CN112643755B - Method and device for full-automatic equal-area blocking of sheet-shaped objects in any shape based on machine vision - Google Patents

Method and device for full-automatic equal-area blocking of sheet-shaped objects in any shape based on machine vision Download PDF

Info

Publication number
CN112643755B
CN112643755B CN202011370045.XA CN202011370045A CN112643755B CN 112643755 B CN112643755 B CN 112643755B CN 202011370045 A CN202011370045 A CN 202011370045A CN 112643755 B CN112643755 B CN 112643755B
Authority
CN
China
Prior art keywords
image
blocking
irregular
coordinate system
sheet
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
CN202011370045.XA
Other languages
Chinese (zh)
Other versions
CN112643755A (en
Inventor
毕文波
赵玉康
葛培琪
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.)
Shandong University
Original Assignee
Shandong University
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 Shandong University filed Critical Shandong University
Priority to CN202011370045.XA priority Critical patent/CN112643755B/en
Publication of CN112643755A publication Critical patent/CN112643755A/en
Application granted granted Critical
Publication of CN112643755B publication Critical patent/CN112643755B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B26—HAND CUTTING TOOLS; CUTTING; SEVERING
    • B26D—CUTTING; DETAILS COMMON TO MACHINES FOR PERFORATING, PUNCHING, CUTTING-OUT, STAMPING-OUT OR SEVERING
    • B26D5/00—Arrangements for operating and controlling machines or devices for cutting, cutting-out, stamping-out, punching, perforating, or severing by means other than cutting
    • B26D5/007—Control means comprising cameras, vision or image processing systems

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Forests & Forestry (AREA)
  • Mechanical Engineering (AREA)
  • Image Processing (AREA)

Abstract

The method comprises the steps of firstly defining the area of a unit block according to requirements to calculate the number of the unit blocks, then calculating the number of pixels of each block after vertical partitioning of the irregular sheet, obtaining the coordinates of the starting points of all vertical partition lines by traversing images, then traversing the images again to obtain the coordinates of the starting points of all horizontal partition lines in each vertical block area, and finally completing partitioning and cutting by a cutter system. The traditional blocking method is fixed in cutting path, the method for fixing the cutting path cannot meet the requirement for equal-area blocking cutting of irregular sheet-shaped objects, for example, a steak processing factory needs to perform equal-area blocking cutting on steaks with irregular shapes, the method and the device can complete full-automatic equal-area blocking cutting on any irregular sheet-shaped object, and have good application prospects.

Description

Method and device for full-automatic equal-area blocking of sheet-shaped objects in any shape based on machine vision
Technical Field
The invention relates to a method and a device for full-automatic equal-area blocking of a sheet-shaped object in any shape based on machine vision, in particular to a method and a device for full-automatic equal-area blocking of a sheet-shaped object in an irregular shape.
Background
The process of cutting the sheet into blocks is widely applied to different industries, and whether the block area is uniform or not can affect the quality and performance of the sheet, such as the glass production industry, the silicon wafer production industry and the like. A certain part of the sheet materials which need to be subjected to the block cutting process all have regular shapes, the cutting path after the equal-area block is calculated by a traditional method, and then the calculated path is transmitted to a numerical control system, so that the cutter is controlled to finish the equal-area block cutting of the regular sheet materials. Meanwhile, some industries have the requirement of performing equal-area block cutting on irregularly-shaped sheets, for example, in the steak processing industry, the equal-area block cutting process of steaks is an essential process, but the steaks to be subjected to block cutting are generally irregular in shape, so that the steak cutting process needs assistance of workers and cannot realize complete automatic cutting, and compared with a full-automatic cutting mode, the block cutting mode is low in efficiency and high in cutting cost. For the irregularly-shaped sheet-like objects, the shapes, areas and the like of the sheet-like objects are different, so that the cutting paths are different when the equally-area block cutting is carried out on the different sheet-like objects, and therefore, the fixed cutting paths cannot be calculated in advance through the traditional method. The acquired images of the sheet-shaped objects can be analyzed through machine vision, the cutting paths of the irregular-shaped sheet-shaped objects with different areas are obtained after the same-area blocking through image processing, and then the control module in the cutter system controls the cutter to complete the equal-area blocking cutting of the irregular-shaped sheet-shaped objects according to the calculated blocking cutting paths.
Disclosure of Invention
In order to overcome the defect that the traditional equal-area blocking method is only suitable for blocking and cutting the sheet-shaped object with a regular shape but not suitable for blocking the sheet-shaped object with a large shape change, the invention provides a full-automatic equal-area blocking method and device for the irregular sheet-shaped object based on machine vision, wherein the method has the advantages of self-adaption to any complicated shape, high blocking precision, good real-time performance and the like, the device can be used as a carrier for realizing the method, and the schematic diagram of each component of the device is shown in figure 1;
the utility model provides a full-automatic equal area blocking device of irregular sheet-like thing based on machine vision, includes following 3 sub-device and constitutes:
sub-device 1. light source: the method is used for increasing the gray value difference of the irregular sheet-shaped object to be segmented and the background in the image;
sub-device 2. industrial camera: the device is used for acquiring an original image of the irregular sheet-shaped object;
sub-device 3. computer: the device is used for installing the blocking software which is compiled according to the full-automatic equal-area blocking method of the irregular sheet-shaped objects;
sub-device 4. cutter system: the control module is used for controlling the cutter to move according to the divided cutting path, and the cutter module is used for finishing the cutting of the irregular sheet-shaped objects.
In order to realize full-automatic equal-area blocking of irregular sheet-shaped objects, the method for full-automatic equal-area blocking of sheet-shaped objects in any shape based on machine vision comprises the following steps:
acquiring an original image of an irregular sheet-shaped object;
step (2) image preprocessing: firstly, separating color components of RGB channels of an image, generating a proper single-channel color component image according to different types of images to be processed, then removing noise in the image by wavelet denoising and filtering, finally converting a gray level image into a binary image by global self-adaptive binarization, and completing segmentation of irregular sheets and a background in the image;
step (3) completing image blocking to obtain a blocking path of the irregular sheet-shaped object;
and (4) outputting the blocking path of the irregular sheet-shaped object to a cutter system to complete the full-automatic equal-area blocking of the irregular sheet-shaped object.
1. Further, the step (3) comprises the following steps:
step (3.1) obtaining the total number N of pixels contained in the target object to be segmented in the image by traversing the imagepAnd coordinate values (u) of each edge pixel included in the objecte,ve)；
Step (3.2) utilizing a camera to calibrate and obtain the dimension d of each pixel in the direction of the image coordinate system UuAnd a dimension d in the direction of the image coordinate system VvObtaining the conversion relation of the size of a single pixel under an image coordinate system and a world coordinate system by using the formula (1), dxwAnd dywRespectively representing the dimensions in the X-and Y-directions of a single pixel after conversion to the world coordinate system, nmRepresents the magnification of the camera;
Figure RE-GDA0002899254700000031
step (3.3) calculates an area value A in a world coordinate system expressed by a single pixel by using the formula (2)wpCalculating the unit block area A of the target object needing to be roughly divided into l unit blocks in the image by using the formula (3);
Awp＝dxw×dyw (2)
Figure RE-GDA0002899254700000032
step (3.4) firstly dividing the irregular target object into l in the direction of the image coordinate system UcBlock, lcThe coordinate value U of the i-th dividing line in the U direction of the image U-V coordinate system is calculated by the formula (5) obtained from the formula (4)iIn which N isuRepresenting the maximum number of pixels, U, of an object in the image that are included in the direction of the U-V coordinate system U0Representing the distance from the nearest pixel point of the target object in the image to the V axis in the U-V coordinate system;
Figure RE-GDA0002899254700000033
Figure RE-GDA0002899254700000034
and (3.5) partitioning the irregular target object in the direction of the image coordinate system V, calculating the number of pixels contained in a unit block by using a formula (6), and obtaining n by using formulas (7) and (8)cAnd nrAnd finding out coordinate values, v, of the starting points of the vertical and horizontal dividing lines by using the loop statements shown in the flow chartiminDenotes the minimum value of the V coordinate at the intersection of the straight line u-i with the object in the image coordinate system, VimaxDenotes the maximum value of the V coordinate at the intersection of the straight line u ═ i and the target in the image coordinate system, uc,l-1U coordinate value, U, representing the l-1 vertical dividing linec,lA U coordinate value representing the first vertical dividing line;
Figure RE-GDA0002899254700000041
Figure RE-GDA0002899254700000042
Figure RE-GDA0002899254700000043
and (3.6) blocking the irregular sheet-shaped object according to the obtained initial coordinate value of the horizontal and vertical blocking line.
1. Further, the step (4) comprises the following steps:
step (4.1) storing the coordinates of the starting point of the vertical dividing line of the irregular sheet-shaped object into a matrix M from left to right according to the positions of the dividing lines;
step (4.2) firstly storing the horizontal dividing lines of the left interval and then storing the horizontal dividing lines of the right interval according to the left-to-right sequence in the interval sequencing of the intervals divided by the vertical dividing lines, then adopting a storage sequence from top to bottom in the interval formed by the vertical dividing lines, firstly storing the horizontal dividing lines positioned at the upper positions of the intervals, then storing the horizontal dividing lines positioned at the lower positions of the intervals, and storing the coordinates of the starting points of the horizontal dividing lines into the matrix M according to the sequence;
and (4.1) transmitting the matrix M to a cutter system, and controlling a cutter to complete vertical blocking according to a vertical dividing line and then complete horizontal blocking according to a horizontal dividing line by a control module in the cutter system.
Compared with the traditional method for cutting the flaky object into blocks, the method and the device have the advantages of strong self-adaptive capacity, capability of completing full-automatic equal-area block cutting on the flaky object with any irregular shape, wide application prospect in the industry needing the equal-area block cutting on the flaky object, and more obvious advantages particularly when the flaky object with the irregular shape is cut in the equal-area block manner.
Drawings
FIG. 1 is a schematic view of the components of the blocking device of the present invention;
FIG. 2 is a basic flow chart of the full-automatic equal-area blocking method of irregular sheet-shaped objects based on machine vision;
FIG. 3 shows the result of image blocking when the number of pixels per block is 1500, taking a steak image as an example;
Detailed Description
The invention will be further described with reference to specific embodiments, and the advantages and features of the invention will become apparent as the description proceeds. The examples are illustrative only and do not limit the scope of the present invention in any way. It will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention, and that such changes and modifications may be made without departing from the spirit and scope of the invention. ,
embodiment 1 a full-automatic equal-area partitioning device for irregular sheet-like objects based on machine vision
As shown in fig. 1, the full-automatic equal-area partitioning device for irregular sheets comprises the following 3 sub-devices:
sub-device 1. light source: the method is used for increasing the gray value difference of the irregular sheet-shaped object to be segmented and the background in the image;
sub-device 2. industrial camera: the device is used for acquiring an original image of the irregular sheet-shaped object;
sub-device 3. computer: the device is used for installing the blocking software which is compiled according to the full-automatic equal-area blocking method of the irregular sheet-shaped objects;
sub-device 4. cutter system: the control module is used for controlling the cutter to move according to the divided cutting path, and the cutter module is used for finishing the cutting of the irregular sheet-shaped objects.
Embodiment 2 method for full-automatic equal-area blocking of sheet-like objects in any shape based on machine vision
As shown in fig. 2, the specific steps are as follows:
setting a light source according to actual conditions, and acquiring an original image of a sheet product through an industrial CCD (charge coupled device) or CMOS (complementary metal oxide semiconductor) camera;
step (2) image preprocessing: firstly, separating color components of RGB channels of an image, generating a proper single-channel color component image according to different processing objects, then removing noise in the image by wavelet denoising and filtering, finally converting a gray level image into a binary image by global self-adaptive binarization, and completing segmentation of irregular sheets and a background in the image;
and (3) completing image blocking to obtain a blocking path of the irregular sheet-shaped object, which comprises the following specific steps:
step (3.1) obtaining the total number N of pixels contained in the target object to be segmented in the image by traversing the imagepAnd coordinate values (u) of each edge pixel included in the objecte,ve)；
Step (3.2) utilizing a camera to calibrate and obtain the dimension d of each pixel in the direction of the image coordinate system UuAnd a dimension d in the direction of the image coordinate system VvObtaining the conversion relation of the size of a single pixel under an image coordinate system and a world coordinate system by using the formula (1), dxwAnd dywRespectively representing the dimensions in the X-and Y-directions of a single pixel after conversion to the world coordinate system, nmRepresents the magnification of the camera;
Figure RE-GDA0002899254700000061
step (3.3) calculates an area value A in a world coordinate system expressed by a single pixel by using the formula (2)wpCalculating the unit block area A of the target object needing to be roughly divided into l unit blocks in the image by using the formula (3);
Awp＝dxw×dyw (2)
Figure RE-GDA0002899254700000062
step (3.4) firstly dividing the irregular target object into l in the direction of the image coordinate system UcBlock, lcThe coordinate value U of the i-th dividing line in the U direction of the image U-V coordinate system is calculated by the formula (5) obtained from the formula (4)iIn which N isuRepresenting the maximum number of pixels, U, of an object in the image that are included in the direction of the U-V coordinate system U0Representing the distance from the nearest pixel point of the target object in the image to the V axis in the U-V coordinate system;
Figure RE-GDA0002899254700000071
Figure RE-GDA0002899254700000072
and (3.5) partitioning the irregular target object in the direction of the image coordinate system V, calculating the number of pixels contained in a unit block by using a formula (6), and obtaining n by using formulas (7) and (8)cAnd nrAnd finding out coordinate values, v, of the starting points of the vertical and horizontal dividing lines by using the loop statements shown in the flow chartiminDenotes the minimum value of the V coordinate at the intersection of the straight line u-i with the object in the image coordinate system, VimaxDenotes the maximum value of the V coordinate at the intersection of the straight line u ═ i and the target in the image coordinate system, uc,l-1U coordinate value, U, representing the l-1 vertical dividing linec,lA U coordinate value representing the first vertical dividing line;
Figure RE-GDA0002899254700000073
Figure RE-GDA0002899254700000074
Figure RE-GDA0002899254700000075
and (3.6) blocking the irregular sheet-shaped target object according to the obtained initial coordinate value of the horizontal and vertical blocking line.
Step (4) outputting the blocking path of the irregular sheet-shaped object to a cutter system to finish the irregular sheet-shaped object
The full-automatic equal-area blocking method of the object comprises the following specific steps:
step (4.1) storing the coordinates of the starting point of the vertical dividing line of the irregular sheet-shaped object into a matrix M from left to right according to the positions of the dividing lines;
step (4.2) firstly storing the horizontal dividing lines of the left interval and then storing the horizontal dividing lines of the right interval according to the left-to-right sequence in the interval sequencing of the intervals divided by the vertical dividing lines, then adopting a storage sequence from top to bottom in the interval formed by the vertical dividing lines, firstly storing the horizontal dividing lines positioned at the upper positions of the intervals, then storing the horizontal dividing lines positioned at the lower positions of the intervals, and storing the coordinates of the starting points of the horizontal dividing lines into the matrix M according to the sequence;
and (4.3) transmitting the matrix M to a cutter system, and controlling a cutter to complete vertical blocking according to a vertical dividing line and then complete horizontal blocking according to a horizontal dividing line by a control module in the cutter system.
Test examples; the result of image blocking when the number of pixels of a unit block is 1500 for a beefsteak image as an example is shown in fig. 3.

Claims (3)

1. The utility model provides a full-automatic equal area blocking device of irregular sheet based on machine vision which characterized in that, the full-automatic equal area blocking device of irregular sheet includes following 3 sub-device and constitutes:
sub-device 1. light source: the method is used for increasing the gray value difference of the irregular sheet-shaped object to be segmented and the background in the image;
sub-device 2. industrial camera: the device is used for acquiring an original image of the irregular sheet-shaped object;
sub-device 3. computer: the device is used for installing the blocking software which is compiled according to the full-automatic equal-area blocking method of the irregular sheet-shaped objects;
the cutter system comprises: the control module is used for controlling the cutter to move according to the divided cutting path, and the cutter module is used for finishing the cutting of the irregular sheet-shaped objects;
the full-automatic equal-area blocking method for the irregular sheet-shaped object by the full-automatic equal-area blocking device based on the machine vision comprises the following steps:
acquiring an original image of an irregular sheet-shaped object;
step (2) image preprocessing: firstly, separating color components of RGB channels of an image, generating a proper single-channel color component image according to different types of images to be processed, then removing noise in the image by wavelet denoising and filtering, finally converting a gray level image into a binary image by global self-adaptive binarization, and completing segmentation of irregular sheets and a background in the image;
step (3) completing image blocking to obtain a blocking path of the irregular sheet-shaped object;
step (4) outputting the blocking path of the irregular sheet-shaped object to a cutter system to complete full-automatic equal-area blocking of the irregular sheet-shaped object;
the step (3) comprises the following steps:
step (3.1) obtaining the total number N of pixels contained in the irregular sheet-shaped object needing to be segmented in the image by traversing the imagepAnd coordinate values (u) of each edge pixel included in the objecte,ve)；
Step (3.2) utilizing a camera to calibrate and obtain the dimension d of each pixel in the direction of the image coordinate system UuAnd a dimension d in the direction of the image coordinate system VvObtaining the conversion relation of the size of a single pixel under an image coordinate system and a world coordinate system by using the formula (1), dxwAnd dywRespectively representing the dimensions in the X-and Y-directions of a single pixel after conversion to the world coordinate system, nmRepresents the magnification of the camera;
Figure FDA0003199869940000021
step (3.3) calculates an area value A in a world coordinate system expressed by a single pixel by using the formula (2)wpCalculating the unit block area A of the target object needing to be roughly divided into l unit blocks in the image by using the formula (3);
Awp＝dxw×dyw (2)
Figure FDA0003199869940000022
step (3.4) firstly dividing the irregular target object into l in the direction of the image coordinate system UcBlock, lcCan be represented by the formula (4) Obtaining the coordinate value U of the ith dividing line in the direction of the image U-V coordinate system U by using the formula (5)iIn which N isuRepresenting the maximum number of pixels, U, of an object in the image that are included in the direction of the U-V coordinate system U0Representing the distance from the nearest pixel point of the target object in the image to the V axis in the U-V coordinate system;
Figure FDA0003199869940000023
Figure FDA0003199869940000024
and (3.5) partitioning the irregular target object in the direction of the image coordinate system V, calculating the number of pixels contained in a unit block by using a formula (6), and obtaining n by using formulas (7) and (8)cAnd nrAnd finding out coordinate values, v, of the starting points of the vertical and horizontal dividing lines by using the loop statements shown in the flow chartiminDenotes the minimum value of the V coordinate at the intersection of the straight line u-i with the object in the image coordinate system, VimaxDenotes the maximum value of the V coordinate at the intersection of the straight line u ═ i and the target in the image coordinate system, uc,l-1U coordinate value, U, representing the l-1 vertical dividing linec,lA U coordinate value representing the first vertical dividing line;
Figure FDA0003199869940000031
Figure FDA0003199869940000032
Figure FDA0003199869940000033
(1) and (3.6) blocking the irregular sheet-shaped target object according to the obtained initial coordinate value of the horizontal and vertical blocking line.
2. The machine vision based full-automatic equal-area blocking device for irregular sheets according to claim 1, wherein in the step (1), an original image of the irregular sheets is acquired through an industrial CCD or CMOS camera.
3. The machine vision based irregular sheet full-automatic equal-area blocking device according to claim 1, wherein the step (4) comprises the following steps:
step (4.1) storing the coordinates of the starting point of the vertical dividing line of the irregular sheet-shaped object into a matrix M from left to right according to the positions of the dividing lines;
step (4.2) firstly storing the horizontal dividing lines of the left interval and then storing the horizontal dividing lines of the right interval according to the left-to-right sequence in the interval sequencing of the intervals divided by the vertical dividing lines, then adopting a storage sequence from top to bottom in the interval formed by the vertical dividing lines, firstly storing the horizontal dividing lines positioned at the upper positions of the intervals, then storing the horizontal dividing lines positioned at the lower positions of the intervals, and storing the coordinates of the starting points of the horizontal dividing lines into the matrix M according to the sequence;
and (4.3) transmitting the matrix M to a cutter system, and controlling a cutter to complete vertical blocking according to a vertical dividing line and then complete horizontal blocking according to a horizontal dividing line by a control module in the cutter system.
CN202011370045.XA 2020-11-30 2020-11-30 Method and device for full-automatic equal-area blocking of sheet-shaped objects in any shape based on machine vision Active CN112643755B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011370045.XA CN112643755B (en) 2020-11-30 2020-11-30 Method and device for full-automatic equal-area blocking of sheet-shaped objects in any shape based on machine vision

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011370045.XA CN112643755B (en) 2020-11-30 2020-11-30 Method and device for full-automatic equal-area blocking of sheet-shaped objects in any shape based on machine vision

Publications (2)

Publication Number Publication Date
CN112643755A CN112643755A (en) 2021-04-13
CN112643755B true CN112643755B (en) 2021-09-07

Family

ID=75349719

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011370045.XA Active CN112643755B (en) 2020-11-30 2020-11-30 Method and device for full-automatic equal-area blocking of sheet-shaped objects in any shape based on machine vision

Country Status (1)

Country Link
CN (1) CN112643755B (en)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS57651A (en) * 1980-06-03 1982-01-05 Hiromitsu Azumi Device for sticking photocomposed photographic paper
CN103171927A (en) * 2013-03-14 2013-06-26 苏州吉视电子科技有限公司 Carpet automatic cutting device and method using real-time machine vision technology
CN103217108A (en) * 2013-04-01 2013-07-24 东华大学 Method for detecting geometrical parameters of spectacle frame
CN205473371U (en) * 2016-04-13 2016-08-17 河北工业大学 Intelligent glass cutting system based on machine vision
CN111445486A (en) * 2020-03-25 2020-07-24 腾讯科技（深圳）有限公司 Image processing method, device, equipment and computer readable storage medium
CN111823303A (en) * 2020-07-16 2020-10-27 中科龙人高新技术有限公司 3D intelligence cloth and leather cutting machine control system

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS57651A (en) * 1980-06-03 1982-01-05 Hiromitsu Azumi Device for sticking photocomposed photographic paper
CN103171927A (en) * 2013-03-14 2013-06-26 苏州吉视电子科技有限公司 Carpet automatic cutting device and method using real-time machine vision technology
CN103217108A (en) * 2013-04-01 2013-07-24 东华大学 Method for detecting geometrical parameters of spectacle frame
CN205473371U (en) * 2016-04-13 2016-08-17 河北工业大学 Intelligent glass cutting system based on machine vision
CN111445486A (en) * 2020-03-25 2020-07-24 腾讯科技（深圳）有限公司 Image processing method, device, equipment and computer readable storage medium
CN111823303A (en) * 2020-07-16 2020-10-27 中科龙人高新技术有限公司 3D intelligence cloth and leather cutting machine control system

Also Published As

Publication number Publication date
CN112643755A (en) 2021-04-13

Similar Documents

Publication Publication Date Title
CN111007073A (en) Method and system for online detection of part defects in additive manufacturing process
CN114820773B (en) Silo transport vehicle carriage position detection method based on computer vision
CN113393464B (en) Three-dimensional detection method for plate glass defects
CN105217324A (en) A kind of novel de-stacking method and system
CN110136211A (en) A kind of workpiece localization method and system based on active binocular vision technology
CN113034593B (en) 6D pose labeling method, system and storage medium
CN112465809A (en) Mold defect detection method based on image recognition, computer-readable storage medium and device
CN114331986A (en) Dam crack identification and measurement method based on unmanned aerial vehicle vision
WO2020133888A1 (en) Scale-invariant depth map mapping method for three-dimensional image
CN114235837A (en) LED packaging surface defect detection method, device, medium and equipment based on machine vision
CN116337887A (en) Method and system for detecting defects on upper surface of casting cylinder body
CN112643755B (en) Method and device for full-automatic equal-area blocking of sheet-shaped objects in any shape based on machine vision
CN110899147A (en) Laser scanning-based online stone sorting method for conveyor belt
CN114842335B (en) Grooving target identification method and system for construction robot
CN116465896A (en) Automobile part vision detection device and detection method based on artificial intelligence
CN113240579A (en) Intelligent industrial product defect detection method and device and computer storage medium thereof
CN116258912A (en) Workpiece identification method based on convolutional neural network
CN115582840B (en) Method and system for calculating sorting and grabbing pose of borderless steel plate workpiece and sorting method
CN116309547B (en) Part surface quality detection method, device, equipment and medium
CN220584069U (en) Automobile part vision detection device
CN116188302A (en) Method, system, device and storage medium for image background illumination homogenization
CN109448057B (en) Safety positioning method based on three-dimensional point cloud
CN113720280A (en) Bar center positioning method based on machine vision
CN116843919A (en) RGB-D surface normal vector estimation method based on fractional differentiation
CN108898590B (en) Self-feature extraction method applied to product appearance visual detection

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