CN105643265B - A kind of detection method for the cooperation of large-scale workpiece fitting surface - Google Patents
A kind of detection method for the cooperation of large-scale workpiece fitting surface Download PDFInfo
- Publication number
- CN105643265B CN105643265B CN201610018222.5A CN201610018222A CN105643265B CN 105643265 B CN105643265 B CN 105643265B CN 201610018222 A CN201610018222 A CN 201610018222A CN 105643265 B CN105643265 B CN 105643265B
- Authority
- CN
- China
- Prior art keywords
- image
- cooperation
- point
- fitting surface
- coordinate value
- 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.)
- Expired - Fee Related
Links
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B23—MACHINE TOOLS; METAL-WORKING NOT OTHERWISE PROVIDED FOR
- B23P—METAL-WORKING NOT OTHERWISE PROVIDED FOR; COMBINED OPERATIONS; UNIVERSAL MACHINE TOOLS
- B23P19/00—Machines for simply fitting together or separating metal parts or objects, or metal and non-metal parts, whether or not involving some deformation; Tools or devices therefor so far as not provided for in other classes
- B23P19/10—Aligning parts to be fitted together
- B23P19/102—Aligning parts to be fitted together using remote centre compliance devices
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Image Processing (AREA)
- Automatic Assembly (AREA)
Abstract
A kind of detection method for the cooperation of large-scale workpiece fitting surface gathers the installation diagram picture of the fitting surface of two large-scale workpieces including 1, using camera respectively, respectively coordinates image I, cooperation image II；2nd, cooperation image I, cooperation image II are passed in computer, i.e., optional 4 characteristic points in image I is coordinated, and identify the pixel coordinate value of each point, the first step initial parameter for completing image adaptation is set；3rd, selected successively in image II is coordinated and coordinate the identical characteristic point selected in image I, and record the pixel coordinate value for preserving selected point successively according to corresponding order, complete the second step initial parameter setting of image adaptation；4th, according to initial parameter, the conversion relational expression of two images is obtained；5th, according to the characteristic point selected in conversion relational expression and two width cooperation image, the flexible, rotational value during II conversion of cooperation image is acquired, this two images is positioned, completes the assembling process of cooperation image.
Description
Technical field
The invention discloses a kind of detection methods for the cooperation of large-scale workpiece fitting surface, belong to the skill that large-scale workpiece assembles
Art field.
Background technology
It is unable to do without machine in life, and machine is then that the mutual cooperation of multiple parts is needed to assemble is coefficient.
Defined performance requirement can be reached by needing not move through any repair in the mutual assembling process of parts, but for big
For type workpiece, installation combines and verify whether cooperation qualification in the process, it is necessary to which artificial participation can just be completed, and exist
Great work intensity, required labour is more, workpiece loss is big and the adverse effects such as time loss is more.
The content of the invention
Based on technical problem in the prior art, coordinate result and error size in order to obtain and reduce and work
Power, the present invention propose a kind of fitting surface fitting method based on large-scale workpiece, are carried out using the image for representing actual large-scale workpiece
The method coordinated two-by-two saves the troublesome operation of staff, directly by the results show of fitting surface in image assembling, simply
It is convenient, clear objective.
The technical solution adopted by the present invention is as follows：
A kind of detection method for the cooperation of large-scale workpiece fitting surface comprises the following steps：
Step 1, gathered respectively using camera two large-scale workpieces fitting surface installation diagram picture, respectively coordinate image I,
Coordinate image II；
Cooperation image I, cooperation image II are passed in computer by step 2, carry out image procossing, i.e., in image I is coordinated
Optional at least four characteristic point, and identify the pixel coordinate value of each point, the first step initial parameter for completing image adaptation is set
It puts；
Step 3 in image II is coordinated selects and coordinates the identical characteristic point selected in image I successively, and according to
Corresponding order records the pixel coordinate value for preserving selected point successively, and the second step initial parameter for completing image adaptation is set
It puts；
Step 4, the initial parameter determined according to step 2 and step 3 obtain the conversion relational expression of two images；
Step 5 coordinates the characteristic point selected in image according to conversion relational expression and two width, acquires the II conversion of cooperation image
When flexible, rotational value, 4 characteristic points of flexible, rotational value and selection is recycled to position this two images, complete to match somebody with somebody
Close the assembling process of image.
Cooperation image I, cooperation image II described in step 1 from different angle, different distance, different focal length it is same
Etc. contents image.
Record the picture for preserving each point in step 2, step 3 respectively successively according to upper left, lower-left, upper right, the order of bottom right
Plain coordinate value.Record the coordinate value of institute's reconnaissance in sequence, simply according to the quadrangle formed each angle direction
For, convenient for preserving and identifying, and the point recorded between two width mating surfaces is corresponded, convenient for coordinating image I
I is corrected, at the same put selection mistake when can be corrected in real time, the order of 4 points can be chosen in any order, only
It is preserved when being and preserving according to the position of corresponding points.
The characteristic point forms a quadrangle.Four points form quadrangle, two width mating surfaces be remedied to same
In one coordinate system, correction while is that all the points in entire image are carried out to reacquire new coordinate value, is become including geometry
It changes, affine transformation etc., each deformation beneficial to mating surface is corrected and obtains correct testing result, if selected four points
If forming straight line, simply to variations such as the rotation and translations on image progress geometric direction, required knot is not achieved
Fruit causes harmful effect to final cooperation result.
The detailed process of step 4 is as follows：Using the transformational relation between two dimensional image coordinate system, the two of mutual cooperation is acquired
The correspondence parametric variable converted between width image obtains final complete conversion relational expression.
The concrete processing procedure of step 5 is as follows：
The conversion relational expression finally acquired according to step 4 brings the pixel coordinate value of each point coordinated in image II into
The conversion relational expression subsolution goes out the pixel coordinate value of each point in the same coordinate system with cooperation image I, is sat with new pixel
Scale value replaces old pixel coordinate value, assigns the position that each in cooperation image II is put again, then according to cooperation image I with
Anchor point in cooperation image II will coordinate image II to overlap with cooperation image I positioning with characteristic point, draw assembling
Cooperation afterwards is as a result, complete the engagement process of large-scale workpiece fitting surface.
Beneficial effects of the present invention are as follows：
The fitting method only needs a high definition camera that can coordinate well large-scale workpiece, after being coordinated
Error size, save time and cost for the installation and the consume of material of follow-up parts.Its feature is that two width coordinate
Image is derived from different angle, different distance, the image of the equivalence of different focal length, using 4 characteristic points to two width figures
Picture is corrected, and changes its rotation angle, scaling, perspective ratio etc., to obtain all equal two images of each factor,
4 characteristic points is recycled to carry out positioning alignment to two images, correctly to obtain the cooperation result of fitting surface.By using 4 points
To coordinating the research of image flame detection, selection determines optimal parametric variable, becomes so as to fulfill to flexible, the rotation of cooperation image II
Change.
Description of the drawings
Fig. 1 coordinates image I and coordinates the characteristic point example of image II selections；
Fig. 2 large-scale workpiece fitting method systems function diagrams；
Fig. 3 large-scale workpiece fitting method system flow charts.
Specific embodiment
The present invention is described in detail below in conjunction with the accompanying drawings：
As shown in Figure 1-Figure 3, a kind of fitting method for large-scale workpiece fitting surface, mainly includes：The selection of characteristic point,
The positioning of image.Wherein, the selection of characteristic point is arbitrary in mating surface, but four characteristic points have to form quadrangle,
Otherwise mating surface II can not be converted according to mating surface I, causes work invalid；The selection of characteristic point is according to cooperation in mating surface I
Upper left, lower-left, upper right, this four order directions of bottom right in face are chosen, while identify each selected characteristic point successively
Pixel coordinate value, record preserves successively in the order described above；The selection of characteristic point is according to selected in mating surface 1 in mating surface II
Characteristic point choose same characteristic point successively, while the pixel coordinate value of each selected characteristic point is identified, according to upper
Stating order, record preserves successively；The selection of 4 pairs of characteristic points is for contacting between mating surface I and mating surface II, to realize image
Cooperation provides data and supports, the correctness that characteristic point is chosen ensure that the requirement of fit precision；Image is positioned for match somebody with somebody
Conjunction face I is fixed with mating surface II, and when image adaptation overlaps two fixing points, is carried out according still further to 4 corresponding characteristic points
Flexible translation transformation, to reach perfect cooperation together, cooperation result is more accurate.The most result exhibition after image adaptation at last
Now in user, user is facilitated to be analyzed and judged, be that the product quality of large-scale workpiece improves reliable suggestion, it is specific to implement
Method is as follows：
1st, the installation diagram picture of the fitting surface of two large-scale workpieces is gathered respectively using high definition camera, respectively cooperation image I,
Coordinate image II.
2nd, the installation diagram picture of the large-scale workpiece of acquisition is passed in computer, carries out image procossing, appointed in image I is coordinated
4 characteristic points are selected, and identify the pixel coordinate value of each point, are recorded successively according to upper left, lower-left, upper right, the order of bottom right
The pixel coordinate value of characteristic point is preserved, the first step initial parameter for completing image adaptation is set.
3rd, select successively in image II is coordinated and coordinate 4 identical characteristic points selected in image I, and according to phase
Corresponding order records the pixel coordinate value for preserving selected point successively, and the second step initial parameter for completing image adaptation is set.
4th, according to the definite initial parameter of step 2 and step 3, using the transformational relation between two dimensional image coordinate system, ask
The correspondence parametric variable converted between the two images that must be cooperated obtains final complete conversion relational expression.Process is as follows：
The image adaptation principle of large-scale workpiece is coordinated according to the characteristic of homography matrix, for homography matrix
Using it is the matrix of a 3*3, i.e.,：
Include 8 unknown parameters ' values, therefore it is all unknown in homography matrix at least to need 4 pairs of characteristic points that can just be obtained
Parameter value, therefore, all pixels coordinate value according to acquired in step 2 and the selected characteristic point of step 3 is as primary data.
It is a prescription formula, i.e., for the relation function that world coordinate system is converted to two dimensional image coordinate system：
It is obtained according to primary data after homography matrix, you can determine what world coordinate system was converted to two dimensional image coordinate system
Transformational relation functional expression；Four characteristic points selected in world coordinate system are represented, with point P1、P2、P3、P4It represents respectively,
In each point include the actual coordinate value of two values i.e. x and y；It represents selected in two dimensional image coordinate system
4 characteristic points, with point P1′、P2′、P3′、P4' represent respectively, wherein each point includes the pixel of two values i.e. x and y
Coordinate value；
5th, the conversion relational expression between different coordinates is finally acquired according to step 4, each point in image II will be coordinated
Pixel coordinate value bring the conversion relational expression subsolution into and go out pixel coordinate with each points of the cooperation image I in the same coordinate system
Value, old pixel coordinate value is replaced with new pixel coordinate value, assigns the position that each in cooperation image II is put again, then
According to cooperation image I with coordinating the anchor point in image II and 4 characteristic points that image II will be coordinated Chong Die with cooperation image I positioning
Together, the cooperation after assembling is drawn as a result, completing the engagement process of large-scale workpiece fitting surface.
Above-mentioned, although the foregoing specific embodiments of the present invention is described with reference to the accompanying drawings, not protects model to the present invention
The limitation enclosed, those skilled in the art should understand that, based on the technical solutions of the present invention, those skilled in the art are not
Need to make the creative labor the various modifications or changes that can be made still within protection scope of the present invention.
Claims (4)
1. a kind of detection method for the cooperation of large-scale workpiece fitting surface, which is characterized in that comprise the following steps：
Step 1, gathered respectively using camera two large-scale workpieces fitting surface installation diagram picture, respectively coordinate image I, cooperation
Image II；
Cooperation image I, cooperation image II are passed in computer by step 2, carry out image procossing, i.e., in image I is coordinated optionally
At least four characteristic point forms a quadrangle, and according to upper left, lower-left, upper right, the order of bottom right, record preserves respectively respectively successively
The position of a point and pixel value, and identify the pixel coordinate value of each point, the first step initial parameter for completing image adaptation is set
It puts；
Step 3 in image II is coordinated selects and coordinates the identical characteristic point selected in image I successively, forms one four
Side shape, and record preserves position and the pixel value of each point respectively successively, and know according to upper left, lower-left, upper right, the order of bottom right
The not pixel coordinate value of each point, the second step initial parameter for completing image adaptation are set；
Step 4, the initial parameter determined according to step 2 and step 3 obtain the conversion relational expression of two images；
Step 5 coordinates the characteristic point selected in image according to conversion relational expression and two width, acquires when cooperation image II is converted
Flexible, rotational value recycles 4 characteristic points of flexible, rotational value and selection to position this two images, completes cooperation figure
The assembling process of picture.
A kind of 2. detection method for the cooperation of large-scale workpiece fitting surface as described in claim 1, which is characterized in that step 1
Described in cooperation image I, cooperation image II from different angle, different distance, the image of the equivalence of different focal length.
A kind of 3. detection method for the cooperation of large-scale workpiece fitting surface as described in claim 1, which is characterized in that step 4
Detailed process it is as follows：Using the transformational relation between two dimensional image coordinate system, acquire and turn between the two images of mutual cooperation
The correspondence parametric variable changed obtains final complete conversion relational expression.
A kind of 4. detection method for the cooperation of large-scale workpiece fitting surface as described in claim 1, which is characterized in that step 5
Concrete processing procedure it is as follows：
The conversion relational expression finally acquired according to step 4 brings the pixel coordinate value of each point coordinated in image II into this turn
The pixel coordinate value for each point that relational expression subsolution goes out with cooperation image I in the same coordinate system is changed, with new pixel coordinate value
Instead of old pixel coordinate value, the position that each in cooperation image II is put is assigned again, then according to cooperation image I and cooperation
Anchor point in image II will coordinate image II to overlap with cooperation image I positioning with characteristic point, draw after assembling
Cooperation is as a result, complete the engagement process of large-scale workpiece fitting surface.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610018222.5A CN105643265B (en) | 2016-01-12 | 2016-01-12 | A kind of detection method for the cooperation of large-scale workpiece fitting surface |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610018222.5A CN105643265B (en) | 2016-01-12 | 2016-01-12 | A kind of detection method for the cooperation of large-scale workpiece fitting surface |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105643265A CN105643265A (en) | 2016-06-08 |
| CN105643265B true CN105643265B (en) | 2018-05-22 |
Family
ID=56486589
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610018222.5A Expired - Fee Related CN105643265B (en) | 2016-01-12 | 2016-01-12 | A kind of detection method for the cooperation of large-scale workpiece fitting surface |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105643265B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106767714B (en) * | 2016-11-29 | 2019-06-21 | 上海卫星工程研究所 | Improve the equivalent mismatch model multistage Calibration Method of satellite image positioning accuracy |
| CN108241858B (en) * | 2016-12-23 | 2022-03-11 | 上海锦渡信息科技有限公司 | Two-stage image separation type positioning acquisition method and system |
| CN109093375B (en) * | 2018-11-06 | 2023-11-03 | 中国工程物理研究院激光聚变研究中心 | Flexible assembly method and assembly device for assembling and calibrating precise element |
| CN112123251B (en) * | 2020-08-31 | 2022-04-15 | 广东工业大学 | Offshore wind turbine bolt set centering method based on visual tracking |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP3889650B2 (en) * | 2002-03-28 | 2007-03-07 | 三洋電機株式会社 | Image processing method, image processing apparatus, computer program, and recording medium |
| CN100412694C (en) * | 2005-03-30 | 2008-08-20 | 北京大学 | Automatic spherical panorama generation method |
| CN101710932B (en) * | 2009-12-21 | 2011-06-22 | 华为终端有限公司 | Image stitching method and device |
| CN101839692B (en) * | 2010-05-27 | 2012-09-05 | 西安交通大学 | Method for measuring three-dimensional position and stance of object with single camera |
| CN104729406B (en) * | 2015-03-23 | 2017-06-13 | 上海瑞伯德智能系统股份有限公司 | A kind of machine vision localization method of element pasted on surface |
| CN105118021B (en) * | 2015-07-28 | 2019-04-19 | 深圳市汇川技术股份有限公司 | Method for registering images and system based on characteristic point |
-
2016
- 2016-01-12 CN CN201610018222.5A patent/CN105643265B/en not_active Expired - Fee Related
Also Published As
| Publication number | Publication date |
|---|---|
| CN105643265A (en) | 2016-06-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105643265B (en) | A kind of detection method for the cooperation of large-scale workpiece fitting surface | |
| Jia et al. | Image stitching using structure deformation | |
| CN100430690C (en) | Method for making three-dimensional measurement of objects utilizing single digital camera to freely shoot | |
| CN103838437A (en) | Touch positioning control method based on projection image | |
| CN111047510A (en) | Large-field-angle image real-time splicing method based on calibration | |
| CN100461820C (en) | Image processing device and registration data generation method in image processing | |
| CN103414910B (en) | Low-distortion three-dimensional picture outer polar line correcting method | |
| CN110246161B (en) | Method for seamless splicing of 360-degree panoramic images | |
| CN104715487A (en) | Method for sub-pixel edge detection based on pseudo Zernike moments | |
| Kudoh et al. | Painting robot with multi-fingered hands and stereo vision | |
| WO2019059343A1 (en) | Workpiece information processing device and recognition method of workpiece | |
| CN107356213A (en) | Optical filter concentricity measuring method and terminal device | |
| CN110807459A (en) | License plate correction method and device and readable storage medium | |
| CN102982524A (en) | Splicing method for corn ear order images | |
| Yao et al. | Relative camera refinement for accurate dense reconstruction | |
| CN102073997B (en) | Small-square document image perspective-recovery method | |
| CN116758063B (en) | Workpiece size detection method based on image semantic segmentation | |
| CN111047513B (en) | Robust image alignment method and device for cylindrical panorama stitching | |
| CN107705244B (en) | Edge connection correction method suitable for large-area multi-remote sensing image | |
| CN114331833B (en) | Bottle label stable high-quality splicing method based on calibration and accurate geometric structure | |
| CN106023169A (en) | Garment-making cutting piece cross stripe alignment method based on image matching | |
| Möller et al. | 3D reconstruction of on-/offshore wind turbines for manual and computational visual inspection | |
| CN106651950B (en) | Single-camera pose estimation method based on quadratic curve perspective projection invariance | |
| CN115147490A (en) | 6D pose estimation data set manufacturing method, device and system | |
| CN113344782A (en) | Image splicing method and device, storage medium and electronic device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C41 | Transfer of patent application or patent right or utility model | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20160729 Address after: The central nanxinzhuang Ji'nan Road, No. 336 of 250022 cities in Shandong Province Applicant after: University of Jinan Applicant after: Shandong Provincial Communications Planning and Design Institute Address before: The central nanxinzhuang Ji'nan Road, No. 336 of 250022 cities in Shandong Province Applicant before: University of Jinan |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20180522 Termination date: 20190112 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |