Lane line determination method, device, electronic device and storage medium

Abstract

The disclosed embodiments disclose a lane line determination method, apparatus, electronic device, and storage medium, wherein the method includes: determining first lane line curve parameters of a target lane in a vehicle coordinate system based on image segmentation results of a target image; determining a target width of the target lane based on the first lane line curve parameters; determining first lane line point pairs corresponding to each first transverse intercept of at least one first transverse intercept corresponding to the target lane in the vehicle coordinate system based on the first lane line curve parameters and the target width, wherein the first lane line point pairs include a first endpoint of the first transverse intercept at a first side lane line of the target lane and a second endpoint of the first transverse intercept at a second side lane line of the target lane; and determining the lane line of the target lane based on the first lane line point pairs. The disclosed embodiments can effectively reduce errors caused by road bumps, changes in road slope, and the like. Compared with dynamic estimation of camera extrinsic parameters, the disclosed embodiments can effectively improve the accuracy of lane lines.

Description

Technical Field

[0001] The present disclosure relates to computer vision technology, and in particular to a method, device, electronic device, and storage medium for determining lane lines. Background Art

[0002] In autonomous driving technology, lane line fitting is an important link. Lane line fitting requires accurate lane line sampling point positions in the vehicle coordinate system. When lane line sampling is implemented based on monocular camera observation of lane lines, the lane line sampling points on the image coordinate system are mapped to the vehicle coordinate system based on pre-calibrated camera extrinsics. However, the ranging of monocular cameras is easily affected by road conditions, such as road bumps, ups and downs, etc., resulting in large errors in ranging, which in turn cause lane line fitting abnormalities. To address this problem, related technologies usually use dynamic estimation of camera extrinsics to reduce the impact of road bumps on lane line fitting. However, dynamic estimation of camera extrinsics can only optimize the errors caused by road bumps, but cannot reduce the errors caused by slope changes. Therefore, the lane line accuracy obtained by the dynamic estimation method of camera extrinsics is poor. Summary of the Invention

[0003] In order to solve the above-mentioned technical problems such as poor accuracy of the obtained lane lines, the present disclosure is proposed. The embodiments of the present disclosure provide a method, apparatus, electronic device and storage medium for determining lane lines.

[0004] According to one aspect of an embodiment of the present disclosure, a method for determining a lane line is provided, including: determining a first lane line curve parameter of a target lane in a vehicle coordinate system based on an image segmentation result of a target image, wherein the first lane line curve parameter is a cubic curve coefficient of a lane line fitting the target lane; determining a target width of the target lane based on the first lane line curve parameter; determining a first lane line point pair corresponding to each of at least one first transverse intercept corresponding to the target lane in the vehicle coordinate system based on the first lane line curve parameter and the target width, wherein the first lane line point pair includes a first end point of the first transverse intercept at a first side lane line of the target lane and a second end point of the first transverse intercept at a second side lane line of the target lane; determining the lane line of the target lane based on the first lane line point pair.

[0005] According to another aspect of an embodiment of the present disclosure, a lane line determination device is provided, including: a first determination module, for determining a first lane line curve parameter of a target lane in a vehicle coordinate system based on an image segmentation result of a target image, wherein the first lane line curve parameter is a cubic curve coefficient of a lane line fitting the target lane; a first processing module, for determining a target width of the target lane based on the first lane line curve parameter; a second processing module, for determining a first lane line point pair corresponding to each first transverse intercept of at least one first transverse intercept corresponding to the target lane in the vehicle coordinate system based on the first lane line curve parameter and the target width, wherein the first lane line point pair includes a first end point of the first transverse intercept at a first side lane line of the target lane and a second end point of the first transverse intercept at a second side lane line of the target lane; and a third processing module, for determining the lane line of the target lane based on the first lane line point pair.

[0006] According to another aspect of the embodiments of the present disclosure, a computer-readable storage medium is provided, wherein the storage medium stores a computer program, and the computer program is used to execute the lane line determination method described in any of the above embodiments of the present disclosure.

[0007] According to another aspect of an embodiment of the present disclosure, an electronic device is provided, comprising: a processor; a memory for storing instructions executable by the processor; and the processor for reading the executable instructions from the memory and executing the instructions to implement the lane line determination method described in any of the above embodiments of the present disclosure.

[0008] Based on the lane line determination method, device, electronic device and storage medium provided by the above-mentioned embodiments of the present disclosure, when determining the lane line, the initial lane line curve parameters in the vehicle coordinate system are determined based on the image segmentation results. The lane width is determined based on the fact that the initial lane line curve parameters and the road conditions have little impact on proximal observations. Then, based on the lane width and the initial lane line curve parameters, the lane line point pairs corresponding to the actual transverse intercept are calculated, so that accurate lane lines can be directly fitted, which solves the problem that the existing technology cannot reduce the error caused by road slope changes through dynamic estimation of camera extrinsic parameters, resulting in poor accuracy of the obtained lane lines.

[0009] The technical solution of the present disclosure is further described in detail below through the accompanying drawings and examples. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The above and other purposes, features, and advantages of the present disclosure will become more apparent through a more detailed description of the embodiments of the present disclosure in conjunction with the accompanying drawings. The accompanying drawings are intended to provide a further understanding of the embodiments of the present disclosure and constitute a part of the specification. Together with the embodiments of the present disclosure, they are used to explain the present disclosure and are not intended to limit the present disclosure. In the drawings, the same reference numerals generally represent the same components or steps.

[0011] Figure 1 This is an exemplary application scenario of the lane line determination method provided by the present disclosure;

[0012] Figure 2 is a flowchart of a method for determining a lane line provided by an exemplary embodiment of the present disclosure;

[0013] Figure 3 is a schematic diagram of a first lane line point pair provided by an exemplary embodiment of the present disclosure;

[0014] Figure 4 is a flowchart of a lane line determination method provided by another exemplary embodiment of the present disclosure;

[0015] Figure 5 is a schematic diagram of a third lane line point pair obtained by sampling provided by an exemplary embodiment of the present disclosure;

[0016] Figure 6 is a flowchart of step 2033 provided by an exemplary embodiment of the present disclosure;

[0017] Figure 7 is an imaging relationship of a road transverse intercept in an image in a camera coordinate system provided by an exemplary embodiment of the present disclosure;

[0018] Figure 8 is a schematic diagram of the relationship between a camera coordinate system and a vehicle coordinate system provided by an exemplary embodiment of the present disclosure;

[0019] Figure 9 is a flowchart of step 2013 provided by an exemplary embodiment of the present disclosure;

[0020] Figure 10 is a schematic structural diagram of a lane line determination device provided by an exemplary embodiment of the present disclosure;

[0021] Figure 11 is a structural diagram of a first processing module 502 provided by an exemplary embodiment of the present disclosure;

[0022] Figure 12 is a structural diagram of a second processing module 503 provided by an exemplary embodiment of the present disclosure;

[0023] Figure 13is a structural diagram of a fifth processing unit 5033 provided by an exemplary embodiment of the present disclosure;

[0024] Figure 14 is a structural diagram of a first determining module 501 provided by an exemplary embodiment of the present disclosure;

[0025] Figure 15 is a structural diagram of the third determining unit 5013 of the first determining module provided by an exemplary embodiment of the present disclosure;

[0026] Figure 16 It is a structural diagram of an application embodiment of the electronic device disclosed in the present invention. DETAILED DESCRIPTION

[0027] Below, the exemplary embodiments according to the present disclosure will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present disclosure, rather than all the embodiments of the present disclosure, and it should be understood that the present disclosure is not limited to the exemplary embodiments described herein.

[0028] It should be noted that the relative arrangement of components and steps, the numerical expressions and numerical values ​​set forth in these embodiments do not limit the scope of the present disclosure unless specifically stated otherwise.

[0029] Those skilled in the art will understand that the terms "first" and "second" in the embodiments of the present disclosure are only used to distinguish different steps, devices or modules, and do not represent any specific technical meanings, nor do they indicate a necessary logical order between them.

[0030] It should also be understood that in the embodiments of the present disclosure, “a plurality of” may refer to two or more than two, and “at least one” may refer to one, two, or more than two.

[0031] It should also be understood that any component, data or structure mentioned in the embodiments of the present disclosure can generally be understood as one or more, unless explicitly limited or otherwise indicated in the context.

[0032] In addition, the term "and / or" in this disclosure is merely a description of the association relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent three situations: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " in this disclosure generally indicates that the related objects are in an "or" relationship.

[0033] It should also be understood that the description of the various embodiments in this disclosure focuses on the differences between the various embodiments, and the same or similar aspects thereof can be referenced with each other. For the sake of brevity, they will not be described one by one.

[0034] At the same time, it should be understood that for the convenience of description, the sizes of the various parts shown in the drawings are not drawn according to the actual proportional relationship.

[0035] The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the present disclosure, its application, or uses.

[0036] Technologies, methods, and equipment known to ordinary technicians in the relevant art may not be discussed in detail, but where appropriate, the technologies, methods, and equipment should be considered part of the specification.

[0037] It should be noted that like reference numerals and letters refer to like items in the following figures, and therefore, once an item is defined in one figure, it need not be further discussed in subsequent figures.

[0038] The embodiments of the present disclosure can be applied to electronic devices such as terminal devices, computer systems, and servers, and can operate in conjunction with numerous other general-purpose or specialized computing system environments or configurations. Examples of well-known terminal devices, computing systems, environments, and / or configurations suitable for use with terminal devices, computer systems, servers, and other electronic devices 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 personal computers, minicomputer systems, mainframe computer systems, and distributed cloud computing technology environments including any of the above systems, among others.

[0039] 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. Generally, 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 a distributed cloud computing environment, where tasks are performed by remote processing devices linked via a communication network. In a distributed cloud computing environment, program modules can be located on local or remote computing system storage media, including storage devices.

[0040] Overview of the Disclosure

[0041] In the process of implementing the present disclosure, the inventors discovered that lane line fitting is an important link in autonomous driving technology. Lane line fitting requires accurate lane line sampling point positions in the vehicle coordinate system. When lane line sampling is implemented based on monocular camera observation of lane lines, the lane line sampling points in the image coordinate system are mapped to the vehicle coordinate system based on pre-calibrated camera extrinsics. However, the ranging of a monocular camera is easily affected by road conditions, such as road bumps, ups and downs, etc., resulting in large errors in ranging, thereby causing lane line fitting abnormalities. To address this problem, related technologies usually reduce the impact of road bumps on lane line fitting through dynamic estimation of camera extrinsics (such as pitch angle). However, the dynamic estimation of camera extrinsics can only optimize the errors caused by road bumps, but cannot reduce the errors caused by slope changes. Therefore, the lane line accuracy obtained by the method of dynamic estimation of camera extrinsics is poor.

[0042] Exemplary Overview

[0043] Figure 1 This is an exemplary application scenario of the lane line determination method provided by the present disclosure. In an autonomous driving scenario, using the lane line determination method of the present disclosure, the first lane line curve parameters of the target lane (such as the main lane where the vehicle is located) in the vehicle coordinate system can be determined based on the segmentation results of the monocular image. The principle that the road slope and vehicle motion have little effect on the proximal lane line sampling points can be used to determine the width of the proximal target lane based on the first lane line curve parameters as the target width of the target lane. According to the principle that the lane width is constant, based on the target width combined with the first lane line curve parameters, a more accurate lane line sampling point (i.e., the first lane line point pair) is determined, thereby determining the lane line of the target lane based on the lane line sampling points. This can not only effectively reduce the error caused by road bumps, but also effectively reduce the error caused by road conditions such as changes in the slope of the road surface, effectively improve the accuracy of the lane line, and solve the problem that the existing technology cannot reduce the error caused by changes in road slope through dynamic estimation of camera extrinsic parameters, resulting in poor accuracy of the obtained lane line. Wherein, xoy represents an exemplary vehicle coordinate system, with the center of the vehicle's rear axle as the coordinate origin, the vehicle's forward direction as the longitudinal axis (x-axis), and the vehicle's width to the right as the horizontal axis (y-axis). In practical applications, any feasible vehicle coordinate system can be used, such as the vehicle coordinate system defined by the ISO international standard, with the center of the vehicle's rear axle as the coordinate origin, the vehicle's forward direction as the longitudinal axis (x-axis), and the vehicle's width to the left as the horizontal axis (y-axis). This disclosure does not limit this.

[0044] Exemplary Methods

[0045] Figure 2This is a flow chart of a lane line determination method provided by an exemplary embodiment of the present disclosure. This embodiment can be applied to electronic devices, such as vehicle-mounted computing platforms, such as Figure 2 As shown, the following steps are included:

[0046] Step 201 : Determine first lane line curve parameters of a target lane in a vehicle coordinate system based on an image segmentation result of a target image. The first lane line curve parameters are cubic curve coefficients of a lane line fitting the target lane.

[0047] Among them, the target image can be an image taken by a forward-facing camera or camera set on the vehicle. For example, in an autonomous driving scenario, it can be the current frame image taken by the camera. The image segmentation result of the target image may include the segmentation type to which each pixel on the target image belongs. The segmentation type can be set according to actual needs. For example, the segmentation type may include at least one of lane lines, curbs, sidewalks, and other possible types. Based on the image segmentation result, all pixel points on the target image that belong to the lane line can be determined. The vehicle coordinate system is a coordinate system with a preset point on the vehicle (such as the center of the rear axle of the vehicle) as the coordinate origin, the longitudinal direction of the vehicle as the x-axis (vertical axis), and the width direction of the vehicle as the y-axis (horizontal axis), see Figure 1 The xoy coordinate system in the image. The target lane can be any lane of the road where the vehicle is located, such as the main lane where the vehicle is located, and can be set according to actual needs. Based on the mapping relationship between the pixel coordinate system of the image and the vehicle coordinate system (based on the mapping relationship of the pre-calibrated camera parameters), the pixel points belonging to the lane line are mapped to the vehicle coordinate system, and the lane line sampling points in the vehicle coordinate system can be determined. Based on the positional relationship between the lane line sampling points and the vehicle, the lane line sampling points of the target lane can be determined, so that the first lane line curve parameters of the target lane can be obtained by fitting. The first lane line curve parameters may include the lane line curve parameters corresponding to the lane lines on both sides of the target lane.

[0048] For example, the curve parameters of the first side lane line (such as the left lane line) of the target lane include Then the cubic curve of the left lane line in the vehicle coordinate system can be expressed as:

[0049]

[0050] Among them, x represents the vertical coordinate of the lane line in the vehicle coordinate system, and y represents the horizontal coordinate of the lane line in the vehicle coordinate system.

[0051] Step 202: Determine a target width of a target lane based on the first lane curve parameter.

[0052] The target width is the width of the target lane. The target width of the target lane can be determined based on the condition of the lane curve corresponding to the first lane curve parameter at the vehicle's near end, based on the assumption that the road slope and vehicle motion have negligible effects on the near end of the lane curve.

[0053] For example, the target width of the target lane can be determined based on the intersection of a straight line perpendicular to the longitudinal axis of the vehicle coordinate system and the lane line curves on both sides at a preset distance in front of the vehicle (the distance between the two intersection points is called the transverse intercept), and the angle between the straight line and the width direction of the target lane.

[0054] Step 203, based on the first lane line curve parameters and the target width, determine the first lane line point pairs corresponding to each first transverse intercept in at least one first transverse intercept corresponding to the target lane in the vehicle coordinate system, the first lane line point pair including the first end point of the first transverse intercept at the first side lane line of the target lane and the second end point of the first transverse intercept at the second side lane line of the target lane.

[0055] The at least one first transverse intercept is a transverse intercept at at least one position along the longitudinal axis of the vehicle coordinate system, from near to far. Because the first lane line point pair includes the first endpoint of the first transverse intercept at the first side lane line and the second endpoint at the second side lane line of the target lane, the first lane line point pair can be used as the sampling points for the lane lines on both sides of the determined target lane.

[0056] For example, Figure 3 This is a schematic diagram of the first lane line point pair provided by an exemplary embodiment of the present disclosure. The dotted line represents the extension line of the longitudinal axis of the vehicle coordinate system, BC_1i represents the i-th (i=1, 2, ..., N) first transverse intercept, and N represents the number of first transverse intercepts, which can be set according to actual needs. 1i and C 1i Represent the first endpoint and the second endpoint of the i-th first lane line point pair respectively.

[0057] Step 204 : Determine the lane line of the target lane based on the first lane line point pair.

[0058] Among them, the first lane line point pair includes sampling points on the lane lines on both sides of the target lane. The first side lane line of the target lane can be obtained by fitting each first endpoint in the first lane line point pair. Similarly, the second side lane line of the target lane can be obtained by fitting each second endpoint in the first lane line point pair. The lane line of the target lane obtained can also be represented by a cubic curve. Compared with the first lane line curve determined by the above-mentioned first lane line curve parameters, the lane line of the target lane finally determined by the present disclosure is optimized based on the constant lane width. The sampling points of the first lane line curve are reduced, which reduces the influence of road slope or bumps on the accuracy of the sampling points of the first lane line curve, making the optimized lane line sampling points closer to the real lane line, so that the obtained lane line is more accurate and stable, and effectively solves the problem that the dynamic estimation of camera extrinsic parameters cannot optimize the error caused by road slope changes.

[0059] The lane line determination method provided in this embodiment determines the initial lane line curve parameters in the vehicle coordinate system based on the image segmentation results when determining the lane line, determines the lane width based on the fact that the initial lane line curve parameters and the road conditions have little influence on the near-end observation, and then calculates the lane line point pair corresponding to the actual cross-intercept based on the lane width and the initial lane line curve parameters, thereby determining a more accurate lane line. This method can not only effectively reduce the error caused by road bumps, but also effectively reduce the error caused by road conditions such as changes in the slope of the road surface, effectively improve the accuracy of the lane line, and solve the problem that the existing technology cannot reduce the error caused by changes in road slope through dynamic estimation of camera extrinsic parameters, resulting in poor accuracy of the obtained lane line.

[0060] Figure 4 It is a flowchart of a lane line determination method provided by another exemplary embodiment of the present disclosure.

[0061] In an optional example, determining the target width of the target lane based on the first lane curve parameter in step 202 may specifically include the following steps:

[0062] Step 2021: Determine a second transverse intercept on the target lane at a first preset distance from the vehicle based on the first lane line curve parameter.

[0063] Among them, the first preset distance can be set according to actual needs. Specifically, it can be set to a distance closer to the vehicle, such as 10 meters, 11 meters, 15 meters in front of the vehicle, etc., based on the situation that the road conditions have little impact on near-end observation. There is no specific limitation. The second horizontal intercept is similar to the above-mentioned first horizontal intercept. Taking 10 meters as an example, the distance between the vertical line (perpendicular to the vertical axis) at x = 10 meters on the vertical axis of the vehicle coordinate system and the intersection of the lane line curves on both sides of the first lane line curve is called the second horizontal intercept.

[0064] Step 2022: Determine the target width of the target lane based on the second transverse intercept.

[0065] Among them, the straight line where the second transverse intercept is located has a certain angle with the width direction of the target lane at x = 10 meters. This angle can be obtained by the first lane line curve determined by the first lane line curve parameters. Therefore, combining the second transverse intercept and this angle can determine the lane width at this location, and then based on the principle that the lane width remains unchanged, this lane width is used as the target width of the target lane.

[0066] In an optional example, the target width can also be determined by integrating multiple frame images to improve the accuracy of the target width. For example, the current frame image and a certain number of historical frame images before the current one are integrated, and each frame image determines the width of a target lane according to the above process. Multiple frame images determine multiple widths, and the average of the multiple widths is used as the target width. The specific setting can be based on actual needs.

[0067] In an optional example, step 203 of determining, based on the first lane line curve parameter and the target width, first lane line point pairs corresponding to respective first transverse intercepts of at least one first transverse intercept corresponding to the target lane in the vehicle coordinate system includes:

[0068] Step 2031 : Based on the first lane line curve parameter, determine a third lane line point pair corresponding to each third transverse intercept in at least one third transverse intercept corresponding to the target lane in the vehicle coordinate system.

[0069] Among them, at least one third transverse intercept is obtained by sampling from near to far along the longitudinal axis of the vehicle coordinate system. For example, the transverse intercepts at x=10 meters, x=15 meters, x=20 meters, x=25 meters, and x=30 meters along the longitudinal axis are used as the third transverse intercepts. The third lane line point pair corresponding to the third transverse intercept includes the endpoints on the lane lines on both sides of the first lane line curve corresponding to the first lane line curve parameters. The number of third transverse intercepts can be set according to actual needs. Specifically, the number of third transverse intercepts can be determined based on the sampling interval and the far-end constraint of the first lane line curve. The far end of the first lane line curve is determined by the pixel points of the lane line belonging to the target lane in the image segmentation result.

[0070] For example, Figure 5 This is a schematic diagram of the third lane line point pair obtained by sampling provided by an exemplary embodiment of the present disclosure. Among them, BC_3i represents the i-th (i=1, 2, ..., N) third transverse intercept, N represents the number of third transverse intercepts, which is the same as the number of first transverse intercepts and can be set according to actual needs. 3i and C 3i Represents the i-th third lane line point pair.

[0071] Step 2032: Based on each third lane line point pair, determine the fourth lane line point pair corresponding to each third transverse intercept in the image coordinate system.

[0072] The fourth lane line point pair is obtained by mapping the third lane line point pair to the image coordinate system according to the mapping relationship between the vehicle coordinate system and the image coordinate system. The mapping from the vehicle coordinate system to the image coordinate system in this step is the inverse mapping from the image coordinate system to the vehicle coordinate system described above, and is achieved based on pre-calibrated camera extrinsics.

[0073] Step 2033: Determine each first lane line point pair based on each fourth lane line point pair and the target width.

[0074] Specifically, each first lane line point pair can be determined based on a preset calculation rule. Based on the difference between the vehicle coordinate system and the camera coordinate system, the relationship between the camera coordinate system and the image coordinate system, and the principle of camera imaging, a calculation rule for converting point pairs in the image coordinate system to first lane line point pairs can be pre-determined and used as the preset calculation rule. The first lane line point pair can then be solved based on each fourth lane line point pair, the target width, and the preset calculation rule. This solves the problem of being unaffected by road conditions and effectively improves the accuracy of lane line sampling points.

[0075] The present disclosure determines the initial lane line sampling points (third lane line point pairs) in the vehicle coordinate system through the first lane line curve, maps them back to the image coordinate system, and determines the operation rules for the sampling points in the image coordinate system and the real lane line point pairs based on the difference between the vehicle coordinate system and the camera coordinate system, and the relationship between the camera coordinate system and the image coordinate system. Based on the pre-acquired operation rules, each first lane line point pair is solved as the lane line sampling points of the final target lane.

[0076] Figure 6 It is a flowchart of step 2033 provided by an exemplary embodiment of the present disclosure.

[0077] In an optional example, determining each first lane line point pair based on each fourth lane line point pair and the target width in step 2033 includes:

[0078] Step 20331: Convert each fourth lane line point pair to the camera coordinate system to obtain the fifth lane line point pair corresponding to each fourth lane line point pair.

[0079] The fourth lane line point pair is transformed from the image coordinate system to the camera coordinate system based on the mapping relationship between the image coordinate system and the camera coordinate system. The specific principle is not repeated here. The fifth lane line point pair is the corresponding transverse intercept point pair of the fourth lane line point pair in the camera coordinate system.

[0080] Step 20332: Based on the first lane line curve parameters, determine the first angles between the transverse intercept directions of each fourth lane line point pair in the vehicle coordinate system and the corresponding road width direction.

[0081] The first angle can be determined by the correspondence between the fourth lane line point pair and the third lane line point pair, and the transverse intercept direction of the third lane line point pair and the road width direction. The first angle is equivalent to the angle between the longitudinal axis of the vehicle coordinate system and the road direction at the corresponding position (the transverse intercept position of the third lane line point pair). The road direction can be determined based on the first lane line curve. For example, the first lane line curve includes the lane line curves on both sides of the target lane. The curve parameters of the two lane line curves can be averaged to obtain the middle curve of the road. The middle curve is then differentiated to obtain the angle between the road direction and the longitudinal axis of the vehicle coordinate system. The specific principles will not be repeated here.

[0082] Step 20333: Determine the target transverse intercepts corresponding to each fourth lane line point pair based on the target width and each first angle.

[0083] The target transverse intercept is a more accurate transverse intercept determined based on the determined target width and the first angle between the width and the transverse intercept. It has a one-to-one correspondence with the initially collected third transverse intercept. After determining the first angle corresponding to each fourth lane line point pair and the target width of the target lane, the target transverse intercept corresponding to each fourth lane line point pair can be determined based on the target width and each first angle.

[0084] Step 20334: Determine the target lane line point pairs for each first lane line point pair in the camera coordinate system based on each fifth lane line point pair and the target transverse intercept corresponding to each fifth lane line point pair.

[0085] The target transverse intercept corresponding to the fifth lane point pair is the target transverse intercept corresponding to the fourth lane point pair corresponding to the fifth lane point pair. The target lane point pair can be determined based on pre-determined solution rules. For example, the solution rule for determining the target lane point pair in the camera coordinate system is determined based on the imaging relationship of the road transverse intercept in the image, the angle between the road transverse intercept and the imaging plane, and the distance relationship between the camera coordinate system origin and the road transverse intercept vector.

[0086] Step 20335: Convert each target lane line point pair to the vehicle coordinate system to obtain each first lane line point pair.

[0087] The target lane line point pairs obtained are point pairs in the camera coordinate system, which need to be converted to the vehicle coordinate system to obtain the first lane line point pair.

[0088] The present invention determines the actual transverse intercept (target transverse intercept) through the angle between the transverse intercept direction and the road width direction and the determined target width. Based on the actual target transverse intercept and the imaging relationship between the road transverse intercept in the camera coordinate system, the optimized lane line sampling points (target lane line point pair) in the camera coordinate system are determined. After conversion to the vehicle coordinate system, a more accurate first lane line point pair can be obtained, that is, a more accurate lane line sampling point is obtained, which is used for lane line fitting of the target lane, thereby improving the accuracy of lane line fitting. In addition, since there is no need to dynamically estimate the camera extrinsic parameters (dynamic estimation of camera extrinsic parameters adds a filter, which will cause lane line fitting to lag), the real-time performance of lane line fitting is effectively guaranteed.

[0089] In an optional example, step 20334 of determining target lane line point pairs for each first lane line point pair in the camera coordinate system based on each fifth lane line point pair and the target transverse intercept corresponding to each fifth lane line point pair includes:

[0090] For each fifth lane line point pair, based on the fifth lane line point pair, the target cross-intercept corresponding to the fifth lane line point pair, the preset angle and the preset rules, the first intermediate coefficient and the second intermediate coefficient corresponding to the fifth lane line point pair are determined; based on the fifth lane line point pair, the first intermediate coefficient and the second intermediate coefficient corresponding to the fifth lane line point pair, the target lane line point pair corresponding to the first lane line point pair of the fifth lane line point pair in the camera coordinates is determined.

[0091] The preset angle refers to the angle between the road cross section and the imaging plane. After the camera is installed on the vehicle, the preset angle is determined. Therefore, the preset angle is a fixed value that can be obtained in advance and is expressed as The preset rule is determined based on the imaging relationship of the road cross-intercept. The first intermediate coefficient and the second intermediate coefficient are coefficients involved in the process of solving the target lane line point pair.

[0092] For example, Figure 7 is the imaging relationship of the road cross-intercept in the image under the camera coordinate system provided by an exemplary embodiment of the present disclosure. Among them, the i-th fifth lane line point pair is represented by B i (x ri ,y ri ,z ri ) and C i (x li ,y li ,z li ), BC represents the target cross-intercept corresponding to the fifth lane line point pair, and the target cross-intercept is expressed as W, B i C i Indicates the imaging position corresponding to BC and is in the imaging plane. i (x ri ,yri ,z ri ) represents the lane line sampling point B(x r ,y r ,z r ) imaging position in the camera coordinate system, C i (x li ,y li ,z li ) is the sampling point C(x l ,y l ,z l ) is the imaging position in the camera coordinate system. And point O(0,0,0), point B i (x ri ,y ri ,z ri ), point B(x r ,y r ,z r ) The three are collinear, O(0,0,0), point C i (x li ,y li ,z li ), point C(x l ,y l ,z l ) The three points are collinear. The target cross-intercept BC forms an angle with the imaging plane

[0093] Since point O(0,0,0), point B i (x ri ,y ri ,z ri ), point B(x r ,y r ,z r ) The three are collinear, so there is the following relationship:

[0094]

[0095]

[0096]

[0097] Similarly, O(0,0,0), point C i (x li ,y li ,z li ), point C(x l ,y l ,z l ) The three points are collinear, and the relationship is as follows:

[0098]

[0099]

[0100]

[0101] Among them, k and m are the intermediate coefficients to be solved, that is, the first intermediate coefficient and the second intermediate coefficient mentioned above.

[0102] Since BC is the target intercept, the following relationship exists:

[0103]

[0104]

[0105] in, Represents the length of vector BC, which is also the target intercept.

[0106]

[0107] Because point B i 、C i In the imaging plane, therefore, the following relationship holds:

[0108] z li =z ri =f

[0109] Where f is the focal length of the camera.

[0110] The following relationship can be obtained:

[0111] (mx li -kx ri ) 2 +(my li -ky ri ) 2 +(mz li -kz ri ) 2 =W 2 Formula 1

[0112] Point O(0,0,0) to vector The distance is:

[0113]

[0114] Combine Formula 1 and Formula 2 and substitute the fifth lane line point pair B obtained above into i (x ri ,y ri ,z ri ) and C i (x li ,y li ,z li), the target cross-intercept W corresponding to the fifth lane line point, the angle formed by the cross-intercept BC and the imaging plane and the camera focal length f, the first intermediate coefficient k and the second intermediate coefficient m can be obtained.

[0115] Based on the fifth lane line point B i (x ri ,y ri ,z ri ) and C i (x li ,y li ,z li ), the first intermediate coefficient k and the second intermediate coefficient m, according to the formula The target lane line point pair of the first lane line point pair in the camera coordinate system can be obtained.

[0116] Figure 8 The figure below is a schematic diagram of the relationship between the camera coordinate system and the vehicle coordinate system, provided by an exemplary embodiment of the present disclosure. Here, xoy represents the vehicle coordinate system, and X_c-O_c-Y_c represents the camera coordinate system. The vehicle coordinate system and the camera coordinate system form an angle yaw in the X direction. Based on the relative position of the camera and the vehicle, the mapping relationship between the camera coordinate system and the vehicle coordinate system can be determined. The specific principles will not be repeated here. Based on the mapping relationship between the camera coordinate system and the vehicle coordinate system, each target lane line point pair can be converted to the vehicle coordinate system to obtain the corresponding first lane line point pair in the vehicle coordinate system.

[0117] Based on the imaging relationship of the road transverse intercept in the camera coordinate system, the present invention derives the calculation rules for solving the intersection of the actual transverse intercept and the lane lines on both sides of the road (the first lane line point pair). The accurate lane line point pair can be solved through the road prior information and the calculation rules, and then the accurate and stable lane lines can be fitted, thereby avoiding the dynamic estimation of the camera extrinsic parameters and the need to estimate the road surface slope change. The accuracy is effectively improved while ensuring the real-time performance of the lane line fitting.

[0118] In an optional example, determining the first lane line curve parameter of the target lane in the vehicle coordinate system based on the image segmentation result of the target image in step 201 includes:

[0119] Step 2011: Determine the first lane line sampling point in the image coordinate system based on the image segmentation result of the target image.

[0120] The first lane line sampling point may include a pixel point belonging to a lane line in the image coordinate system. The lane line may include all lane lines of the road where the vehicle is located. For example, on a three-lane road, it may include four lane lines, and the specific lane line is not limited thereto.

[0121] Step 2012: Determine a second lane line sampling point in the vehicle coordinate system based on the first lane line sampling point.

[0122] Specifically, by converting the first lane line sampling points from the image coordinate system to the vehicle coordinate system, the second lane line sampling points corresponding to each first lane line sampling point can be obtained. The specific coordinate conversion principle will not be repeated here.

[0123] Step 2013: Determine the curve parameters of the first lane line of the target lane based on the second lane line sampling point.

[0124] After determining the second lane line sampling points in the vehicle coordinate system, the first lane line curve parameters of the target lane can be obtained through fitting. Specifically, the second lane line sampling points can be clustered to determine the sampling points belonging to each lane line. Then, based on the positional relationship between the sampling point clusters corresponding to each lane line in the clustering results and the vehicle, the sampling points of the target lane are determined, and the first lane line curve parameters are obtained by fitting the sampling points of the target lane. Alternatively, based on the positional relationship between each second lane line sampling point and the vehicle, the sampling points belonging to the lane lines on both sides of the target lane are determined, and then fitting is performed to obtain the first lane line curve parameters. The specific method for determining the first lane line curve parameters of the target lane can be set according to actual needs.

[0125] Figure 9 It is a flowchart of step 2013 provided by an exemplary embodiment of the present disclosure.

[0126] In an optional example, determining the first lane line curve parameter of the target lane based on the second lane line sampling point in step 2013 includes:

[0127] Step 20131: Perform sparse processing on the second lane line sampling points to obtain sparse third lane line sampling points.

[0128] Sparse processing involves collecting sparser third lane sampling points from the denser second lane sampling points, reducing the number of sampling points while ensuring their validity, thereby improving subsequent data processing efficiency. The specific sparse processing method can be any feasible method and is not limited in this disclosure.

[0129] Step 20132: Determine the fourth lane line sampling point of the target lane based on the thinned third lane line sampling point.

[0130] Specifically, based on the positional relationship between the third lane line sampling points and the vehicle, the fourth lane line sampling points of the target lane are determined. For example, based on the positional relationship and lateral distance between each third lane line sampling point and the vehicle, the sampling points belonging to the left lane line of the target lane and the sampling points belonging to the right lane line of the third lane line sampling points are determined, thereby obtaining the fourth lane line sampling points of the target lane. The specific principles will not be elaborated on here.

[0131] Step 20133: Perform fitting processing on the fourth lane line sampling points to obtain the first lane line curve parameters of the target lane.

[0132] The fitting method may adopt any feasible method, such as the least square method, and may be specifically set according to actual needs, which is not limited in this disclosure.

[0133] In an optional example, determining the lane line of the target lane based on the first lane line point pair in step 204 includes:

[0134] Step 2041: Determine a first side lane line curve and a second side lane line curve of the target lane based on the first lane line point pair and the Kalman filter algorithm.

[0135] The first lane curve and the second lane curve refer to the left and right lane curves of the target lane, respectively. The Kalman filter algorithm was developed for estimating dynamic problems, such as satellite positioning and target tracking. Due to the motion of vehicles, the Kalman filter algorithm is more effective than the least squares algorithm, resulting in more accurate and stable first and second lane curves for the target lane.

[0136] The present invention accurately projects the sampling points in the image to the vehicle coordinate system through the road cross-intercept. There is no need to dynamically estimate the camera extrinsic parameters or estimate the road surface slope. It can achieve real-time and accurate fitting of lane lines without being affected by road conditions. Accurate and stable lane lines can be obtained in scenes such as bumps, uphill and downhill slopes, and ramps.

[0137] Any lane line determination method provided in the embodiments of the present disclosure can be executed by any appropriate device with data processing capabilities, including but not limited to a terminal device and a server. Alternatively, any lane line determination method provided in the embodiments of the present disclosure can be executed by a processor, such as a processor that executes any lane line determination method mentioned in the embodiments of the present disclosure by invoking corresponding instructions stored in a memory. This will not be further described below.

[0138] Exemplary devices

[0139] Figure 10FIG is a schematic diagram of a lane line determination device provided by an exemplary embodiment of the present disclosure. The device of this embodiment can be used to implement the corresponding method embodiment of the present disclosure, such as Figure 10 The device shown includes: a first determining module 501 , a first processing module 502 , a second processing module 503 and a third processing module 504 .

[0140] The first determination module 501 is used to determine the first lane line curve parameters of the target lane in the vehicle coordinate system based on the image segmentation result of the target image, where the first lane line curve parameters are cubic curve coefficients for fitting the lane line of the target lane; the first processing module 502 is used to determine the target width of the target lane based on the first lane line curve parameters obtained by the first determination module 501; the second processing module 503 is used to determine the first lane line point pairs corresponding to each of the first transverse intercepts of at least one first transverse intercept corresponding to the target lane in the vehicle coordinate system based on the first lane line curve parameters obtained by the first determination module 501 and the target width obtained by the first processing module 502, where the first lane line point pairs include the first endpoint of the first transverse intercept at the first side lane line of the target lane and the second endpoint of the first transverse intercept at the second side lane line of the target lane; the third processing module 504 is used to determine the lane line of the target lane based on the first lane line point pairs obtained by the second processing module 503.

[0141] Figure 11 5 is a schematic structural diagram of a first processing module 502 provided by an exemplary embodiment of the present disclosure.

[0142] In an optional example, the first processing module 502 includes: a first processing unit 5021 and a second processing unit 5022 .

[0143] The first processing unit 5021 is used to determine a second transverse intercept at a first preset distance from the vehicle on the target lane based on the first lane line curve parameter; the second processing unit 5022 is used to determine a target width of the target lane based on the second transverse intercept determined by the first processing unit 5021.

[0144] Figure 12 5 is a schematic structural diagram of a second processing module 503 provided by an exemplary embodiment of the present disclosure.

[0145] In an optional example, the second processing module 503 includes: a third processing unit 5031 , a fourth processing unit 5032 , and a fifth processing unit 5033 .

[0146] The third processing unit 5031 is used to determine, based on the first lane line curve parameters, the third lane line point pairs corresponding to each of the third transverse intercepts corresponding to the target lane in the vehicle coordinate system; the fourth processing unit 5032 is used to determine, based on each of the third lane line point pairs, the fourth lane line point pairs corresponding to each of the third transverse intercepts in the image coordinate system; the fifth processing unit 5033 is used to determine each of the first lane line point pairs based on each of the fourth lane line point pairs and the target width.

[0147] Figure 13 3 is a schematic structural diagram of a fifth processing unit 5033 provided by an exemplary embodiment of the present disclosure.

[0148] In an optional example, the fifth processing unit 5033 includes: a first processing sub-unit 50331 , a second processing sub-unit 50332 , a third processing sub-unit 50333 , a fourth processing sub-unit 50334 and a fifth processing sub-unit 50335 .

[0149] The first processing sub-unit 50331 is used to convert each of the fourth lane line point pairs into the camera coordinate system to obtain the fifth lane line point pairs corresponding to each of the fourth lane line point pairs; the second processing sub-unit 50332 is used to determine, based on the first lane line curve parameters, the first angles between the transverse intercept directions of each of the fourth lane line point pairs in the vehicle coordinate system and the corresponding road width directions; the third processing sub-unit 50333 is used to determine, based on the target width and each of the first angles, the target transverse intercepts corresponding to each of the fourth lane line point pairs; the fourth processing sub-unit 50334 is used to determine the target lane line point pairs of each of the first lane line point pairs in the camera coordinate system based on each of the fifth lane line point pairs and the target transverse intercepts corresponding to each of the fifth lane line point pairs; the fifth processing sub-unit 50335 is used to convert each of the target lane line point pairs into the vehicle coordinate system to obtain each of the first lane line point pairs.

[0150] In an optional example, the fourth processing sub-unit 50334 is specifically configured to:

[0151] For each of the fifth lane line point pairs, based on the fifth lane line point pair, the target cross-intercept corresponding to the fifth lane line point pair, the preset angle and the preset rules, the first intermediate coefficient and the second intermediate coefficient corresponding to the fifth lane line point pair are determined; based on the fifth lane line point pair, the first intermediate coefficient and the second intermediate coefficient corresponding to the fifth lane line point pair, the target lane line point pair corresponding to the first lane line point pair of the fifth lane line point pair in the camera coordinates is determined.

[0152] Figure 145 is a structural diagram of a first determining module 501 provided by an exemplary embodiment of the present disclosure.

[0153] In an optional example, the first determining module 501 includes: a first determining unit 5011 , a second determining unit 5012 and a third determining unit 5013 .

[0154] The first determination unit 5011 is used to determine the first lane line sampling point in the image coordinate system based on the image segmentation result; the second determination unit 5012 is used to determine the second lane line sampling point in the vehicle coordinate system based on the first lane line sampling point; and the third determination unit 5013 is used to determine the first lane line curve parameter of the target lane based on the second lane line sampling point.

[0155] Figure 15 2 is a schematic structural diagram of the third determining unit 5013 of the first determining module provided by an exemplary embodiment of the present disclosure.

[0156] In an optional example, the third determination unit 5013 includes: a sixth processing subunit 50131 , a first determination subunit 50132 , and a second determination subunit 50133 .

[0157] The sixth processing subunit 50131 is used to perform sparse processing on the second lane line sampling points to obtain sparse third lane line sampling points; the first determination subunit 50132 is used to determine the fourth lane line sampling points of the target lane based on the sparse third lane line sampling points; the second determination subunit 50133 is used to perform fitting processing on the fourth lane line sampling points to obtain the first lane line curve parameters of the target lane.

[0158] In an optional example, the third processing module 504 is specifically configured to determine a first side lane line curve and a second side lane line curve of the target lane based on the first lane line point pair and a Kalman filter algorithm.

[0159] Exemplary electronic devices

[0160] An embodiment of the present disclosure further provides an electronic device, comprising: a memory for storing a computer program;

[0161] The processor is configured to execute the computer program stored in the memory, and when the computer program is executed, the lane line determination method described in any one of the above embodiments of the present disclosure is implemented.

[0162] Figure 16 FIG. 1 is a schematic diagram of a structure of an application embodiment of an electronic device disclosed in the present invention. In this embodiment, the electronic device 10 includes one or more processors 11 and a memory 12.

[0163] The processor 11 may be a central processing unit (CPU) or other forms of processing units having data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device 10 to perform desired functions.

[0164] 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), a hard disk, a 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 methods of the various embodiments of the present disclosure described above and / or other desired functions. Various contents such as input signals, signal components, noise components, etc. may also be stored in the computer-readable storage medium.

[0165] In one example, the electronic device 10 may further include an input device 13 and an output device 14 , and these components are interconnected via a bus system and / or other forms of connection mechanisms (not shown).

[0166] For example, the input device 13 may be the aforementioned microphone or microphone array, used to capture input signals from a sound source.

[0167] In addition, the input device 13 may also include, for example, a keyboard, a mouse, and the like.

[0168] The output device 14 can output various information to the outside, including determined distance information, direction information, etc. The output device 14 can include, for example, a display, a speaker, a printer, a communication network and a remote output device connected thereto, and the like.

[0169] Of course, to simplify, Figure 16 Only some of the components related to the present disclosure in the electronic device 10 are shown, and components such as buses, input / output interfaces, etc. are omitted. In addition, the electronic device 10 may further include any other appropriate components according to specific application scenarios.

[0170] Exemplary computer program products and computer-readable storage media

[0171] In addition to the above-mentioned methods and devices, an embodiment of the present disclosure may also be a computer program product, which includes computer program instructions, which, when executed by a processor, enable the processor to perform the steps of the method according to various embodiments of the present disclosure described in the above-mentioned "Exemplary Method" section of this specification.

[0172] The computer program product may be written in any combination of one or more programming languages ​​to implement the operations of the disclosed embodiments, including object-oriented programming languages ​​such as Java, C++, and conventional procedural programming languages ​​such as C or similar programming languages. The program code may 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.

[0173] In addition, an embodiment of the present disclosure may also be a computer-readable storage medium having computer program instructions stored thereon, which, when executed by a processor, enable the processor to execute the steps of the method according to various embodiments of the present disclosure described in the above “Exemplary Method” section of this specification.

[0174] The computer-readable storage medium can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can, for example, include but is not limited to a system, device or component of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination thereof. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0175] The basic principles of the present disclosure have been described above in conjunction with specific embodiments. However, it should be noted that the advantages, strengths, and effects mentioned in this disclosure are merely illustrative and not restrictive, and should not be construed as necessarily possessed by each embodiment of the present disclosure. Furthermore, the specific details disclosed above are provided for illustrative purposes and to facilitate understanding, rather than as limitations. These details do not limit the present disclosure to necessarily being implemented using these specific details.

[0176] Each embodiment in this specification is described in a progressive manner, with each embodiment focusing on its differences from the other embodiments. References to the same or similar parts between the various embodiments are sufficient. For system embodiments, since they largely correspond to method embodiments, their description is relatively simple. For relevant parts, references to the description of the method embodiments are sufficient.

[0177] The block diagrams of the devices, devices, equipment, and systems involved in this disclosure 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 will be appreciated by those skilled in the art, these devices, devices, equipment, and systems can be connected, arranged, or configured in any manner. Words such as "include," "comprise," "have," and the like are open-ended words, meaning "including but not limited to," and can be used interchangeably therewith. The words "or" and "and" used herein refer to the words "and / or" and can be used interchangeably therewith, unless the context clearly indicates otherwise. The word "such as" used herein refers to the phrase "such as but not limited to," and can be used interchangeably therewith.

[0178] The methods and apparatus of the present disclosure may be implemented in many ways. For example, the methods and apparatus of the present disclosure may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above order of steps for the method is for illustration only, and the steps of the method of the present disclosure are not limited to the order specifically described above unless otherwise specified. In addition, in some embodiments, the present disclosure may also be implemented as programs recorded in a recording medium, which include machine-readable instructions for implementing the methods according to the present disclosure. Thus, the present disclosure also covers recording media that store programs for executing the methods according to the present disclosure.

[0179] It should also be noted that in the apparatus, device, and method of the present disclosure, each component or each step can be decomposed and / or recombined. Such decomposition and / or recombination should be regarded as equivalent solutions of the present disclosure.

[0180] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present disclosure. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects without departing from the scope of the present disclosure. Therefore, the present disclosure 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.

[0181] The above description has been provided for the purpose of illustration and description. In addition, this description is not intended to limit the embodiments of the present disclosure to the forms disclosed herein. Although a number of example 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 determining a lane line, comprising: Determining, based on an image segmentation result of the target image, a first lane line curve parameter of the target lane in the vehicle coordinate system, where the first lane line curve parameter is a cubic curve coefficient fitting the lane line of the target lane; determining a target width of the target lane based on the first lane curve parameter; Based on the first lane line curve parameter and the target width, determining, in accordance with the lane width invariance principle, a first lane line point pair corresponding to each of the first transverse intercepts corresponding to the target lane in the vehicle coordinate system, the first lane line point pair comprising a first endpoint of the first transverse intercept at a first side lane line of the target lane and a second endpoint of the first transverse intercept at a second side lane line of the target lane; the at least one first transverse intercept comprising a transverse intercept at at least one position along the longitudinal axis of the vehicle coordinate system; Based on the first lane line point pair, a lane line of the target lane is determined.

2. The method according to claim 1, wherein The determining the target width of the target lane based on the first lane curve parameter includes: determining a second transverse intercept on the target lane at a first preset distance from the vehicle based on the first lane curve parameter; A target width of the target lane is determined based on the second transverse intercept.

3. The method according to claim 1, wherein The determining, based on the first lane curve parameter and the target width, first lane point pairs corresponding to respective first transverse intercepts of at least one first transverse intercept corresponding to the target lane in the vehicle coordinate system includes: determining, based on the first lane curve parameter, a third lane point pair corresponding to each of the at least one third transverse intercept corresponding to the target lane in the vehicle coordinate system; Based on each of the third lane line point pairs, determining a fourth lane line point pair corresponding to each of the third transverse intercepts in the image coordinate system; Based on the fourth lane line point pairs and the target width, each of the first lane line point pairs is determined.

4. The method according to claim 3, wherein: The determining each of the first lane line point pairs based on each of the fourth lane line point pairs and the target width includes: Convert each of the fourth lane line point pairs to a camera coordinate system to obtain a fifth lane line point pair corresponding to each of the fourth lane line point pairs; determining, based on the first lane line curve parameter, first angles between the transverse intercept direction of each of the fourth lane line point pairs in the vehicle coordinate system and the corresponding road width direction; Determining target transverse intercepts corresponding to the fourth lane line point pairs based on the target width and the first angles; determining a target lane line point pair for each of the first lane line point pairs in the camera coordinate system based on each of the fifth lane line point pairs and the target transverse intercepts respectively corresponding to each of the fifth lane line point pairs; Each of the target lane line point pairs is converted to the vehicle coordinate system to obtain each of the first lane line point pairs.

5. The method according to claim 4, wherein The determining, based on each of the fifth lane line point pairs and the target transverse intercepts respectively corresponding to each of the fifth lane line point pairs, a target lane line point pair for each of the first lane line point pairs in the camera coordinate system includes: For each of the fifth lane line point pairs, determining a first intermediate coefficient and a second intermediate coefficient corresponding to the fifth lane line point pair based on the fifth lane line point pair, a target transverse intercept corresponding to the fifth lane line point pair, a preset angle, and a preset rule; Based on the fifth lane line point pair, the first intermediate coefficient and the second intermediate coefficient corresponding to the fifth lane line point pair, the target lane line point pair corresponding to the first lane line point pair of the fifth lane line point pair in the camera coordinates is determined.

6. The method according to claim 1, wherein The determining of the first lane line curve parameter of the target lane in the vehicle coordinate system based on the image segmentation result of the target image includes: Based on the image segmentation result, determining a first lane line sampling point in an image coordinate system; Determining a second lane line sampling point in the vehicle coordinate system based on the first lane line sampling point; Determine the first lane line curve parameter of the target lane based on the second lane line sampling point.

7. The method according to claim 6, wherein: The determining, based on the second lane line sampling point, the first lane line curve parameter of the target lane includes: Performing sparse processing on the second lane line sampling points to obtain sparse third lane line sampling points; Determining a fourth lane line sampling point of the target lane based on the thinned third lane line sampling point; Fitting processing is performed on the fourth lane line sampling points to obtain the first lane line curve parameters of the target lane.

8. The method according to any one of claims 1 to 7, wherein: The determining the lane line of the target lane based on the first lane line point pair includes: Based on the first lane line point pair and a Kalman filter algorithm, a first side lane line curve and a second side lane line curve of the target lane are determined.

9. A lane line determination device, comprising: A first determination module is configured to determine a first lane line curve parameter of a target lane in a vehicle coordinate system based on an image segmentation result of the target image, wherein the first lane line curve parameter is a cubic curve coefficient of a lane line fitting the target lane; a first processing module, configured to determine a target width of the target lane based on the first lane curve parameter; a second processing module for determining, based on the first lane line curve parameter and the target width, and in accordance with a lane width invariance principle, a first lane line point pair corresponding to each of the at least one first transverse intercepts corresponding to the target lane in the vehicle coordinate system, wherein the first lane line point pair includes a first endpoint of the first transverse intercept at a first side lane line of the target lane and a second endpoint of the first transverse intercept at a second side lane line of the target lane; the at least one first transverse intercept includes a transverse intercept at at least one position along the longitudinal axis of the vehicle coordinate system; A third processing module is configured to determine a lane line of the target lane based on the first lane line point pair.

10. A computer-readable storage medium storing a computer program, wherein the computer program is used to execute the lane line determination method according to any one of claims 1 to 8.

11. An electronic device, comprising: processor; a memory for storing instructions executable by the processor; The processor is configured to read the executable instructions from the memory and execute the instructions to implement the lane line determination method described in any one of claims 1-8.

Images