Parameter calibration method and device, vehicle and storage medium

Abstract

Embodiments of the present application disclose a parameter calibration method and device, a vehicle and a storage medium. The method comprises: acquiring a target image through a camera, the target image being an image of a calibration board arranged at a preset position, the calibration board comprising a circular target arranged at a preset position; screening the circular target included in the target image based on a preset condition to obtain a preset number of circular targets; determining pixel coordinates of the centers of the preset number of circular targets; and calibrating external parameters of the camera based on the pixel coordinates of the centers and vehicle body coordinates. Through the above method, since the center coordinates of the circular target are used for calibration in the calibration, even if the circular target becomes an ellipse in a very serious distortion scene, the center position is very accurate, and therefore, the calibration precision can be improved by calibrating the external parameters of the camera through the circular target.

Description

Technical Field

[0001] The present application relates to the field of autonomous driving technology, and more specifically, to a parameter calibration method, device, vehicle, and storage medium. Background Art

[0002] The surround-view cameras of autonomous vehicles need to be calibrated when the vehicle leaves the factory or is returned for repair. However, the calibration accuracy of the relevant parameter calibration methods needs to be improved. Summary of the Invention

[0003] In view of the above problems, the present application proposes a parameter calibration method, device, vehicle and storage medium to improve the above problems.

[0004] In a first aspect, the present application provides a parameter calibration method, which is applied to a vehicle, wherein the vehicle is equipped with a camera, and the method comprises: acquiring a target image through the camera, wherein the target image is an image captured of a calibration plate set at a preset position, wherein the calibration plate includes a circular target set at a preset position; based on preset conditions, screening the circular targets included in the target image to obtain a preset number of circular targets; determining the pixel coordinates of the centers of the preset number of circular targets; and calibrating the external parameters of the camera based on the pixel coordinates of the centers and the vehicle body coordinates.

[0005] In the second aspect, the present application provides a parameter calibration device that runs on a vehicle, and the vehicle is equipped with a camera. The device includes: an image acquisition unit, which is used to acquire a target image through the camera, and the target image is an image of a calibration plate set at a preset position, and the calibration plate includes a circular target set at a preset position; a screening unit, which is used to screen the circular targets included in the target image based on preset conditions to obtain a preset number of circular targets; a coordinate determination unit, which is used to determine the pixel coordinates of the centers of the preset number of circular targets; and a calibration unit, which is used to calibrate the external parameters of the camera based on the pixel coordinates of the centers and the vehicle body coordinates.

[0006] In a third aspect, the present application provides a vehicle comprising one or more processors and a memory; one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs are configured to execute the above-mentioned method.

[0007] In a fourth aspect, the present application provides a computer-readable storage medium, in which program code is stored. The program code can be called by a processor to execute the above method.

[0008] The present application provides a parameter calibration method, device, vehicle, and storage medium. First, a target image of a circular target set at a preset position is obtained. Then, based on preset conditions, the circular targets included in the target image are screened to obtain a preset number of circular targets. The pixel coordinates of the centers of the preset number of circular targets are determined. Finally, the external parameters of the camera are calibrated based on the pixel coordinates of the centers and the vehicle body coordinates. Through the above method, since the circular target is calibrated using the center coordinates during calibration, even if it becomes an ellipse in a scene with severe distortion, the center position is very accurate. Therefore, by calibrating the external parameters of the camera using the circular target, the calibration accuracy can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0010] Figure 1 A schematic diagram showing an application scenario of a parameter calibration method proposed in this application;

[0011] Figure 2 Shows a structural block diagram of a vehicle proposed in this application;

[0012] Figure 3 A flow chart of a parameter calibration method proposed in this application is shown;

[0013] Figure 4 A schematic diagram showing the planar layout of a calibration plate proposed in this application is shown;

[0014] Figure 5 A flow chart showing another parameter calibration method proposed in this application is shown;

[0015] Figure 6 A flow chart of another parameter calibration method proposed in this application is shown;

[0016] Figure 7 A schematic diagram showing a target image in another parameter calibration method proposed in this application is shown;

[0017] Figure 8 A flow chart of another parameter calibration method proposed in this application is shown;

[0018] Figure 9 A schematic diagram showing a target image in another parameter calibration method proposed in this application is shown;

[0019] Figure 10It shows a structural block diagram of a parameter calibration device proposed in this application;

[0020] Figure 11 A structural block diagram of a vehicle for executing a parameter calibration method according to an embodiment of the present application is shown;

[0021] Figure 12 It is a storage medium used in this application to store or carry program codes for implementing the parameter calibration method according to the embodiment of this application. DETAILED DESCRIPTION

[0022] The following will be combined with the accompanying drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making any creative efforts are within the scope of protection of this application.

[0023] As society develops and the number of vehicles increases, so too does the number of traffic accidents. Traditional backup cameras, installed only at the rear of the vehicle, cover only a limited area around the rear. Blind spots around the vehicle and in the front undoubtedly increase driving safety risks, making collisions and scrapes more likely in congested urban areas and parking lots. To mitigate the impact of blind spots on driving safety and expand the driver's field of view, in-vehicle surround view systems have emerged.

[0024] Surround view systems use cameras installed on the front, rear, left, and right sides of the vehicle to simultaneously capture images of the vehicle's surroundings and process them to create a seamless, panoramic bird's-eye view of the vehicle's surroundings. This effectively assists the driver in assessing the vehicle's surroundings and serves as a fundamental component of intelligent driving assistance systems, enabling features such as blind spot monitoring and automated parking. Their application prospects are vast.

[0025] To synthesize a 360-degree surround view image of the vehicle, the cameras located in front, behind, left, and right of the vehicle must first be calibrated. This involves calibrating the camera parameters relative to the vehicle's coordinate system. Currently, in-vehicle surround view systems typically use offline calibration methods to calibrate the parameters used by the system's configured cameras. These parameters include internal and external parameters. Internal parameters refer to device parameters such as focal length, optical center, and lens distortion, while external parameters refer to the rotation and translation matrices from the camera coordinate system to the world coordinate system. Calibration of these external parameters is a key technical issue, as their accuracy directly impacts camera performance.

[0026] The inventors found in their research on relevant parameter calibration methods that the calibration accuracy of the relevant parameter calibration methods needs to be improved.

[0027] Therefore, the inventors have proposed the parameter calibration method, device, vehicle, and storage medium of the present application. First, a target image of a circular target set at a preset position is acquired. Then, the pixel coordinates of the center of the circular target are determined. Finally, based on the pixel coordinates of the center and the vehicle coordinates, the camera's external parameters are calibrated. Through the above method, since the circular target is calibrated using the center coordinates, even if it becomes an ellipse in a severely distorted scene, the center position is very accurate. Therefore, calibrating the camera's external parameters using the circular target can improve calibration accuracy.

[0028] The following describes the application environment of the parameter calibration method provided by the present invention:

[0029] See also Figure 1 The parameter calibration method provided by the embodiment of the present invention can be applied to a parameter calibration system 100, which can include a vehicle 110 and a server 120, wherein the server 120 can establish a communication connection with the vehicle 110. Optionally, the number of vehicles 110 can also be one or more.

[0030] In embodiments of the present application, server 120 may run one or more services or software applications that enable execution of the parameter calibration method. In some embodiments, server 120 may be a server in a distributed system. Server 120 may also be a cloud server, or an intelligent cloud computing server or intelligent cloud host with artificial intelligence technology.

[0031] In the embodiment of the present application, the parameter calibration method provided in the embodiment of the present application can be performed collaboratively by the vehicle 110 and the server 120. In this manner of collaborative execution by the vehicle 110 and the server 120, some steps in the parameter calibration method provided in the embodiment of the present application can be performed by the vehicle 110, while other steps can be performed by the server 120.

[0032] Exemplarily, the vehicle 110 may execute the parameter calibration method including: acquiring a target image through a camera and sending the target image to the server 120, and then the server 120 may screen the circular targets included in the target image based on preset conditions to obtain a preset number of circular targets; determining the pixel coordinates of the centers of the preset number of circular targets; calibrating the external parameters of the camera based on the pixel coordinates of the centers and the vehicle body coordinates, and then the server 120 may send the calculated external parameters of the camera to the vehicle 110.

[0033] It should be noted that in this method of collaborative execution by vehicle 110 and server 120, the steps respectively executed by vehicle 110 and server 120 are not limited to the methods introduced in the above examples. In actual applications, the steps respectively executed by vehicle 110 and server 120 can be dynamically adjusted according to actual conditions.

[0034] Of course, the parameter calibration method in the embodiment of the present application can also be executed by the vehicle 110 alone.

[0035] Among them, see Figure 2 The vehicle 110 may include an on-board control device 111 (Body control module, BCM), a central display unit 112 (Central Display Unit, CDU), an industrial bus (Industry controller area network, ICAN), a central gateway 113 (Communication Gateway, CGW), and a positioning device 114.

[0036] Among them, the on-board control device 111 can be respectively communicated with the server 120, the central display device 112 and the positioning device 114, and the on-board control device 111 can be communicated with the central gateway 114 through an industrial bus. Optionally, the on-board control device 111 may include a central interface unit (CIU), a processor electrically connected to the central interface unit, and a memory electrically connected to the processor, wherein the memory can be used to store instructions, programs, codes, code sets or instruction sets, etc. Among them, the central interface device can be used to access the bus. Optionally, the processor may include an XPU cloud computing acceleration chip.

[0037] The positioning device 114 is used to detect the position information of the vehicle 110 in real time. Optionally, the positioning device 114 can be a Global Navigation Satellite System (GNSS), which generally refers to all satellite navigation systems, including global, regional and enhanced satellite navigation systems, such as the United States' Global Positioning System (GPS), Russia's Global Navigation Satellite System (Glonass), Europe's Galileo satellite navigation system (Galileo), China's Beidou satellite navigation system, and related enhancement systems, such as the United States' WAAS (Wide Area Augmentation System), Europe's EGNOS (European Geostationary Navigation Overlay System) and Japan's MSAS (Multifunctional Transport Satellite Augmentation System), etc., and also covers other satellite navigation systems under construction and to be constructed in the future.

[0038] The vehicle-mounted control device 111 can receive data sent by the server 130 and control the central display device 112 to display corresponding information according to the received data.

[0039] In the above-mentioned manner, after the vehicle 110 obtains the target image through the camera, the target image can be sent to the vehicle-mounted control device 111 to perform screening of the circular targets included in the target image based on preset conditions to obtain a preset number of circular targets; determine the pixel coordinates of the centers of the preset number of circular targets; and calibrate the external parameters of the camera based on the pixel coordinates of the centers and the vehicle body coordinates.

[0040] The embodiments of the present application will be described in detail below with reference to the accompanying drawings.

[0041] See also Figure 3 The present application provides a parameter calibration method, which is applied to a vehicle equipped with a camera, and the method comprises:

[0042] Step 110: Acquire a target image through the camera, wherein the target image is an image of a calibration plate set at a preset position, wherein the calibration plate includes a circular target set at a preset position.

[0043] In the embodiment of the present application, cameras are installed at the front, rear, left, and right positions of the vehicle. Therefore, it is necessary to calibrate the parameters of the four cameras installed at the front, rear, left, and rear positions of the vehicle using a pre-designed calibration plate. When calibrating the parameters of the four cameras installed at the front, rear, left, and rear positions of the vehicle, both the external and internal parameters of the four cameras installed at the front, rear, left, and rear positions of the vehicle can be calibrated. In the embodiment of the present application, the external parameters of the four cameras installed at the front, rear, left, and rear positions of the vehicle are mainly calibrated. Among them, the internal parameters may include focal length, optical center, and lens distortion, while the external parameters refer to the rotation matrix and translation matrix from the pixel coordinate system to the vehicle body coordinate system. The vehicle body coordinate system is a coordinate system used to describe the relative positional relationship between objects around the vehicle and the vehicle itself. Several commonly used definitions of vehicle body coordinate systems include ISO international standard definitions, SAE (Society of Automotive Engineers) definitions, and coordinate definitions based on inertial measurement units (IMUs).

[0044] The above three ways of defining the vehicle coordinate system can be shown in the following table:

[0045] ISO definition SAE Definition IMU Definition X positive direction forward forward right Y positive direction Left right forward Z positive direction superior Down superior Roll positive direction To the right To the right To the right Positive pitch direction down up down Positive yaw direction Counterclockwise Clockwise Counterclockwise center Vehicle center of gravity Vehicle center of gravity IMU Location Right-handed coordinate system yes yes yes

[0046] Three different vehicle coordinate systems are defined through the above three definition methods. Among them, the vehicle coordinate system defined by ISO is more common in vehicle dynamics analysis; the vehicle coordinate system defined by SAE is consistent with the body coordinate system commonly used in the aerospace field; the vehicle coordinate system based on IMU definition is more common in IMU related applications. Regardless of which coordinate system definition is used, as long as it is used correctly, it can complete the description of the vehicle body posture and determine the relative position relationship between the surrounding objects and the vehicle. In the embodiment of this application, the vehicle coordinate system can be selected according to application requirements and usage habits.

[0047] In the embodiment of the present application, the calibration plate is obtained by laying markers (circular targets) on the ground in a pre-designed manner. The markers in the calibration plate are placed at preset intervals, wherein the markers are of the same size and the preset intervals can be obtained through multiple experiments. The calibration plate set at the preset position can be understood as the calibration plate placed at the front and rear of the vehicle, such as Figure 4 As shown, in Figure 4 In the figure, a calibration plate with 12 circular targets is placed at the front of the vehicle, and a calibration plate with 12 circular targets is placed at the rear of the vehicle.

[0048] When the external parameters of the camera need to be calibrated, the camera can collect Figure 4The image of the placed calibration plate. During this process, as a way, the camera's shooting angle can be continuously adjusted to ensure that the target image can be obtained.

[0049] As one approach, since cameras are installed at the front, rear, left, and right sides of the vehicle, when acquiring target images through the cameras, the cameras installed at the front, rear, left, and right sides of the vehicle can simultaneously acquire the corresponding target images. Of course, it is also possible to acquire the corresponding target images at different times, which is not specifically limited here.

[0050] Step S120: Based on a preset condition, the circular targets included in the target image are screened to obtain a preset number of circular targets.

[0051] In the embodiment of the present application, the preset conditions may include a first preset condition, a second preset condition, and a third preset condition. The preset conditions may be pre-set conditions for screening circular targets included in the target image. The preset conditions may include the roundness, area, convexity, etc. of the circular targets, and are not specifically limited here.

[0052] As a method, the types of parameters included in the first preset condition, the second preset condition, and the third preset condition can be the same. For example, the first preset condition, the second preset condition, and the third preset condition all include parameters such as the roundness, area, and convexity of the circular target, but the values ​​of each parameter included in the first preset condition, the second preset condition, and the third preset condition are set differently.

[0053] Alternatively, the first, second, and third preset conditions may include different types of parameters. For example, the first preset condition may include parameters such as the roundness and area of ​​the circular target; the second preset condition may include parameters such as the roundness of the circular target; and the third preset condition may include parameters such as the roundness, area, and convexity of the circular target.

[0054] After the target image is acquired, the circular targets included in the target image can be identified, and then the identified circular targets can be screened according to preset conditions to obtain a preset number of circular targets.

[0055] Step 130: Determine the pixel coordinates of the centers of the predetermined number of circular targets.

[0056] In an embodiment of the present application, the pixel coordinates of the centers of a preset number of circular targets may be determined by a pre-set method. Here, the pre-set method may be a connected domain detection method for determining the pixel coordinates of the centers of the circular targets.

[0057] Step 140: Calibrate the external parameters of the camera based on the pixel coordinates of the circle center and the vehicle body coordinates.

[0058] In an embodiment of the present application, when placing the calibration plate, the vehicle coordinates of the center of the circular target included in the calibration plate can be determined based on the position where the calibration plate is placed. After determining the vehicle coordinates of the circular target, the vehicle coordinates of the center of the circular target can be stored. Then, after determining the pixel coordinates of the center of the circular target, the external parameters of the camera can be calibrated based on the circular pixel coordinates of the circular target and the vehicle coordinates.

[0059] This embodiment provides a parameter calibration method that first acquires a target image of a circular target placed at a preset position. Then, based on preset conditions, the circular targets included in the target image are screened to obtain a preset number of circular targets. The pixel coordinates of the centers of the preset number of circular targets are determined. Finally, the camera's external parameters are calibrated based on the pixel coordinates of the centers and the vehicle's body coordinates. Because the circular targets are calibrated using the center coordinates, even if they become elliptical in severely distorted scenes, the center position remains very accurate. Therefore, calibrating the camera's external parameters using circular targets can improve calibration accuracy.

[0060] See also Figure 5 The present application provides a parameter calibration method, which is applied to a vehicle equipped with a camera, and the method comprises:

[0061] Step 210: Acquire a target image through the camera, wherein the target image is an image of a calibration plate set at a preset position, wherein the calibration plate includes a circular target set at a preset position.

[0062] Step 220: Determine a region of interest from the target image.

[0063] In the embodiment of the present application, in image processing, an area to be processed is outlined from the processed image in the form of a box, circle, ellipse, irregular polygon, etc., which is called a region of interest (ROI).

[0064] Machine vision software like Halcon, OpenCV, and Matlab often use various operators and functions to identify regions of interest (ROIs) and perform further image processing. In image processing, a ROI is a region of interest selected from an image that serves as the focus of image analysis. Using this region of interest to identify the image area of ​​interest can reduce image processing time and increase accuracy.

[0065] As one approach, the ROI can be a pre-set ROI of a specified size, which is an area of ​​the image used to enclose a specified number of circular targets. When setting the size of the ROI, it can be set based on the size of the circular targets in the designed calibration plate, making the ROI as large as possible to ensure that the specified number of circular targets will fall within it. Alternatively, the ROI can be set to just enclose the specified number of circular targets. It is understood that in the embodiments of the present application, the ROI can enclose at least four circular targets.

[0066] Step 230: performing binarization processing on the images corresponding to the regions of interest based on a plurality of preset grayscale thresholds to obtain a plurality of binarized images.

[0067] In the embodiment of the present application, a binarization process may be performed on the image corresponding to the region of interest based on each preset grayscale threshold.

[0068] In an embodiment of the present application, after the region of interest is determined, the target image can be cropped based on the size of the region of interest to obtain an image corresponding to the region of interest, and then the image corresponding to the region of interest is binarized based on a preset grayscale threshold, and the grayscale values ​​of the pixels on the image corresponding to the region of interest are set to 0 or 255, that is, the image corresponding to the entire region of interest presents an obvious black and white effect.

[0069] As one approach, the grayscale values ​​of different pixels are set to 0 or 255 through a preset grayscale threshold. In an embodiment of the present application, the grayscale values ​​of pixels in the region of interest whose grayscale values ​​are less than the preset grayscale threshold can be set to 0, and the grayscale values ​​of other pixels in the region of interest can be set to 255 according to the preset grayscale threshold.

[0070] For example, the preset grayscale threshold can be set to 80, 100, 110, 120, etc., which is not specifically limited here. If the region of interest is binarized according to the preset grayscale threshold of 80, then the grayscale values ​​of pixels in the region of interest with grayscale values ​​less than 80 can be set to 0, and the grayscale values ​​of pixels with grayscale values ​​greater than or equal to 80 can be set to 255.

[0071] Step 240: Determine a connected domain corresponding to each of the plurality of binary images.

[0072] In the embodiment of the present application, the connected domain of the binary image refers to an area consisting of pixels with a gray value of 0. In some cases, the connected domain is also the area where the circular target is located.

[0073] Step 250: Based on the connected domain corresponding to each of the binary images, determine the circular target included in each of the binary images.

[0074] In the embodiment of the present application, the circular target included in each binary image can be obtained by identifying the circular target in each binary image.

[0075] Step 260: Determine a preset number of circular targets corresponding to the region of interest based on the preset conditions and the circular targets included in each binary image.

[0076] In an embodiment of the present application, after the circular targets included in each binary image are detected, the circular targets included in multiple binary images are aggregated, and the circular targets at different positions are counted to obtain a preset number of circular targets corresponding to the region of interest.

[0077] Here, counting the circular targets at different positions means that multiple circular targets at the same position among the circular targets included in the multiple binary images are regarded as one circular target, and then the circular targets at different positions can be counted using the same method.

[0078] As one approach, a region of interest is used to enclose a specified number of circular targets. Therefore, in the embodiment of the present application, the preset number of circular targets is the specified number of circular targets. Alternatively, as one approach, a region of interest is used to enclose four circular targets. Therefore, the preset number of circular targets is four circular targets.

[0079] Optionally, if the number of circular targets at different positions counted is greater than a preset number, the circular targets at different positions counted can be filtered based on preset conditions to ultimately obtain the preset number of circular targets. The preset conditions may include, but are not limited to, the roundness, area, and convexity of the circular targets.

[0080] Step 270: Determine the pixel coordinates of the centers of the predetermined number of circular targets.

[0081] In the embodiments of the present application, the circular target can be identified to determine its center, thereby determining the pixel coordinates of the center. As one method, the center of the circular target can be determined by calculating the zero-order moment and first-order moment of the contour. Of course, other methods that can calculate the center of a circular target can also be used to determine the center of the circular target, and this is not specifically limited here.

[0082] Step 280: Calibrate the external parameters of the camera based on the pixel coordinates of the circle center and the vehicle body coordinates.

[0083] This embodiment provides a parameter calibration method that first acquires a target image through a camera, determines a region of interest from the target image, then binarizes the images corresponding to the region of interest based on multiple preset grayscale thresholds to obtain multiple binary images, then determines the connected domain corresponding to each binary image, determines the circular targets included in each binary image based on the connected domain corresponding to each binary image, determines a preset number of circular targets corresponding to the region of interest based on the circular targets included in each binary image, and determines the pixel coordinates of the centers of the preset number of circular targets, and finally calibrates the external parameters of the camera based on the pixel coordinates of the centers and the vehicle coordinates. According to the above method, since the circular targets are calibrated using the center coordinates during calibration, even if they become elliptical in a severely distorted scene, the center position of the circle is very accurate. Therefore, calibrating the external parameters of the camera using the circular targets can improve the calibration accuracy.

[0084] See also Figure 6 The present application provides a parameter calibration method, which is applied to a vehicle equipped with a camera, and the method comprises:

[0085] Step 310: Acquire a target image through the camera, wherein the target image is an image of a calibration plate set at a preset position, wherein the calibration plate includes a circular target set at a preset position.

[0086] Step 320: If the camera is a front camera or a rear camera, determine a first region of interest and a second region of interest from the target image, wherein the first region of interest is a region of the image including a first designated circular target, and the second region of interest is a region of the image including a second designated circular target, the first designated circular target is a circular target set at the middle position of the calibration plate, and the second designated circular target is a circular target set at the edge position of the calibration plate.

[0087] In the embodiment of the present application, since the calibration plate is placed at a position such as Figure 4 As shown, the first designated circular targets are the four circular targets set in the middle of the calibration plate, and the second designated circular targets are the four circular targets set on the left and right of the calibration plate. When the camera is a front camera or a rear camera, the target image obtained by the camera can be as follows Figure 7 As shown, Figure 7 The mark "1" in the embodiment of the present application is the first region of interest, and the mark "2" is the second region of interest in the embodiment of the present application. Figure 7There are two second regions of interest. In the embodiment of the present application, the first region of interest and the second region of interest can be determined simultaneously or at different times. If they are not determined at the same time, the first region of interest can be determined first and then the second region of interest, or the second region of interest can be determined first and then the first region of interest, which is not specifically limited here.

[0088] Step 330: Binarize the images corresponding to the first region of interest based on multiple preset grayscale thresholds to obtain multiple first binary images; binarize the images corresponding to the second region of interest based on multiple preset grayscale thresholds to obtain multiple second binary images.

[0089] Step 340: Determine a connected domain corresponding to each first binary image in the plurality of first binary images; and determine a connected domain corresponding to each second binary image in the plurality of second binary images.

[0090] Step 350: Based on the connected domain corresponding to each of the first binary images, determine the circular target included in each first binary image; based on the connected domain corresponding to each of the second binary images, determine the circular target included in each second binary image.

[0091] The detailed explanation of the steps included in step 330, step 340 and step 350 can refer to the corresponding steps in the aforementioned embodiment and will not be repeated here.

[0092] Step 360: Determine a first number of circular targets corresponding to the first region of interest based on the circular targets included in each first binary image; and determine a second number of circular targets corresponding to the second region of interest based on the circular targets included in each second binary image.

[0093] As an approach, the step of determining the first number of circular targets corresponding to the first region of interest based on the circular targets included in each first binary image includes: screening the circular targets included in each first binary image according to a first preset condition to obtain first candidate circular targets corresponding to the first region of interest; and obtaining the first number of circular targets from the first candidate circular targets.

[0094] The first preset condition is that the pre-set properties of the circular target meet preset values, and the number of circular target detections meets a preset number. The properties of the circular target include its roundness, area, convexity, and moment of inertia ratio. Each preset grayscale threshold corresponds to one detection. Thus, the multiple preset grayscale thresholds, including several preset grayscale thresholds, correspond to multiple detections. The number of circular targets detected each time can be different or the same. After binarizing the first region of interest based on each preset grayscale threshold to obtain a binary image, the number of circular targets and the size and position of each circular target can be counted based on the binary image. Furthermore, after binarizing the first region of interest multiple times based on multiple preset grayscale thresholds to obtain multiple binary images, the number of circular target detections can be determined based on the positions of the circular targets in each of the multiple binary images. For example, if the multiple preset grayscale thresholds include a preset grayscale threshold of 80, a preset grayscale threshold of 90, and a preset grayscale threshold of 100. After binarizing the first region of interest based on a preset grayscale threshold 80 to obtain a corresponding binarized image, the size and position of target 1, target 1; target 2, target 2; target 3, target 3; and target 4, target 4 can be determined based on the binarized image. After binarizing the first region of interest based on a preset grayscale threshold 90 to obtain a corresponding binarized image, the size and position of target 5, target 5; target 6, target 6; target 7, target 7; and target 8, target 8 can be determined based on the binarized image. After binarizing the first region of interest based on a preset grayscale threshold 100 to obtain a corresponding binarized image, the size and position of target 9, target 9; target 10, target 10; target 11, target 11; and target 12, target 12 can be determined based on the binarized image. Among them, target 1, target 5 and target 9 correspond to each other, target 2, target 6 and target 10 correspond to each other; target 3, target 7 and target 11 correspond to each other; target 4, target 8 and target 12 correspond to each other.

[0095] If targets 1, 5, and 9 have the same size and position, then targets 1, 5, and 9 are determined to be the same target and recorded as circular target 1, with a detection count of 3. Similarly, targets 2, 6, and 10 can be determined to be the same target and recorded as circular target 2, with a detection count of 3. If, based on the size and position of the targets, among targets 3, 7, and 11, target 7 is determined to be the same target, then it is recorded as circular target 3, with a detection count of 2, and target 11 is recorded as circular target 4, with a detection count of 1. Targets 4, 8, and 12 are determined to be the same target and recorded as circular target 5, with a detection count of 3. Through the above method, the detection counts of circular targets 1, 2, 3, 4, and 5 can be determined.

[0096] In an embodiment of the present application, in order to screen out the four circular targets with the largest areas, when setting the first preset condition, the preset value corresponding to the circular target's own attribute can be set to be relatively large; and the preset number of times is set to N / 2 (N is the number of detections).

[0097] If the circular target's attributes meet the preset conditions and the number of circular target detections is greater than or equal to the preset number, then the circular target is determined to be the first candidate circular target. In the above example, the number of detections is 3, so the preset number is set to 1.5. Therefore, circular targets 1, 2, 3, and 5 are determined to be the first candidate circular targets.

[0098] After the first candidate circular targets are determined, the first candidate circular targets can be sorted according to their area to obtain the sorted first candidate circular targets. The two circular targets with the largest areas are obtained from the sorted first candidate circular targets as the two circular targets of the near row, and the circular targets with the third and fourth largest areas are obtained as the two circular targets of the far row. Optionally, since the first region of interest is as large as possible, the first candidate circular targets may include more than the first number of circular targets, and then the circular targets collinear with the near row and the circular targets collinear with the far row can be filtered to obtain the first number of circular targets. Among them, the circular targets collinear with the near row and the far row refer to the physical collinearity, that is, Figure 7 A circular target in the second region of interest in FIG.

[0099] As another embodiment, the step of determining the second number of circular targets corresponding to the second region of interest based on the circular targets included in each second binary image includes: screening the circular targets included in each second binary image according to a second preset condition to obtain second candidate circular targets corresponding to the second region of interest; and obtaining the second number of circular targets from the second candidate circular targets.

[0100] The second preset condition is that the pre-set properties of the circular targets satisfy preset values, and the pixel coordinates of the centers of the circular targets conform to a priori positional relationships. The priori positional relationships can be obtained by: determining a homography matrix based on the pixel coordinates of the centers of the first number of circular targets and the vehicle coordinates; and determining reference pixel coordinates of the centers of the circular targets corresponding to the second region of interest based on the homography matrix and the vehicle coordinates of the centers of the circular targets corresponding to the second region of interest, where the reference pixel coordinates are the priori positional relationships.

[0101] Furthermore, by detecting the circular target corresponding to the second region of interest, the actual pixel coordinates of the center of the circular target corresponding to the second region of interest are determined, the reference pixel coordinates and the actual pixel coordinates of the center of the corresponding circular target are compared, and the circular targets whose difference between the reference pixel coordinates and the actual pixel coordinates exceeds a threshold are filtered out to obtain a second candidate circular target; and from the second candidate circular targets, the second number of circular targets is obtained.

[0102] At this time, the second candidate circular targets may be sorted according to the number of detections of each second candidate circular target, thereby obtaining a second number of circular targets.

[0103] Optionally, before obtaining the second number of circular targets from the second candidate circular targets, the step also includes: if the number of the second candidate circular targets is less than the second number, projecting the vehicle coordinates of the centers of the second number of circular targets into a pixel coordinate system based on the homography matrix, and determining a new second region of interest from the target image; and obtaining the second number of circular targets from the new second region of interest.

[0104] In an embodiment of the present application, for the detection of circular targets, since the installation angle of the camera of each vehicle may change, if a fixed second region of interest is manually divided, some circular targets may not be circled, resulting in calibration failure. Therefore, the second region of interest can be adaptively calculated using the pixel coordinates of the center of the circular target, thereby improving the success rate of calibration.

[0105] As one approach, if the number of second candidate circular targets is less than the second number, a new second region of interest can be adaptively calculated based on the pixel coordinates of the centers of the first number of circular targets. The same method as described above can be used for the new second region of interest to obtain a second number of circular targets from the second region of interest.

[0106] Step 370: Determine the pixel coordinates of the centers of the first number of circular targets, and determine the pixel coordinates of the centers of the second number of circular targets.

[0107] Step 380: Calibrate the external parameters of the front camera or the rear camera based on the pixel coordinates of the centers of the first number of circular targets and the vehicle body coordinates, and the pixel coordinates of the centers of the second number of circular targets and the vehicle body coordinates.

[0108] In an embodiment of the present application, after determining the pixel coordinates and vehicle body coordinates of the centers of all circular targets in the calibration plate, the external parameters of the front camera or the rear camera can be calibrated based on the pixel coordinates and vehicle body coordinates of the circles of all circular targets in the calibration plate.

[0109] When calibrating the external parameters of the front or rear camera, the mapping relationship between the pixel coordinates and the vehicle coordinates is calculated based on the pixel coordinates of the center of the circular target and the vehicle coordinates. In other words, the mapping relationship is determined to determine how the vehicle coordinates of the center of the circular target are converted to pixel coordinates. The mapping relationship includes the rotation matrix and the translation matrix.

[0110] This embodiment provides a parameter calibration method. Since the circular target is calibrated using the center coordinates, even if it becomes an ellipse in a scene with severe distortion, the center position is very accurate. Therefore, by calibrating the external parameters of the camera using the circular target, the calibration accuracy can be improved.

[0111] See also Figure 8 The present application provides a parameter calibration method, which is applied to a vehicle equipped with a camera, and the method comprises:

[0112] Step 410: Acquire a target image through the camera, wherein the target image is an image of a calibration plate set at a preset position, wherein the calibration plate includes a circular target set at a preset position.

[0113] Step 420: If the camera is a left camera or a right camera, determine a third region of interest from the target image, where the third region of interest is a region of the image including a third designated circular target, and the third designated circular target is a circular target set at an edge position of a different calibration plate.

[0114] In the embodiment of the present application, since the calibration plate is placed at a position such as Figure 4 As shown, when the camera is the left camera or the right camera, the target image obtained by the camera can be as follows Figure 9 As shown, Figure 9 The mark "3" in the figure is the third region of interest in the embodiment of the present application. Figure 9 The image includes two third regions of interest, and the two third regions of interest are located on different calibration plates.

[0115] Step 430: performing binarization processing on the images corresponding to the third region of interest based on a plurality of preset grayscale thresholds to obtain a plurality of third binarized images.

[0116] Step 440: Determine a connected component corresponding to each of the plurality of third binary images.

[0117] Step 450: determining a circular target included in each third binary image based on the connected domain corresponding to each third binary image;

[0118] Step 460: Determine a third number of circular targets corresponding to the third region of interest based on the preset condition and the circular targets included in each third binarized image.

[0119] As an approach, the step of determining a third number of circular targets corresponding to the third region of interest based on the preset conditions and the circular targets included in each third binary image includes: screening the circular targets included in each third binary image according to the third preset conditions to obtain third candidate circular targets corresponding to the third region of interest; and obtaining the third number of circular targets from the third candidate circular targets.

[0120] In the embodiment of the present application, the third preset condition is that the properties of the preset circular target itself meet the preset values.

[0121] After obtaining the third candidate circular targets, a specified number of circular targets are randomly selected from the third candidate targets, and based on the pixel coordinates of the centers of the selected specified number of circular targets, the figure formed by the centers of the specified number of circular targets is determined, and the similarity between the figure formed by the circles of the specified number of circular targets and the figure formed by the centers of the correct circular targets obtained in advance is calculated, and the combination with the highest similarity is taken as the third number of circular targets.

[0122] For example, if the third number is four circular targets and the third candidate circular targets include five circular targets, then four circular targets can be randomly selected from the five circular targets, and a corresponding pattern can be formed based on the centers of the four circular targets. This method can obtain five corresponding patterns, and the similarities between these five patterns and the pattern formed by the centers of the correct circular targets obtained in advance are calculated to obtain five similarities. The four circular targets corresponding to the highest similarities among these five similarities are used as the third number of circular targets.

[0123] Step 470: Determine the pixel coordinates of the centers of the third number of circular targets.

[0124] Step 480: Calibrate the external parameters of the left camera or the right camera based on the pixel coordinates of the centers of the third number of circular targets and the vehicle body coordinates.

[0125] When calibrating the extrinsic parameters of the left or right camera, the mapping relationship between the pixel coordinates and the vehicle coordinates is calculated based on the pixel coordinates of the center of the circular target at the corresponding position and the vehicle coordinates. In other words, the vehicle coordinates of the center of the circular target are converted to pixel coordinates. This mapping relationship includes the rotation matrix and the translation matrix.

[0126] Optionally, if the external parameters of the vehicle's front camera, rear camera, left camera and right camera are calibrated at the same time, the external parameters corresponding to each camera can be obtained by determining the mapping relationship between the pixel coordinates of the centers of the circles corresponding to the first number of circular targets, the second number of circular targets and the third number of circular targets and the vehicle body coordinates.

[0127] This embodiment provides a parameter calibration method. Since the circular target is calibrated using the center coordinates, even if it becomes an ellipse in a scene with severe distortion, the center position is very accurate. Therefore, by calibrating the external parameters of the camera using the circular target, the calibration accuracy can be improved.

[0128] See also Figure 10 The present application provides a parameter calibration device 500, which is operated on a vehicle equipped with a camera. The device 500 includes:

[0129] The image acquisition unit 510 is configured to acquire a target image through the camera. The target image is an image of a calibration plate disposed at a preset position. The calibration plate includes a circular target disposed at a preset position.

[0130] The screening unit 520 is configured to screen the circular targets included in the target image based on a preset condition to obtain a preset number of circular targets.

[0131] As a method, the screening unit 520 is specifically used to determine a region of interest from the target image; binarize the images corresponding to the region of interest based on multiple preset grayscale thresholds to obtain multiple binary images; determine the connected domain corresponding to each binary image in the multiple binary images; determine the circular targets included in each binary image based on the connected domain corresponding to each binary image; and determine a preset number of circular targets corresponding to the region of interest based on the preset conditions and the circular targets included in each binary image.

[0132] As another embodiment, the screening unit 520 is specifically used to determine a first region of interest and a second region of interest from the target image if the camera is a front camera or a rear camera, wherein the first region of interest is a region of an image including a first designated circular target, and the second region of interest is a region of an image including a second designated circular target, the first designated circular target is a circular target set at the middle position of the calibration plate, and the second designated circular target is a circular target set at the edge position of the calibration plate.

[0133] As another method, the screening unit 520 is specifically used to binarize the images corresponding to the first region of interest based on multiple preset grayscale thresholds to obtain multiple first binary images; and to binarize the images corresponding to the second region of interest based on multiple preset grayscale thresholds to obtain multiple second binary images.

[0134] As another embodiment, the screening unit 520 is specifically configured to screen the circular targets included in each of the first binary images according to a first preset condition to obtain first candidate circular targets corresponding to the first region of interest; obtain a first number of circular targets from the first candidate circular targets; and screen the circular targets included in each of the second binary images according to a second preset condition to obtain second candidate circular targets corresponding to the second region of interest; and obtain a second number of circular targets from the second candidate circular targets.

[0135] Optionally, the screening unit 520 is specifically configured to project the vehicle coordinates of the centers of the second number of circular targets into a pixel coordinate system based on a homography matrix if the number of the second candidate circular targets is less than the second number, and determine a new second region of interest from the target image; and obtain the second number of circular targets from the new second region of interest.

[0136] Optionally, the screening unit 520 is specifically used to determine a third area of ​​interest from the target image if the camera is a left camera or a right camera, the third area of ​​interest being an area of ​​the image including a third designated circular target, and the third designated circular target being a circular target set at the edge position of different calibration plates.

[0137] Optionally, the screening unit 520 is specifically configured to perform binarization processing on the images corresponding to the third region of interest based on a plurality of preset grayscale thresholds to obtain a plurality of third binarized images.

[0138] Optionally, the screening unit 520 is specifically configured to screen the circular targets included in each third binary image according to a third preset condition to obtain third candidate circular targets corresponding to the third region of interest; and obtain a third number of circular targets from the third candidate circular targets.

[0139] The coordinate determination unit 530 is configured to determine the pixel coordinates of the centers of the preset number of circular targets.

[0140] As another approach, the coordinate determining unit 530 is specifically configured to determine the pixel coordinates of the centers of the first number of circular targets, and determine the pixel coordinates of the centers of the second number of circular targets.

[0141] Optionally, the coordinate determining unit 530 is specifically configured to determine the pixel coordinates of the centers of the third number of circular targets.

[0142] The calibration unit 540 is configured to calibrate the external parameters of the camera based on the pixel coordinates of the circle center and the vehicle body coordinates.

[0143] As a method, the calibration unit 540 is specifically used to calibrate the external parameters of the front camera or the rear camera based on the pixel coordinates and vehicle body coordinates of the centers of the first number of circular targets, and the pixel coordinates and vehicle body coordinates of the centers of the second number of circular targets.

[0144] As another way, the calibration unit 540 is specifically configured to calibrate the external parameters of the left camera or the right camera based on the pixel coordinates of the centers of the third number of circular targets and the vehicle body coordinates.

[0145] It should be noted that those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the devices and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. In the several embodiments provided in the present application, the coupling between modules can be electrical, mechanical or other forms of coupling. In addition, the various functional modules in the various embodiments of the present application can be integrated into a processing module, or each module can exist physically alone, or two or more modules can be integrated into one module. The above-mentioned integrated modules can be implemented in the form of hardware or in the form of software functional modules.

[0146] The following will be combined Figure 11 A vehicle provided in this application is described.

[0147] See also Figure 11 Based on the above-mentioned parameter calibration method and apparatus, embodiments of the present application also provide another vehicle 100 capable of executing the aforementioned parameter calibration method. The vehicle 100 in the present application may include one or more (only one shown in the figure) processors 102, a memory 104, a wireless module 106, and a camera 108 coupled to each other. The memory 104 stores a program capable of executing the contents of the above-mentioned embodiments, and the processor 102 may execute the program stored in the memory 104.

[0148] The processor 102 may include one or more processing cores. Using various interfaces and circuits, the processor 102 connects to various components within the vehicle 100. It executes instructions, programs, code sets, or instruction sets stored in the memory 104 and accesses data stored in the memory 104 to perform various functions and process data within the vehicle 100. Optionally, the processor 102 may be implemented using at least one of the following hardware forms: a digital signal processing (DSP), a field-programmable gate array (FPGA), or a programmable logic array (PLA). The processor 102 may integrate one or a combination of a central processing unit (CPU), a graphics processing unit (GPU), and a modem. The CPU primarily handles the operating system, user interface, and application programs; the GPU is responsible for rendering and drawing display content; and the modem handles wireless communications. It is understood that the modem may also be implemented independently of the processor 102 via a separate communications chip.

[0149] The memory 104 may include random access memory (RAM) or read-only memory (ROM). The memory 104 may be used to store instructions, programs, code, code sets, or instruction sets. The memory 104 may include a program storage area and a data storage area. The program storage area may store instructions for implementing an operating system, instructions for implementing at least one function (such as a touch function, a sound playback function, an image playback function, etc.), and instructions for implementing the various method embodiments described below. The data storage area may also store data generated by the vehicle 100 during use (such as a phone book, audio and video data, and chat logs).

[0150] The wireless module 106 is used to receive and transmit electromagnetic waves, converting them into electrical signals, thereby communicating with a communications network or other devices, such as an audio playback device. The wireless module 106 may include various existing circuit components for performing these functions, such as an antenna, a radio frequency transceiver, a digital signal processor, an encryption / decryption chip, a subscriber identity module (SIM) card, memory, and the like. The wireless module 106 can communicate with various networks, such as the Internet, an intranet, or a wireless network, or with other devices via a wireless network. These wireless networks may include cellular telephone networks, wireless local area networks, or metropolitan area networks.

[0151] The camera 108 is used to collect target images in real time and send the target images to the processor 102 for processing. In the embodiment of the present application, the camera can be a surround view camera, a monocular camera, or a fisheye camera.

[0152] Please refer to Figure 12 , which shows a block diagram of a computer-readable storage medium provided in an embodiment of the present application. The computer-readable storage medium 800 stores program code, which can be called by a processor to execute the method described in the above method embodiment.

[0153] Computer-readable storage medium 800 may be an electronic memory such as flash memory, EEPROM (Electrically Erasable Programmable Read-Only Memory), EPROM, a hard disk, or ROM. Alternatively, computer-readable storage medium 800 may comprise a non-transitory computer-readable storage medium. Computer-readable storage medium 800 has storage space for program code 810 for executing any of the method steps described above. This program code can be read from or written to one or more computer program products. Program code 810 may be compressed, for example, in a suitable format.

[0154] In summary, the present application provides a parameter calibration method, device, vehicle, and storage medium. First, a target image of a circular target set at a preset position is acquired. Then, the pixel coordinates of the center of the circular target are determined. Finally, the external parameters of the camera are calibrated based on the pixel coordinates of the center and the vehicle body coordinates. Through the above method, since the circular target is calibrated using the center coordinates during calibration, even if it becomes an ellipse in a scene with severe distortion, the center position is very accurate. Therefore, by calibrating the external parameters of the camera using the circular target, the calibration accuracy can be improved.

[0155] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A parameter calibration method, characterized in that: Applied to a vehicle, the vehicle being equipped with a camera, the method comprising: Acquire a target image through the camera, wherein the target image is an image of a calibration plate set at a preset position, wherein the calibration plate includes a circular target set at a preset position; Based on a preset condition, the circular targets included in the target image are screened to obtain a preset number of circular targets; The method of screening the circular targets included in the target image based on the preset conditions to obtain a preset number of circular targets includes: determining a region of interest from the target image; Binarization is performed on the images corresponding to the regions of interest based on a plurality of preset grayscale thresholds to obtain a plurality of binary images; Determine a connected domain corresponding to each of the plurality of binary images; Determining a circular target included in each binary image based on the connected domain corresponding to each binary image; Determining a preset number of circular targets corresponding to the region of interest based on the preset conditions and the circular targets included in each binarized image; Determining the pixel coordinates of the centers of the preset number of circular targets; The external parameters of the camera are calibrated based on the pixel coordinates of the circle center and the vehicle body coordinates.

2. The method according to claim 1, characterized in that Determining a region of interest from the target image includes: If the camera is a front camera or a rear camera, determining a first region of interest and a second region of interest from the target image, wherein the first region of interest is a region of the image including a first designated circular target, and the second region of interest is a region of the image including a second designated circular target, the first designated circular target is a circular target disposed in the middle of the calibration plate, and the second designated circular target is a circular target disposed at an edge of the calibration plate; The binarization processing is performed on the images corresponding to the regions of interest based on a plurality of preset grayscale thresholds to obtain a plurality of binarized images, including: Performing binarization processing on the images corresponding to the first region of interest based on a plurality of preset grayscale thresholds to obtain a plurality of first binarized images; and performing binarization processing on the images corresponding to the second region of interest based on a plurality of preset grayscale thresholds to obtain a plurality of second binarized images; The determining of a preset number of circular targets corresponding to the region of interest based on the preset condition and the circular targets included in each binarized image includes: According to a first preset condition, the circular targets included in each first binary image are screened to obtain a first candidate circular target corresponding to the first region of interest; Acquire a first number of circular targets from the first candidate circular targets; and According to a second preset condition, the circular targets included in each second binary image are screened to obtain a second candidate circular target corresponding to the second region of interest; Acquire a second number of circular targets from the second candidate circular targets; Determining the pixel coordinates of the centers of the preset number of circular targets includes: The pixel coordinates of the centers of the first number of circular targets are determined, and the pixel coordinates of the centers of the second number of circular targets are determined.

3. The method according to claim 2, characterized in that The calibrating of the external parameters of the camera based on the pixel coordinates of the circle center and the vehicle body coordinates includes: The external parameters of the front camera or the rear camera are calibrated based on the pixel coordinates and vehicle body coordinates of the centers of the first number of circular targets and the pixel coordinates and vehicle body coordinates of the centers of the second number of circular targets.

4. The method according to claim 2, characterized in that Before obtaining the second number of circular targets from the second candidate circular targets, the method further includes: If the number of the second candidate circular targets is less than the second number, projecting the vehicle coordinates of the centers of the second number of circular targets into a pixel coordinate system based on the homography matrix, and determining a new second region of interest from the target image; The second number of circular targets are acquired from the new second region of interest.

5. The method according to claim 1, characterized in that Determining a region of interest from the target image includes: If the camera is a left camera or a right camera, determining a third region of interest from the target image, wherein the third region of interest is a region of the image including a third designated circular target, and the third designated circular target is a circular target set at an edge position of a different calibration plate; The binarization processing is performed on the images corresponding to the regions of interest based on a plurality of preset grayscale thresholds to obtain a plurality of binarized images, including: performing binarization processing on the images corresponding to the third region of interest based on a plurality of preset grayscale thresholds to obtain a plurality of third binarized images; The determining of a preset number of circular targets corresponding to the region of interest based on the preset condition and the circular targets included in each binarized image includes: According to a third preset condition, the circular targets included in each third binary image are screened to obtain a third candidate circular target corresponding to the third region of interest; Acquire a third number of circular targets from the third candidate circular targets; Determining the pixel coordinates of the centers of the preset number of circular targets includes: The pixel coordinates of the centers of the third number of circular targets are determined.

6. The method according to claim 5, characterized in that The calibrating of the external parameters of the camera based on the pixel coordinates of the circle center and the vehicle body coordinates includes: Based on the pixel coordinates of the centers of the third number of circular targets and the vehicle body coordinates, the external parameters of the left camera or the right camera are calibrated.

7. A parameter calibration device, characterized in that: The device is operated on a vehicle equipped with a camera, and includes: An image acquisition unit, configured to acquire a target image through the camera, wherein the target image is an image acquired from a calibration plate disposed at a preset position, wherein the calibration plate includes a circular target disposed at a preset position; a screening unit, configured to screen the circular targets included in the target image based on preset conditions to obtain a preset number of circular targets; the screening of the circular targets included in the target image based on the preset conditions to obtain the preset number of circular targets comprises: determining a region of interest from the target image; binarizing the images corresponding to the region of interest based on a plurality of preset grayscale thresholds to obtain a plurality of binary images; determining a connected domain corresponding to each of the plurality of binary images; determining the circular targets included in each binary image based on the connected domain corresponding to each of the binary images; and determining the preset number of circular targets corresponding to the region of interest based on the preset conditions and the circular targets included in each of the binary images; a coordinate determining unit, configured to determine the pixel coordinates of the centers of the preset number of circular targets; A calibration unit is used to calibrate the external parameters of the camera based on the pixel coordinates of the center of the circle and the vehicle body coordinates.

8. A vehicle, characterized in that: The method comprises a camera, one or more processors and a memory; one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs are configured to execute the method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores program codes, which can be called by a processor to execute the method according to any one of claims 1 to 6.

Images