Lane line distance detection method, device, equipment and medium

Abstract

The embodiments of the present application disclose a lane line distance detection method, device, equipment and medium. The lane line image is obtained by a monitoring device installed on the vehicle; the coordinates of the key points of the lane in the image coordinate system corresponding to the lane line image are obtained; the internal parameter calibration of the monitoring device is performed to obtain the internal parameter matrix; based on the preset vehicle projection model, the proportional coefficient is obtained; wherein the proportional coefficient is related to the projection distance corresponding to the actual distance between the current vehicle and the target point, and the vertical distance between the monitoring device and the ground; based on the internal parameter matrix and the proportional coefficient corresponding to the monitoring device, a first coordinate system conversion equation is established; according to the preset compensation coefficient, the first coordinate system conversion equation is updated to obtain a second coordinate system conversion equation, so as to obtain the distance between the lane line and the vehicle through the second coordinate system conversion equation. The above method improves the accuracy of lane line distance detection.

Description

Technical Field

[0001] The present application relates to the field of computer vision technology, and in particular to a lane line distance detection method, device, equipment and medium. Background Art

[0002] With the continuous development of computer technology and computer hardware, the field of machine vision has made rapid progress and has been widely used in academia and industry. In recent years, the progress of multimodal information technology fusion and the development of various segmentation detection networks have also prompted the development of autonomous driving to a new stage.

[0003] Lane lines are lane markings that guide the direction. They are used to indicate that vehicles should drive in the indicated direction when entering the intersection. Such markings are usually drawn at traffic intersections with heavy traffic, with the purpose of clarifying the driving direction, allowing each vehicle to drive in its own lane, and alleviating traffic pressure. Lane line distance detection is to detect the distance between the vehicle and the lane line on the current road to provide data support for autonomous driving and automatic assisted driving. However, the existing lane line image recognition usually outputs coordinates in a two-dimensional image coordinate system, which is difficult to meet the needs of autonomous driving technology, making it difficult to accurately measure the distance between the vehicle and the lane line. Summary of the invention

[0004] The embodiments of the present application provide a lane line distance detection method, device, equipment and medium for solving the following technical problem: it is difficult to accurately measure the distance between a vehicle and a lane line with the existing technology.

[0005] The present application embodiment adopts the following technical solutions:

[0006] The embodiment of the present application provides a lane line distance detection method. It includes: calibrating the internal parameters of the monitoring device to obtain the internal parameter matrix; obtaining the proportional coefficient based on the preset vehicle projection model; wherein the proportional coefficient is related to the projection distance corresponding to the actual distance between the current vehicle and the target point, and the vertical distance between the monitoring device and the ground; establishing a first coordinate system conversion equation based on the internal parameter matrix and the proportional coefficient corresponding to the monitoring device; wherein the first coordinate system conversion equation is used to realize the conversion of the coordinates of the key points of the lane between the image coordinate system and the monitoring device coordinate system; according to the preset compensation coefficient, the first coordinate system conversion equation is updated to obtain the second coordinate system conversion equation, so as to obtain the distance between the lane line and the vehicle through the second coordinate system conversion equation.

[0007] The embodiment of the present application calibrates the monitoring device to obtain the internal parameter matrix corresponding to the monitoring device, so that the coordinate information of the acquired two-dimensional image of the lane line can be converted into three-dimensional information through the internal parameter matrix. Secondly, the embodiment of the present application obtains the proportional coefficient based on the preset vehicle projection model, so as to determine the distance between the vehicle and the target point in different coordinate systems. In addition, since the distance of the acquired lane line will have errors, and the error values ​​corresponding to different vehicle speeds are also different, the embodiment of the present application updates the coordinate system conversion equation by presetting the compensation coefficient, so that the distance between the vehicle and the lane line is more accurate, thereby better assisting the vehicle in automatic driving.

[0008] In one implementation of the present application, based on a preset vehicle projection model, before obtaining the proportional coefficient, the method also includes: obtaining the pitch angle corresponding to the monitoring device, and determining the sine function value and the cosine function value corresponding to the pitch angle; based on the sine function value and the cosine function value corresponding to the pitch angle, constructing a pitch angle compensation matrix to obtain the proportional coefficient based on the pitch angle compensation matrix.

[0009] In one implementation of the present application, a proportional coefficient is obtained based on a preset vehicle projection model, specifically including: obtaining the vertical distance between the monitoring device and the ground; obtaining the proportional coefficient based on the pitch angle compensation matrix, the internal parameter matrix corresponding to the monitoring device and the vertical distance.

[0010] The embodiment of the present application takes into account the pitch angle problem of the monitoring device and constructs a pitch angle compensation matrix, through which the accuracy of the acquired lane line data can be improved, thereby reducing the measurement error and further improving the accuracy of the acquired lane line distance.

[0011] In one implementation of the present application, a proportional coefficient is obtained based on a pitch angle compensation matrix, an internal parameter matrix corresponding to a monitoring device, and a vertical distance, specifically including: obtaining a projection distance corresponding to the actual distance between the current vehicle and the target point; determining a ratio between the vertical distance and the projection distance, and using the ratio as a reference proportional coefficient; obtaining the proportional coefficient based on the reference proportional coefficient, a pitch angle compensation matrix, and an internal parameter matrix corresponding to a monitoring device.

[0012] In one implementation of the present application, a first coordinate system transformation equation is established based on the internal parameter matrix and the proportional coefficient corresponding to the monitoring device, specifically including: multiplying the proportional coefficient, the internal parameter matrix corresponding to the monitoring device, and the matrix corresponding to the lane key points to obtain the first coordinate system transformation equation.

[0013] In one implementation of the present application, before updating the first coordinate system transformation equation according to the preset compensation coefficient, the method also includes: acquiring lane line data corresponding to different vehicle speeds, so as to determine the lane line widths to be measured corresponding to different vehicle speeds according to the lane line data; establishing a compensation coefficient calibration table according to the lane line widths to be measured corresponding to different vehicle speeds and the actual widths of the lane lines, so as to determine the preset compensation coefficient according to the compensation coefficient calibration table.

[0014] In one implementation of the present application, the first coordinate system transformation equation is updated according to the preset compensation coefficient to obtain the second coordinate system transformation equation, which specifically includes: multiplying the preset compensation coefficient, the lane key point projection ratio coefficient, the internal parameter matrix corresponding to the monitoring device, and the matrix corresponding to the lane key point to obtain the second coordinate system transformation equation.

[0015] The embodiment of the present application provides a lane line distance detection device, including: a lane line acquisition unit, which acquires a lane line image through a monitoring device installed on a vehicle; a lane key point coordinate acquisition unit, which acquires the lane key point coordinates in the image coordinate system corresponding to the lane line image; wherein the lane key points include the starting point and the ending point of the lane line; an internal parameter matrix acquisition unit, which performs internal parameter calibration on the monitoring device to obtain the internal parameter matrix; a proportional coefficient acquisition unit, which acquires the proportional coefficient based on a preset vehicle projection model; wherein the proportional coefficient is related to the projection distance corresponding to the actual distance between the current vehicle and the target point, and the vertical distance between the monitoring device and the ground; a coordinate system conversion first equation establishment unit, which establishes a coordinate system conversion first equation based on the internal parameter matrix and the proportional coefficient corresponding to the monitoring device; wherein the coordinate system conversion first equation is used to realize the conversion of the lane key point coordinates between the image coordinate system and the monitoring device coordinate system; a coordinate system conversion second equation establishment unit, which updates the coordinate system conversion first equation according to the preset compensation coefficient to obtain the coordinate system conversion second equation, so as to obtain the distance between the lane line and the vehicle through the coordinate system conversion second equation.

[0016] A lane line distance detection device comprises: at least one processor; and a memory connected to the at least one processor in communication; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can: obtain a lane line image through a monitoring device installed on a vehicle; obtain the coordinates of lane key points in an image coordinate system corresponding to the lane line image; wherein the lane key points include a starting point and an end point of the lane line; perform internal parameter calibration on the monitoring device to obtain an internal parameter matrix; obtain a proportionality coefficient based on a preset vehicle projection model; wherein the proportionality coefficient is related to the projection distance corresponding to the actual distance between the current vehicle and the target point, and the vertical distance between the monitoring device and the ground; establish a first coordinate system conversion equation based on the internal parameter matrix and the proportionality coefficient corresponding to the monitoring device; wherein the first coordinate system conversion equation is used to realize the conversion of the lane key point coordinates between the image coordinate system and the monitoring device coordinate system; update the first coordinate system conversion equation according to the preset compensation coefficient to obtain a second coordinate system conversion equation, so as to obtain the distance between the lane line and the vehicle through the second coordinate system conversion equation.

[0017] A non-volatile computer storage medium provided in an embodiment of the present application stores computer executable instructions, and the computer executable instructions are configured to: obtain a lane line image through a monitoring device installed on a vehicle; obtain the coordinates of lane key points in an image coordinate system corresponding to the lane line image; wherein the lane key points include the starting point and the ending point of the lane line; perform internal parameter calibration on the monitoring device to obtain an internal parameter matrix; obtain a proportionality coefficient based on a preset vehicle projection model; wherein the proportionality coefficient is related to the projection distance corresponding to the actual distance between the current vehicle and the target point, and the vertical distance between the monitoring device and the ground; establish a first coordinate system conversion equation based on the internal parameter matrix and the proportionality coefficient corresponding to the monitoring device; wherein the first coordinate system conversion equation is used to realize the conversion of the lane key point coordinates between the image coordinate system and the monitoring device coordinate system; update the first coordinate system conversion equation according to the preset compensation coefficient to obtain a second coordinate system conversion equation, so as to obtain the distance between the lane line and the vehicle through the second coordinate system conversion equation.

[0018] At least one of the above technical solutions adopted in the embodiments of the present application can achieve the following beneficial effects: the embodiments of the present application calibrate the monitoring device to obtain the internal parameter matrix corresponding to the monitoring device, so that the coordinate information of the acquired two-dimensional image of the lane line can be converted into three-dimensional information through the internal parameter matrix. Secondly, the embodiments of the present application will obtain the proportional coefficient according to the preset vehicle projection model, so as to determine the distance between the vehicle and the target point in different coordinate systems. In addition, since there will be errors in the distance of the acquired lane line, and the error values ​​corresponding to different vehicle speeds are also different, the embodiments of the present application update the coordinate system conversion equation by presetting the compensation coefficient, so that the distance between the vehicle and the lane line is more accurate, thereby better assisting the vehicle in automatic driving. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. In the drawings:

[0020] Figure 1 A flow chart of a lane line distance detection method provided in an embodiment of the present application;

[0021] Figure 2 A projection diagram of a monitoring device provided in an embodiment of the present application;

[0022] Figure 3 A schematic diagram of the structure of a lane line distance detection device provided in an embodiment of the present application;

[0023] Figure 4 A schematic diagram of the structure of a lane line distance detection device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0024] Embodiments of the present application provide a lane line distance detection method, device, equipment and medium.

[0025] In order to enable those skilled in the art to better understand the technical solutions in this application, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are only part of the embodiments of this application, not all of them. Based on the embodiments of this specification, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this application.

[0026] With the continuous development of computer technology and computer hardware, the field of machine vision has made rapid progress and has been widely used in academia and industry. In recent years, the progress of multimodal information technology fusion and the development of various segmentation detection networks have also prompted the development of autonomous driving to a new stage.

[0027] Lane lines are lane markings that guide the direction. They are used to indicate that vehicles should drive in the indicated direction when entering the intersection. Such markings are usually drawn at traffic intersections with heavy traffic, with the purpose of clarifying the driving direction, allowing each vehicle to drive in its own lane, and alleviating traffic pressure. Lane line distance detection is to detect the distance between the vehicle and the lane line on the current road to provide data support for autonomous driving and automatic assisted driving. However, the existing lane line image recognition usually outputs coordinates in a two-dimensional image coordinate system, which is difficult to meet the needs of autonomous driving technology, making it difficult to accurately measure the distance between the vehicle and the lane line.

[0028] In order to solve the above problems, the embodiments of the present application provide a lane line distance detection method, device, equipment and medium. By calibrating the monitoring device, the internal parameter matrix corresponding to the monitoring device is obtained, so that the coordinate information of the acquired two-dimensional image of the lane line can be converted into three-dimensional information through the internal parameter matrix. Secondly, the embodiment of the present application will obtain the proportional coefficient according to the preset vehicle projection model, so as to determine the distance between the vehicle and the target point in different coordinate systems. In addition, since there will be errors in the distance of the acquired lane line, and the error values ​​corresponding to different vehicle speeds are also different, the embodiment of the present application updates the coordinate system conversion equation by presetting the compensation coefficient, so that the distance between the vehicle and the lane line is more accurate, thereby better assisting the vehicle in automatic driving.

[0029] The technical solution proposed in the embodiments of the present application is described in detail below with reference to the accompanying drawings.

[0030] Figure 1 A flow chart of a lane line distance detection method provided in an embodiment of the present application. Figure 1 As shown, the lane line distance detection method includes the following steps:

[0031] S101. Acquire a lane line image through a monitoring device installed on a vehicle.

[0032] In one embodiment of the present application, a monitoring device is pre-installed on the vehicle. The monitoring device in the embodiment of the present application can be a non-depth monocular camera. The monitoring device is used to photograph the road conditions, and the photographed road conditions are used to assist the vehicle in automatic driving.

[0033] Specifically, the road condition can be photographed by a non-depth monocular camera, and the photographing can be performed in real time or at a fixed time as required. The image information of the lane line on the current road surface can be obtained through the photographed road image.

[0034] Specifically, in the autonomous driving perception system, cameras are indispensable as a major sensor, especially for lane line recognition, where cameras have unique advantages. Compared with the large amount of computation required for binocular vision, the number of communication interfaces occupied, and the complexity of the mechanical layout of miniaturized intelligent driving robot perception equipment, monocular vision is extremely popular. At the same time, compared with the price difference between monocular depth cameras and non-depth cameras, monocular non-depth cameras have better industrial implementation.

[0035] S102. The controller obtains the coordinates of the lane key points in the image coordinate system corresponding to the lane line image.

[0036] In one embodiment of the present application, the acquired lane line image is recognized by a deep learning algorithm to obtain the coordinates corresponding to the lane lines in the image.

[0037] Specifically, multiple lane line images and the coordinates of the starting points and the ending points corresponding to the multiple lane line images can be collected in advance as a training set. The multiple lane line images collected in advance are used as inputs of a preset neural network model, and the coordinates of the starting points and the ending points corresponding to each lane line image are used as outputs. The preset neural network model is trained to obtain a lane key point recognition model.

[0038] Furthermore, the lane line image acquired by the monitoring device of the current vehicle is input into the lane key point recognition model, and the lane line in the image is determined by the lane key point recognition model, and the coordinates of the starting point and the ending point corresponding to the lane line are obtained.

[0039] It should be noted that the coordinates obtained by the lane key point recognition model are coordinates in a two-dimensional image coordinate system. In order to meet the coordinate system requirements of autonomous driving technology, the coordinates in the two-dimensional image coordinate system need to be converted into three-dimensional coordinates.

[0040] S103, calibrating the internal parameters of the monitoring device to obtain an internal parameter matrix.

[0041] In one embodiment of the present application, when the coordinate system is converted, the monitoring device needs to be calibrated, that is, the camera is calibrated to obtain the camera internal parameter matrix K, K = [f 0 u; 0 fv; 0 0 1].

[0042] S104: The controller obtains a scale factor based on a preset vehicle projection model.

[0043] In one embodiment of the present application, the controller obtains the pitch angle corresponding to the monitoring device, and determines the sine function value and cosine function value corresponding to the pitch angle. Based on the sine function value and cosine function value corresponding to the pitch angle, a pitch angle compensation matrix is ​​constructed to obtain a proportional coefficient based on the pitch angle matrix.

[0044] Specifically, the pitch angle of the camera installed on the vehicle is pitch. At this time, the pitch angle compensation matrix established is:

[0045]

[0046] In one embodiment of the present application, the vertical distance between the monitoring device and the ground is obtained. Based on the pitch angle compensation matrix, the internal parameter matrix corresponding to the monitoring device, and the vertical distance, a proportional coefficient is obtained. The proportional coefficient is related to the projection distance corresponding to the actual distance between the current vehicle and the target point, and the vertical distance between the monitoring device and the ground.

[0047] Specifically, the projection distance corresponding to the actual distance between the current vehicle and the target point is obtained. The ratio between the vertical distance and the projection distance is determined, and the ratio is used as a reference proportional coefficient. The proportional coefficient is obtained based on the reference proportional coefficient, the pitch angle compensation matrix, and the internal reference matrix corresponding to the monitoring device.

[0048] Specifically, the camera is calibrated to obtain the camera internal parameter matrix K, K = [f 0 u; 0 fv; 0 0 1]. The camera height above the ground is measured as camera_ground_height. Assuming that the image coordinate system is the lane sampling point coordinate (x, y), the formula can be obtained at this time

[0049]

[0050] S=camera_ground_height / R(1,0) (2)

[0051] In one embodiment of the present application, a common non-depth camera has no longitudinal depth information and cannot obtain the proportionality coefficient S, so a distance transformation method is used to obtain the proportionality coefficient. Figure 2 A projection diagram of a monitoring device provided in an embodiment of the present application. Figure 2 As shown in the figure, A is the current vehicle, B and C are the vehicles in front, assuming that point P of vehicle A is the camera position, and the distance Z1 from point P to vehicle B is projected in the camera as y1. Considering the proportional relationship of similar triangles, the preliminary calculation formula for the proportional coefficient S is: S = H / y1. Considering that the pitch angle of the front camera is not completely vertical, a pitch angle compensation matrix is ​​added. Adding the inverse matrix transformation of the camera internal parameters, the above formulas (1) and (2) are obtained.

[0052] S105. The controller establishes a first coordinate system conversion equation based on the internal parameter matrix and the proportional coefficient corresponding to the monitoring device.

[0053] In one embodiment of the present application, the scale factor, the internal parameter matrix corresponding to the monitoring device, and the matrix corresponding to the lane key points are multiplied to obtain the first coordinate system conversion equation, wherein the first coordinate system conversion equation is used to realize the conversion between the image coordinate system and the monitoring device coordinate system.

[0054] Specifically, based on the obtained proportional coefficient S, the internal parameter matrix K corresponding to the monitoring device, and the matrix corresponding to the lane key points, the first coordinate system transformation equation can be obtained:

[0055]

[0056] Among them, f is the intrinsic parameter obtained by different camera calibrations. Its physical meaning is the focal length of a square pixel sensor in pixels. u and v are the coordinates of the center of the optical axis in the pixel coordinate system of the image plane when the camera is projected. X, Y, and Z are the coordinates in the camera coordinate system.

[0057] After calculation, we can get the formula of lane points in the camera coordinate system. The coordinate X of the lane line on the left side of the vehicle is a negative value, and the coordinate X of the lane line point on the right side is a positive value.

[0058] S106. The controller updates the first coordinate system conversion equation according to a preset compensation coefficient to obtain a second coordinate system conversion equation, so as to obtain the distance between the lane line and the vehicle through the second coordinate system conversion equation.

[0059] In one embodiment of the present application, the controller obtains lane line data corresponding to different vehicle speeds, and determines the lane line widths to be measured corresponding to different vehicle speeds according to the lane line data. According to the lane line widths to be measured corresponding to different vehicle speeds and the actual lane line widths, a compensation coefficient calibration table is established to determine the preset compensation coefficient according to the compensation coefficient calibration table.

[0060] Specifically, the lane line width can be obtained based on the acquired lane line coordinates. By comparing the acquired lane line width with the actual lane line width, it can be found that there is an error between the acquired lane line width and the actual lane line width, and the error is about 5%. Therefore, in order to reduce the error and improve the accuracy of the acquired lane line coordinates, it is necessary to determine the compensation coefficient to update the formula.

[0061] Furthermore, multiple sets of lane line data are collected at different vehicle speeds, as well as the actual lane line width. A compensation coefficient calibration table is prepared based on the collected lane line data and the actual lane line width to obtain the compensation coefficient K:

[0062] K=f(v)

[0063] Furthermore, according to the current vehicle speed, a corresponding compensation coefficient is selected from the compensation coefficient calibration table, so as to reduce the error of the obtained lane line coordinate point by the compensation coefficient.

[0064] In one embodiment of the present application, the preset compensation coefficient, the lane key point projection ratio coefficient, the internal parameter matrix corresponding to the monitoring device, and the matrix corresponding to the lane key point are multiplied to obtain the second coordinate system transformation equation.

[0065] Specifically, according to the formula

[0066]

[0067] The new camera coordinate system sampling point coordinates (X, Y, Z) can be obtained. The distance between the lane line and the vehicle can be determined through the sampling point coordinates of the camera coordinate system. Among them, f is the self-parameter obtained by different camera calibrations, and its physical meaning is the focal length of the square pixel sensor in pixels. u and v are the coordinates of the center of the optical axis in the image plane pixel coordinate system when the camera is projected. X, Y, and Z are the coordinates in the camera coordinate system respectively.

[0068] Figure 3 A schematic diagram of the structure of a lane distance detection device provided in an embodiment of the present application. Figure 3 As shown, the lane line distance detection device includes a lane line acquisition unit 301, a lane key point coordinate acquisition unit 302, an internal parameter matrix acquisition unit 303, a proportional coefficient acquisition unit 304, a coordinate system conversion first equation establishment unit 305, and a coordinate system conversion second equation establishment unit 306.

[0069] The lane line acquisition unit 301 acquires a lane line image through a monitoring device installed on the vehicle;

[0070] A lane key point coordinate acquisition unit 302 is used to acquire the lane key point coordinates in the image coordinate system corresponding to the lane line image; wherein the lane key points include the starting point and the ending point of the lane line;

[0071] The internal parameter matrix acquisition unit 303 performs internal parameter calibration on the monitoring device to obtain an internal parameter matrix;

[0072] The proportionality coefficient acquisition unit 304 acquires the proportionality coefficient based on the preset vehicle projection model; wherein the proportionality coefficient is related to the projection distance corresponding to the actual distance between the current vehicle and the target point, and the vertical distance between the monitoring device and the ground;

[0073] A coordinate system conversion first equation establishing unit 305 establishes a coordinate system conversion first equation based on the internal parameter matrix corresponding to the monitoring device and the proportional coefficient; wherein the coordinate system conversion first equation is used to realize the conversion of the lane key point coordinates between the image coordinate system and the monitoring device coordinate system;

[0074] The coordinate system conversion second equation establishing unit 306 updates the coordinate system conversion first equation according to a preset compensation coefficient to obtain a coordinate system conversion second equation, so as to obtain the distance between the lane line and the vehicle through the coordinate system conversion second equation.

[0075] Furthermore, the device also includes:

[0076] The pitch angle compensation matrix determination unit 307 obtains the pitch angle corresponding to the monitoring device, and determines the sine function value and the cosine function value corresponding to the pitch angle; constructs a pitch angle compensation matrix based on the sine function value and the cosine function value corresponding to the pitch angle, so as to obtain the proportional coefficient based on the pitch angle compensation matrix.

[0077] Furthermore, the device also includes:

[0078] The proportionality coefficient acquisition unit 308 acquires the vertical distance between the monitoring device and the ground; and obtains the proportionality coefficient based on the pitch angle compensation matrix, the internal parameter matrix corresponding to the monitoring device and the vertical distance.

[0079] Furthermore, the device also includes:

[0080] The proportional coefficient determination unit 309 obtains the projection distance corresponding to the actual distance between the current vehicle and the target point; determines the ratio between the vertical distance and the projection distance, and uses the ratio as a reference proportional coefficient; obtains the proportional coefficient based on the reference proportional coefficient, the pitch angle compensation matrix and the internal parameter matrix corresponding to the monitoring device.

[0081] Furthermore, the device also includes:

[0082] The product calculation unit 310 performs product calculation on the proportional coefficient, the internal parameter matrix corresponding to the monitoring device, and the matrix corresponding to the lane key points to obtain the first coordinate system transformation equation.

[0083] Furthermore, the device also includes:

[0084] The preset compensation coefficient determination unit 311 obtains lane line data corresponding to different vehicle speeds to determine the lane line widths to be measured corresponding to different vehicle speeds according to the lane line data; a compensation coefficient calibration table is established according to the lane line widths to be measured corresponding to the different vehicle speeds and the actual lane line widths, so as to determine the preset compensation coefficient according to the compensation coefficient calibration table.

[0085] Furthermore, the device also includes:

[0086] The coordinate system conversion equation updating unit 312 calculates the product of the preset compensation coefficient, the lane key point projection ratio coefficient, the internal parameter matrix corresponding to the monitoring device, and the matrix corresponding to the lane key point to obtain the second coordinate system conversion equation.

[0087] Figure 4 A schematic diagram of the structure of a lane distance detection device provided in an embodiment of the present application. Figure 4 As shown, the lane line distance detection device includes:

[0088] at least one processor; and,

[0089] a memory communicatively connected to the at least one processor; wherein,

[0090] The memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to:

[0091] Acquire lane line images through a monitoring device installed on the vehicle;

[0092] Acquire the coordinates of the lane key points in the image coordinate system corresponding to the lane line image; wherein the lane key points include the starting point and the ending point of the lane line;

[0093] Performing internal parameter calibration on the monitoring device to obtain an internal parameter matrix;

[0094] Based on the preset vehicle projection model, a proportionality coefficient is obtained; wherein the proportionality coefficient is related to the projection distance corresponding to the actual distance between the current vehicle and the target point, and the vertical distance between the monitoring device and the ground;

[0095] Based on the internal parameter matrix corresponding to the monitoring device and the proportional coefficient, a first coordinate system conversion equation is established; wherein the first coordinate system conversion equation is used to realize the conversion of the coordinates of the key points of the lane between the image coordinate system and the monitoring device coordinate system;

[0096] The first coordinate system conversion equation is updated according to the preset compensation coefficient to obtain a second coordinate system conversion equation, so as to obtain the distance between the lane line and the vehicle through the second coordinate system conversion equation.

[0097] The embodiment of the present application further provides a non-volatile computer storage medium storing computer executable instructions, wherein the computer executable instructions are configured as follows:

[0098] Acquire lane line images through a monitoring device installed on the vehicle;

[0099] Acquire the coordinates of the lane key points in the image coordinate system corresponding to the lane line image; wherein the lane key points include the starting point and the ending point of the lane line;

[0100] Performing internal parameter calibration on the monitoring device to obtain an internal parameter matrix;

[0101] Based on the preset vehicle projection model, a proportionality coefficient is obtained; wherein the proportionality coefficient is related to the projection distance corresponding to the actual distance between the current vehicle and the target point, and the vertical distance between the monitoring device and the ground;

[0102] Based on the internal parameter matrix corresponding to the monitoring device and the proportional coefficient, a first coordinate system conversion equation is established; wherein the first coordinate system conversion equation is used to realize the conversion of the coordinates of the key points of the lane between the image coordinate system and the monitoring device coordinate system;

[0103] The first coordinate system conversion equation is updated according to the preset compensation coefficient to obtain a second coordinate system conversion equation, so as to obtain the distance between the lane line and the vehicle through the second coordinate system conversion equation.

[0104] Each embodiment in this application is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device, equipment, and non-volatile computer storage medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0105] The above describes specific embodiments of the present application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0106] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the embodiments of the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the embodiments of the present application should be included in the scope of the claims of the present application.

Claims

1. A lane line distance detection method, characterized in that: The method comprises: Acquire lane line images through a monitoring device installed on the vehicle; Acquire the coordinates of the lane key points in the image coordinate system corresponding to the lane line image; wherein the lane key points include the starting point and the ending point of the lane line; Performing internal parameter calibration on the monitoring device to obtain an internal parameter matrix; Based on the preset vehicle projection model, a proportionality coefficient is obtained; wherein the proportionality coefficient is related to the projection distance corresponding to the actual distance between the current vehicle and the target point, and the vertical distance between the monitoring device and the ground; Based on the internal parameter matrix corresponding to the monitoring device and the proportional coefficient, a first coordinate system conversion equation is established; wherein the first coordinate system conversion equation is used to realize the conversion of the coordinates of the key points of the lane between the image coordinate system and the monitoring device coordinate system; According to the preset compensation coefficient, the first coordinate system conversion equation is updated to obtain a second coordinate system conversion equation, so as to obtain the distance between the lane line and the vehicle through the second coordinate system conversion equation; Before updating the first coordinate system conversion equation according to the preset compensation coefficient, the method further includes: Acquire lane line data corresponding to different vehicle speeds, so as to determine lane line widths to be measured corresponding to different vehicle speeds according to the lane line data; A compensation coefficient calibration table is established according to the lane line widths to be measured and the actual lane line widths corresponding to the different vehicle speeds, so as to determine the preset compensation coefficient according to the compensation coefficient calibration table.

2. A lane line distance detection method according to claim 1, characterized in that: Before obtaining the scale factor based on the preset vehicle projection model, the method further includes: Obtaining the pitch angle corresponding to the monitoring device, and determining the sine function value and cosine function value corresponding to the pitch angle; A pitch angle compensation matrix is ​​constructed based on the sine function value and the cosine function value corresponding to the pitch angle, so as to obtain the proportional coefficient based on the pitch angle compensation matrix.

3. A lane line distance detection method according to claim 2, characterized in that: The obtaining of the scale factor based on the preset vehicle projection model specifically includes: Obtaining the vertical distance between the monitoring device and the ground; The proportional coefficient is obtained based on the pitch angle compensation matrix, the internal parameter matrix corresponding to the monitoring device and the vertical distance.

4. A lane line distance detection method according to claim 3, characterized in that: The obtaining of the proportional coefficient based on the pitch angle compensation matrix, the internal parameter matrix corresponding to the monitoring device and the vertical distance specifically includes: Get the projection distance corresponding to the actual distance between the current vehicle and the target point; Determine a ratio between the vertical distance and the projection distance, and use the ratio as a reference proportionality factor; The proportional coefficient is obtained based on the reference proportional coefficient, the pitch angle compensation matrix and the internal parameter matrix corresponding to the monitoring device.

5. The lane line distance detection method according to claim 1, characterized in that: The first coordinate system conversion equation is established based on the internal parameter matrix corresponding to the monitoring device and the proportional coefficient, specifically including: The first coordinate system transformation equation is obtained by multiplying the proportional coefficient, the internal parameter matrix corresponding to the monitoring device, and the matrix corresponding to the lane key points.

6. A lane line distance detection method according to claim 1, characterized in that: The updating of the first coordinate system conversion equation according to the preset compensation coefficient to obtain the second coordinate system conversion equation specifically includes: The preset compensation coefficient, the proportional coefficient, the internal parameter matrix corresponding to the monitoring device and the matrix corresponding to the lane key point are multiplied to obtain the second coordinate system conversion equation.

7. A lane line distance detection device, comprising: A lane line acquisition unit acquires lane line images through a monitoring device installed on the vehicle; A lane key point coordinate acquisition unit is used to acquire the lane key point coordinates in the image coordinate system corresponding to the lane line image; wherein the lane key points include the starting point and the ending point of the lane line; An internal parameter matrix acquisition unit performs internal parameter calibration on the monitoring device to obtain an internal parameter matrix; A proportional coefficient acquisition unit is configured to acquire a proportional coefficient based on a preset vehicle projection model; wherein the proportional coefficient is related to a projection distance corresponding to an actual distance between the current vehicle and the target point, and a vertical distance between the monitoring device and the ground; A coordinate system conversion first equation establishing unit is used to establish a coordinate system conversion first equation based on the internal parameter matrix corresponding to the monitoring device and the proportional coefficient; wherein the coordinate system conversion first equation is used to realize the conversion of the lane key point coordinates between the image coordinate system and the monitoring device coordinate system; The coordinate system conversion second equation establishing unit updates the first coordinate system conversion equation according to a preset compensation coefficient to obtain the second coordinate system conversion equation, so as to obtain the distance between the lane line and the vehicle through the second coordinate system conversion equation; before updating the first coordinate system conversion equation according to the preset compensation coefficient, it also includes: acquiring lane line data corresponding to different vehicle speeds, so as to determine the lane line widths to be measured corresponding to different vehicle speeds according to the lane line data; establishing a compensation coefficient calibration table according to the lane line widths to be measured corresponding to the different vehicle speeds and the actual lane line width, so as to determine the preset compensation coefficient according to the compensation coefficient calibration table.

8. A lane distance detection device, comprising: at least one processor; as well as, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to: Acquire lane line images through a monitoring device installed on the vehicle; Acquire the coordinates of the lane key points in the image coordinate system corresponding to the lane line image; wherein the lane key points include the starting point and the ending point of the lane line; Performing internal parameter calibration on the monitoring device to obtain an internal parameter matrix; Based on the preset vehicle projection model, a proportionality coefficient is obtained; wherein the proportionality coefficient is related to the projection distance corresponding to the actual distance between the current vehicle and the target point, and the vertical distance between the monitoring device and the ground; Based on the internal parameter matrix corresponding to the monitoring device and the proportional coefficient, a first coordinate system conversion equation is established; wherein the first coordinate system conversion equation is used to realize the conversion of the coordinates of the key points of the lane between the image coordinate system and the monitoring device coordinate system; According to the preset compensation coefficient, the first coordinate system conversion equation is updated to obtain a second coordinate system conversion equation, so as to obtain the distance between the lane line and the vehicle through the second coordinate system conversion equation; Before updating the first coordinate system conversion equation according to the preset compensation coefficient, the method further includes: Acquire lane line data corresponding to different vehicle speeds, so as to determine lane line widths to be measured corresponding to different vehicle speeds according to the lane line data; A compensation coefficient calibration table is established according to the lane line widths to be measured and the actual lane line widths corresponding to the different vehicle speeds, so as to determine the preset compensation coefficient according to the compensation coefficient calibration table.

9. A non-volatile computer storage medium storing computer executable instructions, the computer The executable instructions are set to: Acquire lane line images through a monitoring device installed on the vehicle; Obtain the coordinates of the lane key points in the image coordinate system corresponding to the lane line image; wherein, The lane key points include the starting point and the ending point of the lane line; Performing internal parameter calibration on the monitoring device to obtain an internal parameter matrix; Based on the preset vehicle projection model, a proportionality coefficient is obtained; wherein the proportionality coefficient is related to the projection distance corresponding to the actual distance between the current vehicle and the target point, and the vertical distance between the monitoring device and the ground; Based on the internal parameter matrix corresponding to the monitoring device and the proportional coefficient, a first coordinate system conversion equation is established; wherein the first coordinate system conversion equation is used to realize the conversion of the coordinates of the key points of the lane between the image coordinate system and the monitoring device coordinate system; According to the preset compensation coefficient, the first coordinate system conversion equation is updated to obtain a second coordinate system conversion equation, so as to obtain the distance between the lane line and the vehicle through the second coordinate system conversion equation; Before updating the first coordinate system conversion equation according to the preset compensation coefficient, the method further includes: Acquire lane line data corresponding to different vehicle speeds, so as to determine lane line widths to be measured corresponding to different vehicle speeds according to the lane line data; A compensation coefficient calibration table is established according to the lane line widths to be measured and the actual lane line widths corresponding to the different vehicle speeds, so as to determine the preset compensation coefficient according to the compensation coefficient calibration table.

Images