Camera extrinsic parameter calibration method, apparatus, computer equipment, and readable storage medium

Abstract

This application relates to a camera extrinsic parameter calibration method, apparatus, computer device, and readable storage medium. The method includes: acquiring a calibration image captured by a camera on a calibration target; wherein a mirror device is disposed at the outer edge of the calibration target, the calibration image includes the calibration target and at least a portion of the calibration target as a mirrored calibration target in the mirror device, the calibration target includes multiple original calibration points, and the mirrored calibration target includes multiple mirrored calibration points; acquiring the first coordinates of each calibration point in a world coordinate system; performing feature point detection based on the calibration image, and determining the second coordinates of the detected feature points in an image coordinate system; determining the feature points corresponding to each calibration point from the multiple feature points; and determining the camera's extrinsic parameters based on the first coordinates of each calibration point and the second coordinates of the corresponding feature points. This method can improve the accuracy of the camera extrinsic parameters obtained during calibration.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to a method, apparatus, computer device, and computer-readable storage medium for calibrating camera extrinsic parameters. Background Technology

[0002] With the development of computer technology, computer vision technology has emerged. Computer vision is a science that studies how to make machines "see". More specifically, it refers to machine vision, which uses cameras and computers to replace human eyes to identify, track and measure targets, and further performs graphic processing to make the computer-processed images more suitable for human eyes to observe or to be transmitted to instruments for detection.

[0003] In computer vision technology, camera extrinsic calibration is often required. Camera extrinsic calibration is the process of determining the position and orientation of the camera in the world coordinate system. Based on the extrinsic parameters, a mapping between the image coordinate system and the world coordinate system can be established.

[0004] However, current camera extrinsic calibration methods often suffer from low accuracy in obtaining camera extrinsic parameters. Summary of the Invention

[0005] Therefore, it is necessary to provide a camera extrinsic parameter calibration method, apparatus, computer equipment, computer-readable storage medium, and computer program product that can improve the accuracy of camera extrinsic parameters obtained through calibration, in order to address the aforementioned technical problems.

[0006] Firstly, this application provides a method for calibrating camera extrinsic parameters, including:

[0007] Acquire calibration images captured by the camera targeting the calibration target;

[0008] Wherein, a mirror device is provided at the outer edge of the calibration target, the calibration image includes the calibration target and at least part of the calibration target's mirrored calibration target in the mirror device, the calibration target includes the original calibration point, the mirrored calibration target includes the mirrored calibration point, and the original calibration point and the mirrored calibration point form a calibration point set;

[0009] Obtain the first coordinates of each calibration point in the world coordinate system from the calibration point set;

[0010] Feature point detection is performed based on the calibration image to determine the second coordinates of the feature points corresponding to each calibration point in the calibration point set in the image coordinate system.

[0011] The extrinsic parameters of the camera are determined based on the first coordinates of each calibration point and the second coordinates of the corresponding feature points in the image coordinate system.

[0012] Secondly, this application also provides a camera extrinsic parameter calibration device, comprising:

[0013] A calibration image acquisition module is used to acquire a calibration image captured by a camera targeting a calibration target; wherein, a mirror device is provided at the outer edge of the calibration target, the calibration image includes the calibration target and at least a portion of the calibration target as a mirrored calibration target in the mirror device, the calibration target includes multiple original calibration points, and the mirrored calibration target includes multiple mirrored calibration points;

[0014] The first coordinate acquisition module is used to acquire the first coordinates of each of the original calibration points in the world coordinate system, and to acquire the first coordinates of each of the mirror calibration points in the world coordinate system.

[0015] The second coordinate acquisition module is used to perform feature point detection based on the calibration image and determine the second coordinates of the detected feature points in the image coordinate system.

[0016] The correspondence determination module is used to determine the feature points corresponding to each of the original calibration points and the feature points corresponding to each of the mirror calibration points from the plurality of feature points.

[0017] The extrinsic parameter determination module is used to determine the extrinsic parameters of the camera based on the first coordinates of each of the original calibration points, the second coordinates of the feature points corresponding to each of the original calibration points, the first coordinates of each of the mirror calibration points, and the second coordinates of the feature points corresponding to each of the mirror calibration points.

[0018] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the above-described camera extrinsic parameter calibration method.

[0019] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-described camera extrinsic parameter calibration method.

[0020] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the above-described camera extrinsic parameter calibration method.

[0021] The aforementioned camera extrinsic parameter calibration method, apparatus, computer equipment, computer-readable storage medium, and computer program product include a mirror device at the outer edge of the calibration target. The calibration image includes the calibration target and at least a portion of the calibration target reflected in the mirror device as a mirrored calibration target. The calibration target includes multiple original calibration points, and the mirrored calibration target includes multiple mirrored calibration points. During calibration, the first coordinates of each original calibration point in the world coordinate system and the first coordinates of each mirrored calibration point in the world coordinate system can be obtained. Feature point detection is performed based on the calibration image, and the multiple detected feature points are determined in the image coordinate system. The second coordinates under the calibration system are used to determine the feature points corresponding to each original calibration point and each mirror calibration point from multiple feature points. Based on the first coordinates of each original calibration point, the second coordinates of the feature points corresponding to each original calibration point, the first coordinates of each mirror calibration point, and the second coordinates of the feature points corresponding to each mirror calibration point, the extrinsic parameters of the camera are determined. Since the original calibration target can be extended through the mirror device, the range of extrinsic parameter calibration points can be expanded, improving the accuracy of long-distance projection, and enabling the calibrated extrinsic parameters to be applied to point projection over a larger range. Attached Figure Description

[0022] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 This is a diagram illustrating the application environment of the camera extrinsic parameter calibration method in some embodiments;

[0024] Figure 2 This is a flowchart illustrating the camera extrinsic parameter calibration method in some embodiments;

[0025] Figure 3 This is a schematic diagram showing the location of the mirror calibration points in some embodiments;

[0026] Figure 4 This is a schematic diagram showing the location of the mirrors installed in the factory calibration room in some embodiments;

[0027] Figure 5 This is a schematic diagram of the world coordinate system in the factory calibration room in some embodiments;

[0028] Figure 6 This is a schematic diagram of calibration images captured by a vehicle-mounted camera in some embodiments;

[0029] Figure 7This is a schematic diagram of the overall process involved in the calibration procedure in some embodiments;

[0030] Figure 8 This is a schematic diagram of the corner points of the chessboard grid in some embodiments;

[0031] Figure 9 This is a schematic diagram showing the coordinate positions of corner points in the calibration image in some embodiments;

[0032] Figure 10 This is a schematic diagram illustrating the rearrangement of the corner points in some embodiments;

[0033] Figure 11 This is a structural block diagram of the camera extrinsic parameter calibration device in some embodiments;

[0034] Figure 12 These are internal structural diagrams of the computer device in some embodiments;

[0035] Figure 13 This is an internal structural diagram of a computer device in some other embodiments. Detailed Implementation

[0036] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0037] The camera extrinsic parameter calibration method provided in this application embodiment can be applied to, for example... Figure 1 In the application environment shown, camera 102 can capture a calibration image of a calibration target. A mirror device is provided at the outer edge of the calibration target. The calibration image includes the calibration target and at least a portion of the calibration target as a mirrored calibration target in the mirror device. The calibration target includes multiple original calibration points. After acquiring the calibration image, computer device 104 can acquire the first coordinates of each original calibration point in the world coordinate system and the first coordinates of each mirrored calibration point in the world coordinate system. Based on the calibration image, feature point detection is performed, and the second coordinates of the detected feature points in the image coordinate system are determined. From the multiple feature points, the feature points corresponding to each original calibration point and each mirrored calibration point are determined respectively. Based on the first coordinates of each original calibration point, the second coordinates of the feature points corresponding to each original calibration point, the first coordinates of each mirrored calibration point, and the second coordinates of the feature points corresponding to each mirrored calibration point, the camera's extrinsic parameters are determined.

[0038] The computer device 104 may include, but is not limited to, various personal computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices may include smart speakers, smart TVs, smart air conditioners, smart in-vehicle devices, projection devices, etc. Portable wearable devices may include smartwatches, smart bracelets, head-mounted devices, etc. Head-mounted devices may include virtual reality (VR) devices, augmented reality (AR) devices, smart glasses, etc.

[0039] In some exemplary embodiments, such as Figure 2 As shown, a method for calibrating camera extrinsic parameters is provided, which can be applied to... Figure 1 Taking computer device 104 as an example, the explanation includes the following steps 202 to 210. Wherein:

[0040] Step 202: Obtain a calibration image captured by the camera on the calibration target; wherein, a mirror device is provided at the outer edge of the calibration target, the calibration image includes the calibration target and at least part of the calibration target as a mirrored calibration target in the mirror device, the calibration target includes multiple original calibration points, and the mirrored calibration target includes multiple mirrored calibration points.

[0041] The calibration target is used to assist the calibration process. The calibration target may have known geometric features, such as a checkerboard pattern, a dotted pattern, or other objects with identifiable characteristics. A mirror device is provided at the outer edge of the calibration target. For example, the mirror device may be vertically positioned at the outer edge of the calibration target, such that the mirrored calibration target within the mirror device is symmetrical to the original calibration target about the mirror device. It is understood that in some other embodiments, the mirror device may also be positioned at a preset angle at the outer edge of the calibration target. For example, the mirror device may be positioned at a certain distance from the outer edge of the calibration target. For example, the mirror device may also be positioned parallel to the outer edge of the calibration target.

[0042] Because a mirror device is provided at the outer edge of the calibration target, at least a portion of the calibration target can be mirrored in the mirror device based on the mirror reflection of the mirror device. This mirror image is the mirror calibration target of the at least part of the calibration target in the mirror device. During the process of shooting the calibration target, the camera can face the mirror device directly, so that the captured calibration image can include the calibration target and its mirror image in the mirror device. The calibration target includes multiple original calibration points, which are usually points with certain characteristics, such as corner points of a checkerboard pattern. The mirror calibration target includes multiple mirror calibration points, each corresponding to one of the original calibration points in the calibration target. When a portion of the calibration target containing a certain original calibration point has a corresponding mirror image in the mirror device, that original calibration point has a corresponding mirror image in the mirror device. This mirror image is the mirror calibration point of the original calibration point, thus allowing more calibration points to be expanded using the mirror device.

[0043] Specifically, the computer device can acquire a calibration image taken by the camera targeting the calibration target via wired or wireless means. The calibration image includes the calibration target and a mirror image of at least part of the calibration target in the mirror device. The computer device can further determine the camera's extrinsic parameters based on the calibration image.

[0044] Step 204: Obtain the first coordinates of each original calibration point in the world coordinate system, and obtain the first coordinates of each mirror calibration point in the world coordinate system.

[0045] Specifically, during the calibration process, the origin of the world coordinate system is fixed. Therefore, the first coordinate of the original calibration point in the world coordinate system can be determined according to the position of the origin. For example, assuming the calibration target is a checkerboard pattern, the original calibration point is the corner point of the checkerboard, and the size of each checkerboard is n, the first coordinate of the original calibration point in the world coordinate system can be determined according to the distance between the checkerboard pattern and the origin of the world coordinate system and the position of the checkerboard where the original calibration point is located.

[0046] The first coordinate of the mirror calibration point in world coordinates can be determined based on the first coordinate of its corresponding original coordinate point and the relative positional relationship between the mirror device and the calibration target. For example, when the mirror device is vertically set at the outer edge of the calibration target, for each original calibration point with a mirror calibration point, the distance of the original calibration point from the mirror device can be determined first. The mirror calibration point of the original calibration point is symmetrical to the original calibration point about the mirror device, so the first coordinate of the mirror calibration point in world coordinates can be determined.

[0047] Step 206: Perform feature point detection based on the calibration image, and determine the second coordinates of the multiple detected feature points in the image coordinate system.

[0048] In camera extrinsic calibration, the main purpose of feature point detection is to extract stable and repeatable key points, such as corner points or round points, from the images captured by the camera. These points will be used in subsequent matching and calculation processes to determine the camera's extrinsic parameters.

[0049] Specifically, the computer device can perform feature point detection based on the calibration image to obtain multiple feature points, and then determine the second coordinate of each feature point in the image coordinate system based on the position of each feature point in the calibration image.

[0050] For example, the computer device can first perform distortion correction on the calibration image to obtain the target image, and then use traditional mathematical calculation methods to detect feature points. For example, it can use any of the following algorithms for feature point detection: SIFT (Scale-Invariant Feature Transform), SURF (Speeded Up Robust Features), ORB (Oriented FAST and Rotated BRIEF), or FAST (features from accelerated segment test).

[0051] For example, after obtaining the target image through distortion correction, the computer device can also use deep learning methods to perform feature point detection. For instance, a feature point detection method based on Convolutional Neural Networks (CNN) can be used. By training the network, image features can be automatically learned, which can then be applied to feature point detection on the calibration image.

[0052] Step 208: From multiple feature points, determine the feature points corresponding to each original calibration point and the feature points corresponding to each mirror calibration point.

[0053] Specifically, the calibration image is captured for the calibration target, and the calibration image includes the calibration target and at least a portion of the calibration target as a mirrored calibration target in the mirror device. Therefore, for each original calibration point in the calibration target, there is a corresponding feature point in the calibration image, and for each mirrored calibration point, there is also a corresponding feature point in the calibration image. Thus, after obtaining the feature points in the calibration image, the computer device can establish the correspondence between each original calibration point and its corresponding feature point, and establish the correspondence between each mirrored calibration point and its corresponding feature point.

[0054] For example, the computer device can sort multiple original calibration points and multiple mirror calibration points according to a preset method, and sort multiple feature points according to a preset method. For each original calibration point, the feature point with the same sorting position as the original calibration point is determined as the feature point corresponding to the original calibration point. For each mirror calibration point, the feature point with the same sorting position as the mirror calibration point is determined as the feature point corresponding to the mirror calibration point.

[0055] Step 210: Determine the camera's extrinsic parameters based on the first coordinates of each original calibration point, the second coordinates of the corresponding feature points of each original calibration point, the first coordinates of each mirror calibration point, and the second coordinates of the corresponding feature points of each mirror calibration point.

[0056] Specifically, after establishing the correspondence between calibration points and feature points, including the correspondence between the original calibration points and their corresponding feature points, and the correspondence between the mirror calibration points and their corresponding feature points, the computer equipment can further perform parameter estimation on these point pairs with corresponding relationships. For example, mathematical models and optimization algorithms (such as the least squares method) can be used to estimate the rotation matrix and translation vector. Furthermore, the estimated extrinsic parameters can be verified and optimized. For example, the accuracy of the calibration results can be verified by comparing the predicted image points with the actually observed points, and necessary adjustments can be made.

[0057] The aforementioned camera extrinsic calibration method includes a mirror device at the outer edge of the calibration target. The calibration image includes the calibration target and at least a portion of the calibration target reflected in the mirror device. The calibration target includes multiple original calibration points, and the reflected calibration target includes multiple reflected calibration points. During calibration, the first coordinates of each original calibration point in the world coordinate system and the first coordinates of each reflected calibration point in the world coordinate system are obtained. Feature point detection is performed based on the calibration image, and the second coordinates of the detected feature points in the image coordinate system are determined. In the calibration process, the feature points corresponding to each original calibration point and each mirror calibration point are determined. Based on the first coordinates of each original calibration point, the second coordinates of the feature points corresponding to each original calibration point, the first coordinates of each mirror calibration point, and the second coordinates of the feature points corresponding to each mirror calibration point, the extrinsic parameters of the camera are determined. Since the original calibration target can be extended through the mirror device, the range of extrinsic parameter calibration points can be expanded, improving the accuracy of long-distance projection and enabling the calibrated extrinsic parameters to be applied to point projection over a larger range.

[0058] In some exemplary embodiments, feature point detection is performed based on a calibration image, and the second coordinates of each detected feature point in the image coordinate system are determined, including: performing distortion correction processing on the calibration image to obtain a target image corresponding to the calibration image; performing feature point detection on the target image to obtain multiple feature points; and determining the second coordinates of each feature point in the image coordinate system based on the position of each feature point in the calibration image.

[0059] Image distortion correction uses a series of algorithms and techniques to eliminate distortions caused by camera lens, shooting angle, or environmental factors during image acquisition, enabling the image to more realistically and accurately reflect the appearance of the original scene.

[0060] Specifically, computer equipment can establish a corresponding distortion model based on the distortion coefficients obtained from camera calibration. This distortion model typically includes radial and tangential distortion models to describe the distortion of pixels in the image. Then, each pixel in the calibration image can be remapped using the distortion model, i.e., the position of each pixel in the distortion-free image can be calculated based on the distortion model. This process involves coordinate transformation and interpolation calculations to ensure the quality of the remapped image. The computer equipment can then use interpolation algorithms (such as bilinear interpolation, bicubic interpolation, etc.) to generate a distortion-free image based on the remapped pixel coordinates and the pixel values ​​of the original image. This distorted image is the target image corresponding to the calibration image. The choice of interpolation algorithm depends on the requirements for image quality and computational efficiency.

[0061] After obtaining the target image, the computer device can further perform feature point detection on the target image to obtain multiple feature points. Based on the position of each feature point in the calibrated image, the second coordinate of each feature point in the image coordinate system is determined.

[0062] In this embodiment, by performing distortion correction processing on the calibration image to obtain the target image, and then performing feature point detection on the target image to determine the second coordinates of the feature points, the accuracy of feature detection can be improved, thereby obtaining a more accurate second coordinate and improving the accuracy of camera extrinsic parameter calibration.

[0063] In some embodiments, determining the feature points corresponding to each original calibration point and each mirror calibration point from a plurality of feature points includes:

[0064] Multiple original calibration points and multiple mirror calibration points are sorted according to a preset method; multiple feature points are sorted according to a preset method; for each original calibration point, the feature points with the same sorting position as the original calibration point are identified as the feature points corresponding to the original calibration point; for each mirror calibration point, the feature points with the same sorting position as the mirror calibration point are identified as the feature points corresponding to the mirror calibration point.

[0065] Specifically, the computer equipment can sort all calibration points, including original calibration points and mirror calibration points, according to a preset method, and sort feature points detected based on the calibration image according to the same preset method. Then, for each original calibration point, the feature points with the same sorting position as the original calibration point are identified as the feature points corresponding to the original calibration point; similarly, for each mirror calibration point, the feature points with the same sorting position as the mirror calibration point are identified as the feature points corresponding to the mirror calibration point. It is understood that in specific applications, the sorting method can be set as needed.

[0066] For example, suppose there are 25 calibration points, including the original calibration point and the mirror calibration point. After sorting the calibration points and feature points according to a preset method, if the sorting position of a certain original calibration point is N, then the sorting position of its corresponding feature point is also N. If the sorting position of a certain mirror calibration point is M, then the sorting position of its corresponding feature point is also M. Here, both N and M are less than or equal to 25.

[0067] In the above embodiments, since the calibration points and feature points, including the original calibration points and mirror calibration points, can be sorted in the same sorting manner, and then a corresponding relationship can be established based on the sorting position, the corresponding relationship can be established quickly, thereby improving the efficiency of external parameter calibration.

[0068] In some embodiments, the calibration target is a preset pattern with known geometric features, and the mirror device is vertically disposed at the outer edge of the preset pattern.

[0069] Specifically, in this embodiment, the calibration target can be a preset pattern. The preset pattern has known geometric features. The preset image can be, for example, a checkerboard pattern. The overall shape of the preset pattern can be rectangular and set on a horizontal ground. The mirror device is vertically set at the outer edge of the preset pattern. The lower edge of the mirror device can be parallel to one of the edges of the preset pattern and perpendicular to the horizontal ground.

[0070] For example, when the mirror device is vertically positioned at the outer edge of the preset pattern, it can be spaced a certain distance L from the outer edge to ensure that the preset pattern can be fully reflected in the mirror device. The specific value of L can be set according to actual needs.

[0071] It is understood that in specific applications, the preset pattern is not limited to a checkerboard pattern; any pattern with known geometric features is acceptable. This application does not limit the preset pattern.

[0072] In the above embodiments, since a preset image with known geometric features is used as the calibration target and the mirror device is vertically set at the outer edge of the preset image, the convenience of the external parameter calibration process is improved.

[0073] In some embodiments, when the preset pattern is a checkerboard pattern, obtaining the first coordinates of each original calibration point in the world coordinate system and obtaining the first coordinates of each mirror calibration point in the world coordinate system includes: for each original calibration point, determining the first coordinates of the original calibration point in the world coordinate system based on the position of the original calibration point in the checkerboard pattern; for each mirror calibration point, obtaining the first coordinates of the original calibration point corresponding to the mirror calibration point in the world coordinate system, and determining the first coordinates of the mirror calibration point in the world coordinate system based on the first coordinates of the original calibration point corresponding to the mirror calibration point in the world coordinate system, the size of the checkerboard squares of the checkerboard pattern, and the distance between the mirror device and the outer edge of the checkerboard pattern.

[0074] Specifically, since the origin of the world coordinate system is fixed and the size of the checkerboard squares in the checkerboard pattern is also known, for each original calibration point, the first coordinate of the original calibration point in the world coordinate system can be determined based on the distance between the checkerboard pattern and the origin of the world coordinate system and the position of the checkerboard square where the original calibration point is located.

[0075] For a mirror calibration point, the original calibration point corresponding to the mirror calibration point can be determined first, that is, the original calibration point used to form the mirror calibration point. Then, the first coordinate of the original calibration point in the world coordinate system can be obtained. Based on the first coordinate of the original calibration point in the world coordinate system, the size of the checkerboard squares of the checkerboard pattern, and the distance between the mirror device and the outer edge of the checkerboard pattern, the first coordinate of the mirror calibration point in the world coordinate system can be determined.

[0076] For example, see reference. Figure 3 Suppose that there is an original calibration point P in the checkerboard pattern, and the position of P is as follows: Figure 3 As shown, its coordinates in the world coordinate system are (x... p y p Given that the size of the chessboard square containing p is n*n, and based on the distance L between the mirror device 304 and the chessboard pattern 302, the coordinates of the mirror calibration point p′ of p can be deduced to be (x...). p y p +4*n+2*L), the coordinates of other calibrated chessboard corner points in the world coordinate system can be obtained by the same principle.

[0077] In the above embodiments, since the preset pattern is a checkerboard pattern, the first coordinate of the mirror calibration point in the world coordinate system is determined based on the first coordinate of the original calibration point corresponding to the mirror calibration point in the world coordinate system, the size of the checkerboard squares of the checkerboard pattern, and the distance between the mirror device and the outer edge of the checkerboard pattern. This allows for the rapid determination of the coordinates of the mirror calibration point and improves the efficiency of external parameter calibration.

[0078] In some embodiments, determining the camera's extrinsic parameters based on the first coordinates of each original calibration point, the second coordinates of the corresponding feature points of each original calibration point, the first coordinates of each mirror calibration point, and the second coordinates of the corresponding feature points of each mirror calibration point includes:

[0079] Parameter estimation is performed based on the first coordinates of each original calibration point, the second coordinates of the corresponding feature points of each original calibration point, the first coordinates of each mirror calibration point, and the second coordinates of the corresponding feature points of each mirror calibration point to obtain the initial rotation matrix and the initial translation vector. The initial rotation matrix and the initial translation vector are evaluated to obtain the evaluation results. When the evaluation results meet the preset calibration accuracy conditions, the initial rotation matrix and the initial translation vector are determined as the camera's extrinsic parameters.

[0080] Specifically, after obtaining the first coordinates of each calibration point, including the original calibration point and the mirror calibration point, and the second coordinates of the corresponding feature points of each calibration point and establishing the correspondence, the computer device can perform parameter estimation based on these point pairs with corresponding relationships to obtain the initial extrinsic parameters of the camera, namely the initial rotation matrix and the initial translation vector. The parameter estimation here can be implemented using existing extrinsic parameter calculation functions, which will not be elaborated here.

[0081] The computer equipment can further evaluate the initial extrinsic parameters and obtain evaluation results. By evaluating the initial extrinsic parameters, the accuracy of the camera's initial extrinsic parameters (including the rotation matrix and translation vector) can be checked, ensuring that they can correctly describe the camera's position and attitude in the world coordinate system. The computer equipment can further determine whether the initial extrinsic parameters meet preset calibration accuracy conditions. When the computer equipment determines that the evaluation results meet the preset calibration accuracy conditions, the initial rotation matrix and initial translation vector are determined as the camera's extrinsic parameters. Here, the preset calibration accuracy conditions can be determined according to different evaluation methods.

[0082] For example, a computer device can calculate the reprojection error based on initial extrinsic parameters. If the reprojection error is sufficiently small, such as less than a certain threshold, the initial camera extrinsic parameters are considered to meet the preset calibration accuracy conditions and are therefore accurate. In a specific implementation, points in the world coordinate system can be projected onto the image plane using the camera extrinsic parameters, and the difference between these projected points and the actually detected points in the image can be calculated to obtain the reprojection error.

[0083] For example, a computer device can evaluate initial extrinsic parameters through scene consistency checks. In a specific implementation, the same scene can be captured from multiple perspectives, and the images from different perspectives can be aligned using camera extrinsic parameters. The aligned images are then checked to see if the same feature points remain consistent across different perspectives. If the average difference in the position of feature points across different perspectives is within an acceptable range, such as less than a certain threshold, the initial camera extrinsic parameters are considered to meet the preset calibration accuracy conditions and are therefore accurate.

[0084] Furthermore, when the computer equipment determines that the evaluation results do not meet the preset calibration accuracy conditions, a calibration optimization step is executed.

[0085] For example, the computer device can use any of the algorithms such as gradient descent, Newton's method, or the Levenberg-Marquardt algorithm to minimize the reprojection error by iteratively adjusting the camera's extrinsic parameters until a certain convergence condition is met or a preset number of iterations is reached, thus obtaining the camera's extrinsic parameters.

[0086] For example, computer devices can introduce additional constraints during the optimization process, such as camera non-holonomic constraints and camera motion characteristics, to improve the accuracy and robustness of the optimization results. Taking a vehicle-mounted camera as an example, in specific applications, the Random Sample Consensus Algorithm (RANSAC) can be improved by utilizing the vehicle's motion characteristics to enhance the estimation speed and robustness of camera extrinsic parameters.

[0087] In other embodiments, deep learning models such as convolutional neural networks (CNNs) can be used to learn the camera's motion and pose, thereby automatically determining the camera's position and pose. Furthermore, techniques such as generative adversarial networks (GANs) can be combined to improve the quality of the dataset and accelerate the training process.

[0088] In the above embodiments, after obtaining the initial extrinsic parameters such as the initial rotation matrix and the initial translation vector, the initial extrinsic parameters can be evaluated. Only when the evaluation result meets the preset calibration accuracy conditions will the initial rotation matrix and the initial translation vector be determined as the camera's extrinsic parameters. When the evaluation result does not meet the preset calibration accuracy conditions, a calibration optimization step is performed to obtain the camera's extrinsic parameters, which further improves the accuracy of the calculated camera extrinsic parameters.

[0089] In some embodiments, the camera in this application can be a vehicle-mounted camera, the calibration target is set in the factory calibration room, and the calibration image is taken when the vehicle is moved to the factory calibration room and the origin of the checkerboard pattern is located at the center point of the vehicle.

[0090] In this embodiment, the camera extrinsic parameter calibration method is applied to the factory calibration of camera extrinsic parameters. Unlike other types of extrinsic parameter calibration, the factory calibration of camera extrinsic parameters uses a mechanical device to move the vehicle to a preset position, and the calibration target is a fixed calibration pattern. Therefore, it can obtain relatively accurate calibration point coordinates. Its main features are stability, speed, and high accuracy. It is usually used for factory calibration during camera assembly, such as the extrinsic parameter calibration of the camera on the vehicle after assembly. The factory calibration method is usually based on setting a fixed calibration pattern in a limited space. The calibration pattern covers a range of 1 to 2 meters outward from the vehicle outline, and as the coverage area increases, the construction space requirements and costs also increase.

[0091] The additive extrinsic parameter calibration method provided in this application embodiment can be based on specular reflection and uses a limited space to lay out calibration patterns, but it can calibrate a wider range of accurate extrinsic parameters. In this embodiment, only a mirror needs to be added to the original factory calibration in a low-cost manner to collect calibration data over a larger range than the original calibration. By adding corresponding calibration points to the calibration program, high-accuracy camera extrinsic parameters covering a wider range can be calculated.

[0092] In this embodiment, the construction cost is low by adding a mirror to modify the calibration room; the calibration logic is simple, the calibration range can be expanded, and the accuracy of long-distance projection of external parameters can be significantly improved.

[0093] The following combination Figures 4 to 10 The application of the camera extrinsic parameter calibration method of this application to camera extrinsic parameter factory calibration scenarios is described in detail.

[0094] Currently, a factory calibration room typically consists of the following components: displacement machinery and calibration patterns. The displacement machinery moves the vehicle to the center of the calibration pattern, ensuring that the origin of the calibration pattern's corner coordinates is located at the vehicle's center point. The calibration pattern is a pre-designed pattern with a width of W. Chessboard The length is H Chessboard The coordinates of the corner points of the calibration pattern are fixed in the calibration space. After the camera takes a picture of the calibration pattern, the coordinates of the corner points of the calibration pattern can be obtained by identifying the corner points. Combined with the preset corner point coordinates in the vehicle coordinate system, the camera extrinsic parameters can be calculated.

[0095] Based on the aforementioned calibration room, mirrors need to be fixed on the four walls of the calibration room or on the outer edges of the four sides of the calibration pattern. The fixed mirrors should be parallel to the calibration pattern and at a distance of L. Therefore, the length of the two mirrors (W) can be deduced. Chessboard +2*L), the lengths of the left and right mirror surfaces are (H) Chessboard +2*L), the height of the four mirrors is greater than the height of the calibrated vehicle (assuming the height of the calibrated vehicle is H). car The installed mirrors are strictly perpendicular (90 degrees) to the ground. A schematic diagram of the overall workshop is shown below. Figure 4 As shown.

[0096] After constructing the workshop mirror surface, the calibration pattern in a larger space can be simulated under the imaging of the vehicle-mounted camera due to the principle of mirror reflection. Taking the right side as an example, as shown... Figure 5 As shown in the diagram, the Ego Car moves to the center position of the workshop via a mechanical device. The coordinate system is a preset world coordinate system established with the center of the calibration pattern. The front of the vehicle is the X-axis, the left side of the vehicle is the Y-axis, and the Z-axis is upward. This coordinate system is abbreviated as O. cali The calibration pattern can be expanded using mirrors; for details, please refer to [reference needed]. Figure 3 Where p is a calibration point (i.e., the original calibration point) in a known preset calibration pattern, assumed to be at O cali Coordinates are (x p y p Given that the size of the chessboard square containing p is n*n, based on the mirror mounting dimensions, the coordinates of the mirror calibration point p′ of p can be deduced to be (x...). p y p +4*n+2*L), the coordinates of other calibration checkerboard corner points obtained through mirror expansion can be obtained in the calibration coordinate system using the same principle. Since the calibration pattern is expanded, the calibration image captured by the vehicle-mounted camera can include both the original calibration pattern and the mirror-expanded calibration pattern. Taking the right side as an example (after distortion removal), the calibration image captured by the vehicle-mounted camera is as follows: Figure 6 As shown.

[0097] The above steps establish the basic hardware system for capturing extended-size calibration data within a previously limited calibration space. After constructing a calibration workshop with mounted mirrors, a software workflow system can calibrate high-precision camera extrinsic parameters covering a wider range, thus adapting to more application scenarios. The following section combines... Figure 7 Explanation:

[0098] First, since the original calibration pattern specifications are known, the coordinates of all original calibration points in the calibration coordinate system (i.e., the world coordinate system) are also known. Here, calibration points refer to the corner points of the checkerboard, that is, the intersection points of black and white squares within the checkerboard. Figure 8 In the example, the circled points are the corner points of the checkerboard. Here, it is assumed that there are M original calibration points on the right side of the calibration checkerboard, where M = 4*2 + 6*4 in this example.

[0099] Since the distance between the mirror installation position and the calibration pattern is known to be L, and the mirror is strictly perpendicular to the ground, an extended checkerboard pattern can be constructed using the mirror. On each side of the vehicle, the calibration pattern can be extended outward through the mirror, and the offset of the mirrored calibration pattern is 2*L.

[0100] In practical implementation, the coordinates of the checkerboard corner points (i.e., mirror calibration points) of the mirror can be calculated according to the installation specifications, thereby obtaining the coordinates of the M calibration points extended by the mirror. Combined with the coordinates of the existing M original calibration points, the coordinates of 2*M calibration points can be obtained, thus forming the actual coordinates of the calibration points required for the camera's extrinsic parameters, that is, the coordinates in the calibration coordinate system. On the other hand, the vehicle is driven into the calibration workshop, and the vehicle is moved to the preset position by mechanical equipment. The camera can be started to collect the images required for extrinsic parameter calibration. Here, the camera on the right is taken as an example.

[0101] Because the original image data contains distortion, distortion correction is necessary before identifying the checkerboard corner points. The specific distortion correction process will not be detailed here. After distortion correction, corner point recognition (i.e., feature point detection) can be performed. Specifically, the purpose of corner point recognition is to obtain the coordinates of the checkerboard pattern corner points in the image coordinate system. This recognition operation can be accomplished by calling corresponding OpenCV functions, such as... Figure 9 As shown, the circled dot marks represent the coordinates of the identified corner points. External parameter calculation requires the corner coordinates of the calibration pattern on the image and in the actual calibration coordinate system, forming one-to-one point pairs. Since the order of the identified points is not fixed, they need to be rearranged according to a preset method, as shown in the example below. Figure 10 The calibration points in the corresponding calibration coordinate system are rearranged in the same preset order. After completing the above, the ordered point pairs required for extrinsic parameter calculation are obtained, and the camera extrinsic parameters can be calculated using the extrinsic parameter calculation function.

[0102] The camera extrinsic parameter calibration method provided in this application embodiment is a calibration method that can calibrate a larger range of accurate extrinsic parameters in a limited space. By adding a mirror to the original factory calibration, a calibration pattern with a larger range of mirror extension is collected, and thus calibration data with a larger range than the original calibration can be obtained. Based on this, the calibration program is added with corresponding calibration points due to the mirror extension, and high-accuracy camera extrinsic parameters covering a larger range can be calculated.

[0103] This embodiment has the following advantages:

[0104] 1) Low construction cost: Only four mirrors (front, back, left, and right) need to be added to the existing factory calibration construction plan; 2) Simple calibration logic: No major adjustments are required to the original calibration procedure, only the calibration points expanded by the mirrors need to be added; 3) Improved accuracy of extrinsic parameters: Since this scheme can expand the original calibration pattern by using mirrors, the range of extrinsic parameter points can be expanded to twice the original size, improving the accuracy of long-distance projection and enabling the calibrated extrinsic parameters to be applied to a wider range of point projections.

[0105] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0106] Based on the same inventive concept, this application also provides a camera extrinsic parameter calibration device for implementing the camera extrinsic parameter calibration method described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations in one or more camera extrinsic parameter calibration device embodiments provided below can be found in the limitations of the camera extrinsic parameter calibration method described above, and will not be repeated here.

[0107] In some exemplary embodiments, such as Figure 11 As shown, a camera extrinsic parameter calibration device 1100 is provided, comprising:

[0108] The calibration image acquisition module 1102 is used to acquire a calibration image captured by a camera targeting a calibration target; wherein, a mirror device is provided at the outer edge of the calibration target, the calibration image includes the calibration target and at least part of the calibration target as a mirrored calibration target in the mirror device, the calibration target includes multiple original calibration points, and the mirrored calibration target includes multiple mirrored calibration points;

[0109] The first coordinate acquisition module 1104 is used to acquire the first coordinates of each original calibration point in the world coordinate system and to acquire the first coordinates of each mirror calibration point in the world coordinate system.

[0110] The second coordinate acquisition module 1106 is used to perform feature point detection based on the calibration image and determine the second coordinates of the multiple detected feature points in the image coordinate system.

[0111] The correspondence determination module 1108 is used to determine the feature points corresponding to each original calibration point and the feature points corresponding to each mirror calibration point from multiple feature points.

[0112] The extrinsic parameter determination module 1110 is used to determine the extrinsic parameters of the camera based on the first coordinates of each original calibration point, the second coordinates of the corresponding feature points of each original calibration point, the first coordinates of each mirror calibration point, and the second coordinates of the corresponding feature points of each mirror calibration point.

[0113] The aforementioned camera extrinsic calibration device includes a mirror device at the outer edge of the calibration target. The calibration image includes the calibration target and at least a portion of the calibration target reflected in the mirror device. The calibration target includes multiple original calibration points, and the reflected calibration target includes multiple reflected calibration points. During calibration, the first coordinates of each original calibration point in the world coordinate system and the first coordinates of each reflected calibration point in the world coordinate system are obtained. Feature point detection is performed based on the calibration image, and the second coordinates of the detected feature points in the image coordinate system are determined. In the calibration process, the feature points corresponding to each original calibration point and each mirror calibration point are determined. Based on the first coordinates of each original calibration point, the second coordinates of the feature points corresponding to each original calibration point, the first coordinates of each mirror calibration point, and the second coordinates of the feature points corresponding to each mirror calibration point, the extrinsic parameters of the camera are determined. Since the original calibration target can be extended through the mirror device, the range of extrinsic parameter calibration points can be expanded, improving the accuracy of long-distance projection and enabling the calibrated extrinsic parameters to be applied to point projection over a larger range.

[0114] In some embodiments, the second coordinate acquisition module 1106 is further configured to: perform distortion removal processing on the calibration image to obtain a target image corresponding to the calibration image; perform feature point detection on the target image to obtain multiple feature points; and determine the second coordinates of each feature point in the image coordinate system based on the position of each feature point in the calibration image.

[0115] In some embodiments, the correspondence determination module 1108 is further configured to: sort multiple original calibration points and multiple mirror calibration points according to a preset method; sort multiple feature points according to a preset method; for each original calibration point, determine the feature point with the same sorting position as the original calibration point as the feature point corresponding to the original calibration point; for each mirror calibration point, determine the feature point with the same sorting position as the mirror calibration point as the feature point corresponding to the mirror calibration point.

[0116] In some embodiments, the calibration target is a preset pattern with known geometric features, and the mirror device is vertically disposed at the outer edge of the preset pattern.

[0117] In some embodiments, the preset pattern is a checkerboard pattern. The first coordinate acquisition module 1104 is further configured to: for each original calibration point, determine the first coordinate of the original calibration point in the world coordinate system based on the position of the original calibration point in the checkerboard pattern; for each mirror calibration point, acquire the first coordinate of the original calibration point corresponding to the mirror calibration point in the world coordinate system, and determine the first coordinate of the mirror calibration point in the world coordinate system based on the first coordinate of the original calibration point corresponding to the mirror calibration point in the world coordinate system, the size of the checkerboard squares of the checkerboard pattern, and the distance between the mirror device and the outer edge of the calibration pattern.

[0118] In some embodiments, the camera is an onboard camera of the vehicle, the calibration target is set in the factory calibration room, and the calibration image is taken when the vehicle is moved to the factory calibration room and the origin of the checkerboard pattern is located at the center point of the vehicle.

[0119] In some embodiments, the extrinsic parameter determination module 1110 is further configured to: perform parameter estimation based on the first coordinates of each original calibration point, the second coordinates of the feature points corresponding to each original calibration point, the first coordinates of each mirror calibration point, and the second coordinates of the feature points corresponding to each mirror calibration point to obtain an initial rotation matrix and an initial translation vector; evaluate the initial rotation matrix and the initial translation vector to obtain an evaluation result; when the evaluation result meets the preset calibration accuracy conditions, determine the initial rotation matrix and the initial translation vector as the extrinsic parameters of the camera; when the evaluation result does not meet the preset calibration accuracy conditions, perform a calibration optimization step to obtain the extrinsic parameters of the camera.

[0120] Each module in the aforementioned camera extrinsic calibration device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or stored in the memory of a computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0121] In some exemplary embodiments, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 12As shown, the computer device includes a processor, memory, input / output interfaces (I / O), and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores calibration images, camera extrinsic parameters, and other data. The I / O interfaces are used for information exchange between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements the camera extrinsic parameter calibration method provided in this embodiment.

[0122] In some exemplary embodiments, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 13 As shown, the computer device includes a processor, memory, input / output interface, communication interface, display unit, and input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interface. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The input / output interface is used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, Near Field Communication (NFC), or other technologies. When the computer program is executed by the processor, it implements the camera extrinsic parameter calibration method provided in this embodiment. The display unit of the computer device forms a visually visible image and can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0123] Those skilled in the art will understand that Figure 12 , Figure 13The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0124] In some exemplary embodiments, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the camera extrinsic parameter calibration method described above.

[0125] In some embodiments, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps of the camera extrinsic parameter calibration method described above.

[0126] In some embodiments, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps of the camera extrinsic calibration method described above.

[0127] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0128] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0129] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0130] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for calibrating camera extrinsic parameters, characterized in that, The method includes: A calibration image is acquired by a camera targeting a calibration target; wherein a mirror device is provided at the outer edge of the calibration target, the calibration image includes the calibration target and at least a portion of the calibration target as a mirrored calibration target in the mirror device, the calibration target includes multiple original calibration points, and the mirrored calibration target includes multiple mirrored calibration points; Obtain the first coordinates of each of the original calibration points in the world coordinate system, and obtain the first coordinates of each of the mirror calibration points in the world coordinate system; Feature point detection is performed based on the calibrated image, and the second coordinates of the detected feature points in the image coordinate system are determined. From the plurality of feature points, determine the feature points corresponding to each of the original calibration points and the feature points corresponding to each of the mirror calibration points respectively; The extrinsic parameters of the camera are determined based on the first coordinates of each original calibration point, the second coordinates of the feature points corresponding to each original calibration point, the first coordinates of each mirror calibration point, and the second coordinates of the feature points corresponding to each mirror calibration point.

2. The method according to claim 1, characterized in that, The step of detecting feature points based on the calibrated image and determining the second coordinates of each detected feature point in the image coordinate system includes: The calibration image is subjected to distortion correction processing to obtain the target image corresponding to the calibration image; Feature point detection is performed on the target image to obtain multiple feature points; Based on the position of each feature point in the calibration image, determine the second coordinates of each feature point in the image coordinate system.

3. The method according to claim 2, characterized in that, The step of determining the feature points corresponding to each of the original calibration points and the feature points corresponding to each of the mirror calibration points from the plurality of feature points includes: The plurality of original calibration points and the plurality of mirror calibration points are sorted according to a preset method; The plurality of feature points are sorted according to the preset method; For each original calibration point, the feature points that have the same sorting position as the original calibration point are determined as the feature points corresponding to the original calibration point; For each mirror calibration point, the feature points that have the same sorting position as the mirror calibration point are determined as the feature points corresponding to the mirror calibration point.

4. The method according to claim 1, characterized in that, The calibration target is a preset pattern with known geometric features, and the mirror device is vertically disposed at the outer edge of the preset pattern.

5. The method according to claim 4, characterized in that, The preset pattern is a checkerboard pattern. Obtaining the first coordinates of each of the original calibration points in the world coordinate system, and obtaining the first coordinates of each of the mirror calibration points in the world coordinate system, includes: For each original calibration point, determine the first coordinate of the original calibration point in the world coordinate system based on the position of the original calibration point in the checkerboard pattern; For each mirror calibration point, obtain the first coordinates of the original calibration point corresponding to the mirror calibration point in the world coordinate system. Based on the first coordinates of the original calibration point corresponding to the mirror calibration point in the world coordinate system, the size of the checkerboard squares of the checkerboard pattern, and the distance between the mirror device and the outer edge of the checkerboard pattern, determine the first coordinates of the mirror calibration point in the world coordinate system.

6. The method according to claim 5, characterized in that, The camera is a vehicle-mounted camera, the calibration target is set in the factory calibration room, and the calibration image is obtained by moving the vehicle to the factory calibration room and making the origin of the checkerboard pattern located at the center point of the vehicle.

7. The method according to claim 1, characterized in that, The step of determining the camera's extrinsic parameters based on the first coordinates of each of the original calibration points, the second coordinates of the corresponding feature points of each of the original calibration points, the first coordinates of each of the mirror calibration points, and the second coordinates of the corresponding feature points of each of the mirror calibration points includes: Based on the first coordinates of each of the original calibration points, the second coordinates of the feature points corresponding to each of the original calibration points, the first coordinates of each of the mirror calibration points, and the second coordinates of the feature points corresponding to each of the mirror calibration points, parameter estimation is performed to obtain the initial rotation matrix and the initial translation vector. The initial rotation matrix and the initial translation vector are evaluated to obtain the evaluation results; When the evaluation result meets the preset calibration accuracy condition, the initial rotation matrix and the initial translation vector are determined as the extrinsic parameters of the camera; The method further includes: When the evaluation result does not meet the preset calibration accuracy conditions, a calibration optimization step is performed to obtain the external parameters of the camera.

8. A camera extrinsic parameter calibration device, characterized in that, The device includes: A calibration image acquisition module is used to acquire a calibration image captured by a camera targeting a calibration target; wherein, a mirror device is provided at the outer edge of the calibration target, the calibration image includes the calibration target and at least a portion of the calibration target as a mirrored calibration target in the mirror device, the calibration target includes multiple original calibration points, and the mirrored calibration target includes multiple mirrored calibration points; The first coordinate acquisition module is used to acquire the first coordinates of each of the original calibration points in the world coordinate system, and to acquire the first coordinates of each of the mirror calibration points in the world coordinate system. The second coordinate acquisition module is used to perform feature point detection based on the calibration image and determine the second coordinates of the detected feature points in the image coordinate system. The correspondence determination module is used to determine the feature points corresponding to each of the original calibration points and the feature points corresponding to each of the mirror calibration points from the plurality of feature points. The extrinsic parameter determination module is used to determine the extrinsic parameters of the camera based on the first coordinates of each of the original calibration points, the second coordinates of the feature points corresponding to each of the original calibration points, the first coordinates of each of the mirror calibration points, and the second coordinates of the feature points corresponding to each of the mirror calibration points.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.

Images