A calibration plate, a calibration plate identification method, a calibration plate identification device and a computer readable medium

Abstract

The present invention provides a calibration plate, a calibration plate identification method, device, equipment and computer-readable medium. It belongs to the field of camera calibration technology and solves the problems of low calibration accuracy and poor robustness of calibration plates in the prior art. It includes: 1. The calibration plate is provided with first concentric circular rings and second concentric circular rings distributed in a rectangular array along the row and column directions; the number of the first concentric circular rings includes at least four or more distributed at the four corners of the rectangular array, and the second concentric circular rings are distributed in the row and column directions in the area surrounded by the first concentric circular rings; wherein the outermost circle radius of the first concentric circular ring is greater than the outermost circle radius of the second concentric circular ring, and the distance between the centers of any adjacent concentric circular rings in the row and / or column directions is equal. The present invention can support camera calibration work in a variety of scenarios, improve the stability and accuracy of camera calibration work in various environments, and thus improve the accuracy of subsequent work.

Description

Technical Field

[0001] The present invention relates to the fields of computer vision and camera calibration, and in particular to a camera calibration plate that can be used for industrial purposes, and an identification method, device and computer-readable medium thereof. Background Art

[0002] One of the basic tasks of computer vision is to calculate the geometric information of objects in three-dimensional space from the image information obtained by the camera, and thus reconstruct and identify the objects. Camera calibration is the process of determining the internal geometric model parameters of the camera and the camera pose, and is an important step in establishing the relationship between the three-dimensional scene and the two-dimensional image. In recent decades, in order to improve the accuracy of camera calibration, many vision researchers have invested a lot of energy and proposed many excellent methods, which also provides a good theoretical solution to the camera calibration problem. As for the optimization of camera calibration, in addition to further improving the accuracy of the camera calibration method, it is also necessary to improve the robustness of the camera calibration method to adapt to calibration tasks in various environments.

[0003] The commonly used calibration method is to use the camera to be tested to shoot a calibration pattern consisting of black and white cells with different numbers of rows and columns (hereinafter referred to as a chessboard). Multiple groups of images with complete chessboard patterns are used as input, and the input is detected and the camera parameters (intrinsic and external parameters) are determined through image processing algorithms and calibration algorithms. However, the accuracy of this commonly used calibration method is not enough, that is, the detection accuracy of the chessboard corner points cannot meet the high-precision requirements in actual production and use; at the same time, for each image, the entire calibration plate must be included in full, so that its corner points can be sorted according to the predetermined arrangement rules, which has high requirements for the shooting scene and cannot adapt to relatively harsh or narrow environments; in addition, in a multi-purpose environment, in order to ensure rotation invariance, it is also necessary to put forward requirements for the design of the entire chessboard, which does not have strong universality. Summary of the invention

[0004] In view of this, embodiments of the present invention provide a calibration plate, a calibration plate recognition method, an apparatus, a device and a computer-readable medium, which solve the problem that the calibration plate cannot be adapted and the subsequent recognition accuracy is reduced in harsh scene environments.

[0005] The first aspect of the embodiment of the present invention provides a calibration plate, which is a plane calibration plate, and is provided with first concentric rings and second concentric rings distributed in a rectangular array along the row and column directions; the number of the first concentric rings includes at least four or more distributed at the four corners of the rectangular array, and the second concentric rings are distributed in the area surrounded by the first concentric rings along the row and column directions; wherein the outermost radius of the first concentric rings is greater than the outermost radius of the second concentric rings, and the distance between the centers of any adjacent concentric rings in the row and / or column directions is equal. The present invention uses a concentric ring pattern to replace a checkerboard pattern, and thereby improves the accuracy of key point recognition.

[0006] A second aspect of an embodiment of the present invention provides a calibration plate recognition method, including: taking a plane image of the calibration plate with a camera; obtaining the number of the first concentric circular rings according to the plane image; obtaining the center coordinates of the first concentric circular rings and the second concentric circular rings in the plane image according to an ellipse detection algorithm; calculating the homography matrix for converting the plane image into a bird's-eye view according to the center coordinates of the first concentric circular rings; and performing a projection transformation on the second concentric circular rings according to the homography matrix to obtain a bird's-eye view and number them.

[0007] A third aspect of an embodiment of the present invention provides a calibration plate recognition device, comprising a shooting module, for capturing a plane image of the calibration plate using a camera; a first recognition module, for obtaining the number of the first concentric circular rings based on the plane image; a detection module, for obtaining the center coordinates of the first concentric circular rings and the second concentric circular rings in the plane image based on an ellipse detection algorithm; a conversion module, for calculating a homography matrix for converting the plane image into a bird's-eye view based on the center coordinates of the first concentric circular rings; and a second recognition module, for performing a projection transformation on the second concentric circular rings based on the homography matrix, obtaining a bird's-eye view and numbering them.

[0008] A fourth aspect of an embodiment of the present invention provides a calibration device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned identification method when executing the computer program.

[0009] A fifth aspect of an embodiment of the present invention provides a computer-readable medium, wherein the computer-readable medium stores a computer program, and the computer program implements the steps of the above-mentioned identification method when being processed and executed.

[0010] Compared with the prior art, the camera calibration method provided by the present invention has the following effects:

[0011] The calibration plate provided by the present invention uses a circular ring pattern to replace a checkerboard pattern to improve the accuracy of key point recognition, and adopts a method of combining multiple layers of concentric rings with general concentric rings to improve the efficiency of subsequent recognition and arrangement.

[0012] The method adopted by the present invention arranges the concentric rings on the chessboard in a certain way, and the program has rotation invariance. It can make the calibration task still be completed smoothly when the calibration plate is blocked, so as to achieve higher robustness and adaptability to different scenes.

[0013] The method adopted by the present invention can identify the ID of a specific circular ring, realize the operation of converting a calibration plate in an image into a bird's-eye view, and correctly sort and number all identified key points.

[0014] The method of the present invention is applied to industrial robot parts grasping, has simple conditions, is applicable to a wide range of scenarios, and has important application value and research significance. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, 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.

[0016] Figure 1 This is a calibration plate sample diagram (I) provided in an embodiment of the present invention;

[0017] Figure 2 This is a calibration plate sample diagram (II) provided in an embodiment of the present invention;

[0018] Figure 3 It is the calibration plate sample diagram (III) provided in the embodiment of the present invention;

[0019] Figure 4 This is a calibration plate sample diagram (IV) provided in an embodiment of the present invention;

[0020] Figure 5 It is the calibration plate sample diagram (V) provided in the embodiment of the present invention;

[0021] Figure 6 is a schematic diagram of the first concentric ring structure in an embodiment of the present invention;

[0022] Figure 7 is a flow chart of a calibration plate identification method provided by an embodiment of the present invention;

[0023] Figure 8 is a schematic diagram of the detection results of the calibration plate provided by an embodiment of the present invention;

[0024] Fig. 9 is a schematic diagram of the coding result of the calibration plate provided in an embodiment of the present invention;

[0025] Fig.10 is a structural block diagram of a calibration plate identification device provided by an embodiment of the present invention;

[0026] Fig.11 It is a schematic diagram of a calibration plate identification device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0027] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present invention. However, it should be clear to those skilled in the art that the present invention may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present invention.

[0028] Obviously, the drawings described below are only some examples or embodiments of the present application. For ordinary technicians in this field, the present application can also be applied to other similar scenarios based on these drawings without creative work. In addition, it can also be understood that although the efforts made in this development process may be complicated and lengthy, for ordinary technicians in this field related to the content disclosed in this application, some changes in design, manufacturing or production based on the technical content disclosed in this application are just conventional technical means, and should not be understood as insufficient content disclosed in this application.

[0029] Reference to "embodiments" in this application means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those of ordinary skill in the art that the embodiments described in this application may be combined with other embodiments without conflict.

[0030] Unless otherwise defined, the technical terms or scientific terms involved in this application should be understood by people with ordinary skills in the technical field to which this application belongs. The words "one", "a", "a", "the" and the like involved in this application do not indicate a quantitative limitation, and may represent the singular or plural. The terms "include", "comprise", "have" and any of their variations involved in this application are intended to cover non-exclusive inclusions; for example, a process, method, system, product or device that includes a series of steps or modules (units) is not limited to the listed steps or units, but may also include steps or units that are not listed, or may also include other steps or units inherent to these processes, methods, products or devices. The words "connect", "connected", "coupled" and the like involved in this application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The "multiple" involved in this application refers to two or more. "And / or" describes the association relationship of associated objects, indicating that there may be three relationships, for example, "A and / or B" can represent: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the objects before and after are in an "or" relationship. The terms "first", "second", "third", etc. involved in this application are only used to distinguish similar objects and do not represent a specific ordering of the objects.

[0031] In order to illustrate the technical solution of the present invention, a specific embodiment is provided below for illustration.

[0032] A calibration plate is provided for an embodiment of the present invention. The calibration plate is a flat calibration plate. As for the structural material of the calibration plate, an alumina panel is used, which replaces the previous solution of using ordinary printing paper and plastic sheets. The alumina panel has the advantages of being non-reflective and not easy to deform. In actual scenarios, panels of this material can adapt to more different lighting conditions. The substrate of the calibration plate adopts an aluminum substrate with a honeycomb hollow structure, which replaces the ordinary plastic plate and glass substrate used in the previous stage. Compared with ordinary plastic plates, it is less likely to deform, has a certain weight, and is more stable; compared with glass substrates, its lighter weight can better adapt to the pressure of operators during image acquisition and transportation, and is more durable than glass materials.

[0033] Please refer to Figures 1 to 6, a panel pattern style of a calibration plate is provided, on which first concentric rings 1 and second concentric rings 2 are arranged in a rectangular array along the row and column directions; the number of the first concentric rings 1 includes at least four or more distributed at the four corners of the rectangular array, and the second concentric rings 2 are distributed in the area surrounded by the first concentric rings 1 along the row and column directions; wherein the radius of the outermost circle 11 of the first concentric ring 1 is greater than the radius of the outermost circle of the second concentric ring 2, and the distance between the centers of any adjacent concentric rings in the row and / or column directions is equal. In some specific embodiments, reference Figure 6 , the first concentric rings 1 include an outermost circle 11, at least one intermediate circle 12, and an innermost circle 13; wherein the innermost circle wraps a cross. In the entire calibration plate pattern, for any two of the first concentric rings 1, the radii of the innermost circle 13 and the outermost circle 11 are the same, and the radii of the intermediate circles 12 are different; for any two of the second concentric rings, the radii of all the circles they contain are equal. In other words, all the first concentric ring patterns are different, and all the second concentric ring patterns are the same. As a preferred embodiment, the second concentric rings use four rings and the first concentric rings use six rings, so that the accuracy and robustness of the pattern are better.

[0034] In the present invention, the main purpose of setting the first concentric ring is to distinguish it from the second concentric ring and to number all the rings. Specifically, each first concentric ring represents an accurate ID number. Using these ID numbers, each concentric ring can be numbered according to the arrangement mode of the current calibration plate.

[0035] In a specific embodiment, referring to Figure 1 The overall pattern is composed of 70 concentric rings, of which 16 larger concentric rings (the first concentric ring 1) are visible to the naked eye, and the 16 rings are 6 rings with different patterns, representing 16 different ID numbers. The remaining 54 rings can be identified as 4 rings. The center circle of each ring is designed to be black, in order to make the white cross in the middle (reference Figure 6 The middle cross structure is designed to be more obvious. The middle cross structure is designed to have a more accurate center value when walking a point (such as using a probe to accurately measure the position of the point) in scene applications, making the application scenarios of the entire board more extensive. In this design, for ease of operation, the distance between the centers of any two adjacent concentric circles in rows or columns, or in the row and column directions is set to be the same. In more extensive operations, the distance between two points can be set arbitrarily, that is, according to the idea of ​​this pattern design, more and more flexible pattern styles can be designed to meet the needs of different scenes and improve the high adaptability of the calibration board.

[0036] As reference Figures 2 to 4 The calibration board pattern provided. Figures 2 to 4 In the embodiment, all concentric rings form a rectangular array, wherein the four corners of the rectangle are respectively provided with first concentric rings, and the second concentric rings and the other first rings except the four corners are irregularly distributed in the area surrounded by the four corners, and it is only necessary to ensure that the distance between the centers of any two adjacent concentric rings in the row or column direction is the same (or in the X direction, the Y direction).

[0037] refer to Figure 5 In addition to the first and second concentric rings in the array on the left, there are two extra-large concentric rings on the right. This pattern is only used as an implementation example. The extra-large concentric rings are used for positioning. The first concentric ring in the pattern can rely on its own positioning role to realize the recognition of the calibration plate.

[0038] Figure 7 FIG. 1 is a flow chart of a calibration plate identification method provided by an embodiment of the present invention. Figure 7 The following steps are shown:

[0039] S101: photographing a planar image of the calibration plate using a camera.

[0040] S102: Acquire the serial number of the first concentric ring according to the planar image.

[0041] In the specific implementation of S102, an ellipse detection algorithm is used and the numbers of the ellipses are distinguished according to the relationship between the edges of the ellipses. Here, each circle in the ring can be approximately regarded as an ellipse, including:

[0042] Extract the edges of all ellipses according to the ellipse detection algorithm and fit the ellipses according to the edges;

[0043] Sorting the ellipses according to their radius to obtain the coding information of the ellipses;

[0044] The serial number of the first concentric rings is obtained according to the coding information.

[0045] In the present invention, after obtaining the first concentric ring number, refer to Figure 8 ,, the result is a bird's eye view with the first concentric ring numbering, with 0 as the upper left corner and 69 as the lower right corner.

[0046] S103: Acquire the center coordinates of the first concentric circular ring and the second concentric circular ring in the plane image according to an ellipse detection algorithm.

[0047] In the specific implementation of S103, all ellipse edges are extracted and ellipse equations are constructed according to the ellipse detection algorithm to obtain the center coordinates of each circle in the ring;

[0048] The center distance of each circle is calculated, and a center distance threshold is set. If the center distance is lower than the threshold, it can be considered that the two circles have the same center. Then, a fitting operation is performed on the center coordinates to obtain the center coordinates of the first concentric ring and the second concentric ring.

[0049] S104: Calculate a homography matrix for converting a planar image into a bird's-eye view according to the center coordinates of the first concentric circular rings.

[0050] In this embodiment, the homography matrix is:

[0051]

[0052] Among them, x and y represent the two-dimensional coordinates of the center of the first concentric ring before the bird's eye view is transformed, x′ and y′ represent the two-dimensional coordinates of the center of the first concentric ring after the bird's eye view is transformed, R is a 2×2 rotation matrix, and t is a 2×1 translation matrix.

[0053] In this process, after obtaining the center coordinates of the first concentric ring in the plane image and the center coordinates of the ring in the bird's-eye view after layout (the number is determined, and the center position of the ring in the bird's-eye view is determined), the parameters of the intermediate rotation matrix and translation matrix can be calculated according to the above formula, that is, the homography matrix is ​​obtained.

[0054] S105: Performing projection transformation on the second concentric rings according to the homography matrix, obtaining a bird's-eye view and numbering the image.

[0055] In the specific implementation of S105, the number T of the second concentric ring T is id The calculation formula is:

[0056]

[0057] P′ T .y=H -1 ×P T .y

[0058] P′ T .x=H -1 ×P T .x

[0059] Among them, P T is the coordinate of the second concentric ring in the plane image, H is the homography matrix from the plane image to the bird's-eye view; CHECKERBOARD represents two pieces of information including the number of rows and columns of the plane pattern; cols represents the column; step represents the distance between the centers of two adjacent rings, including the distance in the x-axis direction and the distance in the y-axis direction; P′ T are the coordinates of the second concentric ring in the bird's-eye view.

[0060] In the present invention, the identification method of the calibration plate first identifies all the large circles (first concentric circles), detects the numbers of all the large circles, and then sorts all the points with these numbers and converts them into a bird's-eye view. After converting to a bird's-eye view and sorting, a bird's-eye view with all the large circle numbers can be obtained, with 0 numbered as the upper left corner and 69 numbered as the lower right corner. And based on these large circles, according to the formula, the numbers of all the small circles (second concentric circles) are calculated and sorted according to the numbers of the large circles. Figure 8 To convert the bird's eye view effect, Fig. 9 This is the result of ellipse detection and numbering of the bird's-eye view. It can be seen that after four numbers are made using the first concentric rings, the second concentric rings are sorted and numbered according to the size of the numbers.

[0061] In the present invention, since it involves the operation of converting to a bird's-eye view, the actual requirement for the number of feature points is not that high. This also ensures the robustness of the calibration plate, that is, when the calibration plate is partially blocked, it can still meet the requirements of the entire algorithm. Converting to a bird's-eye view can also theoretically ensure that the center of the ellipse detected at this time can have a better effect, that is, its eccentricity error can be greatly reduced.

[0062] The calibration plate provided by the present invention uses a circular ring pattern to replace a checkerboard pattern to improve the accuracy of key point recognition, and adopts a method of combining multiple layers of concentric rings with general concentric rings to improve the efficiency of subsequent recognition and arrangement.

[0063] The method adopted by the present invention arranges the concentric rings on the chessboard in a certain way, and the program has rotation invariance. It can make the calibration task still be completed smoothly when the calibration plate is blocked, so as to achieve higher robustness and adaptability to different scenes.

[0064] The method adopted by the present invention can identify the ID of a specific circular ring, realize the operation of converting a calibration plate in an image into a bird's-eye view, and correctly sort and number all identified key points.

[0065] The method of the present invention is applied to industrial robot parts grasping, has simple conditions, is applicable to a wide range of scenarios, and has important application value and research significance.

[0066] Please refer to Fig.10 , Fig.10 is a structural block diagram of a calibration plate recognition device provided by an embodiment of the present invention. Fig.10 As shown, it includes a shooting module 101, a first recognition module 102, a detection module 103, a conversion module 104, and a second recognition module 105. The above modules are respectively used to execute Figure 7For details on the specific methods in S101, S102, S103, S104, and S105, see Figure 7 Here is just a brief description of the relevant introduction:

[0067] A shooting module 101 is used to shoot a planar image of the calibration plate using a camera;

[0068] A first recognition module 102, used to obtain the serial number of the first concentric ring according to the plane image;

[0069] A detection module 103, configured to obtain the center coordinates of the first concentric circular ring and the second concentric circular ring in the plane image according to an ellipse detection algorithm;

[0070] A conversion module 104, configured to calculate a homography matrix for converting a plane image into a bird's-eye view according to the coordinates of the center of the first concentric rings;

[0071] The second identification module 105 is used to perform projection transformation on the second concentric circular rings according to the homography matrix, obtain a bird's-eye view image and number it.

[0072] The present invention proposes a high-precision and high-robustness calibration plate by designing a calibration plate pattern and comparing calibration plates of different materials. The present invention uses a combination of special circular rings and ordinary circular rings to deal with the problem of possible occlusion in different scenes. The eccentricity error that occurs when detecting the center of the ellipse is reduced by converting the bird's-eye view, thereby improving the accuracy and robustness. The present invention can support camera calibration work in a variety of scenes, improve the stability and accuracy of camera calibration work in various environments, and thus improve the accuracy of subsequent work.

[0073] Fig.11 FIG. 1 is a schematic diagram of a calibration plate recognition device provided by an embodiment of the present invention. Fig.11 As shown, the calibration plate recognition device 14 of this embodiment includes: a processor 140, a memory 141, and a computer program 142 stored in the memory 141 and executable on the processor 140. When the processor 140 executes the computer program 142, the steps in the above method embodiment are implemented, for example, Figure 7 Alternatively, when the processor 140 executes the computer program 142, the functions of each module / unit in the above-mentioned device embodiments are realized, for example, Fig.10 The functions of modules 101 to 105 are shown.

[0074] Exemplarily, the computer program 142 may be divided into one or more modules / units, which are stored in the memory 141 and executed by the processor 140 to complete the present invention. The one or more modules / units may be a series of computer program instruction segments capable of completing specific functions, which are used to describe the execution process of the computer program 142 in the calibration plate recognition device 14. For example, the computer program 142 may be divided into modules 101 to 105. Modules in a virtual device.

[0075] The processor 140 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0076] The memory 141 may be an internal storage unit of the calibration plate recognition device 14, such as a hard disk or memory of the calibration plate recognition device 14. The memory 141 may also be an external storage device of the calibration plate recognition device 14, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the calibration plate recognition device 14. Further, the memory 141 may also include both an internal storage unit and an external storage device of the calibration plate recognition device 14. The memory 141 is used to store the computer program and other programs and data required by the calibration plate recognition device 14. The memory 141 may also be used to temporarily store data that has been output or is to be output.

[0077] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0078] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0079] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0080] In the embodiments provided by the present invention, it should be understood that the disclosed devices / terminal equipment and methods can be implemented in other ways. For example, the device / terminal equipment embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0081] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0082] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0083] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0084] In the above embodiments, the first calibration parameter, the second calibration parameter, the third calibration parameter, the first reprojection error, the second reprojection error, and the third reprojection error do not represent a certain numerical value, but are the current result, the result before the current result, and the next result in a cycle judgment or calibration. For the convenience of description, the present invention defines them as the first, second, and third in a cycle, which does not limit the embodiments of the present invention.

[0085] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A calibration plate recognition method, characterized in that: The calibration plate is a plane calibration plate, and is provided with first concentric circular rings and second concentric circular rings distributed in a rectangular array along row and column directions; The number of the first concentric circular rings includes at least four or more distributed at the four corners of the rectangular array, and the second concentric circular rings are distributed in the area surrounded by the first concentric circular rings along the row and column directions; The outermost radius of the first concentric rings is greater than the outermost radius of the second concentric rings, and the distances between the centers of any adjacent concentric rings in the row and / or column directions are equal; The method comprises: Taking a planar image of the calibration plate with a camera; Obtaining the serial number of the first concentric ring according to the plane image; Obtaining the center coordinates of the first concentric circle ring and the second concentric circle ring in the plane image according to the ellipse detection algorithm; Calculate the homography matrix for converting the plane image into the bird's-eye view according to the center coordinates of the first concentric ring; The second concentric rings are projected and transformed according to the homography matrix to obtain a bird's-eye view and number them; the second concentric rings T are numbered The calculation formula is: ； ； ； in, , Indicates the two-dimensional coordinates of the center of the first concentric circle before switching to the bird's-eye view. is the coordinate of the second concentric ring in the plane image, H is the homography matrix from the plane image to the bird's-eye view; CHECKERBOARD represents two pieces of information including the number of rows and columns of the plane pattern; cols represents the column; step represents the distance between the centers of two adjacent rings, including the distance in the x-axis direction and the distance in the y-axis direction; are the coordinates of the second concentric ring in the bird's-eye view.

2. The calibration plate recognition method according to claim 1, characterized in that: The first concentric rings include an outermost circle, at least one middle circle, and an innermost circle; for any two of the first concentric rings, the radii of the innermost circle and the outermost circle are the same, and the radii of the middle layer rings are different; for any two of the second concentric rings, the radii of all circles are equal.

3. The calibration plate recognition method according to any one of claims 1 or 2, characterized in that: Obtaining the serial number of the first concentric ring according to the plane image includes: According to the ellipse detection algorithm, the edges of all ellipses are extracted and ellipses are fitted according to the edges; each circle in the ring is approximately regarded as an ellipse; Sorting the ellipses according to their radius to obtain the coding information of the ellipses; The serial number of the first concentric rings is obtained according to the coding information.

4. The calibration plate recognition method according to claim 3, characterized in that: The center coordinates of the first concentric circle ring and the second concentric circle ring in the plane image are obtained according to the ellipse detection algorithm, including: According to the ellipse detection algorithm, all ellipse edges are extracted and the ellipse equation is constructed to obtain the coordinates of the center of each circle in the ring; each circle in the ring is approximately regarded as an ellipse; The center distance of each circle is calculated, and a center distance threshold is set. If the center distance is lower than the threshold, the center coordinates are processed to obtain the center coordinates of the first concentric ring and the second concentric ring.

5. The calibration plate recognition method according to claim 3, characterized in that: The homography matrix for converting the plane image into the bird's-eye view is calculated according to the center coordinates of the first concentric ring; including: The homography matrix is: ； in, , Indicates the two-dimensional coordinates of the center of the first concentric circle before switching to the bird's-eye view. , Indicates the two-dimensional coordinates of the center of the first concentric circle after the bird's-eye view is turned, is a 2×2 rotation matrix, is a 2×1 translation matrix.

6. A calibration plate recognition device, characterized in that: The method for realizing the calibration plate recognition method according to any one of claims 1 to 5 comprises: A shooting module, used for shooting a planar image of the calibration plate using a camera; A first recognition module, for obtaining the serial number of the first concentric ring according to the plane image; A detection module, used for obtaining the center coordinates of the first concentric circular ring and the second concentric circular ring in the plane image according to an ellipse detection algorithm; A conversion module, used for calculating a homography matrix for converting a plane image into a bird's-eye view according to the center coordinates of the first concentric rings; The second recognition module is used to perform projection transformation on the second concentric circular rings according to the homography matrix, obtain a bird's-eye view image and number it.

7. A calibration plate recognition device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.

8. A computer-readable medium storing a computer program, characterized in that: When the computer program is executed, the steps of the method according to any one of claims 1 to 5 are implemented.

Images