Vision measurement platform, calibration data acquisition method, measurement device and storage medium

Abstract

This application relates to the field of parts measurement technology, specifically to a vision measurement platform, a calibration data acquisition method, a measurement device, and a storage medium. The vision measurement platform provided in this application includes: a drive module, a guide module, a platform, a vision module, and a control module. The control module controls the drive module, guide module, platform, and vision module to acquire sampled images of the workpiece. Multiple sampled images are stitched together to form a target image. The target image is then sequentially corrected according to a preset distortion calibration matrix and a first geometric correction matrix to obtain a corrected image. The workpiece is then measured based on the corrected image to obtain the measurement result. This application improves the measurement accuracy of the vision measurement platform by correcting the target image and then performing workpiece inspection based on the corrected image.

Description

Technical Field

[0001] This application relates to the field of parts measurement technology, specifically to a vision measurement platform, a calibration data acquisition method, a measurement device, and a storage medium. Background Technology

[0002] In the field of precision manufacturing, the accuracy of measuring equipment directly determines product quality and production compliance. However, during long-term operation, the core performance indicators of the equipment, such as mechanical transmission accuracy and imaging quality, will gradually decline due to factors such as mechanical wear, aging of electronic components, and environmental corrosion. This leads to increased errors in the measuring equipment and affects the production quality of the products. Summary of the Invention

[0003] In view of the above, it is necessary to propose a visual measurement platform, a calibration data acquisition method, a measurement device and a storage medium to solve the technical problem that the measurement device's error increases during long-term operation, leading to a decrease in product manufacturing quality.

[0004] Firstly, a visual measurement platform is provided, comprising: a driving module, a guiding module, a loading platform, a vision module, and a control module. The control module controls the driving module to drive the guiding module according to preset positioning coordinates, causing the loading platform to sequentially move to each corresponding sampling position. As the loading platform moves to each sampling position, the control module sends sampling commands to the vision module. The vision module responds sequentially to each sampling command, sampling the workpiece to be measured placed on the loading platform to obtain a sampling image of the workpiece at each sampling position, and returns the sampling image to the control module. The sampling image at least displays a portion of the workpiece. The control module stitches multiple sampling images into a target image, performs distortion correction on the target image according to a preset distortion calibration matrix, and performs geometric correction on the distorted target image according to a preset first geometric correction matrix to obtain a corrected image. The workpiece is measured based on the corrected image to obtain the measurement result.

[0005] Optionally, the aforementioned visual measurement platform may further include a measurement module: the measurement module reads the actual displacement distance of the platform when it moves to each sampling position and returns the actual displacement distance to the control module; the control module inputs the actual displacement distance into a preset piecewise exponential calibration model to obtain a compensated displacement distance, and based on the compensated displacement distance, controls the drive module to drive the guide module to perform displacement compensation on the platform; after completing the displacement compensation, a sampling command is sent to the vision module.

[0006] Secondly, a calibration data acquisition method is provided, applied to the visual measurement platform described in any of the above claims. The method includes: acquiring a calibration image obtained by the visual measurement platform after sampling a target calibration board, the target calibration board including a first number of calibration markers; dividing the calibration image into a second number of image regions according to the calibration markers; acquiring a linear coefficient matrix and a nonlinear coefficient matrix for each image region, and obtaining a region calibration matrix for each image region based on the linear coefficient matrix and the nonlinear coefficient matrix; generating a distortion calibration matrix based on the region calibration matrix, the distortion correction matrix being used to correct the distortion of a target image containing the workpiece.

[0007] Optionally, the above-described calibration data acquisition method may further include: acquiring the first center coordinates of each calibration identifier in the calibration image, and constructing a first coordinate matrix based on the first center coordinates; acquiring the preset second center coordinates corresponding to each calibration identifier, and constructing a second coordinate matrix based on the second center coordinates; calculating a first geometric correction matrix based on the first coordinate matrix and the second coordinate matrix, wherein the first geometric correction matrix is ​​used to perform geometric correction on the distortion-corrected target image to obtain a corrected image.

[0008] Optionally, in the above-described calibration data acquisition method, obtaining the first center coordinates of each calibration identifier in the calibration image includes: obtaining the center pixel coordinates of each calibration identifier; converting each center pixel coordinate into image coordinates of each calibration identifier in the calibration image based on the camera intrinsic parameters of the visual measurement platform; and converting each image coordinate into the first center coordinates of each calibration identifier based on the camera extrinsic parameters of the visual measurement platform.

[0009] Optionally, the above-described calibration data acquisition method may further include: acquiring the center pixel coordinates of each calibration marker in each image region; calculating a first center distance for each image region based on each center pixel coordinate; calculating a center distance ratio for each image region based on each first center distance and each preset second center distance; and constructing a second geometric correction matrix based on each center distance ratio. The second geometric correction matrix is ​​used to perform geometric correction on the distortion-corrected target image to obtain a corrected image.

[0010] Optionally, the above-described calibration data acquisition method may further include: acquiring the translation range of the platform in the visual measurement platform, dividing the translation range into multiple translation intervals; acquiring the actual translation distance of the platform in each translation interval; calculating the translation error of the platform in each translation interval based on the actual translation distance and a preset interval translation distance; and fitting an error distribution based on the translation error in each translation interval to construct a piecewise exponential translation model.

[0011] Optionally, in the above-described calibration data acquisition method, after acquiring the translation range of the platform in the visual measurement platform and dividing the translation range into multiple translation intervals, the method further includes: acquiring the vertical value of the platform in each translation interval; calculating the verticality of each translation interval based on the vertical value in each translation interval, and constructing a piecewise index calibration model.

[0012] Thirdly, a measuring device is provided, the measuring device including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the calibration data acquisition method as described in any of the preceding claims.

[0013] Fourthly, a computer-readable storage medium is provided, wherein a computer program is stored therein, and when executed by a processor, the computer program implements the calibration data acquisition method as described in any one of the preceding claims.

[0014] Based on the above, this application uses visual measurement to stitch together multiple sampled images that at least show a part of the workpiece area into a target image. Then, it uses a preset distortion calibration matrix and a first geometric correction matrix to sequentially correct the target image to obtain a corrected image. Finally, it performs workpiece detection based on the corrected image, thereby achieving the purpose of correcting the error of the visual measurement platform, improving the measurement accuracy of the visual measurement platform, and improving the production quality of the product. Attached Figure Description

[0015] Figure 1 This is a schematic diagram of a vision measurement platform provided in an embodiment of this application.

[0016] Figure 2 This is a flowchart of a calibration data acquisition method provided in an embodiment of this application.

[0017] Figure 3 This is a schematic diagram of the structure of a target calibration plate provided in an embodiment of this application.

[0018] Figure 4 This is a flowchart of obtaining the first geometric correction matrix provided in one embodiment of this application.

[0019] Figure 5 This is a flowchart of obtaining the first center coordinates provided in an embodiment of this application.

[0020] Figure 6 This is a flowchart of obtaining the second geometric correction matrix provided in one embodiment of this application.

[0021] Figure 7 This is a schematic diagram of the second center distance provided in an embodiment of this application.

[0022] Figure 8 This is a flowchart of constructing a translational piecewise exponential model provided in one embodiment of this application.

[0023] Figure 9 This is a flowchart of constructing a vertical segmented exponential model provided in one embodiment of this application.

[0024] Figure 10 This is a schematic diagram illustrating an application scenario of the calibration data acquisition method provided in an embodiment of this application.

[0025] Component Symbol Explanation Visual Measurement Platform 100 Driver Module 110 Guide module 120 Cargo platform 130 Visual Module 140 Control Module 150 Metering Module 160 Measuring equipment 10 Memory 11 Processor 12 The following detailed description, in conjunction with the accompanying drawings, will further illustrate this application. Detailed Implementation

[0026] The embodiments of this application are described in detail below. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain this application, and should not be construed as limiting this application.

[0027] In the embodiments of this application, it should be noted that, unless otherwise expressly specified and limited, the word "for example" is used to indicate an example, illustration, or description. Any embodiment or design scheme described as "for example" in the embodiments of this application should not be construed as being better or more advantageous than other embodiments or design schemes. Specifically, the use of the word "for example" is intended to present the relevant concepts in a specific manner.

[0028] In the description of this application, it should be noted that, unless otherwise expressly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection, an electrical connection, or a connection that allows communication between them; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication between two components or the interaction between two components. Those skilled in the art can understand the specific meaning of the above terms in this application according to the specific circumstances.

[0029] In the description of this application, it should be noted that, unless otherwise expressly specified and limited, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, features defined as "first" or "second" may explicitly or implicitly include one or more features. Furthermore, in the description of this application, "multiple" means two or more, unless otherwise expressly and specifically limited.

[0030] To better understand the above-mentioned objectives, features, and advantages of the present invention, the present invention will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that, unless otherwise specified, the embodiments and features described in these embodiments can be combined with each other.

[0031] refer to Figure 1 The diagram shown is a schematic of a vision measurement platform 100 provided in an embodiment of this application. The vision measurement platform 100 includes a drive module 110, a guide module 120, a loading platform 130, a vision module 140, and a control module 150.

[0032] The control module 150 controls the drive module 110 to drive the guide module 120 according to each preset positioning coordinate, so that the platform 130 moves sequentially to each corresponding sampling position, and sends sampling instructions to the vision module 140 when the platform 130 moves sequentially to each sampling position.

[0033] The vision module 140 responds to each sampling command in sequence, samples the workpiece to be measured placed on the platform 130 to obtain the sampling image of the workpiece at each sampling position, and returns the sampling image to the control module 150. The sampling image displays at least a part of the workpiece.

[0034] The control module 150 stitches multiple sampled images into a target image, performs distortion correction on the target image according to a preset distortion calibration matrix, and performs geometric correction on the distorted target image according to a preset first geometric correction matrix to obtain a corrected image; the workpiece is measured based on the corrected image to obtain the measurement result of the workpiece.

[0035] In some embodiments of this application, the visual measurement platform 100 includes, but is not limited to, a flash meter, an image meter, and a microscopic measuring instrument. When measuring a workpiece, the visual measurement platform 100 can select an appropriate measurement method according to the size of the workpiece.

[0036] When the vision measurement platform 100 measures a workpiece, for smaller workpieces, after placing the workpiece on the loading platform 130, the field of view of the vision module 140 can cover the entire workpiece. Therefore, after the control module 150 sends a sampling command to the vision module 140, the vision module 140 responds to the sampling command and samples the loading platform 130 to obtain a target image containing the complete workpiece. However, for larger workpieces, the vision module 140 cannot sample a target image containing the complete workpiece in one go. The control module 150 can control the drive module 110 to drive the guide module 120 according to each preset positioning coordinate, so that the loading platform 130 moves sequentially to the sampling position corresponding to each positioning coordinate. After the loading platform 130 moves sequentially to each sampling position, the control module 150 sends a sampling command to the vision module 140. The vision module 140 responds to the sampling command and samples the sampling position to obtain a sampled image containing part of the workpiece. This process is repeated to obtain the sampled image obtained at each sampling position. Then, all the sampled images are stitched together to form a target image containing the complete workpiece.

[0037] For example, taking four sampling positions as an example, the four sampling positions can include the upper left sampling position, the upper right sampling position, the lower left sampling position, and the lower right sampling position. According to the position of these four sampling positions in the coordinate system of the vision measurement platform, the platform is moved to the upper left sampling position, the upper right sampling position, the lower left sampling position, and the lower right sampling position in sequence. The vision module samples the upper left image, the upper right image, the lower left image, and the lower right image at each sampling position, and then stitches the upper left image, the upper right image, the lower left image, and the lower right image together to form the target image.

[0038] In some embodiments of this application, the drive module 110 is used to provide driving force to the guide module 120. The drive module 110 may include an X-axis drive system (not shown in the figure), a Y-axis drive system (not shown in the figure), and a Z-axis drive system (not shown in the figure). The X-axis drive system is used to provide driving force in the X-axis direction, the Y-axis drive system is used to provide driving force in the Y-axis direction, and the Z-axis drive system is used to provide driving force in the Z-axis direction.

[0039] In some embodiments of this application, the guide module 120 is used to constrain the movement direction of the loading platform 130 and improve the movement accuracy of the loading platform 130. The drive module 110 may specifically include an X-axis drive system, a Y-axis drive system and a Z-axis drive system. Correspondingly, the guide module 120 may include an X-axis guide system (not shown in the figure), a Y-axis guide system (not shown in the figure) and a Z-axis guide system (not shown in the figure). The X-axis drive system is used to provide driving force for the X-axis guide system, the Y-axis drive system is used to provide driving force for the Y-axis guide system and the Z-axis drive system is used to provide driving force for the Z-axis guide system.

[0040] In some embodiments of this application, the loading platform 130 moves under the guidance of the guide module 120. The X-axis guide system moves the loading platform 130 along the X-axis direction, the Y-axis guide system moves the loading platform 130 along the Y-axis direction, and the Z-axis guide system moves the loading platform 130 along the Z-axis direction.

[0041] In some embodiments of this application, when the vision module 140 receives a control command sent by the control module 150, it responds to the control command and samples the workpiece placed on the platform 130. When the control module 150 controls the drive module 110 to drive the guide module 120, and the platform 130 moves to the sampling position each time, it sends a sampling command to the vision module 140. Thus, the platform 130 receives a control command sent by the control module 150 every time it moves to a sampling position, and then responds to the sampling command at each sampling position to sample the workpiece to obtain a sampled image containing different parts of the workpiece. Finally, the control module 150 stitches together all the sampled images, that is, it stitches together the different parts of the workpiece contained in the different sampled images to obtain a target image containing the complete workpiece.

[0042] Specifically, the vision module 140 in this embodiment may include components such as a lens, camera, light source, lens mount, lens adjustment component, light source mounting adjustment component, image acquisition and receiving module, and light source controller. The image acquisition and receiving module and the light source controller can be integrated or embedded in the control module 150, thereby ensuring that the control module 150 acquires sampled images in a timely manner and stitches them together. It should be understood that the components of the vision module 140 described above are merely an illustrative example in this embodiment and do not limit the specific structure of the vision module 140 in this embodiment.

[0043] refer to Figure 1 As shown, the visual measurement platform in this embodiment also includes a measurement module 160. When the loading platform 130 moves to each sampling position, the measurement module 160 reads the actual displacement distance of the loading platform and returns the actual displacement distance to the control module 150.

[0044] The control module 150 inputs the actual displacement distance into a preset piecewise exponential calibration model to obtain the compensated displacement distance. Based on the compensated displacement distance, it controls the drive module 110 to drive the guide module 120, thereby causing the loading platform 130 to perform displacement compensation. After completing the displacement compensation, a sampling command is sent to the vision module 140.

[0045] In some embodiments of this application, the measurement module 160 may include an X-axis measurement system, a Y-axis measurement system, and a Z-axis measurement system. The X-axis measurement system is used to read the actual displacement distance of the platform 130 moving in the X-axis direction, the Y-axis measurement system is used to read the actual displacement distance of the platform 130 moving in the Y-axis direction, and the Z-axis measurement system is used to read the actual displacement distance of the platform 130 moving in the Z-axis direction. Each of the X-axis, Y-axis, and Z-axis measurement systems may include corresponding scales, reading heads, scale mounting bases, reading head mounting adjusters, and counting collectors. It should be understood that the components of the measurement module 160 described above are merely an exemplary illustration in this embodiment and are not intended to limit the specific structure of the measurement module 160 in this embodiment.

[0046] In some embodiments of this application, the piecewise exponential calibration model employs a precision correction method for nonlinear measurement systems (such as sensors), which can divide the entire measurement range of the system into multiple sub-intervals. Each sub-interval uses an independent exponential function to fit the relationship between the true value and the system output value, ultimately achieving high-precision calibration across the entire range and solving the problem that a single model cannot cover the nonlinear error across the entire range.

[0047] Specifically, the piecewise index calibration model in this embodiment may include a calibration model corresponding to the X-axis direction, a calibration model corresponding to the Y-axis direction, and a calibration model corresponding to the Z-axis direction. When the platform 130 moves to one of the sampling positions, the measurement module 160 obtains the actual movement distance of the platform 130 in the X-axis, Y-axis, and Z-axis directions, respectively. Then, the actual movement distances in the X-axis, Y-axis, and Z-axis directions are input into the corresponding piecewise index calibration models to obtain the corresponding compensated displacement distances in the X-axis, Y-axis, and Z-axis directions. Based on the compensated displacement distances, the control drive module drives the guide module, causing the platform to perform displacement compensation in the X-axis, Y-axis, and Z-axis directions, respectively. After completing the displacement compensation, a sampling command is sent to the vision module.

[0048] Based on the above, this embodiment constructs a piecewise index calibration model to obtain the corresponding compensation displacement distances of the loading platform in the X-axis, Y-axis and Z-axis directions, respectively. Then, the position of the loading platform is compensated based on the compensation displacement distance, which reduces the impact of equipment error on measurement accuracy and helps to improve the measurement accuracy of the measuring equipment.

[0049] refer to Figure 2 The diagram shown is a flowchart of a calibration data acquisition method provided in one embodiment of this application. This method is applied to the visual measurement platform provided in any of the above embodiments. Figure 2 The flowchart shown includes the following steps: S201: Obtain the calibration image obtained by the visual measurement platform after sampling the target calibration board, wherein the target calibration board includes a first number of calibration marks.

[0050] In some embodiments of this application, the shape of the calibration marks in the target calibration plate includes any one of the shapes such as circle, square, and triangle, and the number of calibration marks in the target calibration plate can be 16, 64, etc. This embodiment does not limit the shape and number of calibration marks in the target calibration plate. (Reference) Figure 3 The diagram shown is a schematic of a target calibration board provided in an embodiment of this application. The calibration marks in the calibration board are solid circular marks, which are evenly distributed to form a corresponding mark matrix. For example, if there are 16 calibration marks in the target calibration board, the 16 calibration marks can form a 4*4 mark matrix.

[0051] Specifically, in this embodiment, the target calibration board can be sampled by the vision module of the vision measurement platform to obtain a calibration image. When the target calibration board is large, the platform of the vision measurement platform can be moved to different sampling positions to facilitate the vision module to sample different positions of the target calibration board and obtain sampling images at different positions. The sampling images at different positions are then stitched together to form a calibration image.

[0052] In this embodiment, unique feature points can be extracted from sampled images at different locations using feature algorithms such as Scale-Invariant Feature Transform (SIFT) and Speeded-Up Robust Features (SURF). Then, matching feature pairs between different images are selected from the feature points using metrics such as Euclidean distance and Hamming distance, providing a basis for subsequent alignment. Based on the matching feature pairs, the spatial transformation relationship between images (such as homography matrix, affine transformation, etc.) is calculated to achieve accurate image alignment. Finally, if there are overlapping areas in the aligned images, the stitching traces are eliminated using methods such as weighted average fusion and multi-band fusion to obtain the calibration image.

[0053] S202: Divide the calibration image into a second number of image regions according to the calibration identifier.

[0054] In some embodiments of this application, the sampled image can be divided into a second number of image regions based on a first number of calibration marks according to a preset region division rule. The number of calibration marks in each image region is the same, and the number of calibration marks in each image region is determined according to the size of the first number.

[0055] For example, taking a target calibration board with 16 calibration marks as an example, the 16 calibration marks can form a 4*4 mark matrix. Then, the four calibration marks in the upper left corner are divided into one image region, the four calibration marks in the upper right corner are divided into one image region, the four calibration marks in the lower left corner are divided into one image region, and the four calibration marks in the lower right corner are divided into one image region. Thus, the sampled image can be divided into 4 image regions, and each image region contains a 2*2 mark matrix.

[0056] refer to Figure 3 The diagram shown is a structural schematic of a target calibration plate in this embodiment. The calibration marks in the target calibration plate are circular marks, and there are a total of 60 calibration marks, which are equidistantly distributed on the target calibration plate.

[0057] S203: Obtain the linear coefficient matrix and nonlinear coefficient matrix of each image region, and based on the linear coefficient matrix and nonlinear coefficient matrix, obtain the region calibration matrix of each image region.

[0058] In some embodiments of this application, a corresponding linear coefficient matrix can be obtained for each image region. This linear coefficient matrix can be an affine transformation matrix, used to compensate for errors in the corresponding image region, such as translation, rotation, and scaling. Specifically, in this embodiment, linear feature points can first be extracted from the image region, and then the linear transformation relationship between these linear feature points can be solved to obtain the linear coefficient matrix. The method for solving for linear feature points can be the least squares method, and so on, to obtain the linear coefficient matrix for each image region. In this embodiment, linear feature points can be extracted from the image region using the Hough transform algorithm and a corner detection algorithm.

[0059] In some embodiments of this application, a corresponding nonlinear coefficient matrix can be obtained for each image region. The nonlinear coefficient matrix can be a quadratic nonlinear coefficient matrix, which is used to compensate for the corresponding image region, such as to compensate for deformation and curvature errors.

[0060] Specifically, in this embodiment, nonlinear feature points can first be extracted from the image region. Then, based on the distorted and undistorted coordinates of the nonlinear feature points, the distorted and undistorted coordinates are substituted into a quadratic nonlinear model to obtain a quadratic nonlinear equation containing distortion coefficients. Finally, the sum of squared errors of the distorted and undistorted coordinates is minimized using the least squares method to solve for all coefficients, resulting in a nonlinear coefficient matrix. The undistorted coordinates can be obtained from a preset undistorted image containing the target calibration board, or they can be preset according to the actual size of the target calibration board. This embodiment does not limit the method of obtaining the undistorted coordinates. In this embodiment, nonlinear feature points can be extracted from the image region using a contour curvature analysis algorithm.

[0061] In some embodiments of this application, the linear coefficient matrix and the nonlinear coefficient matrix are vector-superimposed to obtain the region calibration matrix of each image region. The region calibration matrix corresponding to each image region is only used to correct or compensate the corresponding image region.

[0062] The equation used to calculate the region calibration matrix in this embodiment is as follows: In the above equation: Represents the region calibration matrix; Represents a linear coefficient matrix; Represents the nonlinear coefficient matrix; Indicates the first Image regions; This indicates that the above method is in the first... Only one image region is valid.

[0063] S204: Based on the region calibration matrix, generate the distortion calibration matrix of the target image. The distortion correction matrix is ​​used to correct the distortion of the target image containing the workpiece.

[0064] In some embodiments of this application, the region calibration matrix in this embodiment is only used to correct the corresponding image region, and cannot correct the entire sampled image. Therefore, after calculating the region calibration matrix of each image region, the region calibration matrices together constitute the distortion calibration matrix of the entire target image.

[0065] When correcting a target image based on a distortion calibration matrix, the target image can be divided into multiple regions to be corrected according to a preset partitioning rule. Each region to be corrected has a mapping relationship with a specific image region; for example, the position of the region to be corrected in the target image corresponds to the position of the image region in the calibration image. Then, based on the correspondence between the regions to be corrected and the image regions, the region calibration matrix corresponding to each region to be corrected is obtained from the distortion calibration matrix. The corresponding regions to be corrected are then corrected based on the region calibration matrix, and the corrected regions are re-stitched into the target image through weighted smoothing to obtain the corrected target image.

[0066] Based on the above, this embodiment calculates a distortion calibration matrix to correct the distortion of the target image containing the workpiece when the vision measurement device measures the workpiece, and to compensate for curvature error, translation error, rotation error and scaling error of the regional image, thereby improving the image accuracy. Based on the corrected target image, workpiece measurement is beneficial to improving measurement accuracy.

[0067] refer to Figure 4 The diagram shown is a flowchart of the calibration data acquisition method provided in an embodiment of this application, which includes the following steps for obtaining the first geometric correction matrix: S401: Obtain the first center coordinates of each calibration marker in the calibration image, and construct the first coordinate matrix based on the first center coordinates.

[0068] In some embodiments of this application, the first center coordinates of the calibration mark can be the world coordinates obtained by converting the pixel coordinates of the center position of the calibration mark. For example, if the calibration mark is a circular mark, the first center coordinates are the world coordinates of the center position of the circular mark. After obtaining the first center coordinates of each calibration mark, a first coordinate matrix is ​​constructed based on the first center coordinates of each calibration mark.

[0069] S402: Obtain the preset second center coordinates corresponding to each calibration mark, and construct the second coordinate matrix based on the second center coordinates.

[0070] In some embodiments of this application, the preset second center coordinates corresponding to each calibration mark are the real-world coordinates of the center position of each calibration mark. In this embodiment, the second center coordinates can be obtained based on a distortion-free real image. The pixel coordinates of the center position of each calibration mark are extracted from the real image, and then the real-world coordinates are obtained based on the pixel coordinates. A second coordinate matrix is ​​constructed based on the second center coordinates of each calibration mark.

[0071] S403: Based on the first coordinate matrix and the second coordinate matrix, the first geometric correction matrix is ​​calculated. The first geometric correction matrix is ​​used to perform geometric correction on the target image after distortion correction to obtain the corrected image.

[0072] In a specific implementation, this embodiment can subtract the elements at corresponding positions in the first coordinate matrix and the second coordinate matrix to obtain the first geometric correction matrix. The coordinates in the first coordinate matrix and the second coordinate matrix are three-dimensional coordinates, and the calculated first geometric correction matrix is ​​also a three-dimensional coordinate matrix. However, when correcting the target image based on the first geometric correction matrix, the pixel coordinates of the target image are corrected, and pixel coordinates are two-dimensional coordinates. Therefore, when correcting the target image based on the first geometric correction matrix, usually only the horizontal and vertical coordinates of the three-dimensional coordinate system are used.

[0073] In some embodiments of this application, each differential coordinate in the first geometric correction matrix is ​​used to perform geometric correction only on the corresponding image region. That is, the differential coordinates corresponding to the first center coordinates of the calibration mark in the calibration image are used to correct the region in the target image that corresponds to the region where the calibration mark is located. By analogy, the whole image of the target image is corrected based on the first geometric correction matrix to obtain the corrected image.

[0074] Based on the above, this embodiment calculates a first geometric correction matrix for geometric correction of the target image, which can achieve the technical effect of accurately eliminating geometric distortion of the target image and restoring the true spatial structure of the target image. This can provide a reliable data foundation for subsequent workpiece measurement and help improve the accuracy of workpiece measurement.

[0075] refer to Figure 5 The flowchart shown is a process for obtaining the preset first center coordinates corresponding to each calibration identifier according to an embodiment of this application. It specifically includes the following steps: S501: Obtain the center pixel coordinates of each calibration mark.

[0076] In some embodiments of the application, the center pixel coordinates of the calibration mark can be the pixel coordinates of the center position of the calibration mark.

[0077] In this specific implementation, an appropriate detection algorithm can be selected based on the shape of the calibration mark (such as a circle, a crosshair, etc.) to extract the center pixel coordinates of each calibration mark from the target image. For example, the Hough Circle Transform detection algorithm is used to extract the preliminary center coordinates from the circular mark, and then the preliminary center coordinates are located using a sub-pixel localization algorithm based on grayscale values ​​to obtain the center pixel coordinates.

[0078] S502: Based on the camera intrinsics of the vision measurement platform, it converts the coordinates of each center pixel into the image coordinates of each calibration marker in the calibration image.

[0079] In some embodiments of this application, the camera intrinsic parameters of the vision measurement platform can be the camera intrinsic parameters of the vision module. Camera intrinsic parameters are a set of parameters describing the optical and geometric characteristics of the camera itself. They do not change with the camera's position or orientation in space, but are determined solely by the camera hardware, and are the core basis for establishing the mapping between pixel coordinates and physical space coordinates. Camera intrinsic parameters include focal length and principal point coordinates. The focal length represents the equivalent focal length of the camera in the x-axis (horizontal) and y-axis (vertical) directions, and the principal point coordinates represent the projection position of the camera's optical principal axis (lens center axis) onto the image sensor, corresponding to the origin of the image coordinate system. Based on the camera intrinsic parameters of the vision measurement platform, the coordinates of each center pixel are converted into the image coordinates of each calibration marker in the calibration image.

[0080] The camera intrinsic parameters in this embodiment can be as follows: Among the aforementioned camera internal parameters, This represents the camera's equivalent focal length along the x-axis (horizontal) direction. This represents the camera's equivalent focal length along the y-axis (vertical) direction. and It represents the projection position of the camera's optical axis (lens center axis) onto the image sensor, corresponding to the origin of the image coordinate system.

[0081] Based on the aforementioned camera intrinsic parameters, the conversion formula for transforming the coordinates of each center pixel into the image coordinates of each calibration marker in the calibration image is as follows: In the above formula, Represents the depth in the camera coordinate system. Represents image coordinates, Indicates camera intrinsic parameters. Represents pixel coordinates.

[0082] S503: Based on the camera extrinsic parameters of the vision measurement platform, it converts each image coordinate into the first center coordinate of each calibration mark.

[0083] In some embodiments of this application, the camera extrinsic parameters of the visual measurement platform are a set of parameters describing the position and orientation of the camera in the world coordinate system. These parameters change with the movement and rotation of the camera, and their core function is to establish a spatial mapping relationship between the camera coordinate system and the world coordinate system. The camera extrinsic parameters include a rotation matrix (R) and a translation vector (T). The rotation matrix describes the camera's orientation (angle), representing the direction of rotation of the camera coordinate system relative to the world coordinate system, and is used to eliminate angular deviations between the two coordinate systems. The translation vector describes the camera's position (displacement), representing the translation distance of the origin of the camera coordinate system relative to the origin of the world coordinate system, and is used to eliminate positional deviations between the two coordinate systems.

[0084] The camera extrinsic parameters in this embodiment can be as follows: Among the aforementioned camera extrinsics, Represents the rotation matrix. This represents the translation vector.

[0085] Based on the aforementioned camera extrinsic parameters, the transformation formula for converting each image coordinate to the first center coordinate of each calibration mark is as follows: In the above formula, Represents the depth in the camera coordinate system. Represents image coordinates, Indicates camera intrinsic parameters. Represents pixel coordinates, Indicates camera external parameters. Represents a three-dimensional point in the world coordinate system (homogeneous coordinate form).

[0086] refer to Figure 6 The diagram shown is a flowchart of obtaining the second geometric correction matrix according to an embodiment of this application, which specifically includes the following steps: S601: Obtain the center pixel coordinates of each calibration mark in each image region.

[0087] In some embodiments of the application, the center pixel coordinates of the calibration mark can be the pixel coordinates of the center position of the calibration mark.

[0088] In this specific implementation, an appropriate detection algorithm can be selected based on the shape of the calibration mark (such as a circle, a crosshair, etc.) to extract the center pixel coordinates of each calibration mark from the target image. For example, the Hough Circle Transform detection algorithm is used to extract the preliminary center coordinates from the circular mark, and then the preliminary center coordinates are located using a sub-pixel localization algorithm based on gray-scale moments to obtain the center pixel coordinates.

[0089] S602: Calculate the first center distance for each image region based on the coordinates of each center pixel.

[0090] In some embodiments of this application, the coordinates of each center pixel can be transformed into center world coordinates in the world coordinate system using camera intrinsic and extrinsic parameters, and then a first center distance can be calculated based on the center world coordinates. The first center distance can be the distance between two adjacent center world coordinates.

[0091] Specifically, in this embodiment, the first center distance includes the horizontal center distance and the vertical center distance. Therefore, the vertical center distance can be calculated based on the world coordinates of two adjacent centers (vertical and horizontal), and the horizontal center distance can be calculated based on the world coordinates of two adjacent centers (left and right), and so on, to calculate the first center distance corresponding to each image region. Specifically, in this embodiment, the vertical center distance is obtained by subtracting the coordinates of two adjacent center pixels, and the horizontal center distance is obtained by subtracting the coordinates of two adjacent center pixels.

[0092] S603: Based on each first center distance and each preset second center distance, calculate the center distance ratio of each image region.

[0093] In some embodiments of this application, each preset second center distance can be the physical distance between the centers of two adjacent calibration marks on the target calibration board, which can be specifically measured from the target calibration board. The second center distance includes the horizontal axis center distance and the vertical axis center distance. Therefore, the physical distance between the centers of two vertically adjacent calibration marks can be measured as the vertical axis center distance, and the physical distance between the centers of two horizontally adjacent calibration marks can be measured as the horizontal axis center distance.

[0094] In a specific implementation, this embodiment can use the ratio of the first center distance to each corresponding second center distance as the center distance ratio. The center distance ratio includes the horizontal axis ratio and the vertical axis ratio. The horizontal axis ratio is the ratio of the horizontal axis distance in the first center distance to the horizontal axis distance in the second center distance, and the vertical axis ratio is the ratio of the vertical axis distance in the first center distance to the vertical axis distance in the second center distance.

[0095] refer to Figure 7 The diagram shown is a schematic of the second center distance provided in an embodiment of this application, wherein Sx represents the horizontal center distance in the second center distance, Sy represents the vertical center distance in the second center distance, and Pt represents one of the coordinates that needs to be corrected.

[0096] S604: Based on the distance ratio of each center, construct a second geometric correction matrix. The second geometric correction matrix is ​​used to perform geometric correction on the distortion-corrected target image to obtain the corrected image.

[0097] In some embodiments of this application, the second geometric correction matrix includes the center distance ratios of all image regions. When correcting the target image based on the second geometric correction matrix, each center distance ratio can only correct the corresponding region in the target image.

[0098] Specifically, in this embodiment, when calibrating the target image, the target image can first be divided into a region to be calibrated of a preset size, which corresponds to the image region of the calibration image. Then, each pixel coordinate in the region to be calibrated is converted into world coordinates. The horizontal coordinate of each world coordinate is multiplied by the horizontal coordinate ratio, and the vertical coordinate of each world coordinate is multiplied by the vertical coordinate ratio to obtain the calibration coordinates. Each calibration coordinate is converted into pixel coordinates to complete the calibration of the region to be calibrated. This process is repeated to complete the calibration of each region to be calibrated. The calibrated regions to be calibrated are then re-stitched to obtain the calibrated image.

[0099] Based on the above, after the distortion correction of the target image is performed based on the distortion calibration matrix, the distortion correction target image can be geometrically corrected based on the second geometric correction matrix, and / or the distortion correction target image can be geometrically corrected based on the first geometric correction matrix. This embodiment does not impose any limitations.

[0100] refer to Figure 8 The diagram shown is a flowchart of constructing a translational piecewise exponential model according to an embodiment of this application, which specifically includes the following steps: S801: Obtain the translation range of the platform in the visual measurement platform and divide the translation range into multiple translation intervals.

[0101] In some embodiments of this application, the translation range of the loading platform can be the translation range along the Z-axis direction of the visual measurement platform. When determining the translation range, the translation range is divided into multiple translation intervals according to a preset interval length.

[0102] For example, taking the translation range in the Z-axis direction as (0,100) as an example, the interval length is 20. The translation range (0,100) can be divided into (0,20), (20,40), (40,60), (60,80), and (80,100) as 5 translation intervals. Similarly, the translation range in each direction can be further divided into multiple corresponding translation intervals.

[0103] S802: Obtain the actual translation distance of the cargo platform within each translation interval.

[0104] In some embodiments of this application, the control module of the visual measurement platform can control the platform to move according to multiple preset translation distances within each translation interval. After the platform moves according to the interval translation distance, the measurement module obtains the actual movement distance of the platform. However, due to aging and wear from prolonged use, the actual translation distance obtained after the control module controls the platform to move according to the interval translation distance will inevitably have a certain error compared to the actual translation distance.

[0105] Specifically, in this embodiment, the measurement module may include a laser interferometer, which measures the actual distance the platform moves after moving according to a preset translation distance.

[0106] S803: Based on the actual translation distance and the preset interval translation distance, the translation error of the cargo platform in each translation interval is calculated.

[0107] Specifically, in this embodiment, the difference between the actual translation distance and the preset interval translation distance can be calculated, and the corresponding translation error can be calculated. Similarly, multiple translation errors within each translation interval can be calculated.

[0108] S804: Based on the translation error fitting error distribution within each translation interval, construct a piecewise exponential translation model.

[0109] In the embodiments of this application, the error distribution is a functional relationship distribution between the translation error and the actual translation distance. Multiple translation errors can be calculated based on each translation interval, and the error distribution within each translation interval can be fitted using an exponential function. Finally, a piecewise exponential translation model is constructed based on the error distribution within each translation interval.

[0110] refer to Figure 9 The diagram shown is a flowchart of constructing a vertical segmented exponential model according to an embodiment of this application, which specifically includes the following steps: S901: Obtain the vertical value of the platform in each translation interval.

[0111] In some embodiments of this application, the vertical value, at a single measurement point within a translation interval, quantifies the specific numerical value of the deviation between the actual vertical state of the platform and the Z-axis and the ideal vertical state. Each translation interval can have multiple measurement points, and each measurement point acquires a corresponding vertical value. The vertical value can include any one or more of the following: the X-axis vertical value between the platform and the Z-axis in the X-axis direction, and the Y-axis vertical value between the platform and the Z-axis in the Y-axis direction. When both X-axis and Y-axis vertical values ​​are included, a piecewise exponential model corresponding to the X-axis and a vertical piecewise exponential model corresponding to the Y-axis can be constructed respectively.

[0112] Specifically, in this embodiment, the laser head of a laser interferometer, an optical right-angle ruler, and a straightness reflector group can be used to measure the vertical value. The laser head of the laser interferometer is used to emit a highly stable parallel laser as a reference line for measurement. The optical right-angle ruler provides a standard 90° orthogonal reference (with an accuracy typically up to 0.001°) for calibrating the vertical relationship of the laser beam path. The straightness reflector group includes a straightness reflector (fixed on the platform) and a reading head, which reflects the laser and feeds back the displacement deviation, recording the vertical value at different translation positions.

[0113] S902: Based on the vertical value within each translation interval, calculate the verticality of each translation interval and construct a vertical segmented index model.

[0114] In some embodiments of this application, verticality refers to the overall evaluation result of the vertical state of the loading platform within each translation interval.

[0115] In a specific implementation, this embodiment can calculate the verticality of each translation interval based on the vertical value within each translation interval using the least squares method, and construct a vertical segmented exponential model based on the verticality of each translation interval.

[0116] Please see Figure 10 This is a schematic diagram illustrating an application scenario of the calibration data acquisition method provided in an embodiment of this application.

[0117] This application provides a calibration data acquisition method that can be applied to a measuring device 10. The measuring device 10 is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions. Its hardware includes, but is not limited to, microprocessors, application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital signal processors (DSPs), embedded devices, etc.

[0118] Specifically, the measuring device 10 is used to: acquire a calibration image obtained by the vision measuring platform after sampling the target calibration plate, calculate calibration data based on the calibration image, and use the calibration data to correct the target image containing the workpiece acquired by the measuring device, so as to improve the measurement accuracy of the measuring device on the workpiece.

[0119] In some embodiments of this application, the measuring device 10 can be communicatively connected to devices such as desktop computers, laptops, handheld computers, and cloud servers.

[0120] In some embodiments of this application, the measuring device 10 can interact with the user via a keyboard, mouse, remote control, touchpad, or voice control device.

[0121] In some embodiments of this application, the measuring device 10 may further include network devices and / or client devices. These network devices include, but are not limited to, a single network server, a server group consisting of multiple network servers, or a cloud server based on cloud computing, consisting of a large number of hosts or network servers.

[0122] In some embodiments of this application, the network where the measuring device 10 is located includes, but is not limited to, the Internet, wide area network, metropolitan area network, local area network, virtual private network (VPN), etc.

[0123] Combination Figure 10 As shown, in some embodiments of this application, the measuring device 10 includes, but is not limited to, a memory 11, a processor 12, and a computer program stored in the memory 11 and executable on the processor 12, such as a calibration data acquisition program. When the computer program is executed by the processor, it implements the calibration data acquisition method as described in the above embodiments.

[0124] Figure 10 Only the measuring device 10, which has a memory 11 and a processor 12, is shown. Those skilled in the art will understand that... Figure 1 The structure shown does not constitute a limitation on the measuring device 10, and may include fewer or more components than shown, or combine certain components, or have different component arrangements.

[0125] The memory 11 in the measuring device 10 stores multiple computer-readable instructions to implement a calibration data acquisition method. The processor 12 can execute multiple instructions to achieve: acquiring a calibration image obtained by the vision measurement platform after sampling the target calibration plate, calculating calibration data based on the calibration image, and using it to correct the target image containing the workpiece acquired by the measuring device, so as to improve the measurement accuracy of the measuring device on the workpiece.

[0126] Specifically, the processor 12's implementation method for the above instructions can be found in [reference needed]. Figure 2 The descriptions of the relevant steps in the corresponding embodiments are not repeated here.

[0127] Those skilled in the art will understand that the schematic diagram is merely an example of the measuring device 10 and does not constitute a limitation on the measuring device 10. The measuring device 10 can be a bus-type structure or a star-type structure. The measuring device 10 may also include more or fewer other hardware or software than shown in the diagram, or different component arrangements. For example, the measuring device 10 may also include input / output devices, network access devices, etc.

[0128] The measuring device 10 described above is merely an example. Other existing or future measuring devices that are suitable for this application should also be included within the scope of protection of this application and are incorporated herein by reference.

[0129] The memory 11 includes at least one type of computer-readable storage medium, which can be non-volatile or volatile. Computer-readable storage media include flash memory, portable hard drives, multimedia cards, card-type memory (e.g., SD memory, DX memory, etc.), magnetic memory, magnetic disks, optical disks, etc. In some embodiments, the memory 11 can be an internal storage unit of the measuring device 10, such as the portable hard drive of the measuring device 10. In other embodiments, the memory 11 can also be an external storage device of the measuring device 10, such as a plug-in portable hard drive, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the measuring device 10. The memory 11 can be used not only to store application software and various types of data installed on the measuring device 10, such as the code of a calibration data acquisition program, but also to temporarily store data that has been output or will be output.

[0130] In some embodiments, the processor 12 may be composed of integrated circuits, such as a single packaged integrated circuit or multiple integrated circuits packaged with the same or different functions, including combinations of one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips. The processor 12 is the control unit of the measuring device 10, connecting various components of the measuring device 10 through various interfaces and lines. It executes programs or modules stored in the memory 11 (e.g., executing a calibration data acquisition program) and calls data stored in the memory 11 to perform various functions of the measuring device 10 and process data.

[0131] The processor 12 executes the operating system of the measuring device 10 and various installed applications. The processor 12 executes these applications to implement the steps described in each of the above embodiments of the calibration data acquisition method, for example... Figure 2 The steps are shown.

[0132] For example, a computer program may be divided into one or more modules / units, one or more of which are stored in memory 11 and executed by processor 12 to complete this application. One or more modules / units may be a series of computer-readable instruction segments capable of performing a specific function, which describe the execution process of the computer program in measuring device 10. For example, the computer program may be divided into an acquisition module 110, a determination module 120, and a compensation module 130.

[0133] The integrated unit implemented as a software functional module described above can be stored in a computer-readable storage medium. This software functional module, stored in a storage medium, includes several instructions to cause a computer device (which may be a personal computer, computer equipment, or network device, etc.) or processor to execute a portion of a calibration data acquisition method according to various embodiments of this application.

[0134] If the modules / units integrated into the measuring device 10 are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments can also be implemented by a computer program instructing related hardware devices. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above.

[0135] Computer programs include computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. Computer-readable media can include: any entity or device capable of carrying computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory, and other types of memory.

[0136] Furthermore, the computer-readable storage medium may primarily include a stored program area and a stored data area, wherein the stored program area may store the operating system, an application program required for at least one function, etc.; and the stored data area may store data created based on the use of blockchain nodes, etc.

[0137] The bus can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This bus can be divided into address bus, data bus, control bus, etc. For ease of representation, in... Figure 1 The symbol is represented by only one arrow, but this does not mean that there is only one bus or one type of bus. The bus is configured to implement communication between memory 11 and at least one processor 12, etc.

[0138] This application also provides a computer-readable storage medium (not shown), which stores computer-readable instructions that are executed by a processor in an electronic device to implement a calibration data acquisition method of any of the above embodiments.

[0139] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and other division methods may be used in actual implementation.

[0140] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0141] Furthermore, the functional modules in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional modules.

[0142] Furthermore, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices described in the specification may also be implemented by a single unit or device through software or hardware. Terms such as "first," "second," etc., are used to indicate names and do not indicate any specific order.

[0143] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application and are not intended to limit it. Although this application has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of this application without departing from the spirit and scope of the technical solutions of this application.

Claims

1. A vision measurement platform, characterized by, The vision measurement platform includes: a drive module, a guide module, a loading platform, a vision module, and a control module, wherein: The control module controls the drive module to drive the guide module according to each preset positioning coordinate, so that the platform moves sequentially to each corresponding sampling position, and sends sampling instructions to the vision module when the platform moves sequentially to each sampling position. The vision module responds sequentially to each sampling command, samples the workpiece to be measured placed on the platform to obtain a sampling image of the workpiece at each sampling position, and samples the target calibration plate to obtain a calibration image; the sampling image and the calibration image are returned to the control module, wherein the sampling image displays at least a portion of the workpiece. The control module divides the calibration image into a second number of image regions based on a first number of calibration markers in the calibration image; extracts linear feature points from the image regions, solves the linear transformation relationship between the linear feature points to obtain a linear coefficient matrix; extracts nonlinear feature points from the image regions, substitutes the distorted and undistorted coordinates of the nonlinear feature points into a quadratic nonlinear model to obtain a quadratic nonlinear equation containing distortion coefficients, minimizes the sum of squared errors of the distorted and undistorted coordinates using the least squares method to obtain a nonlinear coefficient matrix; based on the linear coefficient matrix and the nonlinear coefficient matrix, obtains the region calibration matrix for each image region; based on the region calibration matrix, generates a distortion calibration matrix; and obtains the first center coordinates of each calibration marker in the calibration image. The center coordinates are the pixel coordinates of the center position of the calibration mark, converted to world coordinates; and a first coordinate matrix is ​​constructed based on the first center coordinates; a preset second center coordinates are obtained for each calibration mark, the second center coordinates are the pixel coordinates of the center position of the calibration mark in the real image, converted to world coordinates; and a second coordinate matrix is ​​constructed based on the second center coordinates; the elements at corresponding positions in the first coordinate matrix and the second coordinate matrix are subtracted to obtain a first geometric correction moment; multiple sampled images are stitched together to form a target image, the target image is distorted according to the distortion calibration matrix, and the distorted target image is geometrically corrected according to the first geometric correction matrix to obtain a corrected image; the workpiece is measured based on the corrected image to obtain the measurement result of the workpiece.

2. The visual measurement platform as described in claim 1, characterized in that, The visual measurement platform also includes a metrology module: The metering module reads the actual displacement distance of the platform when the platform moves to each sampling position, and returns the actual displacement distance to the control module. The control module inputs the actual displacement distance into a preset piecewise index calibration model to obtain a compensated displacement distance. Based on the compensated displacement distance, it controls the drive module to drive the guide module, thereby causing the platform to perform displacement compensation. After completing the displacement compensation, a sampling command is sent to the vision module. The piecewise index calibration model includes a translational piecewise index model and a vertical piecewise index model. Constructing the translational piecewise index model includes: obtaining the translation range of the platform in the vision measurement platform and dividing the translation range into multiple translation intervals; obtaining the actual translation distance of the platform in each translation interval; calculating the translation error of the platform in each translation interval based on the actual translation distance and the preset interval translation distance; fitting the error distribution based on the translation error in each translation interval to construct the translational piecewise index model. Constructing the vertical piecewise index model includes: obtaining the vertical value of the platform in each translation interval; calculating the verticality of each translation interval based on the vertical value in each translation interval to construct the vertical piecewise index model.

3. A method for acquiring calibration data, characterized in that, The method, applied to the visual measurement platform of any one of claims 1 to 2, comprises: The calibration image obtained by the visual measurement platform after sampling the target calibration board is acquired, wherein the target calibration board includes a first number of calibration marks; Based on the calibration identifier, the calibration image is divided into a second number of image regions; Obtain the linear coefficient matrix and nonlinear coefficient matrix of each image region, and based on the linear coefficient matrix and the nonlinear coefficient matrix, obtain the region calibration matrix of each image region; Based on the region calibration matrix, a distortion calibration matrix is ​​generated, which is used to correct the distortion of the target image containing the workpiece.

4. The calibration data acquisition method as described in claim 3, characterized in that, The method further includes: Obtain the first center coordinates of each calibration marker in the calibration image, and construct a first coordinate matrix based on the first center coordinates; Obtain the preset second center coordinates corresponding to each calibration identifier, and construct a second coordinate matrix based on the second center coordinates; Based on the first coordinate matrix and the second coordinate matrix, a first geometric correction matrix is ​​calculated. The first geometric correction matrix is ​​used to perform geometric correction on the target image after distortion correction to obtain a corrected image.

5. The calibration data acquisition method as described in claim 4, characterized in that, Obtaining the first center coordinates of each calibration marker in the calibration image includes: Obtain the center pixel coordinates of each calibration identifier; Based on the camera intrinsic parameters of the visual measurement platform, the coordinates of each center pixel are converted into the image coordinates of each calibration marker in the calibration image; Based on the camera extrinsics of the visual measurement platform, each image coordinate is converted into the first center coordinate of each calibration mark.

6. The calibration data acquisition method as described in claim 3, characterized in that, The method further includes: Obtain the center pixel coordinates of each calibration marker in each image region; Based on the coordinates of each center pixel, calculate the first center distance for each corresponding image region; Based on each first center distance and each preset second center distance, the center distance ratio of each image region is calculated; Based on the center distance ratio, a second geometric correction matrix is ​​constructed. This second geometric correction matrix is ​​used to perform geometric correction on the distortion-corrected target image to obtain a corrected image.

7. The calibration data acquisition method according to any one of claims 3 to 6, characterized in that, The piecewise exponent calibration model includes a translational piecewise exponent model, and the method further includes: Obtain the translation range of the platform in the visual measurement platform, and divide the translation range into multiple translation intervals; Obtain the actual translation distance of the loading platform within each translation interval; Based on the actual translation distance and the preset interval translation distance, the translation error of the loading platform in each translation interval is calculated; The translation piecewise exponential model is constructed based on the translation error fitting error distribution within each translation interval.

8. The calibration data acquisition method as described in claim 7, characterized in that, The piecewise index calibration model further includes a vertical piecewise index model. After obtaining the translation range of the platform in the visual measurement platform and dividing the translation range into multiple translation intervals, the method further includes: Obtain the vertical value of the loading platform within each translation interval; Based on the vertical value within each translation interval, the verticality of each translation interval is calculated, and the vertical segmentation index model is constructed.

9. A measuring device, characterized in that, The measuring device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, it implements the calibration data acquisition method as described in any one of claims 3 to 8.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the calibration data acquisition method as described in any one of claims 3 to 8.

Images