Glue path detection method, device and equipment and storage medium

Through spatial point cloud data acquisition and correction technology, the height and width of the glue path are automatically identified and calculated, and the problem of low detection accuracy of existing glue paths is solved, high-precision glue path detection and defect identification are achieved, and labor costs are reduced.

CN118913133APending Publication Date: 2024-11-08SHENZHEN ZHIJI VISION TECH CO LTD
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202410960585.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-17
Publication Date
2024-11-08

AI Technical Summary

Technical Problem

The existing rubber circuit inspection mainly relies on labor, which leads to high cost and low detection accuracy, which cannot effectively solve the accuracy of rubber circuit inspection.

Method used

Using spatial point cloud data acquisition and correction technology, the spatial point cloud data is corrected by fitting the plane to be corrected, rotating the data, identifying the glue path and dividing it into several sections, obtaining the cross-sectional profile of each section, calculating the height and width, and realizing automation Glue circuit inspection.

Benefits of technology

It realizes high-precision automation of glue circuit inspection, reduces labor costs, improves detection accuracy, can accurately judge the height and width of glue circuits, identify defects such as broken glue and wall climbing, and improves product quality control.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118913133A_ABST
    Figure CN118913133A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of glue path detection, and provides a glue path detection method, device and equipment and a storage medium, and the method comprises the steps: collecting spatial point cloud data of a specified surface on a target product; selecting the spatial point cloud data in the same plane as to-be-corrected data at a fixed position of the specified surface; fitting based on the to-be-corrected data to obtain a corresponding to-be-corrected plane, and calculating rotation data for correcting the to-be-corrected plane to a horizontal attitude; performing correction processing on the spatial point cloud data based on the rotation data; determining a glue path on the specified surface based on height information contained in the spatial point cloud data; the glue path is divided into a plurality of sections, and the contour line of the cross section of each section of the glue path obtained through division is obtained; and respectively acquiring the height and the width of each contour line to realize the detection of the glue path. The glue path detection precision can be effectively improved while the labor cost is greatly reduced.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of glue path detection, and in particular to a glue path detection method, device, equipment and storage medium. Background Art

[0002] Many parts and modules in industrial and civilian products must go through the gluing process. To ensure product compliance, it is usually necessary to conduct corresponding inspections on the glue path. The existing technology usually implements glue path inspection manually, but this method has high labor costs and is prone to low accuracy of inspection results due to human subjectivity. Summary of the invention

[0003] In view of this, the present invention provides a glue road detection method, device, equipment and storage medium, which can not only effectively reduce labor costs but also achieve higher detection accuracy.

[0004] The present invention provides the following technical solutions:

[0005] A glue road detection method, comprising:

[0006] Collect spatial point cloud data of the specified surface on the target product;

[0007] At a fixed position of the designated surface, selecting spatial point cloud data in the same plane as data to be corrected;

[0008] A corresponding plane to be corrected is obtained by fitting the data to be corrected, and rotation data for correcting the plane to be corrected to a horizontal posture is calculated;

[0009] Performing correction processing on the spatial point cloud data based on the rotation data;

[0010] Determining the glue path on the designated surface based on the height information included in the spatial point cloud data;

[0011] Dividing the glue road into a plurality of sections to obtain a contour line of a cross section of each glue road section obtained by dividing;

[0012] The height and width of each contour line are obtained respectively to detect the glue path.

[0013] Preferably, before selecting the spatial point cloud data in the same plane as the data to be corrected at the fixed position of the designated surface, the method further comprises:

[0014] The spatial point cloud data is denoised using median filtering, Gaussian filtering or mean filtering.

[0015] Preferably, respectively obtaining the height of each of the contour lines comprises:

[0016] The plane obtained by correcting the plane to be corrected to a horizontal posture is determined as a reference plane, and the distance between the highest point in each of the contour lines and the reference plane is respectively obtained as the height of the corresponding contour line.

[0017] Preferably, respectively obtaining the width of each of the contour lines comprises:

[0018] Determine a height reference line, determine the intersection points between each of the contour lines and the height reference line, and determine the distance between the two farthest intersection points corresponding to each of the contour lines as the width of the corresponding contour line.

[0019] Preferably, respectively obtaining the width of each of the contour lines comprises:

[0020] Determine any contour line as the current contour line;

[0021] Determine the coordinate axis of the current contour line, the horizontal axis is the width direction of the previous contour line, and the vertical axis is the height direction of the current contour line;

[0022] Determine the height reference line, take the height reference line as the new horizontal axis, and derive the vertical axis of the current contour line on the new horizontal axis. The distance between the two points farthest apart whose result is greater than the preset value is the width of the current contour line.

[0023] Preferably, after respectively obtaining the height and width of each of the contour lines, the method further includes:

[0024] If, among any plurality of adjacent contour lines, there are contour lines of a specified proportion whose heights and / or widths are lower than corresponding thresholds, it is determined that glue breaking occurs in the glue path portion corresponding to the arbitrary plurality of adjacent contour lines.

[0025] Preferably, after determining the glue path on the designated surface based on the height information included in the spatial point cloud data, the method further includes:

[0026] If the distance between any point in the glue path and the designated mark position is lower than a corresponding threshold value, it is determined that there is a wall climbing on the glue path at the arbitrary point.

[0027] A glue path detection device, comprising:

[0028] The acquisition module is used to: acquire spatial point cloud data of a specified surface on a target product;

[0029] A selection module is used to: select spatial point cloud data in the same plane at a fixed position of the designated surface as data to be corrected;

[0030] A fitting module, used to: obtain a corresponding plane to be corrected based on the data to be corrected by fitting, and calculate rotation data for correcting the plane to be corrected to a horizontal posture;

[0031] A correction module, used to: perform correction processing on the spatial point cloud data based on the rotation data;

[0032] A determination module, used to: determine the glue path on the specified surface based on the height information included in the spatial point cloud data;

[0033] A division module is used to: divide the glue road into a plurality of sections, and obtain the contour line of the cross section of each glue road obtained by division;

[0034] The acquisition module is used to respectively acquire the height and width of each of the contour lines to detect the glue path.

[0035] A glue path detection device comprises a memory and a processor. When the program stored in the memory is executed by the processor, the steps of the glue path detection method as described in any one of the above items can be implemented.

[0036] A computer-readable storage medium, wherein when a program stored on the computer-readable storage medium is executed by a processor, the steps of the glue path detection method as described in any one of the above items are implemented.

[0037] The present invention incorporates a 3D correction function for inclined plane space, which automatically corrects spatial point cloud data in 3D space, thereby eliminating the problem of inaccurate detection results due to axial or radial rotation caused by the product not being absolutely level, and achieving a significant improvement in detection accuracy; at the same time, after identifying the glue path based on height information, the glue path is divided into several sections to obtain contour lines of several cross sections, and data such as glue width and height are detected on each contour line, so as to accurately judge key parameters such as the height and width of the glue path; and the present invention is fully automatic, and compared with the prior art of manually realizing glue path detection, it can greatly reduce labor costs while effectively improving the glue path detection accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0039] Figure 1 is a flow chart of a glue path detection method provided according to an embodiment of the present invention;

[0040] Figure 2 is an example diagram of contour lines in a glue path detection method provided according to an embodiment of the present invention;

[0041] Figure 3It is a structural schematic diagram of a glue path detection device provided according to an embodiment of the present invention. DETAILED DESCRIPTION

[0042] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0043] See also Figure 1 , which shows a flow chart of a glue path detection method provided by an embodiment of the present invention, which may specifically include:

[0044] S11: Collect spatial point cloud data of the specified surface on the target product.

[0045] Among them, the target product is the product that currently needs to be inspected for glue path, and the designated surface on the target product is the surface on the target product that currently needs to be inspected for glue path. The embodiment of the present invention can collect spatial point cloud data of the designated surface on the target product based on the 3D laser profile sensor and the principle of laser triangulation; these sensors have built-in high-precision 3D algorithms, and can output point cloud data, depth maps, brightness maps and other data information with high frame rate and sub-micron accuracy in real time, which is conducive to the realization of glue path detection; in another embodiment, the embodiment of the present invention can also use a line laser camera or a structured light camera to collect spatial point cloud data of the designated surface on the target product according to the product detection position and detection efficiency requirements, wherein the line laser camera collects spatial point cloud data by scanning and cooperating with the motion axis, while the structured light camera collects spatial point cloud data in a fixed manner. The spatial point cloud data is consistent with the corresponding concept in the prior art, including multiple data such as three-dimensional spatial coordinates and color values, which will not be described in detail here.

[0046] S12: At a fixed position on the designated surface, select spatial point cloud data on the same plane as data to be corrected.

[0047] S13: Obtain a corresponding plane to be corrected based on the data to be corrected by fitting, and calculate rotation data for correcting the plane to be corrected to a horizontal posture.

[0048] S14: Correct the spatial point cloud data based on the rotation data.

[0049] The fixed positions are multiple positions determined on the specified surface where no glue path exists. The spatial point cloud data located on the same plane is taken at the fixed positions. A plane is fitted based on the selected spatial point cloud data (the plane can be used as a reference plane), and the rotation data of the fitted plane when it is corrected to a horizontal posture can be determined, and then all the spatial point cloud data collected in step S11 are corrected based on the rotation data. The rotation data can be a rotation angle. If the fitted plane needs to be rotated in a certain direction by an angle a when it is corrected to a horizontal posture, all the spatial point cloud data are processed into data obtained by rotating in the certain direction by an angle a, and the correction processing of the spatial point cloud data can be realized.

[0050] In a specific implementation, the plane composed of the xy axes is set to be a parallel plane to the horizontal posture plane, and the z axis is a direction perpendicular to the horizontal posture plane. After fitting the plane to be corrected, the rotation angle of the plane to be corrected around the x-axis and the y-axis can be obtained, and the corresponding transformation matrix (that is, the matrix that corrects the plane to be corrected to the horizontal posture) is calculated according to the rotation angle, and all spatial point cloud data are corrected to the corresponding posture based on the transformation matrix.

[0051] It can be seen that the embodiment of the present invention incorporates the inclined plane space 3D correction function, that is, using the specified plane as the reference plane, automatically correcting the spatial point cloud data in the 3D space through certain affine transformation, scaling and rotation, which can eliminate the problem of inaccurate detection results caused by axial or radial rotation due to the product not being absolutely level, thereby making the detection results more accurate than the traditional and currently commonly used methods, and can directly improve the detection accuracy to the sub-micron level, achieving a significant improvement in detection accuracy. These technologies can be widely used in various industries, such as 3C industry and auto parts manufacturing, to achieve accurate glue road detection scenarios.

[0052] S15: Determine the glue path on the designated surface based on the height information included in the spatial point cloud data.

[0053] S16: Divide the glue road into several sections, and obtain the contour line of the cross section of each glue road obtained by division.

[0054] S17: respectively obtaining the height and width of each of the contour lines to detect the glue path.

[0055] In the process of glue path detection, by measuring the height information of the glue path and the surrounding results (information indicating the highest point of the corresponding position), the boundary between the glue path and the surrounding environment, or the position of the glue path, can be clearly identified; this is because the glue is applied on the reference plane, and through the correction of step S12, it is equivalent to detecting glue on a horizontal surface, so the glue can be easily extracted through the height information, that is, the position that is not other structures and is higher than the horizontal surface (or the value higher than the horizontal surface reaches the corresponding threshold) is the position of the glue. Divide the glue path into several sections, and each two adjacent sections of the glue path have cross sections, so as to obtain the contour lines of several cross sections, and detect the glue width, height and other data on each contour line, and then these data can be summarized, that is, the information of the glue path detected.

[0056] The present invention incorporates a 3D correction function for inclined plane space, which automatically corrects spatial point cloud data in 3D space, thereby eliminating the problem of inaccurate detection results due to axial or radial rotation caused by the product not being absolutely level, and achieving a significant improvement in detection accuracy; at the same time, after identifying the glue path based on height information, the glue path is divided into several sections to obtain contour lines of several cross sections, and data such as glue width and height are detected on each contour line, so as to accurately judge key parameters such as the height and width of the glue path; and the present invention is fully automatic, and compared with the prior art of manually realizing glue path detection, it can greatly reduce labor costs while effectively improving the glue path detection accuracy.

[0057] A glue path detection method provided by an embodiment of the present invention may further include, before selecting spatial point cloud data in the same plane as data to be corrected at a fixed position of the designated surface:

[0058] The spatial point cloud data is denoised using median filtering, Gaussian filtering or mean filtering.

[0059] The embodiment of the present invention can use median filtering, Gaussian filtering, mean filtering, etc. to denoise the collected spatial point cloud data according to the characteristics of glue imaging, thereby effectively reducing the impact of interference data and further improving the accuracy of glue path detection.

[0060] A glue path detection method provided by an embodiment of the present invention obtains the height of each of the contour lines respectively, which may include: determining the plane after the plane to be corrected is corrected to a horizontal posture as a reference plane, and obtaining the distance between the highest point in each of the contour lines and the reference plane as the height of the corresponding contour line.

[0061] Obtaining the width of each contour line respectively may include: determining a height reference line, determining the intersection points between each contour line and the height reference line respectively, and determining the distance between the two farthest intersection points corresponding to each contour line as the width of the corresponding contour line.

[0062] Obtaining the width of each of the contour lines separately may include: determining any contour line as the current contour line; determining the coordinate axis of the current contour line, with the horizontal axis being the width direction of the previous contour line and the vertical axis being the height direction of the current contour line; determining a height reference line, using the height reference line as the new horizontal axis, and deriving the vertical axis of the current contour line on the new horizontal axis, and the distance between the two points with the longest distance being greater than a preset value is the width of the current contour line.

[0063] The embodiment of the present invention can use the plane to be corrected after the plane is corrected to a horizontal posture as a reference plane, so that the distance between the highest point in any contour line and the reference plane is used as the height of the arbitrary contour line, thereby acquiring the corresponding height data in a simple and effective manner.

[0064] There are two ways to get the width of the contour line. The common point of the two methods is to identify the left and right endpoints of the glue in the two-dimensional contour line data, and measure the width between the two endpoints as the contour line width. The difference lies in the way of determining the left and right endpoints. Specifically, for any contour line, the contour line can be mapped into a two-dimensional coordinate graph, with the x-axis being the width direction of the contour line and the z-axis being the height direction of the contour line, such as Figure 2 As shown; the height reference line is pre-set based on actual needs. For example, if the width of glue that is 0.02 mm higher than the reference plane needs to be calculated, the height reference line is the line with a z-axis of 0.02; based on this, one way is to determine the intersection point between the contour line and the height reference line that is the farthest apart, which is the left and right end points of the glue corresponding to the contour line. Another way is to derive the z data so that the derivative result is greater than the corresponding threshold set according to actual needs, and the intersection point that is the farthest apart is the left and right end points of the glue corresponding to the contour line.

[0065] A glue path detection method provided by an embodiment of the present invention, after respectively obtaining the height and width of each of the contour lines, may also include: if among any multiple adjacent contour lines, a specified proportion of the contour lines have a height and / or width lower than the corresponding threshold, then it is determined that the glue path portion corresponding to the any multiple adjacent contour lines is broken.

[0066] After determining the glue path on the specified surface based on the height information contained in the spatial point cloud data, it can also include: if the distance between any point in the glue path and the specified mark position is lower than the corresponding threshold, it is determined that there is a wall climbing on the glue path at the arbitrary point.

[0067] The embodiments of the present invention can also automatically identify defects such as wall creeping (the glue line is too close to the marking line such as the border) and glue breaking (insufficient glue or no glue at all) according to the preset defect judgment criteria, thereby ensuring product quality and production efficiency, and playing a vital role in the manufacturing process control of the manufacturing industry. Specifically, if the height and / or width of the contour lines of a specified proportion in a certain section of glue road are lower than the corresponding threshold, it can be determined that the glue road has broken; if the distance between any point and the specified marking position is lower than the corresponding threshold, it can be determined that the glue road at the arbitrary point has wall creeping; wherein, the specified proportion (such as four-fifths, etc.), the specified marking position (a certain border, etc.) and the various thresholds can be pre-set according to actual needs, and are not specifically limited here.

[0068] The embodiment of the present invention also provides a glue path detection device, such as Figure 3 As shown, this may include:

[0069] The acquisition module 11 is used to: acquire spatial point cloud data of a specified surface on a target product;

[0070] A selection module 12 is used to: select spatial point cloud data in the same plane at a fixed position of the designated surface as data to be corrected;

[0071] A fitting module 13 is used to: obtain a corresponding plane to be corrected based on the data to be corrected by fitting, and calculate rotation data for correcting the plane to be corrected to a horizontal posture;

[0072] A correction module 14 is used to: perform correction processing on the spatial point cloud data based on the rotation data;

[0073] A determination module 15 is used to: determine the glue path on the specified surface based on the height information included in the spatial point cloud data;

[0074] A division module 16 is used to divide the glue road into several sections to obtain the contour line of the cross section of each glue road obtained by division;

[0075] The acquisition module 17 is used to respectively acquire the height and width of each of the contour lines to detect the glue path.

[0076] An embodiment of the present invention further provides a glue path detection device, which includes a memory and a processor. When a program stored in the memory is executed by the processor, the steps of the glue path detection method described in any one of the above items can be implemented.

[0077] An embodiment of the present invention further provides a computer-readable storage medium, and when a program stored on the computer-readable storage medium is executed by a processor, the steps of the glue path detection method as described in any one of the above items are implemented.

[0078] For detailed descriptions of the glue path detection device, equipment and storage medium provided in the embodiments of the present invention, please refer to the corresponding contents in the above glue path detection method embodiment. Although the embodiments of the present invention are described in conjunction with the drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the attached claims.

Claims

1. A glue path detection method, characterized in that: include: Collect spatial point cloud data of the specified surface on the target product; At a fixed position of the designated surface, selecting spatial point cloud data in the same plane as data to be corrected; A corresponding plane to be corrected is obtained by fitting the data to be corrected, and rotation data for correcting the plane to be corrected to a horizontal posture is calculated; Performing correction processing on the spatial point cloud data based on the rotation data; Determining the glue path on the designated surface based on the height information included in the spatial point cloud data; Dividing the glue road into a plurality of sections to obtain a contour line of a cross section of each glue road section obtained by dividing; The height and width of each contour line are obtained respectively to detect the glue path.

2. The method according to claim 1, characterized in that Before selecting the spatial point cloud data in the same plane as the data to be corrected at the fixed position of the designated surface, the method further includes: The spatial point cloud data is denoised using median filtering, Gaussian filtering or mean filtering.

3. The method according to claim 2, characterized in that The height of each contour line is obtained respectively, including: The plane obtained by correcting the plane to be corrected to a horizontal posture is determined as a reference plane, and the distance between the highest point in each of the contour lines and the reference plane is respectively obtained as the height of the corresponding contour line.

4. The method according to claim 3, characterized in that The width of each of the contour lines is obtained respectively, including: Determine a height reference line, determine the intersection points between each of the contour lines and the height reference line, and determine the distance between the two farthest intersection points corresponding to each of the contour lines as the width of the corresponding contour line.

5. The method according to claim 3, characterized in that: The width of each of the contour lines is obtained respectively, including: Determine any contour line as the current contour line; Determine the coordinate axis of the current contour line, the horizontal axis is the width direction of the previous contour line, and the vertical axis is the height direction of the current contour line; Determine the height reference line, take the height reference line as the new horizontal axis, and derive the vertical axis of the current contour line on the new horizontal axis. The distance between the two points with the longest distance greater than the preset value is the width of the current contour line.

6. The method according to claim 4 or 5, characterized in that: After respectively obtaining the height and width of each of the contour lines, the method further includes: If, among any plurality of adjacent contour lines, there are contour lines of a specified proportion whose heights and / or widths are lower than corresponding thresholds, it is determined that glue breaking occurs in the glue path portion corresponding to the any plurality of adjacent contour lines.

7. The method according to claim 6, characterized in that After determining the glue path on the specified surface based on the height information included in the spatial point cloud data, the method further includes: If the distance between any point in the glue path and the designated mark position is lower than a corresponding threshold value, it is determined that there is a wall climbing on the glue path at the arbitrary point.

8. A glue path detection device, characterized in that: include: The acquisition module is used to: acquire spatial point cloud data of a specified surface on a target product; A selection module is used to: select spatial point cloud data in the same plane at a fixed position of the designated surface as data to be corrected; A fitting module, used to: obtain a corresponding plane to be corrected based on the data to be corrected by fitting, and calculate rotation data for correcting the plane to be corrected to a horizontal posture; A correction module, used to: perform correction processing on the spatial point cloud data based on the rotation data; A determination module, used to: determine the glue path on the specified surface based on the height information included in the spatial point cloud data; A division module is used to: divide the glue road into a plurality of sections, and obtain the contour line of the cross section of each glue road obtained by division; The acquisition module is used to respectively acquire the height and width of each of the contour lines to detect the glue path.

9. A glue road detection device, characterized in that: The device includes a memory and a processor, and the program stored in the memory can implement the steps of the glue path detection method as described in any one of claims 1 to 7 when executed by the processor.

10. A computer-readable storage medium, characterized in that: When the program stored on the computer-readable storage medium is executed by a processor, the steps of the glue path detection method as described in any one of claims 1 to 7 are implemented.

Citation Information

Cited By

  • Dam glue detection method

    CN120709176A