Machine vision-based material basket inspection method and system

Through machine vision technology, robots and image acquisition equipment are used to automatically detect material frames, solving the existing problems of low manual detection efficiency and safety hazards, and achieving more efficient and safe material frame detection.

WO2024230494A1PCT designated stage expired Publication Date: 2024-11-14JINAN DOUBLEWIN AUTOMOBILE EQUIP ENG +4

Patent Information

Application Number
PCT/CN2024/089700
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Priority Date
2023-05-08
Filing Date
2024-04-25
Publication Date
2024-11-14

AI Technical Summary

Technical Problem

Existing material frame inspection mainly relies on manual inspection, which has problems such as inadequate detection, low efficiency and personal safety hazards.

Method used

Using machine vision-based detection methods, the image data of the material frame is obtained through robots and image acquisition equipment, and detection indicators are constructed to realize automatic detection of material frame defects, avoiding manual judgment errors and safety accidents.

Benefits of technology

It improves the detection success rate, avoids possible scratched materials and personal injury accidents during manual testing, and improves detection efficiency and safety.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN2024089700_14112024_PF_FP_ABST
    Figure CN2024089700_14112024_PF_FP_ABST
Patent Text Reader

Abstract

A machine vision-based material basket inspection method and system. The method comprises: acquiring first contour image data and second contour image data of a material basket; on the basis of the acquired first contour image data, constructing a material basket inspection index; and, according to the second contour image data and the material basket inspection index, implementing inspection of the material basket.
Need to check novelty before this filing date? Find Prior Art

Description

A material frame detection method and system based on machine vision

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This invention claims priority to Chinese patent application No. 202310504441.4 filed with the State Intellectual Property Office of China on May 8, 2023, entitled “A Material Frame Detection Method and System Based on Machine Vision”, the entire contents of which are incorporated by reference into this invention and constitute a part of this invention for all purposes. Technical Field

[0003] The present application belongs to the field of visual inspection technology, and specifically relates to a material frame inspection method and system based on machine vision. Background Art

[0004] The statements in this section merely provide background technical information related to this application and do not necessarily constitute prior art.

[0005] The material frame is used at the end of the stamping production line to place and transport stamping parts. There are many stamping part bearing and limiting mechanisms in the material frame, such as racks, support plates, and insertion rods. Before placing the stamping parts into the material frame, it is necessary to inspect the status of the material frame's bearing and limiting mechanisms to confirm whether they can be used normally to avoid damage such as stacking, scratching, and collision during the loading process.

[0006] According to the inventors' understanding, existing material frame inspection is to regularly conduct manual inspections to determine whether there are missing teeth (such as broken teeth, missing teeth, scratches, etc.), foreign objects, misaligned insertion rods, etc.; manual inspection has the following problems:

[0007] (1) The detection is not in place, some material frame problems are missed or the problem judgment is inaccurate;

[0008] (2) The efficiency is low. The structural parts of the material frame can only provide a narrow operating space, which is difficult to stand and accommodate. When personnel enter the material frame to carry out inspections, they are inevitably restricted by space and cannot be in a good working state. They may even suffer personal injury accidents such as bumps and scratches, stepping on empty space and spraining the ankle.

[0009] Summary of the Invention

[0010] In order to solve the above problems, the present application proposes a material frame detection method and system based on machine vision, which uses a robot and image acquisition equipment to capture images of the material frame, and realizes the detection of the material frame through data processing and analysis, which can improve the detection success rate and avoid the situation where the human eye fails to see damage or misjudgment during manual inspection, resulting in scratches on the material during framing, thereby avoiding personal injury accidents during the inspection process.

[0011] According to some embodiments, a first solution of the present application provides a material frame detection method based on machine vision, which adopts the following technical solutions:

[0012] A material frame detection method based on machine vision, comprising:

[0013] Acquire first contour image data and second contour image data of the material frame;

[0014] Constructing a material frame defect detection index based on the acquired first contour data;

[0015] The material frame is detected according to the second contour image data and the material frame defect detection index.

[0016] As a further technical limitation, the first contour image data is initial contour image data of an unused material frame, and the second contour image data is real-time contour image data of a material frame in use.

[0017] As a further technical limitation, in the process of obtaining the first contour image data of the material frame, an unused material frame is fixed on a material frame positioning table, and then the fixed material frame is placed on one side of the robot, and the first contour image data of the material frame is collected by an image acquisition device arranged on the robot's robotic arm.

[0018] As a further technical limitation, in the process of obtaining the second contour image data of the material frame, the material frame in use is fixed on the material frame positioning table, and then the fixed material frame is placed on one side of the robot, and the real-time image data of the material frame is collected by the image acquisition device set on the robot's robotic arm, that is, the second contour image data is collected.

[0019] As a further technical limitation, based on the first contour data obtained, and with the principle of not delaying the production of the next process, the material frame that affects the loading of the workpiece is set as an unqualified material frame, and combined with actual production experience, the material frame defect detection index is obtained.

[0020] As a further technical limitation, the material frame defects include rod insertion material frame defects and slot material frame defects; the rod insertion material frame defects include rod insertion into the wrong hole defect and rod deformation defect; the slot material frame defects include slot tooth missing, slot rack deformation, foreign matter in the slot or slot wear.

[0021] As a further technical limitation, during the material frame inspection process, the origin of the coordinate system is established through three-point calibration, and defect detection is achieved through coordinate calculation combined with the coordinate information of the acquired second contour image data.

[0022] According to some embodiments, a second solution of the present application provides a material frame detection system based on machine vision, which adopts the following technical solutions:

[0023] A material frame detection system based on machine vision, comprising:

[0024] An acquisition module configured to acquire first contour image data and second contour image data of a material frame;

[0025] A construction module configured to construct a material frame detection index based on the acquired first contour data;

[0026] The detection module is configured to detect the material frame according to the second contour image data and the material frame detection index.

[0027] Compared with the prior art, the present invention has the following advantages:

[0028] The present application uses a robot and an image acquisition device to capture images of the material frame, and realizes the detection of the material frame through data processing and analysis, which can improve the detection success rate, avoid the situation in which the human eye fails to see damage or misjudgment during manual inspection, and cause scratches on the material during framing, thereby avoiding personal injury accidents during the inspection process. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] The drawings in the specification, which constitute a part of this application, are used to provide further understanding of this application. The illustrative embodiments of this application and their descriptions are used to explain this application and do not constitute improper limitations on this application.

[0030] FIG1 is a flow chart of a material frame detection method based on machine vision in Example 1 of the present application;

[0031] FIG2 is a schematic diagram of the structure of the insert rod material frame in the first embodiment of the present application; wherein (a) is a schematic diagram of the structure of the material frame with a normal insert rod, and (b) is a schematic diagram of the structure of the material frame with a defective insert rod;

[0032] FIG3 is a structural diagram of a material frame detection robot based on machine vision in Example 1 of the present application;

[0033] FIG4 is another structural diagram of the material frame detection robot based on machine vision in Example 1 of the present application;

[0034] FIG5 is a schematic diagram of the structure of the positioning platform in Example 1 of the present application;

[0035] FIG6 is a schematic diagram of a calibration action in Example 1 of the present application;

[0036] FIG7 is a structural block diagram of a material frame detection system based on machine vision in Example 2 of the present application;

[0037] Among them, 1. Robot, 2. Robot axis, 3. Image acquisition device, 4. Material frame slot, 5. No. 1 needle alignment, 6. No. 2 needle alignment, 7. No. 3 needle alignment, 8. Robot needle alignment. DETAILED DESCRIPTION

[0038] The present application will be further described below with reference to the accompanying drawings and embodiments.

[0039] It should be noted that the following detailed descriptions are illustrative and intended to provide further explanation of the present application. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which the present application belongs.

[0040] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present application. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprise" and / or "include" are used in this specification, they indicate the presence of features, steps, operations, devices, components and / or combinations thereof.

[0041] In the present application, terms such as "upper", "lower", "left", "right", "front", "back", "vertical", "horizontal", "side", "bottom", etc. indicating directions or positional relationships are based on the directions or positional relationships shown in the accompanying drawings. They are merely relational words determined for the convenience of describing the structural relationships of the various parts or elements of the present application, and do not specifically refer to any part or element in the present application, and should not be understood as limitations on the present application.

[0042] In this application, terms such as "fixed connection," "connected," and "connection" should be interpreted broadly to mean a fixed connection, an integral connection, or a detachable connection; a direct connection or an indirect connection through an intermediary. Relevant researchers or technicians in this field may determine the specific meaning of these terms in this application based on specific circumstances, and they should not be construed as limitations on this application.

[0043] In the absence of conflict, the embodiments and features in the embodiments of this application can be combined with each other.

[0044] Example 1

[0045] Embodiment 1 of the present application introduces a material frame detection method based on machine vision.

[0046] As shown in FIG1 , a material frame detection method based on machine vision includes:

[0047] Acquire first contour image data and second contour image data of the material frame;

[0048] Constructing a material frame defect detection index based on the acquired first contour data;

[0049] The material frame is detected according to the second contour image data and the material frame defect detection index.

[0050] As one or more implementation manners, the first contour image data is initial contour image data of an unused material frame, and the second contour image data is real-time contour image data of a material frame in use.

[0051] As one or more implementation methods, in the process of obtaining the first contour image data of the material frame, an unused material frame is fixed on a material frame positioning table, and then the fixed material frame is placed on one side of the robot, and the first contour image data of the material frame is collected by an image acquisition device set on the robot's robotic arm.

[0052] As one or more implementation methods, in the process of obtaining the second contour image data of the material frame, the material frame in use is fixed on the material frame positioning table, and then the fixed material frame is placed on one side of the robot, and the real-time image data of the material frame is collected by the image acquisition device set on the robot's robotic arm, that is, the second contour image data is collected.

[0053] As one or more implementation methods, based on the acquired first contour data, and with the principle of not delaying the production of the subsequent process, the material frame that affects the loading of the workpiece is set as an unqualified material frame, and combined with actual production experience, a material frame defect detection index is obtained.

[0054] As one or more implementation methods, the material frame defects include rod insertion material frame defects and slot material frame defects; the rod insertion material frame defects include rod insertion into the wrong hole defect and rod deformation defect; the slot material frame defects include slot tooth missing, slot rack deformation, foreign matter in the slot, or slot wear;

[0055] There is a clear difference between inserting the wrong hole and deforming the rod. When the rod is inserted into the wrong hole, no image will be generated during scanning. However, when the rod is deformed, the scanned image is inconsistent with the first contour image and is deformed. After obtaining the second contour image data, an initial judgment on the defect type is first made, and then a specific material frame detection judgment is performed based on the specific second contour image data.

[0056] Specifically, a schematic diagram of the material frame structure of a normal insertion rod is shown in (a) of Figure 2, and a schematic diagram of the material frame structure of a defective insertion rod is shown in (b) of Figure 2. According to (a) and (b) of Figure 2, it can be concluded that the defect of the insertion rod material frame is that there is a foreign object on the left side of the insertion rod and it is slightly tilted to the left. By measuring the first contour image data and the second contour image data of the insertion rod material frame, it is further determined whether the insertion rod defect is within the allowable range.

[0057] As one or more implementation methods, during the material frame inspection process, the origin of the coordinate system is established through three-point calibration, and defect detection is achieved through coordinate calculation in combination with the coordinate information of the acquired second contour image data.

[0058] In this embodiment, as shown in Figures 3, 4, 5 and 6, during the material frame detection process, the material frame to be detected must be set within the field of view of the image acquisition device 3, and an appropriate height must be maintained between the plane where the material frame to be detected is located and the image acquisition device 3. Under the action of the robot 1, the image acquisition device 3 is driven to operate horizontally on the plane where the material frame to be detected is located.

[0059] Under the action of the image acquisition device 3, the initial contour image data of the unused material frame (i.e., the first contour image data) and the real-time contour image data of the used material frame (i.e., the second contour image data) are obtained respectively; after obtaining the image data, the image is calibrated and a certain image allowable error range is set, that is, the material frame defect detection index is constructed.

[0060] During the inspection process, robot 1 drives image acquisition device 3 to the inspection positioning coordinate point, sends a signal to the programmable logic controller (PLC), and the PLC sends a signal to the camera, which activates image acquisition device 3 to scan. Robot 1 begins moving along the inspection surface, maintaining its height and parallelism. When robot 1 reaches the end of the inspection point, it sends a signal to the PLC, which in turn sends a signal to image acquisition device 3, which ends the scan. After the scan is complete, the robot returns to the origin or inspects the work surface.

[0061] When the image acquisition device 3 scans along the material frame slot 4, a corresponding contour image is formed in the host computer after the scanning is completed. The software processes the image, calculates the groove depth, tooth length, and slot length, and compares it with the original standard image to see if it exceeds the allowable error. If it exceeds the allowable error, a No Good (NG) signal is sent to the PLC, and the PLC sends an alarm signal. In combination with the constructed material frame defect detection index, a signal is sent.

[0062] Combined with the reference coordinates, the movement path, and the image captured by the image acquisition device 3, the deformation of the detected rack or plunger relative to the set trajectory is calculated, such as the relative position of certain characteristic points such as parallelism and perpendicularity. At the same time, the actual size data of the material frame is measured and saved for subsequent inspection.

[0063] The entire communication is Ethernet. The image processing software and the detection software are software installed on the computer. The detection software is embedded in the image processing software, and the two software have interfaces for data exchange. The images collected by the front end are transmitted to the image processing software on the computer via Ethernet. The image processing software transmits the data obtained from the image processing to the detection software. The detection software compares the standard image data to determine whether it is qualified (OK for short) or NG, and outputs the detection data to an Excel spreadsheet and saves it in the computer folder. Data analysis and defect detection are performed in the detection software.

[0064] The above scans only the vertical direction of the frame. To scan in the other direction, the robot needs to change its angle. For example, a vertically mounted slot can be scanned in one motion, while a horizontally mounted slot requires the robot to change its angle by 90 degrees.

[0065] Identification method for incorrectly inserted rods: The camera scans at the correct position. If no rod is inserted, no rod feature points are displayed in the image scanned without the rod inserted, and it is judged as NG (if there are upper and lower holes in parallel, to prevent accidental collision, the upper hole should be scanned first to pre-judge whether there is a rod inserted in the upper hole. If there is a rod inserted, it can be judged as NG. If there is no rod inserted, scan again at the correct position).

[0066] Rod deformation: After the camera scans the image, it is compared with the standard image in the visual inspection software sherlock8 to obtain the difference between the two (x a ,y a ,z a ), indicating that when the difference is greater than the set range, it is judged as NG and no subsequent processing is performed. The coordinates of the standard image (x0, y0, z0) plus (x a ,y a ,z a ) calculate the coordinates of the current rod (x0+x a ,y0+y a ,z0+z a ); where x0, y0, and z0 are the coordinates of the standard image on the x-axis, y-axis, and z-axis, respectively. a 、y a 、z a are the coordinate differences between the sherlock8 software and the standard image in the x-axis, y-axis and z-axis respectively; the coordinates of all the rods can be calculated by analogy.

[0067] Explanation of the coordinates (x0, y0, z0) of the standard image: There are three alignment pins installed on the positioning table where the material frame is placed, namely, No. 1 alignment pin 5, No. 2 alignment pin 6 and No. 3 alignment pin 7. The robot calibrates No. 1 alignment pin 5, No. 2 alignment pin 6 and No. 3 alignment pin 7 through the three-point method, establishes the origin of the user coordinate system, and then obtains the coordinates of the standard insertion rod through trial teaching and transmits them to sherlock8 as the coordinates (x0, y0, z0) of the standard image.

[0068] In the process of calibrating the No. 1 alignment needle 5, No. 2 alignment needle 6 and No. 3 alignment needle 7 by the three-point method, the user coordinate system of the robot is established before detection. The alignment needle on the robot is calibrated with the alignment needle on the positioning platform using the teach pendant to establish the origin and X and Y directions of the user coordinate system, and the position of the robot and the positioning platform is associated; the No. 1 alignment needle 5, No. 2 alignment needle 6 and No. 3 alignment needle 7 correspond to the origin, X positive direction and Y positive direction of the coordinate system respectively; the specific process of calibrating the No. 1 alignment needle 5, No. 2 alignment needle 6 and No. 3 alignment needle 7 by the three-point method is as follows:

[0069] (1) Press the following buttons in sequence: [MENU] (i.e. menu) [SETUP] (i.e. settings) -- F1 [Type] (i.e. type) -- [Frames] (i.e. coordinate system) to enter the coordinate system setting interface;

[0070] (2) Move the light to set the specific user coordinate system. Here, the user coordinate system is set to No. 1.

[0071] (3) Switch the robot's teaching coordinates to the world coordinate system;

[0072] (4) Align the robot's needle 8 with the second needle 6 on the positioning table and record the X direction point. After the recording is completed, the X direction becomes recorded;

[0073] (5) Align the robot's needle 8 with the third needle 7 on the positioning platform and record the coordinate origin. After recording is completed, the origin becomes recorded;

[0074] (6) Align the robot needle 8 with the No. 1 needle 5 on the positioning table and record the Y direction point. After the recording is completed, the Y direction becomes recorded.

[0075] This embodiment uses a robot and an image acquisition device to capture images of the material frame, and realizes the detection of the material frame through data processing and analysis, which can improve the detection success rate, avoid the situation where the human eye fails to see damage or misjudgment during manual inspection, and thus avoid personal injury accidents during the inspection process.

[0076] Example 2

[0077] The second embodiment of the present application introduces a material frame detection system based on machine vision.

[0078] As shown in FIG7 , a material frame detection system based on machine vision includes:

[0079] An acquisition module configured to acquire first contour image data and second contour image data of a material frame;

[0080] A construction module configured to construct a material frame detection index based on the acquired first contour data;

[0081] The detection module is configured to detect the material frame according to the second contour image data and the material frame detection index.

[0082] The detailed steps are the same as those of the material frame detection method based on machine vision provided in Example 1, and will not be repeated here.

[0083] The detailed steps are the same as those of the material frame detection method based on machine vision provided in Example 1, and will not be repeated here.

[0084] The above description is merely a preferred embodiment of the present application and is not intended to limit the present application. Various modifications and variations are possible for those skilled in the art. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present application shall be included within the scope of protection of the present application.

Claims

1. A material frame detection method based on machine vision, It is characterized in that include: Acquire first contour image data and second contour image data of a material frame; the first contour image data is initial contour image data of an unused material frame, and the second contour image data is real-time contour image data of a used material frame; Constructing a material frame defect detection index based on the acquired first contour data; Implementing material frame detection according to the second contour image data and the material frame defect detection index; The material frame defects include rod insertion material frame defects and slot material frame defects; the rod insertion material frame defects include rod insertion error hole defects and rod deformation defects; the slot material frame defects include slot tooth missing, slot rack deformation, foreign matter in the slot or slot wear; The specific identification of the rod insert frame defect is as follows: There is a clear difference between the insertion of the wrong hole and the deformation of the rod. There is no image when the insertion of the wrong hole is scanned, and the deformation of the rod is that the scanned image is inconsistent with the first contour image and has deformation. After obtaining the second contour image data, the initial judgment on the defect type is first performed, and then the specific material frame detection judgment is performed based on the specific second contour image data; The identification method of wrong insertion of the rod includes: the camera scans at the correct position, and no rod feature points are displayed in the image of the scanned image without the rod, which is judged as unqualified; if there are upper and lower parallel holes, in order to prevent accidental contact, the upper hole should be scanned first to pre-judge whether there is a rod in the upper hole, and if there is a rod, it can be judged as unqualified, and if there is no rod, scan again at the correct position to start scanning; The method for identifying the deformation of the plug-in rod includes: after the camera scans the image, the difference between the image and the standard image is compared in the visual inspection software. When the difference is greater than the set range, it is judged as unqualified, and the coordinates of the current plug-in rod are calculated by the coordinates of the standard image; and the coordinates of all the plug-in rods are calculated in this way; The card slot material frame defect identification is: When the image acquisition device scans along the slot of the material frame, a corresponding contour image is formed in the host computer after the scanning is completed. The software processes the image, calculates the slot depth, tooth length, and slot length, and compares it with the original standard image to see if it exceeds the allowable error. If it exceeds the allowable error, it is judged as unqualified; In the process of material frame detection, the origin of the coordinate system is established through three-point calibration, and the coordinate information of the acquired second contour image data is combined to realize defect detection through coordinate calculation; The coordinate system origin is established by three-point calibration, specifically: Use the teach pendant to operate the alignment needle on the robot and calibrate it with the three alignment needles on the positioning table where the material frame is placed to establish the origin of the coordinate system and the X and Y directions, and associate the position of the robot with the positioning table; the robot The three-point method is used to calibrate the three needles and establish the origin of the user coordinate system.

2. A material frame detection method based on machine vision as claimed in claim 1, It is characterized in that The first contour image data is initial contour image data of an unused material frame, and the second contour image data is real-time contour image data of a used material frame.

3. A material frame detection method based on machine vision as claimed in claim 1, It is characterized in that In the process of obtaining the first contour image data of the material frame, an unused material frame is fixed on a material frame positioning table, and then the fixed material frame is placed on one side of the robot, and the first contour image data of the material frame is collected by an image acquisition device arranged on the robot's mechanical arm.

4. A material frame detection method based on machine vision as described in claim 1, It is characterized in that In the process of obtaining the second contour image data of the material frame, the material frame in use is fixed on the material frame positioning table, and then the fixed material frame is placed on one side of the robot. The real-time image data of the material frame is collected by the image acquisition device arranged on the robot's mechanical arm, that is, the second contour image data is collected.

5. A material frame detection method based on machine vision as claimed in claim 1, It is characterized in that Based on the first contour data obtained, the material frame that affects the loading of workpieces is set as an unqualified material frame in order not to delay the production of the next sequence process. Combined with actual production experience, the material frame defect detection index is obtained.

6. A material frame detection system based on machine vision, It is characterized in that include: An acquisition module is configured to acquire first contour image data and second contour image data of a material frame; the first contour image data is initial contour image data of an unused material frame, and the second contour image data is real-time contour image data of a used material frame; A construction module configured to construct a material frame defect detection index based on the acquired first contour data; A detection module, configured to detect the material frame according to the second contour image data and the material frame defect detection index; The material frame defects include rod insertion material frame defects and slot material frame defects; the rod insertion material frame defects include rod insertion error hole defects and rod deformation defects; the slot material frame defects include slot tooth missing, slot rack deformation, foreign matter in the slot or slot wear; The specific identification of the rod insert frame defect is as follows: There is a clear difference between the insertion of the wrong hole and the deformation of the rod. There is no image when the insertion of the wrong hole is scanned, and the deformation of the rod is that the scanned image is inconsistent with the first contour image and has deformation. After obtaining the second contour image data, the initial judgment on the defect type is first performed, and then the specific material frame detection judgment is performed based on the specific second contour image data; The identification method of wrong insertion of the rod includes: the camera scans at the correct position, and no rod feature points are displayed in the image of the scanned image without the rod, which is judged as unqualified; if there are upper and lower parallel holes, in order to prevent accidental contact, the upper hole should be scanned first to pre-judge whether there is a rod in the upper hole, and if there is a rod, it can be judged as unqualified, and if there is no rod, scan again at the correct position to start scanning; The method for identifying the deformation of the plug-in rod includes: after the camera scans the image, the difference between the image and the standard image is compared in the visual inspection software. When the difference is greater than the set range, it is judged as unqualified, and the coordinates of the current plug-in rod are calculated by the coordinates of the standard image; and the coordinates of all the plug-in rods are calculated in this way; The card slot material frame defect identification is: When the image acquisition device scans along the slot of the material frame, a corresponding contour image is formed in the host computer after the scanning is completed. The software processes the image, calculates the slot depth, tooth length, and slot length, and compares it with the original standard image to see if it exceeds the allowable error. If it exceeds the allowable error, it is judged as unqualified; In the process of material frame detection, the origin of the coordinate system is established through three-point calibration, and the coordinate information of the acquired second contour image data is combined to realize defect detection through coordinate calculation; The coordinate system origin is established by three-point calibration, specifically: Use the teach pendant to operate the alignment needle on the robot and calibrate it with the three alignment needles on the positioning table where the material frame is placed to establish the origin of the coordinate system and the X and Y directions, and associate the position of the robot with that of the positioning table; the robot calibrates the three alignment needles using the three-point method to establish the origin of the user coordinate system.

Citation Information

Patent Citations

  • Multi-robot cooperative workpiece flaw detection method

    CN112394065A

  • Robot vision detection method for multi-category mixed line production control cabinet

    CN112666164A

  • Defect detection method, device and system based on machine vision

    CN115753791A

  • Visual detection method and device based on template matching, equipment and medium

    CN115937203A

  • Material frame detection method and system based on machine vision

    CN116245877A

Cited By

  • Square shell material frame detection method based on machine vision

    CN119417820A

  • Batch detection device and method for quality inspection in falling process of optical fiber assembly

    CN119846370A

  • Material box truck hopper motor and camera calibration method and system and storage medium

    CN122435053A