A camera calibration board corner point recognition method and system based on machine vision

Abstract

This application relates to the field of machine vision technology and provides a machine vision-based method and system for corner recognition of camera calibration boards. The method includes first acquiring calibration board image information in real time using a camera; then, based on an edge detection algorithm, quickly determining edge point set information according to the calibration board image information; and finally, performing a Hough transform on the calibration board image information based on the edge point set information to effectively determine the target corner point set information. This application can accurately detect and locate each corner point of the calibration board image, and can still detect and identify corner point coordinates even in various blurred images. It is highly practical, effectively avoids image blurring, significantly improves the reliability of image recognition and the success rate of corner point recognition, and ensures the accuracy and efficiency of subsequent processing steps.

Description

Technical Field

[0001] This application relates to the technical field of machine vision, and more specifically, to a machine vision-based method and system for recognizing corner points on a camera calibration board. Background Technology

[0002] As a crucial means of mimicking human binocular perception, vision technology has been widely applied in various scenarios such as industrial inspection, robot navigation, 3D reconstruction, and autonomous driving. The prerequisite for achieving these functions is accurately acquiring the camera's internal parameters (such as focal length, principal point coordinates, and distortion coefficients) and external parameters (such as the relative position and orientation between cameras). This process is called machine vision camera calibration, and the calibration accuracy directly affects the performance and measurement accuracy of the entire vision system.

[0003] The mainstream camera calibration method is the Zhang Zhengyou calibration method, which uses a dedicated calibration board (such as a checkerboard) as a reference object. Its basic process includes: taking images of the calibration board from multiple different angles and orientations, detecting feature points in the images (such as the corner points of the checkerboard), and solving for the camera's intrinsic and extrinsic parameters by combining spatial geometric constraints.

[0004] Common corner detection algorithms include Harris corner detection and FAST corner detection, which are all local feature detection methods. For example, the Harris algorithm determines whether a region is a corner by calculating grayscale changes within a local window of an image; when the window shows significant grayscale changes in all directions, it is identified as a corner location.

[0005] Currently, in practical machine vision systems, to acquire stereo vision information, calibration boards often need to be placed at a large angle to the camera lens optical axis, and the calibration board image must cover the entire field of view. Especially during close-range imaging, a phenomenon often occurs where the image center is sharp while the edges are blurry. Alternatively, due to external light interference and lens distortion, some edges or corners of the calibration board may be sharp, while other areas are blurry. This significantly reduces the success rate of corner detection, limits the placement and orientation of the calibration board, makes the calibration process inflexible, and results in low reliability, requiring further improvement. Summary of the Invention

[0006] Based on this, embodiments of this application provide a machine vision-based camera calibration board corner point recognition method and system to solve the problem of low reliability in the prior art.

[0007] In a first aspect, embodiments of this application provide a machine vision-based method for recognizing corner points on a camera calibration board, the method comprising:

[0008] Based on the preset camera, acquire image information of the calibration board; Based on a preset edge detection algorithm, edge point set information is determined according to the calibration board image information; Based on the edge point set information, a Hough transform is performed on the calibration board image information to determine the target corner point set information.

[0009] Compared with the prior art, the beneficial effects are as follows: The camera calibration board corner recognition system based on machine vision provided in this application embodiment allows the terminal device to first use the camera to acquire calibration board image information in real time, then use the edge detection algorithm to quickly determine the edge point set information based on the calibration board image information, and finally use the edge point set information to perform Hough transform on the calibration board image information to effectively determine the target corner point set information, thereby accurately determining each corner point, effectively improving reliability, and solving the problem of low reliability in the current system to a certain extent.

[0010] Secondly, embodiments of this application provide a camera calibration board corner recognition system based on machine vision, the system comprising: Calibration board image information acquisition module: used to acquire calibration board image information based on a preset camera; Edge point set information determination module: used to determine edge point set information based on the calibration board image information according to the preset edge detection algorithm; Target corner point set information determination module: used to perform Hough transform on the calibration board image information based on the edge point set information to determine the target corner point set information.

[0011] Thirdly, embodiments of this application provide a terminal device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the method described in the first aspect above.

[0012] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the method described in the first aspect above.

[0013] It is understood that the beneficial effects of the second to fourth aspects mentioned above can be found in the relevant descriptions in the first aspect mentioned above, and will not be repeated here. Attached Figure Description

[0014] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below.

[0015] Figure 1 This is a schematic flowchart of a camera calibration board corner point recognition method provided in an embodiment of this application; Figure 2 This is a schematic diagram showing partial blurring of a calibration plate according to an embodiment of this application; Figure 3 This is a flowchart illustrating the process before step S200 in a camera calibration board corner point recognition method provided in an embodiment of this application. Figure 4 This is an original schematic diagram of a calibration plate provided in one embodiment of this application; Figure 5 This is a black-and-white binarized schematic diagram of a calibration board provided in an embodiment of this application; Figure 6 This is a schematic diagram of the edge of a calibration plate provided in one embodiment of this application; Figure 7 This is a flowchart illustrating step S300 in a camera calibration board corner point recognition method provided in an embodiment of this application; Figure 8 This is a schematic diagram of the Hough space provided in an embodiment of this application; Figure 9 This is a detailed schematic diagram of the Hough space provided in an embodiment of this application; Figure 10 This is a flowchart illustrating step S330 of the camera calibration board corner point recognition method provided in an embodiment of this application; Figure 11 This is a schematic diagram of the test results provided in one embodiment of this application; Figure 12 This is a first schematic diagram of multiple tests provided in an embodiment of this application; Figure 13 This is a second schematic diagram illustrating multiple tests provided in an embodiment of this application; Figure 14 This is a third schematic diagram illustrating multiple tests provided in an embodiment of this application; Figure 15 This is a block diagram of a camera calibration board corner recognition system provided in one embodiment of this application; Figure 16 This is a schematic diagram of a terminal device provided in an embodiment of this application. Detailed Implementation

[0016] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0017] In the description of this application and the appended claims, the terms "first," "second," "third," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0018] References to "one embodiment" or "some embodiments" as described in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0019] To illustrate the technical solution described in this application, specific embodiments are provided below.

[0020] Please see Figure 1 , Figure 1 This is a flowchart illustrating the camera calibration board corner recognition system based on machine vision provided in this embodiment. In this embodiment, the execution subject of the camera calibration board corner recognition method is a terminal device. It is understood that the types of terminal devices include, but are not limited to, tablet computers, laptops, ultra-mobile personal computers (UMPCs), netbooks, personal digital assistants (PDAs), etc., and this embodiment does not impose any restrictions on the specific type of terminal device.

[0021] Please see Figure 1 The camera calibration board corner point identification method provided in this application includes, but is not limited to, the following steps: In S100, image information of the calibration board is acquired based on a preset camera.

[0022] Specifically, the terminal device can first acquire calibration board image information based on a preset camera. The calibration board image information is used to describe the image obtained by taking a picture of the calibration board using the camera.

[0023] For example, please refer to Figure 2 , Figure 2The image shows a cube calibration board obtained using a Hikvision MV-CA050-10GM industrial camera with a resolution of 2448×2048 and a telecentric lens with a field of view of 6.4mm×4.8mm. Due to the characteristics of the optical system, the calibration board image exhibits barrel distortion and shows different imaging effects in two dimensions: one dimension is blurred, while the other is clearly discernible. When the Camera Calibrator application in the Image Processing and Computer Vision Toolbox of Matlab 2023a is opened and the "Add Images" button is clicked to load the calibration board image, the system displays the message "no calibration patterns were detected in the images," indicating that no valid corner points were identified.

[0024] In S200, edge point set information is determined based on a preset edge detection algorithm and the calibration board image information.

[0025] Specifically, after the terminal device acquires the calibration board image information, it can perform edge detection processing on the calibration board image information based on a preset edge detection algorithm to determine the edge point set information.

[0026] For some possible implementations, please refer to [link / reference needed] to improve reliability. Figure 3 Before step S200, the method also includes, but is not limited to, the following steps: In S201, the calibration board image information is normalized to generate normalized calibration board image information.

[0027] Specifically, after the terminal device acquires the calibration board image information, it can normalize the calibration board image information to generate normalized calibration board image information.

[0028] In S202, the normalized calibration board image information is binarized to generate binary image information.

[0029] For example, please refer to Figure 4 After the terminal device generates the normalized calibration board image information, it can perform black-and-white binarization processing on the normalized calibration board image information to generate binary image information.

[0030] Accordingly, step S200 includes, but is not limited to, the following steps: In S210, edge detection processing is performed on the binary image information based on a preset edge detection algorithm to determine the edge point set information.

[0031] For example, please refer to Figure 5 and Figure 6 After the terminal device generates binary image information, it can perform edge detection processing on the binary image information based on a preset edge detection algorithm to determine the edge point set information. The edge detection algorithm can be based on the Canny operator, and the edge point set information includes multiple edge point information, which describes the edge points in the binary image information. Figure 5 This is used to demonstrate how edge detection algorithms such as Canny can be used to find edge points in a binarized image. Figure 6 Used to display possible edge points using white pixels.

[0032] In S300, based on the edge point set information, a Hough transform is performed on the calibration board image information to determine the target corner point set information.

[0033] Specifically, the Hough transform is a fundamental and powerful tool in computer vision, particularly suitable for extracting geometric structures from noisy edge images. The essence of the Hough transform is to transform the image from image space to parameter space for analysis. Therefore, after the terminal device determines the edge point set information, it can perform the Hough transform on the calibration board image information based on the edge point set information to determine the target corner point set information.

[0034] In some possible implementations, to determine the target corner point set information, please refer to [link / reference needed]. Figure 7 Step S300 includes, but is not limited to, the following steps: In S310, a Hough transform is performed on the calibration board image information to construct the Hough parameter space.

[0035] Specifically, after the terminal device determines the edge point set information, the terminal device can perform Hough transform on the calibration board image information to construct the Hough parameter space. The Hough parameter space includes multiple candidate intersection point information, which is used to describe the points where the lines corresponding to the points on the same straight line in the calibration board image information intersect in the Hough parameter space.

[0036] For example, in the image space, the original image is composed of pixels (x, y), and the information of the intersection point to be selected is the pixel; each point in the image space corresponds to a straight line in the Hough parameter space, and all points in the image space on the same straight line will intersect at a point in the Hough parameter space, and the intersecting point is the information of the intersection point to be selected.

[0037] Without loss of generality, the information of the candidate intersection point can be represented as (m,c) in the image space, and the equation of the line corresponding to the intersection point can be: , In the formula, The vertical coordinate of the pixel in the calibration board image information. Let be the slope of the line in the Hough parameter space. The x-coordinate of the pixel in the calibration board image information. It is the intercept of the line.

[0038] In S320, a polar coordinate Hough transformation is performed on the Hough parameter space to determine the polar coordinate equation corresponding to the line.

[0039] Without loss of generality, the Hough parameter space is a space consisting of line parameters (m,c). For a point (x0,y0) in the image space, there are infinitely many lines passing through that point, each satisfying the equation... Furthermore, this line is a straight line in the (m,c) parameter space. Similarly, the second point (x1,y1) in the image space also corresponds to a straight line in the parameter space. If (x0, y0) and (x1, y1) lie on the same straight line in the image space, then in the parameter space, the two straight lines will intersect at a point (m0, c0), where m0 is the slope of the straight line in the image space and c0 is the intercept of the straight line in the image space.

[0040] Specifically, in practical calculations, the parameter space (m,c) presents a problem: when the line is perpendicular, the slope m becomes infinite. This problem is mathematically difficult to handle. Therefore, after constructing the Hough parameter space on the terminal device, the terminal device can perform a polar coordinate Hough transformation on the Hough parameter space to effectively determine the polar coordinate equation corresponding to the line. The polar coordinate equation is: , In the formula, The perpendicular distance from the origin to the line; The x-coordinate of the pixel on the line; Let be the angle between the perpendicular line and the positive x-axis, which allows the Hough parameter space to be transformed into (ρ,θ) space, when At that time, the terminal device can calculate its corresponding ρ value, and the point (x0, y0) is a sine curve in polar coordinate space; The vertical coordinate of the pixel on the line.

[0041] For example, please refer to Figure 6 , Figure 8 and Figure 9 ,right Figure 6 The image shown is subjected to a polar coordinate Hough transform, and the result is as follows: Figure 8 As shown. Figure 8 Used to showcase the Hof Space Figure 9 Used to display local details of the Hof space, from Figure 9As can be seen, the edges of the edge image are multiple sine curves.

[0042] In S330, based on the polar coordinate equation, voting is performed on the information of each edge point until the target corner point set information is determined.

[0043] Specifically, after the terminal device determines the polar coordinate equation, it can perform voting processing on the information of each edge point based on the polar coordinate equation until the target corner point set information is determined. The target corner point set information includes multiple target corner point information.

[0044] In some possible implementations, in order to determine the target corner point set information, the method may include, but is not limited to, the following steps before step S330: In S3301, based on the preset discretization parameter space, the range of values ​​for both the vertical distance and the included angle are divided into multiple units to generate initial accumulator unit information.

[0045] Specifically, the terminal device can divide the range of vertical distance and the range of included angle into multiple units based on a preset discretized parameter space, and generate initial accumulator unit information.

[0046] For example, in the discretized parameter space, the terminal device can divide the range of values ​​of ρ and θ into multiple small cells, which can be called "accumulator cells" or "voting boxes", and then perform subsequent voting processing.

[0047] Accordingly, please refer to Figure 10 Step S330 includes, but is not limited to, the following steps: In S331, for each edge point information: when the included angle is within the specified range, calculate the vertical distance corresponding to each edge point information.

[0048] Specifically, after the terminal device generates the initial accumulator unit information, the terminal device can perform this processing for each edge point information: when the included angle is within a specified range, calculate the vertical distance corresponding to each edge point information, where the specified range is... .

[0049] In S332, based on the vertical distance, the initial accumulator unit information corresponding to each specified point is numerically increased.

[0050] Specifically, after the terminal device calculates the vertical distance corresponding to each edge point, it can increment the initial accumulator unit information corresponding to each specified point based on the vertical distance. The specified point information is... .

[0051] For example, for each edge point (x, y) in the edge image, when When the terminal device can calculate the corresponding ρ, for each point (ρ, θ), the value of the corresponding accumulator unit is incremented by 1. This execution process is called voting.

[0052] In S333, the initial accumulator cell information is filtered based on a preset threshold, and the target accumulator cell information is retained.

[0053] Specifically, after the terminal device performs numerical increment processing, the terminal device can filter the initial accumulator unit information based on a preset threshold and retain the target accumulator unit information. The target accumulator unit information is used to describe the initial accumulator unit information where the final value is greater than the threshold.

[0054] For example, after the voting ends, the local maximum value in the accumulator corresponds to a straight line in the image space. For instance, if the value of (120, 35°) in the accumulator is 100, then there are 100 edge points on the straight line ρ≈100, θ≈30°. The terminal device can then set a threshold to select only accumulators with more than the threshold, thereby filtering out false straight lines caused by noise and obtaining the true edge lines of the calibrated image blocks.

[0055] In S334, the target corner point set information is determined based on the straight line corresponding to the target accumulator unit information.

[0056] Specifically, after the terminal device retains the target accumulator unit information, the terminal device can effectively determine the target corner point set information based on the straight line corresponding to the target accumulator unit information, thereby accurately determining multiple target corner point information.

[0057] For example, please refer to Figure 8 ,exist Figure 8 In the Hough space shown, the white boxes circle the local maxima of 4 horizontal lines and 4 vertical lines. By setting a length threshold > 1500, 6 line segments are detected and identified. The 6 line segments are shown in Table 1 below, and the intersection points corresponding to the lines are shown in Table 2 below. It should be noted that the coordinate units in Tables 1 and 2 are all pixels.

[0058] Table 1. Table of Retained Straight Lines

[0059] Table 2. Intersections of retained straight lines

[0060] Specifically, Table 2 shows the nine intersection points formed by the pairwise intersection of the six lines. The positions of the nine intersection points can be marked on... Figure 4, Figure 5 and Figure 6 In the middle, the marking results are as follows Figure 11 As shown; in one possible scenario, the terminal device can also use the camera calibration board corner detection method to perform the same processing on multiple sets of calibration images, and the results of multiple tests are as follows: Figure 12 , Figure 13 and Figure 14 As shown in the results of multiple tests, the camera calibration board corner point recognition method of this application can effectively detect and identify the corner points of each block, proving that this application is stable, reliable and highly practical.

[0061] The implementation principle of the camera calibration board corner recognition system based on machine vision in this application embodiment is as follows: The terminal device can first use the camera to acquire calibration board image information in real time, and then, based on the edge detection algorithm, quickly determine the edge point set information according to the calibration board image information. Finally, based on the edge point set information, perform Hough transform on the calibration board image information to effectively determine the target corner point set information, thereby accurately determining each corner point and effectively improving reliability.

[0062] It should be noted that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0063] Embodiments of this application also provide a machine vision-based camera calibration board corner recognition system. For ease of explanation, only the parts relevant to this application are shown, such as... Figure 15 As shown, the system 150 includes: Calibration board image information acquisition module 151: used to acquire calibration board image information based on a preset camera; Edge point set information determination module 152: used to determine edge point set information based on a preset edge detection algorithm and calibration board image information; Target corner point set information determination module 153: Used to perform Hough transform on calibration board image information based on edge point set information to determine target corner point set information.

[0064] Optionally, the system 150 also includes: Calibration board image information generation module: used to normalize the calibration board image information and generate normalized calibration board image information; Binary image information generation module: used to perform binarization processing on the normalized calibration board image information to generate binary image information.

[0065] Accordingly, the edge point set information determination module 152 includes: Edge point set information determination submodule: It is used to perform edge detection processing on binary image information based on a preset edge detection algorithm to determine edge point set information, which includes multiple edge point information.

[0066] Optionally, the target corner point set information determination module 153 mentioned above includes: The Hough parameter space construction submodule is used to perform a Hough transform on the calibration board image information and construct the Hough parameter space. This Hough parameter space includes multiple candidate intersection point information points, which describe the points where the lines corresponding to points on the same straight line in the calibration board image intersect in the Hough parameter space. The equations of the lines corresponding to the straight lines in the calibration board image information are: , In the formula, The vertical coordinate of the pixel in the calibration board image information. Let be the slope of the line in the Hough parameter space. The x-coordinate of the pixel in the calibration board image information. The intercept of the line; The polar equation determination submodule performs a polar coordinate Hough transform on the Hough parameter space to determine the polar equation corresponding to the line, where the polar equation is: , In the formula, The perpendicular distance from the origin to the line is... The x-coordinate of the pixel on the line. The angle between the perpendicular line and the positive x-axis is denoted as . The ordinate of the pixel on the line; The target corner point set information determination submodule is used to perform voting processing on the information of each edge point based on the polar coordinate equation until the target corner point set information is determined. The target corner point set information includes multiple target corner point information.

[0067] Optionally, the system 150 also includes: Initial accumulator cell information generation module: Based on a preset discretization parameter space, it divides the range of vertical distance and the range of included angle into multiple cells to generate initial accumulator cell information. Accordingly, the polar coordinate equation determination submodule includes: Vertical distance calculation module: used to calculate the vertical distance of each edge point when the included angle is within a specified range; Numerical increment processing module: Used to increment the numerical values ​​of the initial accumulator unit information corresponding to each specified point based on the vertical distance. The specified point information is... ; Target accumulator cell information retention module: used to filter the initial accumulator cell information based on a preset threshold and retain the target accumulator cell information, wherein the target accumulator cell information is used to describe the initial accumulator cell information whose final value is greater than the threshold; Target Corner Set Information Determination Module: Used to determine the target corner set information based on the straight line corresponding to the target accumulator unit information.

[0068] It should be noted that the information interaction and execution process between the above modules are based on the same concept as the method embodiments of this application. For details on their specific functions and technical effects, please refer to the method embodiments section, which will not be repeated here.

[0069] This application also provides a terminal device, such as... Figure 16 As shown, the terminal device 160 of this embodiment includes: a processor 161, a memory 162, and a computer program 163 stored in the memory 162 and executable on the processor 161. When the processor 161 executes the computer program 163, it implements the steps in the above-described camera calibration board corner point recognition method embodiment, for example... Figure 1 The steps S100 to S300 are shown; or, when the processor 161 executes the computer program 163, it implements the functions of each module in the above-described device, for example... Figure 15 The functions of modules 151 to 153 are shown.

[0070] The terminal device 160 can be a desktop computer, laptop, handheld computer, cloud server, or other computing device. The terminal device 160 includes, but is not limited to, a processor 161 and a memory 162. Those skilled in the art will understand that... Figure 16 This is merely an example of terminal device 160 and does not constitute a limitation on terminal device 160. It may include more or fewer components than shown, or combine certain components, or different components. For example, terminal device 160 may also include input / output devices, network access devices, buses, etc.

[0071] The processor 161 can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.; the general-purpose processor can be a microprocessor or any conventional processor, etc.

[0072] The memory 162 can be an internal storage unit of the terminal device 160, such as the hard disk or memory of the terminal device 160. The memory 162 can also be an external storage device of the terminal device 160, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the terminal device 160. Furthermore, the memory 162 can include both internal storage units and external storage devices of the terminal device 160. The memory 162 can also store computer program 163 and other programs and data required by the terminal device 160. The memory 162 can also be used to temporarily store data that has been output or will be output.

[0073] One embodiment of this application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable file, or some intermediate form. The computer-readable medium can include any entity or device capable of carrying computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc.

[0074] The above are all preferred embodiments of this application, and are not intended to limit the scope of protection of this application. Therefore, all equivalent changes made in accordance with the methods, principles and structures of this application should be covered within the scope of protection of this application.

Claims

1. A method for identifying corner points on a camera calibration board based on machine vision, characterized in that, The method includes: Based on the preset camera, acquire image information of the calibration board; Based on a preset edge detection algorithm, edge point set information is determined according to the calibration board image information; Based on the edge point set information, a Hough transform is performed on the calibration board image information to determine the target corner point set information.

2. The method according to claim 1, characterized in that, Before determining the edge point set information based on the calibration board image information using the preset edge detection algorithm, the method further includes: The calibration board image information is normalized to generate normalized calibration board image information; The normalized calibration board image information is binarized to generate binary image information; Accordingly, the edge point set information determined based on the preset edge detection algorithm and the calibration board image information includes: Based on a preset edge detection algorithm, edge detection processing is performed on the binary image information to determine edge point set information, wherein the edge point set information includes multiple edge point information.

3. The method according to claim 2, characterized in that, The step of performing a Hough transform on the calibration board image information based on the edge point set information to determine the target corner point set information includes: A Hough transform is performed on the calibration board image information to construct a Hough parameter space. This Hough parameter space includes multiple candidate intersection point information points, which describe the points where the lines corresponding to points on the same straight line in the calibration board image information intersect in the Hough parameter space. The equations of the straight lines corresponding to the lines in the calibration board image information are: ， In the formula, The vertical coordinate of the pixel in the calibration board image information. Let be the slope of the line in the Hough parameter space. The x-coordinate of the pixel in the calibration board image information. The intercept of the line is given. Perform a polar coordinate Hough transform on the Hough parameter space to determine the polar coordinate equation corresponding to the line, wherein the polar coordinate equation is: ， In the formula, The perpendicular distance from the origin to the line is... The x-coordinate of the pixel on the line. The angle between the perpendicular line and the positive x-axis is denoted as . The vertical coordinate of the pixel point on the line; Based on the polar coordinate equation, voting is performed on the information of each edge point until the target corner point set information is determined, wherein the target corner point set information includes multiple target corner point information.

4. The method according to claim 3, characterized in that, Before the voting process is performed on the edge point information based on the polar coordinate equation until the target corner point set information is determined, the method further includes: Based on the preset discretized parameter space, the range of values ​​for the vertical distance and the included angle are divided into multiple units to generate initial accumulator unit information. Accordingly, the process of voting on the information of each edge point based on the polar coordinate equation until the target corner point set information is determined includes: For each edge point: when the included angle is within a specified range, calculate the vertical distance corresponding to each edge point; Based on the vertical distance, the initial accumulator unit information corresponding to each specified point information is numerically incremented, wherein the specified point information is... ; Based on a preset threshold, the initial accumulator unit information is filtered to retain the target accumulator unit information, wherein the target accumulator unit information is used to describe the initial accumulator unit information whose final value is greater than the threshold. Based on the straight line corresponding to the target accumulator unit information, the target corner point set information is determined.

5. A camera calibration board corner point recognition system based on machine vision, characterized in that, The system includes: Calibration board image information acquisition module: used to acquire calibration board image information based on a preset camera; Edge point set information determination module: used to determine edge point set information based on the calibration board image information according to the preset edge detection algorithm; Target corner point set information determination module: used to perform Hough transform on the calibration board image information based on the edge point set information to determine the target corner point set information.

6. The system according to claim 5, characterized in that, The system includes: Calibration board image information generation module: used to normalize the calibration board image information and generate normalized calibration board image information; Binary image information generation module: used to perform binarization processing on the normalized calibration board image information to generate binary image information.

7. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method as described in any one of claims 1 to 4.

8. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1 to 4.

Images