CN112296999B - Irregular workpiece machining path generation method based on machine vision - Google Patents

Irregular workpiece machining path generation method based on machine vision Download PDF

Info

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
Application number
CN201911102219.1A
Other languages
Chinese (zh)
Other versions
CN112296999A (en
Inventor
赵忠志
马世杰
王安红
雷海卫
闫常春
肖方生
岳军
曹金亮
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Taiyuan University of Science and Technology
Northwest Electronic Equipment Institute of Technology
Original Assignee
Taiyuan University of Science and Technology
Northwest Electronic Equipment Institute of Technology
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Taiyuan University of Science and Technology, Northwest Electronic Equipment Institute of Technology filed Critical Taiyuan University of Science and Technology
Priority to CN201911102219.1A priority Critical patent/CN112296999B/en
Publication of CN112296999A publication Critical patent/CN112296999A/en
Application granted granted Critical
Publication of CN112296999B publication Critical patent/CN112296999B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

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
Figure DEST_PATH_IMAGE002
To obtain
Figure DEST_PATH_IMAGE004
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

Irregular workpiece machining path generation method based on machine vision
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,
Figure BDA0002270200540000011
Figure BDA0002270200540000012
Figure BDA0002270200540000021
Figure BDA0002270200540000022
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;
Figure BDA0002270200540000023
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，
Figure BDA0002270200540000024
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：
Figure BDA0002270200540000031
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):
Figure BDA0002270200540000032
Figure BDA0002270200540000033
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,
Figure BDA0002270200540000041
Figure BDA0002270200540000042
Figure BDA0002270200540000043
Figure BDA0002270200540000044
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;
Figure BDA0002270200540000051
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，
Figure BDA0002270200540000052
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：
Figure BDA0002270200540000053
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):
Figure BDA0002270200540000061
Figure BDA0002270200540000062
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
Figure BDA0002270200540000071
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,
Figure FDA0002270200530000011
Figure FDA0002270200530000012
Figure FDA0002270200530000013
Figure FDA0002270200530000014
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;
Figure FDA0002270200530000015
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，
Figure FDA0002270200530000021
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：
Figure FDA0002270200530000022
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):
Figure FDA0002270200530000023
Figure FDA0002270200530000024
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).
CN201911102219.1A 2019-11-12 2019-11-12 Irregular workpiece machining path generation method based on machine vision Active CN112296999B (en)

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)

* Cited by examiner, † Cited by third party
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)

* Cited by examiner, † Cited by third party
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)

* Cited by examiner, † Cited by third party
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

Patent Citations (8)

* Cited by examiner, † Cited by third party
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)

* Cited by examiner, † Cited by third party
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
CN110259067A (en) The tile loading position recognition methods of robot and system
CN104647390B (en) For the multiple-camera associating active tracing order calibration method of mechanical arm remote operating
CN106524917B (en) Object volume measurement method on a kind of conveyer belt
CN110246079B (en) B-spline surface fitting-based camera distortion correction method, system and medium
CN109493426B (en) Monocular imaging-based three-dimensional reconstruction method and system for blast furnace charge level
CN112288796B (en) Method for extracting center of perspective image mark point
CN110411338A (en) The welding gun tool parameters 3-D scanning scaling method of robot electric arc increasing material reparation
CN109671059B (en) Battery box image processing method and system based on OpenCV
zur Jacobsmühlen et al. Robustness analysis of imaging system for inspection of laser beam melting systems
CN107442973A (en) Welding bead localization method and device based on machine vision
CN105809736B (en) A kind of three-dimensional rebuilding method and device of pipeline
CN109483545B (en) Weld joint reconstruction method, intelligent robot welding method and system
CN116628800A (en) Building design system based on BIM
CN109299556A (en) A kind of ring cutting cutter orbit making and optimization method based on image procossing
CN103136756B (en) A kind of demarcation target and scaling method thereof that can be used for different accuracy camera calibration
CN104463964A (en) Method and equipment for acquiring three-dimensional model of object
CN109801340A (en) A kind of wheel grinding method based on image procossing
CN109544509B (en) Workpiece positioning method and device based on secondary template matching and storage device
CN106780425B (en) Positioning method of vortex detection system of heat transfer tube of VVER steam generator
CN113129442A (en) Calibration method of linear structured light vision sensor based on single-cylinder 3D target
CN113888558A (en) Ladle slag surface image correction method
CN110276296A (en) A kind of structure light welding seam recognition methods based on image procossing

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