Fixed viewpoint hand-eye calibration method and system based on two-dimensional code

Abstract

The application provides a fixed viewpoint hand-eye calibration method and system based on a two-dimensional code, according to obtained two-dimensional code image data of a mechanical arm end, an edge line of a two-dimensional code positioning area is obtained by using a Canny edge detection operator, and a corner point position of the two-dimensional code is obtained through coordinate transformation; according to obtained two-dimensional code image data of the mechanical arm end, a corner point position of the two-dimensional code is obtained by solving through EPnP; whether errors of four corner points of the two-dimensional code are all less than a first set threshold value is judged, if yes, calibration of positive and inverse matrix parameters of the mechanical arm is carried out according to the corner point position of the two-dimensional code obtained through coordinate transformation; the application combines the recognition result of the two-dimensional code at the mechanical arm end, ensures positioning accuracy of the mechanical arm, is simple to operate and has good timeliness.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of mechanical arm parameter calibration, and in particular relates to a fixed-viewpoint hand-eye calibration method and system based on a two-dimensional code. BACKGROUND

[0002] The statements in this section merely provide background technology related to the present application and do not necessarily constitute prior art.

[0003] With the development of industrial automation and intelligentization, industrial robots are widely used in various fields of production and manufacturing. As the "eyes" of industrial robots, the vision system effectively improves the flexibility and intelligentization of industrial robots in production applications, greatly improving production efficiency and automation level.

[0004] There are mainly two ways of associating vision systems with robots: non-fixed viewpoint vision and fixed viewpoint vision. Non-fixed viewpoint robot vision usually installs a camera at the end of a manipulator and moves with the end of the manipulator, which is the main way for robots to realize active vision; fixed viewpoint robot vision separates the camera from the manipulator, and the camera is installed in a fixed position and is stationary, so the system structure is easy to install, the vision system will not change the structure due to the movement of the robot, and the precision is relatively high, so it is widely used in industrial robots.

[0005] However, the inventors have found that the fixed viewpoint is usually installed above the fixed manipulator, and can see the entire movement range of the manipulator globally; when the fixed viewpoint and the moving manipulator are on the same side, there are several problems in the joint calibration of the camera and the manipulator, first of all, due to the movement range and the number of joints of the manipulator, it is not possible to fix the calibration board at the end of the manipulator for joint calibration; secondly, the field of view angle of the camera is small and cannot contain the entire calibration board. SUMMARY

[0006] In order to solve the problems of the prior art, the present application provides a fixed viewpoint hand-eye calibration method and system based on a two-dimensional code, which combines the recognition result of the two-dimensional code at the end of the manipulator, ensures the positioning accuracy of the manipulator, is simple to operate and has good timeliness.

[0007] In order to achieve the above purpose, the present application adopts the following technical solutions:

[0008] The present application provides a fixed viewpoint hand-eye calibration method based on a two-dimensional code.

[0009] A fixed viewpoint hand-eye calibration method based on a two-dimensional code, comprising the following processes:

[0010] Obtaining two-dimensional code image data at the end of the manipulator;

[0011] According to the obtained mechanical arm end two-dimensional code image data, the edge line of the two-dimensional code positioning area is obtained by using a Canny edge detection operator, and the corner point position of the two-dimensional code is obtained through coordinate transformation;

[0012] According to the obtained mechanical arm end two-dimensional code image data, the corner point position of the two-dimensional code is obtained by solving EPnP;

[0013] According to the corner point position of the two-dimensional code obtained through coordinate transformation and the corner point position of the two-dimensional code obtained by solving EPnP, the error corresponding to each corner point is obtained, and it is judged whether the errors of the four corner points of the two-dimensional code are all less than a first set threshold value, if yes, the forward and inverse matrix parameters of the mechanical arm are calculated according to the corner point position of the two-dimensional code obtained through coordinate transformation, and the next step is executed, otherwise, the standard deviation of the Canny edge detection operator is adjusted until the errors of the four corner points of the two-dimensional code are all less than the first set threshold value;

[0014] It is judged whether the difference between the calculated forward and inverse matrix parameters of the mechanical arm and the forward and inverse matrix parameters of the starting mechanical arm is less than a second set threshold value, if yes, the forward and inverse matrix parameters of the starting mechanical arm are taken as the calibrated parameters, otherwise, the calculated forward and inverse matrix parameters of the mechanical arm are taken as the calibrated parameters.

[0015] The second aspect of the application provides a fixed-viewpoint hand-eye calibration system based on a two-dimensional code.

[0016] A fixed-viewpoint hand-eye calibration system based on a two-dimensional code comprises:

[0017] A data acquisition module is configured to acquire two-dimensional code image data at the end of a mechanical arm;

[0018] A first two-dimensional code corner point position generation module is configured to obtain the edge line of the two-dimensional code positioning area by using a Canny edge detection operator according to the acquired two-dimensional code image data at the end of the mechanical arm, and obtain the corner point position of the two-dimensional code through coordinate transformation;

[0019] A second two-dimensional code corner point position generation module is configured to obtain the corner point position of the two-dimensional code by solving EPnP according to the acquired two-dimensional code image data at the end of the mechanical arm;

[0020] A mechanical arm forward and inverse matrix parameter calculation module is configured to obtain the error corresponding to each corner point according to the corner point position of the two-dimensional code obtained through coordinate transformation and the corner point position of the two-dimensional code obtained by solving EPnP, judge whether the errors of the four corner points of the two-dimensional code are all less than a first set threshold value, if yes, calculate the forward and inverse matrix parameters of the mechanical arm according to the corner point position of the two-dimensional code obtained through coordinate transformation, and execute the next step, otherwise, adjust the standard deviation of the Canny edge detection operator until the errors of the four corner points of the two-dimensional code are all less than the first set threshold value.

[0021] The forward and inverse matrix parameters of the mechanical arm are configured as a calibration module, configured to judge whether the difference between the calculated forward and inverse matrix parameters of the mechanical arm and the forward and inverse matrix parameters of the starting mechanical arm is less than a second set threshold, if yes, the forward and inverse matrix parameters of the starting mechanical arm are taken as the calibrated parameters, otherwise, the calculated forward and inverse matrix parameters of the mechanical arm are taken as the calibrated parameters.

[0022] The third aspect of the present application provides a computer readable storage medium, which stores a program, and the program is executed by a processor to realize the steps in the fixed viewpoint hand-eye calibration method based on a two-dimensional code according to the first aspect of the present application.

[0023] The fourth aspect of the present application provides an electronic device, which includes a memory, a processor, and a program stored in the memory and executable on the processor, and the processor executes the program to realize the steps in the fixed viewpoint hand-eye calibration method based on a two-dimensional code according to the first aspect of the present application.

[0024] Compared with the prior art, the present application has the following beneficial effects:

[0025] The fixed viewpoint hand-eye calibration method and system based on a two-dimensional code can correct the accuracy of the camera coordinate conversion value, ensure the positioning accuracy of the mechanical arm, and are simple to operate and have good timeliness.

[0026] The advantages of the additional aspects of the present application will be partially given in the following description, partially become obvious from the following description, or be understood through the practice of the present application. BRIEF DESCRIPTION OF DRAWINGS

[0027] The drawings accompanying the specification of the present application serve to provide a further understanding of the present application, and the illustrative embodiments of the present application and their descriptions serve to explain the present application, and do not constitute an improper limitation on the present application.

[0028] Figure 1 A flowchart of the fixed viewpoint hand-eye calibration method based on a two-dimensional code provided for the first embodiment of the present application is shown in the figure.

[0029] Figure 2 A principle diagram of the fixed viewpoint hand-eye calibration method based on a two-dimensional code provided for the first embodiment of the present application is shown in the figure.

[0030] Figure 3 A left transformation diagram provided for the first embodiment of the present application is shown in the figure. DETAILED DESCRIPTION

[0031] The present application will be further described below in combination with the drawings and embodiments.

[0032] It should be noted that the following detailed description is exemplary in nature and is intended to provide further description of the application. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.

[0033] It is to be understood that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments in accordance with the present application. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and / or "comprising," when used in this specification, specify the presence of stated features, steps, operations, elements, components, and / or groups thereof, but do not preclude the presence or addition of one or more other features, steps, operations, elements, components, and / or groups thereof.

[0034] The embodiments in the present application and the features in the embodiments can be combined with each other without conflict.

[0035] Embodiment 1

[0036] The embodiment 1 of the present application provides a fixed viewpoint hand-eye calibration method based on a two-dimensional code, a camera and a mechanical arm are installed, and a two-dimensional code is fixed at the end of the mechanical arm at the same horizontal position;

[0037] A mechanical arm end coordinate system, a two-dimensional code coordinate system, a camera coordinate system and a mechanical arm base coordinate system are established;

[0038] A rotation matrix and a translation vector of the two-dimensional code coordinate system and the mechanical arm end coordinate system, a rotation matrix and a translation vector of the mechanical arm end coordinate system and the mechanical arm base coordinate system, a rotation matrix and a translation vector of the mechanical arm base coordinate system and the camera coordinate system, and a rotation matrix and a translation vector of the camera coordinate system and the two-dimensional code coordinate system are obtained;

[0039] By moving the mechanical arm to a specified position, the pose of the mechanical arm at each position is recorded, the mechanical arm end coordinates (X, Y, Z) and the mechanical arm end pose (Rx, Ry, Rz) are obtained, the intrinsic calibration of the monocular camera is completed, the hand-eye extrinsic parameters R and T given by the mechanical drawing are obtained, the two-dimensional code under each position is shot, the coordinates of the two-dimensional code in the camera coordinates are obtained through image processing coordinate conversion and EPnP solving, respectively, the error of the two methods is obtained, and R and T are adjusted.

[0040] In the embodiment, the installation center of the camera and the base center position of the mechanical arm are determined when the mechanical design is performed, wherein the translation vector T is the coordinate value of the camera center with the mechanical arm base center as the origin, and the rotation matrix R is the transformation of the camera center to the mechanical arm center coordinates;

[0041] For example:

[0042]

[0043] In the formula, represents the rotation matrix of B in the A coordinate with A as the reference, represents the angle of rotation of z, y, x of B coordinate to A coordinate Each corresponding rotation matrix.

[0044] Specifically, as Figure 1 indicated, the following processes are included:

[0045] S1: Start, pre-construct the camera and the mechanical arm on the AGV trolley, as Figure 2 indicated, the mechanical arm and the camera are on the same side;

[0046] S2: Initialize the mechanical arm R and T, the R and T described in the embodiment are the inverse matrix parameters of the mechanical arm obtained;

[0047] Specifically, the R and T of the mechanical arm here are required to solve the forward and inverse solutions of the mechanical arm. First, a labeled D-H parameter table of the mechanical arm is established, and then the following formula is used:

[0048]

[0049] The conversion relationship of each axis of the mechanical arm relative to the previous axis can be obtained;

[0050] For example, a D-H parameter table is first given:

[0051]

[0052] Here, is the angle of rotation of each joint, is the rotation angle of the x-axis from to , is the distance along the x-axis from to , is the distance along the z-axis from to ;

[0053] Then, according to the above formula, the conversion relationship of each joint relative to the previous one can be obtained:

[0054]

[0055] Next, the solution is established:

[0056]

[0057] Here, Abbreviated as s1, It is abbreviated as c1, and the others are similar.

[0058] S3: Move the robotic arm to the marked point, and move the end effector of the robotic arm into the camera's field of view;

[0059] S4: Obtain the robot arm pose information for each marked point, specifically including the position and rotation angle information for each location;

[0060] S5: Pre-calibrate the camera's intrinsic parameters. Specifically, calibrate the camera's intrinsic parameter parameters using Zhang Dingyou's camera calibration method.

[0061] S6: Input the hand-eye external parameters R and T. The hand-eye external parameters R and T are the values ​​that need to be corrected in this invention. The offset parameters of the theoretically designed camera center and robotic arm center are input in advance, but they may not be accurate after processing. Therefore, it is necessary to calibrate and correct these two values.

[0062] S7: Obtain the ultrasonic ranging value. The conversion from pixel coordinates to camera coordinates requires the distance along the camera's Z-axis. Therefore, ultrasonic ranging is needed to obtain the distance to the target so that it can be used for subsequent conversion.

[0063] This is a transformation process from the camera coordinate system to the image coordinate system, in which... Let be the vertical distance from the camera center to the target. This distance is obtained through ultrasonic ranging. The ultimate goal is to calculate... and The known values ​​are x, y, and f, and then ultrasound provides... It can be obtained and ,refer to Figure 3 , where x and y are image coordinates, and f is the camera's focal length.

[0064] S8: Open the camera to recognize the QR code at the end of the robotic arm, and then proceed to step S9;

[0065] S9: Image processing and decoding. The image edge detection operator used here is the Canny edge detection operator. As an improvement, the Gaussian filtering in the first step of the Canny edge detection operator is replaced with bilateral filtering, which can preserve the edge, texture, and detail features in the image. The formula for the bilateral filtering operator is as follows:

[0066] Spatial domain core: This formula is based on the Gaussian kernel function, where Here, (k, l) represents the standard deviation, (i, j) represents the coordinates of the center pixel of the model, and (i, j) represents the coordinates of the surrounding pixels.

[0067] Range kernel: ,in It is the standard deviation. f(k, l) The grayscale value of the center pixel of the template. f(i, j) The grayscale value is the value of the surrounding pixels.

[0068] The bilateral filter template is: Then, the template and the image are directly convolved to obtain the filtered image.

[0069] S10: After image processing in the previous step, the edge line of the QR code positioning area is obtained, and the corner position information of the QR code is obtained through coordinate transformation.

[0070] S11: Obtain the corner position information of the QR code through EPNP calculation, specifically including:

[0071] Select control points, and calculate the results based on the 3D points and control points in the 3D-2D matching pair. ;

[0072] According to this Calculate the 3D coordinates of the control points in the camera coordinate system from the 2D points in the 3D-2D matching pair;

[0073] Based on the 3D coordinates, the internal 3D coordinates of the previous 2D-3D matching are used to construct a 3D-3D problem, which is then solved using ICP to obtain the final corner position information of the QR code.

[0074] Specifically, the pixel coordinates of the four corner points of the QR code obtained through EPnP are as follows: , ), ( , (), , (), , Since R and T here are theoretically obtained, they constitute... .

[0075] S12: Calculate the error corresponding to each corner point;

[0076] For example: = .

[0077] S13: Determine if the error is within the set threshold. If the error is large, adjust the standard deviation of image processing in S9.

[0078] Determine if the error is within the set threshold. If not, first adjust the binarization threshold during image processing, thereby adjusting the standard deviation of the spatial domain kernel and the range kernel. and Continue until the error corresponding to each corner point is within the acceptable range.

[0079] S14: Hand-eye calibration calculates R and T;

[0080] is the camera's intrinsic parameter, which has been calibrated, and u and v are the average values of each corner point after the S13 step, 、 and is the coordinate position of the end of the robot arm obtained in S4, is the value obtained by the ultrasonic ranging in S7, and the remaining unknown is calculated by the following formula:

[0081]

[0082] where K1 is the camera intrinsic parameter, K2 is the camera extrinsic parameter, , is the focal length of the camera, and is the center of the current set image, is the vertical distance from the camera center to the target;

[0083] .

[0084] S15: Compare the initial R and T to determine whether to update, here a threshold value (i.e. the second set threshold value) is set, and if the deviation threshold value (the difference between the initial R and T is greater than the second set threshold value), R and T need to be corrected (replace the initial R and T with the calculated R and T);

[0085] S16: End.

[0086] Embodiment 2:

[0087] The embodiment 2 of the application provides a fixed viewpoint hand-eye calibration system based on a two-dimensional code, comprising:

[0088] A data acquisition module configured to acquire two-dimensional code image data at the end of a robot arm;

[0089] A first two-dimensional code corner position generation module configured to obtain edge lines of a two-dimensional code positioning area by using a Canny edge detection operator according to the acquired two-dimensional code image data at the end of the robot arm, and obtain the corner position of the two-dimensional code through coordinate transformation;

[0090] A second two-dimensional code corner position generation module configured to obtain the corner position of the two-dimensional code by EPnP solving according to the acquired two-dimensional code image data at the end of the robot arm;

[0091] The forward and inverse matrix parameter calculation module is configured to: obtain the error corresponding to each corner point according to the corner point position of the two-dimensional code obtained through coordinate transformation and the corner point position of the two-dimensional code obtained through EPnP solving, respectively, judge whether the errors of the four corner points of the two-dimensional code are all less than a first set threshold, if yes, calculate the forward and inverse matrix parameters of the mechanical arm according to the corner point position of the two-dimensional code obtained through coordinate transformation, and perform the next step, otherwise, adjust the standard deviation of the Canny edge detection operator until whether the errors of the four corner points of the two-dimensional code are all less than the first set threshold.

[0092] The forward and inverse matrix parameter of the mechanical arm is configured as a calibration module, configured to: judge whether the difference between the calculated forward and inverse matrix parameters of the mechanical arm and the initial forward and inverse matrix parameters of the mechanical arm is less than a second set threshold, if yes, take the initial forward and inverse matrix parameters of the mechanical arm as the calibrated parameters, otherwise, take the calculated forward and inverse matrix parameters of the mechanical arm as the calibrated parameters.

[0093] The working method of the system is the same as the fixed-viewpoint hand-eye calibration method based on a two-dimensional code provided in Embodiment 1, and will not be repeated here.

[0094] Embodiment 3

[0095] Embodiment 3 of the present application provides a computer readable storage medium, which stores a program, and the program is executed by a processor to realize the steps in the fixed-viewpoint hand-eye calibration method based on a two-dimensional code as described in Embodiment 1 of the present application.

[0096] Embodiment 4

[0097] Embodiment 4 of the present application provides an electronic device, which includes a memory, a processor, and a program stored in the memory and executable on the processor, and the processor executes the program to realize the steps in the fixed-viewpoint hand-eye calibration method based on a two-dimensional code as described in Embodiment 1 of the present application.

[0098] Those skilled in the art will appreciate that embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can take the form of hardware embodiments, software embodiments, or embodiments combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer usable storage media (including but not limited to disk storage and optical storage, etc.) containing computer usable program code.

[0099] The embodiments of methods, apparatuses (systems) and computer program products according to the present application can be described in flowcharts and / or block diagrams in reference to the methods, apparatuses (systems) and computer program products according to the embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and combinations of flows and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing apparatus to produce a machine, so that the instructions, which are executed via the processor of the computer or other programmable data processing apparatus, generate a device implemented in the flowcharts and / or block diagrams. Figure 1 one or more flows and / or blocks. Figure 1 one or more flows and / or blocks.

[0100] These computer program instructions can also be stored in a computer readable storage medium that can direct the computer or other programmable data processing apparatus to work in a specific manner, so that the instructions stored in the computer readable storage medium produce a manufactured product including instruction devices, which implement the functions specified in the flowcharts and / or block diagrams. Figure 1 one or more flows and / or blocks. Figure 1 one or more flows and / or blocks.

[0101] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus, so that a series of operation steps are performed on the computer or other programmable data processing apparatus to produce a computer implemented process, so that the instructions executed on the computer or other programmable data processing apparatus provide steps for implementing the functions specified in the flowcharts and / or block diagrams. Figure 1 one or more flows and / or blocks. Figure 1 one or more flows and / or blocks.

[0102] A person of ordinary skill in the art can understand that all or part of the above-mentioned embodiment methods can be implemented by computer program instructions to instruct related hardware, and the program can be stored in a computer readable storage medium. When the program is executed, it can include the flow of each method embodiment as described above. The storage medium can be a magnetic disc, an optical disc, a read-only memory (ROM) or a random access memory (RAM), etc.

[0103] The above only describes the preferred embodiments of the present application and is not intended to limit the present application. For those skilled in the art, the present application can have various modifications and changes. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A fixed-viewpoint hand-eye calibration method based on QR codes, characterized in that: Includes the following processes: Acquire the QR code image data at the end of the robotic arm; fix the QR code at the end of the robotic arm; Based on the acquired QR code image data at the end of the robotic arm, the Canny edge detection operator is used to obtain the edge line of the QR code positioning area, and the corner positions of the QR code are obtained through coordinate transformation. Based on the acquired QR code image data at the end of the robotic arm, the corner positions of the QR code are obtained by solving the EPnP algorithm. Based on the corner positions of the QR code obtained by coordinate transformation and the corner positions of the QR code obtained by EPnP, the error corresponding to each corner point is obtained. It is determined whether the errors of the four corner points of the QR code are all less than the first set threshold. If so, the positive and negative matrix parameters of the robotic arm are calculated based on the corner positions of the QR code obtained by coordinate transformation, and the next step is executed; otherwise, the standard deviation of the Canny edge detection operator is adjusted until the errors of the four corner points of the QR code are all less than the first set threshold. Determine whether the difference between the calculated forward and inverse matrix parameters of the robotic arm and the forward and inverse matrix parameters of the initial robotic arm is less than the second set threshold. If so, the forward and inverse matrix parameters of the initial robotic arm are used as the calibrated parameters; otherwise, the calculated forward and inverse matrix parameters of the robotic arm are used as the calibrated parameters. The Canny edge detection operator uses bilateral filtering, and the bilateral filtering template is: The image is obtained by convolving a bilateral filter template with the QR code image; among which, For spatial domain kernel functions, Let (k, l) be the kernel function of the range, (k, l) be the coordinates of the center pixel of the model, and (i, j) be the coordinates of the surrounding pixels.

2. The fixed-viewpoint hand-eye calibration method based on QR codes as described in claim 1, characterized in that: EPnP solves for the corner positions of the QR code, including: Select control points, and calculate the results based on the 3D points and control points in the 3D-2D matching pair. ; according to Calculate the 3D coordinates of the control points in the camera coordinate system by matching the 2D points in the 3D-2D matching pair; finally, based on the 3D coordinates and the 3D coordinates in the previous 2D-3D matching pair, construct a 3D-3D problem and use ICP to solve it to obtain the final corner positions of the QR code.

3. The fixed-viewpoint hand-eye calibration method based on QR codes as described in claim 1, characterized in that: Acquire QR code image data at the end effector of the robotic arm, including: By moving the end effector of the robotic arm to a designated position within the camera's field of view, the location information of the QR code at that position is obtained.

4. A fixed-viewpoint hand-eye calibration system based on QR codes, characterized in that: include: The data acquisition module is configured to: acquire QR code image data at the end of the robotic arm; and fix the QR code to the end of the robotic arm. The first QR code corner position generation module is configured to: obtain the edge line of the QR code positioning area by using the Canny edge detection operator based on the acquired QR code image data at the end of the robotic arm, and obtain the corner position of the QR code through coordinate transformation; The corner position generation module of the second QR code is configured to: obtain the corner position of the QR code by solving EPnP based on the acquired QR code image data at the end of the robotic arm; The robotic arm's forward and inverse matrix parameter calculation module is configured to: obtain the corner positions of the QR code obtained from coordinate transformation and the corner positions of the QR code obtained from EPnP, respectively, obtain the error corresponding to each corner point, determine whether the errors of the four corner points of the QR code are all less than a first set threshold, if so, calculate the forward and inverse matrix parameters of the robotic arm based on the corner positions of the QR code obtained from coordinate transformation, and proceed to the next step; otherwise, adjust the standard deviation of the Canny edge detection operator until the errors of the four corner points of the QR code are all less than the first set threshold. The robot arm's forward and inverse matrix parameters are used as a calibration module and are configured to: determine whether the difference between the calculated forward and inverse matrix parameters of the robot arm and the forward and inverse matrix parameters of the initial robot arm is less than a second set threshold; if so, the forward and inverse matrix parameters of the initial robot arm are used as the calibrated parameters; otherwise, the calculated forward and inverse matrix parameters of the robot arm are used as the calibrated parameters. The Canny edge detection operator uses bilateral filtering, and the bilateral filtering template is: The image is obtained by convolving a bilateral filter template with the QR code image; among which, For spatial domain kernel functions, Let (k, l) be the kernel function of the range, (k, l) be the coordinates of the center pixel of the model, and (i, j) be the coordinates of the surrounding pixels.

5. The fixed-viewpoint hand-eye calibration system based on QR codes as described in claim 4, characterized in that: EPnP solves for the corner positions of the QR code, including: Select control points, and calculate the results based on the 3D points and control points in the 3D-2D matching pair. ; according to Calculate the 3D coordinates of the control points in the camera coordinate system by matching the 2D points in the 3D-2D matching pair; finally, based on the 3D coordinates and the 3D coordinates in the previous 2D-3D matching pair, construct a 3D-3D problem and use ICP to solve it to obtain the final corner positions of the QR code.

6. The fixed-viewpoint hand-eye calibration system based on QR codes as described in claim 4, characterized in that: Acquire QR code image data at the end effector of the robotic arm, including: By moving the end effector of the robotic arm to a designated position within the camera's field of view, the location information of the QR code at that position is obtained.

7. A computer-readable storage medium having a program stored thereon, characterized in that, When executed by the processor, the program implements the steps in the QR code-based fixed-viewpoint hand-eye calibration method as described in any one of claims 1-3.

8. An electronic device comprising a memory, a processor, and a program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps in the fixed-viewpoint hand-eye calibration method based on QR codes as described in any one of claims 1-3.

Images