CN108734135A - A kind of acquisition methods and device of training image - Google Patents
A kind of acquisition methods and device of training image Download PDFInfo
- Publication number
- CN108734135A CN108734135A CN201810497451.9A CN201810497451A CN108734135A CN 108734135 A CN108734135 A CN 108734135A CN 201810497451 A CN201810497451 A CN 201810497451A CN 108734135 A CN108734135 A CN 108734135A
- Authority
- CN
- China
- Prior art keywords
- image
- regions
- pixel
- hand
- depth image
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Psychiatry (AREA)
- Social Psychology (AREA)
- Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
This disclosure relates to image identification technical field, and in particular to a kind of acquisition methods of training image, a kind of acquisition device of training image.The method includes：Obtain the coloured image and depth image of the hand for wearing colored gloves, wherein the colour gloves include multiple color regions；It identifies the color region in the coloured image belonging to each pixel and is marked；The label of each pixel in the depth image is obtained according to the pixel correspondence between the depth image and the coloured image；Using the depth image of label as training image.The disclosure can utilize the correspondence according to each pixel in depth image and coloured image, depth image is marked automatically, it can effectively ensure that the accuracy of depth image label, and the labeling effciency to depth image can be improved, and then improve the accuracy of gesture identification.
Description
Technical field
This disclosure relates to image identification technical field, and in particular to a kind of acquisition methods of training image, a kind of training figure
The acquisition device of picture.
Background technology
With the development of AI (Artificial Intelligence, artificial intelligence) technology, by a large amount of reference numerals
According to being trained, to obtain the mainstream solution that good recognition performance has become image recognition technology.And image is known
The key of other technology is efficient model (algorithm) and accurate flag data.Possess and largely marks accurate data for carrying
The result of hi-vision identification is of great significance.
For the gesture identification in image recognition technology, two-dimentional gesture identification and three-dimension gesture can generally be divided to know.
Wherein, for three-dimension gesture identification, the acquisition of training data is a sufficiently complex and cumbersome job.The prior art
When obtaining the training image of three-dimension gesture, the three dimensional space coordinate needs in order to obtain each artis of hand largely mark
Depth image, and the label of depth image is then mainly completed by the way of handmarking by research staff.Such mark
Note mode consumes the plenty of time of research staff.If also, handmarking is of low quality, can will directly affect trained knot
Fruit.And then lead to the mistake of gesture identification.
It should be noted that information is only used for reinforcing the reason to the background of the disclosure disclosed in above-mentioned background technology part
Solution, therefore may include the information not constituted to the prior art known to persons of ordinary skill in the art.
Invention content
The disclosure is designed to provide a kind of acquisition methods method of training image, a kind of acquisition methods of training image
Device, and then one or more caused by the limitation and defect of the relevant technologies is overcome to ask at least to a certain extent
Topic.
Other characteristics and advantages of the disclosure will be apparent from by the following detailed description, or partially by the disclosure
Practice and acquistion.
According to the disclosure in a first aspect, provide a kind of acquisition methods of training image, including：
Obtain the coloured image and depth image of the hand for wearing colored gloves, wherein the colour gloves include multiple
Color region；
It identifies the color region in the coloured image belonging to each pixel and is marked；
It is obtained according to the pixel correspondence between the depth image and the coloured image each in the depth image
The label of pixel；
Using the depth image of label as training image.
In a kind of exemplary embodiment of the disclosure, the method further includes：
Three-dimension gesture identification is carried out according to the training image, to obtain the three dimensional space coordinate of each artis of hand.
In a kind of exemplary embodiment of the disclosure, the coloured image and depth for obtaining the hand for wearing colored gloves
Spending image includes：
The hand for wearing colored gloves is acquired to obtain the coloured silk of each gesture using depth camera under solid background
Color image and depth image.
In a kind of exemplary embodiment of the disclosure, the color area in the identification coloured image belonging to each pixel
Domain and be marked including：
Using image segmentation algorithm to the coloured image according to the color region carry out image segmentation, and to segmentation after
Image in each pixel be marked.
In a kind of exemplary embodiment of the disclosure, multiple color regions of the colour gloves include 12 regions；
Wherein, 10 regions of finger of the corresponding hand, and corresponding each 2 regions of finger；And the corresponding hand
2 regions of palm in portion.
In a kind of exemplary embodiment of the disclosure, multiple color regions of the colour gloves include 16 regions；
Wherein, 14 regions of finger of the corresponding hand；Wherein, 2 regions of corresponding first finger, corresponding second-hand
Refer to, 3 regions of third finger, the 4th finger and the 5th finger；2 regions of palm of the corresponding hand.
In a kind of exemplary embodiment of the disclosure, the method further includes：To each region division front surface region
The rear surface regions and.
In a kind of exemplary embodiment of the disclosure, the adjacent color region is distinguished using different colours.
According to the second aspect of the disclosure, a kind of acquisition device of training image is provided, including：
Image collection module, coloured image and depth image for obtaining the hand for wearing colored gloves, wherein described
Colored gloves include multiple color regions；
Region identification module the color region in the coloured image belonging to each pixel and is marked for identification；
Element marking module, for being obtained according to the pixel correspondence between the depth image and the coloured image
The label of each pixel in the depth image；
Training image acquisition module, the depth image for that will mark is as training image.
In a kind of exemplary embodiment of the disclosure, described device further includes：
Image training module, for carrying out three-dimension gesture identification according to the training image, to obtain each joint of hand
The three dimensional space coordinate of point.
The training image acquisition methods that a kind of embodiment of the disclosure is provided, by the way that there is difference for the configuration of colored gloves
The multiple regions of color, and the coloured image and depth image of the hand of wearing gloves are obtained simultaneously；Further according in coloured image
Each affiliated color of pixel is marked, and is obtained in depth image according to the correspondence of each pixel in depth image and coloured image
Each pixel label, and then the depth image after being marked, to realize the automatic label to depth image, and can
It is effective to ensure the accuracy of depth image label, and the labeling effciency to depth image can be improved.And then improve gesture identification
Accuracy.
It should be understood that above general description and following detailed description is only exemplary and explanatory, not
The disclosure can be limited.
Description of the drawings
The drawings herein are incorporated into the specification and forms part of this specification, and shows the implementation for meeting the disclosure
Example, and together with specification for explaining the principles of this disclosure.It should be evident that the accompanying drawings in the following description is only the disclosure
Some embodiments for those of ordinary skill in the art without creative efforts, can also basis
These attached drawings obtain other attached drawings.
Fig. 1 schematically shows a kind of schematic diagram of the acquisition methods of training image in disclosure exemplary embodiment；
Fig. 2 schematically shows a kind of hand region division schematic diagram in disclosure exemplary embodiment；
Fig. 3 schematically shows in the disclosure exemplary embodiment another kind to the schematic diagram of hand region division；
Fig. 4 schematically shows a kind of composition schematic diagram of the acquisition device of training image in disclosure exemplary embodiment；
Fig. 5 schematically shows a kind of another signal of the acquisition device of training image in disclosure exemplary embodiment
Figure；
Fig. 6 schematically shows a kind of another signal of the acquisition device of training image in disclosure exemplary embodiment
Figure.
Specific implementation mode
Example embodiment is described more fully with reference to the drawings.However, example embodiment can be with a variety of shapes
Formula is implemented, and is not understood as limited to example set forth herein；On the contrary, thesing embodiments are provided so that the disclosure will more
Fully and completely, and by the design of example embodiment comprehensively it is communicated to those skilled in the art.Described feature, knot
Structure or characteristic can be in any suitable manner incorporated in one or more embodiments.
A kind of acquisition methods of training image are provided firstly in this example embodiment, can be applied to three-dimension gesture
Identification.With reference to shown in figure 1, the acquisition methods of above-mentioned training image may comprise steps of：
Step S101 obtains the coloured image and depth image of the hand for wearing colored gloves, wherein the colour gloves
Including multiple color regions；
Step S102 identifies the color region in the coloured image belonging to each pixel and is marked；
Step S103 obtains the depth according to the pixel correspondence between the depth image and the coloured image
The label of each pixel in image；
Step S104, using the depth image of label as training image.
The training image acquisition methods that this example embodiment was provided provided, by having for the configuration of colored gloves
The multiple regions of different colours, and the coloured image and depth image of the hand of wearing gloves are obtained simultaneously；Further according to cromogram
Each affiliated color of pixel is marked as in, and depth map is obtained according to the correspondence of each pixel in depth image and coloured image
The label of each pixel as in, and then the depth image after mark, to which realization is to the automatic label of depth image, and
It can effectively ensure that the accuracy of depth image label, and the labeling effciency to depth image can be improved.And then improve gesture
The accuracy of identification.
In the following, accompanying drawings and embodiments will be combined to each step in the acquisition methods of the training image in this example embodiment
Suddenly it is described in detail.
Step S101 obtains the coloured image and depth image of the hand for wearing colored gloves, wherein the colour gloves
Including multiple color regions.
In this example embodiment, the hand for wearing colored gloves can be carried out using depth camera under solid background
Acquisition is to obtain the coloured image and depth image of each gesture.Above-mentioned gesture can be for example：, hold, capture, palm it is curved
The actions such as bent, digital flexion and hand stretching, extension.Wherein, such as kinect cameras, ratio difficult to understand may be used in above-mentioned depth camera
The equipment such as middle smooth camera.
Above-mentioned colored gloves can include multiple regions, and each region has different colors, and phase can be arranged
Neighbouring region has color different and that color difference is larger, to the convenient Boundary Recognition to each region.
For example, refering to what is shown in Fig. 2, being divided for hand region, and palm of the hand face and the back of the hand face of hand are not differentiated between.It can be with
12 regions are divided to colored gloves, wherein 10 regions of finger of the corresponding hand, and corresponding each 2 regions of finger；
And 2 regions of palm of the corresponding hand.As shown in Fig. 2, can be the palm of the hand face of left hand, then corresponding left hand the back of the hand face
Palm corresponding position be with the left hand palm of the hand face be the same area.
Certainly, in other exemplary embodiments of the disclosure, in order to which hand region division is more in line with human hand
Hand can also be divided into 16 regions by structure with reference to as indicated at 3.Wherein, 14 regions of finger of the corresponding hand；
Wherein, corresponding first finger, 2 regions, corresponding second finger, third finger, the 4th finger and the 5th finger 3 regions；It is right
Answer 2 regions of palm of the hand.
Can also be that hand region distinguishes front surface region and the back side in this illustrative embodiments based on the above
Region is that hand region carries out further region division according to palm of the hand face and the back of the hand face.Distinguishing front surface region and the back side
When region, then when above-mentioned 12 regions of division, colored gloves can be divided 24 regions；Such as the 1st area shown in Fig. 2
Domain may include the 1st region front and the 1st region back side.It, then can be with likewise, be divided into 16 regions for above-mentioned hand
Colored gloves are divided into 32 regions.For example, the 8th region shown in Fig. 3 may include the 8th region front and the 8th region back side.
In addition, for the front surface region and rear surface regions in each region, the mode of average division, i.e. facial area may be used
Area having the same is expected at domain and the back side.Or according to demand or hand shape divides front surface region and the back side and is expected to have not
Same area.The disclosure does not do this particular determination.
Further, between region and region boundary, in each region front surface region and rear surface regions boundary, can
It is divided with the lines using rule, such as straight line, the camber line etc. with fixed radian.It is of course also possible to use irregular
Curve or broken line boundary is divided.The length and width in each region can be set according to hand model.The disclosure
Particular determination is not done to above-mentioned zone boundary, zone length and width.
For the color in each region, adjacent area can be filled using the larger color of heterochromia.Citing
For, the multiple colors such as red, orange, yellow, green, cyan, blue, purple may be used in color.If as shown in Fig. 2, the 1st region use yellow,
Then the 2nd adjacent region, the 3rd region and then orange, cyan can be respectively adopted in the fourth region, purple is filled.
By dividing multiple color areas for colored gloves, and it is filled using different colors for adjacent area, it can
So that the region division of hand is more reasonable, facility is provided for subsequent element marking.And the label of depth image can be made just
Valence is accurate.
Step S102 identifies the color region in the coloured image belonging to each pixel and is marked.
In this example embodiment, after the coloured image and depth image for obtaining each gesture, image point can be utilized
It cuts algorithm and image segmentation is carried out according to the color region to the coloured image, and each pixel in the image after segmentation is carried out
Label.
Specifically, the depth image and color RGB image of each gesture motion can be obtained simultaneously using depth camera.
At this point, can be divided to each color region in RGB image using image segmentation algorithm, to regions of different colours
Interior pixel is marked, that is, obtains the color mark of each pixel.For example, edge can be utilized to be split or color cluster
Mode etc. divides each region in RGB color image, and to each pixel in the region and region of different colours into
Line flag.For example, for clustering algorithm, such as K-means algorithms, mean-shift algorithm (average driftings may be used
Algorithm) etc. to coloured image carry out region division.Using the algorithm above to image carry out region division detailed process be compared with
Conventional image partition method, the disclosure do not do this particular determination.
Step S103 obtains the depth according to the pixel correspondence between the depth image and the coloured image
The label of each pixel in image.
In this example embodiment, if the depth image of a certain gesture is image D, corresponding color RGB image is image
d.If the pixel p in the coloured image d of the gesture in the 1st region is labeled as 1, according to the gesture coloured image and depth image
In each pixel correspondence, then the label of respective pixel P should also be as being 1 in corresponding depth image.It, can based on this
Label according to each pixel in coloured image each pixel progress accurate marker in being is obtained when remote holder is completed to mark
The gesture depth image of note.The label information of each pixel may include the color mark and coordinate label of the pixel in depth image
Deng.
Step S104, using the depth image of label as training image.
It, can be as the instruction of the gesture for the depth image after the label of a certain gesture in this example embodiment
Practice image.For the depth image of each gesture, the set of a training image can also be generated.
Based on the above, the method for the offer of the disclosure can also include：
Step S105 carries out three-dimension gesture identification, to obtain the three-dimensional of each artis of hand according to the training image
Space coordinate.
The acquisition methods for the training image that the disclosure provides, by the color RGB image and depth that obtain different gestures simultaneously
Image is spent, and first each pixel in coloured image is marked, further according to pair of each pixel in depth image and coloured image
It should be related to, respective pixel in depth image is marked using the label of each pixel in coloured image, to realize to depth
The automatic label of image.It can effectively ensure that the accuracy to each element marking in depth image, and can improve to depth map
The labeling effciency of picture.And then effectively improve the accuracy of gesture identification.
Further, it refering to what is shown in Fig. 4, also providing a kind of acquisition device 4 of training image in this exemplary embodiment, wraps
It includes：Image collection module 41, region identification module 42, element marking module 43 and training image acquisition module 44.Wherein：
Described image acquisition module 41 can be used for obtaining the coloured image and depth image for the hand for wearing colored gloves,
Wherein, the colored gloves include multiple color regions.
The region identification module 42 can be used for identifying that the color region in the coloured image belonging to each pixel is gone forward side by side
Line flag.
The element marking module 43 can be used for according to the pixel pair between the depth image and the coloured image
Answer the label of each pixel in depth image described in Relation acquisition.
The depth image that the training image acquisition mould 44 can be used for mark is as training image.
Further, in this exemplary embodiment, the acquisition device 4 of above-mentioned training image can also include that image is instructed
Practice module.
Described image training module can be used for carrying out three-dimension gesture identification according to the training image, each to obtain hand
The three dimensional space coordinate of a artis.
Further, in this exemplary embodiment, above-mentioned image collection module 41 may include：Under solid background
The hand for wearing colored gloves is acquired to obtain the coloured image and depth image of each gesture using depth camera.
Further, in this exemplary embodiment, the region identification module 42 may include：It is calculated using image segmentation
Method carries out image segmentation to the coloured image according to the color region, and to each pixel in the image after segmentation into rower
Note.
Further, in this exemplary embodiment, the acquisition device 4 of above-mentioned training image can also include：Region
Division module.
The region division module can be used for multiple color regions of the colored gloves dividing 12 regions；Its
In, 10 regions of finger of the corresponding hand, and corresponding each 2 regions of finger；And 2, the palm of the corresponding hand
Region.
Alternatively, including 16 regions by multiple color regions of the colored gloves；
Wherein, 14 regions of finger of the corresponding hand；Wherein, 2 regions of corresponding first finger, corresponding second-hand
Refer to, 3 regions of third finger, the 4th finger and the 5th finger；2 regions of palm of the corresponding hand.
Further, in this exemplary embodiment, above-mentioned region division module can also include：Positive and negative region division
Module.
The positive and negative region division module can be used for each region division front surface region and rear surface regions.
Further, in this exemplary embodiment, the acquisition device 4 of above-mentioned training image can also include：Color
Configuration module.
The color configuration module can be used for distinguishing adjacent area using different colours.
The detail of each module is in the acquisition of corresponding training image in the acquisition device of above-mentioned training image
It is described in detail in method, therefore details are not described herein again.
It should be noted that although being referred to several modules or list for acting the equipment executed in above-detailed
Member, but this division is not enforceable.In fact, according to embodiment of the present disclosure, it is above-described two or more
The feature and function of module either unit can embody in a module or unit.Conversely, an above-described mould
Either the feature and function of unit can be further divided into and embodied by multiple modules or unit block.
In an exemplary embodiment of the disclosure, a kind of acquisition methods that can realize above-mentioned training image are additionally provided
Electronic equipment.
Person of ordinary skill in the field it is understood that various aspects of the invention can be implemented as system, method or
Program product.Therefore, various aspects of the invention can be embodied in the following forms, i.e.,：It is complete hardware embodiment, complete
The embodiment combined in terms of full Software Implementation (including firmware, microcode etc.) or hardware and software, can unite here
Referred to as circuit, " module " or " system ".
The electronic equipment 600 of this embodiment according to the present invention is described referring to Fig. 5.The electronics that Fig. 5 is shown
Equipment 600 is only an example, should not bring any restrictions to the function and use scope of the embodiment of the present invention.
As shown in figure 5, electronic equipment 600 is showed in the form of universal computing device.The component of electronic equipment 600 can wrap
It includes but is not limited to：Above-mentioned at least one processing unit 610, above-mentioned at least one storage unit 620, connection different system component
The bus 630 of (including storage unit 620 and processing unit 610).
Wherein, the storage unit has program stored therein code, and said program code can be held by the processing unit 610
Row so that the processing unit 610 executes various according to the present invention described in above-mentioned " illustrative methods " part of this specification
The step of illustrative embodiments.For example, the processing unit 610 can execute S101 as shown in Figure 1：It obtains and wears coloured silk
The coloured image and depth image of the hand of color gloves, wherein the colour gloves include multiple color regions；S102：Identification
Color region in the coloured image belonging to each pixel is simultaneously marked；S103：According to the depth image and the colour
Pixel correspondence between image obtains the label of each pixel in the depth image；S104：By the depth map of label
As being used as training image.
Storage unit 620 may include the readable medium of volatile memory cell form, such as Random Access Storage Unit
(RAM) 6201 and/or cache memory unit 6202, it can further include read-only memory unit (ROM) 6203.
Storage unit 620 can also include program/utility with one group of (at least one) program module 6205
6204, such program module 6205 includes but not limited to：Operating system, one or more application program, other program moulds
Block and program data may include the realization of network environment in each or certain combination in these examples.
Bus 630 can be to indicate one or more in a few class bus structures, including storage unit bus or storage
Cell controller, peripheral bus, graphics acceleration port, processing unit use the arbitrary bus structures in a variety of bus structures
Local bus.
Electronic equipment 600 can also be with one or more external equipments 700 (such as keyboard, sensing equipment, bluetooth equipment
Deng) communication, can also be enabled a user to one or more equipment interact with the electronic equipment 600 communicate, and/or with make
Any equipment that the electronic equipment 600 can be communicated with one or more of the other computing device (such as router, modulation /demodulation
Device etc.) communication.This communication can be carried out by input/output (I/O) interface 650.Also, electronic equipment 600 can be with
By network adapter 660 and one or more network (such as LAN (LAN), wide area network (WAN) and/or public network,
Such as internet) communication.As shown, network adapter 660 is communicated by bus 630 with other modules of electronic equipment 600.
It should be understood that although not shown in the drawings, other hardware and/or software module can not used in conjunction with electronic equipment 600, including but not
It is limited to：Microcode, device driver, redundant processing unit, external disk drive array, RAID system, tape drive and
Data backup storage system etc..
Through the above description of the embodiments, those skilled in the art is it can be readily appreciated that example described herein is implemented
Mode can also be realized by software realization in such a way that software is in conjunction with necessary hardware.Therefore, according to the disclosure
The technical solution of embodiment can be expressed in the form of software products, the software product can be stored in one it is non-volatile
Property storage medium (can be CD-ROM, USB flash disk, mobile hard disk etc.) in or network on, including some instructions are so that a calculating
Equipment (can be personal computer, server, terminal installation or network equipment etc.) is executed according to disclosure embodiment
Method.
In an exemplary embodiment of the disclosure, a kind of computer readable storage medium is additionally provided, energy is stored thereon with
Enough realize the program product of this specification above method.In some possible embodiments, various aspects of the invention may be used also
In the form of being embodied as a kind of program product comprising program code, when described program product is run on the terminal device, institute
State program code for make the terminal device execute described in above-mentioned " illustrative methods " part of this specification according to this hair
The step of bright various illustrative embodiments.
Refering to what is shown in Fig. 6, describing the program product for realizing the above method according to the embodiment of the present invention
800, portable compact disc read only memory (CD-ROM) may be used and include program code, and can in terminal device,
Such as it is run on PC.However, the program product of the present invention is without being limited thereto, in this document, readable storage medium storing program for executing can be with
To be any include or the tangible medium of storage program, the program can be commanded execution system, device either device use or
It is in connection.
The arbitrary combination of one or more readable mediums may be used in described program product.Readable medium can be readable letter
Number medium or readable storage medium storing program for executing.Readable storage medium storing program for executing for example can be but be not limited to electricity, magnetic, optical, electromagnetic, infrared ray or
System, device or the device of semiconductor, or the arbitrary above combination.The more specific example of readable storage medium storing program for executing is (non exhaustive
List) include：It is electrical connection, portable disc, hard disk, random access memory (RAM) with one or more conducting wires, read-only
Memory (ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disc read only memory
(CD-ROM), light storage device, magnetic memory device or above-mentioned any appropriate combination.
Computer-readable signal media may include in a base band or as the data-signal that a carrier wave part is propagated,
In carry readable program code.The data-signal of this propagation may be used diversified forms, including but not limited to electromagnetic signal,
Optical signal or above-mentioned any appropriate combination.Readable signal medium can also be any readable Jie other than readable storage medium storing program for executing
Matter, which can send, propagate either transmission for used by instruction execution system, device or device or and its
The program of combined use.
The program code for including on readable medium can transmit with any suitable medium, including but not limited to wirelessly, have
Line, optical cable, RF etc. or above-mentioned any appropriate combination.
It can be write with any combination of one or more programming languages for executing the program that operates of the present invention
Code, described program design language include object oriented program language-Java, C++ etc., further include conventional
Procedural programming language-such as " C " language or similar programming language.Program code can be fully in user
It executes on computing device, partly execute on a user device, being executed as an independent software package, partly in user's calculating
Upper side point is executed or is executed in remote computing device or server completely on a remote computing.It is being related to far
In the situation of journey computing device, remote computing device can pass through the network of any kind, including LAN (LAN) or wide area network
(WAN), it is connected to user calculating equipment, or, it may be connected to external computing device (such as utilize ISP
To be connected by internet).
In addition, above-mentioned attached drawing is only the schematic theory of the processing included by method according to an exemplary embodiment of the present invention
It is bright, rather than limit purpose.It can be readily appreciated that the time that above-mentioned processing shown in the drawings did not indicated or limited these processing is suitable
Sequence.In addition, being also easy to understand, these processing for example can be executed either synchronously or asynchronously in multiple modules.
Those skilled in the art after considering the specification and implementing the invention disclosed here, will readily occur to its of the disclosure
His embodiment.This application is intended to cover any variations, uses, or adaptations of the disclosure, these modifications, purposes or
Adaptive change follow the general principles of this disclosure and include the undocumented common knowledge in the art of the disclosure or
Conventional techniques.The description and examples are only to be considered as illustrative, and the true scope and spirit of the disclosure are by claim
It points out.
It should be understood that the present disclosure is not limited to the precise structures that have been described above and shown in the drawings, and
And various modifications and changes may be made without departing from the scope thereof.The scope of the present disclosure is only limited by the attached claims.
Claims (10)
1. a kind of acquisition methods of training image, which is characterized in that including：
Obtain the coloured image and depth image of the hand for wearing colored gloves, wherein the colour gloves include multiple colors
Region；
It identifies the color region in the coloured image belonging to each pixel and is marked；
Each pixel in the depth image is obtained according to the pixel correspondence between the depth image and the coloured image
Label；
Using the depth image of label as training image.
2. according to the method described in claim 1, it is characterized in that, the method further includes：
Three-dimension gesture identification is carried out according to the training image, to obtain the three dimensional space coordinate of each artis of hand.
3. according to the method described in claim 1, it is characterized in that, the coloured image for obtaining the hand for wearing colored gloves
Include with depth image：
The hand for wearing colored gloves is acquired to obtain the cromogram of each gesture using depth camera under solid background
Picture and depth image.
4. method according to claim 1 or 3, which is characterized in that in the identification coloured image belonging to each pixel
Color region and be marked including：
Image segmentation is carried out according to the color region to the coloured image using image segmentation algorithm, and to the figure after segmentation
Each pixel is marked as in.
5. according to the method described in claim 1, it is characterized in that, multiple color regions of the colour gloves include 12 areas
Domain；
Wherein, 10 regions of finger of the corresponding hand, and corresponding each 2 regions of finger；And the corresponding hand
2 regions of palm.
6. according to the method described in claim 1, it is characterized in that, multiple color regions of the colour gloves include 16 areas
Domain；
Wherein, 14 regions of finger of the corresponding hand；Wherein, corresponding first finger, 2 regions, corresponding second finger, the
3 regions of three fingers, the 4th finger and the 5th finger；2 regions of palm of the corresponding hand.
7. method according to claim 5 or 6, which is characterized in that the method further includes：Just to each region division
Face region and rear surface regions.
8. method according to claim 5 or 6, which is characterized in that the adjacent color region is distinguished using different colours.
9. a kind of acquisition device of training image, which is characterized in that including：
Image collection module, coloured image and depth image for obtaining the hand for wearing colored gloves, wherein the colour
Gloves include multiple color regions；
Region identification module the color region in the coloured image belonging to each pixel and is marked for identification；
Element marking module, described in being obtained according to the pixel correspondence between the depth image and the coloured image
The label of each pixel in depth image；
Training image acquisition module, the depth image for that will mark is as training image.
10. device according to claim 9, which is characterized in that described device further includes：
Image training module, for carrying out three-dimension gesture identification according to the training image, to obtain each artis of hand
Three dimensional space coordinate.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810497451.9A CN108734135A (en) | 2018-05-22 | 2018-05-22 | A kind of acquisition methods and device of training image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810497451.9A CN108734135A (en) | 2018-05-22 | 2018-05-22 | A kind of acquisition methods and device of training image |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108734135A true CN108734135A (en) | 2018-11-02 |
Family
ID=63934966
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810497451.9A Pending CN108734135A (en) | 2018-05-22 | 2018-05-22 | A kind of acquisition methods and device of training image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108734135A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111127535A (en) * | 2019-11-22 | 2020-05-08 | 北京华捷艾米科技有限公司 | Hand depth image processing method and device |
| CN111695585A (en) * | 2019-03-14 | 2020-09-22 | 顶级手套国际有限公司 | Glove taking and placing method and system |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104167016A (en) * | 2014-06-16 | 2014-11-26 | 西安工业大学 | Three-dimensional motion reconstruction method based on RGB color and depth image |
| CN105389539A (en) * | 2015-10-15 | 2016-03-09 | 电子科技大学 | Three-dimensional gesture estimation method and three-dimensional gesture estimation system based on depth data |
-
2018
- 2018-05-22 CN CN201810497451.9A patent/CN108734135A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104167016A (en) * | 2014-06-16 | 2014-11-26 | 西安工业大学 | Three-dimensional motion reconstruction method based on RGB color and depth image |
| CN105389539A (en) * | 2015-10-15 | 2016-03-09 | 电子科技大学 | Three-dimensional gesture estimation method and three-dimensional gesture estimation system based on depth data |
Non-Patent Citations (2)
| Title |
|---|
| WANG,RY 等: "Real-time hand-tracking with a color glove", 《ACM TRANSACTIONS ON GRAPHICS》 * |
| 王豫: "基于Kinect的手臂关节三维运动捕获", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111695585A (en) * | 2019-03-14 | 2020-09-22 | 顶级手套国际有限公司 | Glove taking and placing method and system |
| CN111127535A (en) * | 2019-11-22 | 2020-05-08 | 北京华捷艾米科技有限公司 | Hand depth image processing method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP7248799B2 (en) | IMAGE PROCESSING METHOD, IMAGE PROCESSING APPARATUS, COMPUTER PROGRAM, AND IMAGE PROCESSING DEVICE | |
| WO2021120834A1 (en) | Biometrics-based gesture recognition method and apparatus, computer device, and medium | |
| US20180082178A1 (en) | Information processing device | |
| US20200184721A1 (en) | 3d hand shape and pose estimation | |
| JP2021518022A (en) | Hand key point recognition model training method and its device, hand key point recognition method and its device, and computer program | |
| CN108197547A (en) | Face pose estimation, device, terminal and storage medium | |
| US11934485B2 (en) | Method and apparatus for generating training sample of semantic segmentation model, storage medium, and electronic device | |
| CN109344804A (en) | A kind of recognition methods of laser point cloud data, device, equipment and medium | |
| CN107992188A (en) | Virtual reality exchange method, device and system | |
| CN106547356A (en) | Intelligent interactive method and device | |
| CN108885801A (en) | Information processing apparatus, information processing method, and program | |
| CN107203963A (en) | A kind of image processing method and device, electronic equipment | |
| CN110807379B (en) | Semantic recognition method, semantic recognition device and computer storage medium | |
| CN110536006A (en) | A kind of object's position method of adjustment and electronic equipment | |
| CN108734135A (en) | A kind of acquisition methods and device of training image | |
| CN104866824A (en) | Manual alphabet identification method based on Leap Motion | |
| CN110188766A (en) | Image major heading detection method and device based on convolutional neural networks | |
| CN108549487A (en) | Virtual reality exchange method and device | |
| CN109623848A (en) | A kind of hotel service robot | |
| CN107818709A (en) | Interactive and game clearance theory exploitation automotive practical-training equipment method is touched based on point | |
| CN114049674A (en) | Three-dimensional face reconstruction method, device and storage medium | |
| CN109815854A (en) | It is a kind of for the method and apparatus of the related information of icon to be presented on a user device | |
| CN113989462A (en) | Railway signal indoor equipment maintenance system based on augmented reality | |
| CN104123008B (en) | A kind of man-machine interaction method and system based on static gesture | |
| CN109901705A (en) | Information processing unit and the computer-readable medium for storing program |
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 |