CN112296999B - Irregular workpiece machining path generation method based on machine vision - Google Patents
Irregular workpiece machining path generation method based on machine vision Download PDFInfo
- Publication number
- CN112296999B CN112296999B CN201911102219.1A CN201911102219A CN112296999B CN 112296999 B CN112296999 B CN 112296999B CN 201911102219 A CN201911102219 A CN 201911102219A CN 112296999 B CN112296999 B CN 112296999B
- Authority
- CN
- China
- Prior art keywords
- contour
- image
- workpiece
- coordinate
- smooth
- 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
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1694—Programme controls characterised by use of sensors other than normal servo-feedback from position, speed or acceleration sensors, perception control, multi-sensor controlled systems, sensor fusion
- B25J9/1697—Vision controlled systems
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1656—Programme controls characterised by programming, planning systems for manipulators
- B25J9/1664—Programme controls characterised by programming, planning systems for manipulators characterised by motion, path, trajectory planning
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Engineering & Computer Science (AREA)
- Robotics (AREA)
- Mechanical Engineering (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention relates to a machine vision-based irregular workpiece machining path generation method, which belongs to the technical field of image calculation and solves the technical problem that artificial monitoring and correction are needed in the machining process of various different-shaped contours, and comprises the following steps: camera calibration → shooting workpiece image and preprocessing → finding boundary and forming workpiece outline image → calibrating outline centroid and coordinate system of processing platform → generating set of indented outline coordinates S required by user on workpiece outline imagec→ smoothing the contour with median filtering
To obtain
Generating a plurality of contour lines covering the workpiece image according to a user preset condition → generating a machining path according to the contour lines. The invention can adaptively adjust the processing contour according to different shapes, so that each contour can be adjusted according to different shapesThe anisotropic forming process does not need manual monitoring and correction, and the automatic process and the high-efficiency production of the anisotropic forming process are improved.
Description
Technical Field
The invention belongs to the technical field of image calculation, and particularly relates to a method for generating an irregular workpiece machining path based on machine vision.
Background
As computer technology and image processing algorithms are becoming mature, various visual numerical control systems have appeared in machining, and there are many such forming processes throughout the entire machining field: if a plate rolling machine tool is used for rolling metal cylinders with various shapes, the same processing parameters and environmental conditions exist, because the shape error and the material of the plates are not uniform, the former plate can realize the butt joint between plate seams to form the cylinder, and the latter plate can not be butt jointed, so the position and the speed of the roller are required to be adjusted while rolling, the whole process can not be manually participated, and the similar conditions exist in the processing of bending pipes, bending plates, extrusion forming and the like. The processing has a common point that different conditions occur in each new processing process, manual monitoring and correction are needed, the different conditions are different from the same mould forming processing, namely the different forming processing, and the different characteristics restrict the automatic process and the efficient production of the processing. Therefore, a method for adaptively adjusting the machining profile according to different shapes is needed.
Disclosure of Invention
The purpose of the invention is: the invention provides a method for generating an irregular workpiece machining path based on machine vision, which aims to solve the technical problem that manual monitoring and correction are needed in the process of machining various different forming contours.
In order to achieve the above object, the present invention is achieved by the following means.
A method for generating an irregular workpiece machining path based on machine vision comprises the following steps:
s1, calibrating camera
Erecting a camera and a backlight plate, calibrating the focal length of the camera, and adjusting the exposure of the camera to ensure that the camera can clearly distinguish a workpiece from the backlight plate; using n multiplied by n checkerboard to shoot m calibration images, and obtaining a homography matrix H and a distortion coefficient distCoeffs ═ k by using a Zhang-Zhengyou calibration method1，k2，p1，p2]Internal reference matrix M1＝[fx，fy，cx，cy]External reference matrix M2；
S2, shooting workpiece image and preprocessing
The robot arm is driven to place the workpiece on the stage, an image of the workpiece is taken, and the image is set as an image a, and the distortion coefficient distCoeffs and the internal reference matrix M obtained in step S1 are used1Correcting the image A according to the following formulas (1) to (4) to obtain an image B with image distortion removed,
wherein x isA、yAIs the horizontal and vertical coordinate, x, of the same pixel in image AB、yBThe horizontal and vertical coordinates of the same pixel in the image B are shown, and r is an intermediate variable;
s3, finding boundary and forming workpiece contour image
Carrying out binarization processing on the image B subjected to distortion removal in the step S2 to obtain an image Bb, then searching a boundary of the image Bb, finding all connected contour areas, and keeping the contour with the largest area as CmaxDeleting other outlines to obtain an outline image D of the workpiece;
s4, calibrating the coordinate system of the outline centroid and the processing platform
The contour C in step S3 is obtainedmaxCharacteristic moment m ═ m00，m10，m01In which m is00Is the area of the profile, m10Is the sum of x-coordinate values in the contour region, m01Is the sum of the y coordinate values in the contour region; the profile centroid coordinate P (x) is obtained according to the following formula (5)c,yc) Setting the centroid coordinate P as the origin of the processing platform;
s5, generating a set S of indented contour coordinates required by the user on the workpiece contour imagec
For the contour C in step S3maxAccording to the profile indentation parameter P set by the usersawtoothUsing the following formula (6) to retract inwards to obtain the retracted contour coordinate set S required by the userc，
Where (x, y) is the pixel coordinate of the outline in the image D, (x ', y') is the pixel coordinate of (x, y) adjacent in the image D, kx、 kyRespectively representing the horizontal and vertical proportion of the image visual field to the size of the platform, wherein the element is a coordinate element;
s6 smoothing contour S by median filteringcTo obtain Sc-smooth
When a user is not satisfied with a certain current section of contour, the section of contour can be intercepted by drawing a straight line L through a mouse in an image D, and the intersection point of the L and the contour is obtained as a (x)a,ya)，b(xb,yb) And replacing the contour of the section by a line section ab, smoothing n contour points in front of and behind the intersection points a and b according to a median filtering method, and generating an adjusted smooth contour Sc-smooth；
S7, generating a plurality of contour lines covering the workpiece image according to the preset conditions of the user
For the contour Sc-smoothAccording to the profile expansion parameter P set by the userexpendThe profile S obtained in step S6 is expressed by the following formula (7)c-smoothExpanding outwards to generate a plurality of contours as Sc-expend：
Where (x, y) is the contour S in the image Dc-smoothIs (x ', y') the pixel coordinate of (x, y) adjacent in the image D, kx、kyRespectively representing the horizontal and vertical proportion of the image visual field to the size of the platform, wherein the element is a coordinate element;
s8, generating a machining path from the contour line
The contour S obtained in step S7c-expendThe pixel coordinates in (b) are converted into the shooting platform actual coordinates according to the homography matrix H in step S1 using the following equations (8) and (9):
wherein u and v are Sc-expendThe pixel coordinate value above, w is the gray value, x, y are the actual coordinate values of the machining path, x ', y', w 'are the intermediate parameters, (x', y ', w', are the intermediate parametersc,yc) And (4) obtaining the origin coordinates of the processing platform obtained in the step (4).
Compared with the prior art, the invention has the beneficial effects that:
the irregular workpiece processing path generation method based on machine vision can adaptively adjust the processing contour according to different shapes, so that the different forming processing does not need manual monitoring and correction, and the automatic process and the efficient production of the different forming processing are improved.
Drawings
FIG. 1 is a flow chart of the present invention;
FIG. 2 is a checkerboard image taken in the present invention;
FIG. 3 is an image of a workpiece taken in the present invention;
FIG. 4 is an image of a workpiece after pretreatment in accordance with the present invention;
FIG. 5 is an image of a workpiece with a single contour generated in accordance with the present invention;
FIG. 6 is an image of a workpiece with a manually adjusted contour in accordance with the present invention;
FIG. 7 is an image of a workpiece after manual contour adjustment in accordance with the present invention;
fig. 8 is a diagram of a workpiece image in which a plurality of contour lines are generated according to a preset condition in the present invention.
Detailed Description
The invention is described in further detail below with reference to the figures and examples.
The method for generating the irregular workpiece machining path based on the machine vision as shown in fig. 1 to 8 comprises the following steps:
s1, calibrating camera
Erecting a camera and a backlight plate, calibrating the focal length of the camera, and adjusting the exposure of the camera to ensure that the camera can clearly distinguish a workpiece from the backlight plate; using n multiplied by n checkerboard to shoot m calibration images, and obtaining a homography matrix H and a distortion coefficient distCoeffs ═ k by using a Zhang-Zhengyou calibration method1，k2，p1，p2]Internal reference matrix M1＝[fx，fy，cx，cy]External reference matrix M2(ii) a FIG. 2 shows the calibration result of the present embodiment;
s2, shooting workpiece image and preprocessing
The robot arm is driven to place the workpiece on the stage, and the image of the workpiece is captured and set as an image a, as shown in fig. 3, using the distortion coefficient distCoeffs obtained in step S1 and the internal reference matrix M1Correcting the image A according to the following formulas (1) to (4) to obtain an image B with image distortion removed,
wherein x isA、yAIs the horizontal and vertical coordinate, x, of the same pixel in image AB、yBThe horizontal and vertical coordinates of the same pixel in the image B are shown, and r is an intermediate variable;
s3, finding boundary and forming workpiece contour image
Binarizing the image B which has been subjected to the distortion removal in step S2 to obtain an image BbThen, as shown in fig. 4, the boundary is found for the image Bb, and all connected contour areas are found, and the contour with the largest reserved area is CmaxDeleting other outlines to obtain an outline image D of the workpiece, as shown in FIG. 5;
s4, calibrating the coordinate system of the outline centroid and the processing platform
The contour C in step S3 is obtainedmaxCharacteristic moment m ═ m00，m10，m01In which m is00Is the area of the profile, m10Is the sum of x-coordinate values in the contour region, m01Is the sum of the y coordinate values in the contour region; the contour centroid coordinate P (x) is obtained according to the following formula (5)c,yc) Setting the centroid coordinate P as the origin of the processing platform;
s5, generating a set S of indented contour coordinates required by the user on the workpiece contour imagec
For the contour C in step S3maxAccording to the profile indentation parameter P set by the usersawtoothUsing the following formula (6) to retract inwards to obtain the retracted contour coordinate set S required by the userc，
Where (x, y) is the pixel coordinate of the outline in the image D, (x ', y') is the pixel coordinate of (x, y) adjacent in the image D, kx、 kyRespectively representing the horizontal and vertical proportion of the image visual field to the size of the platform, wherein the element is a coordinate element;
s6 smoothing contour S by median filteringcTo obtain Sc-smooth
When a user is not satisfied with a certain current section of contour, the section of contour can be intercepted by drawing a straight line L through a mouse in an image D, and the intersection point of the L and the contour is obtained as a (x)a,ya)，b(xb,yb) The line ab replaces the contour of the section, and the front and the back n contour points of the intersection points a and b are smoothed according to a median filtering method to generate an adjusted smooth contour Sc-smoothAs shown in fig. 6;
s7, generating a plurality of contour lines covering the workpiece image according to the preset conditions of the user
For the contour Sc-smoothAccording to the profile expansion parameter P set by the userexpendThe profile S obtained in step S6 is expressed by the following formula (7)c-smoothExpanding outwards to generate a plurality of contours as Sc-expend：
FIG. 7 shows the machining path adjusted by the user; where (x, y) is the contour S in the image Dc-smoothIs (x ', y') the pixel coordinate of (x, y) adjacent in the image D, kx、kyRespectively representing the horizontal and vertical proportion of the image visual field to the size of the platform, wherein the element is a coordinate element;
s8, generating a machining path from the contour line
The contour S obtained in step S7c-expendThe pixel coordinates in (b) are converted into the shooting platform actual coordinates according to the homography matrix H in step S1 using the following equations (8) and (9):
wherein u and v are Sc-expendThe pixel coordinate value of (A) is a gray value, x and y are actual coordinate values of the machining path, x ', y', w 'are intermediate parameters, and (x', y ', w' are intermediate parametersc，yc) Is the processing platform origin coordinate obtained in step (4), in this embodiment, the processing platform origin coordinate is as follows:
[ outline ]
Center of circle X-coordinate 37.222561
Center Y-coordinate 50.059418
Inner ring profile area 1219.784027
Inner ring profile circumference of 145.181081
Number of turns of the profile being 8
[ 1-circle outline coordinate ]
6220 points of outline
Profile coordinate ρ 1-84.789702
Contour coordinate θ 1 is 160.668961
Profile coordinate ρ 2-84.754012
Contour coordinate θ 2 is 160.698242
Profile coordinate ρ 3-84.744780
Contour coordinate θ 3-160.743301
Profile coordinate ρ 4-84.735564
Contour coordinate θ 4-160.788422
Profile coordinate ρ 5-84.726375
Contour coordinate θ 5 160.833542
Profile coordinate ρ 6-84.717204
Contour coordinate θ 6-160.878677
Profile coordinate ρ 7-84.708056
Contour coordinate θ 7-160.923859
Profile coordinate ρ 8-84.698924
Contour coordinate θ 8 is 160.969055
Profile coordinate ρ 9-84.689818
Contour coordinate θ 9 is 161.014267
Profile coordinate ρ 10-84.680732
Contour coordinate θ 10-161.059509
Profile coordinate ρ 11-84.671664
Contour coordinate θ 11 is 161.104782
The profile coordinate ρ 12 is 84.662619.
As shown in fig. 8, a plurality of machining paths from rough to fine are finally generated.
To verify the accuracy of the profile, we measured three different sizes of standard circles with radius R1-20 mm, R2-30 mm, and R3-40 mm, respectively, as shown in table 1.
TABLE 1
Experiments show that the error between the system measurement and the actual measurement is within 0.03mm, and the enterprise requirements are met.
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present invention are included in the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the appended claims.
Claims (1)
1. A method for generating an irregular workpiece machining path based on machine vision is characterized by comprising the following steps:
s1, calibrating camera
Erecting a camera and a backlight plate, calibrating the focal length of the camera, and adjusting the exposure of the camera to ensure that the camera can clearly distinguish a workpiece from the backlight plate; using n multiplied by n checkerboard to shoot m calibration images, and obtaining a homography matrix H and a distortion coefficient distCoeffs ═ k by using a Zhang-Zhengyou calibration method1，k2，p1，p2]Internal reference matrix M1＝[fx，fy，cx，cy]External reference matrix M2；
S2, shooting workpiece image and preprocessing
The robot arm is driven to place the workpiece on the stage, an image of the workpiece is taken, and the image is set as an image a, and the distortion coefficient distCoeffs and the internal reference matrix M obtained in step S1 are used1Correcting the image A according to the following formulas (1) to (4) to obtain an image B with image distortion removed,
wherein x isA、yAIs the horizontal and vertical coordinate, x, of the same pixel in image AB、yBThe horizontal and vertical coordinates of the same pixel in the image B are obtained, and r is an intermediate variable;
s3, finding boundary and forming workpiece contour image
Carrying out binarization processing on the image B subjected to distortion removal in the step S2 to obtain an image Bb, then searching a boundary of the image Bb, finding all connected contour areas, and keeping the contour with the largest area as CmaxDeleting other outlines to obtain an outline image D of the workpiece;
s4, calibrating the coordinate system of the outline centroid and the processing platform
The contour C in step S3 is obtainedmaxCharacteristic moment m ═ m00，m10，m01In which m is00Is the area of the profile, m10Is the sum of x-coordinate values in the contour region, m01Is the sum of the y coordinate values in the contour region; the contour centroid coordinate P (x) is obtained according to the following formula (5)c,yc) Setting the centroid coordinate P as the origin of the processing platform;
s5, generating the set S of the indented contour coordinates required by the user on the workpiece contour imagec
For the contour C in step S3maxAccording to the profile indentation parameter P set by the usersawtoothUsing the following formula (6) to retract inwards to obtain the retracted contour coordinate set S required by the userc，
Where (x, y) is the pixel coordinate of the outline in the image D, (x ', y') is the pixel coordinate of (x, y) adjacent in the image D, kx、kyRespectively representing the horizontal and vertical proportion of the image visual field to the size of the platform, wherein the element is a coordinate element;
s6 smoothing the contour S by median filteringcTo obtain Sc-smooth
When a user is not satisfied with a certain current section of contour, the section of contour can be intercepted by drawing a straight line L through a mouse in an image D, and the intersection point of the L and the contour is obtained as a (x)a,ya)，b(xb,yb) And replacing the contour of the section by a line section ab, smoothing n contour points in front of and behind the intersection points a and b according to a median filtering method, and generating an adjusted smooth contour Sc-smooth；
S7, generating a plurality of contour lines covering the workpiece image according to the preset conditions of the user
For the contour Sc-smoothAccording to the profile expansion parameter P set by the userexpendThe profile S obtained in step S6 is expressed by the following formula (7)c-smoothExpanding outwards to generate a plurality of contours as Sc-expend：
Where (x, y) is the contour S in the image Dc-smooth(x ', y') is an image DIn (x, y) adjacent pixel coordinates, kx、kyRespectively representing the horizontal and vertical proportion of the image visual field to the size of the platform, wherein the element is a coordinate element;
s8, generating a machining path from the contour line
The contour S obtained in step S7c-smoothThe pixel coordinates in (b) are converted into the shooting platform actual coordinates according to the homography matrix H in step S1 using the following equations (8) and (9):
wherein u and v are Sc-smoothThe pixel coordinate value of (A) is a gray value, x and y are actual coordinate values of the machining path, x ', y', w 'are intermediate parameters, and (x', y ', w' are intermediate parametersc,yc) And (4) obtaining the origin coordinates of the processing platform obtained in the step (4).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911102219.1A CN112296999B (en) | 2019-11-12 | 2019-11-12 | Irregular workpiece machining path generation method based on machine vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911102219.1A CN112296999B (en) | 2019-11-12 | 2019-11-12 | Irregular workpiece machining path generation method based on machine vision |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112296999A CN112296999A (en) | 2021-02-02 |
| CN112296999B true CN112296999B (en) | 2022-07-08 |
Family
ID=74336233
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911102219.1A Active CN112296999B (en) | 2019-11-12 | 2019-11-12 | Irregular workpiece machining path generation method based on machine vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112296999B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113063804B (en) * | 2021-03-16 | 2022-07-15 | 太原科技大学 | Automatic positioning method of thermal cutting machine vision system based on image processing |
| CN114234808B (en) * | 2021-12-17 | 2022-10-28 | 湖南大学 | Size measuring method and device for deformation area of rotary magnetic pulse crimping part |
| CN115138527B (en) * | 2022-06-22 | 2023-12-26 | 深圳市双翌光电科技有限公司 | Rapid processing path generation method through visual guidance |
| CN116909208B (en) * | 2023-09-12 | 2023-11-24 | 深圳市钧诚精密制造有限公司 | Shell processing path optimization method and system based on artificial intelligence |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101488017A (en) * | 2009-02-24 | 2009-07-22 | 上海奈凯电子科技有限公司 | Real-time control method of process tool route of numerical control machine based on machine vision |
| CN104259670A (en) * | 2014-07-07 | 2015-01-07 | 河海大学常州校区 | Turbine blade laser cutting system based on machine vision and industrial robot |
| CN108161931A (en) * | 2016-12-07 | 2018-06-15 | 广州映博智能科技有限公司 | The workpiece automatic identification of view-based access control model and intelligent grabbing system |
| CN108972573A (en) * | 2018-06-12 | 2018-12-11 | 浙江大学 | A kind of industrial robot automation wheel hub polishing system and method based on characteristics of image identification |
| CN109158734A (en) * | 2018-10-31 | 2019-01-08 | 芜湖常瑞汽车部件有限公司 | A kind of automatic tracking system and method for abnormal shape weld seam |
| CN109190628A (en) * | 2018-08-15 | 2019-01-11 | 东北大学 | A kind of plate camber detection method based on machine vision |
| CN109454642A (en) * | 2018-12-27 | 2019-03-12 | 南京埃克里得视觉技术有限公司 | Robot coating track automatic manufacturing method based on 3D vision |
| CN109948247A (en) * | 2019-03-18 | 2019-06-28 | 福州大学 | A kind of handicraft surface in Automatic Optimal spraying direction sprays emulation mode |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP6157066B2 (en) * | 2012-06-11 | 2017-07-05 | キヤノン株式会社 | Image processing apparatus, object extraction system, image processing method, and program |
-
2019
- 2019-11-12 CN CN201911102219.1A patent/CN112296999B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101488017A (en) * | 2009-02-24 | 2009-07-22 | 上海奈凯电子科技有限公司 | Real-time control method of process tool route of numerical control machine based on machine vision |
| CN104259670A (en) * | 2014-07-07 | 2015-01-07 | 河海大学常州校区 | Turbine blade laser cutting system based on machine vision and industrial robot |
| CN108161931A (en) * | 2016-12-07 | 2018-06-15 | 广州映博智能科技有限公司 | The workpiece automatic identification of view-based access control model and intelligent grabbing system |
| CN108972573A (en) * | 2018-06-12 | 2018-12-11 | 浙江大学 | A kind of industrial robot automation wheel hub polishing system and method based on characteristics of image identification |
| CN109190628A (en) * | 2018-08-15 | 2019-01-11 | 东北大学 | A kind of plate camber detection method based on machine vision |
| CN109158734A (en) * | 2018-10-31 | 2019-01-08 | 芜湖常瑞汽车部件有限公司 | A kind of automatic tracking system and method for abnormal shape weld seam |
| CN109454642A (en) * | 2018-12-27 | 2019-03-12 | 南京埃克里得视觉技术有限公司 | Robot coating track automatic manufacturing method based on 3D vision |
| CN109948247A (en) * | 2019-03-18 | 2019-06-28 | 福州大学 | A kind of handicraft surface in Automatic Optimal spraying direction sprays emulation mode |
Non-Patent Citations (7)
| Title |
|---|
| An identification and classification method for circular object based on rotating image template matching;Jianke Chen et al.;《2013 IEEE International Conference on Mechatronics and Automation》;20131003;全文 * |
| On the determination of 3D trajectory of moving targets by stereovision;G. Bourgeniere ET AL.;《2005 1st International Conference on Computers, Communications, & Signal Processing with Special Track on Biomedical Engineering》;IEEE;20051116;全文 * |
| 不规则轮廓的机器视觉检测算法研究;孙坤;《中国优秀硕士学位论文全文电子期刊网 信息科技辑》;20181215;全文 * |
| 基于图像分割的船舶涂装轮廓检测方法;白伟志等;《机电一体化》;20160315(第03期);全文 * |
| 基于视觉的陶瓷点胶系统研究;张宽;《中国优秀硕士学位论文全文电子期刊网》;20181215;全文 * |
| 机器视觉在热切机中的应用;肖方生;《电子工业专用设备》;20180420(第02期);全文 * |
| 机器视觉在生瓷片印刷机中的应用;田辉等;《电子工艺技术》;20120718(第04期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112296999A (en) | 2021-02-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112296999B (en) | Irregular workpiece machining path generation method based on machine vision | |
| CN108088390B (en) | Optical losses three-dimensional coordinate acquisition methods based on double eye line structure light in a kind of welding detection | |
| CN107516098B (en) | Target contour three-dimensional information extraction method based on edge curvature angle | |
| CN108873700B (en) | Laser cladding closed-loop control method based on stereoscopic vision | |
| CN106524917B (en) | Object volume measurement method on a kind of conveyer belt | |
| CN110259067A (en) | The tile loading position recognition methods of robot and system | |
| CN105242568B (en) | Tobacco leaf based on Digital Image Processing accurately rejects control method | |
| CN112288796B (en) | Method for extracting center of perspective image mark point | |
| CN110246079B (en) | B-spline surface fitting-based camera distortion correction method, system and medium | |
| CN110411338A (en) | The welding gun tool parameters 3-D scanning scaling method of robot electric arc increasing material reparation | |
| CN115096206A (en) | Part size high-precision measurement method based on machine vision | |
| CN105809736B (en) | A kind of three-dimensional rebuilding method and device of pipeline | |
| CN109671059B (en) | Battery box image processing method and system based on OpenCV | |
| CN109671084B (en) | Method for measuring shape of workpiece | |
| CN109493426B (en) | Monocular imaging-based three-dimensional reconstruction method and system for blast furnace charge level | |
| CN107442973A (en) | Welding bead localization method and device based on machine vision | |
| CN109299556A (en) | A kind of ring cutting cutter orbit making and optimization method based on image procossing | |
| CN109895086A (en) | A kind of door of elevator snatch device and method of machine vision | |
| CN103136756B (en) | A kind of demarcation target and scaling method thereof that can be used for different accuracy camera calibration | |
| CN107705244B (en) | Edge connection correction method suitable for large-area multi-remote sensing image | |
| CN113888558A (en) | Ladle slag surface image correction method | |
| CN107146286B (en) | Three-dimensional model automatic adjustment method based on image edge characteristics | |
| CN110276296A (en) | A kind of structure light welding seam recognition methods based on image procossing | |
| CN112215846B (en) | Billet counting method and system based on three-dimensional point cloud | |
| CN113450350B (en) | Detection method based on texture features of cloth area |
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 |