Calibration Parameter Determination Method, Hybrid Calibration Plate, Device, Equipment and Medium

Abstract

The present application discloses a calibration parameter determination method, a hybrid calibration board, a device, equipment and a medium, relating to the technical field of camera calibration. The method includes: obtaining a calibration image acquired by performing image acquisition on the hybrid calibration board; the hybrid calibration board includes a first calibration reference object and a second calibration reference object; the positions of the corner points of the first calibration reference object do not undergo perspective deformation; according to the positions of the corner points of the first calibration reference object in the calibration image, determining a reference object image corresponding to the second calibration reference object from the calibration image; determining the initial calibration point coordinates of the second calibration reference object according to the reference object image, and correcting the initial calibration point coordinates; based on the corrected calibration point coordinates, determining the image acquisition calibration parameters corresponding to the hybrid calibration board. Using this method can effectively improve the accuracy of the calibration parameters.

Description

Technical Field

[0001] The present application relates to the technical field of camera calibration, and particularly to a method for determining calibration parameters, a hybrid calibration board, a device, equipment, and a medium. Background Art

[0002] In the process of three-dimensional measurement and three-dimensional reconstruction, calibrating the device parameters of an image acquisition device is a very important step. Currently, a two-dimensional planar calibration board is usually used for calibrating the device parameters. For example, a circular array calibration board can be used for camera calibration. Among them, in the process of calibration using a two-dimensional planar calibration board, a perspective transformation needs to be performed on the calibration reference pattern in the two-dimensional planar calibration board.

[0003] However, the calibration reference patterns in some two-dimensional planar calibration boards are prone to deformation after perspective transformation, resulting in inaccurate determination of the calibration parameters of the image acquisition device. For example, the circles in a circular array calibration board are very likely to become ellipses in the calibration image after perspective transformation. Therefore, there may be errors in the positions of the calibration points determined from the calibration image, which in turn affects the accuracy of the calibration parameters. Summary of the Invention

[0004] Based on this, the present application provides a method for determining calibration parameters, a hybrid calibration board, a device, equipment, and a medium that can improve the accuracy of calibration parameters.

[0005] In a first aspect, the present application provides a method for determining calibration parameters. The method includes:

[0006] Obtaining a calibration image obtained by image acquisition of a hybrid calibration board; the hybrid calibration board includes a first calibration reference object and a second calibration reference object; the positions of the corner points of the first calibration reference object do not undergo perspective deformation;

[0007] Determining, from the calibration image, a reference object image corresponding to the second calibration reference object according to the corner point positions of the corner points of the first calibration reference object in the calibration image;

[0008] Determining an initial calibration point position of the second calibration reference object according to the reference object image and correcting the initial calibration point position;

[0009] Based on the corrected calibration point position, determining the image acquisition calibration parameters corresponding to the hybrid calibration board.

[0010] In a second aspect, the present application further provides a hybrid calibration board, including: a board body; the board body is a planar structure; at least one first calibration reference object and at least one second calibration reference object are provided on the surface of the board body; the first calibration reference object is an object whose corner point positions do not undergo perspective deformation;

[0011] The first calibration reference object and the second calibration reference object are arranged at intervals on the surface of the plate body.

[0012] In some embodiments, both the first calibration reference object and the second calibration reference object are multiple; the multiple first calibration reference objects are arranged in central symmetry on the surface of the plate body; the multiple second calibration reference objects are arranged in central symmetry on the surface of the plate body.

[0013] In some embodiments, the first calibration reference object is a rectangular pattern, and the second calibration reference object is a concentric circle pattern.

[0014] In a third aspect, the present application also provides a calibration parameter determination device. The device includes:

[0015] An image acquisition module, configured to acquire a calibration image obtained by performing image acquisition on a hybrid calibration plate; the hybrid calibration plate includes a first calibration reference object and a second calibration reference object; the positions of the corner points of the first calibration reference object do not undergo perspective deformation;

[0016] An image determination module, configured to determine a reference object image corresponding to the second calibration reference object from the calibration image according to the corner point positions of the corner points of the first calibration reference object in the calibration image;

[0017] A position correction module, configured to determine an initial calibration point position of the second calibration reference object according to the reference object image and correct the initial calibration point position;

[0018] A parameter determination module, configured to determine image acquisition calibration parameters corresponding to the hybrid calibration plate based on the calibrated calibration point positions.

[0019] In some embodiments, the corner point position is the corner point image coordinate of the corner point of the first calibration reference object in the image coordinate system where the calibration image is located. The image determination module includes a coordinate acquisition unit, a relationship determination unit, and an image positioning unit. The coordinate acquisition unit is configured to acquire the corner point calibration coordinates of the corner points of the first calibration reference object in the calibration coordinate system where the hybrid calibration plate is located; the relationship determination unit is configured to determine a mapping conversion relationship according to the positional relationship between the corner point image coordinates and the corner point calibration coordinates; the mapping conversion relationship is used to implement the mapping conversion between the plane where the calibration image is located and the plane where the calibration plate template image is located in the calibration coordinate system; the image positioning unit is configured to locate the reference object image corresponding to the second calibration reference object from the calibration image according to the mapping conversion relationship and the calibration plate template image.

[0020] In some embodiments, the image positioning unit is further configured to map the calibrated image to the plane where the calibration plate template image is located in the calibration coordinate system according to the mapping conversion relationship to obtain a reference image; compare the positions of the second calibration reference object in the reference image with the second calibration reference object in the calibration plate template image to determine the coding identifier of the second calibration reference object in the reference image; the coding identifier has a uniquely corresponding position information; based on the mapping conversion relationship, inversely map the position information corresponding to the coding identifier to the calibrated image to locate the reference object image corresponding to the second calibration reference object in the calibrated image.

[0021] In some embodiments, the second calibration reference object is a concentric circle pattern, and the position correction module includes a contour extraction unit and a position determination unit. The contour extraction unit is configured to extract a plurality of reference circle contours of the concentric circle pattern from the reference object image; the position determination unit is configured to obtain the center coordinates corresponding to the reference circle contour in the reference object image as the initial calibration point position.

[0022] In some embodiments, the contour extraction unit is further configured to perform binarization processing on the reference object image to obtain a binarized image; perform edge detection on the binarized image to extract the preliminary edge contour of the binarized image; perform fitting processing on the preliminary edge contour to obtain a plurality of reference circle contours.

[0023] In some embodiments, the position correction module is further configured to determine a calibration circle contour matching the reference circle contour from the hybrid calibration plate; perform eccentricity error correction according to the initial calibration point position and the physical radius corresponding to the calibration circle contour in the hybrid calibration plate to obtain the corrected calibration point position.

[0024] In some embodiments, the calibration parameter determination device further includes a parameter optimization module, and the parameter optimization module is configured to calculate the reprojection error of the calibrated image according to the image acquisition calibration parameters; construct a cost function based on the reprojection error and the image acquisition calibration parameters; take minimizing the cost function as the optimization objective, and optimize the image acquisition calibration parameters to obtain the optimized image acquisition calibration parameters.

[0025] In a fourth aspect, the present application further provides a computer device. The computer device includes a memory and a processor, the memory stores a computer program, and when the processor executes the computer program, the steps in the above-mentioned calibration parameter determination method are implemented.

[0026] In a fifth aspect, the present application further provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the above-mentioned calibration parameter determination method are implemented.

[0027] In a sixth aspect, the present application also provides a computer program product. The computer program product includes a computer program which, when executed by a processor, implements the steps in the above-described calibration parameter determination method.

[0028] In the above-described calibration parameter determination method, hybrid calibration board, calibration parameter determination device, computer device, storage medium, and computer program product, calibration images obtained by image acquisition of the hybrid calibration board are acquired; the hybrid calibration board includes a first calibration reference object and a second calibration reference object; the positions of the corner points of the first calibration reference object do not undergo perspective deformation; according to the positions of the corner points of the first calibration reference object in the calibration images, a reference object image corresponding to the second calibration reference object is determined from the calibration images; initial calibration point coordinates of the second calibration reference object are determined based on the reference object image, and the initial calibration point coordinates are corrected; based on the corrected calibration point coordinates, image acquisition calibration parameters corresponding to the hybrid calibration board are determined. The present application designs a hybrid calibration board including different calibration reference objects, and proposes a brand-new calibration parameter determination method based on the hybrid calibration board, that is, the second calibration reference object image is accurately determined from the calibration images through the first calibration reference object whose corner point positions do not undergo perspective deformation, thereby ensuring the accuracy of the initial calibration point positions obtained based on the second calibration reference object; correcting the initial calibration point positions can effectively improve the accuracy of the corrected calibration point positions, and further improve the accuracy of the calibration parameters. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 is a flowchart of a calibration parameter determination method according to an embodiment of the present application;

[0030] Figure 2 is a schematic diagram of a hybrid calibration board according to an embodiment of the present application;

[0031] Figure 3 is a schematic diagram of the contour of a reference circle in a reference object image according to an embodiment of the present application;

[0032] Figure 4 is a flowchart of a calibration parameter determination method according to another embodiment of the present application;

[0033] Figure 5 is a structural block diagram of a calibration parameter determination device according to an embodiment of the present application;

[0034] Figure 6 is an internal structure diagram of a computer device according to an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0035] In order to make the objectives, technical solutions and advantages of the present application more clear and understandable, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0036] In order to make the objectives, technical solutions and advantages of the present application more clear and understandable, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0037] In some embodiments, as Figure 1 shown, a method for determining calibration parameters is provided. In this embodiment, the method is illustrated by taking its application to a computer device as an example. The computer device may be a server or a terminal. It can be understood that the method can also be applied to a system including a server and a terminal and implemented through the interaction between the server and the terminal. Among them, the terminal includes at least one of a mobile phone, a tablet computer, a laptop computer or a desktop computer. In this embodiment, the method includes the following steps:

[0038] Step 102: Obtain a calibration image obtained by performing image acquisition on a hybrid calibration board.

[0039] Among them, the calibration board refers to a geometric model with a pattern array of fixed pitch, and the hybrid calibration board refers to a geometric model with a fixed pitch and including two or more different pattern arrays.

[0040] In some embodiments, the hybrid calibration board includes a first calibration reference object and a second calibration reference object. Among them, the first calibration reference object refers to one of the patterns in the hybrid calibration board and is used for subsequent calibration. The second calibration reference object refers to another pattern in the hybrid calibration board that is different from the first calibration reference object and is also used for subsequent calibration.

[0041] A corner point is an extreme point, that is, a point that is particularly prominent in terms of certain attributes, such as the end point of a line segment, the vertex of a geometric figure, or a point with the maximum local curvature on a curve. The corner points in the present application may refer to the vertices in the pattern.

[0042] In some embodiments, the positions of the corner points of the first calibration reference object do not undergo perspective distortion during the calibration process. Here, perspective distortion refers to the difference between how an object and its surrounding area appear in reality and how they appear in the standard lens of an image acquisition device. That is, due to the relative proportion change of the near and far features, the object and its surrounding area in the standard lens of the image acquisition device may be bent or distorted. Since the corner points of a rectangle basically do not undergo perspective distortion during the calibration process, the first calibration reference object can be a rectangle, and the corner points of the first calibration reference object can be the vertices of the rectangle.

[0043] In some embodiments, the first calibration reference object includes at least one of a checkerboard pattern, a QR code pattern, or a binary coding pattern. Among them, the binary coding pattern, namely the ArUco pattern, refers to a pattern composed of a binary matrix formed by black borders. The black borders help improve the accuracy of its positioning and detection in the image, and the binary matrix is used to represent the uniqueness of the marker.

[0044] In some embodiments, the graphic complexity of the second calibration reference object is lower than that of the first calibration reference object. In this application, a second calibration reference object with a lower graphic complexity than the first calibration reference object is introduced into the hybrid calibration plate. On the premise of ensuring no offset error using the first calibration reference object, the process requirements for manufacturing the hybrid calibration plate can also be reduced through the second calibration reference object. Here, graphic complexity refers to the complexity of the structure and elements of a graphic. If a graphic has numerous elements and a cumbersome structure, it is considered to have a relatively high complexity; otherwise, it is considered to have a relatively low complexity.

[0045] In some embodiments, the second calibration reference object includes at least one of a circular pattern or a concentric circle pattern.

[0046] In some embodiments, since the ArUco pattern has good robustness and the concentric circle pattern has good wear resistance, the ArUco pattern can be selected as the first calibration reference object, and the concentric circle pattern can be selected as the second calibration reference object to combine the respective advantages of the two patterns.

[0047] In some embodiments, a blank area for placing an object can also be provided in the middle of the hybrid calibration plate to ensure that when the object is placed on the hybrid calibration plate, it does not block at least one of the first positioning reference object or the second positioning reference object.

[0048] In some embodiments, the design drawing of the hybrid calibration plate including the ArUco pattern 202 and the concentric circle pattern 204 can refer to Figure 2It can be seen that the overall shape of the hybrid calibration board is a symmetric figure, and the ArUco pattern 202 and the concentric circle pattern 204 are arranged at intervals. Among them, the overall shape of the hybrid calibration board is circular, and the object is placed within the range of the regular polygon inscribed in the circle. The ArUco pattern 202 is placed at the positions of the vertices of the regular polygon inscribed in the circle, and several concentric circle patterns 204 are placed between the straight lines connecting every two adjacent ArUco patterns 202. After several concentric circle patterns 204 are generated, it is also possible to calculate the coordinates of multiple other concentric circles that form an equilateral triangle with these several concentric circle patterns 204, so as to form a distribution of concentric circles.

[0049] Specifically, the image acquisition device takes pictures of the hybrid calibration board at multiple angles to obtain calibration images. Then, the computer device acquires the corresponding calibration images from the image acquisition device. Among them, the image acquisition device refers to a device with a photographing function, which can be but is not limited to various cameras and mobile devices.

[0050] Step 104: Determine the reference object image corresponding to the second calibration reference object from the calibration image according to the corner positions of the corners of the first calibration reference object in the calibration image.

[0051] Among them, the reference object image is an image formed by the image area corresponding to the second calibration reference object in the calibration image.

[0052] Specifically, the computer device can determine the mapping conversion relationship between the plane where the corners of the first calibration reference object are located and the plane where the calibration image is located according to the corner positions of the corners of the first calibration reference object in the calibration image. The computer device roughly locates the second calibration reference object in the calibration image according to this mapping conversion relationship, and determines the corresponding reference object image from the calibration image according to the position of the second calibration reference object in the calibration image obtained through rough positioning.

[0053] Step 106: Determine the initial calibration point position of the second calibration reference object according to the reference object image, and correct the initial calibration point position.

[0054] Among them, the initial calibration point position refers to the position of the calibration point of the second calibration reference object in the reference object image. The calibration point of the second calibration reference object refers to one or more points used to locate the second calibration reference object in the second calibration reference object, such as at least one of the center point or the edge point in the second calibration reference object.

[0055] It can be understood that the calibration points of the second calibration reference object, that is, the initial calibration point positions, may deviate during the perspective transformation process. To ensure the accuracy of the calculation of the calibration parameters, it is considered that after determining the initial calibration point positions, it is also necessary to correct the initial calibration point positions.

[0056] Specifically, the computer device determines the position of the calibration points of the second calibration reference object in the reference object image from the reference object, that is, the initial calibration point position. Then, the computer device corrects the coordinate position of the initial calibration point to obtain the calibrated calibration point coordinates, so as to eliminate the offset error caused by perspective transformation, and thus effectively improve the accuracy of the position of the calibrated calibration point.

[0057] Step 108: Based on the position of the calibrated calibration point, determine the image acquisition calibration parameters corresponding to the hybrid calibration board.

[0058] Among them, the image acquisition calibration parameters include at least one of the internal parameters of the image acquisition device or the external parameters of the device from the coordinate system where the calibration image is located to the coordinate system where the hybrid calibration board is located.

[0059] Specifically, based on the position of the calibrated calibration point, the computer device can establish a mathematical model from the coordinate system where the calibration image is located to the coordinate system where the hybrid calibration board is located according to the position of the calibrated calibration point, and calculate the image acquisition calibration parameters based on the calibration function in the established mathematical model.

[0060] In some embodiments, the calibration function in OpenCV can be used to calculate the image acquisition calibration parameters. Among them, OpenCV is a cross-platform computer vision and machine learning software library.

[0061] In the above calibration parameter determination method, a calibration image obtained by image acquisition of the hybrid calibration board is acquired; the hybrid calibration board includes a first calibration reference object and a second calibration reference object; the positions of the corner points of the first calibration reference object do not undergo perspective deformation; according to the positions of the corner points of the first calibration reference object in the calibration image, a reference object image corresponding to the second calibration reference object is determined from the calibration image; the initial calibration point coordinates of the second calibration reference object are determined according to the reference object image, and the initial calibration point coordinates are corrected; based on the corrected calibration point coordinates, the image acquisition calibration parameters corresponding to the hybrid calibration board are determined. The present application designs a hybrid calibration board including different calibration reference objects, and proposes a brand-new calibration parameter determination method based on this hybrid calibration board, that is, accurately determining the second calibration reference object image from the calibration image through the first calibration reference object whose corner point position does not undergo perspective deformation, so as to ensure the accuracy of the initial calibration point position obtained based on the second calibration reference object; correcting the initial calibration point position can also effectively improve the accuracy of the position of the calibrated calibration point, and thus improve the accuracy of the calibration parameters.

[0062] In some embodiments, the corner position is the corner image coordinates of the corner of the first calibration reference object in the image coordinate system where the calibration image is located. Step 104 specifically includes, but is not limited to: obtaining the corner calibration coordinates of the corner of the first calibration reference object in the calibration coordinate system where the hybrid calibration board is located; determining the mapping conversion relationship according to the positional relationship between the corner image coordinates and the corner calibration coordinates; and positioning the reference object image corresponding to the second calibration reference object from the calibration image according to the mapping conversion relationship and the calibration board template image.

[0063] Among them, the mapping conversion relationship is used to implement the mapping conversion between the plane where the calibration image is located and the plane where the calibration board template image is located in the calibration coordinate system. That is to say, the calibration image can be converted to the plane where the calibration board template image is located in the calibration coordinate system according to this mapping relationship, and the calibration template image can also be converted to the plane where the calibration image is located according to this mapping relationship.

[0064] The calibration template image refers to the top view obtained by only photographing the hybrid calibration board at a plane parallel to the plane where the hybrid calibration board is located.

[0065] Specifically, the computer device obtains the corner calibration coordinates of the corner of the first calibration reference object in the calibration coordinate system where the hybrid calibration board is located. Then, the computer device determines the mapping conversion relationship between the plane where the calibration image is located and the plane where the calibration board template image is located in the calibration coordinate system according to the positional relationship between the corner image coordinates and the corner calibration coordinates. Finally, according to the above mapping conversion relationship, the computer device can locate the position of the second calibration reference image in the calibration image based on the position of the second calibration reference object in the calibration template image, and extract the corresponding image area from the calibration image based on the position of the second calibration reference image in the calibration image to obtain the reference object image. In this application, by using the second calibration reference object whose corner position does not undergo perspective deformation, an accurate mapping conversion relationship can be obtained, thereby ensuring the accuracy of locating the reference object image corresponding to the second calibration reference object from the calibration image according to this mapping conversion relationship and the calibration board template image.

[0066] In some embodiments, the step of "positioning the reference object image corresponding to the second calibration reference object from the calibration image according to the mapping conversion relationship and the calibration board template image" specifically includes, but is not limited to: mapping the calibration image to the plane where the calibration board template image is located in the calibration coordinate system according to the mapping conversion relationship to obtain a reference image; comparing the positions of the second calibration reference object in the reference image and the second calibration reference object in the calibration board template image to determine the coding identifier of the second calibration reference object in the reference image; and reversely mapping the position information corresponding to the coding identifier to the calibration image based on the mapping conversion relationship to locate the reference object image corresponding to the second calibration reference object from the calibration image.

[0067] Among them, the coding identifier is used to distinguish different second positioning reference objects. The coding identifier has a uniquely corresponding position information, that is, the coding identifier corresponding to each second calibration reference object has a uniquely corresponding position information to the second calibration reference object, such as the position coordinates under the calibration coordinates. It can be understood that the coding identifier can be uniquely determined in advance according to the positions of each second calibration reference object in the hybrid calibration board or the calibration board template diagram.

[0068] Specifically, the computer device maps the calibration image to the plane where the calibration board template diagram is located under the calibration coordinates according to the mapping conversion relationship between the plane where the calibration image is located and the plane where the calibration board template diagram is located under the calibration coordinates, so as to obtain a reference image. Since the reference image and the calibration template diagram are both located on the same plane, the computer device can compare the positions of the second calibration reference objects in the reference image with those of the second calibration reference objects in the calibration board template diagram. If the computer device identifies that the positions of a certain second calibration reference object in the reference image and a certain second calibration reference object in the calibration board template diagram are the same, it is determined that the coding identifiers corresponding to these two second calibration reference objects are the same, thereby determining the coding identifier of the second calibration reference object in the reference image. Then, the computer device reversely maps the position information corresponding to the coding identifier to the calibration image based on the mapping conversion relationship between the plane where the calibration image is located and the plane where the calibration board template diagram is located under the calibration coordinates, so as to locate the reference object image corresponding to the second calibration reference object in the calibration image. By matching the coding identifiers of each second calibration reference object in the reference image in this application, the position of the corresponding second calibration reference object in the calibration image can be accurately determined, thereby ensuring the accuracy of the reference object image corresponding to the second calibration reference object extracted based on this position.

[0069] In some embodiments, the mapping conversion relationship can be reflected by a single mapping transformation matrix. After the computer device obtains the corner calibration coordinates, it can perform a single mapping transformation matrix for rough positioning of the second calibration reference object according to the position relationship between the corner image coordinates and the corner calibration coordinates. Then, the computer device transforms the calibration image to the plane where the calibration board template diagram is located under the calibration coordinates through the single mapping transformation matrix to obtain a reference image. After obtaining the reference image, the positions of the second calibration reference objects in the reference image are compared with those of the second calibration reference objects in the calibration board template diagram to determine the coding identifiers of the second calibration reference objects in the reference image. Then, the computer device reversely maps the position information corresponding to the coding identifier to the calibration image according to the inverse matrix of the single mapping transformation matrix, so as to locate the reference object image corresponding to the second calibration reference object in the calibration image. The reference object image obtained by reversely mapping the position information corresponding to the coding identifier is as Figure 3 shown. From Figure 3It can be seen that the reference object image is the result of the deformation of concentric circles.

[0070] In some embodiments, the second calibration reference object is a concentric circle pattern, and step 106 specifically includes but is not limited to: extracting a plurality of reference circle contours of the concentric circle pattern from the reference object image; obtaining the center coordinates corresponding to the reference circle contours in the reference object image as the initial calibration point positions.

[0071] Among them, concentric circles refer to circles with the same center but different radii. The reference circle contour refers to the contour corresponding to each circle with the same center and different radii in the concentric circles. It should be noted that the contours of the concentric circles in the calibration image obtained after the perspective transformation of the hybrid calibration plate are very likely to become ellipses. Correspondingly, the reference circle contour may be an ellipse contour.

[0072] Specifically, the computer device extracts a plurality of reference circle contours of the concentric circle pattern from the reference object image and obtains the center coordinates corresponding to each reference circle contour in the reference object image as the initial calibration point coordinates. Among them, the plurality of reference circle contours of the concentric circle pattern can be referred to Figure 3 . Using the circle coordinates of the concentric circle pattern as the initial calibration point coordinates, since all pixels on the periphery of the circle of the concentric circle can be utilized, the influence of image noise can be reduced, thereby ensuring the accuracy of the initial calibration point coordinates.

[0073] In some embodiments, the step of "extracting a plurality of reference circle contours of the concentric circle pattern from the reference object image" specifically includes but is not limited to: performing binarization processing on the reference object image to obtain a binarized image; performing edge detection on the binarized image to extract the preliminary edge contour of the binarized image; performing fitting processing on the preliminary edge contour to obtain a plurality of reference circle contours.

[0074] Among them, binarization processing is to set the grayscale value of the pixel points on the image to 0 or 255, that is, to present the entire image with an obvious visual effect of only black and white.

[0075] Edge detection is a basic problem in image processing and computer vision. The purpose of edge detection is to identify the points with obvious brightness changes in a digital image.

[0076] Fitting is to connect a series of points on a plane with a smooth curve.

[0077] Specifically, the computer device performs binarization processing on the reference object to obtain a binarized image with an obvious visual effect of only black and white. Then, the computer device performs edge detection on the binarized image to obtain a preliminary edge contour formed by a plurality of edge points. In addition, the computer device further performs fitting processing on the plurality of edge points obtained by edge detection to obtain a plurality of clearer reference circle contours.

[0078] In some embodiments, after the computer device performs edge detection on the binarized image, it can also extract only sub-pixel edges, perform least squares fitting on the extracted sub-pixel edges, and eliminate the fitting points with errors greater than the threshold to obtain a fitting result, and cluster the fitting result into multiple reference circle contours. Among them, a sub-pixel is a unit smaller than a pixel obtained by further subdividing the basic unit of a pixel, which can improve the image resolution. Usually, sub-pixel edges exist in areas where the image gradually changes excessively.

[0079] In some embodiments, step 106 specifically further includes but is not limited to: determining a calibration circle contour that matches the reference circle contour from the mixed calibration plate; performing eccentricity error correction based on the initial calibration point position and the physical radius of the calibration circle contour corresponding to the calibration circle contour in the mixed calibration plate to obtain the corrected calibration point position.

[0080] Among them, the calibration circle contour refers to the contour corresponding to a circle with the same center as the concentric circles and different radii among the concentric circle patterns on the mixed calibration plate.

[0081] The physical radius of the calibration circle contour corresponding to the calibration circle contour in the mixed calibration plate refers to the radius value of the calibration circle contour actually measured in the mixed calibration plate.

[0082] Eccentricity error refers to the situation where the center projection of a circle in space is not equal to the center of the projected ellipse, and there is an error between the two centers.

[0083] Specifically, the computer device determines a calibration circle contour that matches the reference circle contour from the calibrated mixed plate. Matching means that at least one of the area of the reference circle contour is the same as the area of the calibration circle contour, the radius of the reference circle contour is the same as the radius of the calibration circle contour, or the diameter of the reference circle contour is the same as the diameter of the calibration circle contour. Then, the computer device performs eccentricity error correction based on the initial calibration point position and the physical radius of the calibration circle contour corresponding to the calibration circle contour in the mixed calibration plate to obtain the corrected calibration point position. By calibrating the eccentricity error of the initial calibration point position in this application, it is possible to effectively avoid the offset error generated by the center of the concentric circle pattern after perspective transformation, so as to improve the calibration accuracy.

[0084] In some embodiments, the calibration point position refers to the coordinates of the calibration point corresponding in the calibration image. If the concentric circle pattern in the reference object includes three ellipses with the same center as the concentric circles and different radii, denoted as ellipse 1, ellipse 2, and ellipse 3, and the center coordinates of ellipse 1, ellipse 2, and ellipse 3 are respectively: (u B1 , v B1 ), (u B2 , v B2 ), (u B3 , vB3 ) and the physical radii corresponding to the ellipse 1, ellipse 2, and ellipse 3 in the hybrid calibration plate are r1, r2, and r3 respectively. According to the eccentricity error principle of a circle in perspective transformation, the abscissa and ordinate of the calibration point in the calibration image are determined, and the coordinates corresponding to the calibration point in the calibration image are determined according to the abscissa and ordinate of the calibration point.

[0085] In some embodiments, first, the computer device calculates a first intermediate variable, i.e., P, through the abscissa of the ellipse 1 in the calibration image, the abscissa of the ellipse 2 in the calibration image, the abscissa of the ellipse 3 in the calibration image, the physical radius corresponding to the ellipse 1 in the hybrid calibration plate, the physical radius corresponding to the ellipse 2 in the hybrid calibration plate, and the physical radius corresponding to the ellipse 3 in the hybrid calibration plate. 2 . Second, the computer device calculates a second intermediate variable, i.e., K, through the abscissa of the ellipse 1 in the calibration image, the abscissa of the ellipse 2 in the calibration image, the physical radius corresponding to the ellipse 1 in the hybrid calibration plate, the physical radius corresponding to the ellipse 2 in the hybrid calibration plate, and the first intermediate variable. Then, the computer device calculates a third intermediate variable, i.e., L, according to the ordinate of the ellipse 1 in the calibration image, the ordinate of the ellipse 2 in the calibration image, the physical radius corresponding to the ellipse 1 in the hybrid calibration plate, the physical radius corresponding to the ellipse 2 in the hybrid calibration plate, and the first intermediate variable. It should be noted that in this application, the first intermediate variable, the second intermediate variable, and the third intermediate variable can be calculated through formula (1), formula (2), and formula (3) respectively.

[0086] After the computer device calculates the first intermediate variable, the second intermediate variable, and the third intermediate variable, it calculates the abscissa of the calibration point in the calibration image according to the abscissa of the ellipse 1 in the calibration image, the physical radius corresponding to the ellipse 1 in the hybrid calibration plate, the first intermediate variable, and the second intermediate variable. The computer device calculates the ordinate of the calibration point in the calibration image according to the ordinate of the ellipse 1 in the calibration image, the physical radius corresponding to the ellipse 1 in the hybrid calibration plate, the first intermediate variable, and the third intermediate variable. It should be noted that in this application, the abscissa of the calibration point in the calibration image and the ordinate of the calibration point in the calibration image can be calculated through formula (4) and formula (5) respectively.

[0087]

[0088]

[0089]

[0090]

[0091]

[0092] where P 2 , K, and L are all intermediate variables used to calculate the coordinates of the calibrated calibration points, and u c refers to the abscissa of the calibrated calibration point, and v c refers to the ordinate of the calibrated calibration point. (u c , v c ) refers to the coordinates of the calibrated calibration point.

[0093] In some embodiments, the method for determining the calibration parameters of the present application specifically further includes but is not limited to: calculating the reprojection error of the calibration image according to the image acquisition calibration parameters; constructing a cost function based on the reprojection error and the image acquisition calibration parameters; and optimizing the image acquisition calibration parameters with the goal of minimizing the cost function to obtain the optimized image acquisition calibration parameters.

[0094] Among them, the reprojection error refers to the difference between the projection and reprojection of a real three-dimensional space point on the plane of the calibration image. The projection of the real three-dimensional space point on the plane of the calibration image refers to the pixel point on the calibration image, and the reprojection refers to the virtual pixel point obtained based on the image acquisition calibration parameters.

[0095] Specifically, the computer device extracts the pixel coordinates of the position of the calibrated calibration point in the calibration image, and performs inverse calculation based on the coordinates of the calibration point in the calibration coordinate system where the hybrid calibration board is located and the image acquisition calibration parameters to obtain new pixel coordinates. Then, the computer device calculates the sum of the two-norms of the pixel coordinates of the position of the calibrated calibration point and the new pixel coordinates and takes the average value to obtain the reprojection error of the calibration image. After the computer device calculates the reprojection error, it constructs a cost function based on the reprojection error and the image acquisition calibration parameters, and then minimizes the cost function to optimize the single mapping transformation matrix, thereby further optimizing the image acquisition calibration parameters calculated based on the single mapping transformation matrix to obtain the optimized image acquisition calibration parameters. By optimizing the image acquisition calibration parameters through the reprojection error, the present application can simultaneously consider the calculation error of the single mapping transformation matrix and the measurement error of the calibration point position, so its accuracy will be higher.

[0096] In some embodiments, assuming that the internal parameters of the image acquisition device are K, and the external parameters R kca and t kca from the coordinate system where the calibration image is located to the coordinate system where the hybrid calibration board is located, a first optimization can be performed using the coordinates obtained from the position of the calibration point of the calibration parameters as a constraint. The specific cost function is shown in formula (6):

[0097] r rpj = K(R kca X ia + t kca ) - m ik(6)

[0098] Among them, K() represents projecting the three-dimensional space coordinates in the device coordinate system where the image acquisition device is located onto the two-dimensional image coordinates of the calibration image through the device internal parameters. ia represents the three-dimensional coordinates of the position of the i-th calibration point to be optimized, m ik represents the two-dimensional image coordinate position detected on the k-th calibration image at the position of the i-th calibration point.

[0099] In some other embodiments, the motion change of the hybrid calibration plate can also be used as a constraint for secondary optimization, that is, the three-dimensional point in the world coordinate system is X w , and the three-dimensional point in the device coordinate system where the image acquisition device is located is c , then the relationship between the device coordinate system and the world coordinate system is shown in formula (7):

[0100] X c = R cw (X w - c cw ) (7)

[0101] Among them, R cw is the orientation of the image acquisition device, and c cw is the coordinate of the center of the image acquisition device in the world coordinate system.

[0102] In some embodiments, assuming that the three-dimensional point in the calibration plate coordinate system of the hybrid calibration plate is X a , then at the k-th moment of each photographing of the hybrid calibration plate by the image acquisition device, w and X a The relationship is shown in formula (8):

[0103] X w = R kwa (X a - c wa ) (8)

[0104] Among them, kwa is the rotation of the calibration plate relative to the world coordinate system, wa is the offset of the calibration plate coordinate system relative to the world coordinate system. At this time, the transformation relationship between the device coordinate system where the image acquisition device is located and the calibration plate coordinate system at the k-th moment of each photographing can be deduced, as shown in formula (9):

[0105] X c = R cw R kwa X a - R cw (c cw + R kwa c wa) (9)

[0106] Analyze and transform formulas (6) to (10), and change the final reprojection error to rpjt , and the specific calculation process is shown in formula (10). According to the finally calculated reprojection error, the image acquisition calibration parameters can be further optimized to improve the calibration accuracy.

[0107] r rpjt = K(R cw R kwa X ia -R cw (c cw +R kwa c wa )) - m ik (10)

[0108] In some embodiments, the first calibration reference object in the hybrid calibration plate is an ArUco pattern, and the second calibration reference object is a concentric circle pattern. As Figure 4 shown, the method for determining the calibration parameters of the present application specifically further includes but is not limited to the following steps:

[0109] Step 402, obtain the calibration images obtained by image acquisition of the hybrid calibration plate.

[0110] Step 404, roughly locate the position of the concentric circle pattern in the calibration image to obtain the reference object image.

[0111] In some embodiments, the computer device can obtain the corner calibration coordinates of the ArUco pattern in the calibration coordinate system where the hybrid calibration plate is located. According to the positional relationship between the corner image coordinates and the corner calibration coordinates of the ArUco pattern in the image coordinate system where the calibration image is located, determine the mapping conversion relationship. According to the mapping conversion relationship, map the calibration image to the plane where the calibration plate template image is located in the calibration coordinate system to obtain a reference image. Compare the position of the concentric circle pattern in the reference image with the concentric circle pattern in the calibration plate template image to determine the coding identifier of the concentric circle pattern in the reference image. Based on the mapping conversion relationship, reverse-map the position information corresponding to the coding identifier to the calibration image to locate the reference object image corresponding to the concentric circle pattern in the calibration image.

[0112] Step 406, perform elliptical edge detection on the reference object image to obtain the initial calibration point positions of the reference circle contours in the reference object image.

[0113] In some embodiments, the reference object image is binarized to obtain a binarized image. Edge detection is performed on the binarized image to extract the preliminary edge contour of the binarized image. Fitting processing is performed on the preliminary edge contour to obtain a plurality of reference circle contours. The center coordinates corresponding to the reference circle contour in the reference object image are obtained as the initial calibration point positions.

[0114] Step 408, perform eccentricity error correction on the initial calibration point positions to obtain the corrected calibration point positions.

[0115] In some embodiments, the calibration circle contour matching the reference circle contour is determined from the hybrid calibration plate. Eccentricity error correction is performed according to the initial calibration point positions and the physical radii corresponding to the calibration circle contour in the hybrid calibration plate to obtain the corrected calibration point positions.

[0116] Step 410, based on the corrected calibration point positions, determine the image acquisition calibration parameters corresponding to the hybrid calibration plate.

[0117] Step 412, optimize the image acquisition calibration parameters.

[0118] In some embodiments, the reprojection error of the hybrid calibration plate is calculated according to the image acquisition calibration parameters. A cost function is constructed based on the reprojection error and the image acquisition calibration parameters. With the goal of minimizing the cost function, the image acquisition calibration parameters are optimized to obtain the optimized image acquisition calibration parameters.

[0119] It should be understood that although the steps in the flowcharts involved in the above-described embodiments are shown in sequence according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear indication in this article, the execution of these steps has no strict order limit, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-described embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be executed alternately or alternately with at least a part of other steps or steps in other steps.

[0120] Based on the same inventive concept, an embodiment of the present application also provides a calibration parameter determination device for implementing the above-mentioned calibration parameter determination method. The implementation solution provided by this device to solve problems is similar to the implementation solution described in the above method. Therefore, the specific limitations in one or more embodiments of the calibration parameter determination device provided below can refer to the limitations on the calibration parameter determination method in the above text, and will not be repeated here.

[0121] In some embodiments, the present application further provides a hybrid calibration board, which includes a board body. The board body has a planar structure, and at least one first calibration reference object and at least one second calibration reference object are provided on the surface of the board body; the first calibration reference object is an object whose corner positions do not undergo perspective deformation, and the first calibration reference object and the second calibration reference object are arranged at intervals on the surface of the board body.

[0122] In some embodiments, both the first calibration reference object and the second calibration reference object are multiple; the multiple first calibration reference objects are arranged in central symmetry on the surface of the board body; the multiple second calibration reference objects are arranged in central symmetry on the surface of the board body.

[0123] In some embodiments, the first calibration reference object is a rectangular pattern, and the second calibration reference object is a concentric circle pattern.

[0124] In some embodiments, as Figure 5 shown, a calibration parameter determination device is provided, including: an image acquisition module 502, an image determination module 504, a position correction module 506, and a parameter determination module 508, where:

[0125] The image acquisition module 502 is configured to acquire a calibration image obtained by performing image acquisition on the hybrid calibration board; the hybrid calibration board includes a first calibration reference object and a second calibration reference object; the corner positions of the first calibration reference object do not undergo perspective deformation;

[0126] The image determination module 504 is configured to determine a reference object image corresponding to the second calibration reference object from the calibration image according to the corner positions of the corners of the first calibration reference object in the calibration image;

[0127] The position correction module 506 is configured to determine the initial calibration point position of the second calibration reference object according to the reference object image and correct the initial calibration point position;

[0128] The parameter determination module 508 is configured to determine the image acquisition calibration parameters corresponding to the hybrid calibration board based on the calibrated calibration point positions.

[0129] In the above calibration parameter determination device, a calibration image obtained by acquiring an image of a mixed calibration board is obtained; the mixed calibration board includes a first calibration reference object and a second calibration reference object; the positions of the corner points of the first calibration reference object do not undergo perspective distortion; according to the positions of the corner points of the first calibration reference object in the calibration image, a reference object image corresponding to the second calibration reference object is determined from the calibration image; the initial calibration point coordinates of the second calibration reference object are determined according to the reference object image, and the initial calibration point coordinates are corrected; based on the corrected calibration point coordinates, the image acquisition calibration parameters corresponding to the mixed calibration board are determined. The present application designs a mixed calibration board including different calibration reference objects, and proposes a brand-new calibration parameter determination method based on the mixed calibration board, that is, the second calibration reference object image is accurately determined from the calibration image through the first calibration reference object whose corner point position does not undergo perspective distortion, thereby ensuring the accuracy of the initial calibration point position obtained based on the second calibration reference object; correcting the initial calibration point position can also effectively improve the accuracy of the corrected calibration point position, thereby improving the accuracy of the calibration parameters.

[0130] In some embodiments, the corner point position is the corner point image coordinates of the corner points of the first calibration reference object in the image coordinate system where the calibration image is located. The image determination module 504 includes a coordinate acquisition unit, a relationship determination unit, and an image positioning unit. The coordinate acquisition unit is used to acquire the corner point calibration coordinates of the corner points of the first calibration reference object in the calibration coordinate system where the mixed calibration board is located; the relationship determination unit is used to determine the mapping conversion relationship according to the positional relationship between the corner point image coordinates and the corner point calibration coordinates; the mapping conversion relationship is used to implement the mapping conversion between the plane where the calibration image is located and the plane where the calibration board template image is located in the calibration coordinate system; the image positioning unit is used to locate the reference object image corresponding to the second calibration reference object from the calibration image according to the mapping conversion relationship and the calibration board template image.

[0131] In some embodiments, the image positioning unit is further used to map the calibration image to the plane where the calibration board template image is located in the calibration coordinate system according to the mapping conversion relationship to obtain a reference image; compare the positions of the second calibration reference object in the reference image and the second calibration reference object in the calibration board template image to determine the coding identifier of the second calibration reference object in the reference image; the coding identifier has a uniquely corresponding position information; based on the mapping conversion relationship, the position information corresponding to the coding identifier is inversely mapped to the calibration image to locate the reference object image corresponding to the second calibration reference object from the calibration image.

[0132] In some embodiments, the second calibration reference object is a concentric circle pattern, and the position correction module includes a contour extraction unit and a position determination unit. The contour extraction unit is configured to extract a plurality of reference circle contours of the concentric circle pattern from the reference object image; the position determination unit is configured to obtain the center coordinates corresponding to the reference circle contours in the reference object image as the initial calibration point positions.

[0133] In some embodiments, the contour extraction unit is further configured to perform binarization processing on the reference object image to obtain a binarized image; perform edge detection on the binarized image to extract a preliminary edge contour of the binarized image; and perform fitting processing on the preliminary edge contour to obtain a plurality of reference circle contours.

[0134] In some embodiments, the position correction module is further configured to determine a calibration circle contour matching the reference circle contour from the hybrid calibration plate; and perform eccentricity error correction based on the initial calibration point position and the physical radius corresponding to the calibration circle contour in the hybrid calibration plate to obtain the corrected calibration point position.

[0135] In some embodiments, the calibration parameter determination device further includes a parameter optimization module. The parameter optimization module is configured to calculate the reprojection error of the calibration image according to the image acquisition calibration parameters; construct a cost function based on the reprojection error and the image acquisition calibration parameters; and optimize the image acquisition calibration parameters with the goal of minimizing the cost function to obtain the optimized image acquisition calibration parameters.

[0136] Each module in the above calibration parameter determination device can be implemented in whole or in part by software, hardware, and their combination. Each of the above modules can be embedded in the processor of the computer device in hardware form or independent of it, or stored in the memory of the computer device in software form, so as to facilitate the processor to call and execute the operations corresponding to each of the above modules.

[0137] In some embodiments, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as Figure 6 shown. The computer device includes a processor, a memory, and a network interface connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data related to the calibration parameters. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, it implements a calibration parameter determination method.

[0138] Those skilled in the art can understand, Figure 6The structure shown is only a block diagram of some structures related to the solution of this application, and does not constitute a limitation on the computer device to which the solution of this application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0139] In some embodiments, a computer device is further provided, including a memory and a processor. A computer program is stored in the memory, and when the processor executes the computer program, the steps in the above method embodiments are implemented.

[0140] In some embodiments, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0141] In some embodiments, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0142] Those of ordinary skill in the art can understand that all or part of the processes in the above-described method embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the method embodiments as described above. Among them, any reference to a memory, database, or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memories. Non-volatile memories can include read-only memory (ROM), magnetic tapes, floppy disks, flash memories, optical memories, high-density embedded non-volatile memories, resistive random access memories (ReRAM), magnetoresistive random access memories (MRAM), ferroelectric random access memories (FRAM), phase change memories (PCM), graphene memories, etc. Volatile memories can include random access memory (RAM) or external cache memories, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the embodiments provided in the present application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the embodiments provided in the present application can be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, data processing logics based on quantum computing, etc., without limitation.

[0143] The technical features of the above embodiments can be combined arbitrarily. For the sake of concise description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope described in this specification.

[0144] The above-described embodiments merely represent several implementation manners of the present application. Their descriptions are relatively specific and detailed, but they should not be construed as limiting the patent scope of the present application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

Claims

1. A method for determining calibration parameters, characterized in that, The method includes: Obtaining a calibration image acquired by image acquisition of a hybrid calibration board; the hybrid calibration board includes a first calibration reference object and a second calibration reference object; the positions of the corner points of the first calibration reference object do not undergo perspective deformation; Determining a mapping conversion relationship according to the positional relationship between the corner point positions of the corner points of the first calibration reference object in the calibration image and the corner point calibration coordinates; the corner point positions are the corner point image coordinates of the corner points of the first calibration reference object in the image coordinate system where the calibration image is located; the corner point calibration coordinates are the corner point calibration coordinates of the corner points of the first calibration reference object in the calibration coordinate system where the hybrid calibration board is located; Mapping the calibration image to the plane where the calibration board template image is located in the calibration coordinate system according to the mapping conversion relationship to obtain a reference image; the calibration board template image is a top view obtained by photographing only the hybrid calibration board in a plane parallel to the plane where the hybrid calibration board is located; Comparing the positions of the second calibration reference object in the reference image with the second calibration reference object in the calibration board template image to determine the coding identifier of the second calibration reference object in the reference image; the coding identifier has a uniquely corresponding position information; Based on the mapping conversion relationship, inversely mapping the position information corresponding to the coding identifier to the calibration image to locate the reference object image corresponding to the second calibration reference object in the calibration image; Determining the initial calibration point position of the second calibration reference object according to the reference object image and correcting the initial calibration point position; Based on the calibrated calibration point position, determining the image acquisition calibration parameters corresponding to the hybrid calibration board.

2. The method according to claim 1, characterized in that, The second calibration reference object is a concentric circle pattern; the determining the initial calibration point position of the second calibration reference object according to the reference object image includes: Extracting a plurality of reference circle contours of the concentric circle pattern from the reference object image; Obtaining the center coordinates corresponding to the reference circle contour in the reference object image as the initial calibration point position.

3. The method according to claim 2, wherein The extracting a plurality of reference circle contours of the concentric circle pattern from the reference object image includes: Performing binarization processing on the reference object image to obtain a binarized image; Performing edge detection on the binarized image to extract the preliminary edge contour of the binarized image; Performing fitting processing on the preliminary edge contour to obtain a plurality of reference circle contours.

4. The method according to claim 3, characterized in that, The correcting the initial calibration point position includes: Determining a calibration circle contour in the hybrid calibration board that matches the reference circle contour; Performing eccentricity error correction according to the initial calibration point position and the physical radius corresponding to the calibration circle contour in the hybrid calibration board to obtain the calibrated calibration point position.

5. The method according to any one of claims 1 to 4, characterized in that The method further includes: Calculating the reprojection error of the calibration image according to the image acquisition calibration parameters; Constructing a cost function based on the reprojection error and the image acquisition calibration parameters; Taking minimizing the cost function as an optimization objective, optimizing the image acquisition calibration parameters to obtain optimized image acquisition calibration parameters.

6. A hybrid calibration plate according to any one of the methods of claims 1 to 5, characterized in that Including: A plate body; the plate body has a planar structure; at least one first calibration reference object and at least one second calibration reference object are provided on the surface of the plate body; the first calibration reference object is an object whose corner positions do not undergo perspective deformation. The first calibration reference object and the second calibration reference object are arranged at intervals on the surface of the plate body.

7. The hybrid calibration plate according to claim 6, characterized in that, Both the first calibration reference object and the second calibration reference object are multiple; multiple first calibration reference objects are arranged in central symmetry on the surface of the plate body; multiple second calibration reference objects are arranged in central symmetry on the surface of the plate body.

8. The hybrid calibration plate according to claim 7, wherein, The first calibration reference object is a rectangular pattern, and the second calibration reference object is a concentric circle pattern.

9. A calibration parameter determination device, characterized in that, The device includes: An image acquisition module for acquiring a calibration image obtained by performing image acquisition on a mixed calibration plate; the mixed calibration plate includes a first calibration reference object and a second calibration reference object; the corner positions of the first calibration reference object do not undergo perspective deformation. An image determination module for determining a mapping conversion relationship according to the positional relationship between the corner positions of the corners of the first calibration reference object in the calibration image and the corner calibration coordinates; the corner positions are the corner image coordinates of the corners of the first calibration reference object in the image coordinate system where the calibration image is located; the corner calibration coordinates are the corner calibration coordinates of the corners of the first calibration reference object in the calibration coordinate system where the mixed calibration plate is located; according to the mapping conversion relationship, mapping the calibration image to the plane where the calibration plate template image in the calibration coordinate system is located to obtain a reference image; the calibration plate template image is a top view obtained by only photographing the mixed calibration plate in a plane parallel to the plane where the mixed calibration plate is located; comparing the positions of the second calibration reference object in the reference image with the second calibration reference object in the calibration plate template image to determine the coding identifier of the second calibration reference object in the reference image; the coding identifier has a uniquely corresponding position information; based on the mapping conversion relationship, inversely mapping the position information corresponding to the coding identifier to the calibration image to locate the reference object image corresponding to the second calibration reference object in the calibration image. A position correction module for determining the initial calibration point position of the second calibration reference object according to the reference object image and correcting the initial calibration point position. A parameter determination module for determining the image acquisition calibration parameters corresponding to the mixed calibration plate based on the calibrated calibration point positions.

10. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 5.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the method according to any one of claims 1 to 5.

Images