Lane line marking method and device, equipment and medium
By automatically supplementing the labeling points in the lane line images taken by the fisheye camera, using straight line types and cubic spline types, the problem of low labeling efficiency caused by fisheye camera distortion is solved, and the labeling efficiency and accuracy are improved.
Patent Information
- Application Number
- CN202411309202.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-19
- Publication Date
- 2025-01-03
AI Technical Summary
In the prior art, the lane line images taken by fisheye cameras are largely distorted, resulting in low labeling efficiency, and more points are needed to be marked, which has problems such as cumbersome operation and poor fit.
By automatically supplementing the annotation points on the basis of the user's annotation points, and automatically labeling using the straight line type and cubic spline type, the number and difficulty of user's annotation are reduced and the labeling efficiency is improved.
The efficiency and accuracy of lane line labeling are improved, the difficulty of users in labeling lane line labeling is reduced, and the problems of complex, time-consuming and low accuracy in the prior art are overcome.
Smart Images
Figure CN119251840A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of intelligent driving technology, and in particular to a lane marking method, device, equipment and medium. Background Art
[0002] Lane detection plays a vital role in autonomous driving and intelligent transportation systems, and is the basis for vehicle navigation, path planning, and environmental perception. With the rapid development of deep learning technology, lane detection technology has made significant progress. Lane detection models based on image processing, machine learning, and deep learning have greatly improved the accuracy and robustness of the detection system. Since the training of lane detection models requires manually labeled lane samples, accurate lane annotation is the basis for improving the performance of lane detection models.
[0003] In the prior art, fisheye cameras are mainly used to capture lane line images. However, fisheye cameras have large distortion, and straight lane lines in the fisheye lens will become curved. In order to ensure the fitting degree of the lane lines, more points need to be manually marked on the lane line images taken by the fisheye camera, resulting in low marking efficiency. Summary of the invention
[0004] The present application provides a lane marking method, device, equipment and medium to solve the problem of low marking efficiency in the prior art.
[0005] In a first aspect, the present application provides a lane marking method, comprising:
[0006] Display road images taken by a fisheye camera;
[0007] In response to the labeling process of the lane line in the road image, a first labeling point after the labeling process is performed is obtained;
[0008] According to the first marking point, the lane line is automatically supplemented with marking points.
[0009] Optionally, based on the first annotation point, the lane line is automatically supplemented with annotation points, including:
[0010] Determine the annotation type according to the first annotation point, the annotation type including a straight line type and a cubic spline curve type;
[0011] The lane line is automatically supplemented with annotation points according to the annotation type to obtain a second annotation point, and the distance between any two adjacent annotation points of the first annotation point and the second annotation point meets the preset distance requirement.
[0012] Optionally, determining the annotation type according to the first annotation point includes:
[0013] If the first annotation point is on the same straight line, the annotation type is determined to be a straight line type;
[0014] If the first annotation point is not on the same straight line, the annotation type is determined to be a cubic spline curve type.
[0015] Optional, when the annotation type is a straight line type,
[0016] Automatically add annotation points to the lane line according to the annotation type to obtain the second annotation point, including:
[0017] According to the first marked point, determine the starting point and the end point of the straight line;
[0018] Determine the second dimension point between the start and end points.
[0019] Optional, when the annotation type is cubic spline type,
[0020] Automatically add annotation points to the lane line according to the annotation type to obtain the second annotation point, including:
[0021] Determine the curve data of the curve where the first marked point is located;
[0022] According to the curve data, a second marking point is determined between adjacent first marking points.
[0023] Optionally, display the road image captured by the fisheye camera, including:
[0024] Obtain an initial road image taken by a fisheye camera;
[0025] Performing dedistortion processing on the initial road image to obtain a road image;
[0026] Displays road images.
[0027] Optionally, the method further includes:
[0028] According to the marking result of the lane line, the marking result is converted into the coordinate system of the initial road image to obtain a third marking point;
[0029] The initial lane line in the initial road image is marked according to the third marking point.
[0030] In a second aspect, the present application provides a lane marking device, comprising:
[0031] A display module, used for displaying the road image captured by the fisheye camera;
[0032] A response module, configured to respond to the marking process of the lane line in the road image and obtain a first marking point after the marking process is performed;
[0033] The marking module is used to automatically add marking points to the lane line according to the first marking points.
[0034] In a third aspect, the present application provides an electronic device, comprising: a processor, and a memory communicatively connected to the processor;
[0035] Memory stores computer-executable instructions;
[0036] The processor executes the computer-executable instructions stored in the memory to implement the method provided in the present application.
[0037] In a fourth aspect, the present application provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the method provided by the present application.
[0038] The lane line marking method, device, equipment and medium provided in the present application display a road image taken by a fisheye camera, and in response to the marking processing of the lane lines in the road image, obtain a first marking point after the marking processing is executed, and finally automatically supplement the marking points for the lane lines based on the first marking points, thereby reducing the difficulty of lane line marking for users and improving the marking efficiency. BRIEF DESCRIPTION OF THE DRAWINGS
[0039] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.
[0040] Figure 1 A schematic diagram of a lane marking scenario provided in an embodiment of the present application;
[0041] Figure 2 A schematic diagram of a process flow of a lane marking method provided in an embodiment of the present application;
[0042] Figure 3 A schematic diagram of a process flow of another lane marking method provided in an embodiment of the present application;
[0043] Figure 4 A schematic diagram of an initial road image provided in an embodiment of the present application;
[0044] Figure 5 A schematic diagram of a road image provided in an embodiment of the present application;
[0045] Figure 6 A schematic diagram of a third marking point provided in an embodiment of the present application;
[0046] Figure 7 A schematic diagram of the labeling results provided in the embodiment of the present application;
[0047] Figure 8A schematic diagram of a third marking point provided in an embodiment of the present application;
[0048] Fig. 9 A schematic diagram of the structure of a lane marking device provided in an embodiment of the present application;
[0049] Fig.10 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.
[0050] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION
[0051] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.
[0052] In order to clearly understand the technical solution of the present application, the solution of the prior art is first introduced in detail.
[0053] Lane detection plays a vital role in autonomous driving and intelligent transportation systems, and is the basis for vehicle navigation, path planning, and environmental perception. With the rapid development of deep learning technology, lane detection technology has made significant progress. Lane detection models based on image processing, machine learning, and deep learning have greatly improved the accuracy and robustness of the detection system. Since the training of lane detection models requires manually labeled lane samples, accurate lane annotation is the basis for improving the performance of lane detection models, enabling the model to have good environmental perception capabilities in complex environments, thereby ensuring driving safety under various weather and lighting conditions.
[0054] In the past, lane line image output was mainly based on panoramic pinhole cameras. Since the pinhole camera has less distortion, only two points need to be marked on the lane line image to fit a straight line. In order to reduce sensor costs, some OEMs or smart driving solution providers have begun to use fisheye cameras for lane line image output. Fisheye cameras have greater distortion, and the straight lane lines in the fisheye lens will also become curved. In order to ensure the fit of the lane line, the existing method is to mark more points on the lane line to form a broken line to fit the curvature of the lane line, but this method requires more points for annotation, which is cumbersome to operate and has poor fit.
[0055] In response to the above technical problems, the inventors discovered during research that the lane lines can be marked by automatically supplementing the marking points based on the marking points marked by the user, thereby improving the marking efficiency.
[0056] The following introduces the application scenarios of the lane line marking method provided in the embodiments of the present application.
[0057] Figure 1 A schematic diagram of a lane marking scenario provided in an embodiment of the present application, such as Figure 1 As shown, the scene includes: a road image taken by a fisheye camera and an electronic device, wherein the electronic device is used to display the road image taken by the fisheye camera, and in response to the labeling processing of the lane line in the road image, obtain the first labeling point after executing the labeling processing, and finally automatically supplement the labeling point for the lane line according to the first labeling point to complete the labeling of the lane line.
[0058] Figure 2 A schematic diagram of a lane marking method provided in an embodiment of the present application is shown in FIG. Figure 2 As shown, the method includes:
[0059] S201: Display a road image captured by a fisheye camera.
[0060] In this embodiment, the electronic device can obtain a road image taken by a fisheye camera from a database, and display the road image on a display device, so that the user can annotate the road image. The fisheye camera can refer to a wide-angle camera with a focal length of 16 mm or less and a viewing angle close to or equal to 180°. The road image can refer to an image containing lane lines, and the road image can be an original image directly taken by a fisheye camera, or an image processed from the original image taken by a fisheye camera, and this application does not impose any restrictions on this.
[0061] S202: In response to the labeling process of the lane line in the road image, a first labeling point after the labeling process is performed is obtained.
[0062] In this embodiment, after obtaining the road image, the user can mark the lane lines on the road image to obtain the marked points. In response to the user's marking of the lane lines in the road image, the electronic device obtains the marked points marked by the user as the first marked points. The marking process may refer to the user marking the lane lines on the road image by operating tools in the marking system. The marked points also include coordinates, which can be determined by the coordinates of the marked points in the coordinate system of the road image. For example, the user can obtain the position of the pointer on the display by clicking the mouse or the touch panel to obtain the coordinates of the marked points.
[0063] S203: Automatically add annotation points to the lane line based on the first annotation point.
[0064] In this embodiment, after obtaining the first marking points, the electronic device can automatically supplement marking points between the first marking points according to the coordinates of the first marking points, thereby reducing the number of markings performed by the user and improving marking efficiency.
[0065] Specifically, automatically supplementing the lane line with annotation points according to the first annotation point may include:
[0066] Determine the annotation type according to the first annotation point, the annotation type including a straight line type and a cubic spline curve type;
[0067] The lane line is automatically supplemented with annotation points according to the annotation type to obtain a second annotation point, and the distance between any two adjacent annotation points of the first annotation point and the second annotation point meets the preset distance requirement.
[0068] In this embodiment, after obtaining the first marking point, it is necessary to determine the shape of the lane line marked by the user based on the characteristics of the first marking point, so as to determine the marking type, so as to automatically supplement the marking point for the lane line according to different marking types, and obtain the second marking point, so as to reduce the number of user markings, thereby reducing the marking difficulty and improving the marking accuracy.
[0069] The line type may refer to the type of points added to the line.
[0070] The cubic spline curve type may refer to a type of filling points for a non-straight line according to a cubic spline curve. The cubic spline curve may refer to a mathematical method used for numerical interpolation and data fitting.
[0071] Automatically supplementing annotation points means interpolating according to the straight line type or the cubic spline curve type, so that the automatically supplemented annotation points are more uniform and accurate than the manual annotations, thereby improving the fitting effect of the lane line.
[0072] If too many values are inserted during interpolation, it will be difficult to fit completely and require subsequent manual adjustment. If too few values are inserted, the fit will be too poor. Therefore, the number of annotation points needs to be set. Generally, the preset distance requirement is determined based on the distance between any two adjacent annotation points in the first annotation point and the second annotation point. For example, the preset distance requirement may not exceed 10 pixels.
[0073] In some embodiments, after automatically adding annotation points, if the user finds that the second annotation point does not fit the lane line in the image, the user can also adjust the second annotation point, for example, by dragging the second annotation point with a mouse until the second annotation point completely fits the lane line.
[0074] Specifically, determining the annotation type according to the first annotation point may include:
[0075] If the first annotation point is on the same straight line, the annotation type is determined to be a straight line type;
[0076] If the first annotation point is not on the same straight line, the annotation type is determined to be a cubic spline curve type.
[0077] In this embodiment, after obtaining the first annotation points, the shape of the lane line annotated by the user is determined by judging the positional relationship between the first annotation points. Generally speaking, for higher annotation efficiency, if the lane line is a straight line, the user needs to at least mark the starting point and end point of the lane line. If the lane line is a non-straight line, the user needs to at least mark the starting point, end point and the place where the curvature changes significantly. Therefore, based on the above situation, the annotation type can be determined by judging whether each first annotation point is on the same straight line.
[0078] Specifically, when the annotation type is a straight line type, automatically supplementing the lane line with annotation points according to the annotation type to obtain the second annotation point may include:
[0079] According to the first marked point, determine the starting point and the end point of the straight line;
[0080] Determine the second dimension point between the start and end points.
[0081] In this embodiment, when the annotation type is a straight line type, the first annotation point includes at least two, and the starting point and the end point of the straight line can be determined according to the coordinates of the first annotation point. According to the starting point and the end point of the straight line, k and b in the linear equation y=kx+b of the straight line are determined, and then the value of x or y is interpolated between the starting point and the end point to obtain the coordinates of the second annotation point.
[0082] Specifically, when the annotation type is a cubic spline curve type, automatically supplementing the lane line with annotation points according to the annotation type to obtain the second annotation point may include:
[0083] Determine the curve data of the curve where the first marked point is located;
[0084] According to the curve data, a second marking point is determined between adjacent first marking points.
[0085] In this embodiment, when the annotation type is a cubic spline curve, the first annotation points include at least three. Since the cubic spline curve has continuity of first-order and second-order derivatives between each control point, the curve is not only continuous at the control point, but also its slope and curvature are continuous, thereby ensuring a smooth transition of the curve. At the same time, adjusting a control point of the cubic spline curve will only locally affect the shape of the curve and will not have a significant impact on the entire curve. Therefore, according to the first annotation point, the cubic spline curve equation of the curve where all the first annotation points are located is determined. According to the curve data in the cubic spline curve equation, the curve data may include the slope and curvature of the curve, so that the annotation points are automatically supplemented between adjacent first annotation points according to the curve data to obtain multiple second annotation points.
[0086] The lane line marking method provided in the embodiment of the present application displays a road image taken by a fisheye camera, and in response to the marking processing of the lane lines in the road image, obtains a first marking point after the marking processing is executed, and finally automatically supplements the lane lines with marking points based on the first marking points, thereby reducing the difficulty of lane line marking for users and improving marking efficiency.
[0087] Figure 3 A schematic diagram of a process flow of another lane marking method provided in an embodiment of the present application is shown as follows: Figure 3 As shown, the method includes:
[0088] S301: Acquire an initial road image captured by a fisheye camera.
[0089] In this embodiment, the initial road image may refer to an initial image taken by a fisheye camera.
[0090] S302: Dedistort the initial road image to obtain a road image.
[0091] In this embodiment, since the initial road image captured by the fisheye camera may be distorted, for example, a straight lane line may appear as a curved lane line. More annotation points are required for the annotation of curves than for the annotation of straight lines, which increases the difficulty of annotation. Therefore, in order to improve the annotation efficiency, this embodiment performs a de-distortion process on the initial road image to obtain a road image, which is convenient for users to annotate on the road image. The fisheye camera may refer to an isometric projection model, and the de-distortion process may refer to making the initial road image more realistic and more consistent with the real scene seen by the human eye through the internal parameters of the fisheye camera.
[0092] Specifically, the method for performing dedistortion processing on the initial road image may include:
[0093] Determining a first radial distance according to a second coordinate of each pixel point in the initial road image;
[0094] Determining a second radial distance according to the first radial distance and a focal length of the fisheye camera;
[0095] Obtaining a third coordinate according to the second coordinate, the first radial distance, and the second radial distance;
[0096] A road image is obtained according to the third coordinate of each pixel point in the initial road image.
[0097] In this embodiment, a coordinate system is first constructed for the initial road image. The left side of the initial road image can be used as the x-axis, and the top side of the initial road image can be used as the y-axis. Then, the coordinates of each pixel in the initial road image are determined. For ease of distinction, they are referred to as second coordinates here. According to the second coordinates of each pixel in the initial road image, the first radial distance of each pixel is determined. Then, the incident angle is obtained according to the first radial distance and the focal length in the internal parameters of the fisheye camera. The second radial distance of the pixel after dedistortion is obtained according to the incident angle and the focal length. Then, the third coordinate of each pixel after dedistortion is obtained according to the second coordinate, the first radial distance, and the second radial distance of each pixel. Finally, the road image is obtained according to the third coordinate of each pixel after dedistortion.
[0098] For example, assume that the coordinates of the pixel point A in the initial road image are (x d ,y d ), the first radial distance r of pixel point A d for:
[0099]
[0100] The incident angle θ of pixel point A is:
[0101]
[0102] The second radial distance r after dedistortion u for:
[0103] r u =f·tan(θ),
[0104] Where f is the focal length of the fisheye camera.
[0105] The coordinates of pixel point A after distortion removal (x u ,y u )for:
[0106]
[0107] S303: Display the road image.
[0108] S304: In response to the labeling process for the lane line in the road image, a first labeling point after the labeling process is performed is obtained.
[0109] S305: Automatically add annotation points to the lane line based on the first annotation point.
[0110] S306 . According to the marking result of the lane line, convert the marking result into the coordinate system of the initial road image to obtain a third marking point.
[0111] In this embodiment, after obtaining the marking results of the lane lines in the road image, the electronic device converts the marking results into the coordinate system of the initial road image through the internal parameters of the fisheye camera to obtain the third marking point, which facilitates the marking of the initial road image.
[0112] Specifically, according to the lane line marking result, converting the marking result into the coordinate system of the initial road image to obtain the third marking point may include:
[0113] According to the focal length and principal point coordinates of the fisheye camera, the coordinates of each marked point in the marking result are transformed to obtain normalized coordinates on the normalized image plane;
[0114] According to the normalized coordinates, the distortion radius is obtained;
[0115] The distortion coordinates are obtained according to the distortion radius, the normalized coordinates and the distortion coefficient of the fisheye camera;
[0116] According to the focal length and the principal point coordinates, the distorted coordinates are inversely transformed to obtain the coordinates of the third marked point.
[0117] In this embodiment, the focal length of the fisheye camera and the coordinates of the principal point of the road image are first determined, and each annotation point in the annotation result is converted from the coordinate system of the road image to the normalized image plane according to the focal length of the fisheye camera and the coordinates of the principal point of the road image to obtain normalized coordinates, wherein the normalized image plane may refer to the coordinates of all pixels of the road image being transferred to a unit distance in front of the camera, and the converted coordinates of each pixel point are called normalized coordinates, and then the distortion radius of the normalized coordinates is obtained according to the normalized coordinates, and then the distortion coefficient of the camera is used to convert the normalized coordinates into distorted coordinates, and finally the distorted coordinates are converted into the coordinate system of the initial road image to obtain a third annotation point corresponding to each annotation point in the annotation result.
[0118] For example, assume that the coordinates of the marked point A in the marking result are (x undistorted ,y undistorted ), then the normalized coordinate (x norm ,y norm )for:
[0119]
[0120] Among them, (c x ,cy ) is the coordinate of the main point, which can also be called the optical center point, (f x ,f y ) is the focal length of the fisheye camera.
[0121] Determine the distortion radius r as:
[0122]
[0123] Determine the distortion coordinates (x distorted ,y distorted )for:
[0124] x distorted =x norm ·(1+k1·r 2 +k2·r 4 +k3·r 6 ),
[0125] y distorted =y norm ·(1+k1·r 2 +k2·r 4 +k3·r 6 ),
[0126] Among them, k1, k2, and k3 are distortion coefficients.
[0127] Get the coordinates of the marked point A in the coordinate system of the initial road image (x original ,y original )for:
[0128] x original =x distorted ·f x +c x ,
[0129] y original =y distorted ·f y +c y .
[0130] S307: Annotate the initial lane line in the initial road image according to the third annotation point.
[0131] In this embodiment, after obtaining the third annotation point, the third annotation point is set on the initial lane line in the initial road image to achieve the annotation of the initial lane line in the initial road image, so that the third annotation point is fitted according to the annotation label of the lane line and the annotation type of the lane line to obtain the annotated lane line, and the annotated lane line in the initial road image can be used as a training sample for model training to obtain a lane line recognition model that can recognize the lane line in the road image taken by the fisheye camera. The annotation label can include a solid line, a dotted line, a roadside line, and other types of lane lines, and the annotation label can be a label annotated by the user.
[0132] For example, Figure 4 A schematic diagram of an initial road image provided in an embodiment of the present application, such as Figure 4 As shown in the figure, the white lane lines on both sides of the vehicle should be straight lines, but after being photographed by the fisheye camera, the lane lines appear curved. Figure 4 To mark the lane lines in the vehicle, more than three coordinates need to be marked, and then curve fitting is performed based on the marked coordinates. On the one hand, this makes the user operation more cumbersome, and on the other hand, the curve fitting may have a poor fitting effect, requiring the user to manually adjust or supplement the marked coordinates, which further reduces the efficiency of marking. Figure 4 After de-distortion processing, we get Figure 5 , Figure 5 This is a schematic diagram of a road image provided by an embodiment of the present application. From the environment in the figure, it can be seen that the white lane lines on both sides of the vehicle in the figure have been displayed as straight lines. At this time, the user only needs to mark the starting point and end point of the straight line in the figure. When the user completes the marking, the Figure 6 , Figure 6 A schematic diagram of the third annotation point provided in the embodiment of the present application. It can be seen from the figure that two first annotation points are marked on each lane line, which are shown as dots in the figure. After obtaining the first annotation points marked by the user, the electronic device determines that the lane line is a straight line, and then automatically marks multiple second annotation points between the first annotation points marked by the user. Figure 7 , Figure 7 A schematic diagram of the marking results provided in the embodiment of the present application, such as Figure 7 As shown in the figure, multiple dots are marked on the straight lane lines, and all the dots of each lane line are collectively referred to as the marking result. After obtaining the marking result, the coordinates of each marked point in the marking result are converted into the coordinate system of the initial road image to obtain Figure 8 , Figure 8 A schematic diagram of a third marking point provided in an embodiment of the present application, Figure 8 Each annotation point of each lane line in is called the third annotation point, and we get Figure 8 Afterwards, you can Figure 8Lane line fitting is performed for all third marked points of each lane line in the image. Compared with the coordinates manually marked by the user, the coordinates automatically marked by the electronic device through the algorithm are more accurate, which makes the fitting effect better and improves the user's marking efficiency.
[0133] Another lane line marking method provided by an embodiment of the present application obtains and displays a road image by performing a dedistortion process on an initial road image. Then, in response to the marking process of the lane line in the road image, a first marking point after the marking process is performed is obtained. Then, based on the first marking point, the lane line is automatically supplemented with marking points. Then, based on the marking result of the lane line, the marking result is converted into the coordinate system of the initial road image to obtain a third marking point. Finally, based on the third marking point, the initial lane line in the initial road image is marked. By automatically supplementing the marking points marked by the user, the difficulty of lane line marking is greatly reduced, the accuracy and efficiency of marking are improved, and the problems of complex, time-consuming and low-precision marking in the prior art are overcome.
[0134] Fig. 9 A schematic diagram of the structure of a lane marking device provided in an embodiment of the present application is shown in FIG. Fig. 9 As shown, the device comprises:
[0135] Display module 901, used to display the road image taken by the fisheye camera;
[0136] A response module 902, configured to obtain a first annotation point after the annotation processing is performed in response to the annotation processing of the lane line in the road image;
[0137] The marking module 903 is used to automatically add marking points to the lane line according to the first marking points.
[0138] In some implementations, the marking module 903 is further used to:
[0139] Determine the annotation type according to the first annotation point, the annotation type including a straight line type and a cubic spline curve type;
[0140] The lane line is automatically supplemented with annotation points according to the annotation type to obtain a second annotation point, and the distance between any two adjacent annotation points of the first annotation point and the second annotation point meets the preset distance requirement.
[0141] In some implementations, the marking module 903 is further used to:
[0142] If the first annotation point is on the same straight line, the annotation type is determined to be a straight line type;
[0143] If the first annotation point is not on the same straight line, the annotation type is determined to be a cubic spline curve type.
[0144] In some implementations, the marking module 903 is further used to:
[0145] According to the first marked point, determine the starting point and the end point of the straight line;
[0146] Determine the second dimension point between the start and end points.
[0147] In some implementations, the marking module 903 is further used to:
[0148] Determine the curve data of the curve where the first marked point is located;
[0149] According to the curve data, a second marking point is determined between adjacent first marking points.
[0150] In some implementations, the display module 901 is also used for:
[0151] Obtain an initial road image taken by a fisheye camera;
[0152] Performing dedistortion processing on the initial road image to obtain a road image;
[0153] Displays road images.
[0154] Fig.10 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Fig.10 As shown, the electronic device 100 includes:
[0155] The electronic device 100 may include a processor 1001 with one or more processing cores, a memory 1002 with one or more computer-readable storage media, a communication component 1003 and other components. The processor 1001, the memory 1002 and the communication component 1003 are connected via a bus 1004.
[0156] In a specific implementation process, at least one processor 1001 executes computer-executable instructions stored in the memory 1002, so that at least one processor 1001 executes the above lane line marking method.
[0157] The specific implementation process of the processor 1001 can be found in the above method embodiment, and its implementation principle and technical effect are similar, so this embodiment will not be repeated here.
[0158] In the above Fig.10In the illustrated embodiment, it should be understood that the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. A general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in the invention may be directly implemented as being executed by a hardware processor, or may be executed by a combination of hardware and software modules in the processor.
[0159] The memory may include a high-speed memory (Random Access Memory, RAM), and may also include a non-volatile memory (Non-volatile Memory, NVM), such as at least one disk memory.
[0160] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the bus in the drawings of the present application is not limited to only one bus or one type of bus.
[0161] In some embodiments, a computer program product is also proposed, including a computer program or instructions, which implement the steps in any of the above lane line marking methods when executed by a processor.
[0162] The specific implementation of the above operations can be found in the previous embodiments, which will not be described in detail here.
[0163] A person of ordinary skill in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be completed by instructions, or by controlling related hardware through instructions. The instructions may be stored in a computer-readable storage medium and loaded and executed by a processor.
[0164] To this end, an embodiment of the present application provides a computer-readable storage medium, in which multiple instructions are stored, and the instructions can be loaded by a processor to execute the steps in any lane line marking method provided in the embodiment of the present application.
[0165] The storage medium may include: a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.
[0166] According to one aspect of the present application, a computer program product or a computer program is provided. The computer program product or the computer program comprises computer instructions stored in a computer-readable storage medium.
[0167] Since the instructions stored in the storage medium can execute the steps in any lane line marking method provided in the embodiments of the present application, the beneficial effects that can be achieved by any lane line marking method provided in the embodiments of the present application can be achieved. Please refer to the previous embodiments for details and will not be repeated here.
[0168] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any modification, use or adaptation of the present application, which follows the general principles of the present application and includes common knowledge or customary techniques in the art that are not disclosed in the present application. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present application are indicated by the following claims.
[0169] It should be understood that the present application is not limited to the precise structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.
Claims
1. A lane marking method, characterized in that: include: Display road images taken by a fisheye camera; In response to the marking process of the lane line in the road image, a first marking point after the marking process is performed is obtained; According to the first marking point, the lane line is automatically supplemented with marking points.
2. The method according to claim 1, characterized in that The automatically supplementing the lane line with annotation points according to the first annotation point includes: Determine a marking type according to the first marking point, wherein the marking type includes a straight line type and a cubic spline curve type; The lane line is automatically supplemented with annotation points according to the annotation type to obtain second annotation points, and the distance between any two adjacent annotation points of the first annotation points and the second annotation points meets a preset distance requirement.
3. The method according to claim 2, characterized in that The step of determining the annotation type according to the first annotation point includes: If the first marking points are on the same straight line, determining the marking type to be a straight line type; If the first marking points are not on the same straight line, the marking type is determined to be a cubic spline curve type.
4. The method according to claim 2, characterized in that: When the annotation type is a straight line type, The automatically supplementing the lane line with annotation points according to the annotation type to obtain a second annotation point includes: Determine the starting point and the end point of the straight line according to the first marked point; A second marking point is determined between the starting point and the end point.
5. The method according to claim 2, characterized in that: When the annotation type is a cubic spline curve type, The automatically supplementing the lane line with annotation points according to the annotation type to obtain a second annotation point includes: Determine curve data of the curve where the first marked point is located; According to the curve data, a second marking point is determined between adjacent first marking points.
6. The method according to any one of claims 1 to 5, characterized in that: The display of the road image captured by the fisheye camera includes: Obtain an initial road image taken by a fisheye camera; Performing a dedistortion process on the initial road image to obtain a road image; The road image is displayed.
7. The method according to claim 6, characterized in that The method further comprises: According to the marking result of the lane line, converting the marking result into the coordinate system of the initial road image to obtain a third marking point; Annotate the initial lane line in the initial road image according to the third annotation point.
8. A lane marking device, characterized in that: include: A display module, used for displaying the road image captured by the fisheye camera; A response module, configured to respond to the marking process of the lane line in the road image and obtain a first marking point after the marking process is performed; A marking module is used to automatically supplement marking points for the lane line according to the first marking points.
9. An electronic device, characterized in that: include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 7 when executed by a processor.