Calibration plate, calibration method and system

Abstract

The present invention discloses a calibration plate, comprising a chessboard unit arranged on the surface of the calibration plate, wherein: each of the chessboard units is individually provided with at least one dot; the dots at least include a first characteristic dot and a second characteristic dot, the first characteristic dot and the second characteristic dot are arranged on the chessboard unit according to a random rule or a specific rule, and the diameter of the first characteristic dot is greater than the diameter of the second characteristic dot. The calibration plate of the present invention utilizes the characteristics of high detection accuracy and strong anti-blurring ability of dot marking, and combines with the corner points of the chessboard unit to improve the stability and accuracy of the calibration plate detection.

Description

Technical Field

[0001] The present invention relates to the technical fields of image processing, computer vision and camera calibration, and in particular to a calibration plate, a calibration method and a system. Background Art

[0002] Calibration plates are widely used in machine vision, image measurement, photogrammetry, and 3D reconstruction. By taking an image of a calibration plate with a fixed-pitch pattern array by a camera, the geometric model of the camera can be obtained through calculation by the calibration algorithm, thereby obtaining high-precision measurement and reconstruction results.

[0003] In the process of camera calibration, the most widely used method is to use a chessboard. However, this chessboard has no directionality and cannot be blocked. It is required that the image captured during camera calibration must contain the entire chessboard and all corner points on the chessboard can be detected, otherwise the data collected by the calibration camera is invalid. During the calibration process, the existing improved ChArco calibration plate has low accuracy in the position of corner points, and if the camera focal length becomes smaller, the collected image will be blurred, which can easily lead to the failure to detect corner points.

[0004] The disclosure of the above background technology content is only used to assist in understanding the inventive concept and technical solution of the present invention. It does not necessarily belong to the prior art of this patent application. In the absence of clear evidence that the above content has been disclosed on the filing date of this patent application, the above background technology should not be used to evaluate the novelty and creativity of the present application. Summary of the invention

[0005] The object of the present invention is to provide a calibration plate, a calibration method and a system to solve at least one of the above-mentioned background technical problems.

[0006] To achieve the above object, the technical solution of the embodiment of the present invention is implemented as follows:

[0007] A calibration plate, comprising a checkerboard unit arranged on the surface of the calibration plate, wherein:

[0008] At least one dot is individually arranged in each of the chessboard cells;

[0009] The dots include at least a first characteristic dot and a second characteristic dot, the first characteristic dot and the second characteristic dot are arranged on the checkerboard unit according to a random rule or a specific rule, and the diameter of the first characteristic dot is greater than the diameter of the second characteristic dot.

[0010] In some embodiments, the centers of the first characteristic dots and the second characteristic dots are centroids, wherein the centroids of the characteristic dots have perspective invariance, and the centroids of characteristic dots of different diameters have positioning information of the checkerboard unit.

[0011] In some embodiments, the checkerboard unit includes black and white square grids, wherein the intersection points of the black squares are the corner points of the checkerboard unit.

[0012] Another technical solution of the embodiment of the present invention is:

[0013] A calibration method comprises the following steps:

[0014] S1: Acquire a calibration image of a calibration plate captured by a camera; wherein the calibration plate comprises checkerboard units arranged on a surface of the calibration plate, and each checkerboard unit is individually provided with at least one dot; the dots comprise at least a first characteristic dot and a second characteristic dot, and the diameter of the first characteristic dot is greater than the diameter of the second characteristic dot;

[0015] S2: Determine the position of the calibration plate in the calibration image and detect the dots on the calibration plate;

[0016] S3: gridding the detected dots based on the checkerboard unit to obtain a first two-dimensional matrix;

[0017] S4: Based on the first two-dimensional matrix, binarize the detected dots according to their types to obtain a second two-dimensional matrix;

[0018] S5: Matching the second two-dimensional matrix with the preset calibration plate number template matrix to obtain the center of mass coordinate number information of the second two-dimensional matrix;

[0019] S6: According to the dot centroid coordinate numbering information obtained in step S5, the corresponding corner point numbering information of the chessboard unit where the dot is located is output, and the calibration data is obtained by solving the preset calibration algorithm according to the dot centroid coordinate numbering information, the chessboard corner point numbering information and the corresponding camera model.

[0020] In some embodiments, in step S1, the calibration plate is placed within the field of view of a camera, and the camera is used to perform imaging processing at multiple preset distances to obtain multiple calibration images containing the calibration plate.

[0021] In some embodiments, in step S3, based on the checkerboard units, each dot detected to meet the preset requirements is connected into a grid to obtain the first two-dimensional matrix.

[0022] In some embodiments, in step S4, based on the first two-dimensional matrix, the diameter of the detected dots that meet the requirements is judged. If the detected dots are first characteristic dots, the values ​​of the corresponding positions in the first two-dimensional matrix remain unchanged. If the detected dots are second characteristic dots, the values ​​of the corresponding positions in the first two-dimensional matrix change, thereby obtaining the second two-dimensional matrix.

[0023] In some embodiments, in step S5, the second two-dimensional matrix is ​​matched with a preset calibration plate number template matrix, wherein the preset calibration plate number template has the same size as the calibration plate used to obtain the calibration image and the same dot arrangement.

[0024] In some embodiments, in step S5, the second two-dimensional matrix is ​​traversed in sequence, and the second two-dimensional matrix is ​​matched with the preset calibration plate number template matrix. If the match is successful, the detected orientation information of the center of mass of the dots is output according to the orientation information of the center of mass of the dots on the preset calibration plate number template.

[0025] Another technical solution of the embodiment of the present invention is:

[0026] A calibration system includes the calibration board, camera, processor and memory described in the above technical solution; wherein:

[0027] The camera is used to capture a calibration image of the calibration plate;

[0028] The memory is used to store executable instructions for executing the calibration method;

[0029] The processor is used to read executable instructions from the memory, and calibrate the corresponding camera model using the calibration image to obtain calibration data.

[0030] The beneficial effects of the technical solution of the present invention are:

[0031] The calibration plate of the present invention utilizes the characteristics of high detection accuracy and strong anti-blurring ability of dot markings, and combines them with the corner points of the checkerboard units to improve the stability and accuracy of calibration plate detection. Even if the calibration plate is partially blocked or exceeds the camera field of view, camera calibration can be performed normally, and calibration mapping is more flexible. It is also suitable for evaluating and verifying the performance of calibration results. The accuracy of the calibration data is evaluated through the obtained calibration data and camera model using indicators such as reprojection error and calibration plate reconstruction. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0033] Figure 1 It is a structural schematic diagram of a calibration board provided according to an embodiment of the present invention.

[0034] Figure 2 is a flow chart of a calibration method provided according to an embodiment of the present invention.

[0035] Figure 3 is a two-dimensional matrix schematic diagram of a calibration method provided according to an embodiment of the present invention.

[0036] Figure 4 is a schematic diagram of a calibration system provided according to another embodiment of the present invention. DETAILED DESCRIPTION

[0037] In order to make the technical problems, technical solutions and beneficial effects to be solved by the embodiments of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0038] It should be noted that when a component is referred to as being "fixed to" or "disposed on" another component, it can be directly on the other component or indirectly on the other component. When an element is referred to as being "connected to" another element, it can be directly connected to the other element or indirectly connected to the other element. In addition, connection can be used for fixing or for circuit connection.

[0039] It should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating the orientation or position relationship, are based on the orientation or position relationship shown in the accompanying drawings, and are only for the convenience of describing the embodiments of the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention.

[0040] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of the embodiments of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0041] Reference Figure 1 As shown, Figure 1 The schematic diagram of the structure of a calibration plate provided according to an embodiment of the present invention. The calibration plate 100 is provided with checkerboard units 101 on its surface, and at least one dot is individually provided in each checkerboard unit 101; wherein the dots at least include a first characteristic dot 102 and a second characteristic dot 103, and the first characteristic dot 102 and the second characteristic dot 103 are arranged on the checkerboard according to a random rule or a specific rule, and the diameter of the first characteristic dot 102 is greater than the diameter of the second characteristic dot 103. It should be understood that the dots may include three or more characteristic dots, and each characteristic dot has a different diameter. The present invention is only described with two characteristic dots of different diameters, and is not limited here.

[0042] In one embodiment, the checkerboard unit 101 includes black and white square grids, wherein the intersection of the black grid is the corner point 104 of the checkerboard unit 101; the center of the first characteristic dot 102 and the second characteristic dot 103 is the center of mass, the center of mass of the characteristic dot has perspective invariance, and the center of mass of characteristic dots of different diameters has the positioning information of the checkerboard unit 101; for example, the dots are similar to binary encoding, the first characteristic dot is 1, and the second characteristic dot is 0, then a local area of ​​the calibration plate is equivalent to a two-dimensional code, so that the calibration plate 100 has directionality, so that the calibration plate 100 has the characteristic of allowing the local view to be blocked when applied. It should be understood that this embodiment does not make any special restrictions on the specific color of the checkerboard, as long as the contrast between the checkerboard unit and the interval color is greater than a certain preset threshold. This preset threshold can be set by itself according to the intensity of the contrast to meet the camera calibration requirements.

[0043] The embodiments of the present invention utilize the characteristics of high detection accuracy and strong anti-blurring ability of dot markers, and combine them with the corner points of the checkerboard units to improve the stability and accuracy of calibration plate detection. Even if the calibration plate is partially blocked or exceeds the camera field of view, camera calibration can be performed normally, and calibration mapping is more flexible. It is also suitable for evaluating and verifying the performance of calibration results. The accuracy of the calibration data is evaluated through the obtained calibration data and camera model using indicators such as reprojection error and calibration plate reconstruction.

[0044] Reference Figure 2 As shown, Figure 2 This is a flow chart of a calibration method proposed based on the calibration board 100 of the above embodiment, and the method includes the following steps:

[0045] S1: Acquire a calibration image of the calibration plate of the above embodiment taken by a camera;

[0046] S2: Determine the position of the calibration plate in the calibration image and detect the dots on the calibration plate;

[0047] S3: gridding the detected dots based on the checkerboard unit to obtain a first two-dimensional matrix;

[0048] S4: Based on the first two-dimensional matrix, binarize it according to the types of the detected dots to obtain a second two-dimensional matrix;

[0049] S5: Matching the second two-dimensional matrix with the preset calibration plate number template matrix to obtain the center of mass coordinate number information of the second two-dimensional matrix;

[0050] S6: According to the dot centroid coordinate numbering information obtained in step S5, the corresponding corner point numbering information of the chessboard unit where the dot is located is output, and the calibration data is obtained by solving the preset calibration algorithm according to the dot centroid coordinate numbering information, the chessboard corner point numbering information and the corresponding camera model.

[0051] Specifically, in step S1, the calibration plate is placed within the field of view of the camera, and the camera is used to perform imaging processing at multiple preset distances to obtain multiple calibration images containing the calibration plate; in one embodiment, the direction of the calibration plate or the camera and the distance between the two can be adjusted to obtain multiple sets of calibration images with rich coordinate information at different positions, angles, and postures using the camera; wherein the calibration image can be a complete calibration plate image or an incomplete calibration plate image. It is understandable that the camera in this embodiment can also be other imaging devices such as a video camera or a camera head, and can be a single imaging device or multiple imaging devices arranged in parallel. It is sufficient that the calibration plate is within the field of view of each of the multiple imaging devices, and the type and quantity of imaging are not limited in the embodiment of the present invention.

[0052] In step S2, the position of the calibration plate in the calibration image is random, and the size of the calibration plate in the calibration image will change with the distance of the position. Therefore, it is necessary to first determine the position of the calibration plate in the calibration image and then detect the dots on the calibration plate. The position and centroid of the dots on the calibration plate in the calibration image are detected using the Hough transform circle detection algorithm.

[0053] In step S3, on the basis of the checkerboard cells, each dot that meets the preset requirements is connected into a grid to obtain a first two-dimensional matrix. Figure 3 As shown in (a), the centroid is checked in the grid based on the checkerboard unit. If the centroid is detected, the corresponding position in the first two-dimensional matrix is ​​represented by a value of 1. If the centroid is not detected in the grid based on the checkerboard unit, the corresponding position in the first two-dimensional matrix is ​​represented by a value of -1. It should be understood that other values ​​can also be used to represent the result of the centroid detection in the first two-dimensional matrix, as long as it indicates whether the centroid exists in the current grid, and there is no limitation here.

[0054] In step S4, based on the first two-dimensional matrix obtained in step S3, the diameter of the dots that meet the requirements is judged, and the dots are divided into first characteristic dots and second characteristic dots according to their diameters. The diameter of the first characteristic dots is larger than that of the second characteristic dots. If the detected dots are first characteristic dots, the value of the corresponding position in the first two-dimensional matrix remains unchanged and is still 1. If the detected dots are second characteristic dots, the value of the corresponding position in the first two-dimensional matrix changes and becomes 0. Therefore, the following can be obtained: Figure 3 (b) The second two-dimensional matrix shown in FIG. It should be understood that other values ​​may be used to replace the values ​​at the corresponding positions in the first two-dimensional matrix. It is sufficient to indicate that the values ​​in the current first two-dimensional matrix have changed. This is not limited here.

[0055] In step S5, the second two-dimensional matrix is ​​matched with a preset calibration plate number template matrix, wherein the preset calibration plate number template has the same size as the calibration plate used to obtain the calibration image, and the dot arrangement is also the same, and the calibration plate number template has information such as checkerboard corner points, checkerboard size, and the orientation of the dot mass center in addition to the number information on each dot (such as (1, 2), (2, 3)). The second two-dimensional matrix is ​​traversed in sequence and matched with the preset calibration plate number template matrix, and the direction of the calibration plate can be calibrated according to the positional relationship of the dot mass center, and the position information of the dot mass center detected by the remaining checkerboard cells in the calibration image is gradually matched in a diffusion manner. If the match is successful, the orientation information of the detected dot mass center is output according to the orientation information of the dot mass center on the preset calibration plate number template.

[0056] In step S6, according to the dot centroid numbering information in step S5, the corner point numbering information corresponding to the chessboard unit where the dot is located is output, and the calibration data, such as the internal and external parameters of the camera and the lens distortion coefficient, are obtained by solving the dot centroid numbering information, the chessboard corner point numbering information, the corresponding camera model (such as the pinhole model) and the preset calibration algorithm.

[0057] Reference Figure 4 As shown, Figure 4It is a calibration system based on the calibration method of the above-mentioned embodiment provided according to another embodiment of the present invention. System 400 includes a camera 401, a processor 402, a memory 403, and the calibration plate 100 in the above-mentioned embodiment. Among them, the camera 401 is used to shoot a calibration image containing the above-mentioned calibration plate 100; the processor 402 is used to read the executable instructions containing the above-mentioned calibration method from the memory, calibrate the corresponding camera model using the calibration image to obtain calibration data, and upload it to the memory 403 for storage; the memory 403 is used to store the executable instructions of the above-mentioned calibration method, and store the calibration data obtained by the processor 402. In some embodiments, the camera is controlled to capture images of the calibration plate at multiple preset distances to obtain multiple calibration images. In some embodiments, the calibration data obtained by the processor includes an intrinsic parameter matrix, an extrinsic parameter matrix, and a distortion parameter.

[0058] An embodiment of the present invention further provides a storage medium for storing a computer program, which at least performs the calibration method described above when executed.

[0059] The storage medium may be implemented by any type of volatile or non-volatile storage device, or a combination thereof. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a magnetic random access memory (FRAM), a flash memory, a magnetic surface memory, an optical disc, or a compact disc read-only memory (CD-ROM); the magnetic surface memory may be a disk memory or a tape memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example but not limitation, many forms of RAM are available, such as static random access memory (SRAM), synchronous static random access memory (SSRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), direct memory bus random access memory (DRRAM). The storage media described in the embodiments of the present invention are intended to include, but are not limited to, these and any other suitable types of memory.

[0060] It is to be understood that the above content is a further detailed description of the present invention in conjunction with specific / preferred embodiments, and it cannot be determined that the specific implementation of the present invention is limited to these descriptions. For those of ordinary skill in the technical field to which the present invention belongs, without departing from the concept of the present invention, it can also make several substitutions or modifications to these described embodiments, and these substitutions or modifications should be deemed to belong to the protection scope of the present invention. In the description of this specification, the description of reference terms "an embodiment", "some embodiments", "preferred embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention.

[0061] In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples without contradicting each other. Although the embodiments of the present invention and their advantages have been described in detail, it should be understood that various changes, substitutions and modifications can be made herein without departing from the scope defined by the appended claims.

[0062] Furthermore, the scope of the present invention is not intended to be limited to the particular embodiments of the processes, machines, manufactures, compositions of matter, means, methods, and steps described in the specification. One of ordinary skill in the art will readily appreciate that the above disclosures, processes, machines, manufactures, compositions of matter, means, methods, or steps, currently existing or to be developed, may be utilized to perform substantially the same functions as the corresponding embodiments described herein or to obtain substantially the same results as the embodiments described herein. Therefore, the appended claims are intended to include within their scope such processes, machines, manufactures, compositions of matter, means, methods, or steps.

Claims

1. A calibration method, characterized in that: The steps include: S1: Acquire a calibration image of a calibration plate captured by a camera; wherein the calibration plate comprises checkerboard units arranged on a surface of the calibration plate, and each checkerboard unit is individually provided with at least one dot; the dots comprise at least a first characteristic dot and a second characteristic dot, and the diameter of the first characteristic dot is greater than the diameter of the second characteristic dot; S2: Determine the position of the calibration plate in the calibration image and detect the dots on the calibration plate; S3: gridding the detected dots based on the checkerboard unit to obtain a first two-dimensional matrix; S4: Based on the first two-dimensional matrix, binarize the detected dots according to their types to obtain a second two-dimensional matrix; S5: Matching the second two-dimensional matrix with the preset calibration plate number template matrix to obtain the center of mass coordinate number information of the second two-dimensional matrix; S6: According to the dot centroid coordinate numbering information obtained in step S5, the corresponding corner point numbering information of the chessboard unit where the dot is located is output, and the calibration data is obtained by solving the preset calibration algorithm according to the dot centroid coordinate numbering information, the chessboard corner point numbering information and the corresponding camera model.

2. The calibration method according to claim 1, characterized in that: The centers of the first characteristic dots and the second characteristic dots are centroids, wherein the centroids of the characteristic dots have perspective invariance, and the centroids of characteristic dots with different diameters have positioning information of the checkerboard unit.

3. The calibration method according to claim 2, characterized in that: The chessboard unit includes black and white square grids, wherein the intersection points of the black square grids are the corner points of the chessboard unit.

4. The calibration method according to claim 1, characterized in that: In step S1, the calibration plate is placed within the field of view of a camera, and the camera is used to perform imaging processing at multiple preset distances to obtain multiple calibration images containing the calibration plate.

5. The calibration method according to claim 1, characterized in that: In step S3, based on the checkerboard units, each dot detected to meet the preset requirements is connected into a grid to obtain the first two-dimensional matrix.

6. The calibration method according to claim 1, characterized in that: In step S4, based on the first two-dimensional matrix, the diameter of the detected dots that meet the requirements is judged. If the detected dots are first characteristic dots, the values ​​of the corresponding positions in the first two-dimensional matrix remain unchanged. If the detected dots are second characteristic dots, the values ​​of the corresponding positions in the first two-dimensional matrix change, thereby obtaining the second two-dimensional matrix.

7. The calibration method according to claim 1, characterized in that: In step S5, the second two-dimensional matrix is ​​matched with a preset calibration plate number template matrix, wherein the preset calibration plate number template has the same size as the calibration plate used to obtain the calibration image and the same dot arrangement.

8. The calibration method according to claim 7, characterized in that: In step S5, the second two-dimensional matrix is ​​traversed in sequence, and the second two-dimensional matrix is ​​matched with the preset calibration plate number template matrix. If the match is successful, the detected orientation information of the center of mass of the circle dots is output according to the orientation information of the center of mass of the circle dots on the preset calibration plate number template.

9. A calibration system, characterized in that: It includes a calibration board, a camera, a processor and a memory; wherein, The camera is used to capture a calibration image of the calibration plate; The memory is used to store executable instructions of the calibration method according to any one of claims 1 to 8; The processor is used to read executable instructions from the memory, and calibrate the corresponding camera model using the calibration image to obtain calibration data.

Images