Lane line information detection method and device, computer equipment, medium and product

Abstract

The invention relates to a lane line information detection method and device, computer equipment, a medium and a product. The method comprises the steps that the current illumination intensity of the environment where a target vehicle is located and the current vehicle speed of the target vehicle are acquired; according to the current illumination intensity and the current vehicle speed, determining a ground detection area of image detection equipment in the target vehicle and area position information of the ground detection area under a vehicle coordinate system; controlling an image detection device to collect a target detection image of the ground detection area; and detecting lane line information in the target detection image based on a lane line extraction model according to the region position information and the target detection image. By adopting the method, the lane line can be efficiently and accurately detected.

Description

Technical Field

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

[0002] During driving, lane lines play an extremely important role, indicating the direction of the road ahead, assisting drivers in road judgment, and timely changing lanes, turning, etc. In the front window navigation of the vehicle, real-time lane line information is also extremely important, which can provide road feature information such as the trend and parameters of the current lane, and guide the driver to correct navigation.

[0003] At present, deep learning methods are usually used to train lane detection models, and the lane detection model detects lanes. However, this method has high requirements on computing resources and data volume, requires strong computing power and a large amount of training data, and is highly affected by environmental interference, which leads to low efficiency and accuracy of lane information detection. Summary of the invention

[0004] Based on this, it is necessary to provide a lane line information detection method, device, computer equipment, medium and product that can efficiently and accurately detect lane lines in response to the above technical problems.

[0005] In a first aspect, the present application provides a lane line information detection method, comprising:

[0006] Obtaining the current light intensity of the environment in which the target vehicle is located and the current speed of the target vehicle;

[0007] Determine, according to the current light intensity and the current vehicle speed, a ground detection area of ​​an image detection device in the target vehicle, and regional position information of the ground detection area in a vehicle coordinate system;

[0008] Controlling the target detection image of the ground detection area collected by the image detection device;

[0009] Based on the lane line extraction model, the lane line information in the target detection image is detected according to the area position information and the target detection image.

[0010] In one embodiment, the ground detection area is a rectangular area, and the image detection device includes a camera; accordingly, determining the ground detection area of ​​the image detection device in the target vehicle and the regional position information of the ground detection area in the vehicle coordinate system according to the current light intensity and the current vehicle speed includes:

[0011] Determine the area width of the ground detection area and the farthest distance between the front of the target vehicle and the ground detection area according to the calibration information of the camera; wherein the shortest distance is the distance between the front of the target vehicle and the edge of the ground detection area close to the target vehicle;

[0012] Determine the area length of the ground detection area according to the current light intensity, the current vehicle speed, the calibration information and the closest distance; wherein the side corresponding to the area length is parallel to the driving direction of the target vehicle;

[0013] According to the area width and the area length, area position information of the ground detection area in the vehicle coordinate system of the target vehicle is determined.

[0014] In one embodiment, determining the area length of the ground detection area according to the current light intensity, the current vehicle speed, the calibration information and the closest distance includes:

[0015] Determining a distance threshold according to the body parameters of the target vehicle;

[0016] Determining a candidate maximum distance according to the current light intensity, the current vehicle speed and the closest distance;

[0017] Selecting a smaller value between the candidate maximum distance and the distance threshold as the target maximum distance;

[0018] The difference between the maximum target distance and the minimum target distance is used as the area length of the ground detection area.

[0019] In one embodiment, determining the candidate maximum distance according to the current light intensity, the current vehicle speed and the closest distance includes:

[0020] Determining a first distance according to the current vehicle speed and the shortest distance;

[0021] Determining a second distance according to the current illumination;

[0022] The absolute value of the difference between the product of the first distance and the preset first coefficient and the product of the second distance and the preset second coefficient is used as a candidate maximum distance.

[0023] In one embodiment, the lane line extraction model is based on the target detection image, and the lane line information in the target detection image is detected, including:

[0024] Determining first position information of each pixel in the target detection image according to the area position information of the ground detection area;

[0025] Inputting the target detection image and the first position information into a lane line extraction model to obtain an initial lane line image and second position information corresponding to each pixel point in the initial lane line image;

[0026] Preprocessing the initial lane line image; wherein the preprocessing includes grayscale processing and binarization processing;

[0027] The lane line information in the target detection image is detected according to the preprocessed initial lane line image and the second position information.

[0028] In one embodiment, the detecting the lane line information in the target detection image according to the preprocessed initial lane line image and the second position information includes:

[0029] According to the second position information, the preprocessed initial lane line image is subjected to an inverse perspective transformation to obtain a target lane line image and third position information corresponding to each pixel point in the target lane line image;

[0030] Based on a statistical filtering method, a pixel point corresponding to the lane line is selected from each pixel point in the target lane line image as a lane line pixel point;

[0031] The lane line pixel points are fitted to obtain the lane line information in the target detection image.

[0032] In a second aspect, the present application also provides a lane line information detection device, comprising:

[0033] An information acquisition module, used to acquire the current light intensity of the environment in which the target vehicle is located and the current speed of the target vehicle;

[0034] An area determination module, used to determine the ground detection area of ​​the image detection device in the target vehicle and the area position information of the ground detection area in the vehicle coordinate system according to the current light intensity and the current vehicle speed;

[0035] An image acquisition module, used for controlling the image detection device to acquire the target detection image of the ground detection area;

[0036] The information detection module is used to detect the lane line information in the target detection image based on the lane line extraction model according to the area position information and the target detection image.

[0037] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0038] Obtaining the current light intensity of the environment in which the target vehicle is located and the current speed of the target vehicle;

[0039] Determine, according to the current light intensity and the current vehicle speed, a ground detection area of ​​an image detection device in the target vehicle, and regional position information of the ground detection area in a vehicle coordinate system;

[0040] Controlling the target detection image of the ground detection area collected by the image detection device;

[0041] Based on the lane line extraction model, the lane line information in the target detection image is detected according to the area position information and the target detection image.

[0042] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0043] Obtaining the current light intensity of the environment in which the target vehicle is located and the current speed of the target vehicle;

[0044] Determine, according to the current light intensity and the current vehicle speed, a ground detection area of ​​an image detection device in the target vehicle, and regional position information of the ground detection area in a vehicle coordinate system;

[0045] Controlling the target detection image of the ground detection area collected by the image detection device;

[0046] Based on the lane line extraction model, the lane line information in the target detection image is detected according to the area position information and the target detection image.

[0047] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:

[0048] Obtaining the current light intensity of the environment in which the target vehicle is located and the current speed of the target vehicle;

[0049] Determine, according to the current light intensity and the current vehicle speed, a ground detection area of ​​an image detection device in the target vehicle, and regional position information of the ground detection area in a vehicle coordinate system;

[0050] Controlling the target detection image of the ground detection area collected by the image detection device;

[0051] Based on the lane line extraction model, the lane line information in the target detection image is detected according to the area position information and the target detection image.

[0052] The above lane line information detection method, device, computer equipment, medium and product obtain the current light intensity of the target vehicle's environment and the current speed of the target vehicle; determine the ground detection area of ​​the image detection device in the target vehicle and the regional position information of the ground detection area in the vehicle coordinate system based on the current light intensity and the current speed; control the target detection image of the ground detection area collected by the image detection device; based on the lane line extraction model, detect the lane line information in the target detection image according to the regional position information and the target detection image. The above scheme comprehensively considers the current light intensity of the target vehicle's environment and the current speed of the target vehicle, and adjusts and determines the ground detection area in real time, which meets the timeliness of the target vehicle's computing power, reduces the interference of traditional methods in lane line detection, and ensures the effectiveness and timeliness of the determined ground detection area; further, based on the lane line extraction model, the lane line information in the target detection image is detected according to the regional position information and the target detection image, thereby improving the detection efficiency and accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the drawings required for use in the embodiments or the related technical descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0054] Figure 1 A diagram showing an application environment of a lane line information detection method in an embodiment;

[0055] Figure 2 1 is a flow chart of a lane line information detection method in one embodiment;

[0056] Figure 3 A schematic diagram of a vehicle coordinate system and a ground detection area in an embodiment;

[0057] Figure 4 A schematic diagram of a process for determining regional location information in one embodiment;

[0058] Figure 5 A schematic diagram of a process for determining the area length of a ground detection area in one embodiment;

[0059] Figure 6 A schematic diagram of a process for determining a candidate maximum distance in one embodiment;

[0060] Figure 7 A schematic diagram of a process for detecting lane line information in one embodiment;

[0061] Figure 8 A schematic diagram of a process for detecting lane line information in another embodiment;

[0062] Fig. 9 is a schematic diagram of comparison between an initial lane line image and a target lane line image in one embodiment;

[0063] Fig.10 A schematic diagram of a process flow of a lane line information detection method in another embodiment;

[0064] Fig.11 is a structural block diagram of a lane line information detection device in one embodiment;

[0065] Fig.12 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0066] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0067] The lane line information detection method provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown. Among them, the image processing device 101 is a device in the target vehicle for processing the image collected by the image detection device 102; the image detection device 102 is a device installed at the front part of the target vehicle and used to collect images of the road on which the target vehicle is traveling. Optionally, after the image processing device 101 obtains the current light intensity of the environment in which the target vehicle is located and the current speed of the target vehicle, it determines the ground detection area of ​​the image detection device in the target vehicle and the regional position information of the ground detection area in the vehicle coordinate system according to the current light intensity and the current speed; and controls the target detection image of the ground detection area collected by the image detection device 102; further, based on the lane line extraction model, the lane line information in the target detection image is detected according to the regional position information and the target detection image.

[0068] In one embodiment, Figure 2 As shown, a lane line information detection method is provided, and the method is applied to Figure 1 The image processing device 101 in the embodiment is taken as an example to illustrate, which specifically includes the following steps:

[0069] S201, obtaining the current light intensity of the environment in which the target vehicle is located and the current speed of the target vehicle.

[0070] Among them, the current light intensity is the light intensity in the environment at the current moment; the current vehicle speed is the speed of the target vehicle at the current moment.

[0071] Optionally, the light information and speed information in the environment can be collected periodically through sensors or monitoring equipment installed in the target vehicle as the current light intensity and the current vehicle speed, respectively. For example, the light intensity measuring instrument installed on the vehicle body can be used to collect the light intensity in the environment as the current light intensity; at the same time, the speed of the target vehicle can be obtained through a speedometer installed in the vehicle as the current vehicle speed.

[0072] S202, determining a ground detection area of ​​an image detection device in a target vehicle and regional position information of the ground detection area in a vehicle coordinate system according to a current light intensity and a current vehicle speed.

[0073] Among them, the image detection device is a device in the target vehicle used to detect road conditions; the ground detection area is the ground area that can be detected by the image detection device. In the embodiment of the present application, the ground detection area is a rectangular area; the vehicle coordinate system is a coordinate system established with the vehicle as a reference, which is used to describe the movement of the car.

[0074] Optionally, since the vehicle head-up display system (HUD) is particularly sensitive to vehicle speed and light intensity, the display effect of the HUD will be affected during vehicle driving. Different vehicle speeds and different light intensity will result in different areas to be detected, that is, different ground detection areas. Therefore, the ground detection area of ​​the image detection device in the target vehicle can be adjusted according to the current light intensity and the current vehicle speed. Specifically, when the vehicle speed is slow and the light intensity is high, the ground detection area does not need to be selected too large, which can effectively reduce the data processing time and reduce the interference of other detection lines. When the vehicle speed is too fast or the light intensity is low, the ground detection area can be selected to expand the range to improve the stability of the detection, give the driver enough distance and time for processing, and can more accurately ensure better driving safety. Further, after determining the ground detection area, the coordinates of the ground detection area are calculated according to the pre-constructed vehicle coordinate system as the area position information.

[0075] Optionally, the vehicle coordinate system can be constructed with the center of mass of the vehicle or any point on the ground where the vehicle is located as the origin. Figure 3 As shown, the vehicle coordinate system and ground detection area constructed in the embodiment of the present application are shown. The vehicle coordinate system is constructed according to the right-hand rule, with a point on the ground to the left of the target vehicle's driving direction as the origin and the target vehicle's driving direction as the horizontal axis, i.e., the x-axis.

[0076] S203, controlling the image detection device to collect target detection images of the ground detection area.

[0077] The image detection device is a device installed at the front end of the target vehicle for collecting lane line images. The target detection image is an image including the ground detection area.

[0078] Optionally, after determining the area position information of the ground detection area, the image detection device is controlled to collect the target detection image of the ground detection area.

[0079] S204: Based on the lane line extraction model, the lane line information in the target detection image is detected according to the regional position information and the target detection image.

[0080] The lane line extraction model is a model used to extract lane lines contained in the target detection image.

[0081] Optionally, the region position information and the target detection image may be input into a lane line extraction model, so that the lane line extraction model extracts the lane line information in the target detection image according to the model parameters.

[0082] In the above lane line information detection method, the current light intensity of the target vehicle's environment and the current speed of the target vehicle are obtained; according to the current light intensity and the current speed, the ground detection area of ​​the image detection device in the target vehicle and the regional position information of the ground detection area in the vehicle coordinate system are determined; the target detection image of the ground detection area collected by the image detection device is controlled; based on the lane line extraction model, the lane line information in the target detection image is detected according to the regional position information and the target detection image. The above scheme comprehensively considers the current light intensity of the target vehicle's environment and the current speed of the target vehicle, and adjusts and determines the ground detection area in real time, which meets the timeliness of the target vehicle's computing power, reduces the interference of traditional methods in lane line detection, and ensures the effectiveness and timeliness of the determined ground detection area; further, based on the lane line extraction model, the lane line information in the target detection image is detected according to the regional position information and the target detection image, thereby improving the detection efficiency and accuracy.

[0083] Optionally, in an embodiment of the present application, the ground detection area is a rectangular area, and the image detection device includes a camera. On this basis, in order to ensure the accuracy of the determined regional location information, in one embodiment, Figure 4 As shown, a method for determining regional location information is provided, which specifically includes the following steps:

[0084] S401, determining the area width of the ground detection area and the shortest distance between the front of the target vehicle and the ground detection area according to the calibration information of the camera.

[0085] The camera calibration information includes the parameters of the geometric model for determining the camera imaging, and the calibration information is obtained through experiments and calculations; the area width is the width of the ground monitoring area. The closest distance is the distance between the front of the target vehicle and the edge of the ground detection area close to the target vehicle.

[0086] For example, Figure 3 As shown, Figure 3 The ground detection area is a rectangle ABCD, and the AD side is the width of the ground detection area. is the closest distance.

[0087] Optionally, the width that the camera can capture can be calculated based on the camera's calibration information and actual needs, and the obtained width can be used as the area width of the ground detection area and the closest distance between the front of the target vehicle and the ground detection area.

[0088] S402, determining the area length of the ground detection area according to the current light intensity, the current vehicle speed, the calibration information and the closest distance.

[0089] Among them, the side corresponding to the area length is parallel to the driving direction of the target vehicle.

[0090] For example, Figure 3 As shown, the AB side can be used as the width of the ground detection area.

[0091] Optionally, based on experiments and derivation processes, the functional relationship between the area length and the current light intensity, the current vehicle speed, the calibration information and the nearest distance can be determined, and the area length of the ground detection area can be calculated based on the current light intensity, the current vehicle speed, the calibration information and the nearest distance.

[0092] S403, determining the area position information of the ground detection area in the vehicle coordinate system of the target vehicle according to the area width and the area length.

[0093] Optionally, the target detection area is placed in the vehicle coordinate system, and based on the measurement tool, the position coordinates of each point in the ground detection area in the vehicle coordinate system of the target vehicle can be determined according to the area width and area length as the area position information of the ground detection area.

[0094] In this embodiment, by determining the maximum distance according to the calibration information of the camera and limiting the shape of the ground detection area, the timeliness and rationality of the determined ground detection area are guaranteed, while the accuracy of the determined area detection position is guaranteed.

[0095] Optionally, in one embodiment, Figure 5 As shown, a method for determining the area length of a ground detection area is provided, which specifically includes the following steps:

[0096] S501, determining a distance threshold according to the body parameters of the target vehicle.

[0097] The body parameters are parameters that characterize the body features of the target vehicle. In the embodiment of the present application, the body parameters include but are not limited to the body size. The distance threshold is the maximum distance between the target vehicle and the ground detection area, and the farthest distance is the maximum value of the distance between the target vehicle and the edge of the ground detection area farthest from the target vehicle. For example, Figure 3 As shown, Figure 3 Marked in is the maximum distance.

[0098] It is understandable that the smaller the maximum distance is, the less interference is contained in the collected target detection image. Therefore, it is necessary to set a maximum value for the maximum distance, that is, the distance threshold, to ensure the validity of the collected target detection image.

[0099] Optionally, since different vehicles have different models and shapes, the distance threshold can be determined by the body parameters of the target vehicle to ensure the applicability and accuracy of the distance threshold.

[0100] S502, determining a candidate maximum distance according to the current light intensity, the current vehicle speed and the closest distance.

[0101] The candidate maximum distance is the maximum distance determined as a candidate by taking into account the light intensity and the vehicle speed.

[0102] Optionally, the functional relationship between the maximum distance and the light intensity, vehicle speed and maximum distance can be determined through testing and experimentation, and based on the functional relationship, the maximum distance can be calculated according to the current light intensity, current vehicle speed and closest distance as a candidate maximum distance.

[0103] S503: Select a smaller value between the candidate maximum distance and the distance threshold as the target maximum distance.

[0104] It is understandable that, since the maximum distance cannot exceed the distance threshold, the smaller value between the candidate maximum distance and the distance threshold should be selected as the target maximum distance. That is, when the candidate maximum distance is greater than the distance threshold, the distance threshold is used as the target maximum distance; when the candidate maximum distance is less than the distance threshold, the candidate maximum distance is used as the target maximum distance.

[0105] S504: The difference between the maximum distance and the minimum distance of the target is used as the area length of the ground detection area.

[0106] In this embodiment, the rationality of the determined distance threshold is ensured based on the body parameters of the target vehicle, and the accuracy and rationality of the determined area length of the ground detection area are ensured by introducing the distance threshold and the maximum target distance.

[0107] Optionally, in one embodiment, Figure 6 As shown, a method for determining a candidate maximum distance is provided, which specifically includes the following steps:

[0108] S601, determining a first distance according to the current vehicle speed and the closest distance.

[0109] Optionally, the current vehicle speed is multiplied by a preset coefficient and then added to the shortest distance, and the sum obtained by adding the coefficients is used as the first distance. In the embodiment of the present application, the preset coefficient may be 3.6. Specifically, the first distance may be expressed by the following formula (1):

[0110] (1)

[0111] in, is the first distance; is the shortest distance; is the current vehicle speed.

[0112] S602: Determine a second distance according to the current illumination.

[0113] Optionally, the current illumination may be multiplied by a preset coefficient to obtain the second distance. Specifically, the second distance may be expressed by the following formula (2):

[0114] (2)

[0115] in, is the second distance; The current light intensity in lux.

[0116] It should be noted that in order to ensure the impact of extreme light on the ground detection area, in the embodiment of the present application, the light intensity range is defined as between 0lux and 3000lux, that is, when the current light intensity is greater than 3000lux, the current light intensity is 3000lux.

[0117] S603: taking the absolute value of the difference between the product of the first distance and the preset first coefficient and the product of the second distance and the preset second coefficient as a candidate maximum distance.

[0118] Among them, the first coefficient and the second coefficient are pre-set coefficients. In the embodiment of the present application, the first coefficient may be 0.95 and the second coefficient may be 0.05, which can be determined based on experiments or experience.

[0119] Optionally, the absolute value of the difference between the product of the first distance and the preset first coefficient and the product of the second distance and the preset second coefficient is used as the candidate maximum distance, which can be specifically expressed by the following formula (3):

[0120] (3)

[0121] In this embodiment, by introducing the first distance and the second distance, a method is provided that can accurately and conveniently determine the candidate maximum distance according to the current light intensity, the current vehicle speed and the closest distance.

[0122] Optionally, in one embodiment, Figure 7 As shown, a method for detecting lane line information is provided, which specifically includes the following steps:

[0123] S701, determining first position information of each pixel in the target detection image according to the area position information of the ground detection area.

[0124] The first position information is the position coordinates of each pixel in the target detection image.

[0125] Optionally, based on a coordinate calibration tool, according to the regional position information of the ground detection area, the position coordinates of each pixel point in the target detection image are determined as the first position information.

[0126] S702: Input the target detection image and the first position information into a lane line extraction model to obtain an initial lane line image and second position information corresponding to each pixel point in the initial lane line image.

[0127] Optionally, since common lane lines on roads are mainly white lines and yellow lines and involve fewer colors, the target detection image and the first position information can be input into a lane line extraction model so that the lane line extraction model extracts yellow and white features according to a set threshold, extracts the lane lines contained in the target detection image as the initial lane line image, and obtains the second position information corresponding to each pixel point in the initial lane line image based on the first position information.

[0128] S703: pre-process the initial lane line image.

[0129] Among them, preprocessing includes grayscale processing and binarization processing.

[0130] Optionally, a weighted averaging method is used to grayscale the initial lane line image. Furthermore, due to various reasons, there will be noise points and noise in the initial lane line image. Therefore, it is necessary to binarize the initial lane line image after grayscale processing to reduce the noise in the initial lane line image. In an embodiment of the present application, a Gaussian smoothing method can be used to binarize the initial lane line image after grayscale processing, thereby reducing the interference of the initial lane line image.

[0131] S704: Detect lane line information in the target detection image according to the preprocessed initial lane line image and the second position information.

[0132] Optionally, based on the image detection model, lane line information in the target detection image may be detected according to the preprocessed initial lane line image and the second position information.

[0133] In this embodiment, by introducing the initial lane line image and the second position information and preprocessing the initial lane line image, the noise interference in the initial lane line image is reduced to a certain extent; at the same time, based on the preprocessed initial lane line image and the second position information, the accuracy of the detected lane line information is guaranteed.

[0134] Optionally, based on the above embodiment, in one embodiment, as Figure 8 As shown, a method for detecting lane line information is provided, which specifically includes the following steps:

[0135] S801, performing an inverse perspective transformation on the preprocessed initial lane line image according to the second position information to obtain a target lane line image and third position information corresponding to each pixel point in the target lane line image.

[0136] Optionally, the preprocessed initial lane line image is converted from a front-view angle to a top-view angle using an inverse perspective transformation. After the inverse perspective transformation, the lane lines in the target lane line image obtained become vertical.

[0137] Specifically, based on the inverse perspective transformation interface provided by the cross-platform computer vision library, four matching points can be found on the preprocessed initial lane line image and the target lane line image. The four matching points found correspond one-to-one to the pixels on the preprocessed initial lane line image and the target lane line image, and eight corresponding points are obtained. Furthermore, the eight corresponding points can be used to calculate the transformation matrix after the inverse perspective transformation.

[0138] Optionally, the inverse perspective transformation formula is as shown in the following formula (4):

[0139] (4)

[0140] in, is the position coordinate before inverse perspective transformation; is the position coordinate after inverse perspective transformation; is the inverse perspective transformation matrix. In the embodiment of the present application, since the vehicle coordinate system is a two-dimensional coordinate system, , so the position coordinates in the third position information can be expressed by the following formula (5):

[0141] (5)

[0142] For example, Fig. 9 As shown in Figure 1, it is a schematic diagram of the comparison between the initial lane line image and the target lane line image. Fig. 9 (a) is the initial lane line image after preprocessing; Fig. 9 (b) in the figure is the target lane line image.

[0143] S802, based on a statistical filtering method, selecting a pixel point corresponding to the lane line from each pixel point in the target lane line image as a lane line pixel point.

[0144] It should be noted that there may still be some interference in the target lane line image obtained after the inverse perspective transformation. Therefore, in order to accurately detect the boundary of the lane line in the target lane line image, it is also necessary to determine which factors in the target lane line image belong to the lane line.

[0145] In an embodiment of the present application, the pixel values ​​of each column are counted along the x-axis in the vehicle coordinate system, and the position information of the left and right lane lines is determined by histogram statistical filtering, and the positions with the largest pixel values ​​on the left and right sides are found, and the corresponding x-axis coordinates are the positions of the left and right lane lines.

[0146] Furthermore, a bottom-up approach is adopted to locate lane line pixels using 10 sliding windows of 20 pixels wide. In each sliding window, the center position of the area where the sliding window is located is determined, thereby extracting the pixel points on each lane line.

[0147] S803, performing fitting processing on lane line pixels to obtain lane line information in the target detection image.

[0148] Optionally, for lane lines, lane lines are generally in a vertical state and in a curved state when turning, so the lane line pixels are fitted in the vehicle coordinate system. The lane line pixels can be fitted using the least squares method based on a quadratic function curve.

[0149] Furthermore, the abnormalities in the fitted curve are filtered. For example, lane lines with too large slopes and too large deviations are deleted, and for lane lines that are too close, only the lane lines on the side that matches the vehicle's driving direction are retained, and the redundant lane lines are deleted. After abnormal filtering, the lane line information in the target detection image can be obtained.

[0150] In this embodiment, the accuracy of the lane line pixel points is ensured by a statistical filtering method; at the same time, by fitting the lane line pixel points, the accuracy of the detected lane line information is improved, and the interference information in the lane line information is reduced to a certain extent.

[0151] Fig.10 FIG. 2 is a flow chart of a lane line information detection method in another embodiment. Based on the above embodiment, this embodiment provides an optional example of a lane line information detection method. Fig.10 The specific implementation process is as follows:

[0152] S1001, obtaining the current light intensity of the environment in which the target vehicle is located and the current speed of the target vehicle.

[0153] S1002, determining the width of the ground detection area and the distance between the front of the target vehicle and the ground detection area according to the calibration information of the camera.

[0154] S1003, determining the shortest distance between the front of the target vehicle and the ground detection area according to the calibration information of the camera in the image detection device.

[0155] The closest distance is the distance between the front of the target vehicle and the edge of the ground detection area close to the target vehicle.

[0156] S1004, determining the area length of the ground detection area according to the current light intensity, the current vehicle speed, the calibration information and the closest distance.

[0157] Among them, the side corresponding to the area length is parallel to the driving direction of the target vehicle.

[0158] Optionally, determine a distance threshold based on the body parameters of the target vehicle; determine a candidate maximum distance based on the current light intensity, the current vehicle speed and the nearest distance; select the smaller value between the candidate maximum distance and the distance threshold as the target maximum distance; and use the difference between the target maximum distance and the nearest distance as the area length of the ground detection area.

[0159] Optionally, a first distance is determined based on the current vehicle speed and the shortest distance; a second distance is determined based on the current lighting; and the absolute value of the difference between the product of the first distance and a preset first coefficient and the product of the second distance and a preset second coefficient is used as a candidate maximum distance.

[0160] S1005: Determine the area position information of the ground detection area in the vehicle coordinate system of the target vehicle according to the area width and the area length.

[0161] S1006, controlling the image detection device to collect target detection images of the ground detection area.

[0162] S1007, determining first position information of each pixel in the target detection image according to the area position information of the ground detection area.

[0163] S1008, input the target detection image and the first position information into the lane line extraction model to obtain the initial lane line image and the second position information corresponding to each pixel point in the initial lane line image.

[0164] S1009: pre-process the initial lane line image.

[0165] Among them, preprocessing includes grayscale processing and binarization processing.

[0166] S1010, performing an inverse perspective transformation on the preprocessed initial lane line image according to the second position information to obtain a target lane line image and third position information corresponding to each pixel point in the target lane line image.

[0167] S1011, based on a statistical filtering method, selecting a pixel point corresponding to the lane line from each pixel point in the target lane line image as a lane line pixel point.

[0168] S1012, performing fitting processing on lane line pixels to obtain lane line information in the target detection image.

[0169] The specific process of the above S1001-S1012 can be found in the description of the above method embodiment. The implementation principle and technical effect are similar and will not be repeated here.

[0170] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0171] Based on the same inventive concept, the embodiment of the present application also provides a lane line information detection device for implementing the lane line information detection method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more lane line information detection device embodiments provided below can refer to the limitations of the lane line information detection method above, and will not be repeated here.

[0172] In one embodiment, Fig.11 As shown, a lane line information detection device 1 is provided, comprising: an information acquisition module 10, a region determination module 20, an image acquisition module 30 and an information detection module 40, wherein:

[0173] The information acquisition module 10 is used to acquire the current light intensity of the environment in which the target vehicle is located and the current speed of the target vehicle.

[0174] The area determination module 20 is used to determine the ground detection area of ​​the image detection device in the target vehicle and the area position information of the ground detection area in the vehicle coordinate system according to the current light intensity and the current vehicle speed.

[0175] The image acquisition module 30 is used to control the image detection device to acquire the target detection image of the ground detection area.

[0176] The information detection module 40 is used to detect the lane line information in the target detection image based on the lane line extraction model according to the regional position information and the target detection image.

[0177] In one embodiment, the ground detection area is a rectangular area, and the image detection device includes a camera; the area determination module 20 includes:

[0178] The distance determination unit is used to determine the area width of the ground detection area and the closest distance between the front of the target vehicle and the ground detection area according to the calibration information of the camera; wherein the closest distance is the distance between the front of the target vehicle and the edge of the ground detection area close to the target vehicle.

[0179] The length determination unit is used to determine the area length of the ground detection area according to the current light intensity, the current vehicle speed, the calibration information and the closest distance; wherein the side corresponding to the area length is parallel to the driving direction of the target vehicle.

[0180] The position determination unit is used to determine the area position information of the ground detection area in the vehicle coordinate system of the target vehicle according to the area width and the area length.

[0181] In one embodiment, the length determination unit comprises:

[0182] The first subunit is used to determine a distance threshold according to body parameters of the target vehicle.

[0183] The second subunit is used to determine a candidate maximum distance according to the current light intensity, the current vehicle speed and the closest distance.

[0184] The third subunit is used to select a smaller value between the candidate maximum distance and the distance threshold as the target maximum distance.

[0185] The fourth subunit is used to use the difference between the maximum distance and the minimum distance of the target as the area length of the ground detection area.

[0186] In one embodiment, the second subunit is specifically used for:

[0187] Determine the first distance according to the current vehicle speed and the shortest distance; determine the second distance according to the current lighting; and use the absolute value of the difference between the product of the first distance and the preset first coefficient and the product of the second distance and the preset second coefficient as the candidate maximum distance.

[0188] In one embodiment, the information detection module 40 includes:

[0189] The first determining unit is used to determine first position information of each pixel in the target detection image according to the area position information of the ground detection area.

[0190] The second determination unit is used to input the target detection image and the first position information into the lane line extraction model to obtain the initial lane line image and the second position information corresponding to each pixel point in the initial lane line image.

[0191] The image processing unit is used to preprocess the initial lane line image; wherein the preprocessing includes grayscale processing and binarization processing.

[0192] The information detection unit is used to detect the lane line information in the target detection image according to the preprocessed initial lane line image and the second position information.

[0193] In one embodiment, the information detection unit is specifically used to:

[0194] According to the second position information, the preprocessed initial lane line image is subjected to an inverse perspective transformation to obtain the target lane line image and the third position information corresponding to each pixel point in the target lane line image; based on the statistical filtering method, the pixel point corresponding to the lane line is selected from each pixel point in the target lane line image as the lane line pixel point; the lane line pixel point is fitted to obtain the lane line information in the target detection image.

[0195] Each module in the lane information detection device can be implemented in whole or in part by software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.

[0196] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Fig.12 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a lane line information detection method is implemented.

[0197] Those skilled in the art will understand that Fig.12 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0198] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0199] Obtain the current light intensity of the target vehicle's environment and the current speed of the target vehicle;

[0200] Determine the ground detection area of ​​the image detection device in the target vehicle and the regional position information of the ground detection area in the vehicle coordinate system according to the current light intensity and the current vehicle speed;

[0201] Controlling the target detection image of the ground detection area collected by the image detection device;

[0202] Based on the lane line extraction model, the lane line information in the target detection image is detected according to the regional position information and the target detection image.

[0203] In one embodiment, the ground detection area is a rectangular area, and the image detection device includes a camera; when the processor executes the computer program to determine the ground detection area of ​​the image detection device in the target vehicle and the regional position information of the ground detection area in the vehicle coordinate system according to the current light intensity and the current vehicle speed, the following steps are also implemented:

[0204] According to the calibration information of the camera, the area width of the ground detection area and the closest distance between the front of the target vehicle and the ground detection area are determined; wherein the closest distance is the distance between the front of the target vehicle and the edge of the ground detection area close to the target vehicle; according to the current light intensity, the current vehicle speed, the calibration information and the closest distance, the area length of the ground detection area is determined; wherein the edge corresponding to the area length is parallel to the driving direction of the target vehicle; according to the area width and the area length, the area position information of the ground detection area in the vehicle coordinate system of the target vehicle is determined.

[0205] In one embodiment, when the processor executes the computer program to determine the area length of the ground detection area according to the current light intensity, the current vehicle speed, the calibration information and the closest distance, the processor further implements the following steps:

[0206] Determine the distance threshold according to the body parameters of the target vehicle; determine the candidate maximum distance according to the current light intensity, the current vehicle speed and the closest distance; select the smaller value between the candidate maximum distance and the distance threshold as the target maximum distance; and use the difference between the target maximum distance and the closest distance as the area length of the ground detection area.

[0207] In one embodiment, when the processor executes the computer program to determine the candidate maximum distance according to the current light intensity, the current vehicle speed and the closest distance, the processor further implements the following steps:

[0208] Determine the first distance according to the current vehicle speed and the shortest distance; determine the second distance according to the current lighting; and use the absolute value of the difference between the product of the first distance and the preset first coefficient and the product of the second distance and the preset second coefficient as the candidate maximum distance.

[0209] In one embodiment, when the processor executes the computer program to detect lane line information in the target detection image based on the lane line extraction model and according to the target detection image, the processor further implements the following steps:

[0210] According to the regional position information of the ground detection area, the first position information of each pixel in the target detection image is determined; the target detection image and the first position information are input into the lane line extraction model to obtain the initial lane line image and the second position information corresponding to each pixel in the initial lane line image; the initial lane line image is preprocessed; wherein the preprocessing includes grayscale processing and binarization processing; according to the preprocessed initial lane line image and the second position information, the lane line information in the target detection image is detected.

[0211] In one embodiment, when the processor executes the computer program to detect the lane line information in the target detection image according to the preprocessed initial lane line image and the second position information, the processor further implements the following steps:

[0212] According to the second position information, the preprocessed initial lane line image is subjected to an inverse perspective transformation to obtain the target lane line image and the third position information corresponding to each pixel point in the target lane line image; based on the statistical filtering method, the pixel point corresponding to the lane line is selected from each pixel point in the target lane line image as the lane line pixel point; the lane line pixel point is fitted to obtain the lane line information in the target detection image.

[0213] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0214] Obtain the current light intensity of the target vehicle's environment and the current speed of the target vehicle;

[0215] Determine the ground detection area of ​​the image detection device in the target vehicle and the regional position information of the ground detection area in the vehicle coordinate system according to the current light intensity and the current vehicle speed;

[0216] Controlling the target detection image of the ground detection area collected by the image detection device;

[0217] Based on the lane line extraction model, the lane line information in the target detection image is detected according to the regional position information and the target detection image.

[0218] In one embodiment, the ground detection area is a rectangular area, and the image detection device includes a camera; when the processor executes the computer program to determine the ground detection area of ​​the image detection device in the target vehicle and the regional position information of the ground detection area in the vehicle coordinate system according to the current light intensity and the current vehicle speed, the following steps are also implemented:

[0219] According to the calibration information of the camera, the area width of the ground detection area and the closest distance between the front of the target vehicle and the ground detection area are determined; wherein the closest distance is the distance between the front of the target vehicle and the edge of the ground detection area close to the target vehicle; according to the current light intensity, the current vehicle speed, the calibration information and the closest distance, the area length of the ground detection area is determined; wherein the edge corresponding to the area length is parallel to the driving direction of the target vehicle; according to the area width and the area length, the area position information of the ground detection area in the vehicle coordinate system of the target vehicle is determined.

[0220] In one embodiment, when the processor executes the computer program to determine the area length of the ground detection area according to the current light intensity, the current vehicle speed, the calibration information and the closest distance, the processor further implements the following steps:

[0221] Determine the distance threshold according to the body parameters of the target vehicle; determine the candidate maximum distance according to the current light intensity, the current vehicle speed and the closest distance; select the smaller value between the candidate maximum distance and the distance threshold as the target maximum distance; and use the difference between the target maximum distance and the closest distance as the area length of the ground detection area.

[0222] In one embodiment, when the processor executes the computer program to determine the candidate maximum distance according to the current light intensity, the current vehicle speed and the closest distance, the processor further implements the following steps:

[0223] Determine the first distance according to the current vehicle speed and the shortest distance; determine the second distance according to the current lighting; and use the absolute value of the difference between the product of the first distance and the preset first coefficient and the product of the second distance and the preset second coefficient as the candidate maximum distance.

[0224] In one embodiment, when the processor executes the computer program to detect lane line information in the target detection image based on the lane line extraction model and according to the target detection image, the processor further implements the following steps:

[0225] According to the regional position information of the ground detection area, the first position information of each pixel in the target detection image is determined; the target detection image and the first position information are input into the lane line extraction model to obtain the initial lane line image and the second position information corresponding to each pixel in the initial lane line image; the initial lane line image is preprocessed; wherein the preprocessing includes grayscale processing and binarization processing; according to the preprocessed initial lane line image and the second position information, the lane line information in the target detection image is detected.

[0226] In one embodiment, when the processor executes the computer program to detect the lane line information in the target detection image according to the preprocessed initial lane line image and the second position information, the processor further implements the following steps:

[0227] According to the second position information, the preprocessed initial lane line image is subjected to an inverse perspective transformation to obtain the target lane line image and the third position information corresponding to each pixel point in the target lane line image; based on the statistical filtering method, the pixel point corresponding to the lane line is selected from each pixel point in the target lane line image as the lane line pixel point; the lane line pixel point is fitted to obtain the lane line information in the target detection image.

[0228] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:

[0229] Obtain the current light intensity of the target vehicle's environment and the current speed of the target vehicle;

[0230] Determine the ground detection area of ​​the image detection device in the target vehicle and the regional position information of the ground detection area in the vehicle coordinate system according to the current light intensity and the current vehicle speed;

[0231] Controlling the target detection image of the ground detection area collected by the image detection device;

[0232] Based on the lane line extraction model, the lane line information in the target detection image is detected according to the regional position information and the target detection image.

[0233] In one embodiment, the ground detection area is a rectangular area, and the image detection device includes a camera; when the processor executes the computer program to determine the ground detection area of ​​the image detection device in the target vehicle and the regional position information of the ground detection area in the vehicle coordinate system according to the current light intensity and the current vehicle speed, the following steps are also implemented:

[0234] According to the calibration information of the camera, the area width of the ground detection area and the closest distance between the front of the target vehicle and the ground detection area are determined; wherein the closest distance is the distance between the front of the target vehicle and the edge of the ground detection area close to the target vehicle; according to the current light intensity, the current vehicle speed, the calibration information and the closest distance, the area length of the ground detection area is determined; wherein the edge corresponding to the area length is parallel to the driving direction of the target vehicle; according to the area width and the area length, the area position information of the ground detection area in the vehicle coordinate system of the target vehicle is determined.

[0235] In one embodiment, when the processor executes the computer program to determine the area length of the ground detection area according to the current light intensity, the current vehicle speed, the calibration information and the closest distance, the processor further implements the following steps:

[0236] Determine the distance threshold according to the body parameters of the target vehicle; determine the candidate maximum distance according to the current light intensity, the current vehicle speed and the closest distance; select the smaller value between the candidate maximum distance and the distance threshold as the target maximum distance; and use the difference between the target maximum distance and the closest distance as the area length of the ground detection area.

[0237] In one embodiment, when the processor executes the computer program to determine the candidate maximum distance according to the current light intensity, the current vehicle speed and the closest distance, the processor further implements the following steps:

[0238] Determine the first distance according to the current vehicle speed and the shortest distance; determine the second distance according to the current lighting; and use the absolute value of the difference between the product of the first distance and the preset first coefficient and the product of the second distance and the preset second coefficient as the candidate maximum distance.

[0239] In one embodiment, when the processor executes the computer program to detect lane line information in the target detection image based on the lane line extraction model and according to the target detection image, the processor further implements the following steps:

[0240] According to the regional position information of the ground detection area, the first position information of each pixel in the target detection image is determined; the target detection image and the first position information are input into the lane line extraction model to obtain the initial lane line image and the second position information corresponding to each pixel in the initial lane line image; the initial lane line image is preprocessed; wherein the preprocessing includes grayscale processing and binarization processing; according to the preprocessed initial lane line image and the second position information, the lane line information in the target detection image is detected.

[0241] In one embodiment, when the processor executes the computer program to detect the lane line information in the target detection image according to the preprocessed initial lane line image and the second position information, the processor further implements the following steps:

[0242] According to the second position information, the preprocessed initial lane line image is subjected to an inverse perspective transformation to obtain the target lane line image and the third position information corresponding to each pixel point in the target lane line image; based on the statistical filtering method, the pixel point corresponding to the lane line is selected from each pixel point in the target lane line image as the lane line pixel point; the lane line pixel point is fitted to obtain the lane line information in the target detection image.

[0243] It should be noted that the data involved in this application (including but not limited to data used for analysis, storage, display, etc.) are all information and data fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0244] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0245] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0246] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A lane line information detection method, characterized in that: The method comprises: Obtaining the current light intensity of the environment in which the target vehicle is located and the current speed of the target vehicle; Determine, according to the current light intensity and the current vehicle speed, a ground detection area of ​​an image detection device in the target vehicle, and regional position information of the ground detection area in a vehicle coordinate system; Controlling the target detection image of the ground detection area collected by the image detection device; Based on the lane line extraction model, the lane line information in the target detection image is detected according to the area position information and the target detection image.

2. The method according to claim 1, characterized in that: The ground detection area is a rectangular area, and the image detection device includes a camera; accordingly, determining the ground detection area of ​​the image detection device in the target vehicle and the regional position information of the ground detection area in the vehicle coordinate system according to the current light intensity and the current vehicle speed includes: Determine the area width of the ground detection area and the closest distance between the front of the target vehicle and the ground detection area according to the calibration information of the camera; wherein the closest distance is the distance between the front of the target vehicle and the edge of the ground detection area close to the target vehicle; Determine the area length of the ground detection area according to the current light intensity, the current vehicle speed, the calibration information and the closest distance; wherein the side corresponding to the area length is parallel to the driving direction of the target vehicle; According to the area width and the area length, area position information of the ground detection area in the vehicle coordinate system of the target vehicle is determined.

3. The method according to claim 2, characterized in that The determining the area length of the ground detection area according to the current light intensity, the current vehicle speed, the calibration information and the closest distance includes: Determining a distance threshold according to the body parameters of the target vehicle; Determining a candidate maximum distance according to the current light intensity, the current vehicle speed and the closest distance; Selecting a smaller value between the candidate maximum distance and the distance threshold as the target maximum distance; The difference between the maximum target distance and the minimum target distance is used as the area length of the ground detection area.

4. The method according to claim 3, characterized in that: The determining of the candidate maximum distance according to the current light intensity, the current vehicle speed and the closest distance includes: Determining a first distance according to the current vehicle speed and the shortest distance; Determining a second distance according to the current illumination; The absolute value of the difference between the product of the first distance and the preset first coefficient and the product of the second distance and the preset second coefficient is used as a candidate maximum distance.

5. The method according to claim 1, characterized in that The lane line extraction model is based on the target detection image, and the lane line information in the target detection image is detected, including: Determining first position information of each pixel in the target detection image according to the area position information of the ground detection area; Inputting the target detection image and the first position information into a lane line extraction model to obtain an initial lane line image and second position information corresponding to each pixel point in the initial lane line image; Preprocessing the initial lane line image; wherein the preprocessing includes grayscale processing and binarization processing; The lane line information in the target detection image is detected according to the preprocessed initial lane line image and the second position information.

6. The method according to claim 5, characterized in that The detecting the lane line information in the target detection image according to the preprocessed initial lane line image and the second position information includes: According to the second position information, the preprocessed initial lane line image is subjected to an inverse perspective transformation to obtain a target lane line image and third position information corresponding to each pixel point in the target lane line image; Based on a statistical filtering method, a pixel point corresponding to the lane line is selected from each pixel point in the target lane line image as a lane line pixel point; The lane line pixel points are fitted to obtain the lane line information in the target detection image.

7. A lane line information detection device, characterized in that: The device comprises: An information acquisition module, used to acquire the current light intensity of the environment in which the target vehicle is located and the current speed of the target vehicle; An area determination module, used to determine the ground detection area of ​​the image detection device in the target vehicle and the area position information of the ground detection area in the vehicle coordinate system according to the current light intensity and the current vehicle speed; An image acquisition module, used for controlling the image detection device to acquire the target detection image of the ground detection area; The information detection module is used to detect the lane line information in the target detection image based on the lane line extraction model according to the area position information and the target detection image.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images