Vehicle-mounted camera external parameter calibration method and device based on vertical calibration plate

Abstract

The invention provides a vehicle-mounted camera external parameter calibration method and device based on a vertical calibration plate. The method comprises the following steps: establishing the vertical calibration plate comprising a checkerboard target plate and an adjustable bracket; the vertical calibration plate is arranged in front of the vehicle-mounted camera to be calibrated, and the position of the adjustable support is adjusted so that the position of the checkerboard target plate can meet the set calibration condition; calculating physical coordinates of each angular point in the checkerboard target plate according to a given offset parameter of the adjustable bracket relative to the original point of the vehicle coordinate system and a checkerboard parameter; acquiring pixel coordinates of each angular point on the target plate image according to an angular point detection algorithm; and calculating a rotation matrix initial value of the to-be-calibrated vehicle-mounted camera according to the physical coordinates and the pixel coordinates of all the angular points, and then adjusting the adjustable bracket to correct the rotation matrix initial value to obtain a final rotation matrix. According to the method, the calibration work of the external parameters of the camera can be quickly completed on site by only needing a small calibration plate without measuring the parameters from the target plate to the vehicle.

Description

Technical Field

[0001] The present invention relates to a vehicle-mounted camera calibration technology, and in particular to a vehicle-mounted camera extrinsic parameter calibration method and device based on a vertical calibration plate. Background Art

[0002] With the development of automotive intelligence, camera sensors have been widely used in assisted driving functions such as target ranging and surround view stitching due to their low cost, high resolution, and rich texture. On-board cameras need to be calibrated with internal and external parameters before they can be used normally. The calibration accuracy affects the performance of the product, and the convenience of the calibration process affects the installation and after-sales maintenance of the product.

[0003] The traditional external parameter calibration methods for vehicle-mounted cameras include target calibration and targetless calibration. The target calibration method is usually used in car factories. It can quickly achieve a high-precision calibration process by investing a relatively high cost to build a calibration workshop with high-precision targets and combining wheel fixing tools to fix the position of the vehicle body. However, when developing calibration or installing aftermarket products, a calibration room is generally not specially established. Usually, a piece of open space is selected on site and specific targets are placed on the ground manually for calibration. The targetless calibration method is usually implemented by extracting specific environmental feature points.

[0004] In order to increase the imaging ratio of the target in the vehicle-mounted camera, a larger target will be used when using a target for calibration. However, the larger target has the characteristics of low manufacturing precision, easy to stretch, and easy to wrinkle, which will cause a certain calibration accuracy error. Although it can be corrected to improve the calibration accuracy, for example, Chinese patent CN113160336A provides a vehicle-mounted surround camera calibration method in a simple calibration environment. This method corrects the world coordinates of the feature points in an iterative manner to improve the technical problem of reduced calibration accuracy due to factors such as inaccurate calibration pattern size, calibration pattern medium stretching deformation, and calibration pattern medium wrinkles. However, it still cannot avoid the need for a larger calibration site, and still needs to measure the size of the calibration cloth to the vehicle body, and the process is still cumbersome.

[0005] Furthermore, the method of manually placing specific targets often requires placing the targets according to specific rules, and requires accurate measurement of the position information of the targets. The placement of targets is cumbersome. Chinese patent CN114202588A discloses a method and device for rapid automatic calibration of a vehicle-mounted surround-view camera. This method only needs to ensure that the calibration pattern has appeared in the public field of view of the camera during the calibration process. It does not need to know the coordinates of the feature points, and does not need to set the calibration pattern according to conditions such as position and distance. There is no need to limit the parking position of the vehicle during calibration, or set a strict route through the calibration pattern. A simple calibration scheme can quickly realize the calibration of the surround-view camera. However, it is aimed at the joint calibration of multiple cameras to solve the camera external parameters, and the target needs to appear in the public field of view of adjacent cameras. It is not suitable for the rapid calibration of a single camera, nor is it suitable for products where some adjacent cameras do not have a large public field of view.

[0006] In general, the existing method of calibrating the external parameters of an airborne camera by using a target has the problems of cumbersome calibration process and low accuracy. Summary of the invention

[0007] In order to solve the technical problems that the existing method of calibrating the extrinsic parameters of an onboard camera by using a target has a cumbersome calibration process and low precision, the present invention discloses a method for calibrating the extrinsic parameters of an onboard camera based on a vertical calibration plate, the method comprising the following steps:

[0008] S101, establishing a vertical calibration plate including a checkerboard target plate and an adjustable bracket;

[0009] S102, placing the vertical calibration plate in front of the vehicle-mounted camera to be calibrated, adjusting the position of the adjustable bracket so that the position of the checkerboard target plate meets the set calibration conditions, wherein the calibration conditions include that the checkerboard target plate is parallel to the vehicle body, the upper edge of the checkerboard target plate is parallel to the ground, and the checkerboard target plate completely falls within the viewing angle of the vehicle-mounted camera to be calibrated;

[0010] S103, calculating the physical coordinates of each corner point in the checkerboard target plate according to the given offset parameters of the adjustable bracket relative to the origin of the vehicle coordinate system and the checkerboard parameters;

[0011] S104, collecting an image of the checkerboard target plate by using the vehicle-mounted camera to be calibrated, and obtaining the pixel coordinates of each corner point on the image according to a corner point detection algorithm;

[0012] S105. Calculate the initial value of the rotation matrix of the vehicle-mounted camera to be calibrated according to the physical coordinates and the pixel coordinates of all the corner points, and use the initial value of the rotation matrix as the external parameter of the vehicle-mounted camera to be calibrated.

[0013] Furthermore, in the above step S101, the establishment of a vertical calibration plate including a checkerboard target plate and an adjustable bracket includes:

[0014] S1011, determining checkerboard parameters according to the calibration distance and the target board image range, and preparing a checkerboard target board using the checkerboard parameters, wherein the calibration distance is the horizontal distance between the checkerboard target board and the vehicle-mounted camera to be calibrated, the target board image range is the proportion of the checkerboard target board falling into the viewing angle of the vehicle-mounted camera to be calibrated, and the checkerboard parameters include the number of checkerboards and the size of each checkerboard;

[0015] S1012, clamping the checkerboard target plate on the adjustable bracket, adjusting the position of the checkerboard target plate so that the upper edge of the checkerboard target plate is perpendicular to the adjustable bracket, and obtaining the vertical calibration plate.

[0016] Furthermore, in the above step S102, the vertical calibration plate is set in front of the vehicle-mounted camera to be calibrated, and the position of the adjustable bracket is adjusted so that the position of the checkerboard target plate meets the set calibration conditions, including:

[0017] Place the vertical calibration plate in front of the vehicle-mounted camera to be calibrated, adjust the height and rotation angle of the adjustable bracket, and adjust the horizontal distance between the vertical calibration plate and the vehicle-mounted camera to be calibrated, so that the checkerboard target plate is parallel to the vehicle body and the checkerboard target plate completely falls within the viewing angle of the vehicle-mounted camera to be calibrated.

[0018] Furthermore, in the above step S104, obtaining the pixel coordinates of each corner point on the image according to the corner point detection algorithm includes:

[0019] S1041, extracting the initial pixel coordinates of each corner point on the image by using a corner point detection algorithm;

[0020] S1042: Dedistort the initial pixel coordinates using the internal parameters of the vehicle-mounted camera to be calibrated to obtain the pixel coordinates of each corner point.

[0021] Furthermore, the above-mentioned vehicle-mounted camera extrinsic parameter calibration method based on the vertical calibration plate further includes:

[0022] The center of the bottom surface of the vehicle is taken as the origin of the vehicle coordinate system, the front of the vehicle is defined as the positive direction of the y coordinate, the right side of the vehicle is defined as the positive direction of the x coordinate, and the upward direction of the ground is defined as the positive direction of the z coordinate; the offset parameter is obtained based on the positional relationship between the adjustable bracket and the origin of the vehicle coordinate system.

[0023] Furthermore, the above-mentioned vehicle-mounted camera extrinsic parameter calibration method based on the vertical calibration plate further includes:

[0024] S106. According to a given calibration line, the initial value of the rotation matrix is ​​evaluated and corrected to obtain a final rotation matrix, and the final rotation matrix is ​​used as an external parameter of the vehicle-mounted camera to be calibrated.

[0025] Furthermore, in the above step S106, the initial value of the rotation matrix is ​​evaluated and corrected according to the given calibration line to obtain the final rotation matrix, including:

[0026] S1061. Given a calibration line parallel to the vehicle body, project the calibration line according to the initial value of the rotation matrix to obtain a projection line, and compare the projection line with the vehicle body;

[0027] S1062: If the projection line is parallel to the vehicle body, use the initial value of the rotation matrix as the final rotation matrix;

[0028] S1063. If the projection line is not parallel to the vehicle body, correct the initial value of the rotation matrix until a rotation matrix corresponding to the projection line parallel to the vehicle body is obtained as a final rotation matrix.

[0029] Furthermore, in the above step S1063, the initial value of the rotation matrix is ​​corrected until a rotation matrix corresponding to the projection line parallel to the vehicle body is obtained as a final rotation matrix, including:

[0030] S10631, adjusting the rotation angle of the adjustable bracket, re-collecting a new image of the checkerboard target plate, and obtaining new pixel coordinates of each corner point on the new image according to a corner point detection algorithm;

[0031] S10632. Calculate a new rotation matrix of the vehicle-mounted camera to be calibrated based on the physical coordinates of all the corner points and the new pixel coordinates, and evaluate and correct the new rotation matrix until a rotation matrix corresponding to the projection line parallel to the vehicle body is obtained as the final rotation matrix.

[0032] An embodiment of the present invention also provides a vehicle-mounted camera extrinsic parameter calibration device based on a vertical calibration plate, the device comprising a vertical calibration plate, an offset parameter setting module, a corner point physical coordinate calculation module, a corner point pixel coordinate acquisition module and a vehicle-mounted camera extrinsic parameter calculation module.

[0033] Wherein, the vertical calibration plate comprises a checkerboard target plate and an adjustable bracket, and the checkerboard target plate is clamped on the adjustable bracket;

[0034] The physical coordinate calculation module is used to calculate the physical coordinates of each corner point in the checkerboard target plate according to the given offset parameters of the adjustable bracket relative to the origin of the vehicle coordinate system and the checkerboard parameters;

[0035] The corner point pixel coordinate acquisition module is used to collect the image of the checkerboard target plate through the vehicle-mounted camera to be calibrated, and obtain the pixel coordinates of each corner point on the image according to the corner point detection algorithm;

[0036] The vehicle-mounted camera extrinsic parameter calculation module is used to calculate the initial value of the rotation matrix of the vehicle-mounted camera to be calibrated according to the physical coordinates and the pixel coordinates of all the corner points, and use the initial value of the rotation matrix as the extrinsic parameter of the vehicle-mounted camera to be calibrated.

[0037] Furthermore, the above-mentioned device also includes an evaluation and correction module, which is used to evaluate and correct the initial value of the rotation matrix according to a given calibration line to obtain a final rotation matrix, and use the final rotation matrix as an external parameter of the vehicle-mounted camera to be calibrated.

[0038] Compared with the prior art, the beneficial effects that can be achieved by at least one of the above-mentioned technical solutions adopted in the embodiments of this specification include at least: the method for calibrating the external parameters of a vehicle-mounted camera of the present invention first establishes a vertical calibration plate, places the vertical calibration plate in front of the vehicle-mounted camera to be calibrated, and adjusts its position to meet the calibration conditions; secondly, the physical coordinates of each corner point are determined according to the offset parameters of the given adjustable bracket relative to the origin of the vehicle coordinate system and the checkerboard parameters; then, the pixel coordinates of each corner point in the image of the collected checkerboard target plate are obtained using a corner point detection algorithm; finally, according to the coordinate pairs of the pixel coordinates and physical coordinates of all corner points on the checkerboard target plate, the initial value of the rotation matrix of the vehicle-mounted camera to be calibrated is calculated to obtain its external parameter results.

[0039] Compared with the traditional method, the method of the present invention does not need to prepare a large-sized calibration cloth, but only needs a small-sized chessboard calibration plate (such as the size of A4 paper), which is portable and highly accurate, and does not need to measure the parameters of the calibration plate to the vehicle. Even in a harsh and narrow on-site calibration environment, it is easy to calibrate, and the calibration effect can be observed intuitively, and the parameters can be adjusted conveniently and quickly to ensure the reliability of the calibration effect. It can be suitable for various professionals and non-professionals to quickly complete the installation and calibration work on site. Furthermore, the method of the present invention is suitable for the external parameter calibration of single and multiple lenses. During calibration, it is only necessary to place the calibration plate in front of the camera to be calibrated, and the data of other cameras are required. The method has good adaptability. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0041] Figure 1It is a flow chart of the extrinsic parameter calibration method of a vehicle-mounted camera based on a vertical calibration plate disclosed in an embodiment of the present invention;

[0042] Figure 2 It is a structural diagram of an extrinsic parameter calibration device for a vehicle-mounted camera based on a vertical calibration board disclosed in an embodiment of the present invention;

[0043] Among them, 201, vertical calibration plate; 202, corner point physical coordinate calculation module; 203, corner point pixel coordinate acquisition module; 204, vehicle-mounted camera external parameter calculation module; 205, evaluation and correction module. DETAILED DESCRIPTION

[0044] The embodiments of the present application are described in detail below with reference to the accompanying drawings.

[0045] The following describes the implementation methods of the present application through specific specific examples, and those skilled in the art can easily understand other advantages and effects of the present application from the content disclosed in this specification. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. The present application can also be implemented or applied through other different specific implementation methods, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present application. It should be noted that the following embodiments and the features of the embodiments can be combined with each other in the absence of conflict. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without making creative work belong to the scope of protection of the present application.

[0046] The parameters of a vehicle-mounted camera generally include camera intrinsic parameters and camera extrinsic parameters. The camera intrinsic parameters are determined at the factory, including the intrinsic parameter matrix K and the distortion coefficient D. The camera extrinsic parameters represent the relationship between the camera coordinate system and the vehicle body coordinate system, that is, the installation position and posture of the camera relative to the vehicle. They need to be calibrated after installation, including the rotation matrix R and translation vector T that transfer the world coordinate system to the camera coordinate system.

[0047] The embodiment of the present invention provides a method for calibrating the external parameters of a vehicle-mounted camera based on a vertical calibration plate. Figure 1 As shown, the method comprises the following steps:

[0048] S101, establishing a vertical calibration plate including a checkerboard target plate and an adjustable bracket;

[0049] S102, setting the vertical calibration plate in front of the vehicle-mounted camera to be calibrated, adjusting the position of the adjustable bracket so that the position of the checkerboard target plate meets the set calibration conditions, wherein the calibration conditions include that the checkerboard target plate is parallel to the vehicle body, the upper edge of the checkerboard target plate is parallel to the ground, and the checkerboard target plate completely falls within the viewing angle of the vehicle-mounted camera to be calibrated;

[0050] S103, calculating the physical coordinates of each corner point in the checkerboard target plate according to the given offset parameters of the adjustable bracket relative to the origin of the vehicle coordinate system and the checkerboard parameters;

[0051] S104, collecting an image of the checkerboard target plate by using the vehicle-mounted camera to be calibrated, and obtaining the pixel coordinates of each corner point on the image according to a corner point detection algorithm;

[0052] S105. Calculate the initial value of the rotation matrix of the vehicle-mounted camera to be calibrated according to the physical coordinates and the pixel coordinates of all the corner points, and use the initial value of the rotation matrix as the external parameter of the vehicle-mounted camera to be calibrated.

[0053] Furthermore, in the above step S101, the establishment of a vertical calibration plate including a checkerboard target plate and an adjustable bracket includes:

[0054] S1011, determining checkerboard parameters according to the calibration distance and the target board image range, and preparing a checkerboard target board using the checkerboard parameters, wherein the calibration distance is the horizontal distance between the checkerboard target board and the vehicle-mounted camera to be calibrated, the target board image range is the proportion of the checkerboard target board falling into the viewing angle of the vehicle-mounted camera to be calibrated, the checkerboard parameters include the number of checkerboards and the size of each checkerboard, the number of checkerboards is expressed as the number of horizontal grids*the number of vertical grids, and the size of the checkerboard refers to the width and length of the checkerboard;

[0055] Specifically, according to the requirement that the calibration plate is placed at a calibration distance of 10 to 30 cm in front of the camera to be calibrated, and that the calibration plate can completely fall within the viewing angle of the camera to be calibrated at this distance, a black and white checkerboard calibration plate with a specification of 5*7 grids and each grid of 3 cm can be prepared. The vertical calibration plate prepared by the present invention is a small-sized vertical calibration plate, and placing it close to the camera can also ensure that it can completely fall within the viewing angle of the camera.

[0056] S1012, clamping the checkerboard target board on the adjustable bracket, adjusting the position of the checkerboard target board so that the upper edge of the checkerboard target board is perpendicular to the adjustable bracket, and obtaining the vertical calibration board. The adjustable bracket can be a retractable tripod, and upper and lower buckles are set on the bracket to clamp and fix the checkerboard target board. At the same time, the upper and lower buckles can also be used to adjust the horizontal direction of the checkerboard target board so that its upper edge is perpendicular to the bracket, thereby ensuring that the horizontal plane of the checkerboard target board is parallel to the xy plane of the vehicle coordinate system.

[0057] Furthermore, in the above step S102, the vertical calibration plate is set in front of the vehicle-mounted camera to be calibrated, and the position of the adjustable bracket is adjusted so that the position of the checkerboard target plate meets the set calibration conditions, which specifically includes:

[0058] Place the vertical calibration plate in front of the vehicle camera to be calibrated, adjust the height and rotation angle of the adjustable bracket, and adjust the horizontal distance between the vertical calibration plate and the vehicle camera to be calibrated (such as adjusting the horizontal distance between the two to a range of 10 to 30 cm), so that the checkerboard target plate is parallel to the vehicle body, and the checkerboard target plate completely falls within the viewing angle of the vehicle camera to be calibrated. Specifically, the height of the adjustable bracket can be adjusted first, and then rotated, so that the checkerboard target plate is kept as parallel to the vehicle body as possible.

[0059] Further, in the above step S103, after the vertical calibration board is placed, the world coordinates of the corner points on the checkerboard target board can be automatically calculated by the offset parameters and the checkerboard parameters. Since the checkerboard target board is only used to calibrate the rotation matrix in the external parameters, the translation matrix is ​​fixed according to the position of the lens to the center of the vehicle ground, and there is no need to accurately calibrate the translation matrix, the world coordinates (i.e., physical coordinates) of each corner point on it can be obtained according to a set of default parameters from the given checkerboard target board to the vehicle body. In specific implementation, the height of the checkerboard target board from the ground and the distance from the vehicle body do not need to be measured. It is only necessary to set a default value (such as the calibration distance given when designing the checkerboard target board) according to the front, back, left, and right directions of the lens installed on the vehicle body. For example, if the lens is on the right side of the vehicle, the distance from the checkerboard target board to the right side of the vehicle can be set to 0.3m, the distance to the front side of the vehicle can be set to 0m, and the distance from the bottom edge of the checkerboard target board to the ground can be set to 1.6m.

[0060] Furthermore, in the above step S104, obtaining pixel coordinates of corner points on the image according to a corner point detection algorithm includes:

[0061] S1041, extracting the initial pixel coordinates of each corner point on the image by using a corner point detection algorithm;

[0062] S1042: Dedistort the initial pixel coordinates using the internal parameters of the vehicle-mounted camera to be calibrated to obtain the pixel coordinates of each corner point.

[0063] Furthermore, the above-mentioned vehicle-mounted camera extrinsic parameter calibration method based on the vertical calibration plate further includes:

[0064] The center of the bottom surface of the vehicle is taken as the origin of the vehicle coordinate system, the front of the vehicle is defined as the positive direction of the y coordinate, the right side of the vehicle is defined as the positive direction of the x coordinate, and the upward direction of the ground is defined as the positive direction of the z coordinate; the offset parameter is obtained based on the positional relationship between the adjustable bracket and the origin of the vehicle coordinate system.

[0065] Furthermore, the above-mentioned vehicle-mounted camera extrinsic parameter calibration method based on the vertical calibration plate further includes:

[0066] S106. According to a given calibration line, the initial value of the rotation matrix is ​​evaluated and corrected to obtain a final rotation matrix, and the final rotation matrix is ​​used as an external parameter of the vehicle-mounted camera to be calibrated.

[0067] Specifically, the initial value of the rotation matrix is ​​evaluated and corrected according to the given calibration line to obtain the final rotation matrix, including:

[0068] S1061, given a calibration line 1m away from the vehicle body, on the ground and parallel to the vehicle body, projecting the calibration line according to the initial value of the rotation matrix to obtain a projection line, and comparing the projection line with the vehicle body;

[0069] S1062: If the projection line is parallel to the vehicle body, use the initial value of the rotation matrix as the final rotation matrix;

[0070] S1063. If the projection line is not parallel to the vehicle body, it means that the error of the initial value of the rotation matrix calculated in the previous stage is relatively large, and the initial value of the rotation matrix needs to be corrected until the rotation matrix corresponding to the projection line parallel to the vehicle body is obtained as the final rotation matrix.

[0071] Furthermore, in the above step S1063, the initial value of the rotation matrix is ​​corrected until a rotation matrix corresponding to the projection line parallel to the vehicle body is obtained as a final rotation matrix, including:

[0072] S10631, adjusting the rotation angle of the adjustable bracket, re-collecting a new image of the checkerboard target plate, and obtaining new pixel coordinates of each corner point on the new image according to a corner point detection algorithm;

[0073] S10632. Calculate a new rotation matrix of the vehicle-mounted camera to be calibrated based on the physical coordinates of all the corner points and the new pixel coordinates, and evaluate and correct the new rotation matrix until a rotation matrix corresponding to the projection line parallel to the vehicle body is obtained as the final rotation matrix.

[0074] The extrinsic parameter calibration method of a vehicle-mounted camera of the present invention comprises the following steps: firstly, a vertical calibration plate is established, the vertical calibration plate is placed in front of the vehicle-mounted camera to be calibrated, and its position is adjusted to satisfy the calibration conditions; secondly, the physical coordinates of each corner point are determined according to the offset parameters of a given adjustable bracket relative to the origin of a vehicle coordinate system and the checkerboard parameters; then, the pixel coordinates of each corner point in the image of the acquired checkerboard target plate are obtained by using a corner point detection algorithm; finally, the initial value of the rotation matrix of the vehicle-mounted camera to be calibrated is calculated according to the coordinate pairs of the pixel coordinates and the physical coordinates of all the corner points on the checkerboard target plate, so as to obtain its extrinsic parameter result.

[0075] Compared with the traditional method, the method of the present invention does not need to prepare a large-sized calibration cloth, but only needs a small-sized chessboard calibration plate (such as the size of A4 paper), which is portable and highly accurate, and does not need to measure the parameters of the calibration plate to the vehicle. Even in a harsh and narrow on-site calibration environment, it is easy to calibrate, and the calibration effect can be observed intuitively, and the parameters can be adjusted conveniently and quickly to ensure the reliability of the calibration effect. It can be suitable for various professionals and non-professionals to quickly complete the installation and calibration work on site. Furthermore, the method of the present invention is suitable for the external parameter calibration of single and multiple lenses. During calibration, it is only necessary to place the calibration plate in front of the camera to be calibrated, and the data of other cameras are required. The method has good adaptability.

[0076] Based on the same inventive concept, an embodiment of the present invention also provides an extrinsic parameter calibration device for a vehicle-mounted camera based on a vertical calibration plate, as described in the following embodiments. Since the principle of solving the problem by the extrinsic parameter calibration device for a vehicle-mounted camera is similar to that of the extrinsic parameter calibration method for a vehicle-mounted camera in the above-mentioned embodiment, the implementation of the extrinsic parameter calibration device for a vehicle-mounted camera can refer to the implementation of the extrinsic parameter calibration method for a vehicle-mounted camera, and the repeated parts will not be repeated. As used below, the terms "unit" or "module" may be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, the implementation in hardware, or a combination of software and hardware, is also possible and conceivable.

[0077] Figure 2 is a structural block diagram of an extrinsic calibration device for a vehicle-mounted camera based on a vertical calibration plate disclosed in an embodiment of the present invention, such as Figure 2 As shown, it includes: a vertical calibration plate 201, a corner point physical coordinate calculation module 202, a corner point pixel coordinate acquisition module 203 and a vehicle-mounted camera external parameter calculation module 204. The structure is described below.

[0078] The vertical calibration plate 201 includes a checkerboard target plate and an adjustable bracket, and the checkerboard target plate is clamped on the adjustable bracket.

[0079] The physical coordinate calculation module 202 is used to calculate the physical coordinates of each corner point in the checkerboard target plate using the offset parameters and the checkerboard parameters;

[0080] The corner pixel coordinate acquisition module 203 is used to calculate the physical coordinates of each corner point in the checkerboard target plate according to the given offset parameters of the adjustable bracket relative to the origin of the vehicle coordinate system and the checkerboard parameters;

[0081] The vehicle camera extrinsic parameter calculation module 204 is used to calculate the initial value of the rotation matrix of the vehicle camera to be calibrated according to the physical coordinates and the pixel coordinates of all the corner points, and use the initial value of the rotation matrix as the extrinsic parameter of the vehicle camera to be calibrated.

[0082] Further, see Figure 2 As shown, the above-mentioned device also includes an evaluation and correction module 205, which is used to evaluate and correct the initial value of the rotation matrix according to a given calibration line to obtain a final rotation matrix, and use the final rotation matrix as an external parameter of the vehicle-mounted camera to be calibrated.

[0083] In this embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method of any of the above-mentioned corner point physical coordinate calculation module 202, corner point pixel coordinate acquisition module 203, vehicle-mounted camera external parameter calculation module 204, and evaluation and correction module 205 is implemented.

[0084] Specifically, the computer device may be a computer terminal, a server or a similar computing device.

[0085] In this embodiment, a computer-readable storage medium is provided, which stores a computer program for executing any of the above-mentioned corner point physical coordinate calculation module 202, corner point pixel coordinate acquisition module 203, vehicle-mounted camera external parameter calculation module 204 and evaluation and correction module 205.

[0086] Specifically, computer-readable storage media include permanent and non-permanent, removable and non-removable media that can store information by any method or technology. Information can be computer-readable instructions, data structures, program modules or other data. Examples of computer-readable storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable storage media does not include transitory media such as modulated data signals and carrier waves.

[0087] Obviously, those skilled in the art should understand that the modules or steps of the above-mentioned embodiments of the present invention can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, and optionally, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order from that here, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. In this way, the embodiments of the present invention are not limited to any specific combination of hardware and software.

[0088] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the embodiments of the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for calibrating extrinsic parameters of a vehicle-mounted camera based on a vertical calibration plate, characterized in that: The method comprises: Establishing a vertical calibration plate including a checkerboard target plate and an adjustable bracket; The vertical calibration plate is set in front of the vehicle-mounted camera to be calibrated, and the position of the adjustable bracket is adjusted so that the position of the checkerboard target plate meets the set calibration conditions, wherein the calibration conditions include that the checkerboard target plate is parallel to the vehicle body, the upper edge of the checkerboard target plate is parallel to the ground, and the checkerboard target plate completely falls within the viewing angle of the vehicle-mounted camera to be calibrated; Calculate the physical coordinates of each corner point in the checkerboard target plate according to the given offset parameters of the adjustable bracket relative to the origin of the vehicle coordinate system and the checkerboard parameters; The image of the checkerboard target plate is collected by the on-board camera to be calibrated, and the pixel coordinates of each corner point on the image are obtained according to a corner point detection algorithm; According to the physical coordinates and the pixel coordinates of all the corner points, the initial value of the rotation matrix of the vehicle-mounted camera to be calibrated is calculated, and the initial value of the rotation matrix is ​​used as the external parameter of the vehicle-mounted camera to be calibrated.

2. The vehicle-mounted camera extrinsic parameter calibration method based on a vertical calibration plate according to claim 1, characterized in that: The method of establishing a vertical calibration plate including a checkerboard target plate and an adjustable bracket includes: Determine a checkerboard parameter according to a calibration distance and a target board image range, and prepare a checkerboard target board using the checkerboard parameter, wherein the calibration distance is a horizontal distance between the checkerboard target board and the vehicle-mounted camera to be calibrated, the target board image range is a ratio of the checkerboard target board falling into the viewing angle of the vehicle-mounted camera to be calibrated, and the checkerboard parameter includes the number of checkerboards and the size of each checkerboard; The checkerboard target plate is clamped on the adjustable bracket, and the position of the checkerboard target plate is adjusted so that the upper edge of the checkerboard target plate is perpendicular to the adjustable bracket, thereby obtaining the vertical calibration plate.

3. The vehicle-mounted camera extrinsic calibration method based on a vertical calibration plate according to claim 1, characterized in that: The vertical calibration plate is arranged in front of the vehicle-mounted camera to be calibrated, and the position of the adjustable bracket is adjusted so that the position of the checkerboard target plate meets the set calibration conditions, including: Place the vertical calibration plate in front of the vehicle-mounted camera to be calibrated, adjust the height and rotation angle of the adjustable bracket, and adjust the horizontal distance between the adjustable bracket and the vehicle-mounted camera to be calibrated, so that the checkerboard target plate is parallel to the vehicle body and the checkerboard target plate completely falls within the viewing angle of the vehicle-mounted camera to be calibrated.

4. The vehicle-mounted camera extrinsic parameter calibration method based on a vertical calibration plate according to claim 1, characterized in that: The step of obtaining the pixel coordinates of each corner point on the image according to the corner point detection algorithm includes: Extracting the initial pixel coordinates of each corner point on the image by a corner point detection algorithm; The initial pixel coordinates are dedistorted using the internal parameters of the vehicle-mounted camera to be calibrated to obtain the pixel coordinates of each corner point.

5. The vehicle-mounted camera extrinsic calibration method based on a vertical calibration plate according to any one of claims 1 to 4, characterized in that: The method further comprises: The center of the bottom surface of the vehicle is taken as the origin of the vehicle coordinate system, the front of the vehicle is defined as the positive direction of the y coordinate, the right side of the vehicle is defined as the positive direction of the x coordinate, and the upward direction of the ground is defined as the positive direction of the z coordinate; the offset parameter is obtained based on the positional relationship between the adjustable bracket and the origin of the vehicle coordinate system.

6. The vehicle-mounted camera extrinsic calibration method based on a vertical calibration plate according to any one of claims 1 to 4, characterized in that: The method further comprises: According to a given calibration line, the initial value of the rotation matrix is ​​evaluated and corrected to obtain a final rotation matrix, and the final rotation matrix is ​​used as an external parameter of the vehicle-mounted camera to be calibrated.

7. The vehicle-mounted camera extrinsic calibration method based on a vertical calibration plate according to claim 6, characterized in that: The step of evaluating and correcting the initial value of the rotation matrix according to the given calibration line to obtain the final rotation matrix includes: Given a calibration line parallel to the vehicle body, projecting the calibration line according to the initial value of the rotation matrix to obtain a projection line, and comparing the projection line with the vehicle body; If the projection line is parallel to the vehicle body, the initial value of the rotation matrix is ​​used as the final rotation matrix; If the projection line is not parallel to the vehicle body, the initial value of the rotation matrix is ​​corrected until a rotation matrix corresponding to the projection line parallel to the vehicle body is obtained as the final rotation matrix.

8. The vehicle-mounted camera extrinsic parameter calibration method based on a vertical calibration plate according to claim 7, characterized in that: The initial value of the rotation matrix is ​​corrected until a rotation matrix corresponding to the projection line parallel to the vehicle body is obtained as a final rotation matrix, including: Adjusting the rotation angle of the adjustable bracket, re-collecting a new image of the checkerboard target plate, and obtaining new pixel coordinates of each corner point on the new image according to a corner point detection algorithm; According to the physical coordinates of all the corner points and the new pixel coordinates, a new rotation matrix of the vehicle-mounted camera to be calibrated is calculated, and the new rotation matrix is ​​evaluated and corrected until a rotation matrix corresponding to the projection line parallel to the vehicle body is obtained as the final rotation matrix.

9. A vehicle-mounted camera extrinsic calibration device based on a vertical calibration plate, characterized in that: include: A vertical calibration plate, the vertical calibration plate comprising a checkerboard target plate and an adjustable bracket, the checkerboard target plate being clamped on the adjustable bracket; A corner point physical coordinate calculation module, the physical coordinate calculation module is used to calculate the physical coordinates of each corner point in the checkerboard target plate according to the given offset parameters of the adjustable bracket relative to the origin of the vehicle coordinate system and the checkerboard parameters; A corner point pixel coordinate acquisition module, the corner point pixel coordinate acquisition module is used to collect the image of the checkerboard target plate through the vehicle-mounted camera to be calibrated, and obtain the pixel coordinates of each corner point on the image according to the corner point detection algorithm; The vehicle-mounted camera extrinsic parameter calculation module is used to calculate the initial value of the rotation matrix of the vehicle-mounted camera to be calibrated according to the physical coordinates and the pixel coordinates of all the corner points, and use the initial value of the rotation matrix as the extrinsic parameter of the vehicle-mounted camera to be calibrated.

10. The vehicle-mounted camera extrinsic parameter calibration device based on a vertical calibration plate according to claim 9, characterized in that: Also includes: The evaluation and correction module is used to evaluate and correct the initial value of the rotation matrix according to a given calibration line to obtain a final rotation matrix, and use the final rotation matrix as an external parameter of the vehicle-mounted camera to be calibrated.

Images