CN111178296B - Multi-workpiece visual positioning and identifying method - Google Patents
Multi-workpiece visual positioning and identifying method Download PDFInfo
- Publication number
- CN111178296B CN111178296B CN201911417127.2A CN201911417127A CN111178296B CN 111178296 B CN111178296 B CN 111178296B CN 201911417127 A CN201911417127 A CN 201911417127A CN 111178296 B CN111178296 B CN 111178296B
- Authority
- CN
- China
- Prior art keywords
- workpiece
- coordinate system
- robot
- machine vision
- camera
- 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.)
- Active
Links
- 230000000007 visual effect Effects 0.000 title claims abstract description 13
- 238000000034 method Methods 0.000 title claims abstract description 12
- 238000003466 welding Methods 0.000 claims abstract description 26
- 239000011159 matrix material Substances 0.000 claims abstract description 9
- 238000001914 filtration Methods 0.000 claims abstract description 4
- 238000004364 calculation method Methods 0.000 claims description 5
- 238000006243 chemical reaction Methods 0.000 claims description 5
- 238000000605 extraction Methods 0.000 claims description 4
- 238000004458 analytical method Methods 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 2
- 230000008901 benefit Effects 0.000 abstract description 4
- 238000004519 manufacturing process Methods 0.000 abstract description 4
- 238000003708 edge detection Methods 0.000 abstract description 2
- 230000001629 suppression Effects 0.000 abstract 1
- 229910000831 Steel Inorganic materials 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 239000003973 paint Substances 0.000 description 1
- 238000010422 painting Methods 0.000 description 1
- 238000007790 scraping Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 239000010959 steel Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
- G06K7/00—Methods or arrangements for sensing record carriers, e.g. for reading patterns
- G06K7/10—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation
- G06K7/10544—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation by scanning of the records by radiation in the optical part of the electromagnetic spectrum
- G06K7/10712—Fixed beam scanning
- G06K7/10722—Photodetector array or CCD scanning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/22—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Electromagnetism (AREA)
- Health & Medical Sciences (AREA)
- Toxicology (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Manipulator (AREA)
- Numerical Control (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
A visual positioning and identifying method for multiple workpieces includes utilizing high-precision industrial-grade camera to collect image information of machine visual positioning module by visual sensor, carrying out filtering and noise suppression on image, extracting edge characteristic data, utilizing fitting algorithm to fit edge, finally utilizing Canny edge detection algorithm to calculate out plane coordinate value of workpiece and to establish workpiece coordinate system, determining workpiece coordinate position and rotation angle to be welded, utilizing algorithm of homogeneous matrix to unify workpiece coordinate system and robot coordinate system to robot coordinate system so as to guide robot to realize automatic welding process. The invention can achieve the advantages of improving welding quality, improving production efficiency and reducing labor cost.
Description
Technical Field
The invention relates to the technical field of welding and positioning of robots.
Background
In the age of rapid development of economy, the yield of ships is larger and larger, the types of different workpieces are more and more, and the requirement of productivity cannot be met by the traditional mode of fixing the workpieces correspondingly by a fixed platform. The technology of domestic automatic welding has been used in many fields, such as automatic welding of frames of automobiles, for example. At present, due to the fact that the work environment of shipyards is severe, workpieces are large in size and large in types, mainly manual welding is adopted, and the defects of low welding efficiency, high cost, long time consumption and relatively low quality exist. In order to solve the problem, the ship industry introduces the function of machine vision, but because the field environment of a shipyard is severe, the size of a workpiece is large, an open working environment light source and instability thereof generate very large interference on the positioning of the machine vision, and because the specificity of the workpiece is deeper, the problem can be solved by painting the background color of a platform to increase the contrast ratio of the workpiece and the platform, but because the upper workpiece and the lower workpiece frequently cause repeated maintenance on the background paint scraping of the platform, the cost is high, the construction period is long, and the production efficiency is seriously affected.
Disclosure of Invention
The invention aims to provide a multi-workpiece visual positioning and identifying method, which can quickly identify and position workpieces through machine vision and guide a robot to realize automatic welding.
The invention can realize the aim by designing a multi-workpiece visual positioning and identifying method, which comprises the following steps:
A. setting a large welding working platform, placing a workpiece on the welding platform, and respectively placing machine vision positioning modules at the outer edges of the workpiece;
B. the camera obtains pixel equivalent through shooting a calibration caliper; the camera obtains the image information of the machine vision positioning module through the photographing machine vision positioning module and performs analysis operation to obtain the coordinates of the point cloud on the edge; scanning the two-dimensional code through a camera, and determining model batch information of the workpiece; removing noise points of a reference visual image by a nonlinear median filtering algorithm on the reference image acquired by the camera;
C. converting the data of the camera coordinate system by using a homogeneous matrix algorithm, fitting the point cloud, determining the coordinates of the workpiece in the world coordinate system, calculating to obtain a rotation angle, and sending the rotation angle to a robot database to guide a robot to realize automatic welding of the workpiece;
the conversion relation of two coordinate systems is expressed as homogeneous matrix
Wherein: s represents sin and c represents cos;
and carrying out fitting calculation on the point clouds of the two-dimensional codes on the same axis on the workpiece to obtain a fitted straight line, and intersecting the two fitted straight lines of the X axis and the Y axis to obtain the coordinate of the intersection point.
Furthermore, feature extraction at the pixel level adopts Canny operators and Log operators.
Still further, assuming that the points are (x 1, y 1), (x 2, y 2), (x 2), and (xn, yn), then the correlation coefficient of the linear fit formula is
b＝(n(x1y1+x2y2+...+xnyn)-(x1+...+x2)(y1+...+yn))/(n((x1) 2 +(x2) 2 +...+(xn) 2 )-(x1+...+x2) 2 )，
a＝(y1+...+yn)/n-b*(x1+...+x2)/n。
The invention can achieve the advantages of improving welding quality, improving production efficiency and reducing labor cost, and can be popularized in the welding industry of shipyards in the future so that more shipyards benefit in the welding field.
Drawings
FIG. 1 is a flow chart of a preferred embodiment of the present invention;
FIG. 2 is a schematic view of the welding robot coordinates and ZYX Euler angles in accordance with a preferred embodiment of the present invention;
FIG. 3 is a schematic diagram of a preferred embodiment of the present invention.
Detailed Description
The invention is further described below with reference to examples.
As shown in fig. 1, a method for visual positioning and identifying multiple workpieces includes the following steps:
A. a large welding working platform is arranged, the workpiece 1 is placed on the welding platform, and the machine vision positioning modules 2 are respectively placed on the outer edges of the workpiece 1, as shown in fig. 3. A large work platform is required to place workpieces of different sizes on the welding platform.
B. The camera 4 obtains pixel equivalent by shooting a calibration caliper, and the camera 4 obtains image information of the machine vision positioning module by shooting the machine vision positioning module and performs analysis operation to obtain coordinates of point cloud on the edge; and scanning the two-dimensional code 3 by a camera to determine model batch information of the workpiece. Camera calibration by shooting a calliper means a process of calibration of each camera coordinate system, i.e. the source of pixel equivalents.
The control mechanism 7 sends an instruction to the industrial computer 6, the industrial computer 6 starts the image acquisition card 5, the camera 4 scans the two-dimensional code 3 on the workpiece to acquire images, the industrial computer 6 directly acquires information contained in the two-dimensional code, the information comprises the model, the specification and the like of the workpiece, and meanwhile, the coordinates of point clouds on the edge line of the two-dimensional code are extracted through the function of a visual software algorithm.
The reference image collected by the camera sometimes has high-frequency pixel points and noise due to vibration, light, scraps and the like. The ideal contour of the reference edge is a smooth curve, so the nonlinear median filtering algorithm is particularly suitable for the reference visual image noise point removal. The feature extraction at the pixel level is mature, and the feature is obtained more stably and more rapidly by adopting the Canny operator and the Log operator, so that the method is suitable for the static high-precision pixel feature extraction. Theoretically, the maximum error of edge positioning of these operators is 0.5 pixel, and the number of pixels between two feature points may have an error of 1 pixel.
C. Converting the data of the camera coordinate system by using a homogeneous matrix algorithm, fitting the point cloud, determining the coordinates of the workpiece in the world coordinate system, calculating to obtain a rotation angle, and sending the rotation angle to a robot database to guide the robot to realize automatic welding of the workpiece.
And carrying out fitting calculation on the point clouds of the machine vision positioning module on the same axis on the workpiece to obtain a fitted straight line, and intersecting the two fitted straight lines of the X axis and the Y axis to obtain the coordinate of the intersection point. Assuming that the points are (x 1, y 1), (x 2, y 2), (x 2), and (xn, yn), then the correlation coefficient of the linear fit formula is
b＝(n(x1y1+x2y2+...+xnyn)-(x1+...+x2)(y1+...+yn))/(n((x1) 2 +(x2) 2 +...+(xn) 2 )-(x1+...+x2) 2 )，
a＝(y1+...+yn)/n-b*(x1+...+x2)/n。
As shown in fig. 2 (a), the robot coordinate systemThe coordinates in the coordinate system O-xyz are [ XYZABC ]]It essentially represents the coordinate system O-xyz to the robot coordinate system +.>The conversion sequence is translation followed by rotation. X, Y, Z the robot coordinate System->The origin O' of (c) is located in mm in the coordinate system O-xyz. A. B, C it is expressed that the origin of the coordinate system O-xyz is translated to O' and then the coordinate system O-xyz is shifted from>To the coordinate system->The unit is degree through ZYX Euler transformation.
As shown in FIG. 2 (b), A represents a coordinate systemWind->The rotation angle of the shaft, B represents the coordinate system after rotation +.>The rotation angle of the shaft, C represents +.>Angle of rotation.
The conversion relation of two coordinate systems is expressed as homogeneous matrix
Wherein: s represents sin and c represents cos.
If the matrix is multiplied from right to left, it means that each rotation rotates about the relevant axis of the reference frame O. I.e. first around x by an angle C, then around y by an angle B, and finally around z by an angle a.
And sending the conversion calculation result to a robot database to guide the robot to realize automatic welding of the workpiece.
The method has the advantages that the machine vision positioning module and the method for attaching the two-dimensional code are respectively arranged on the outer edge of the workpiece, and the workpiece is well positioned by correcting the multi-layer complex algorithm of the fitting algorithm, the edge detection algorithm and the homogeneous matrix algorithm.
The invention reduces the number of fixed working platforms, saves the cost and improves the production efficiency. The invention is mainly applied to the field of welding large steel workpieces in ships and shipyards, and realizes a full-automatic welding mode instead of manual welding by scanning and positioning workpiece coordinates to guide a robot.
Claims (1)
1. The multi-workpiece visual positioning and identifying method is characterized by comprising the following steps of:
A. setting a large welding working platform, placing a workpiece on the welding platform, and respectively placing machine vision positioning modules at the outer edges of the workpiece;
B. the camera obtains a pixel equivalent unit by shooting a calibration caliper; the camera obtains the image information of the machine vision positioning module through the photographing machine vision positioning module and performs analysis operation to obtain the coordinates of the point cloud on the edge; scanning the two-dimensional code through a camera, and determining model batch information of the workpiece; removing noise points of a reference visual image by a nonlinear median filtering algorithm on the reference image acquired by the camera; the feature extraction of the pixel level adopts a Canny operator or a Log operator;
C. converting the data of the camera coordinate system by using a homogeneous matrix algorithm, fitting the point cloud, determining the coordinates of the workpiece in the world coordinate system, calculating to obtain a rotation angle, and sending the rotation angle to a robot database to guide a robot to realize automatic welding of the workpiece;
fitting calculation is carried out on point clouds of the machine vision positioning module on the same axis on the workpiece to obtain a fitted straight line, and the coordinate of an intersection point is obtained by intersecting the two fitted straight lines of the X axis and the Y axis; assuming that the points are (x 1, y 1), (x 2, y 2), (x 2), and (xn, yn), then the correlation coefficient of the linear fit formula is
b＝(n(x1y1+x2y2+...+xnyn)-(x1+...+x2)(y1+...+yn))/(n((x1) 2 +(x2) 2 +...+(xn) 2 )-(x1+...+x2) 2 )，
a＝(y1+...+yn)/n-b*(x1+...+x2)/n；
The conversion relation of two coordinate systems is expressed as homogeneous matrix
Wherein: s represents sin and c represents cos; x, Y, Z the robot coordinate SystemThe position of the origin O' of (2) in the coordinate system O-xyz is given in mm; A. b, C it is expressed that the origin of the coordinate system O-xyz is translated to O' and then the coordinate system O-xyz is shifted from>To the coordinate system->The unit is degree through ZYX Euler transformation;
and carrying out fitting calculation on the point clouds of the machine vision positioning module on the same axis on the workpiece to obtain a fitted straight line, and intersecting the two fitted straight lines of the X axis and the Y axis to obtain the coordinate of the intersection point.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911417127.2A CN111178296B (en) | 2019-12-31 | 2019-12-31 | Multi-workpiece visual positioning and identifying method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911417127.2A CN111178296B (en) | 2019-12-31 | 2019-12-31 | Multi-workpiece visual positioning and identifying method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111178296A CN111178296A (en) | 2020-05-19 |
| CN111178296B true CN111178296B (en) | 2024-03-01 |
Family
ID=70654316
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911417127.2A Active CN111178296B (en) | 2019-12-31 | 2019-12-31 | Multi-workpiece visual positioning and identifying method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111178296B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111595266A (en) * | 2020-06-02 | 2020-08-28 | 西安航天发动机有限公司 | Spatial complex trend catheter visual identification method |
| CN113592955B (en) * | 2021-07-27 | 2024-04-09 | 中国科学院西安光学精密机械研究所 | Round workpiece plane coordinate high-precision positioning method based on machine vision |
| CN115540749A (en) * | 2022-09-14 | 2022-12-30 | 泰州市创新电子有限公司 | Three-dimensional vision measurement data processing method and device |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101949687A (en) * | 2010-09-19 | 2011-01-19 | 天津大学 | Detection method of automobile door based on vision measurement |
| CN107976147A (en) * | 2017-12-11 | 2018-05-01 | 西安迈森威自动化科技有限公司 | A kind of glass locating and detecting device based on machine vision |
| CN108550141A (en) * | 2018-03-29 | 2018-09-18 | 上海大学 | A kind of movement wagon box automatic identification and localization method based on deep vision information |
| CN109448054A (en) * | 2018-09-17 | 2019-03-08 | 深圳大学 | Target step-by-step positioning method, application, device and system based on visual fusion |
| CN110110760A (en) * | 2019-04-17 | 2019-08-09 | 浙江工业大学 | A kind of workpiece positioning and recognition methods based on machine vision |
| CN110524580A (en) * | 2019-09-16 | 2019-12-03 | 西安中科光电精密工程有限公司 | A kind of welding robot visual component and its measurement method |
| CN110599544A (en) * | 2019-08-08 | 2019-12-20 | 佛山科学技术学院 | Workpiece positioning method and device based on machine vision |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8126260B2 (en) * | 2007-05-29 | 2012-02-28 | Cognex Corporation | System and method for locating a three-dimensional object using machine vision |
| JP5549129B2 (en) * | 2009-07-06 | 2014-07-16 | セイコーエプソン株式会社 | Position control method, robot |
-
2019
- 2019-12-31 CN CN201911417127.2A patent/CN111178296B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101949687A (en) * | 2010-09-19 | 2011-01-19 | 天津大学 | Detection method of automobile door based on vision measurement |
| CN107976147A (en) * | 2017-12-11 | 2018-05-01 | 西安迈森威自动化科技有限公司 | A kind of glass locating and detecting device based on machine vision |
| CN108550141A (en) * | 2018-03-29 | 2018-09-18 | 上海大学 | A kind of movement wagon box automatic identification and localization method based on deep vision information |
| CN109448054A (en) * | 2018-09-17 | 2019-03-08 | 深圳大学 | Target step-by-step positioning method, application, device and system based on visual fusion |
| CN110110760A (en) * | 2019-04-17 | 2019-08-09 | 浙江工业大学 | A kind of workpiece positioning and recognition methods based on machine vision |
| CN110599544A (en) * | 2019-08-08 | 2019-12-20 | 佛山科学技术学院 | Workpiece positioning method and device based on machine vision |
| CN110524580A (en) * | 2019-09-16 | 2019-12-03 | 西安中科光电精密工程有限公司 | A kind of welding robot visual component and its measurement method |
Non-Patent Citations (2)
| Title |
|---|
| 赵善政.基于机器视觉的玻璃在线定位方法.《硕士电子期刊》.2013,全文. * |
| 郝永平等.面向视觉测量的像素当量标定方法.《纳米技术与精密工程》.2014,373-380. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111178296A (en) | 2020-05-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111178296B (en) | Multi-workpiece visual positioning and identifying method | |
| CN109612390B (en) | Large-size workpiece automatic measuring system based on machine vision | |
| CN101840736B (en) | Device and method for mounting optical glass under vision guide | |
| CN110717872B (en) | Method and system for extracting characteristic points of V-shaped welding seam image under laser-assisted positioning | |
| CN112529858A (en) | Welding seam image processing method based on machine vision | |
| WO2015120734A1 (en) | Special testing device and method for correcting welding track based on machine vision | |
| CN111645074A (en) | Robot grabbing and positioning method | |
| CN113146172A (en) | Multi-vision-based detection and assembly system and method | |
| CN109671059B (en) | Battery box image processing method and system based on OpenCV | |
| CN110480127A (en) | A kind of seam tracking system and method based on structured light visual sensing | |
| CN113843797B (en) | Automatic disassembly method for part hexagonal bolt under non-structural environment based on single-binocular hybrid vision | |
| CN110625644B (en) | Workpiece grabbing method based on machine vision | |
| CN108389184A (en) | A kind of workpiece drilling number detection method based on machine vision | |
| CN107160241A (en) | A kind of vision positioning system and method based on Digit Control Machine Tool | |
| CN110568866A (en) | Three-dimensional curved surface vision guiding alignment system and alignment method | |
| CN113822810A (en) | Method for positioning workpiece in three-dimensional space based on machine vision | |
| CN114926531A (en) | Binocular vision based method and system for autonomously positioning welding line of workpiece under large visual field | |
| CN115830018A (en) | Carbon block detection method and system based on deep learning and binocular vision | |
| CN111639538B (en) | Casting positioning method based on vision | |
| CN105068139B (en) | A kind of characterization processes of piston cooling nozzle installment state | |
| CN115283905A (en) | Welding gun posture adjusting method of welding robot | |
| CN113433129B (en) | Six-axis robot deburring cutter detection mechanism and method thereof | |
| CN107843602B (en) | Image-based weld quality detection method | |
| CN116740141A (en) | Machine vision-based weld joint positioning system and method for small preceding assembly | |
| CN116766201A (en) | An industrial robot control system based on machine vision |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |