Methods and devices for attitude correction of vehicle-mounted cameras, storage media, and electronic devices

Abstract

A method and apparatus for attitude correction of a vehicle-mounted camera, a storage medium, and an electronic device are disclosed. The method includes: acquiring a first image of a vehicle-mounted camera containing multiple lane lines; in response to the multiple lane lines meeting preset conditions, determining the image lane lines corresponding to each lane line in the first image in the image coordinate system; determining the current pose information of the vehicle-mounted camera relative to the vehicle; and correcting at least one attitude angle in the current pose information based on the image lane lines to obtain the corrected target pose information of the vehicle-mounted camera relative to the vehicle; wherein the attitude angle includes at least one of the following: pitch angle, roll angle, and yaw angle.

Description

Technical Field

[0001] This application relates to a method and apparatus for posture correction of a vehicle-mounted camera, a storage medium, and an electronic device. Background Technology

[0002] Visual perception plays a crucial role in current autonomous driving scenarios, providing vehicles with perceptual information about their surroundings. Visual perception is indispensable in many application scenarios (such as Automatic Emergency Braking (AEB) and Adaptive Cruise Control (ACC). To effectively support forward-looking perception, it is necessary to calibrate the extrinsic parameters of the camera. However, the extrinsic parameters of cameras in current technologies are usually highly dependent on the scene in which the vehicle is located. For example, the vehicle needs to be parked at a specific location in a specific scene, or the vehicle needs to maintain a straight line. Summary of the Invention

[0003] To address the aforementioned technical problems, this application is proposed. Embodiments of this application provide a method and apparatus for correcting the attitude of a vehicle-mounted camera, a storage medium, and an electronic device.

[0004] According to one aspect of this application, a method for attitude correction of a vehicle-mounted camera is provided, comprising:

[0005] Acquire the first image, including multiple lane lines, captured by the vehicle-mounted camera;

[0006] In response to the multiple lane lines meeting preset conditions, the image lane lines corresponding to each lane line in the first image are determined in the image coordinate system.

[0007] Determine the current pose information of the vehicle-mounted camera relative to the vehicle;

[0008] Based on the lane lines in the image, at least one attitude angle in the current pose information is corrected to obtain the corrected target pose information of the vehicle-mounted camera relative to the vehicle; wherein, the attitude angle includes at least one of the following: pitch angle, roll angle, and yaw angle.

[0009] According to another aspect of this application, a vehicle-mounted camera attitude correction device is provided, comprising:

[0010] The image acquisition module is used to acquire the first image, which includes multiple lane lines, captured by the vehicle-mounted camera.

[0011] A lane line determination module is used to determine the image lane lines in the first image acquired by the image acquisition module in the image coordinate system in response to the multiple lane lines meeting preset conditions; wherein, each lane line corresponds to one image lane line;

[0012] An initial pose determination module is used to determine the current pose information of the vehicle-mounted camera relative to the vehicle.

[0013] The pose correction module is used to correct at least one attitude angle in the current pose information determined by the initial pose determination module based on the image lane line determined by the lane line determination module, so as to obtain the corrected target pose information of the vehicle camera relative to the vehicle; wherein, the at least one attitude angle includes at least one of the following: pitch angle, roll angle, and yaw angle.

[0014] According to another aspect of this application, a computer-readable storage medium is provided, the storage medium storing a computer program for performing the vehicle-mounted camera attitude correction method described in any of the above embodiments.

[0015] According to another aspect of this application, an electronic device is provided, the electronic device comprising:

[0016] processor;

[0017] Memory used to store the processor's executable instructions;

[0018] The processor is configured to read the executable instructions from the memory and execute the instructions to implement the vehicle camera attitude correction method described in any of the above embodiments.

[0019] Based on the vehicle camera attitude correction method, device, storage medium, and electronic device provided in the above embodiments of this disclosure, the method corrects the current pose information of the vehicle camera relative to the vehicle by using images of multiple lane lines in a natural driving scene collected during vehicle driving. The natural driving scene can be any driving scene, so it does not depend on a specific scene. Furthermore, the method corrects the current pose information of the vehicle camera relative to the vehicle by using the image lane line equations of the multiple lane lines in the image coordinate system corresponding to the image. This achieves correction of at least one pose angle that only requires knowledge of the current pose information. Since it does not require much prior knowledge and does not depend on a specific scene, the method provided in this embodiment can be applied to a variety of driving scenarios. Attached Figure Description

[0020] The above and other objects, features, and advantages of this application will become more apparent from the more detailed description of the embodiments of this application in conjunction with the accompanying drawings. The drawings are provided to further illustrate the embodiments of this application and form part of the specification. They are used together with the embodiments of this application to explain this application and do not constitute a limitation thereof. In the drawings, the same reference numerals generally represent the same components or steps.

[0021] Figure 1 This is a flowchart illustrating an exemplary embodiment of the vehicle-mounted camera attitude correction method provided in this application.

[0022] Figure 2 This is a public announcement Figure 1 The illustrated embodiment is a flowchart of step 108.

[0023] Figure 3a This is a public announcement Figure 2 The illustrated embodiment is a flowchart of step 1082.

[0024] Figure 3b This is a schematic diagram of determining the pitch angle increment in one of the optional examples provided in this disclosure.

[0025] Figure 3c It is Figure 3b The diagram shows the lane direction vector obtained by transforming the intersection line OV to the new camera coordinate system.

[0026] Figure 3d It is Figure 3c The diagram shows the direction vector of the lane line as seen from above along the oz direction.

[0027] Figure 4 This is a public announcement Figure 1 Another flowchart of step 108 in the illustrated embodiment.

[0028] Figure 5a This is a public announcement Figure 4 The illustrated embodiment is a flowchart of step 1085.

[0029] Figure 5b This is a schematic diagram of determining the roll angle increment in one of the optional examples provided in this disclosure.

[0030] Figure 6 This is a public announcement Figure 1 The illustrated embodiment shows another flowchart of step 108.

[0031] Figure 7a This is a public announcement Figure 6 The illustrated embodiment is a flowchart of step 1088.

[0032] Figure 7b This is a schematic diagram of determining the yaw angle increment in one of the optional examples provided in this disclosure.

[0033] Figure 8 This is a schematic diagram of the structure of an in-vehicle camera attitude correction device provided in an exemplary embodiment of this application.

[0034] Figure 9 This is a schematic diagram of the structure of a vehicle-mounted camera attitude correction device provided in another exemplary embodiment of this application.

[0035] Figure 10This is a structural diagram of an electronic device provided in an exemplary embodiment of this application. Detailed Implementation

[0036] Hereinafter, exemplary embodiments according to this application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are merely some embodiments of this application, and not all embodiments of this application. It should be understood that this application is not limited to the exemplary embodiments described herein.

[0037] It should be noted that, unless otherwise specifically stated, the relative arrangement, numerical expressions, and values ​​of the components and steps set forth in these embodiments do not limit the scope of this disclosure.

[0038] Those skilled in the art will understand that the terms "first," "second," etc., in the embodiments of this disclosure are only used to distinguish different steps, devices, or modules, and do not represent any specific technical meaning, nor do they indicate a necessary logical order between them.

[0039] It should also be understood that in the embodiments disclosed herein, "a plurality of" may refer to two or more, and "at least one" may refer to one, two or more.

[0040] It should also be understood that any component, data or structure mentioned in the embodiments of this disclosure can generally be understood as one or more unless expressly defined or given to the contrary in the context.

[0041] Furthermore, the term "and / or" in this disclosure is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this disclosure generally indicates that the preceding and following related objects have an "or" relationship.

[0042] It should also be understood that the description of the various embodiments in this disclosure emphasizes the differences between the various embodiments, and the similarities or similarities can be referred to each other. For the sake of brevity, they will not be described in detail.

[0043] At the same time, it should be understood that, for ease of description, the dimensions of the various parts shown in the accompanying drawings are not drawn according to actual scale.

[0044] The following description of at least one exemplary embodiment is merely illustrative and is in no way intended to limit this disclosure or its application or use.

[0045] Techniques, methods, and equipment known to those skilled in the art may not be discussed in detail, but where appropriate, such techniques, methods, and equipment should be considered part of the specification.

[0046] It should be noted that similar labels and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be discussed further in subsequent figures.

[0047] The embodiments disclosed herein can be applied to electronic devices such as terminal devices, computer systems, and servers, and can operate together with a wide range of other general-purpose or special-purpose computing system environments or configurations. Examples of well-known terminal devices, computing systems, environments, and / or configurations suitable for use with electronic devices such as terminal devices, computer systems, and servers include, but are not limited to: personal computer systems, server computer systems, thin clients, thick clients, handheld or laptop devices, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputer systems, mainframe computer systems, and distributed cloud computing environments including any of the above systems, etc.

[0048] Electronic devices such as terminal devices, computer systems, and servers can be described in the general context of computer system executable instructions (such as program modules) executed by a computer system. Typically, program modules can include routines, programs, object programs, components, logic, data structures, etc., which perform specific tasks or implement specific abstract data types. Computer systems / servers can be implemented in distributed cloud computing environments, where tasks are executed by remote processing devices linked through communication networks. In distributed cloud computing environments, program modules can reside on local or remote computing system storage media, including storage devices.

[0049] Application Overview

[0050] In the process of realizing this disclosure, the inventors discovered that the existing camera extrinsic parameter determination methods require the vehicle to remain at a specific position in a specific scene, or the vehicle to keep driving in a straight line. In other words, there are excessive requirements for the scene or driving conditions, and excessive reliance on external prior inputs and assumptions, which leads to the problem that calibration is impossible in natural scenes.

[0051] Exemplary methods

[0052] Figure 1 This is a schematic flowchart of an exemplary embodiment of the vehicle-mounted camera attitude correction method provided in this application. This embodiment can be applied to electronic devices, such as... Figure 1 As shown, it includes the following steps:

[0053] Step 102: Collect images of multiple lane lines using the vehicle-mounted camera to obtain the first image.

[0054] When a vehicle is driving in a natural road scene, an image of the current road surface is captured by an onboard camera. The resulting first image includes multiple lane lines. The onboard camera may include one or more cameras, and the orientation of the onboard camera is at least directly in front of the vehicle, and may also include left front, right front, etc. By capturing the road surface in front of the vehicle, multiple lane lines on the natural road (e.g., highway, etc.) can be obtained (all legal roads for normal vehicle travel have multiple lane lines), wherein the multiple lane lines include at least the lane lines on both sides of the lane where the vehicle is traveling; wherein, the natural road scene can be any road scene where vehicles can legally travel, such as highways, other urban roads, etc. In this embodiment, the attitude correction of the onboard camera can be achieved when the vehicle is driving normally.

[0055] Step 104: In response to multiple lane lines meeting preset conditions, determine the image lane line corresponding to each lane line in the image coordinate system.

[0056] Each lane line corresponds to an image lane line. The lane line refers to the actual lane line that exists on the road surface, while the image lane line refers to the coordinate representation of the lane line in the image coordinate system corresponding to the image after it is captured by the vehicle-mounted camera.

[0057] Optionally, the preset conditions referred to in this embodiment can be set according to the actual application scenario. Different attitude angles can be corrected with different preset conditions or the same preset conditions. Optionally, the preset conditions can include, but are not limited to, one or more of the following: multiple lane lines are all non-curved, the number of lane lines is greater than or equal to a set number (this set number can be set according to the actual scenario, for example: 2 or 3), and the spacing between lane lines is the same. For example, when correcting the pitch angle, the corresponding preset condition can be that multiple lane lines are all non-curved; when correcting the roll angle, the corresponding preset condition can be that the number of lane lines is greater than a set number (for example, 3); when correcting the yaw angle, the corresponding preset condition can be that the spacing between lane lines is the same. For example, when the above three preset conditions are met at the same time, the pitch angle, roll angle and yaw angle can be corrected. The image lane lines are the images of the lane lines in the image of the road surface captured by the vehicle camera.

[0058] Step 106: Determine the current pose information of the vehicle-mounted camera relative to the vehicle.

[0059] In this embodiment, the location and method of installing the vehicle-mounted camera in each vehicle are determined according to the vehicle's factory settings. In this embodiment, the current position and pose information of the vehicle can be determined based on the vehicle's factory settings information.

[0060] Step 108: Based on the lane lines in the image, at least one attitude angle in the current pose information is corrected to obtain the corrected target pose information of the vehicle camera relative to the vehicle.

[0061] The attitude angles include at least one of the following: pitch angle, roll angle, and yaw angle.

[0062] In this embodiment, at least one of the pitch angle, roll angle, and yaw angle can be corrected to adjust the camera pose information. The camera pose can be corrected based on a single frame image including lane lines, which can be applied to more driving scenarios. The corrected target pose information can better provide the vehicle with perception information of the surrounding environment.

[0063] The above-described embodiments of this disclosure provide a method for correcting the attitude of an in-vehicle camera. This method corrects the attitude of the in-vehicle camera by using images of natural driving scenes, including multiple lane lines, collected during vehicle movement. The natural driving scene can be any driving scene, thus not depending on a specific scene. Furthermore, the method corrects the current pose information of the in-vehicle camera relative to the vehicle by using the image lane line equations of the multiple lane lines in the image coordinate system corresponding to the image. This achieves correction of at least one pose angle that only requires knowledge of the current pose information. Since it does not require much prior knowledge and is not dependent on a specific scene, the method provided in this embodiment can be applied to various driving scenarios.

[0064] like Figure 2 As shown above, in the above Figure 1 Based on the illustrated embodiment, step 108 may include the following steps:

[0065] Step 1081: Based on the image lane lines and the current pose information, determine the first ground corresponding to the multiple lane lines.

[0066] The first ground is either the initial ground or the first corrected ground corresponding to the current pose information. The first corrected ground is the ground corresponding to the pose information obtained after correcting the roll angle and / or yaw angle in the current pose information. A plane in the image coordinate system can be determined by multiple image lane lines (two or more straight lines can determine a plane). By performing coordinate system transformation through the current pose information, the plane in the camera coordinate system can be transformed into the world coordinate system, thus determining the first ground.

[0067] Optionally, in this embodiment, when only the pitch angle of the vehicle-mounted camera is corrected, the first ground is the initial ground; or when the object to be corrected is multiple attitude angles, and the pitch angle is corrected first, the first ground is the initial ground; when the object to be corrected is multiple attitude angles, and the pitch angle is corrected later, the first ground is the first corrected ground (the first corrected ground is the ground after correcting other attitude angles that were corrected before the pitch angle).

[0068] Step 1082: Determine the pitch angle increment based on the origin of the camera coordinate system corresponding to the vehicle-mounted camera and the first ground lane line corresponding to each lane line in the first ground.

[0069] Each lane line corresponds to a first ground lane line; the origin of the camera coordinate system is usually the optical center of the vehicle camera; based on the determination of the first ground, each image lane line in the camera coordinate system is projected onto the first ground to determine the first ground lane line.

[0070] Step 1083: Correct the pitch angle in the current pose information based on the pitch angle increment to obtain the corrected target pose information of the vehicle camera relative to the vehicle.

[0071] This embodiment corrects the pitch angle of the vehicle-mounted camera. In this embodiment, only the pitch angle of the vehicle-mounted camera can be corrected by pitch angle increment. In this case, the first ground is the initial ground. Alternatively, in addition to calibrating the pitch angle, the roll angle and / or yaw angle can also be corrected. In this case, the order of correction of multiple attitude angles is not limited. The pitch angle can be corrected first, followed by the roll angle and / or yaw angle, or the roll angle and / or yaw angle can be corrected first, followed by the pitch angle. The order of correction does not constitute a limitation on the scope of protection disclosed. For example, in one example, the pitch angle is corrected first, then the roll angle is corrected, and finally the yaw angle is corrected.

[0072] This embodiment can determine the pitch angle increment based solely on the origin of the camera coordinate system and the multiple lane lines corresponding to the multiple lane lines on the first ground surface, achieving rapid pitch angle correction. Apart from the multiple lane lines on the road surface, it does not rely on other information, reducing the difficulty of pitch angle correction.

[0073] like Figure 3a As shown above, in the above Figure 2 Based on the illustrated embodiment, step 1082 may include the following steps:

[0074] Step 301: Based on the origin of the camera coordinate system and the first ground lane lines corresponding to each lane line in the multiple lane lines, determine multiple first planes.

[0075] Each first plane includes a first ground lane line and the origin of the camera coordinate system; that is, in this embodiment, a plane is defined as a first plane by a point (the origin of the camera coordinate system) and a line (a first ground lane line); therefore, each first ground lane line corresponds to a first plane, resulting in multiple first planes.

[0076] In this embodiment, the calculation of the pitch angle increment mainly relies on the parallel characteristics between multiple lane lines (the preset condition required by this embodiment is that all lane lines are non-curved). A schematic diagram of the first plane can be referred to. Figure 3b The diagram shows a spatial arrangement. Point O is the origin of the camera coordinate system, and line segments AB and CD are two parallel first ground lane lines. In this embodiment, plane OAB is obtained by forming a plane with point O and line segment AB; plane OCD is obtained by forming a plane with point O and line segment CD. It can be understood that both plane OAB and plane OCD are first planes.

[0077] Step 302: Determine the pitch angle increment based on the angle between the intersection line of multiple first planes and the first ground.

[0078] This embodiment uses the intersection lines between multiple first planes to represent the direction vector of the lane lines. The angle between this direction vector and the first ground surface represents the pitch angle error of the current vehicle camera, thus determining the pitch angle increment. This embodiment can determine the pitch angle increment using a single frame of an image including multiple lane lines, enabling the vehicle to adjust the pitch angle while driving in non-curved scenarios; for example, Figure 3b As shown, the intersection line OV of plane OAB and plane OCD represents the direction vectors of lane lines AB and CD. The specific process for calculating the angle between the intersection line OV and the first ground surface can be found in [reference needed]. Figure 3b To understand this, transforming the intersection line OV to a new camera coordinate system (a new virtual coordinate system aligned with the first plane) yields the following: Figure 3c The coordinate diagram shown, after normalizing the intersection line OV, yields the arctan (arctangent) value of the ratio of its y-axis to z-axis components, which represents the pitch angle increment. An upward tilt of oz is positive, and a downward tilt is negative. Rotating the camera coordinate system by this pitch angle increment and viewing from above along the oz direction yields the following... Figure 3d The top view shown; at this time, ov is located in the zox plane. Moving the zox plane along the oy direction, the intersection lines with the plane OAB and the plane OCD are all parallel lines, and are all parallel to ov. This means that the pitch angle at this time matches the currently acquired image, and the pitch angle of the vehicle camera is now adjusted.

[0079] like Figure 4 As shown above, in the above Figure 1Based on the illustrated embodiment, step 108 may further include the following steps:

[0080] Step 1084: Based on the image lane lines and the current pose information, determine the second ground corresponding to multiple lane lines.

[0081] The second ground is either the initial ground or the second corrected ground corresponding to the current pose information. The second corrected ground is the ground corresponding to the pose information obtained after correcting the pitch angle and / or yaw angle in the current pose information. A plane in the image coordinate system can be determined by multiple image lane lines (two or more straight lines can determine a plane). By transforming the coordinate system through the current pose information, the plane in the camera coordinate system can be transformed into the world coordinate system, thus determining the second ground.

[0082] Optionally, when only the roll angle of the vehicle camera is corrected in this embodiment, or when multiple attitude angles are corrected and the roll angle is corrected first, the second ground is the initial ground; while when multiple attitude angles are corrected, and other attitude angles are corrected first and then the roll angle is corrected, the second ground is the second corrected ground.

[0083] Step 1085: Determine the roll angle increment based on the origin of the camera coordinate system corresponding to the vehicle-mounted camera and the second ground lane lines corresponding to each lane line in the second ground.

[0084] Each lane line corresponds to a second ground lane line; once the second ground is determined, each image lane line in the camera coordinate system is projected onto the second ground to determine the second ground lane line.

[0085] Step 1086: Correct the roll angle in the current pose information based on the roll angle increment to obtain the corrected target pose information of the vehicle camera relative to the vehicle.

[0086] This embodiment corrects the roll angle of the vehicle-mounted camera. In this embodiment, only the roll angle of the vehicle-mounted camera can be corrected by increasing the roll angle. In this case, the first ground is the initial ground. Alternatively, in addition to correcting the roll angle, the pitch angle and / or yaw angle can also be corrected. In this case, there is no restriction on the order of correction of multiple attitude angles. The pitch angle can be corrected first, and then the roll angle and / or yaw angle can be corrected, or the roll angle and / or yaw angle can be corrected first, and then the pitch angle can be corrected. The order of correction does not affect the correction effect.

[0087] This embodiment achieves rapid roll angle correction without relying on other information besides the multiple lane lines on the road surface, thus reducing the difficulty of roll angle correction.

[0088] like Figure 5a As shown above, in the above Figure 4Based on the illustrated embodiment, step 1085 may include the following steps:

[0089] Step 501: Determine the three first intersection points between the three adjacent lane lines of the second ground and the vertical plane in the camera coordinate system.

[0090] In this embodiment, the roll angle correction relies on the equal width constraint between lane lines. Two lane lines on the second ground can determine a width. To achieve the equal width constraint, at least two widths are required. Therefore, the second ground must include at least three lane lines. When the number of lane lines on the second ground is greater than or equal to three, three adjacent lane lines on the second ground are selected to correct the roll angle.

[0091] Since the three second ground lane lines are located on the same virtual image plane, the three first intersection points lie on a straight line, for example, as shown below. Figure 5b In the provided example, e, c, and d are the three first intersection points, o c This represents the origin of the camera coordinate system.

[0092] Step 502: Determine three simulated lane lines based on the three second ground lane lines and the origin of the camera coordinate system.

[0093] Based on modern road construction standards, lane lines are equidistant and have a set arch angle. In this embodiment, the three second ground lane lines displayed in the image captured by the vehicle-mounted camera and the origin of the camera coordinate system can be projected to obtain three simulated lane lines in the real scene that correspond to the three second ground lane lines respectively.

[0094] Step 503: Determine the three second intersection points between the three simulated lane lines and the vertical plane in the camera coordinate system.

[0095] Each simulated lane line intersects with the vertical plane in the camera coordinate system at a point where a second intersection point is formed. The three simulated lane lines thus yield three second intersection points.

[0096] Because of the arched curvature between the actual lane lines, the distances between the three second ground lane lines projected onto the same plane will inevitably be unequal, that is... Figure 5b In this context, ed is not equal to ec, and in real-world scenarios, the distance between two adjacent lane lines is equal. Therefore, based on o... c The extension of d, and o c The extension of c determines two points b and a on the vertical plane that correspond to the two simulated lane lines respectively, such that eb = ea, which means that the spacing between two adjacent simulated lane lines is the same among the three simulated lane lines.

[0097] Step 504: Determine the roll angle increment based on the three first intersection points and the three second intersection points.

[0098] In this embodiment, it is necessary to update the corresponding local ground plane equation (e.g., Figure 5b The roll angle increment, calculated using the plane corresponding to the center line segment (ced), depends on lane width constraints. That is, roll angle calibration can be enabled when three adjacent lane lines are observed; otherwise, the roll angle is not adjusted. In this embodiment, the roll angle increment can be determined by simulating the angle between the lane line and the second ground equation corresponding to the second ground lane line. The calculation process only requires analytical operations based on geometry, which reduces the computational power requirement for calculating the roll angle increment and does not have too many priors or scene dependencies.

[0099] Optionally, based on the above embodiments, step 504 may include:

[0100] The first line segment is determined based on the three first intersection points;

[0101] Based on the three second intersection points, determine two second line segments of equal length;

[0102] The roll angle increment is determined based on the angle between the first line segment and one of the two second line segments.

[0103] The determination of the roll angle increment can be referred to Figure 5b To understand the example shown, consider the presence of a cross slope on the road surface, meaning that lanes of equal width are not on the same plane. The intersection points of the simulated lane line and the vertical plane in the camera coordinate system are points a, e, and b (the second intersection points). Under the second ground equation (which represents a plane) corresponding to the second ground lane line, these are points c, e, and d (the first intersection points), corresponding to the first line segment in this embodiment. c and o g Let e ​​be the origin of the camera coordinate system and the origin of the local ground coordinate system, respectively. The origin of the local ground coordinate system is the position of the camera's optical center projected perpendicularly onto the ground. Draw perpendicular lines through point e to intersect o. c a and o c b is given by m and n. Given be = ea = r, angle bea can be determined by the lateral slope in the road construction specifications, or by estimation during actual vehicle operation. Angle nem can also be calculated based on the lane lines in each frame of the image. Assuming angle θ = θ1 + θ2 = 2π - ∠bea - ∠nem, where θ2 = ∠ben and θ1 = ∠aem, under the condition that angle θ is known, θ1 can be solved according to the geometric relationship. Then the roll angle increment ∠aec to be calibrated in the figure can be determined according to the following formula (1):

[0104] ∠aec=θ1-∠cem Formula (1)

[0105] Based on the above, the roll angle increment can be determined through simple geometric calculations, thus solving the problem of high computing power requirements in existing technologies.

[0106] like Figure 6 As shown above, in the above Figure 1 Based on the illustrated embodiment, step 108 may further include the following steps:

[0107] Step 1087: Based on the image lane lines and the current pose information, determine the third ground corresponding to multiple lane lines.

[0108] The third ground is either the initial ground or the third corrected ground corresponding to the current pose information. The third corrected ground is the ground corresponding to the pose information obtained after correcting the roll angle and / or pitch angle in the current pose information. A plane in the image coordinate system can be determined by multiple image lane lines (two or more straight lines can determine a plane). By transforming the coordinate system through the current pose information, the plane in the camera coordinate system can be transformed into the world coordinate system, thus determining the third ground.

[0109] Optionally, when only the yaw angle of the vehicle-mounted camera is corrected in this embodiment, or when multiple attitude angles are corrected and the yaw angle is corrected first, the third ground is the initial ground; while when multiple attitude angles are corrected, and other attitude angles are corrected first and then the yaw angle is corrected, the third ground is the third corrected ground.

[0110] Step 1088: Determine the yaw angle increment based on the origin of the camera coordinate system corresponding to the vehicle-mounted camera and the third ground lane lines corresponding to each lane line in the third ground.

[0111] Each lane line corresponds to a third ground lane line; once the third ground is determined, each image lane line in the camera coordinate system is projected onto the third ground to determine the third ground lane line.

[0112] Step 1089: Correct the yaw angle in the current pose information based on the yaw angle increment to obtain the corrected target pose information of the vehicle camera relative to the vehicle.

[0113] This embodiment corrects the yaw angle of the vehicle-mounted camera. In this embodiment, only the yaw angle of the vehicle-mounted camera can be corrected by yaw angle increment. In this case, the third ground is the initial ground. Alternatively, in addition to correcting the yaw angle, the roll angle and / or pitch angle can also be corrected. In this case, there is no restriction on the order of correction of multiple attitude angles. The pitch angle can be corrected first, and then the roll angle and / or yaw angle can be corrected, or the roll angle and / or yaw angle can be corrected first, and then the pitch angle can be corrected. The order of correction does not affect the correction effect.

[0114] This embodiment can determine the yaw angle increment based solely on the origin of the camera coordinate system and the multiple lane lines corresponding to the third ground in the third ground, achieving rapid yaw angle correction. Apart from motion estimation and multiple lane lines on the road surface, it does not rely on other information, reducing the difficulty of yaw angle correction.

[0115] like Figure 7a As shown above, in the above Figure 6 Based on the illustrated embodiment, before performing step 1088, the method further includes: acquiring images of multiple lane lines using an onboard camera to obtain a second image; step 1088 may include the following steps:

[0116] Step 701: Determine the fourth ground lane line corresponding to the second image.

[0117] In this embodiment, the second image can be any frame before or after the first image is captured by the vehicle-mounted camera during vehicle movement. The acquisition interval between the first and second images does not exceed a set number of frames. For example, the second image is a frame after the first image is captured, or the second image is a frame before the first image is captured. The smaller the interval between the second and first images, the smaller the change in the lane lines on the road surface, and the more convenient it is to calculate the yaw angle increment. This avoids the phenomenon that the lane line shape changes due to a large time interval, which would increase the amount of calculation or make it impossible to calculate.

[0118] Step 702: Determine the first projection point of the origin of the camera coordinate system in the third ground corresponding to the first image, and determine the second projection point of the origin of the camera coordinate system in the third ground corresponding to the second image.

[0119] Based on a method similar to determining the third ground corresponding to the first image, a ground corresponding to the second image can be determined. To enable comparison between the first and second images, it is necessary to determine the transformation relationship between the ground corresponding to the second image and the third ground (since they are both planes, the transformation relationship only includes translation distance and translation direction). This transformation relationship can be determined by using motion estimation methods to determine the vehicle motion estimation information between the first and second images. The projection point of the origin of the camera coordinate system onto the ground corresponding to the second image is transformed by this transformation relationship to obtain the second projection point. That is, the second projection point of the origin of the camera coordinate system onto the third ground corresponding to the second image is determined by motion estimation. There are many ways to implement motion estimation. For example, the position and direction of the vehicle at the time of acquiring the first image and the time of acquiring the second image can be obtained through a vehicle positioning system, or the distance and direction can be determined by the vehicle speed and driving direction, etc.

[0120] Step 703: Determine the yaw angle increment based on the first distance between the first projection point and the third ground lane line, and the second distance between the second projection point and the fourth ground lane line.

[0121] In this embodiment, the third and fourth ground lane lines, which are determined by the first and second distances, are obtained from the same lane line.

[0122] This embodiment proposes to determine the yaw angle increment by acquiring a first image and a second image of the same lane line based on two adjacent or close frames. Considering the ground coordinate system corresponding to the vehicle camera between the two frames (when correcting the yaw angle, the pitch angle and roll angle are not processed, so the first image and the second image correspond to the same ground coordinate system corresponding to the third ground), the projection points of the origin corresponding to the first image and the second image corresponding to the camera coordinate system of the vehicle camera onto the ground coordinate system are used to determine the distances between the two projection points and the corresponding third and fourth ground lane lines, respectively. Thus, the yaw angle increment can be determined. This embodiment achieves simple, fast, and accurate yaw angle correction during vehicle operation.

[0123] Specifically, determining the yaw angle increment in the ground coordinate system corresponding to the third ground, i.e., the process of rotating around the z-axis of that ground plane coordinate system, may optionally include step 703 as follows:

[0124] In the third ground, a first arc is obtained with the first projection point as the center and the first distance as the radius; a second arc is obtained with the second projection point as the center and the second distance as the radius.

[0125] Determine the common tangent of the first and second circular arcs;

[0126] The yaw angle increment is determined based on the angle between the tangent line and the lane line.

[0127] Alternatively, refer to Figure 7b As shown, in the third ground plane, the first projection point is marked as o1, the two third ground plane lane lines on both sides of the vehicle are marked as l1 and l2, the second projection point is marked as o2, and the two fourth ground plane lane lines on both sides of the vehicle are marked as l ′ 1 and l ′ 2. At this point, the line connecting the first projection point and the second projection point can be referenced. Figure 7b The dashed line on the left side of the middle section indicates that the common tangent of the first and second arcs can be referenced. Figure 7b The dashed line on the right side of the middle line determines the common tangent line to l1 or l ′ The angle between l1 and l2 is the yaw angle increment. The angle can be determined by the common tangent direction vector and l1 or l2. ′The angle between the directional vectors is used to determine the position. In this embodiment, the connecting line reflects the relative planar motion offset of the camera origin between two frames of images. The angle between the common tangent and the lane line is the yaw angle increment of the camera itself. After adjusting the camera pose based on this yaw angle increment, the calibrated lane line can be made parallel to the common tangent.

[0128] In some optional embodiments, the method provided in this embodiment may further include:

[0129] Once the target pose information is determined to meet the preset convergence conditions, the current pose information is replaced based on the target pose information.

[0130] Since this embodiment implements real-time automatic correction of the vehicle's pose information from the onboard camera during vehicle operation, the onboard camera may need to be corrected again after a certain period. Therefore, this embodiment sets a time limit within a certain period, where the target pose information replaces the current pose information when the target pose information meets a preset convergence condition, completing a single correction cycle. The preset convergence condition can be set according to the actual scenario. For example, the preset convergence condition is that the difference between two consecutive calculated target pose information is less than a set value, or the time of the set period is reached. In the next cycle, the target pose information corrected in the previous cycle can be used as the current pose information. This achieves real-time pose correction covering the entire usage cycle of vehicle driving in natural scenarios, and is applicable to most driving scenarios.

[0131] Any of the vehicle-mounted camera attitude correction methods provided in this disclosure can be executed by any suitable device with data processing capabilities, including but not limited to: terminal devices and servers. Alternatively, any of the vehicle-mounted camera attitude correction methods provided in this disclosure can be executed by a processor, such as by a processor executing any of the vehicle-mounted camera attitude correction methods mentioned in this disclosure by calling corresponding instructions stored in memory. Further details will not be elaborated below.

[0132] Exemplary device

[0133] Figure 8 This is a schematic diagram of the structure of a vehicle-mounted camera attitude correction device provided in an exemplary embodiment of this application. Figure 8 As shown, the apparatus provided in this embodiment includes:

[0134] Image acquisition module 81 is used to acquire the first image, which includes multiple lane lines, captured by the vehicle-mounted camera.

[0135] The lane line determination module 82 is used to determine the image lane lines in the first image acquired by the image acquisition module 81 in the image coordinate system in response to multiple lane lines meeting preset conditions.

[0136] Each lane line corresponds to one image lane line.

[0137] The initial pose determination module 83 is used to determine the current pose information of the vehicle-mounted camera relative to the vehicle.

[0138] The pose correction module 84 is used to correct at least one attitude angle in the current pose information determined by the initial pose determination module 83 based on the image lane line determined by the lane line determination module 82, so as to obtain the corrected target pose information of the vehicle camera relative to the vehicle.

[0139] Among them, at least one attitude angle includes at least one of the following: pitch angle, roll angle, and yaw angle.

[0140] The vehicle-mounted camera attitude correction device provided in the above embodiments of this disclosure acquires images including multiple lane lines in a natural driving scene during vehicle driving, without depending on a specific scene; and corrects the current pose information of the vehicle-mounted camera relative to the vehicle by at least one attitude angle through the image lane line equations in the image coordinate system corresponding to the image of the multiple lane lines. It only requires known current pose information and does not require too much prior knowledge, and can cover a wide range of driving scenarios.

[0141] Figure 9 This is a schematic diagram of the structure of a vehicle-mounted camera attitude correction device provided in another exemplary embodiment of this application. Figure 9 As shown, in the device provided in this embodiment, optionally, the pose correction module 84 includes:

[0142] The first ground determination unit 841 is used to determine the first ground corresponding to multiple lane lines based on the image lane lines and the current pose information.

[0143] Wherein, the first ground is the initial ground or the first corrected ground corresponding to the current pose information, and the first corrected ground is the ground corresponding to the pose information obtained after correcting the roll angle and / or yaw angle in the current pose information.

[0144] The pitch angle determination unit 842 is used to determine the pitch angle increment based on the origin of the camera coordinate system corresponding to the vehicle camera and the first ground lane line corresponding to each lane line in the first ground.

[0145] The pitch angle correction unit 843 is used to correct the pitch angle in the current pose information based on the pitch angle increment, so as to obtain the target pose information of the vehicle camera relative to the vehicle.

[0146] Optionally, the pitch angle determination unit 842 is specifically used to determine multiple first planes based on the origin of the camera coordinate system and the first ground lane lines corresponding to each lane line in the multiple lane lines; wherein each first plane includes a first ground lane line and the origin of the camera coordinate system; and to determine the pitch angle increment based on the angle between the intersection line of the multiple first planes and the first ground.

[0147] Optionally, the pose correction module 84 may also include:

[0148] The second ground determination unit 844 is used to determine the second ground corresponding to multiple lane lines based on the image lane lines and the current pose information.

[0149] The second ground is either the initial ground or the second corrected ground corresponding to the current pose information. The second corrected ground is the ground corresponding to the pose information obtained after correcting the pitch angle and / or yaw angle in the current pose information.

[0150] The roll angle determination unit 845 is used to determine the roll angle increment based on the origin of the camera coordinate system corresponding to the vehicle camera and the second ground lane lines corresponding to each lane line in the second ground.

[0151] The roll angle correction unit 846 is used to correct the roll angle in the current pose information based on the roll angle increment, so as to obtain the corrected target pose information of the vehicle camera relative to the vehicle.

[0152] Optionally, the roll angle determination unit 845 is specifically used to determine three first intersection points between three adjacent second ground lane lines in the second ground and the vertical plane in the camera coordinate system; determine three simulated lane lines based on the three second ground lane lines and the origin of the camera coordinate system; determine three second intersection points between the three simulated lane lines and the vertical plane in the camera coordinate system; and determine the roll angle increment based on the three first intersection points and the three second intersection points.

[0153] Optionally, when determining the roll angle increment based on three first intersection points and three second intersection points, the roll angle determination unit 845 is used to determine a first line segment based on the three first intersection points; determine two second line segments of equal length based on the three second intersection points; and determine the roll angle increment based on the angle between the first line segment and one of the two second line segments.

[0154] Optionally, the pose correction module 84 may also include:

[0155] The third ground determination unit 847 is used to determine the third ground corresponding to multiple lane lines based on the image lane lines and the current pose information.

[0156] The third ground is either the initial ground or the third corrected ground corresponding to the current pose information. The third corrected ground is the ground corresponding to the pose information obtained after correcting the roll angle and / or pitch angle in the current pose information.

[0157] The yaw angle determination unit 848 is used to determine the yaw angle increment based on the origin of the camera coordinate system corresponding to the vehicle camera and the third ground lane lines corresponding to each lane line in the third ground.

[0158] Yaw angle correction unit 849 is used to correct the yaw angle in the current pose information based on the yaw angle increment, so as to obtain the corrected target pose information of the vehicle camera relative to the vehicle.

[0159] Optionally, the pose correction module 84 is also used to acquire a second image including multiple lane lines captured by the vehicle-mounted camera;

[0160] The yaw angle determination unit 848 is specifically used to determine the fourth ground lane line corresponding to the second image; determine the first projection point of the origin of the camera coordinate system in the third ground corresponding to the first image, and determine the second projection point of the origin of the camera coordinate system in the third ground corresponding to the second image; and determine the yaw angle increment based on the first distance between the first projection point and the third ground lane line, and the second distance between the second projection point and the fourth ground lane line.

[0161] Optionally, the transformation relationship between the ground corresponding to the second image and the third ground is determined by using a motion estimation method to determine the vehicle motion estimation information between the first image and the second image, and the second projection point is determined by using this transformation relationship.

[0162] Optionally, when determining the yaw angle increment based on the first distance between the first projection point and the third ground lane line and the second distance between the second projection point and the fourth ground lane line, the yaw angle determination unit 848 is used to obtain a first arc with the first projection point as the center and the first distance as the radius in the third ground; obtain a second arc with the second projection point as the center and the second distance as the radius; determine the common tangent of the first arc and the second arc; determine the connecting line between the first projection point and the second projection point; and determine the yaw angle increment based on the angle between the common tangent and the lane line.

[0163] Optionally, the preset conditions may include, but are not limited to, at least one of the following:

[0164] Multiple lane lines are non-curved, the number of lane lines is greater than or equal to the set number, and the spacing between lane lines is the same.

[0165] Optionally, the apparatus provided in this embodiment further includes:

[0166] The pose replacement module 85 is used to determine that the target pose information meets the preset convergence conditions and replace the current pose information based on the target pose information of the pose correction module 84.

[0167] Exemplary electronic devices

[0168] Below, for reference Figure 10 This describes an electronic device according to embodiments of the present application. The electronic device may be either or both of a first device 100 and a second device 200, or a standalone device independent of them, which may communicate with the first and second devices to receive acquired input signals from them.

[0169] Figure 10 A block diagram of an electronic device according to an embodiment of this application is illustrated.

[0170] like Figure 10 As shown, the electronic device 10 includes one or more processors 11 and memory 12.

[0171] The processor 11 may be a central processing unit (CPU) or other form of processing unit with data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device 10 to perform desired functions.

[0172] The memory 12 may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory. The non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 11 may execute the program instructions to implement the vehicle-mounted camera attitude correction methods of the various embodiments of this application described above, and / or other desired functions. Various contents such as input signals, signal components, and noise components may also be stored in the computer-readable storage medium.

[0173] In one example, the electronic device 10 may also include an input device 13 and an output device 14, which are interconnected via a bus system and / or other forms of connection mechanism (not shown).

[0174] For example, when the electronic device is a first device 100 or a second device 200, the input device 13 can be the aforementioned microphone or microphone array for capturing the input signal from the sound source. When the electronic device is a standalone device, the input device 13 can be a communication network connector for receiving the acquired input signals from the first device 100 and the second device 200.

[0175] In addition, the input device 13 may also include, for example, a keyboard, a mouse, etc.

[0176] The output device 14 can output various information to the outside, including determined distance information, direction information, etc. The output device 14 may include, for example, a display, a speaker, a printer, and a communication network and its connected remote output devices, etc.

[0177] Of course, for the sake of simplicity, Figure 10 Only some of the components of the electronic device 10 relevant to this application are shown in this illustration; components such as buses, input / output interfaces, etc., are omitted. In addition, the electronic device 10 may include any other suitable components depending on the specific application.

[0178] Exemplary computer program products and computer-readable storage media

[0179] In addition to the methods and devices described above, embodiments of this application may also be computer program products, which include computer program instructions that, when executed by a processor, cause the processor to perform the steps in the vehicle camera attitude correction methods according to various embodiments of this application described in the "Exemplary Methods" section of this specification.

[0180] The computer program product can be written in any combination of one or more programming languages ​​to perform the operations of the embodiments of this application. The programming languages ​​include object-oriented programming languages ​​such as Java and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0181] Furthermore, embodiments of this application may also be computer-readable storage media storing computer program instructions thereon, which, when executed by a processor, cause the processor to perform the steps in the vehicle camera attitude correction method according to various embodiments of this application described in the "Exemplary Methods" section above.

[0182] The computer-readable storage medium may be any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may, for example, include, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: electrical connections having one or more wires, portable disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0183] The basic principles of this application have been described above with reference to specific embodiments. However, it should be noted that the advantages, benefits, and effects mentioned in this application are merely examples and not limitations, and should not be considered as essential features of each embodiment of this application. Furthermore, the specific details disclosed above are for illustrative and facilitative purposes only, and are not limitations. These details do not limit the application to the necessity of employing the aforementioned specific details for implementation.

[0184] The block diagrams of devices, apparatuses, devices, and systems involved in this application are merely illustrative examples and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. As those skilled in the art will recognize, these devices, apparatuses, devices, and systems can be connected, arranged, and configured in any manner. Words such as “comprising,” “including,” “having,” etc., are open-ended terms meaning “including but not limited to,” and are used interchangeably with them. The terms “or” and “and” as used herein refer to the terms “and / or,” and are used interchangeably with them unless the context clearly indicates otherwise. The term “such as” as used herein refers to the phrase “such as but not limited to,” and is used interchangeably with it.

[0185] It should also be noted that in the apparatus, equipment, and methods of this application, the components or steps can be disassembled and / or recombined. These disassemblies and / or recombinations should be considered as equivalent solutions of this application.

[0186] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use this application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein can be applied to other aspects without departing from the scope of this application. Therefore, this application is not intended to be limited to the aspects shown herein, but rather to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0187] The above description has been given for purposes of illustration and description. Furthermore, this description is not intended to limit the embodiments of this application to the forms disclosed herein. Although numerous exemplary aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and sub-combinations thereof.

Claims

1. A method for vehicle camera pose rectification, comprising: acquiring, by a vehicle camera, images of a plurality of lane lines to obtain a first image; in response to the plurality of lane lines meeting a preset condition, determining, for each lane line of the plurality of lane lines, a corresponding image lane line in an image coordinate system; determining current pose information of the vehicle camera relative to a vehicle; rectifying, based on the image lane lines, at least one attitude angle in the current pose information to obtain target pose information of the vehicle camera relative to the vehicle after rectification; wherein the attitude angle comprises at least one of a pitch angle, a roll angle, and a yaw angle; and rectifying, based on the image lane lines, at least one attitude angle in the current pose information to obtain target pose information of the vehicle camera relative to the vehicle after rectification, comprises: determining, based on the image lane lines and the current pose information, a first ground surface corresponding to the plurality of lane lines; determining a pitch angle increment based on an included angle between an intersection of a plurality of first planes and the first ground surface; rectifying, based on the pitch angle increment, a pitch angle in the current pose information to obtain target pose information of the vehicle camera relative to the vehicle after rectification; and / or determining, based on the image lane lines and the current pose information, a second ground surface corresponding to the plurality of lane lines; determining a roll angle increment by simulating an included angle between a lane line and a second ground surface equation corresponding to a second ground lane line of each lane line of the plurality of lane lines in the second ground surface, based on an origin of a camera coordinate system corresponding to the vehicle camera and the second ground lane line; rectifying, based on the roll angle increment, a roll angle in the current pose information to obtain target pose information of the vehicle camera relative to the vehicle after rectification; and / or determining, based on the image lane lines and the current pose information, a third ground surface corresponding to the plurality of lane lines; determining a yaw angle increment based on distances between two projection points and corresponding third ground lane lines and fourth ground lane lines of each lane line of the plurality of lane lines in the third ground surface, based on an origin of a camera coordinate system corresponding to the vehicle camera and the third ground lane line; rectifying, based on the yaw angle increment, a yaw angle in the current pose information to obtain target pose information of the vehicle camera relative to the vehicle after rectification. 2.The method of claim 1, wherein: the first ground surface is an initial ground surface corresponding to the current pose information or a first rectified ground surface corresponding to the current pose information after rectification of a roll angle and / or a yaw angle in the current pose information; and before determining the pitch angle increment based on the included angle between the intersection of the plurality of first planes and the first ground surface, the method further comprises: determining a plurality of first planes based on the origin of the camera coordinate system and the first ground lane line corresponding to each lane line of the plurality of lane lines; wherein each first plane comprises the first ground lane line and the origin of the camera coordinate system. ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ 3. The method of claim 2, wherein, ​ ​ 4. The method according to any one of claims 1 to 3, wherein, The second ground is an initial ground corresponding to the current pose information or a second corrected ground, and the second corrected ground is a ground corresponding to pose information obtained after correcting a pitch angle and / or a yaw angle in the current pose information.

5. The method of claim 4, wherein, The determining of the roll angle increment based on the origin of the camera coordinate system corresponding to the vehicle-mounted camera and the second ground lane corresponding to each lane in the plurality of lane lines in the second ground, by simulating an included angle between the lane line and the second ground lane, comprises: determining three first intersection points of adjacent three second ground lanes in the second ground and a vertical plane in the camera coordinate system; determining three simulated lane lines based on the three second ground lanes and the origin of the camera coordinate system; determining three second intersection points of the three simulated lane lines and the vertical plane in the camera coordinate system; determining the roll angle increment based on the three first intersection points and the three second intersection points.

6. The method of claim 5, wherein, The determining of the roll angle increment based on the three first intersection points and the three second intersection points, comprises: determining a first line segment based on the three first intersection points; determining two equal-length second line segments based on the three second intersection points; determining the roll angle increment based on an included angle between the first line segment and any one of the two equal-length second line segments.

7. The method of any one of claims 1-3, wherein, The third ground is an initial ground corresponding to the current pose information or a third corrected ground, and the third corrected ground is a ground corresponding to pose information obtained after correcting a roll angle and / or a pitch angle in the current pose information.

8. The method of claim 7, further comprising: acquiring a second image based on the vehicle-mounted camera collecting the plurality of lane lines; The two projection points include a first projection point and a second projection point, and the determining of the yaw angle increment based on the origin of the camera coordinate system corresponding to the vehicle-mounted camera and the third ground lane and the fourth ground lane corresponding to the plurality of lane lines in the third ground, comprises: determining a fourth ground lane corresponding to the second image; determining the first projection point of the origin of the camera coordinate system in the third ground corresponding to the first image, and determining the second projection point of the origin of the camera coordinate system in the third ground corresponding to the second image; determining the yaw angle increment based on a first distance between the first projection point and the third ground lane, and a second distance between the second projection point and the fourth ground lane.

9. The method of claim 8, wherein, The determining of the yaw angle increment based on the first distance between the first projection point and the third ground lane, and the second distance between the second projection point and the fourth ground lane, comprises: in the third ground, a first circular arc is obtained with the first projection point as the center and the first distance as the radius, and a second circular arc is obtained with the second projection point as the center and the second distance as the radius; determine a tangent line of the first arc and the second arc, and determine a connection line of the first projection point and the second projection point; determine the yaw angle increment based on an included angle between the tangent line and the connection line.

10. The method of any one of claims 1-3, wherein, The preset condition includes: The plurality of lane lines are non-bend lanes, the number of the lane lines is greater than or equal to a set number, and the intervals between the lane lines are the same.

11. The method of any one of claims 1-3, further comprising: determining that the target pose information meets a preset convergence condition, and replacing the current pose information based on the target pose information.

12. A vehicle-mounted camera pose rectification apparatus, comprising: an image acquisition module configured to acquire a first image including a plurality of lane lines captured by a vehicle-mounted camera; a lane line determination module configured to, in response to the plurality of lane lines meeting a preset condition, determine image lane lines of the plurality of lane lines in the first image acquired by the image acquisition module in an image coordinate system, wherein each lane line corresponds to an image lane line; an initial pose determination module configured to determine current pose information of the vehicle-mounted camera relative to a vehicle; a pose rectification module configured to rectify at least one attitude angle in the current pose information determined by the initial pose determination module based on the image lane lines determined by the lane line determination module, to obtain target pose information of the vehicle-mounted camera relative to the vehicle after rectification, wherein the at least one attitude angle includes at least one of a pitch angle, a roll angle, and a yaw angle; the pose rectification module includes: a first ground determination unit configured to determine a first ground corresponding to the plurality of lane lines based on the image lane lines and the current pose information; a pitch angle determination unit configured to determine a pitch angle increment based on an included angle between intersection lines of a plurality of first planes and the first ground; a pitch angle rectification unit configured to rectify the pitch angle in the current pose information based on the pitch angle increment, to obtain the target pose information of the vehicle-mounted camera relative to the vehicle after rectification; and / or a second ground determination unit configured to determine a second ground corresponding to the plurality of lane lines based on the image lane lines and the current pose information; a roll angle determination unit configured to determine a roll angle increment based on an origin of a camera coordinate system corresponding to the vehicle-mounted camera and second ground lane lines corresponding to each lane line in the plurality of lane lines in the second ground, by simulating an included angle between the lane lines and second ground equations corresponding to the second ground lane lines; a roll angle rectification unit configured to rectify the roll angle in the current pose information based on the roll angle increment, to obtain the target pose information of the vehicle-mounted camera relative to the vehicle after rectification; and / or a third ground determination unit configured to determine a third ground corresponding to the plurality of lane lines based on the image lane lines and the current pose information. The yaw angle determination unit is configured to determine a yaw angle increment based on a distance between two projection points and corresponding third ground lane line and fourth ground lane line, respectively, wherein the two projection points are determined based on an origin of a camera coordinate system corresponding to the vehicle-mounted camera and the third ground lane line and the fourth ground lane line, respectively, corresponding to each lane line in the plurality of lane lines in the third ground. The yaw angle correction unit is configured to correct a yaw angle in the current pose information based on the yaw angle increment to obtain target pose information of the vehicle-mounted camera relative to the vehicle. 13.A computer readable storage medium, the storage medium storing a computer program, the computer program being configured to execute the vehicle-mounted camera pose correction method according to any one of claims 1-11. 14.An electronic device, comprising: a processor; a memory configured to store instructions executable by the processor; the processor is configured to read the executable instructions from the memory and execute the instructions to implement the vehicle-mounted camera pose correction method according to any one of claims 1-11.

Images