A calibration plate, a calibration method, a device and a medium for three-dimensional reconstruction

Abstract

The application discloses a kind of calibration plate for three-dimensional reconstruction, calibration method, equipment and medium, the system includes: calibration plate main body, first calibration area and second calibration area are equipped on calibration plate main body;First calibration area is arranged around second calibration area, and second calibration area is located in the center part of calibration plate main body;Several composite calibration areas are uniformly arranged on first calibration area;The application can reduce the number of pictures required for calibration, and can ensure the accuracy of calibration, under the premise of both, without large area calibration plate design is also needed, and the corresponding calibration field of view demand can be met, calibration efficiency and calibration convenience degree are higher, with strong applicability.

Description

Technical Field

[0001] This invention relates to the field of 3D camera calibration technology, and in particular to a calibration plate, calibration method, equipment and medium for 3D reconstruction. Background Technology

[0002] Camera calibration is a fundamental step in computer vision processes such as visual inspection and 3D reconstruction. The accuracy and precision of the calibration determine whether a 3D vision system can function properly, and it is also a key factor affecting accuracy in 3D reconstruction. The camera calibration process involves using the camera system to capture images of a calibration board. By combining the image coordinates of feature points with real-world coordinates, the intrinsic and extrinsic parameters of the camera system can be calculated.

[0003] In existing technologies, calibration boards used for camera calibration are mostly checkerboard or circular arrays:

[0004] Among them, checkerboard calibration mainly uses checkerboard grids to obtain corner points (i.e., the intersection of every four small squares) through the checkerboard grid. Using the edge of the checkerboard grid as a reference, all feature points in the image are obtained, and the camera system calibration results are obtained by analyzing the corner point positions. However, this method has poor accuracy in obtaining corner points, and the characteristics of the checkerboard grid also require high light source conditions, such as uniform lighting. The calibration accuracy is within 1%, and 20-50 images need to be taken. The calibration process is relatively complex, the calibration efficiency is low, and there is a large accuracy error.

[0005] Among them, circular array calibration mainly uses a circular array calibration board, which contains reference points. The reference points are used to confirm the direction and position the calibration board. By obtaining the position of the center of each circle in the circular array, the calibration of the camera system is calculated. However, such calibration boards generally have a large number of points, so they have good results for extrinsic camera calibration, but generally poor results for intrinsic parameters. Therefore, they require strict control over angles and attitudes. When the camera has a large field of view, the area of ​​the calibration board needs to be very large, making it difficult to guarantee both the accuracy and ease of use of the calibration board. On the other hand, if a smaller calibration board is used, multiple angles, distances, and attitudes are required, which is difficult to apply. Therefore, the existing circular array calibration board cannot balance ease of use and accuracy. Summary of the Invention

[0006] The purpose of this invention is to address the aforementioned problems in the prior art by providing a calibration plate, calibration method, device, and medium for three-dimensional reconstruction, thereby resolving the issue that the existing calibration plates and calibration methods cannot simultaneously achieve both ease of use and accuracy.

[0007] To solve the above-mentioned technical problems, the specific technical solution of the present invention is as follows:

[0008] On one hand, the present invention provides a calibration plate for three-dimensional reconstruction, comprising:

[0009] A calibration plate body, wherein a first calibration area and a second calibration area are provided on the calibration plate body;

[0010] The first calibration area is arranged around the second calibration area, and the second calibration area is located in the central part of the calibration plate body;

[0011] Several composite calibration areas are evenly distributed on the first calibration area.

[0012] As an improved solution, each of the composite calibration areas is provided with a circular bottom surface, on which a pair of calibration numbers and five calibration points are provided around the calibration numbers.

[0013] As an improved solution, the five calibration points include: a first calibration point, a second calibration point, a third calibration point, a fourth calibration point, and a fifth calibration point;

[0014] The first calibration point is located above the pair of calibration numbers;

[0015] The second calibration point is located below the pair of calibration numbers and corresponds to the first calibration point;

[0016] The third calibration point is located on one side of the pair of calibration numbers, and the fourth calibration point is located on the other side of the calibration numbers relative to the third calibration point;

[0017] The fifth calibration point is located near the third calibration point and is positioned directly below the third calibration point.

[0018] As an improved solution, the calibration plate body is rectangular;

[0019] The colors of the first calibration area and the second calibration area are set to be opposite;

[0020] The color of the circular bottom surface matches the color of the second calibration area; the calibration number and the colors of the five calibration points match the color of the first calibration area.

[0021] On the other hand, the present invention also provides a calibration method for a calibration plate for three-dimensional reconstruction, the method comprising the following steps:

[0022] The calibration board is coarsely positioned, and the position information of the feature circle is confirmed based on the coarse positioning and the edge detection algorithm.

[0023] The positional relationship of the calibration points is verified based on the positional information of the feature circles, and the feature circle numbering information is confirmed based on the verification of the positional relationship of the calibration points.

[0024] The image center information and the actual center information are confirmed based on the feature circle number information, and the camera intrinsic and extrinsic parameters are calibrated based on the image center information and the actual center information.

[0025] As an improved approach, the coarse positioning of the calibration board, and the confirmation of the feature circle position information based on the coarse positioning and edge detection algorithm, includes:

[0026] A first image of the calibration board is captured using the camera to be calibrated.

[0027] The second position information of the second calibration region of the calibration board is confirmed based on the threshold segmentation algorithm.

[0028] The calibration board is coarsely located based on the second position information;

[0029] A threshold segmentation algorithm is used to separate the first calibration region and the second calibration region in the calibration board after coarse positioning;

[0030] Sub-pixel edge detection is performed on the separated first calibration region based on the interpolation algorithm, and the first feature circle and the position information of the feature circle corresponding to the first feature circle are determined based on the sub-pixel edge detection.

[0031] As an improved solution, the step of verifying the positional relationship of calibration points based on the positional information of the feature circles, and confirming the feature circle number information based on the verification of the positional relationship of the calibration points, includes:

[0032] The first feature circle is located based on the feature circle position information;

[0033] Whether the first feature circle used for identification and positioning contains five calibration points;

[0034] If so, the feature circle is determined to be correctly positioned, and the relative positional relationship between the five calibration points is identified;

[0035] Determine whether the calibration plate has flipped based on the relative positional relationship;

[0036] If the calibration plate is not flipped, the calibration point position information of the five calibration points is determined according to the relative position relationship;

[0037] Determine the position information of the calibration numbers within the five calibration points based on the calibration point position information;

[0038] The first calibration number region is located based on the location information of the calibration number;

[0039] The feature circle numbering information within the first calibrated numbering area is identified using OCR recognition technology.

[0040] As an improved solution, the step of confirming the image center information and the actual center information based on the feature circle number information, and performing camera intrinsic and extrinsic parameter calibration based on the image center information and the actual center information, includes:

[0041] Detect the position information of the first center of the first feature circle corresponding to the feature circle number information;

[0042] Confirm the position information of the second center of the first feature circle in the first image;

[0043] Let the first center position information be taken as the actual center information;

[0044] Let the second center position information be used as the image center information;

[0045] Align the image center information with the actual center information.

[0046] On the other hand, the present invention also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of the calibration method.

[0047] On the other hand, the present invention also provides a computer device, the computer device including a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; wherein:

[0048] The memory is used to store computer programs;

[0049] The processor is configured to execute the steps of the calibration method by running a program stored in the memory.

[0050] The beneficial effects of the technical solution of this invention are:

[0051] The calibration plate for 3D reconstruction described in this invention can reduce the number of images required for calibration and ensure calibration accuracy. Under these two conditions, it does not require the design of a large-area calibration plate and can meet the corresponding calibration field of view requirements. It has high calibration efficiency and convenience and has strong applicability.

[0052] The calibration method described in this invention can perform fewer calibration operations using the calibration board described in this invention, thereby completing high-precision calibration of camera intrinsic and extrinsic parameters, ensuring both calibration accuracy and a certain degree of precision.

[0053] The computer-readable storage medium of the present invention can realize the operation logic of the calibration method of the present invention, and the computer-readable storage medium of the present invention also effectively improves the operability of the calibration method.

[0054] The computer device described in this invention can store and execute the computer-readable storage medium, thereby implementing the calibration method described in this invention. Attached Figure Description

[0055] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0056] Figure 1 This is a schematic diagram of the calibration plate for three-dimensional reconstruction as described in Embodiment 1 of the present invention;

[0057] Figure 2 This is a schematic diagram of the architecture of the composite calibration image in the calibration plate for three-dimensional reconstruction described in Embodiment 1 of the present invention;

[0058] Figure 3 This is a schematic diagram showing the relative positional relationship between the five calibration points in the calibration method described in Embodiment 2 of the present invention;

[0059] Figure 4 This is a schematic flowchart of the calibration method described in Embodiment 2 of the present invention;

[0060] Figure 5 This is a schematic diagram of the structure of the computer device described in Embodiment 4 of the present invention;

[0061] The markings in the attached diagram are explained as follows:

[0062] 1. Calibration plate main body; 2. Second calibration area; 3. First calibration area; 4. Composite calibration image; 5. Circular bottom surface; 6. Arabic numerals;

[0063] 101. First calibration point; 102. Second calibration point; 103. Third calibration point; 104. Fourth calibration point; 105. Fifth calibration point;

[0064] 1501. Processor; 1502. Communication interface; 1503. Memory; 1504. Communication bus. Detailed Implementation

[0065] The preferred embodiments of the present invention will now be described in detail with reference to the accompanying drawings, so that the advantages and features of the present invention can be more easily understood by those skilled in the art, thereby providing a clearer and more explicit definition of the scope of protection of the present invention.

[0066] In the description of this invention, it should be noted that the embodiments described in this invention are only some embodiments of this invention, not all embodiments; based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0067] The terms "first," "second," etc., used in this specification, claims, and accompanying drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, apparatus, product, or device that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices. Example 1

[0068] This embodiment provides a calibration plate for three-dimensional reconstruction, such as... Figure 1 and Figure 2 As shown, it includes: a calibration plate body 1 and a first calibration area 3 and a second calibration area 2 disposed on the calibration plate body 1;

[0069] The first calibration area 3 is arranged around the second calibration area 2, and the second calibration area 2 is located in the central part of the calibration plate body 1;

[0070] As one embodiment of the present invention, such as Figure 1 As shown, the calibration plate body 1 is rectangular; the second calibration area 2 is a rectangular area, and the area color of the second calibration area 2 is white. This second calibration area 2 is used for calibrating the optical engine and performing coarse positioning; the first calibration area 3 consists of a rectangular annular area surrounding the first calibration area 3, and several composite calibration images 4 (i.e., composite calibration areas) uniformly arranged on the rectangular annular area; as shown... Figure 1 As shown, the rectangular annular area is black, and there are 42 composite calibration images 4, which are respectively set on the upper and lower sides of the rectangular annular area, and are located on the upper and lower sides of the second calibration area 2 respectively; the composite calibration images 4 play a more precise and accurate calibration role;

[0071] As one embodiment of the present invention, such as Figure 2 As shown, each composite calibration image 4 consists of a circular base 5, five calibration points set on the circular base 5, and a pair of Arabic numerals 6 (i.e., a pair of calibration numbers); the circular base 5 is white, the five calibration points and the pair of Arabic numerals 6 are black, and the pair of Arabic numerals 6 are arranged side by side at the center of the circular base 5. Of the five calibration points, the first calibration point 101 is located above the pair of Arabic numerals 6, the second calibration point 102 is located below the pair of Arabic numerals 6 and corresponds to the first calibration point 101; the third calibration point 103 is located on one side of the pair of Arabic numerals 6 and away from the first calibration point 101 and the second calibration point 102. Figure 2 In the diagram, the third reference point 103 is located to the left of the pair of Arabic numerals 6 "23", and the fourth reference point 104 is located on the opposite side of the pair of Arabic numerals 6, relative to the third reference point 103. Figure 2 In the diagram, the fourth calibration point 104 is located to the right of the pair of Arabic numerals 6 "23", and the fifth calibration point 105 is located near the third calibration point 103 and below the third calibration point 103; as a possible implementation, such as Figure 1 As shown, the pair of Arabic numerals 6 in each composite calibration image 4 is different, through... Figure 2 The design of each composite calibration image 4 enables high-precision and wide-range calibration of camera intrinsic and extrinsic parameters. The calibration plate in this application features a special arrangement of text and calibration points. By rotating the calibration plate, the entire field of view of the camera can be covered after a few angle and position changes. Compared with the prior art, this improves the efficiency and convenience of detection, while also compensating for the calibration plate area problem in the prior art. This reduces the calibration difficulty while maintaining a certain level of calibration accuracy, and has high application value. Example 2

[0072] This embodiment is based on the same inventive concept as the calibration plate for three-dimensional reconstruction described in Embodiment 1, and provides a calibration method, such as... Figure 3 and Figure 4 As shown, it includes the following steps:

[0073] It should be noted that camera calibration results are specifically divided into camera intrinsic parameter calibration and camera extrinsic parameter calibration. Camera intrinsic parameters include parameters within the camera system, such as distortion and focus distance; camera extrinsic parameters include the relative relationships between multiple cameras, such as rotation and translation matrices. During calibration, calculations are primarily performed on the above data. Image distortion correction during intrinsic parameter calibration is particularly complex, with distortion mainly categorized into three types: barrel distortion, pincushion distortion, and perspective distortion. Because edge distortion is more pronounced, a larger calibration plate is typically used during calibration, usually occupying 2 / 3 of the field of view. However, high accuracy is also required during calibration, and it is difficult to fabricate a high-precision, large-area calibration plate for large fields of view. Therefore, the industry typically uses… Using calibration boards with multiple positions and angles to compensate for the area problem typically involves about 20-50 sets of images, and with a high-precision calibration board, the calibration error can reach 1%-0.5%. Although this method solves the problems of field of view and accuracy, it undoubtedly increases the difficulty, complexity, cost, and efficiency of calibration. In this method, based on the calibration board in Example 1, the problem of not being able to balance area and accuracy can be solved. During calibration, the calibration board in Example 1 can cover the entire field of view by rotating and changing its position. The operation is convenient and can reduce the number of images and the complexity of operation compared with traditional methods, thereby improving calibration efficiency and ensuring calibration accuracy. Moreover, using the calibration board in Example 1 can control the error to about 0.1%.

[0074] Specifically, based on the identification of the calibration board in Example 1, the calibration method is as follows:

[0075] First, an image of the calibration board is captured by the camera that needs to be calibrated to confirm the position of the calibration board in the image. In specific operation, threshold segmentation is used to confirm the position information of the white rectangular area in the center of the calibration board. Based on the obtained position information, the calibration board is coarsely located to obtain the position of the calibration board in the image.

[0076] Furthermore, each feature circle within the calibration board in the image is identified, and the region of each feature circle is cropped. In specific operation, the white area in the center of the calibration board is separated from the digital area by threshold segmentation, and sub-pixel edge detection is performed on the separated digital area by interpolation to obtain the location of the feature circle in the digital area.

[0077] Furthermore, the region of the feature circle can be determined based on its location. Subsequently, the calibration plate is checked for flipping based on the five calibration points within each feature circle, and the center position is determined based on the relative positions of the five calibration points within each feature circle. The specific judgment operation is as follows: First, confirm whether there are five calibration points within the feature circle. If so, it means the feature circle has been correctly located, and the subsequent judgment and calibration operations begin. Specifically, in the calibration plate of Example 1, the relative positions between the five calibration points in each feature circle are fixed. The first calibration point 101 is pre-numbered 1, the second calibration point 102 is numbered 2, the third calibration point 103 is numbered 3, the fourth calibration point 104 is numbered 4, and the fifth calibration point 105 is numbered 5. Between any two of these five calibration points, such as... Figure 3 As shown, there exists the following straight line:

[0078] The first straight line "L" between the third calibration point 103 (numbered 3) and the fifth calibration point 105 (numbered 5) 35 ”;

[0079] The second straight line "L" between the fifth calibration point 105 (numbered 5) and the fourth calibration point 104 (numbered 4) 54 ”;

[0080] The third straight line "L" between the third calibration point 103 (numbered 3) and the fourth calibration point 104 (numbered 4) 34 ”;

[0081] The fourth straight line "L" between the fourth calibration point 104 (numbered 4) and the fifth calibration point 105 (numbered 5) 45 ”;

[0082] The fifth straight line "L" contains the first calibration point 101 (numbered 1) and the second calibration point 102 (numbered 2). 12 ”;

[0083] Based on the fixed distance relationship between the two points mentioned above, and assuming the calibration plate is not flipped, the first straight line "L" 35 The distance between the two lines is the smallest, and the second line "L" is the shortest. 54 The distance to the fifth straight line "L" is the greatest. 12 "and the third straight line "L 34 The angle between the two straight lines must be greater than that between the fifth straight line "L". 12 "and the fourth line "L 45 The straight-line angle between them; based on this, for the aforementioned characteristic circle, the distance between each calibration point and other calibration points can be calculated, according to the above "L" 35 " and "L 54By comparing the distances, the two points corresponding to the maximum distance and the two points corresponding to the minimum distance within the found feature circle can be identified. This allows us to determine the positions of the third calibration point 103, the fourth calibration point 104, and the fifth calibration point 105 within the feature circle. Based on the aforementioned straight-line angle relationship, the fifth straight line "L" within the feature circle can be determined. 12 "; Based on the determined positions of the third calibration point 103, the fourth calibration point 104, and the fifth calibration point 105, as well as the fifth straight line "L" 12 This allows us to determine whether the calibration plate containing the currently found feature circle has been flipped; if the calibration plate has not been flipped, based on the determined positions of the third calibration point 103, the fourth calibration point 104, and the fifth calibration point 105, as well as the fifth straight line "L", we can determine whether the calibration plate has been flipped. 12 This will determine the fifth line "L". 12 "The corresponding first calibration point 101 and second calibration point 102 are identified, and their positions are calculated. At this point, the position information of the five calibration points of the feature circle found during the calibration process is known. Based on this position information, a pair of Arabic numeral regions surrounded by the five calibration points within the feature circle can be determined. The corresponding numerical code of this Arabic numeral region is identified using OCR technology. Based on this numerical code, the position of the found feature circle on the calibration plate can be determined. For example..." Figure 2 As shown, the feature circle is "23". Based on this number, the center position of this feature circle in the actual calibration plate is detected. At the same time, the center position of the feature circle in the image captured by the camera is obtained. By aligning the center position of the image with the detected center position, the accurate calibration of the camera's intrinsic and extrinsic parameters can be achieved.

[0084] In this method, the position of the calibration plate is first determined, then the "large circle" (i.e., the feature circle) in the calibration plate is identified, and five "small circles" (i.e., five calibration points) are identified from the "large circle". The rotation of the calibration plate and the specific position of the "large circle" are determined by the positional relationship of the five "small circles", and then the camera is calibrated. The operation is convenient and efficient. While ensuring accuracy, it also meets the requirements of area and field of view, and has high application value.

[0085] The calibration operation based on this method and the calibration board in Example 1 improves the accuracy by about 50% compared with the circular array calibration board in the prior art. The calibration result error is 0.14 pixels, and the binocular error is about 0.2 pixels at a distance of 2m, which has high application value. Example 3

[0086] This embodiment provides a computer-readable storage medium, including:

[0087] The storage medium is used to store computer software instructions for implementing the calibration method described in Embodiment 2 above, which includes a program for executing the calibration method. Specifically, the executable program can be built into a configurable electronic device, so that the electronic device can implement the calibration method described in Embodiment 2 by executing the built-in executable program.

[0088] Furthermore, the computer-readable storage medium in this embodiment can be any combination of one or more readable storage media, wherein the readable storage medium includes an electrical, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. Example 4

[0089] This embodiment provides an electronic device, such as... Figure 5 As shown, the electronic device may include: a processor 1501, a communication interface 1502, a memory 1503, and a communication bus 1504, wherein the processor 1501, the communication interface 1502, and the memory 1503 communicate with each other through the communication bus 1504.

[0090] Memory 1503 is used to store computer programs;

[0091] When the processor 1501 executes the computer program stored in the memory 1503, it implements the steps of the calibration method described in Embodiment 1 above.

[0092] As one embodiment of the present invention, the communication bus mentioned in the terminal above can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 5 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0093] As one embodiment of the present invention, the communication interface is used for communication between the aforementioned terminal and other devices.

[0094] In one embodiment of the present invention, the memory may include random access memory (RAM) or non-volatile memory, such as at least one disk storage device. Optionally, the memory may also be at least one storage device located remotely from the aforementioned processor.

[0095] As one embodiment of the present invention, the processor described above may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0096] Unlike existing technologies, the calibration plate, calibration method, equipment and medium for 3D reconstruction proposed in this application can reduce the number of images required for calibration and ensure calibration accuracy. Under these two conditions, there is no need to design a large-area calibration plate, and it can meet the corresponding calibration field of view requirements. The calibration efficiency and convenience are high, and it has strong applicability.

[0097] It should be understood that in the various embodiments of this document, the sequence number of each process does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this document.

[0098] It should also be understood that, in the embodiments herein, the term "and / or" is merely a description of the relationship between associated objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this document generally indicates that the preceding and following associated objects have an "or" relationship.

[0099] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this document.

[0100] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0101] In the embodiments provided herein, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the couplings or direct couplings or communication connections shown or discussed may be indirect couplings or communication connections through some interfaces, devices, or units, or they may be electrical, mechanical, or other forms of connection.

[0102] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of the embodiments described herein, depending on actual needs.

[0103] Furthermore, the functional units in the various embodiments of this document can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0104] If the integrated unit is implemented as 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 technical solution of this paper, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this paper. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0105] The above description is merely an embodiment of the present invention and does not limit the patent scope of the present invention. Any equivalent structural or procedural transformations made based on the content of the present invention's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of the present invention.

Claims

1. A calibration plate for three-dimensional reconstruction, characterized in that, include: A calibration plate body, wherein a first calibration area and a second calibration area are provided on the calibration plate body; The first calibration area is arranged around the second calibration area, and the second calibration area is located in the central part of the calibration plate body; Several composite calibration areas are evenly distributed on the first calibration area; Each of the composite calibration areas is provided with a circular bottom surface, and a pair of calibration numbers and five calibration points arranged around the calibration numbers are provided on the circular bottom surface; The five calibration points include: the first calibration point, the second calibration point, the third calibration point, the fourth calibration point, and the fifth calibration point; The first calibration point is located above the pair of calibration numbers; The second calibration point is located below the pair of calibration numbers and corresponds to the first calibration point; The third calibration point is located on one side of the pair of calibration numbers, and the fourth calibration point is located on the other side of the calibration numbers relative to the third calibration point; The fifth calibration point is located near the third calibration point and is positioned directly below the third calibration point; The calibration plate is rectangular in shape. The colors of the first calibration area and the second calibration area are set to be opposite; The color of the circular bottom surface matches the color of the second calibration area; the calibration number and the colors of the five calibration points match the color of the first calibration area.

2. A calibration method for a calibration plate for three-dimensional reconstruction as described in claim 1, characterized in that, The method includes the following steps: The calibration board is coarsely positioned, and the position information of the feature circle is confirmed based on the coarse positioning and the edge detection algorithm. The positional relationship of the calibration points is verified based on the positional information of the feature circles, and the feature circle numbering information is confirmed based on the verification of the positional relationship of the calibration points. The image center information and the actual center information are confirmed based on the feature circle number information, and the camera intrinsic and extrinsic parameters are calibrated based on the image center information and the actual center information.

3. The calibration method according to claim 2, characterized in that: The coarse positioning of the calibration board, and the confirmation of the feature circle position information based on the coarse positioning and the edge detection algorithm, includes: A first image of the calibration board is captured using the camera to be calibrated. The second position information of the second calibration region of the calibration board is confirmed based on the threshold segmentation algorithm. The calibration board is coarsely located based on the second position information; A threshold segmentation algorithm is used to separate the first calibration region and the second calibration region in the calibration board after coarse positioning; Sub-pixel edge detection is performed on the separated first calibration region based on the interpolation algorithm, and the first feature circle and the position information of the feature circle corresponding to the first feature circle are determined based on the sub-pixel edge detection.

4. The calibration method according to claim 3, characterized in that: The step of verifying the positional relationship of calibration points based on the positional information of the feature circles, and confirming the feature circle number information based on the verification of the positional relationship of the calibration points, includes: The first feature circle is located based on the feature circle position information; Whether the first feature circle used for identification and positioning contains five calibration points; If so, the feature circle is determined to be correctly positioned, and the relative positional relationship between the five calibration points is identified; Determine whether the calibration plate has flipped based on the relative positional relationship; If the calibration plate is not flipped, the calibration point position information of the five calibration points is determined according to the relative position relationship; Determine the position information of the calibration numbers within the five calibration points based on the calibration point position information; The first calibration number region is located based on the location information of the calibration number; The feature circle numbering information within the first calibrated numbering area is identified using OCR recognition technology.

5. The calibration method according to claim 4, characterized in that: The step of confirming the image center information and the actual center information based on the feature circle number information, and performing camera intrinsic and extrinsic parameter calibration based on the image center information and the actual center information, includes: Detect the position information of the first center of the first feature circle corresponding to the feature circle number information; Confirm the position information of the second center of the first feature circle in the first image; Let the first center position information be taken as the actual center information; Let the second center position information be used as the image center information; Align the image center information with the actual center information.

6. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the calibration method described in claim 5.

7. A computer device, characterized in that, It includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; wherein: The memory is used to store computer programs; The processor is configured to execute the steps of the calibration method of claim 5 by running a program stored in the memory.

Images