 3D input equipment that the camera is shot includes:
The image of preset quantity is added in the corresponding training set of initial pictures identification model;
Described image is trained using the initial pictures identification model, obtains image recognition model;
Described image is identified by described image identification model, obtains recognition result.
The recognition result includes the input content of the user's operation 3D input equipment, and the input content includes number
Word, symbol, letter.
Described to be trained using the initial pictures identification model to described image, obtaining image recognition model includes:
It is concentrated from the target training data and chooses sample image, current sample image is input to initial pictures identification mould
Type obtains recognition result;
Judge whether the recognition result is consistent with the result of user's operation 3D input equipment, iteration executes above-mentioned trained
Journey, until meet the recognition result it is consistent with the result of user's operation 3D input equipment until, obtain trained image and know
Other model.
The target training set includes the image of user's operation 3D input equipment.
The present invention provides a kind of new input modes, it may not be necessary to which physical keyboard can realize input, in input
Appearance can be changed according to user demand, have flexibility.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention for those of ordinary skill in the art without creative efforts, can be with
It obtains other drawings based on these drawings.
Fig. 1 is the flow chart of virtual input method provided in an embodiment of the present invention;
Fig. 2 is the flow chart provided in an embodiment of the present invention for obtaining image recognition model.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
Fig. 1 is the flow chart of virtual input method provided in an embodiment of the present invention, and the virtual input method includes:
S101, the 3D rendering for generating input equipment.
The method of the 3D rendering for generating input equipment includes persistence of vision technology or hologram technology.
Persistence of vision technology, that is, POV (Persistence of vision) technology, object in quick movement, when
After the image that human eye is seen disappears, human eye remains to the image for continuing to retain 0.1-0.4 seconds, and this phenomenon is referred to as the persistence of vision
Phenomenon.When human eye watches object, images on retina, and human brain is inputted by optic nerve, feel the picture of object, but work as object
When removing, optic nerve will not disappear to the impression of object immediately, and continue 0.1-0.4 seconds time, this property of human eye
Referred to as " persistence of visions of eyes ".
The persistence of vision technology includes fan, and evenly distributed LED on the blade of the fan, the fan is with default
Speed rotation, obtains 3D rendering.In this way, just fan rotation and LED light bar are shown and combined, principle is persisted using human eye,
Form the aerial mirage phantom of figure, animation and video.It is that LED light shines, the shell on periphery is dark-coloured and will not send out when imaging
Light, in this way, human eye would only receive the stop of light, and dark mat can not then be differentiated because of too fast by brain, in this way
Display effect can only rest on light shown by LED light, just realize the effect of air-borne imagery in this way, then show 3D
Floating image.Specifically be exactly: light to visual effect caused by retina after light fails, when can still retain one section
Between.Although the identification precision of human eye is very high, the time needed for image transmitting to brain is 1/24 second by optic nerve.Just
It is using this factor, when multiple screen switching speed that fix reach 24 frames, can to form continuous picture (referred herein
24 frames are the frame per second directly shown to human eye, rather than the frame per second conducted to part machine of picture).When holographic 3D advertisement machine is run
Frame per second generally in 30 frame per second or so, i other words the time of each video freezing is 1/30 second, the effect being imaged in this way is just
It realizes.It is that LED light shines when equipment imaging simultaneously, the shell on periphery is dark-coloured and does not shine, then operating in equipment
When, human eye would only receive the stop of light, and can not then being differentiated by brain because of too fast for dark mat, show effect in this way
Fruit can only rest on light shown by LED, just realize the effect of holographic 3D imaging in this way.
The hologram technology is that the simultaneously true 3-D image of reconstructed object is recorded using interference and diffraction principle
Technology.The holographic technique is divided into two bundles using laser as lighting source, and by the light that light source issues, a branch of directly to penetrate
To sensitive film, another beam directive sensitive film again after the reflection of object.Two-beam is superimposed generation interference on sensitive film, finally
It is further processed using the hologram that digital picture basic principle reproduces, removes digital interference, obtain clearly hologram
Picture.User does not need to wear with anaglyph spectacles or other any ancillary equipments, so that it may watch shadow in different angle naked eyes
Picture.
It is fairly simple or to (input equipment compares in simple terms in the higher situation of cost requirement if it is input equipment
Simply refer to that function is relatively smaller, the type of the image of input is relatively smaller, the product low to the required precision of image, in security protection
The keyboard of the electronic equipments such as left front, mobile phone, the computer in face, input equipment are relative complex), 3D can be generated by POV technology
Figure, if it is the more complicated virtual game such as based on AI of input equipment, large-scale security system, building structure model, machine
People etc. or high-end equipment can generate 3D figure by hologram technology.
S102, the image that user's operation 3D input equipment is shot using camera.
When user's operation 3D input equipment clicks some part in the 3D rendering such as user, the video camera shooting institute
State the operating process of user.
S103, the image input picture identification model that the camera is shot to user's operation 3D input equipment, the figure
As the input content of the identification model user's operation 3D input equipment for identification.
Video camera shoots the user and clicks the image of the 3D input equipment, and described image is input to image recognition
Module, to identify the operation of user, for example, user clicks the alphabetical M of the 3D input equipment, and camera shoots user's point
This image of the alphabetical M of the 3D input equipment is hit, and described image is input to described image identification module, described image
Identification module may determine that the content i.e. letter M that user inputs in described image.
Image input picture identification model by the user's operation 3D input equipment that the camera is shot includes:
(1), the image of preset quantity is added in the corresponding training set of initial pictures identification model;
When some part as described in clicking user in 3D rendering of user's operation 3D input equipment, video camera shoots to obtain institute
The operating result i.e. input content of user can be obtained in the image for stating the operating process of user from described image.The video camera
The image for shooting the operating process for obtaining the user can be used as the training image of initial pictures identification model training, addition
To in the corresponding training set of the initial pictures identification model.
(2), described image is trained using the initial pictures identification model, obtains image recognition model;
The initial pictures identification model, which is trained described image, includes:
It is concentrated from the target training data and chooses sample image, current sample image is input to initial pictures identification mould
Type, obtains recognition result, and the target training set includes the image of user's operation 3D input equipment;
Judge whether the recognition result is consistent with the result of user's operation input equipment, iteration executes above-mentioned trained
Journey, until meet the recognition result it is consistent with the result of user's operation 3D input equipment until, obtain trained image and know
Other model.
(3), described image is identified by described image identification model, obtains recognition result.
The image that the video camera is shot to obtain the operating process of the user inputs the initial pictures identification model
In, obtain recognition result.The recognition result includes the input content of the user's operation input equipment, the input content packet
Include number, symbol, letter.
S104, the input content is shown in display equipment.
Described to be identified by described image identification model to described image, the recognition result of acquisition passes through display equipment
Display.
The display equipment includes the communication terminal having a display function such as mobile phone, computer, iPad.
The present invention provides a kind of new input modes, it may not be necessary to which physical keyboard can realize input, in input
Appearance can be changed according to user demand, have flexibility.
Fig. 2 is the flow chart provided in an embodiment of the present invention for obtaining image recognition model, and described image identification model obtains
The process is taken to include:
S201, the image of preset quantity is added in the corresponding training set of initial pictures identification model;
Image input picture identification model by the user's operation 3D input equipment that the camera is shot includes:
When some part as described in clicking user in 3D rendering of user's operation 3D input equipment, video camera shoots to obtain institute
The operating result i.e. input content of user can be obtained in the image for stating the operating process of user from described image.The video camera
The image for shooting the operating process for obtaining the user can be used as the training image of initial pictures identification model training, addition
To in the corresponding training set of the initial pictures identification model.
S202, described image is trained using the initial pictures identification model, obtains image recognition model;
The initial pictures identification model, which is trained described image, includes:
It is concentrated from the target training data and chooses sample image, current sample image is input to initial pictures identification mould
Type, obtains recognition result, and the target training set includes the image of user's operation input equipment;
Judge whether the recognition result is consistent with the result of user's operation input equipment, iteration executes above-mentioned trained
Journey, until meet the recognition result it is consistent with the result of user's operation 3D input equipment until, obtain trained image and know
Other model.
S203, described image is identified by described image identification model, obtains recognition result.
The image that the video camera is shot to obtain the operating process of the user inputs the initial pictures identification model
In, obtain recognition result.The recognition result includes the input content of the user's operation input equipment, the input content packet
Include number, symbol, letter.
The above is only a preferred embodiment of the present invention, it is noted that for the ordinary skill people of the art
For member, without departing from the technical principles of the invention, several improvement and replacement can also be made, these are improved and replacement
Also it should be regarded as protection scope of the present invention.
Claims (8)
1. a kind of virtual input method characterized by comprising
The 3D rendering for generating input equipment, obtains 3D input equipment;
Using the image of camera shooting user's operation 3D input equipment;
By the image input picture identification model of camera shooting user's operation 3D input equipment, described image identification model
The input content of the user's operation 3D input equipment for identification;
The input content is shown in display equipment.
2. virtual input method as described in claim 1, which is characterized in that the method for the 3D rendering for generating input equipment
Including persistence of vision technology or hologram technology.
3. virtual input method as claimed in claim 2, which is characterized in that the persistence of vision technology includes fan, described
Evenly distributed LED, the fan are rotated on the blade of fan with pre-set velocity, obtain 3D rendering.
4. virtual input method as claimed in claim 2, which is characterized in that the line holographic projections technology includes:
Using laser as lighting source, and the light that the lighting source issues is divided into two bundles, a branch of directive sensitive film is another
Beam sensitive film described in directive again after the reflection of object;
The two-beam is superimposed generation interference on the sensitive film;
It is further processed using the hologram that digital picture basic principle reproduces, removes digital interference, obtain 3D rendering.
5. virtual input method as described in claim 1, which is characterized in that the user's operation for shooting the camera
The image input picture identification model of 3D input equipment includes:
The image of preset quantity is added in the corresponding training set of initial pictures identification model;
Described image is trained using the initial pictures identification model, obtains image recognition model;
Described image is identified by described image identification model, obtains recognition result.
6. virtual input method as claimed in claim 5, which is characterized in that the recognition result includes the user's operation 3D
The input content of input equipment, the input content include number, symbol, letter.
7. virtual input method as claimed in claim 5, which is characterized in that described to utilize the initial pictures identification model pair
Described image is trained, and is obtained image recognition model and is included:
It is concentrated from the target training data and chooses sample image, current sample image is input to initial pictures identification model,
Obtain recognition result;
Judging whether the recognition result is consistent with the result of user's operation 3D input equipment, iteration executes above-mentioned training process,
Until meet the recognition result it is consistent with the result of user's operation 3D input equipment until, obtain trained image recognition mould
Type.
8. virtual input method as claimed in claim 7, which is characterized in that the target training set includes user's operation 3D defeated
Enter the image of equipment.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910332812.9A CN110096166A (en) | 2019-04-23 | 2019-04-23 | A kind of virtual input method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910332812.9A CN110096166A (en) | 2019-04-23 | 2019-04-23 | A kind of virtual input method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110096166A true CN110096166A (en) | 2019-08-06 |
Family
ID=67445764
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910332812.9A Pending CN110096166A (en) | 2019-04-23 | 2019-04-23 | A kind of virtual input method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110096166A (en) |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20070009207A (en) * | 2005-07-15 | 2007-01-18 | 엘지전자 주식회사 | Apparatus and method for input holographic keyboard in mobile terminal |
CN103105930A (en) * | 2013-01-16 | 2013-05-15 | 中国科学院自动化研究所 | Non-contact type intelligent inputting method based on video images and device using the same |
CN105224069A (en) * | 2014-07-03 | 2016-01-06 | 王登高 | The device of a kind of augmented reality dummy keyboard input method and use the method |
CN105446461A (en) * | 2014-06-24 | 2016-03-30 | 北京创思博德科技有限公司 | Gesture recognition method, palm virtual keyboard using same, and input method |
CN106027898A (en) * | 2016-06-21 | 2016-10-12 | 广东申义实业投资有限公司 | Method and apparatus for shooting and displaying object in range of 360 degrees |
CN106155199A (en) * | 2015-09-12 | 2016-11-23 | 北京佳拓思科技有限公司 | Computer system with optical projection input equipment |
CN106845335A (en) * | 2016-11-29 | 2017-06-13 | 歌尔科技有限公司 | Gesture identification method, device and virtual reality device for virtual reality device |
CN106980362A (en) * | 2016-10-09 | 2017-07-25 | 阿里巴巴集团控股有限公司 | Input method and device based on virtual reality scenario |
CN109003473A (en) * | 2018-08-23 | 2018-12-14 | 重庆贝锦科技有限公司 | A kind of interactive mode holography 3D fan instructional device |
-
2019
- 2019-04-23 CN CN201910332812.9A patent/CN110096166A/en active Pending
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20070009207A (en) * | 2005-07-15 | 2007-01-18 | 엘지전자 주식회사 | Apparatus and method for input holographic keyboard in mobile terminal |
CN103105930A (en) * | 2013-01-16 | 2013-05-15 | 中国科学院自动化研究所 | Non-contact type intelligent inputting method based on video images and device using the same |
CN105446461A (en) * | 2014-06-24 | 2016-03-30 | 北京创思博德科技有限公司 | Gesture recognition method, palm virtual keyboard using same, and input method |
CN105224069A (en) * | 2014-07-03 | 2016-01-06 | 王登高 | The device of a kind of augmented reality dummy keyboard input method and use the method |
CN106155199A (en) * | 2015-09-12 | 2016-11-23 | 北京佳拓思科技有限公司 | Computer system with optical projection input equipment |
CN106027898A (en) * | 2016-06-21 | 2016-10-12 | 广东申义实业投资有限公司 | Method and apparatus for shooting and displaying object in range of 360 degrees |
CN106980362A (en) * | 2016-10-09 | 2017-07-25 | 阿里巴巴集团控股有限公司 | Input method and device based on virtual reality scenario |
CN106845335A (en) * | 2016-11-29 | 2017-06-13 | 歌尔科技有限公司 | Gesture identification method, device and virtual reality device for virtual reality device |
WO2018098861A1 (en) * | 2016-11-29 | 2018-06-07 | 歌尔科技有限公司 | Gesture recognition method and device for virtual reality apparatus, and virtual reality apparatus |
CN109003473A (en) * | 2018-08-23 | 2018-12-14 | 重庆贝锦科技有限公司 | A kind of interactive mode holography 3D fan instructional device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109086726B (en) | Local image identification method and system based on AR intelligent glasses | |
JP7110252B2 (en) | Methods and systems for creating virtual and augmented reality | |
US10593025B2 (en) | Method and system for reconstructing obstructed face portions for virtual reality environment | |
US20170103440A1 (en) | Wearable augmented reality eyeglass communication device including mobile phone and mobile computing via virtual touch screen gesture control and neuron command | |
US20170115742A1 (en) | Wearable augmented reality eyeglass communication device including mobile phone and mobile computing via virtual touch screen gesture control and neuron command | |
US20190368868A1 (en) | Method and system for generating a virtual user interface related to a totem | |
CN102591016B (en) | Optimized focal area for augmented reality displays | |
CN102999160B (en) | The disappearance of the real-world object that user controls in mixed reality display | |
CN111833418A (en) | Animation interaction method, device, equipment and storage medium | |
US9696798B2 (en) | Eye gaze direction indicator | |
CN107376349A (en) | The virtual image being blocked is shown | |
CN110018736A (en) | The object via near-eye display interface in artificial reality enhances | |
WO2015006784A2 (en) | Planar waveguide apparatus with diffraction element(s) and system employing same | |
CN111914629A (en) | Method, apparatus, device and storage medium for generating training data for face recognition | |
EP3302740A1 (en) | Reactive animation for virtual reality | |
CN110082911A (en) | For showing the device and method for how staring at the expression of object in display video | |
WO2017042070A1 (en) | A gazed virtual object identification module, a system for implementing gaze translucency, and a related method | |
CN103257703A (en) | Augmented reality device and method | |
Kwon et al. | An enhanced multi-view human action recognition system for virtual training simulator | |
CN112926523B (en) | Eyeball tracking method and system based on virtual reality | |
CN106296796B (en) | Information processing method, information processing unit and user equipment | |
CN114222076A (en) | Face changing video generation method, device, equipment and storage medium | |
CN110096166A (en) | A kind of virtual input method | |
CN210136481U (en) | Virtual input device | |
CN110119197A (en) | A kind of holographic interaction system |
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 |