Calibration template, calibration system and calibration method thereof

Abstract

The application discloses a calibration sample plate, a calibration system and a calibration method thereof. The calibration sample plate comprises a calibration pattern and at least one identification pattern. The calibration pattern comprises a plurality of black grids and a plurality of white grids which are distributed alternately. Each identification pattern is embedded in one black grid or one white grid of the calibration pattern. Each identification pattern comprises at least one identification angle. The size of each identification pattern is smaller than that of the black grid or the white grid embedded with the identification pattern. The boundary color of each identification pattern is different from that of the black grid or the white grid embedded with the identification pattern. The application provides a novel calibration sample plate. The positioning is performed by introducing the identification pattern in the calibration sample plate, so that the calibration accuracy and stability can be effectively improved.

Description

Technical Field

[0001] This application relates to the field of parking assistance technology, and in particular to calibration templates, calibration systems and calibration methods. Background Technology

[0002] 360° panoramic parking assist systems, as a new type of intelligent parking assistance system, are increasingly being used in new car models. However, during actual mass production at car factories, each vehicle's camera has different installation errors. Therefore, automatic calibration and correction are required for each vehicle so that the system can correct the impact of manufacturing process factors on image display and stitching effects. The speed and effectiveness of this calibration method depend on the calibration site and calibration cloth.

[0003] The current calibration method uses four common cameras, an LVDS (Low-Voltage Differential Signaling) coaxial cable, and a checkerboard calibration cloth covering the entire front, rear, left, and right sides of the car. By measuring the world coordinates of each checkerboard point, the internal / external and distortion parameters of the four cameras installed on the front, rear, left, and right sides of the car can be obtained using an algorithm, thus completing the camera calibration process. The calibrated parameters can be used to generate a 360-degree surround top-down view. However, this calibration method has the following drawbacks: the checkerboard pattern on the calibration cloth covers the front, rear, left, and right sides of the car, resulting in a large computational load during calibration and making actual measurement quite cumbersome; therefore, it needs improvement. Summary of the Invention

[0004] This application provides a calibration template, calibration system, and calibration method for panoramic parking to solve the above-mentioned problems.

[0005] To solve the above-mentioned technical problems, one technical solution adopted in this application is: to provide a calibration template for camera calibration, the calibration template including a calibration pattern and at least one identification pattern, the calibration pattern including multiple black grids and multiple white grids distributed alternately, each identification pattern being embedded in one black grid or white grid of the calibration pattern, wherein each identification pattern includes at least one identification corner, the size of each identification pattern is smaller than the size of the black grid or white grid it is embedded in, and the boundary color of each identification pattern is different from the color of the black grid or white grid it is embedded in.

[0006] Wherein, at least one of the logo patterns includes four logo corners.

[0007] The at least one identification pattern includes one or more of the following: AprilTag identification code, QR code, and barcode.

[0008] The calibration template is used to calibrate the cameras in the vehicle parking system.

[0009] The number of the at least one identification pattern is set according to the number of cameras that need to be calibrated.

[0010] The at least one marking pattern includes at least one marking pattern respectively disposed in the rear and front areas of the vehicle to be calibrated, and at least two marking patterns respectively disposed in the areas on both sides of the vehicle body to be calibrated.

[0011] Each logo is unique.

[0012] The calibration pattern includes three calibration areas: the first calibration area includes the calibration pattern on the edge of the calibration template; the second calibration area includes the calibration pattern around the identification pattern; and the third calibration area includes the remaining calibration pattern on the calibration template.

[0013] The area of ​​the calibration pattern in the first calibration region is greater than the area of ​​the calibration pattern in the third calibration region, and the area of ​​the calibration pattern in the second calibration region is greater than the area of ​​the calibration pattern in the third calibration region.

[0014] The calibration template is formed by splicing multiple templates, and the splicing templates are provided with alignment and splicing patterns;

[0015] The alignment pattern of one of the splicing templates is aligned with the alignment pattern of the other splicing template.

[0016] To solve the aforementioned technical problems, another technical solution adopted in this application is: providing a calibration system for camera calibration, wherein the calibration system includes a computing terminal and a calibration template, wherein...

[0017] The calibration template is the calibration template described above; and

[0018] The computing terminal is used to acquire an image corresponding to the calibration template captured by the camera to be calibrated, and to identify at least one marker corner of the marker pattern in the image to obtain the position of the marker pattern, and to locate the calibration pattern by the position of the marker pattern.

[0019] The computing terminal is also used to generate parameters required to acquire a panoramic image around the target vehicle based on the world coordinates preset by the calibration pattern. The parameters include parameters for distortion correction of the camera and parameters required to stitch together the images captured by the camera corresponding to the calibration template.

[0020] To solve the above-mentioned technical problems, another technical solution adopted in this application is: providing a calibration method for calibrating a camera, wherein the calibration method employs a calibration template including a calibration pattern and at least one identifier pattern, the calibration pattern including multiple alternating black grids and multiple white grids, each identifier pattern being embedded in one of the black or white grids of the calibration pattern, wherein each identifier pattern includes at least one identifier corner, the size of each identifier pattern is smaller than the size of the black or white grid it is embedded in, and the boundary color of each identifier pattern is different from the color of the black or white grid it is embedded in, the calibration method comprising:

[0021] Acquire images of the calibration template corresponding to the area captured by the camera to be calibrated within its own shooting range; and

[0022] The position of the marker pattern is obtained by identifying at least one marker corner of the marker pattern in the image, and the calibration pattern is located by the position of the marker pattern.

[0023] The calibration method further includes generating parameters required to acquire a panoramic image around the target vehicle based on the world coordinates preset by the calibration pattern. These parameters include parameters for distortion correction of the camera and parameters required to stitch together the images captured by the camera corresponding to the calibration template.

[0024] Unlike existing technologies, the advantages of this application are as follows: The calibration template of this application includes a calibration pattern and at least one marking pattern. The calibration pattern includes multiple alternating black grids and multiple white grids. Each marking pattern is embedded in one of the black or white grids of the calibration pattern. Each marking pattern includes at least one marking corner. The size of each marking pattern is smaller than the size of the black or white grid it is embedded in, and the boundary color of each marking pattern is different from the color of the black or white grid it is embedded in. This application provides a novel calibration template. By introducing marking patterns in this calibration template for positioning, the efficiency, accuracy, and stability of calibration can be effectively improved. Attached Figure Description

[0025] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0026] Figure 1 This is a schematic diagram of the structure of an embodiment of the calibration template provided in this application;

[0027] Figure 2This is a schematic diagram of another embodiment of the calibration template provided in this application;

[0028] Figure 3 This is a schematic diagram of the structure of yet another embodiment of the calibration sample provided in this application;

[0029] Figure 4 This is a schematic diagram of the structure of an embodiment of the panoramic parking calibration system provided in this application;

[0030] Figure 5 This is a flowchart illustrating an embodiment of the calibration method provided in this application;

[0031] Figure 6 This is a schematic diagram of the structure of an embodiment of the terminal device provided in this application;

[0032] Figure 7 This is a schematic diagram of the structure of an embodiment of the computer storage medium provided in this application. Detailed Implementation

[0033] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0034] Please refer to the details. Figure 1 and Figure 2 , Figure 1 This is a schematic diagram of the structure of an embodiment of the calibration template provided in this application. Figure 2 This is a schematic diagram of another embodiment of the calibration template provided in this application.

[0035] like Figure 1 and Figure 2 As shown, the calibration template 100 of this embodiment includes a calibration pattern 11 and at least one identification pattern 12. The calibration pattern 11 consists of multiple alternating black and white grids, and the identification pattern 12 can be embedded within one of the black grids of the calibration pattern 11, such as... Figure 1 As shown, or the identification pattern 12 can be embedded in a white square in the marking pattern 11.

[0036] The following description uses the example of the marking pattern 12 embedded within a black grid, where the marking pattern 12 is surrounded by at least three white checkerboard squares. Specifically, when the marking pattern 12 is positioned at the edge of the marking pattern 11, the marking pattern 12 is surrounded by three white checkerboard squares; when the marking pattern 12 is positioned inside the marking pattern 11, the marking pattern 12 is surrounded by four white checkerboard squares.

[0037] The type of the identification pattern 12 includes, but is not limited to, one or more of AprilTag identification codes, QR codes, and barcodes. That is, the calibration template 100 can be set with one type of identification pattern 12 or multiple types of identification patterns 12, and there is no limit to the number.

[0038] by Figure 1 Taking the AprilTag identifier as an example, since the four corners of the AprilTag identifier are easy to identify, and different AprilTag identifiers correspond to different four corners, the location and type of the AprilTag identifier can be quickly determined by identifying the four corners of the AprilTag identifier.

[0039] In other possible embodiments, the marking pattern 12 may also include only one marking corner, similarly... Figure 1 Taking the AprilTag identifier as an example, in this embodiment, only the upper left corner of the AprilTag identifier can be used as the identifier corner, while other corners are not recognized. Therefore, this embodiment does not limit the number of identifier corners. In one embodiment, the identifier pattern may include one identifier pattern with four identifier corners, another identifier pattern with three identifier corners, another identifier pattern with one or two identifier corners, and yet another identifier pattern with five identifier corners, and so on. In another embodiment, all identifier patterns include the same number of identifier corners, for example, all including one, two, four, or more identifier corners. In other embodiments, at least two identifier patterns have the same number of identifier corners, for example, both having four, while other identifier patterns may have one, two, or other numbers of identifier corners. Therefore, the number of identifier corners for each identifier pattern can be freely set in this invention and is not limited.

[0040] In this embodiment, the system locates the absolute position of the corner markers (corners of the squares) by identifying the position of the marker pattern 12 (such as the AprilTag identifier). For example, during the calibration process, the computing terminal can identify the position and content of the AprilTag identifier by recognizing the four corner markers of the marker pattern in the image captured by the camera. That is, the world coordinates of the chessboard squares around the AprilTag identifier can be quickly located based on the AprilTag identifier. Specifically, the corner markers of the AprilTag identifier are mainly used for the intersection of the black and white squares around the AprilTag identifier. This embodiment of the application introduces the AprilTag identifier to locate the intersection of the black and white squares more quickly and accurately, thereby locating the black and white squares.

[0041] The AprilTag identifier is generated as follows: First, the positional correspondence between the AprilTag identifier to be generated and the calibration pattern 11 is determined; then, this positional correspondence is input into the program as a parameter; finally, the AprilTag identifier is generated according to the parameters in the program.

[0042] As can be seen from the AprilTag generation process, the different relative positions of each AprilTag with the calibration pattern 11 result in different identification angles for each AprilTag. During the calibration process of the vehicle parking system's cameras, the terminal identifies the identification angle of the AprilTag, using this angle to determine the content of the AprilTag—that is, the positional correspondence between the AprilTag and the calibration pattern 11—and obtains the world coordinates of the AprilTag's identification angle. Finally, based on the world coordinates of the identification angle, the world coordinates of the intersection of the black and white grids are quickly located.

[0043] After locating the world coordinates of all black and white squares (their intersecting corners) of the calibration template 100, the computing terminal generates parameters required to acquire a panoramic image surrounding the target vehicle. These parameters include distortion correction parameters for the cameras and parameters required to stitch together the images captured by the cameras corresponding to the calibration template, thus completing the calibration of panoramic parking. Then, the computing terminal corrects the distortion of the cameras based on the distortion correction parameters, and stitches together the images captured by each camera based on the parameters required to stitch together the images captured by the cameras corresponding to the calibration template, to generate a bird's-eye view (or panoramic image) of the ground. The images captured by each camera corresponding to the calibration template are not necessarily images of the calibration template itself; they can also be images corresponding to the positions of the calibration template, to form a panoramic image (stitching together the images captured by the cameras to create a panoramic image surrounding the target vehicle or a bird's-eye view of the ground).

[0044] Regarding the distortion correction principle of the camera, the algorithms for solving the camera's intrinsic and extrinsic parameters can be performed using the same principles as existing technologies. Existing technologies typically use the corner points of a black-and-white grid or the center of a circular pattern as initial coordinates during distortion correction. When using the corner points of a black-and-white grid as initial coordinates, due to camera distortion, these corner points are difficult to find in the captured image and are easily lost. Using the center of a circular pattern as initial coordinates is complex due to the difficulty in obtaining the center's coordinates and introduces significant errors. This invention uses the corner points of a marker pattern as initial coordinates. This makes the marker pattern easier to identify in the captured image, thus making it easier to find its corner points and, consequently, more easily and reliably locate the intersection of the black-and-white grid. This improves the efficiency and accuracy of finding the initial coordinates, simplifies the algorithm, and allows for faster and more accurate generation of a bird's-eye view of the ground, as well as stitching together a complete image surrounding the vehicle body.

[0045] Furthermore, to better identify the marking patterns 12, the boundary color of each marking pattern 12 in this embodiment is different from the color of the black or white grids it contains. For example... Figure 1 As shown, the border color of the logo pattern 12 is white, and the grid inside it is black; as Figure 2 As shown, the border color of the logo pattern 12 is black, and the squares embedded within it are white squares. The border color can refer to the color at the junction of the logo pattern and the corresponding black or white squares, where the color at the junction is different from the color of the corresponding black or white squares, and preferably has a clear contrast (e.g., black against white, white against black as mentioned above; or other suitable colors that can be clearly distinguished).

[0046] Please continue reading. Figure 1 and Figure 3 , Figure 3 This is a schematic diagram of another embodiment of the calibration sample provided in this application. The calibration template 100 of this application embodiment can be used to calibrate cameras in a vehicle parking system. Specifically, the number of marking patterns 12 on the calibration template 100 can be set to correspond to the number of cameras to be calibrated, or the number of marking patterns 12 on the calibration template 100 can be enabled to correspond to the number of cameras to be calibrated.

[0047] like Figure 3As shown, the calibration template 100 has at least one AprilTag identifier directly in front of the target vehicle's area, and at least one AprilTag identifier directly behind the target vehicle's area. The calibration template 100 also has at least two AprilTag identifiers on the left and right sides of the target vehicle's area. Having at least two AprilTag identifiers on each side of the target vehicle's area effectively accommodates target vehicles of varying lengths. If the side camera cannot recognize one AprilTag identifier, the other can assist in recognition. For example, when the target vehicle is long, the side camera may not be able to recognize the AprilTag identifier further forward on the side; in this case, the AprilTag identifier further backward on the side can be recognized for calibration.

[0048] It should be noted that the embodiments of this application are also applicable to different numbers and different positions of AprilTag identifiers, which will not be elaborated here.

[0049] The dimensions of the black and white checkerboard grids in calibration pattern 11, such as length, width, and / or area, depend on their relative positions to the camera and the camera's distortion parameters.

[0050] Specifically, the calibration pattern 11 can be divided into three calibration areas (not shown in the figure): a first calibration area, a second calibration area, and a third calibration area. The first calibration area includes the black squares at the edge of the camera's field of view; the second calibration area includes the black squares surrounding the calibration pattern; and the third calibration area includes the remaining black squares. It should be noted that this description of the calibration areas only refers to the black squares; it should be understood that the calibration areas also include white squares.

[0051] In this calibration, the area of ​​the black squares in the first calibration region is larger than the area of ​​the black squares in the third calibration region, and the calibration area of ​​the second calibration region is larger than that of the third calibration region.

[0052] Furthermore, since the black grids at the edge of the camera's field of view are significantly distorted, the width or area of ​​the black grids in the first calibration region needs to be set to a larger value so that the boundary between the black grids and adjacent white grids in the image captured by the camera can be clearly distinguished. Additionally, since the calibration template 100 in this embodiment first identifies the identification pattern 12, and then identifies the black and white checkerboard grids surrounding the identification pattern 12, the width or area of ​​the black grids in the second calibration region also needs to be set to a larger value to ensure accurate recognition results and high recognition efficiency.

[0053] In addition, the width or area of ​​the third calibration area can also be set in the following ways: First, the width or area of ​​the black grid is set to be equal; Second, the width or area of ​​the black grid is gradually reduced in the direction from the first calibration area to the second calibration area.

[0054] The calibration template 100 is made of non-woven fabric or a ground surface. The calibration template 100 can be printed on different materials and appear in different forms, such as printed on non-woven fabric or directly painted onto a fixed ground surface.

[0055] It should be noted that in the workshops of OEM car manufacturers, where there are fixed spaces and workstations, paint is generally applied to fixed floors. However, for the sake of flexibility, paint is usually printed on non-reflective non-woven fabric, which is convenient for folding, storage, and transportation.

[0056] Please continue reading. Figure 1 and Figure 2 In the calibration template 100, multiple indicator lines 13 are drawn on the rear of the left and right sides of the target vehicle, with each indicator line spaced 20cm apart.

[0057] In this embodiment, multiple indicator lines 13 are drawn on the rear of the left and right sides of the calibration template 100, with distances marked such as 20cm, 40cm, 60cm...120cm to accommodate vehicles of different lengths. In use, the calibration template 100 can be stretched to positions of 20cm, 40cm, 60cm...120cm, making it applicable to vehicles of different lengths. For example, for an A-class sedan, it can be stretched to 80cm; for a typical SUV, it can be stretched to 120cm, avoiding operational errors caused by operators measuring distances with a ruler.

[0058] In addition, since the calibration template 100 is generally formed by splicing multiple templates, the splicing templates are provided with alignment splicing patterns 14. In this embodiment of the application, the alignment splicing pattern 14 can be a circular four-division pattern. In other embodiments, the alignment splicing pattern 14 can also be other patterns, which will not be described in detail here.

[0059] In existing technologies on the market, aligning the splicing templates during installation takes a lot of time and requires measuring the relative distance between the templates with a ruler. This operation is very cumbersome and it is difficult to guarantee accuracy. Different operators have very different methods, resulting in poor consistency, all of which will significantly affect the calibration results.

[0060] In this embodiment of the application, by introducing an alignment pattern, when laying the splicing template, the position and distance of the alignment pattern can be observed to ensure that the splicing templates are aligned, thereby ensuring that the calibration template is successfully spliced.

[0061] In addition, the calibration template 100 is laid out on black or white grids around the target vehicle, with multiple indicator words 15 drawn on it, such as... Figure 1 The white grid shown contains the indicator words "front", "back", "left", "right", etc., which help to quickly find a suitable parking location when parking the target vehicle.

[0062] Please continue reading. Figure 4 , Figure 4 This is a schematic diagram of an embodiment of the panoramic parking calibration system provided in this application.

[0063] like Figure 4 As shown, the calibration system 200 of this application embodiment includes a computing terminal 22 and a calibration template 21. The calibration template 21 can be specifically referred to in the description of the above embodiments, and will not be repeated here.

[0064] The computing terminal 22 can be the central control system of the target vehicle, or a processing terminal with data processing capabilities outside the central control system of the target vehicle. The computing terminal 21 is used to acquire an image corresponding to a calibration template captured by the camera to be calibrated, and to identify at least one marker angle of the marker pattern in the image to obtain the position of the marker pattern, and to locate the calibration pattern using the position of the marker pattern. The computing terminal 21 is also used to generate parameters required to acquire a panoramic image surrounding the target vehicle based on the pre-set world coordinates of the calibration pattern, including parameters for distortion correction of the camera and parameters required to stitch the image corresponding to the calibration template captured by the camera.

[0065] Based on the aforementioned calibration template and calibration system, this application also provides a calibration method for panoramic parking, for details please refer to [link / reference needed]. Figure 5 , Figure 5 This is a flowchart illustrating an embodiment of the calibration method provided in this application.

[0066] The panoramic parking calibration method of this application is applied to a terminal device, wherein the terminal device can be a server, a mobile device, or a system in which the server and mobile device cooperate with each other. Accordingly, the various parts of the terminal device, such as various units, sub-units, modules, and sub-modules, can all be set in the server, all in the mobile device, or separately in the server and the mobile device.

[0067] Furthermore, the aforementioned server can be either hardware or software. When the server is hardware, it can be implemented as a distributed server cluster consisting of multiple servers, or as a single server. When the server is software, it can be implemented as multiple software programs or software modules, such as software or software modules used to provide distributed server functionality, or as a single software program or software module; no specific limitations are made here.

[0068] like Figure 5 As shown, the calibration method in this embodiment specifically includes the following steps:

[0069] Step S11: Obtain the image of the calibration template corresponding to the shooting range of the camera to be calibrated, and transmit it to the computing terminal.

[0070] Step S12: The computing terminal obtains the position of the identification pattern by identifying at least one identification corner of the identification pattern in the image captured by the camera to be calibrated, and locates the calibration pattern by the position of the identification pattern.

[0071] Step S13: The computing terminal generates parameters required to acquire a panoramic image around the target vehicle based on the world coordinates preset by the calibration pattern. The parameters include parameters for distortion correction of the camera and parameters required to stitch together the images captured by the camera corresponding to the calibration template.

[0072] After locating the world coordinates of all black and white squares (their intersecting corners) of the calibration template 100, the computing terminal generates parameters required to acquire a panoramic image surrounding the target vehicle. These parameters include distortion correction parameters for the cameras and parameters required to stitch together the images captured by the cameras corresponding to the calibration template, thus completing the calibration of panoramic parking. Then, the computing terminal corrects the distortion of the cameras based on the distortion correction parameters, and stitches together the images captured by each camera based on the parameters required to stitch together the images captured by the cameras corresponding to the calibration template, to generate a bird's-eye view (or panoramic image) of the ground. The images captured by each camera corresponding to the calibration template are not necessarily images of the calibration template itself; they can also be images corresponding to the positions of the calibration template, to form a panoramic image (stitching together the images captured by the cameras to create a panoramic image surrounding the target vehicle or a bird's-eye view of the ground).

[0073] The specific processes of steps S11 to S13 have been described in the embodiments of the calibration template and calibration system, and will not be repeated here. In this embodiment, the above-mentioned calibration template can be used to calibrate the camera.

[0074] To implement the calibration method described in the above embodiments, this application also provides a terminal device, please refer to [link / reference needed]. Figure 6 , Figure 6 This is a schematic diagram of the structure of an embodiment of the terminal device provided in this application.

[0075] like Figure 6 As shown, the terminal device 400 in this embodiment includes a processor 41, a memory 42, an input / output device 43, and a bus 44.

[0076] The processor 41, memory 42, and input / output device 43 are respectively connected to the bus 44. The memory 42 stores a computer program, and the processor 41 is used to execute the computer program to implement the calibration method of the above embodiment.

[0077] In this embodiment, processor 41 can also be referred to as CPU (Central Processing Unit). Processor 41 may be an integrated circuit chip with signal processing capabilities. Processor 41 can also be a general-purpose processor, digital signal processor (DSP), application-specific integrated circuit (ASIC), field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. Processor 41 can also be GPU (Graphics Processing Unit), also known as a display core, visual processor, or display chip, which is a microprocessor specifically designed for image processing in personal computers, workstations, game consoles, and some mobile devices (such as tablets and smartphones). The purpose of a GPU is to convert and drive the display information required by the computer system, provide line scanning signals to the display, control the correct display of the display, and is an important component connecting the display and the personal computer motherboard, as well as one of the important devices for "human-computer interaction." As an important component of the computer host, the graphics card is responsible for outputting and displaying graphics, and is very important for people engaged in professional graphic design. The general-purpose processor can be a microprocessor, or processor 41 can be any conventional processor.

[0078] This application also provides a computer storage medium, such as Figure 7 As shown, the computer storage medium 500 is used to store a computer program 51, which, when executed by a processor, is used to implement the method described in the calibration method embodiment of this application.

[0079] The methods involved in the calibration method embodiments of this application, when implemented as software functional units and sold or used as independent products, can be stored in a device, such as a computer-readable storage medium. Based on this understanding, the technical solution of this application, 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.) or processor to execute all or part of the steps of the methods described in the various embodiments of this invention. 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.

[0080] 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 template for calibrating a camera, characterized in that, The calibration template includes a calibration pattern and at least one identification pattern. The calibration pattern includes multiple black squares and multiple white squares distributed alternately. Each identification pattern is embedded in one of the black or white squares of the calibration pattern. Each identification pattern includes at least one identification corner. The size of each identification pattern is smaller than the size of the black or white square it is embedded in. The boundary color of each identification pattern is different from the color of the black or white square it is embedded in. The calibration pattern includes three calibration areas: the first calibration area includes the calibration pattern at the edge of the calibration template; the second calibration area includes the calibration pattern around the marking pattern; and the third calibration area includes the remaining calibration pattern of the calibration template. The area of ​​the calibration pattern in the first calibration region is greater than the area of ​​the calibration pattern in the third calibration region, and the area of ​​the calibration pattern in the second calibration region is greater than the area of ​​the calibration pattern in the third calibration region.

2. The calibration template according to claim 1, characterized in that, At least one of the logo patterns includes four logo corners.

3. The calibration template according to claim 1, characterized in that, The at least one identification pattern includes one or more of the following: AprilTag identification code, QR code, and barcode.

4. The calibration template according to claim 1, characterized in that, The calibration template is used to calibrate the cameras in the vehicle parking system.

5. The calibration template according to claim 4, characterized in that, The number of at least one identification pattern is set according to the number of cameras that need to be calibrated.

6. The calibration template according to claim 4, characterized in that, The at least one marking pattern includes at least one marking pattern respectively disposed in the rear and front areas of the vehicle to be calibrated, and at least two marking patterns respectively disposed in the areas on both sides of the vehicle body to be calibrated.

7. The calibration template according to claim 6, characterized in that, Each logo is unique.

8. The calibration template according to claim 1, characterized in that, The calibration template is formed by splicing multiple templates, and the splicing templates are provided with alignment and splicing patterns; The alignment pattern of one of the splicing templates is aligned with the alignment pattern of the other splicing template.

9. A calibration system for calibrating a camera, characterized in that, The calibration system includes a computing terminal and a calibration template, wherein... The calibration template is the calibration template according to any one of claims 1-8; and The computing terminal is used to acquire an image corresponding to the calibration template captured by the camera to be calibrated, and to identify at least one marker corner of the marker pattern in the image to obtain the position of the marker pattern, and to locate the calibration pattern by the position of the marker pattern.

10. The calibration system according to claim 9, characterized in that, The computing terminal is also used to generate parameters required to acquire a panoramic image around the vehicle to be calibrated based on the world coordinates preset in the calibration pattern. The parameters include parameters for distortion correction of the camera and parameters required to stitch together the images captured by the camera corresponding to the calibration template.

11. A calibration method for calibrating a camera, characterized in that, The calibration method employs a calibration template including a calibration pattern and at least one identifier pattern. The calibration pattern comprises multiple alternating black and white squares. Each identifier pattern is embedded within one of the black or white squares of the calibration pattern. Each identifier pattern includes at least one identifier corner. The size of each identifier pattern is smaller than the size of the black or white square it is embedded in, and the boundary color of each identifier pattern is different from the color of the black or white square it is embedded in. The calibration pattern includes three calibration areas: the first calibration area includes the calibration pattern at the edge of the calibration template; the second calibration area includes the calibration pattern around the marking pattern; and the third calibration area includes the remaining calibration pattern of the calibration template. The area of ​​the calibration pattern in the first calibration region is larger than the area of ​​the calibration pattern in the third calibration region, and the area of ​​the calibration pattern in the second calibration region is larger than the area of ​​the calibration pattern in the third calibration region. The calibration method includes: Acquire images of the calibration template corresponding to the area captured by the camera to be calibrated within its own shooting range; and The position of the marker pattern is obtained by identifying at least one marker corner of the marker pattern in the image, and the calibration pattern is located by the position of the marker pattern.

12. The calibration method according to claim 11, characterized in that, The calibration method further includes generating parameters required to acquire a panoramic image around the vehicle to be calibrated based on the world coordinates preset by the calibration pattern. The parameters include parameters for distortion correction of the camera and parameters required to stitch together the images captured by the camera corresponding to the calibration template.

Images