CN109872365A - 3D four-wheel position finder destination disk image-recognizing method - Google Patents
3D four-wheel position finder destination disk image-recognizing method Download PDFInfo
- Publication number
- CN109872365A CN109872365A CN201910126336.5A CN201910126336A CN109872365A CN 109872365 A CN109872365 A CN 109872365A CN 201910126336 A CN201910126336 A CN 201910126336A CN 109872365 A CN109872365 A CN 109872365A
- Authority
- CN
- China
- Prior art keywords
- destination
- disks
- recognizing method
- wheel position
- destination disk
- 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
- 238000000034 method Methods 0.000 title claims abstract description 44
- 238000003491 array Methods 0.000 claims description 3
- 239000003086 colorant Substances 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000009471 action Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000005352 clarification Methods 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
Landscapes
- Length Measuring Devices By Optical Means (AREA)
- Image Analysis (AREA)
Abstract
The present invention relates to a kind of 3D four-wheel position finder destination disk image-recognizing methods, belong to auto industry technical field.3D four-wheel position finder destination disk image-recognizing method of the invention calculates the preliminary threshold of photo first, determines the Position Approximate range of two destination disks；The threshold value of two destination disks is calculated separately again；And then determine all circular centers of circle in two destination disks；After arrangement and export.So as to prepare, efficiently identify the position of the dot in destination disk, the accuracy of four-wheel aligner is further improved.And 3D four-wheel position finder destination disk image-recognizing method implementation of the invention is easy, cost of implementation is cheap, and application range is also quite extensive.
Description
Technical field
The present invention relates to auto industry technical fields, in particular to four-wheel aligner method and technology field, in particular to one kind
3D four-wheel position finder destination disk image-recognizing method.
Background technique
3D four-wheel aligner is the pattern identified in destination disk by machine vision, to obtain destination disk in three-dimensional space
In coordinate, positioning of the Lai Shixian for wheel.
Need to carry out four-wheel aligner just to need to analyze the picture that camera is taken pictures, obtain circle all in pattern and
Calculate the round center of circle.
Machine vision is fast-developing branch of artificial intelligence.In brief, machine vision is exactly to use machine
It measures and judges instead of human eye.NI Vision Builder for Automated Inspection be by machine vision product (i.e. image-pickup device, divide CMOS and
Two kinds of CCD) it target will be ingested is converted into picture signal, it sends dedicated image processing system to, obtains the shape of target subject
State information.According to the information such as pixel distribution and brightness, color, it is transformed into digitized signal；Picture system carries out these signals
Clarification of objective is extracted in various operations, and then the device action at scene is controlled according to the result of differentiation.
In four-wheel position finder product, it is necessary to be applied to this technology.
How to provide efficient, the accurate destination disk image-recognizing method of one kind is this field urgent problem to be solved.
Summary of the invention
The purpose of the present invention is overcome it is above-mentioned in the prior art the shortcomings that, provide it is a kind of it is efficient, accurate 3D four-wheel is fixed
Position instrument destination disk image-recognizing method.
In order to achieve the above purpose, 3D four-wheel position finder destination disk image-recognizing method of the present invention the following steps are included:
(1) photo is obtained, the photo includes at least two destination disk images；
(2) preliminary threshold for calculating the photo, determines the Position Approximate range of described two destination disks；
(3) threshold value of described two destination disks is calculated；
(4) all circular centers of circle in described two destination disks are determined；
(5) all circular centers of circle in described two destination disks are arranged and are exported.
In the 3D four-wheel position finder destination disk image-recognizing method, the step (1) specifically includes the following steps:
(11) gray scale pictures are obtained, which includes at least two destination disk images；
(12) gray scale pictures described in binaryzation are stated that two kinds of colors of black and white.
In the 3D four-wheel position finder destination disk image-recognizing method, the step (2) specifically includes the following steps:
(21) preliminary threshold of the gray scale pictures is calculated；
(22) it according to the preliminary threshold, identifies in the gray scale pictures, the continuous white area in horizontal direction,
As horizontal target region；
(23) it according to the preliminary threshold, identifies in the gray scale pictures, the continuous white area in vertical direction,
As vertical target region；
(24) the horizontal target region part Chong Die with the vertical target region is centainly extended, is made
For the Position Approximate range of described two destination disks.
In the 3D four-wheel position finder destination disk image-recognizing method, the step (24) specifically:
The horizontal target region part Chong Die with the vertical target region is extended to the outside into 5 to 10 pictures
Element, using the region after extension as the Position Approximate range of described two destination disks.
In the 3D four-wheel position finder destination disk image-recognizing method, the step (3) specifically:
Within the scope of the Position Approximate of described two destination disks, the image threshold of described two destination disks is calculated separately.
In the 3D four-wheel position finder destination disk image-recognizing method, the step (4) specifically includes the following steps:
(41) according to the image threshold of two destination disks, all circles in described two destination disks are identified；
(42) all circular centers of circle in described two destination disks are positioned.
In the 3D four-wheel position finder destination disk image-recognizing method, the step (41) specifically:
Pixel whole in two destination disks is traversed, determines that each pixel is black according to the image threshold of the destination disk
Color or white, and using continuous black pixel point as one circular pixel of composition.
The step (42) specifically:
According to the coordinate for forming each circular whole black pixel point, the circular central coordinate of circle is determined.
In the 3D four-wheel position finder destination disk image-recognizing method, the step (5) specifically:
It is that first center of circle from left to right arranges from top to bottom with the center of circle in the upper left corner, generates and two targets
The corresponding two bidimensional arrays of disk, and export.
Using the 3D four-wheel position finder destination disk image-recognizing method of the invention, the preliminary threshold of photo is calculated first
Value, determines the Position Approximate range of two destination disks；The threshold value of two destination disks is calculated separately again；And then determine two destination disks
In all circular centers of circle；After arrangement and export.So as to prepare, efficiently identify the position of the dot in destination disk, into
One step improves the accuracy of four-wheel aligner.And 3D four-wheel position finder destination disk image-recognizing method implementation letter of the invention
Just, cost of implementation is cheap, and application range is also quite extensive.
Detailed description of the invention
Fig. 1 is the step flow chart of 3D four-wheel position finder destination disk image-recognizing method of the invention.
Fig. 2 is the four-wheel aligner destination disk that need to be identified using 3D four-wheel position finder destination disk image-recognizing method of the invention
Photo schematic diagram.
Fig. 3 is two targets of identification of 3D four-wheel position finder destination disk image-recognizing method of the invention in practical applications
The schematic diagram of the Position Approximate range of disk.
Fig. 4 is the flow diagram of 3D four-wheel position finder destination disk image-recognizing method of the invention in practical applications.
Specific embodiment
In order to be more clearly understood that technology contents of the invention, spy lifts following embodiment and is described in detail.
Refering to Figure 1, being the step flow chart of 3D four-wheel position finder destination disk image-recognizing method of the invention.
In one embodiment, the 3D four-wheel position finder destination disk image-recognizing method the following steps are included:
(1) photo is obtained, the photo includes at least two destination disk images；
(2) preliminary threshold for calculating the photo, determines the Position Approximate range of described two destination disks；
(3) threshold value of described two destination disks is calculated；
(4) all circular centers of circle in described two destination disks are determined；
(5) all circular centers of circle in described two destination disks are arranged and are exported.
In a preferred embodiment, the step (1) specifically includes the following steps:
(11) gray scale pictures are obtained, which includes at least two destination disk images；
(12) gray scale pictures described in binaryzation are stated that two kinds of colors of black and white.
In another preferred embodiment, the step (2) specifically includes the following steps:
(21) preliminary threshold of the gray scale pictures is calculated；
(22) it according to the preliminary threshold, identifies in the gray scale pictures, the continuous white area in horizontal direction,
As horizontal target region；
(23) it according to the preliminary threshold, identifies in the gray scale pictures, the continuous white area in vertical direction,
As vertical target region；
(24) the horizontal target region part Chong Die with the vertical target region is centainly extended, is made
For the Position Approximate range of described two destination disks.
In a kind of further preferred embodiment, the step (24) specifically:
The horizontal target region part Chong Die with the vertical target region is extended to the outside into 5 to 10 pictures
Element, using the region after extension as the Position Approximate range of described two destination disks.
In another preferred embodiment, the step (3) specifically:
Within the scope of the Position Approximate of described two destination disks, the image threshold of described two destination disks is calculated separately.
In another further preferred embodiment, the step (4) specifically includes the following steps:
(41) according to the image threshold of two destination disks, all circles in described two destination disks are identified；
(42) all circular centers of circle in described two destination disks are positioned.
In a kind of further preferred embodiment, the step (41) specifically:
Pixel whole in two destination disks is traversed, determines that each pixel is black according to the image threshold of the destination disk
Color or white, and using continuous black pixel point as one circular pixel of composition.
The step (42) specifically:
According to the coordinate for forming each circular whole black pixel point, the circular central coordinate of circle is determined.
In preferred embodiment, the step (5) specifically:
It is that first center of circle from left to right arranges from top to bottom with the center of circle in the upper left corner, generates and two targets
The corresponding two bidimensional arrays of disk, and export.
In practical applications, image-recognizing method of the invention is black in white area pattern in identification destination disk picture
Color circle, and calculate the center of circle of each circle.
It in any environment, is taken pictures to obtain the picture to be identified by camera, as shown in Fig. 2, there are two the same figures in figure
Case, because two patterns of distance have size, by image recognition software, to obtain the center of circle of each dark circles in picture
Coordinate, the picture lower left corner be coordinate (0,0), central coordinate of circle precision is 0.01 pixel.
Identification process is as shown in figure 4, generally comprise following steps:
1. initial threshold is calculated, for looking for destination disk Position Approximate
The threshold value for calculating white area first directly obtains gray scale picture because being black and white camera.Calculate picture entirety threshold
Value searches most bright point, can be set to pre- threshold value more than certain amount, be expressed as with binaryzation black and white.The first step first finds out cross
Into projection, the region of continuous white, is drawn, second step is found out in vertical projection in thick red area to be connected with red thick line
Continuous white area, is drawn with The Thin Red Line.As shown in Figure 3.
2. micro-adjustment expanded scope again draws entire white area
Referring to Fig. 3 Green wire frame region.Method is in the general area drawn, in four direction up and down
Extend, discovery, which is often shown in greater than 5 pixels, to be stopped, and several pixels are then re-extended.
3. calculating each accurate threshold value in region
Because each pattern has distance, to calculate the center of circle inaccurate with will lead to if the same threshold value, so calculating as far as possible
The threshold value of each destination disk pattern out.
4. finding out the center of circle
The region of each destination disk has been found now, next will look for the center of circle of dark circles.The method of this patent is
Black color dots are looked for since the first row in region, if centre encounters white point and is taken as next circle, in the mistake for looking for black color dots
Cheng Zhong is added the coordinate of continuous black, so as to the subsequent calculations center of circle.The first row starts following a line, method after having detected
As lastrow, continuous black is looked for, if but find black color dots in the x coordinate of lastrow black color dots during this, just
Think to be the same circle with the black color dots of lastrow, the coordinate of black color dots is added in this black region of lastrow.Last line
After the completion, the value all black regions being added just obtains central coordinate of circle divided by black color dots number.
5. the sequence arrangement of circle
Behind the center of circle for finding all circles, the center of circle in the upper left corner is classified as first circle and is from left to right arranged from top to bottom.
Ultimately produce two bidimensional array outputs.
The example procedure of image-recognizing method of the invention in practical applications is as follows:
Using the 3D four-wheel position finder destination disk image-recognizing method of the invention, the preliminary threshold of photo is calculated first
Value, determines the Position Approximate range of two destination disks；The threshold value of two destination disks is calculated separately again；And then determine two destination disks
In all circular centers of circle；After arrangement and export.So as to prepare, efficiently identify the position of the dot in destination disk, into
One step improves the accuracy of four-wheel aligner.And 3D four-wheel position finder destination disk image-recognizing method implementation letter of the invention
Just, cost of implementation is cheap, and application range is also quite extensive.
In this description, the present invention is described with reference to its specific embodiment.But it is clear that can still make
Various modifications and alterations are without departing from the spirit and scope of the invention.Therefore, the description and the appended drawings should be considered as illustrative
And not restrictive.
Claims (8)
1. a kind of 3D four-wheel position finder destination disk image-recognizing method, which is characterized in that the method the following steps are included:
(1) photo is obtained, the photo includes at least two destination disk images；
(2) preliminary threshold for calculating the photo, determines the Position Approximate range of described two destination disks；
(3) threshold value of described two destination disks is calculated；
(4) all circular centers of circle in described two destination disks are determined；
(5) all circular centers of circle in described two destination disks are arranged and are exported.
2. 3D four-wheel position finder destination disk image-recognizing method according to claim 1, which is characterized in that the step
(1) specifically includes the following steps:
(11) gray scale pictures are obtained, which includes at least two destination disk images；
(12) gray scale pictures described in binaryzation are stated that two kinds of colors of black and white.
3. 3D four-wheel position finder destination disk image-recognizing method according to claim 2, which is characterized in that the step
(2) specifically includes the following steps:
(21) preliminary threshold of the gray scale pictures is calculated；
(22) it according to the preliminary threshold, identifies in the gray scale pictures, the continuous white area in horizontal direction, by it
As horizontal target region；
(23) it according to the preliminary threshold, identifies in the gray scale pictures, the continuous white area in vertical direction, by it
As vertical target region；
(24) the horizontal target region part Chong Die with the vertical target region is centainly extended, as institute
State the Position Approximate range of two destination disks.
4. 3D four-wheel position finder destination disk image-recognizing method according to claim 3, which is characterized in that the step
(24) specifically:
The horizontal target region part Chong Die with the vertical target region is extended to the outside into 5 to 10 pixels, it will
Position Approximate range of the region as described two destination disks after extension.
5. 3D four-wheel position finder destination disk image-recognizing method according to claim 3, which is characterized in that the step
(3) specifically:
Within the scope of the Position Approximate of described two destination disks, the image threshold of described two destination disks is calculated separately.
6. 3D four-wheel position finder destination disk image-recognizing method according to claim 5, which is characterized in that the step
(4) specifically includes the following steps:
(41) according to the image threshold of two destination disks, all circles in described two destination disks are identified；
(42) all circular centers of circle in described two destination disks are positioned.
7. 3D four-wheel position finder destination disk image-recognizing method according to claim 6, which is characterized in that
The step (41) specifically:
Traverse pixel whole in two destination disks, according to the image threshold of the destination disk determine each pixel be black or
White, and using continuous black pixel point as one circular pixel of composition.
The step (42) specifically:
According to the coordinate for forming each circular whole black pixel point, the circular central coordinate of circle is determined.
8. 3D four-wheel position finder destination disk image-recognizing method according to claim 6, which is characterized in that the step
(5) specifically:
It is that first center of circle from left to right arranges from top to bottom with the center of circle in the upper left corner, generates and two destination disks pair
The two bidimensional arrays answered, and export.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910126336.5A CN109872365A (en) | 2019-02-20 | 2019-02-20 | 3D four-wheel position finder destination disk image-recognizing method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910126336.5A CN109872365A (en) | 2019-02-20 | 2019-02-20 | 3D four-wheel position finder destination disk image-recognizing method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109872365A true CN109872365A (en) | 2019-06-11 |
Family
ID=66918999
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910126336.5A Pending CN109872365A (en) | 2019-02-20 | 2019-02-20 | 3D four-wheel position finder destination disk image-recognizing method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109872365A (en) |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5724743A (en) * | 1992-09-04 | 1998-03-10 | Snap-On Technologies, Inc. | Method and apparatus for determining the alignment of motor vehicle wheels |
| CN102721548A (en) * | 2012-05-18 | 2012-10-10 | 朱迪文 | 3D four-wheel aligner with no car pushing required |
| CN103679695A (en) * | 2013-07-04 | 2014-03-26 | 深圳市圳天元科技开发有限责任公司 | 3D four-wheel locating instrument reflection target and image recognition method thereof |
| CN104574312A (en) * | 2015-01-06 | 2015-04-29 | 深圳市元征软件开发有限公司 | Method and device of calculating center of circle for target image |
| CN104915973A (en) * | 2015-06-30 | 2015-09-16 | 南京大学 | Method for solving center of regular circle in image |
| CN106446894A (en) * | 2016-09-27 | 2017-02-22 | 广东技术师范学院 | Method for recognizing position of spherical object based on contour |
| CN106920262A (en) * | 2017-03-07 | 2017-07-04 | 湖南科技大学 | A kind of machine vision 3D four-wheel aligners instrument target binding method |
| CN106969726A (en) * | 2017-05-16 | 2017-07-21 | 桂林施瑞德科技发展有限公司 | The 3D four-wheel position finders and its control method of intelligent capture target image |
| CN107909610A (en) * | 2017-10-31 | 2018-04-13 | 常州大学 | A kind of gray scale target perimeter evaluation method based on image grain and sub-pix border detection |
| CN108230401A (en) * | 2018-01-12 | 2018-06-29 | 上海鼎盛汽车检测设备有限公司 | 3D four-wheel position finder automatic camera calibration method and system |
| CN108288065A (en) * | 2017-01-09 | 2018-07-17 | 南京理工大学 | A kind of four-wheel position finder detection method based on image analysis |
| CN207717379U (en) * | 2018-01-10 | 2018-08-10 | 上海鼎盛汽车检测设备有限公司 | Stablize convenient 3D four-wheel position finders |
-
2019
- 2019-02-20 CN CN201910126336.5A patent/CN109872365A/en active Pending
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5724743A (en) * | 1992-09-04 | 1998-03-10 | Snap-On Technologies, Inc. | Method and apparatus for determining the alignment of motor vehicle wheels |
| CN102721548A (en) * | 2012-05-18 | 2012-10-10 | 朱迪文 | 3D four-wheel aligner with no car pushing required |
| CN103679695A (en) * | 2013-07-04 | 2014-03-26 | 深圳市圳天元科技开发有限责任公司 | 3D four-wheel locating instrument reflection target and image recognition method thereof |
| CN104574312A (en) * | 2015-01-06 | 2015-04-29 | 深圳市元征软件开发有限公司 | Method and device of calculating center of circle for target image |
| CN104915973A (en) * | 2015-06-30 | 2015-09-16 | 南京大学 | Method for solving center of regular circle in image |
| CN106446894A (en) * | 2016-09-27 | 2017-02-22 | 广东技术师范学院 | Method for recognizing position of spherical object based on contour |
| CN108288065A (en) * | 2017-01-09 | 2018-07-17 | 南京理工大学 | A kind of four-wheel position finder detection method based on image analysis |
| CN106920262A (en) * | 2017-03-07 | 2017-07-04 | 湖南科技大学 | A kind of machine vision 3D four-wheel aligners instrument target binding method |
| CN106969726A (en) * | 2017-05-16 | 2017-07-21 | 桂林施瑞德科技发展有限公司 | The 3D four-wheel position finders and its control method of intelligent capture target image |
| CN107909610A (en) * | 2017-10-31 | 2018-04-13 | 常州大学 | A kind of gray scale target perimeter evaluation method based on image grain and sub-pix border detection |
| CN207717379U (en) * | 2018-01-10 | 2018-08-10 | 上海鼎盛汽车检测设备有限公司 | Stablize convenient 3D four-wheel position finders |
| CN108230401A (en) * | 2018-01-12 | 2018-06-29 | 上海鼎盛汽车检测设备有限公司 | 3D four-wheel position finder automatic camera calibration method and system |
Non-Patent Citations (2)
| Title |
|---|
| 刘宇辰: "视觉四轮定位标定***的设计与实现", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 张娟等: "基于图像处理与计算机视觉的车辆四轮定位仪的设计与实现", 《现代电子技术》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111243032B (en) | Full-automatic detection method for checkerboard corner points | |
| CN103345755B (en) | A kind of Chessboard angular point sub-pixel extraction based on Harris operator | |
| CN109215063B (en) | Registration method of event trigger camera and three-dimensional laser radar | |
| US10151664B2 (en) | Method and system for measuring lens distortion | |
| CN110956660B (en) | Positioning method, robot, and computer storage medium | |
| CN108986129B (en) | Calibration plate detection method | |
| CN110580481B (en) | Light field image key position detection method based on EPI | |
| CN110334678A (en) | A kind of pedestrian detection method of view-based access control model fusion | |
| CN112964724B (en) | Multi-target multi-region visual detection method and detection system | |
| CN111950426A (en) | Target detection method and device and delivery vehicle | |
| CN107014291B (en) | A kind of vision positioning method of material precision transfer platform | |
| CN110458858A (en) | A kind of detection method of cross drone, system and storage medium | |
| CN111046843A (en) | Monocular distance measurement method under intelligent driving environment | |
| CN107957246A (en) | Article geometrical size measuring method on conveyer belt based on binocular vision | |
| CN107644442B (en) | Spatial position calibration method of double-camera module | |
| CN117496401A (en) | Full-automatic identification and tracking method for oval target points of video measurement image sequences | |
| JPH05215547A (en) | Method for determining corresponding points between stereo images | |
| JP2019027882A (en) | Object distance detector | |
| JP2014191685A (en) | Image processing apparatus and image processing method | |
| CN109872365A (en) | 3D four-wheel position finder destination disk image-recognizing method | |
| CN112541943A (en) | Robot positioning method based on visual road signs | |
| CN106713707B (en) | Lens array imaging method and device | |
| CN110956640B (en) | Heterogeneous image edge point detection and registration method | |
| CN112102347A (en) | Step detection and single-stage step height estimation method based on binocular vision | |
| CN113840135A (en) | Color cast detection method, device, equipment and storage medium |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190611 |