CN107221000A - Acupoint Visualization Platform and its image processing method based on augmented reality - Google Patents
Acupoint Visualization Platform and its image processing method based on augmented reality Download PDFInfo
- Publication number
- CN107221000A CN107221000A CN201710231105.1A CN201710231105A CN107221000A CN 107221000 A CN107221000 A CN 107221000A CN 201710231105 A CN201710231105 A CN 201710231105A CN 107221000 A CN107221000 A CN 107221000A
- Authority
- CN
- China
- Prior art keywords
- acupoint
- image
- point
- acupuncture point
- platform
- 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
- 230000003190 augmentative effect Effects 0.000 title claims abstract description 21
- 238000012800 visualization Methods 0.000 title claims abstract description 19
- 238000003672 processing method Methods 0.000 title claims abstract description 10
- 238000001467 acupuncture Methods 0.000 claims abstract description 35
- 238000011161 development Methods 0.000 claims abstract description 35
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 claims description 15
- 230000009466 transformation Effects 0.000 claims description 13
- 238000000034 method Methods 0.000 claims description 12
- 210000002659 acromion Anatomy 0.000 claims description 11
- 238000011160 research Methods 0.000 claims description 11
- 230000000007 visual effect Effects 0.000 claims description 11
- 238000007781 pre-processing Methods 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 9
- 239000011159 matrix material Substances 0.000 claims description 7
- 238000000605 extraction Methods 0.000 claims description 6
- 230000006870 function Effects 0.000 claims description 5
- 238000006243 chemical reaction Methods 0.000 claims description 4
- 238000004891 communication Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 claims description 3
- SZGZILRQIYNODJ-UHFFFAOYSA-L disodium;7,12-dihydroquinoxalino[3,2-b]phenazine-2,9-disulfonate Chemical compound [Na+].[Na+].[O-]S(=O)(=O)C1=CC=C2N=C(C=C3C(NC4=CC=C(C=C4N3)S(=O)(=O)[O-])=C3)C3=NC2=C1 SZGZILRQIYNODJ-UHFFFAOYSA-L 0.000 claims 2
- 230000009286 beneficial effect Effects 0.000 abstract description 3
- 238000004458 analytical method Methods 0.000 abstract description 2
- 230000003993 interaction Effects 0.000 abstract 1
- 238000005516 engineering process Methods 0.000 description 8
- 239000003814 drug Substances 0.000 description 4
- 238000002474 experimental method Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 230000001419 dependent effect Effects 0.000 description 2
- 230000004438 eyesight Effects 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000007654 immersion Methods 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 235000001968 nicotinic acid Nutrition 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 238000011426 transformation method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/50—Depth or shape recovery
- G06T7/55—Depth or shape recovery from multiple images
-
- G06T3/02—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2200/00—Indexing scheme for image data processing or generation, in general
- G06T2200/08—Indexing scheme for image data processing or generation, in general involving all processing steps from image acquisition to 3D model generation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2200/00—Indexing scheme for image data processing or generation, in general
- G06T2200/28—Indexing scheme for image data processing or generation, in general involving image processing hardware
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
Abstract
The present invention provides a kind of acupoint Visualization Platform based on augmented reality, and the platform includes the FPGA development boards and host computer of interconnection.IMAQ control module is write with pretreatment module using Verilog HDL language, and is downloaded in the fpga chip of FPGA development boards, and host computer is responsible for acupoint information being accurately registered on image and communicated with FPGA development boards.There is provided a kind of image processing method of acupoint Visualization Platform simultaneously.Beneficial effect is that the platform is that the shortcoming for making up original acupuncture teaching gimmick has major and immediate significance and use value, also a kind of interaction, dynamic, intuitively model have been provided the user, be clinic of the traditional Chinese medical science, impart knowledge to students it is a kind of intuitively, beneficial to the powerful of complete observation and comprehensive analysis.
Description
Technical field
The present invention relates to image processing field, refer specifically to a kind of acupoint Visualization Platform based on augmented reality and its
Image processing method.
Technical background
Chinese medicine acupuncture is the rarity of Chinese nation's medical science, its exclusive dredging the channel, the curative effect of YIN and YANG balance regulating in recent years by
To the concern and favor of increasing some medical workers both at home and abroad.With the international development process of the traditional Chinese medical science, with allusion
The science of channels and collaterals starts upsurge in countries in the world for the acupuncture technique of core, and the demand of study acupuncture skill also increasingly increases.It is existing
Acupuncture teaching method is generally operated on oneself body using diagram, clinical, collaterals of human acupoint model or student, is trained and mutually tied
The mode of conjunction, therefore have that acupuncture skill is directly perceived, teaching efficiency is not obvious, the shortcomings of Students ' Learning is dangerous big.Therefore, build
Found an acupoint visual research platform extremely urgent., can be fine using augmented reality by investigating and analyzing
Ground is visualized acupuncture skill with human body acupuncture point information.
Augmented reality (Augmented Reality, AR) is on virtual reality (Virtual Reality, VR) basis
On the new technology that grows up, be called and do mixed reality.In the early 1980s, VPL companies of the U.S. propose on computers
Create it is complete, on the spot in person interact 3D environment, to provide the user feeling of immersion, this technology is exactly virtual reality skill
Art.But virtual reality is the virtual environment (Virtual Environment, VE) that user is immersed in computer creation
In, it is isolated with the real world, so that user loses the chance interacted with real world.Therefore, in order to overcome this
The problem of kind, has just developed augmented reality on the basis of virtual reality.Augmented reality is to observe generation using virtualization technology
A kind of mode on boundary, is, using technologies such as computer visions, to pass through the addition that real-time media is as seamless as possible into true environment
Dummy object generated by computer and non-existent, so as to reach the mesh in the real world that enhancing or supplement user are seen
's.Interactive by being carried out with virtual image, user can complete more complicated work.Augmented reality is before the application of medical domain
Scape widely, can be applied to auxiliary diagnosis, and medical education and training etc. are all multi-direction.But it is there is not yet visual in Chinese medicine acupuncture
Application in terms of change.
In recent years, field programmable gate array (Field Programmable Gate Array, FPGA) technology gradually exists
Biomedical sector is widely used.In the implementation method of hardware, compared to extensive Analogous Integrated Electronic Circuits flexibility
Poor the shortcomings of, FPGA has calculating speed fast, small volume, the characteristics of concurrent operation, therefore it is flat to be widely used in bionics, intelligence
In terms of platform, image procossing.
Existing technology is scarcely out of swaddling-clothes, therefore still suffers from following shortcoming:It there is no the function based on augmented reality complete
Kind acupoint Visualization Platform;With camera calibration, traditional actual situation register method of coordinate system transformation has precision concurrently not
Height, the low shortcoming of robustness, and man-machine interface is not perfect enough.The work of camera calibration is also complicated loaded down with trivial details, its inner parameter with
Lens focus once changes, it is necessary to video camera is demarcated again.From current technology level, due to platform in itself
The inexactness and lag characteristic being had, based on camera calibration and world coordinate system, camera coordinate system, image coordinate system
The method of conversion can not solve the actual situation registration problem of AR applications well.
The content of the invention
For deficiency present in above-mentioned technology, it is an object of the invention to provide a kind of acupoint based on augmented reality
Visualization Platform and its image processing method, are calculated using FPGA image preprocessings ability and host computer feature extraction with affine transformation
Method, realizes virtual acupoint information being accurately registered on the image that binocular camera is obtained;It is strong to solve acupoint positioning
With acupuncture skill is directly perceived, the unconspicuous problem of teaching efficiency, improve the interactivity of platform and user, dynamic with it is directly perceived
Property so that the solution of actual situation registration problem is no longer dependent on the calibration of camera internal and external parameter, simplifies virtual acupoint information
Registration.
To achieve the above object, the technical solution adopted by the present invention be to provide a kind of acupoint based on augmented reality can
Depending on changing platform, wherein:Acupoint Visualization Platform, it is characterized in that:The platform include binocular camera, FPGA development boards and
Host computer;Binocular camera is connected by GPIO interface with FPGA development boards, and FPGA development boards pass through USB interface and host computer
It is connected;FPGA development boards include IMAQ control module and image pre-processing module, IMAQ control module and figure
As pretreatment module is all write using Verilog HDL language, and compiling is downloaded in the fpga chip of FPGA development boards;
Acupoint information is stored in host computer according to sex, the database developed for acupuncture point Visualization Platform.
Described image acquisition control module is realized by Verilog HDL Programming with Pascal Language, through on USB interface and FPGA development boards
Fpga chip set up data communication, and compile and download in FPGA development boards;IMAQ control module passes through I2C buses pair
Function register is configured, to realize image resolution ratio, frame frequency and the setting as matter parameter of binocular camera.
Color image senser element in the binocular camera is connected with MIPI decoders, by color image sensor
The view data of part collection, which is exported, gives MIPI decoders;The data that MIPI decoders can input color image senser element are simultaneously
Row output, is that follow-up image preprocessing is prepared.
The effect of the present invention is that the Visualization Platform realizes registration of the human acupoint on video camera shooting human body image,
Have visual man-machine interface concurrently, improve platform and interactivity, dynamic and the intuitive of user.Meanwhile, the experiment porch
For the traditional Chinese medical science clinic with teaching provide it is a kind of intuitively, beneficial to the powerful of complete observation and comprehensive analysis.This platform is carried
Go out and had the advantage that the visualization structure that augmented reality is used for traditional Chinese medical science human acupoint:1st, described acupoint information note
Volume module realizes the registration of acupoint information by global affine transformation, by the static registration control errors of augmented reality in minimum model
In enclosing, the required precision of medicine equipment is met;2nd, upper computer software interface can observe camara module in real time in this platform
The image and treatment effect of shooting, more preferable visualized experiment research platform is provided for the quantitative research of Chinese medicine acupuncture.
Brief description of the drawings
Fig. 1 is FPGA hardware of the invention and host computer experiment porch structural representation;
Fig. 2 is camera review acquisition control module hardware architecture diagram;
Fig. 3 is characterized extraction and matching module flow chart;
Fig. 4 is acupoint information Registering modules flow chart.
In figure:
1. the image pre-processing module of 3. IMAQ control module of binocular camera 2.FPGA development boards 4.
5. the collection collection image two of image 1 of binocular human body image acquisition control processing module 6.
8. the host computer Output Display Unit of 9. acupoint information Registering modules of feature extracting and matching module 10.
11.MIPI camara module OV8865 color image sensor 12.MIPI decoders
13.2x20 pin GPIO connectors
Embodiment
With reference to acupoint visual research platform and its image processing method based on augmented reality of the accompanying drawing to the present invention
Method is illustrated.
The design of the acupoint visual research platform and its image processing method based on augmented reality of the present invention is thought
Think to set up IMAQ control module on FPGA development boards first, to realize the control to binocular camera.And to shooting
The real human body image that machine is caught carries out image preprocessing.Binocular vision imaging principle is then based on, is calculated using host computer editor
Method recovers the three-dimensional data information of two dimensional image, and is carried out using the standardized human body's acupoint model data stored in a computer
Affine transformation, so that acupuncture point is registered on real human body image, obtains the acupoint information matched with real human body.
The present invention the acupoint Visualization Platform based on augmented reality include interconnection FPGA development boards and
Host computer.IMAQ control module is write with pretreatment module using Verilog HDL language, and downloads to fpga chip
In, host computer is responsible for acupoint information being accurately registered on image and communicated with FPGA development boards.
The picture format of described image acquisition control module, wherein camera output is Bayer types, can pass through GPIO interface
Access FPGA development boards.Development board needs to be equipped with the MIPI camara module OV8865 color image sensors of 8,000,000 pixels,
In its 8,000,000 pixel, there should be at least 7990272 (3264x2448) pixels to can be used for exporting.Camera function memory parameter by
I2C buses are controlled.Should possess VCM (Voice Coil Motor, VCM) driving cores on the MIPI camara modules of video camera
Piece, for the regulation of camera focal length.In order to which MIPI camara modules are directly accessed into development board, IMAQ control module
Also need to possess MIPI decoders, the view data that MIPI interfaces are inputted is converted to the view data of parallel output.MIPI is solved
Code device is subjected to the reference clock of FPGA inputs, and exports 25MHz clock camera is controlled;
The algorithm that the pretreatment module is related to is realized that compiling downloads to FPGA cores by Verilog HDL Programming with Pascal Language
In piece.Pretreatment module includes image format conversion and handled with gray processing.Wherein, image format conversion uses 2x2 neighborhood territory pixels
Interpolation method is replicated, i.e., image is divided into 2x2 elementary cell according to the characteristics of the color filter array of Bayer picture formats, profit
The color component of missing is supplemented with R, G, B color component in 2x2 elementary cells.Gray processing processing uses weighted average
Value method, the gray level image of different-effect is formed by changing tri- kinds of color weights of R, G, B;
The host computer is connected by USB interface with FPGA development boards realizes data communication, and host computer image procossing is calculated
Method is write by MATLAB, and it includes two parts:Feature extracting and matching module and acupoint information Registering modules.Feature extraction
Realized with matching module by SURF operators.It is all to be less than default extreme value by presetting control of the extreme value realization to feature point number
Value be all dropped, increase extreme value reduces the characteristic point quantity that detects, and finally only several feature point of maximum intensity can be detected
Measure and.By matching the SURF characteristic points in two images, calculate basis matrix F to try to achieve polar curve expression formula, and according to pole
Line constraints is screened to the characteristic point of matching.Acupoint information Registering modules are realized by affine transformation.Application space is affine
Transformation theory, by the way that real scene, video camera and dummy object are defined under same coordinate system, so as to get around different coordinates
The Solve problems of transformational relation between system so that the problem of actual situation is registered is no longer dependent on the demarcation of camera inside and outside parameter.Utilize
Any 4 characteristic points in the two images that previous step is extracted and matched are as on the origin of affine coordinate system and three reference axis
Some projection under binocular camera image coordinate system, in conjunction with the standardized human body's acupuncture points on the human body data stored in a computer
Storehouse carries out affine transformation, so that related acupuncture point is registered on real human body, obtains believing with the acupuncture point that real human body matches
Breath.
What the acupoint Visualization Platform function based on augmented reality of the present invention was realized in:
Need to gather human acupoint spatial position data first.In way of realization, it can be sat in the same world of the same space
Under mark system to the main acupuncture point of many crowds and left acromion, right acromion, anterior superior spine, left eye, right eye 6 characteristic points relative to people
The world coordinate system origin of work setting carries out the collection of locus, so as to constitute human acupoint's model data, and by the acupuncture
Acupoint information is stored in computer according to sex, for the pin position visual research platform development data based on augmented reality
Storehouse.
Secondly, registration human body is treated using binocular camera to be shot.Video camera need to pick up human body to be registered when shooting
Whole body information, that is, obtain people to be registered whole body shine.The whole body shot to video camera is carried according to 6 characteristic points of progress manually
Take, i.e., left acromion, the coordinate of right acromion, anterior superior spine, left eye, right eye under present image coordinate system.Finally by host computer
Registration algorithm carry out acupuncture point registration, realize acupoint Visualization Platform.
As shown in figure 1, using the IMAQ control module 3 in FPGA development boards 2, by I2C buses to image sensing
Device 11 and MIPI decoders 12 are controlled, to realize the shooting work of binocular camera 1.The image of shooting is in FPGA development boards
Image pre-processing module 4 is carried out in 2.Video camera collectively constitutes binocular human body image acquisition control processing module with FPGA development boards
5.The two images 6 and 7 of shooting pass through feature extracting and matching module 8 and acupoint information Registering modules 9 in host computer, realize
The registration at acupuncture point, registering result is exported finally by display 10.
As shown in Fig. 2 being configured to hardware experiment platform, using low-power consumption Cyclone IV EP4CE115F29C7N
Model fpga chip, based on the development platforms of Quartus II 11.0, IMAQ control is write using Verilog HDL language
Module 3, is controlled to I2C buses, to realize the control to MIPI camera colors imaging sensor 11 and MIPI decoders 12
System.Using MIPI decoders 12, view data is carried out to 10bit parallel output, and develop by GPIO interface 13 and FPGA
Plate 2 is connected.
As shown in figure 3, being programmed using MATLAB softwares to host computer feature extraction with characteristic matching module 8.First
Feature extraction and characteristic matching are carried out to input image group using SURF operators.And obtain the basis matrix between two image coordinate systems
F.Secondly, according to epipolar geom etry principle m'T(m and m' are represented in two images corresponding two because of EP point Fm=0 respectively
Match point;Matrix based on F), the corresponding point of two images is located on straight line, i.e. epipolar line restriction, to the spy matched
Levy and screened, final obtain meets the epipolar line restriction feature point group that the match is successful
As shown in figure 4, being programmed using MATLAB softwares to host computer acupoint information Registering modules 9.First from feature
Extract and export the most strong characteristic point of selection 4 in the match is successful point group as world coordinates with matching module 8 and tie up to two width figures
As the projection under coordinate system.Define after origin and 3 reference axis, global affine coordinate system can be just determined, and at this moment be strengthened
The affine coordinate that every bit in reality scene on actual situation object has each self-retaining is represented.Secondly, by obtaining artificial setting
Characteristic point, i.e. eyes, shoulder breadth, the wide transformation matrix between current coordinate system and global affine coordinate system of waist.Finally, with reference to
Transformation matrix and human acupoint's model data, realize the registration of acupoint information.
Claims (3)
1. a kind of acupoint Visualization Platform, it is characterized in that:The platform includes binocular camera (1), FPGA development boards (2)
With host computer (10);Binocular camera is connected by GPIO interface with FPGA development boards (2), and FPGA development boards (2) pass through USB
Interface is connected with host computer (10);FPGA development boards (2) include IMAQ control module (3) and image pre-processing module
(4), IMAQ control module (3) and image pre-processing module (4) are all write using Verilog HDL language, and compile
Translate and download in the fpga chip of FPGA development boards (2);Acupoint information is stored in host computer (10) according to sex, is used for
The database of acupuncture point Visualization Platform exploitation;
Described image acquisition control module (3) is realized by Verilog HDL Programming with Pascal Language, through USB interface and FPGA development boards (2)
On fpga chip set up data communication, and compile and download in FPGA development boards (2);IMAQ control module (3) passes through
I2C buses are configured to function register, to realize the image resolution ratio of binocular camera (1), frame frequency and as matter parameter
Set;
Color image senser element (11) in the binocular camera (1) is connected with MIPI decoders (12), by chromaticity diagram
MIPI decoders are given as the view data of senser element (11) collection is exported;MIPI decoders can be by color image senser element
The data parallel output of input, is that follow-up image preprocessing is prepared.
2. acupoint Visualization Platform according to claim 1, it is characterized in that:The acupuncture point visual research platform is opened
The database of hair includes:The title at the main acupuncture point of human body, under a certain selected world coordinate system each acupuncture point space coordinate
With the left acromion under the same world coordinate system of the same space, right acromion, anterior superior spine, left eye, right eye this six human body spies
Space coordinate a little is levied, acupuncture point visual research platform development database is the different crowd that medical institutions are directed to different age group
Carry out acupuncture point collection and formed;It is in way of realization:To 12 of many crowds under the same world coordinate system of the same space
Main acupuncture point:SHANZHONG acupoint, Guanyuan point, ZHONGWAN acupoint, RUGEN acupoint, RUGEN acupoint, Renzhong acupoint, Jingming acupoint, Shenting point, point st 36, three
Yinjiao point and six characteristic points:Left acromion, right acromion, anterior superior spine, left eye, right eye, relative to the world coordinates manually set
It is that origin carries out the collection of locus, so that human acupoint's model data is constituted, and by the acupoint information according to sex
It is stored in computer, for the acupuncture point visual research platform development database based on augmented reality.
3. the image processing method of acupoint Visualization Platform according to claim 1, it is characterized in that:The processing method
Be binocular camera collection image after image processing method is handled, result is opened with acupuncture point visual research platform
Acupoint information in hair database is matched, and finally realizes acupuncture point being accurately registered on filmed image, this method including with
Lower step:
Step 1
The spatial position data of human acupoint is gathered, is in way of realization:It is right under the same world coordinate system of the same space
The main acupuncture point of 12 of many crowds:SHANZHONG acupoint, Guanyuan point, ZHONGWAN acupoint, RUGEN acupoint, RUGEN acupoint, Renzhong acupoint, Jingming acupoint, Shenting
Cave, point st 36, SANYINJIAO acupoint and six characteristic points:Left acromion, right acromion, anterior superior spine, left eye, right eye, relative to artificial
The world coordinate system origin of setting carries out the collection of locus, so as to constitute human acupoint's model data, and by the acupuncture cave
Position information is stored in host computer according to sex, the database developed for acupuncture point Visualization Platform;
Step 2
By IMAQ control module, to the image resolution ratio of binocular camera, frame frequency and as matter parameter is pre-seted;
Step 3
The binocular camera finished using pre-seting, from the different angle shot two images of same object, its two images should
Whole body information including whole human body;
Step 4
The image of input is pre-processed using the image pre-processing module on FPGA development boards, uses interpolation algorithm will first
The image of Bayer format is converted to the image of PNG format, recycles gray processing Processing Algorithm to handle PNG format image,
The dimensionality reduction of image is realized, the gray level image one and gray level image two of PNG format is finally given;
Step 5
Six characteristic points are extracted to image one and image two on the output display screen of host computer by mouse;Six characteristic points
Position correspond to the left eye and right eye of the both sides acromion of skeleton, both sides anterior superior spine and people respectively, finally obtain this six
Coordinate of the characteristic point under present image coordinate system;These points have recorded the wide information of shoulder breadth, waistline and face of real human body, be imitative
Penetrate the important parameter that virtual acupoint information registration is realized in conversion;
Step 6
Algorithm in host computer includes feature extracting and matching module and acupoint information Registering modules;Feature extracting and matching module
It is made up of SURF operators, acupoint information Registering modules are made up of affine coordinate transformation computing;Image one and image two are carried out
The processing of SURF feature extraction algorithms, and screened according to epipolar line restriction condition;Epipolar line restriction condition refers to two width figures
As corresponding point should be on straight line, i.e., on EP point;Therefore the feature that the match is successful is finally obtained according to the geometrical principle
Point is some;The characteristic point of any four groups of successful match is chosen as a little existing on the origin of affine coordinate system and three reference axis
Projection under binocular camera image coordinate system, in conjunction with acquisition in acupuncture point visual research platform development database and step 5
Six characteristic points image coordinate carry out computing, obtain affine transformation matrix;Affine transformation is two-dimensional coordinate to two-dimensional coordinate
Between linear transformation, realize registration of the acupuncture point on real human body image using the affine transformation matrix, finally give with
The acupoint information that real human body matches.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710231105.1A CN107221000A (en) | 2017-04-11 | 2017-04-11 | Acupoint Visualization Platform and its image processing method based on augmented reality |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710231105.1A CN107221000A (en) | 2017-04-11 | 2017-04-11 | Acupoint Visualization Platform and its image processing method based on augmented reality |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107221000A true CN107221000A (en) | 2017-09-29 |
Family
ID=59928377
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710231105.1A Pending CN107221000A (en) | 2017-04-11 | 2017-04-11 | Acupoint Visualization Platform and its image processing method based on augmented reality |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107221000A (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107898626A (en) * | 2017-12-20 | 2018-04-13 | 大连交通大学 | A kind of binocular vision acupoint positioning instrument and its method of work |
CN108108724A (en) * | 2018-01-19 | 2018-06-01 | 浙江工商大学 | A kind of wagon detector training method learnt automatically based on multiple subarea area image feature |
CN109243575A (en) * | 2018-09-17 | 2019-01-18 | 华南理工大学 | A kind of virtual acupuncture-moxibustion therapy method and system based on mobile interaction and augmented reality |
CN109758355A (en) * | 2019-03-07 | 2019-05-17 | 西安伊蔓蒂电子科技有限公司 | One kind is based on the processing of human acupoint two dimensional image and 3 D stereo localization method |
CN110070788A (en) * | 2019-03-18 | 2019-07-30 | 叶哲伟 | A kind of human body 3D meridian point method for visualizing based on mixed reality |
CN110349661A (en) * | 2019-07-08 | 2019-10-18 | 艾炳蔚 | A kind of acupuncture remote diagnosis system |
US11564633B2 (en) | 2018-12-21 | 2023-01-31 | Industrial Technology Research Institute | State assessment system, diagnosis and treatment system, and method for operating the diagnosis and treatment system |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102622916A (en) * | 2012-03-09 | 2012-08-01 | 浙江大学 | Human body acupuncture point projection demonstration method and device |
CN102743282A (en) * | 2012-07-03 | 2012-10-24 | 成都中医药大学 | Intelligent acupuncture point locating device and method based on image identification |
CN105832528A (en) * | 2016-03-17 | 2016-08-10 | 中国科学院微电子研究所 | Digital human meridian and acupuncture point model display method and device |
-
2017
- 2017-04-11 CN CN201710231105.1A patent/CN107221000A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102622916A (en) * | 2012-03-09 | 2012-08-01 | 浙江大学 | Human body acupuncture point projection demonstration method and device |
CN102743282A (en) * | 2012-07-03 | 2012-10-24 | 成都中医药大学 | Intelligent acupuncture point locating device and method based on image identification |
CN105832528A (en) * | 2016-03-17 | 2016-08-10 | 中国科学院微电子研究所 | Digital human meridian and acupuncture point model display method and device |
Non-Patent Citations (4)
Title |
---|
滕玮等: "仿射变换在增强现实智能针灸系统中的应用研究", 《江苏科技大学学报(自然科学版)》 * |
滕玮等: "基于增强现实技术的智能针灸系统的视觉处理", 《华东船舶工业学院学报(自然科学版)》 * |
蔡成涛、苏丽、梁燕华: "《海洋环境下的计算机视觉技术》", 31 October 2015 * |
郭宝龙、孙伟: "《数字图像处理系统工程导论》", 31 July 2012 * |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107898626A (en) * | 2017-12-20 | 2018-04-13 | 大连交通大学 | A kind of binocular vision acupoint positioning instrument and its method of work |
CN108108724A (en) * | 2018-01-19 | 2018-06-01 | 浙江工商大学 | A kind of wagon detector training method learnt automatically based on multiple subarea area image feature |
CN108108724B (en) * | 2018-01-19 | 2020-05-08 | 浙江工商大学 | Vehicle detector training method based on multi-subregion image feature automatic learning |
CN109243575A (en) * | 2018-09-17 | 2019-01-18 | 华南理工大学 | A kind of virtual acupuncture-moxibustion therapy method and system based on mobile interaction and augmented reality |
CN109243575B (en) * | 2018-09-17 | 2022-04-22 | 华南理工大学 | Virtual acupuncture method and system based on mobile interaction and augmented reality |
US11564633B2 (en) | 2018-12-21 | 2023-01-31 | Industrial Technology Research Institute | State assessment system, diagnosis and treatment system, and method for operating the diagnosis and treatment system |
CN109758355A (en) * | 2019-03-07 | 2019-05-17 | 西安伊蔓蒂电子科技有限公司 | One kind is based on the processing of human acupoint two dimensional image and 3 D stereo localization method |
CN110070788A (en) * | 2019-03-18 | 2019-07-30 | 叶哲伟 | A kind of human body 3D meridian point method for visualizing based on mixed reality |
CN110349661A (en) * | 2019-07-08 | 2019-10-18 | 艾炳蔚 | A kind of acupuncture remote diagnosis system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107221000A (en) | Acupoint Visualization Platform and its image processing method based on augmented reality | |
CN111028330B (en) | Three-dimensional expression base generation method, device, equipment and storage medium | |
CN104318569B (en) | Space salient region extraction method based on depth variation model | |
WO2021184933A1 (en) | Three-dimensional human body model reconstruction method | |
CN110892408A (en) | Systems, methods, and apparatus for stereo vision and tracking | |
CN109934864A (en) | Residual error network depth learning method towards mechanical arm crawl pose estimation | |
CN110363116A (en) | Irregular face antidote, system and medium based on GLD-GAN | |
CN108701359A (en) | Across the video frame tracking interest region with corresponding depth map | |
CN106296825B (en) | A kind of bionic three-dimensional information generating system and method | |
CN111819568A (en) | Method and device for generating face rotation image | |
CN101520902A (en) | System and method for low cost motion capture and demonstration | |
CN109816731A (en) | A kind of method of RGB and depth information accuracy registration | |
CN108230384A (en) | Picture depth computational methods, device, storage medium and electronic equipment | |
CN110914873A (en) | Augmented reality method, device, mixed reality glasses and storage medium | |
CN109191508A (en) | A kind of simulation beauty device, simulation lift face method and apparatus | |
CN110021445A (en) | A kind of medical system based on VR model | |
CN104680570B (en) | A kind of motion capture system and method based on video | |
CN110197156B (en) | Single-image human hand action and shape reconstruction method and device based on deep learning | |
CN112767252B (en) | Image super-resolution reconstruction method based on convolutional neural network | |
CN107481280A (en) | The antidote and computing device of a kind of skeleton point | |
CN106780680A (en) | Three-dimensional animation generation method, terminal and system based on augmented reality | |
CN112365578A (en) | Three-dimensional human body model reconstruction system and method based on double cameras | |
JP2022512262A (en) | Image processing methods and equipment, image processing equipment and storage media | |
CN108509830A (en) | A kind of video data handling procedure and equipment | |
CN108742495A (en) | A kind of three-dimensional stereo laparoscope system and solid matching method for medical field |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170929 |
|
RJ01 | Rejection of invention patent application after publication |