Automatic deviation rectifying method, device and equipment for glass substrate conveying and storage medium

Abstract

The invention provides an automatic deviation rectifying method, device and equipment for glass substrate conveying and a storage medium, and relates to the technical field of glass substrate packaging. The method comprises the following steps: acquiring actual position information of a glass substrate of a packaging station; wherein the actual position information comprises actual coordinate information of four corner points of the glass substrate; calculating position deviation information between the actual position information and the preset coordinate information; calculating adjustment information of a film taking mechanism according to the position deviation information, affine transformation and a least square method; wherein the adjustment information comprises the X-axis translation amount, the Y-axis translation amount and the rotation angle of the film taking mechanism; controlling the sheet taking mechanism to adjust the position of the glass substrate according to the adjustment information; according to the adjusted position of the glass substrate and preset coordinate information, whether the adjusted position of the glass substrate reaches a preset condition or not is judged, and when the preset condition is met, deviation rectification is ended. The deviation correcting device can automatically correct the deviation of the glass substrate when the glass substrate is conveyed.

Description

Technical Field

[0001] The present invention relates to the technical field of glass substrate packaging, and particularly to an automatic deviation correction method, device, equipment and storage medium for glass substrate transportation. Background Art

[0002] Currently, during the handling of semi-finished glass substrates, a transport cart is usually used to clamp the glass and perform horizontal transportation. These glasses are usually perpendicular to the ground, and during the handling process, the jaws of the transport cart rely on the elastic force of mechanical springs to clamp the glass. After the glass comes out of the thermal working area, the transport cart will use the jaws to clamp the glass so as to move it to the next station for further handling. However, during the handling process, actions such as the start and stop of the transport cart will cause a certain degree of deviation of the clamped glass, which may lead to operation errors at subsequent packaging stations.

[0003] Therefore, there is an urgent need for a method for correcting the deviation of glass substrate transportation. Summary of the Invention

[0004] Embodiments of the present invention provide an automatic deviation correction method, device, equipment and storage medium for glass substrate transportation to solve the problem of deviation of glass substrates during transportation.

[0005] In a first aspect, embodiments of the present invention provide an automatic deviation correction method for glass substrate transportation, including:

[0006] Obtain the actual position information of the glass substrate at the packaging station; wherein, the actual position information includes the actual coordinate information of the four corner points of the glass substrate;

[0007] Calculate the position deviation information between the actual position information and the preset coordinate information;

[0008] Calculate the adjustment information of the sheet taking mechanism according to the position deviation information, affine transformation and least squares method; wherein, the adjustment information includes the X-axis translation amount, Y-axis translation amount and rotation angle of the sheet taking mechanism;

[0009] Control the sheet taking mechanism to adjust the position of the glass substrate according to the adjustment information;

[0010] Judge whether the position of the adjusted glass substrate reaches the preset condition according to the position of the adjusted glass substrate and the preset coordinate information, and end the deviation correction when the preset condition is reached.

[0011] In a possible implementation manner, calculating the adjustment information of the sheet taking mechanism according to the position deviation information, affine transformation and least squares method includes:

[0012] Construct an affine transformation model according to the position deviation information; wherein, the affine transformation model represents the translation, rotation and scaling of the glass substrate;

[0013] Construct an equation set according to the affine transformation model and solve it using the least squares method to obtain the affine transformation parameters;

[0014] Calculate the adjustment information of the sheet taking mechanism according to the affine transformation parameters.

[0015] In a possible implementation manner, obtain the actual position information of the glass substrate at the packaging station, including:

[0016] Obtain the image data of the glass substrate at the packaging station and preprocess the image data;

[0017] Extract features from the preprocessed image data; wherein, feature extraction includes edge detection and Harris corner detection;

[0018] Determine the preliminary coordinate information of the four corner points of the glass substrate according to the results of feature extraction;

[0019] Determine the straight line equation of the edge of the glass substrate according to the preliminary coordinate information and the Hough transform, determine the accurate coordinate information of the four corner points of the glass substrate according to the straight line equation, and obtain the actual position information of the glass substrate according to the accurate coordinate information of the four corner points.

[0020] In a possible implementation manner, calculate the position deviation information between the actual position information and the preset coordinate information, including:

[0021] Calculate the deviation values of each corner point on the X-axis and Y-axis respectively according to the actual coordinate information and the preset coordinate information of each corner point, and obtain the position deviation information according to the deviation values.

[0022] In a possible implementation manner, before extracting features from the preprocessed image data, the method further includes:

[0023] Pre-calibrate the device parameters for image acquisition through a calibration plate;

[0024] Calculate the perspective transformation matrix according to the device parameters;

[0025] Map each coordinate point in the image to the corrected coordinate system through the perspective transformation matrix to correct the image data.

[0026] In a possible implementation manner, determine whether the position of the adjusted glass substrate meets the preset conditions according to the position of the adjusted glass substrate and the preset coordinate information, including:

[0027] Calculate the residual deviation of each corner point in the X direction and Y direction according to the coordinate information of the position of the adjusted glass substrate and the preset coordinate information;

[0028] When the residual deviations of all corner points are less than or equal to a preset threshold, it is determined that the preset condition is met;

[0029] When there is at least one corner point with a residual deviation greater than the preset threshold, it is determined that the preset condition is not met.

[0030] In a possible implementation, the method further includes:

[0031] When the preset condition is not met, update the adjustment information of the sheet taking mechanism according to the residual deviation;

[0032] Use the sheet taking mechanism to update the position of the glass substrate according to the updated adjustment information;

[0033] Update the residual deviations of each corner point in the X direction and Y direction according to the coordinate information of the updated position of the glass substrate and the preset coordinate information;

[0034] Judge whether the preset condition is met according to the updated residual deviation;

[0035] When the preset condition is met, it is determined that the rectification is completed;

[0036] When the preset condition is not met and the number of updates reaches the preset number, it is determined that the rectification is completed.

[0037] In a second aspect, an embodiment of the present invention provides an automatic rectification device for glass substrate transportation, including:

[0038] An actual position acquisition module, configured to acquire the actual position information of the glass substrate at the packaging station; wherein, the actual position information includes the actual coordinate information of the four corner points of the glass substrate;

[0039] A position deviation calculation module, configured to calculate the position deviation information between the actual position information and the preset coordinate information;

[0040] An adjustment information calculation module, configured to calculate the adjustment information of the sheet taking mechanism according to the position deviation information, affine transformation, and least squares method; wherein, the adjustment information includes the X-axis translation amount, Y-axis translation amount, and rotation angle of the sheet taking mechanism;

[0041] A position adjustment module, configured to control the sheet taking mechanism to adjust the position of the glass substrate according to the adjustment information; and configured to judge whether the position of the adjusted glass substrate meets the preset condition according to the position of the adjusted glass substrate and the preset coordinate information, and when the preset condition is met, the rectification is completed.

[0042] In a third aspect, an embodiment of the present invention provides an electronic device, including a memory and a processor, the memory stores a computer program, and when the processor executes the computer program, the method in the first aspect or any possible implementation manner of the first aspect is implemented.

[0043] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the method in the first aspect above or any possible implementation of the first aspect.

[0044] In the embodiment of the present invention, by calculating the position deviation information, constructing an affine transformation model, solving the transformation parameters, and calculating the adjustment information of the sheet-taking mechanism therefrom, including the translation amounts of the X-axis and Y-axis and the rotation angle, the precise adjustment of the position of the glass substrate is realized. By precisely calculating the position deviation and adjustment information, controlling the sheet-taking mechanism to perform high-precision position adjustment on the glass substrate, and performing position verification after the adjustment, it is ensured that the position of the glass substrate reaches the preset conditions, thereby effectively improving the product quality and the stability of subsequent processes. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 is a flowchart of the implementation of the automatic deviation correction method for glass substrate transportation provided by an embodiment of the present invention;

[0046] Figure 2 is a schematic structural diagram of the automatic deviation correction device for glass substrate transportation provided by an embodiment of the present invention;

[0047] Figure 3 is a schematic diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0048] The embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0049] Refer to Figure 1 , which shows a flowchart of the implementation of the automatic deviation correction method for glass substrate transportation provided by an embodiment of the present invention, and is described in detail as follows:

[0050] Step 101: Obtain the actual position information of the glass substrate at the packaging station; wherein, the actual position information includes the actual coordinate information of the four corner points of the glass substrate.

[0051] In this embodiment, the actual position information includes the actual coordinate information of the four corner points of the glass substrate, providing an accurate data basis for subsequent position deviation calculation and adjustment.

[0052] Step 102: Calculate the position deviation information between the actual position information and the preset coordinate information.

[0053] In this embodiment, by comparing the actual position with the preset position, it is determined whether the glass substrate is offset. The position deviation information is the basis for adjusting the position and posture of the sheet picking mechanism to ensure that the glass substrate can be accurately picked and placed. By comparing the actual position information of the glass substrate obtained at the packaging station (i.e., the actual coordinates of the four corner points of the glass substrate) with the pre-set standard or preset coordinate information, the deviation of the glass substrate in position is calculated, and this deviation information will be used in the subsequent adjustment process to ensure that the position of the glass substrate is corrected to the ideal state.

[0054] Step 103: Calculate the adjustment information of the sheet picking mechanism according to the position deviation information, affine transformation, and least squares method; wherein, the adjustment information includes the X-axis translation amount, Y-axis translation amount, and rotation angle of the sheet picking mechanism.

[0055] In this embodiment, using the position deviation information between the actual position and the ideal position of the glass substrate, the adjustments (translation and rotation) that the sheet picking mechanism needs to make are calculated through affine transformation and the least squares method to ensure that the glass substrate can be accurately picked and placed.

[0056] In this embodiment, the position deviation information is obtained by comparing the actual position information (actual coordinates) of the glass substrate with the preset coordinate information. Specifically, it is to calculate the deviation values (ΔX and ΔY) of the four corner points of the glass substrate on the X-axis and Y-axis.

[0057] In this embodiment, affine transformation is a geometric transformation. In the present invention, affine transformation is used to construct a transformation model that can describe the translation, rotation, and scaling of the glass substrate according to the deviation information of the four corner points of the glass substrate.

[0058] In this embodiment, the least squares method is a mathematical optimization method used to find the best parameter estimation values in the case of multiple equations and unknowns, so that the sum of the squares of the errors of all equations is minimized. In the present invention, the parameters in the affine transformation are solved by the least squares method.

[0059] In this embodiment, the X-axis translation amount is the distance that the sheet picking mechanism needs to move in the X-axis direction. The Y-axis translation amount is the distance that the sheet picking mechanism needs to move in the Y-axis direction. The rotation angle is the angle that the sheet picking mechanism needs to rotate and can be calculated from the parameters in the affine transformation matrix.

[0060] Step 104: Control the sheet picking mechanism to adjust the position of the glass substrate according to the adjustment information.

[0061] In this embodiment, the adjustment information (including the X-axis translation amount, Y-axis translation amount, and rotation angle) is applied to the sheet picking mechanism, enabling it to make corresponding adjustments to the position of the glass substrate according to this information, thereby correcting the offset of the glass substrate and ensuring its position is accurate.

[0062] Step 105: Determine whether the position of the adjusted glass substrate reaches a preset condition according to the position of the adjusted glass substrate and the preset coordinate information. When the preset condition is reached, the rectification ends.

[0063] In this embodiment, the position information of the adjusted glass substrate is compared with the preset ideal position information. If the position of the adjusted glass substrate meets the preset conditions (such as the position deviation is within the allowable range), it is considered that the rectification process is completed and the entire rectification operation can be ended.

[0064] In a possible implementation manner, the adjustment information of the sheet taking mechanism is calculated according to the position deviation information, affine transformation, and least squares method, including:

[0065] Construct an affine transformation model according to the position deviation information; wherein, the affine transformation model represents the translation, rotation, and scaling of the glass substrate;

[0066] Construct an equation set according to the affine transformation model and solve it using the least squares method to obtain the affine transformation parameters;

[0067] Calculate the adjustment information of the sheet taking mechanism according to the affine transformation parameters.

[0068] In this embodiment, the position deviation information is the difference between the actual position and the preset position. Through these deviation information, an affine transformation model can be constructed, which can describe the translation, rotation, and scaling changes of the glass substrate.

[0069] Specifically, assume that the actual coordinates of the four corner points of the glass substrate are:

[0070] (x1, y1), (x2, y2), (x3, y3), (x4, y4)

[0071] The preset coordinates are (x′1, y′1), (x′2, y′2), (x′3, y′3), (x′4, y′4)

[0072] Then the position deviation information is:

[0073] Δx i = x i - x′ i , Δy i = y i - y′ i ,

[0074] The affine transformation model is:

[0075]

[0076] In the formula, is a linear transformation (such as rotation, scaling), while is the translation amount.

[0077] By constructing a system of equations, substituting the position deviation information into the affine transformation model, and then using the least squares method to solve the unknown parameters in the model.

[0078] For each corner point, the following equations can be obtained:

[0079]

[0080] Substituting the coordinates of the four corner points, 8 equations are obtained. These equations can be expressed in matrix form:

[0081]

[0082] Using the least squares method to solve this system of linear equations, the parameters a, b, c, d, t x , t y .

[0083] According to the obtained affine transformation parameters, calculate the adjustment information required for the sheet taking mechanism, including the X-axis translation amount t x , the Y-axis translation amount t y and the rotation angle. The rotation angle is calculated from the parameters in the affine transformation matrix. For example, the rotation angle can be calculated by the following formula:

[0084]

[0085] In a possible implementation, obtain the actual position information of the glass substrate at the packaging station, including:

[0086] Obtain the image data of the glass substrate at the packaging station and preprocess the image data;

[0087] Extract features from the preprocessed image data; among them, feature extraction includes edge detection and Harris corner detection;

[0088] Determine the preliminary coordinate information of the four corner points of the glass substrate according to the results of feature extraction;

[0089] Determine the straight line equation of the edge of the glass substrate according to the preliminary coordinate information and the Hough transform, determine the accurate coordinate information of the four corner points of the glass substrate according to the straight line equation, and obtain the actual position information of the glass substrate according to the accurate coordinate information of the four corner points.

[0090] In this embodiment, an image of the glass substrate is captured by an industrial camera with high resolution (≥5 million pixels), and a global shutter is used to avoid motion blur. The lens distortion rate should be less than 0.1%. A standardized LED light source (color temperature 5500K ± 100K, illuminance ≥ 1000 Lux) is configured to ensure that the light evenly covers the glass surface and avoid interference from reflections or shadows. When the transport cart enters the packaging station, the camera is triggered by a photoelectric sensor to continuously capture 3 images (with an interval of 0.1 seconds), and the clearest one is selected for subsequent processing.

[0091] In this embodiment, preprocessing is performed on the image, including using Gaussian filtering (kernel size 5×5, σ = 1.5) to eliminate random noise in the image. The RGB image is converted to a grayscale image by the weighted average method (Y = 0.299R + 0.587G + 0.114B) for subsequent processing. The adaptive threshold algorithm (block size 15×15, C = 2) is applied to distinguish the glass edge and the background in the image.

[0092] In this embodiment, the Canny algorithm (low threshold = 50, high threshold = 150) is used for edge detection to extract the glass contour. After Harris corner detection (window size 3×3, k = 0.04), sub-pixel level optimization (iteration accuracy 0.01 pixel) is used to identify the preliminary coordinate information of the four corner points.

[0093] In this embodiment, the Hough transform is used to detect the straight line equation of the glass substrate edge. Through these straight line equations, the coordinates of the four corner points of the glass substrate can be determined more precisely. Based on the accurate coordinate information of the four corner points, the actual position and orientation of the glass substrate at the packaging station can be determined. This information will be used for subsequent position deviation calculation and adjustment.

[0094] In a possible implementation, the position deviation information between the actual position information and the preset coordinate information is calculated, including:

[0095] The deviation values of each corner point on the X-axis and Y-axis are calculated respectively according to the actual coordinate information and the preset coordinate information of each corner point, and the position deviation information is obtained based on the deviation values.

[0096] In this embodiment, through image processing and feature extraction, the actual coordinates of the four corner points of the glass substrate have been obtained, denoted as (x1, y1), (x2, y2), (x3, y3), (x4, y4)

[0097] The preset coordinates are (x′1, y′1), (x′2, y′2), (x′3, y′3), (x′4, y′4)

[0098] For each corner point, calculate its deviation values on the X-axis and Y-axis:

[0099] Δxi = x i - x' i (X - axis deviation), Δy i = y i - y' i (Y - axis deviation)

[0100] Where i is the number of the corner point (from 1 to 4).

[0101] In this embodiment, the X - axis and Y - axis deviation values of all corner points are summarized to form position deviation information. These deviation values describe the differences between the actual position and the preset position of the glass substrate, including translation, rotation, and possible scaling changes.

[0102] In a possible implementation, before feature extraction of the pre - processed image data, the method further includes:

[0103] Pre - calibrating the device parameters obtained by the image acquisition device through a calibration board;

[0104] Calculating the perspective transformation matrix according to the device parameters;

[0105] Mapping each coordinate point in the image to the corrected coordinate system through the perspective transformation matrix to correct the image data.

[0106] In this embodiment, the calibration board is an object with a known geometric shape and size, usually used for camera calibration. By photographing the calibration board, the internal parameters (such as focal length, principal point coordinates) and external parameters (such as rotation matrix and translation vector) of the camera, as well as the lens distortion parameters, can be calculated.

[0107] In this embodiment, the calibration process includes using an image acquisition device (such as a camera) to photograph multiple calibration board images at different angles. Detect the corner point positions on the calibration board in each image. According to the detected corner point positions and the actual size of the calibration board, calculate the internal parameters, external parameters, and distortion parameters of the camera.

[0108] In this embodiment, corresponding points (such as the corner points on the calibration board) are determined in the original image and the preset coordinate system. Using these corresponding points, calculate the perspective transformation matrix through an algorithm (such as direct linear transformation). Transform the coordinates of each pixel point in the original image through the perspective transformation matrix to obtain the corrected coordinates. According to the corrected coordinates, map the pixel values of the original image to a new image, thereby correcting the image data to ensure more accurate subsequent image processing and analysis.

[0109] In a possible implementation, judging whether the position of the adjusted glass substrate meets the preset conditions according to the position of the adjusted glass substrate and the preset coordinate information includes:

[0110] Calculate the residual deviations of each corner point in the X and Y directions based on the coordinate information of the adjusted position of the glass substrate and the preset coordinate information;

[0111] When the residual deviations of all corner points are less than or equal to the preset threshold, it is determined that the preset condition is met;

[0112] When there is at least one corner point with a residual deviation greater than the preset threshold, it is determined that the preset condition is not met.

[0113] In this embodiment, after the adjustment of the sheet picking mechanism, the new position information of the glass substrate includes the new coordinates of the four corner points:

[0114] (x1", y1"), (x2", y2"), (x"3, y3"), (x"4, y4")

[0115] The preset coordinates are (x′1, y′1), (x′2, y′2), (x′3, y′3), (x′4, y′4)

[0116] For each corner point, calculate the differences between the adjusted coordinates and the preset coordinates on the X-axis and Y-axis: Δx i ” = x i ” - x′ i (Residual deviation in the X direction), Δy i ” = y i ” - y′ i (Residual deviation in the Y direction)

[0117] In the formula, i is the number of the corner point (from 1 to 4).

[0118] The preset threshold is the preset maximum allowable deviation value, such as 0.1 mm. If the residual deviations of all corner points are less than or equal to this value, it means that the position of the glass substrate has been adjusted to the ideal position, and the rectification process can be ended. If the residual deviation of one or more corner points exceeds the preset threshold, it means that the position of the glass substrate is not accurate enough and needs further adjustment.

[0119] In a possible implementation, the method further includes:

[0120] When the preset condition is not met, update the adjustment information of the sheet picking mechanism according to the residual deviation;

[0121] Use the sheet picking mechanism to update the position of the glass substrate according to the updated adjustment information;

[0122] Update the residual deviations of each corner point in the X and Y directions according to the coordinate information of the updated position of the glass substrate and the preset coordinate information;

[0123] Judge whether the preset condition is met according to the updated residual deviation;

[0124] When the preset condition is reached, it is determined that the rectification is completed;

[0125] When the preset condition is not reached and the number of update times reaches the preset number, it is determined that the rectification is completed.

[0126] In this embodiment, if the position of the adjusted glass substrate does not reach the preset condition (that is, there is at least one corner with a residual deviation exceeding the preset threshold), the system will use this residual deviation information to recalculate the adjustment parameters of the sheet-taking mechanism. The sheet-taking mechanism adjusts the position of the glass substrate again according to the recalculated adjustment information (such as the new translation amount and rotation angle). After the re-adjustment, the system re-obtains the current position information of the glass substrate and recalculates the residual deviation of each corner. The system checks again whether the residual deviations of all corners are less than or equal to the preset threshold. If the residual deviations of all corners are within the allowable range, the system considers that the position of the glass substrate has been corrected in place, and the entire rectification process ends. If after multiple adjustments (reaching the preset maximum number of iterations), there are still corners with residual deviations exceeding the threshold, the system will stop the adjustment and end the rectification process. This is to avoid an infinite loop and perform other processing in a timely manner when the ideal position cannot be reached.

[0127] In this embodiment, the sheet-taking mechanism is, for example, a robot. The system sends the adjustment information to the robot through the industrial Ethernet. Based on the received adjustment information, the robot synchronously adjusts the position and posture of the end effector when taking the sheet to ensure that the center of the gripper is aligned with the glass edge.

[0128] It should be understood that the magnitudes of the sequence numbers of the steps in the above embodiments do not mean the order of execution. The order of execution of each process should be determined according to its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.

[0129] The following is the device embodiment of the present invention. For the details not described in detail, reference can be made to the corresponding method embodiment above.

[0130] Figure 2 The structural schematic diagram of the automatic rectification device for glass substrate transportation provided by the embodiment of the present invention is shown. For the convenience of description, only the parts related to the embodiment of the present invention are shown and are described in detail as follows:

[0131] As Figure 2 shown, the automatic rectification device 2 for glass substrate transportation includes:

[0132] An actual position acquisition module 21, configured to acquire the actual position information of the glass substrate at the packaging station; wherein, the actual position information includes the actual coordinate information of the four corners of the glass substrate;

[0133] A position deviation calculation module 22, configured to calculate position deviation information between actual position information and preset coordinate information;

[0134] An adjustment information calculation module 23, configured to calculate adjustment information of the sheet taking mechanism according to the position deviation information, affine transformation, and least squares method; wherein, the adjustment information includes the X-axis translation amount, Y-axis translation amount, and rotation angle of the sheet taking mechanism;

[0135] A position adjustment module 24, configured to control the sheet taking mechanism to adjust the position of the glass substrate according to the adjustment information; and configured to determine whether the position of the adjusted glass substrate reaches a preset condition according to the position of the adjusted glass substrate and the preset coordinate information, and when the preset condition is reached, the deviation correction ends.

[0136] In a possible implementation manner, the adjustment information calculation module 23 is further configured to:

[0137] Construct an affine transformation model according to the position deviation information; wherein, the affine transformation model represents the translation, rotation, and scaling of the glass substrate;

[0138] Construct an equation set according to the affine transformation model and solve it using the least squares method to obtain affine transformation parameters;

[0139] Calculate the adjustment information of the sheet taking mechanism according to the affine transformation parameters.

[0140] In a possible implementation manner, the actual position acquisition module 21 is further configured to:

[0141] Acquire image data of the glass substrate at the packaging station and preprocess the image data;

[0142] Extract features from the preprocessed image data; wherein, the feature extraction includes edge detection and Harris corner detection;

[0143] Determine preliminary coordinate information of the four corner points of the glass substrate according to the results of the feature extraction;

[0144] Determine the straight line equation of the edge of the glass substrate according to the preliminary coordinate information and Hough transform, determine the accurate coordinate information of the four corner points of the glass substrate according to the straight line equation, and obtain the actual position information of the glass substrate according to the accurate coordinate information of the four corner points.

[0145] In a possible implementation manner, the position deviation calculation module 22 is further configured to:

[0146] Calculate the deviation values of each corner point on the X-axis and Y-axis respectively according to the actual coordinate information and preset coordinate information of each corner point, and obtain the position deviation information according to the deviation values.

[0147] In a possible implementation, the actual position acquisition module 21 is further configured to:

[0148] Pre-calibrate the device parameters for image acquisition through a calibration board;

[0149] Calculate a perspective transformation matrix based on the device parameters;

[0150] Map each coordinate point in the image to a corrected coordinate system through the perspective transformation matrix to correct the image data.

[0151] In a possible implementation, the position adjustment module 24 is further configured to:

[0152] Calculate the residual deviation of each corner point in the X direction and the Y direction according to the coordinate information of the adjusted position of the glass substrate and the preset coordinate information;

[0153] When the residual deviation of all corner points is less than or equal to a preset threshold, it is determined that the preset condition is reached;

[0154] When the residual deviation of at least one corner point is greater than the preset threshold, it is determined that the preset condition is not reached.

[0155] Figure 3 It is a schematic diagram of an electronic device provided by an embodiment of the present invention. As Figure 3 shown, the electronic device 3 of this embodiment includes: a processor 30 and a memory 31. The memory 31 stores a computer program 32. When the processor 30 executes the computer program 32, the steps in the above-mentioned various method embodiments are implemented. Alternatively, when the processor 30 executes the computer program 32, the functions of each module / unit in the above-mentioned various device embodiments are implemented.

[0156] Exemplarily, the computer program 32 can be divided into one or more modules / units, and the one or more modules / units are stored in the memory 31 and executed by the processor 30 to complete the present invention. The one or more modules / units can be a series of computer program instruction segments capable of performing specific functions, and the instruction segments are used to describe the execution process of the computer program 32 in the electronic device 3.

[0157] The electronic device 3 may include, but is not limited to, a processor 30 and a memory 31. Those skilled in the art can understand that Figure 3 merely an example of the electronic device 3, which does not constitute a limitation on the electronic device 3, and may include more or fewer components than shown in the figure, or combine certain components, or different components. For example, the electronic device 3 may further include input / output devices, network access devices, buses, etc.

[0158] The processor 30 may be a Central Processing Unit (CPU), or may also be 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 may be a microprocessor or the processor may also be any conventional processor, etc.

[0159] The memory 31 may be an internal storage unit of the electronic device 3, such as the hard disk or memory of the electronic device 3. The memory 31 may also be an external storage device of the electronic device 3, such as a plug-in hard disk, Smart Media Card (SMC), Secure Digital (SD) card, Flash Card, etc. equipped on the electronic device 3. Further, the memory 31 may also include both the internal storage unit and the external storage device of the electronic device 3. The memory 31 is used to store the computer program 32 and other programs and data required by the electronic device 3. The memory 31 may also be used to temporarily store the data that has been output or will be output.

[0160] For the convenience and simplicity of description, only the above-mentioned division of each functional module / unit is used as an example. In actual applications, the above functions may be allocated to different functional modules / units according to needs. The above modules / units may be implemented in the form of hardware, may also be implemented in the form of software, or may be implemented in the form of a combination of hardware and software.

[0161] The embodiment of the present invention also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by the processor, the methods in the above-mentioned method embodiments are implemented.

[0162] The embodiment of the present invention also provides a computer program product, including a computer program. When the computer program is executed by the processor, the methods in the above-mentioned method embodiments are implemented.

[0163] Among them, the computer program includes computer program code, which can be in the form of source code, object code, executable file or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disc, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc.

[0164] In the above embodiments, the descriptions of each embodiment have their own emphases. For the parts not detailed or recorded in a certain embodiment, reference can be made to the relevant descriptions of other embodiments. Without special instructions and logical conflicts, the terms and / or descriptions between different embodiments are consistent and can be referenced to each other. The technical features in different embodiments can be combined to form new embodiments according to their inherent logical relationships.

[0165] The above-described embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. An automatic deviation correction method for conveying a glass substrate, characterized in that: include: Acquire actual position information of the glass substrate at the packaging station; wherein the actual position information includes actual coordinate information of four corner points of the glass substrate; Calculate the position deviation information between the actual position information and the preset coordinate information; Calculating adjustment information of the film taking mechanism according to the position deviation information, affine transformation and least square method; wherein the adjustment information includes X-axis translation, Y-axis translation and rotation angle of the film taking mechanism; Controlling the film taking mechanism to adjust the position of the glass substrate according to the adjustment information; It is determined whether the adjusted position of the glass substrate meets a preset condition according to the adjusted position of the glass substrate and the preset coordinate information, and the deviation correction ends when the preset condition is met.

2. The automatic deviation correction method for conveying a glass substrate according to claim 1, characterized in that: The step of calculating the adjustment information of the film taking mechanism according to the position deviation information, affine transformation and least square method includes: Constructing an affine transformation model according to the position deviation information; wherein the affine transformation model represents the translation, rotation and scaling of the glass substrate; Constructing a set of equations according to the affine transformation model and solving them using the least square method to obtain affine transformation parameters; The adjustment information of the film taking mechanism is calculated according to the affine transformation parameters.

3. The automatic deviation correction method for conveying a glass substrate according to claim 1, characterized in that: The obtaining of the actual position information of the glass substrate at the packaging station includes: Acquire image data of a glass substrate at a packaging station, and pre-process the image data; Performing feature extraction on the preprocessed image data; wherein the feature extraction includes edge detection and Harris corner point detection; Determining preliminary coordinate information of four corner points of the glass substrate according to the result of feature extraction; The straight line equation of the edge of the glass substrate is determined according to the preliminary coordinate information and Hough transform, the precise coordinate information of the four corner points of the glass substrate is determined according to the straight line equation, and the actual position information of the glass substrate is obtained according to the precise coordinate information of the four corner points.

4. The automatic deviation correction method for conveying a glass substrate according to claim 3, characterized in that: The calculating of the position deviation information between the actual position information and the preset coordinate information includes: The deviation values ​​of each corner point on the X-axis and the Y-axis are calculated respectively according to the actual coordinate information and the preset coordinate information of each corner point, and the position deviation information is obtained according to the deviation values.

5. The automatic deviation correction method for conveying a glass substrate according to claim 3, characterized in that: Before extracting features from the preprocessed image data, the method further includes: Pre-calibrate the device parameters acquired by the image using a calibration plate; Calculating a perspective transformation matrix according to the device parameters; Each coordinate point in the image is mapped to the corrected coordinate system through the perspective transformation matrix to correct the image data.

6. The automatic deviation correction method for conveying a glass substrate according to claim 1, characterized in that: The step of judging whether the adjusted position of the glass substrate meets a preset condition according to the adjusted position of the glass substrate and the preset coordinate information includes: Calculating the residual deviation of each corner point in the X direction and the Y direction according to the coordinate information of the adjusted position of the glass substrate and the preset coordinate information; When the residual deviations of all corner points are less than or equal to the preset threshold, it is determined that the preset condition is met; When there is at least one corner point whose residual deviation is greater than the preset threshold, it is determined that the preset condition is not met.

7. The automatic deviation correction method for conveying a glass substrate according to claim 6, characterized in that: The method further comprises: When the preset condition is not met, updating the adjustment information of the film taking mechanism according to the residual deviation; Using the film taking mechanism to update the position of the glass substrate according to the updated adjustment information; Update the residual deviation of each corner point in the X direction and the Y direction according to the updated coordinate information of the position of the glass substrate and the preset coordinate information; Determine whether the preset condition is met based on the updated residual deviation; When the preset conditions are met, it is determined that the deviation correction is completed; When the preset condition is not met and the number of updates reaches the preset number, it is determined that the correction is completed.

8. An automatic deviation-correcting device for conveying a glass substrate, characterized in that: include: An actual position acquisition module, used to acquire actual position information of the glass substrate at the packaging station; wherein the actual position information includes actual coordinate information of four corner points of the glass substrate; A position deviation calculation module is used to calculate the position deviation information between the actual position information and the preset coordinate information; An adjustment information calculation module, used to calculate the adjustment information of the film taking mechanism according to the position deviation information, affine transformation and least square method; wherein the adjustment information includes the X-axis translation amount, Y-axis translation amount and rotation angle of the film taking mechanism; The position adjustment module is used to control the film picking mechanism to adjust the position of the glass substrate according to the adjustment information; and is used to determine whether the adjusted position of the glass substrate meets the preset conditions according to the adjusted position of the glass substrate and the preset coordinate information, and the correction ends when the preset conditions are met.

9. An electronic device, characterized in that: The method comprises a memory and a processor, wherein the memory stores a computer program, and the processor implements the method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images