Lane line detection method, electronic device and storage medium

Abstract

The embodiment of the present invention provides a lane line detection method, electronic device and storage medium, the method comprising: obtaining an observed lane line observed online, the observed lane line being a lane line observed and obtained by a sensor mounted on a vehicle; matching the observed lane line with a high-precision map lane line within a preset local range; and determining the detected lane line according to the matching result. In this way, the reliability of the high-precision map lane line is judged by the relatively reliable observed lane line in the vicinity, and the high-precision map lane line in the distance is used to repair the problem of low accuracy and obstruction of the observed lane line, and finally a high-precision and high-reliability detected lane line is obtained.

Description

Technical Field

[0001] Embodiments of the present invention relate to the field of intelligent driving technology, and in particular to a lane line detection method, electronic equipment, and storage medium. Background Art

[0002] With the development of intelligent driving, in order to improve the safety of intelligent driving, it is necessary to check the lane lines on the road. The current method for checking lane lines is online observation, that is, using a visual navigation system to find the position of lane lines in the road image from the captured road image, and then realize the lane line inspection.

[0003] However, the method of observing lane lines online is affected by the accuracy of visual sensors. Lane lines are more accurate at close range, and the farther away from the vehicle, the lower the accuracy and the less reliable. At the same time, if there are vehicles, obstacles, etc. blocking the field of view of the camera sensor, the detection result of the lane line is inaccurate. Summary of the invention

[0004] The embodiments of the present invention provide a lane line detection method, an electronic device and a storage medium to achieve accurate lane line detection.

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

[0006] Acquire an observed lane line observed online, where the observed lane line is a lane line observed and acquired by a sensor mounted on the vehicle;

[0007] Matching the observed lane line with the high-precision map lane line within a preset local range to obtain a matching result;

[0008] According to the matching result, the detected lane line is determined.

[0009] In a second aspect, an embodiment of the present application provides an electronic device, including:

[0010] Memory for storing computer programs;

[0011] The processor is used to execute the computer program, specifically to execute:

[0012] Acquire an observed lane line observed online, where the observed lane line is a lane line observed and acquired by a sensor mounted on the vehicle;

[0013] Matching the observed lane line with the high-precision map lane line within a preset local range to obtain a matching result;

[0014] According to the matching result, the detection lane line is determined by the observed lane line and the high-precision map lane line.

[0015] In a third aspect, an embodiment of the present application provides a vehicle, comprising: a vehicle body and an electronic device according to any one of the second aspects mounted on the vehicle body.

[0016] In a fourth aspect, an embodiment of the present application provides a vehicle, comprising: a vehicle body and an electronic device as described in any one of the second aspects installed on the vehicle body.

[0017] In a fifth aspect, an embodiment of the present application provides a computer storage medium, in which a computer program is stored. When the computer program is executed, the lane line detection method as described in any one of the first aspects is implemented.

[0018] The lane line detection method, electronic device and storage medium provided in the embodiments of the present application obtain the observed lane line observed online, wherein the observed lane line is the lane line observed and obtained by the sensor mounted on the vehicle; within a preset local range, the observed lane line and the high-precision map lane line are matched to obtain a matching result; and the detected lane line is determined according to the matching result. In this way, the high-precision map lane line is judged whether there are positioning offsets, outdated problems, etc. through the more reliable observed lane line in the vicinity. If the reliability of the high-precision map lane line is high, the high-precision map lane line in the distance is used to repair the low accuracy and obstruction of the observed lane line, and finally obtain a high-precision and high-reliability detected lane line. The vehicle plans the state of intelligent driving of the vehicle according to the high-precision detected lane line, such as changing lanes, slowing down or stopping, etc., which can achieve accurate guidance of intelligent driving, thereby improving the safety of intelligent driving. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0020] Figure 1 A schematic diagram of an application scenario involved in an embodiment of the present application;

[0021] Figure 2 A flowchart of a lane line detection method provided in an embodiment of the present application;

[0022] Figure 3 A flowchart of a lane line detection method provided in an embodiment of the present application;

[0023] Figure 4 A schematic diagram of an electronic device provided in an embodiment of the present application;

[0024] Figure 5 A schematic diagram of the structure of a vehicle provided in an embodiment of the present application;

[0025] Figure 6 A schematic diagram of the structure of a vehicle provided in an embodiment of the present application. DETAILED DESCRIPTION

[0026] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0027] The method of the embodiment of the present invention is applicable to the technical fields of computer vision, intelligent driving, etc., and can realize the detection of lane lines, thereby improving the safety of intelligent driving. Among them, intelligent driving includes automatic driving and assisted driving.

[0028] When performing intelligent driving, the vehicle needs to obtain a local lane map to plan and formulate a driving plan and predict the trend of other vehicles. Among them, the use of on-board sensors to build fused local information in real time is called online measurement.

[0029] The lane line data detected by the vehicle-mounted sensor is projected, segmented or fused to obtain the online observed lane line, which is recorded as the observed lane line. Projection refers to transforming the coordinates of the lane line on the sensor to the bird's-eye view map through geometric calculation. Segmentation refers to clustering the lane line points on the bird's-eye view map and assigning each lane line point a label corresponding to the lane line. Fusion refers to data association of multiple frames of labeled bird's-eye views, merging the lane lines of multiple frames in time sequence, and optimizing the curve parameters of the lane lines.

[0030] When driving intelligently, the vehicle can also obtain its current absolute position and read the pre-collected, modeled, and annotated high-precision map (HD Map) around the vehicle from the database based on the absolute position. Among them, the lane lines marked in the HD map (i.e., HD map lane lines) can also be used to plan and formulate vehicle driving plans and predict the trends of other vehicles.

[0031] During intelligent driving, using only observed lane lines will result in the following problems: due to the accuracy of the sensor, the lane lines are more accurate at close range, and the farther away from the vehicle, the lower the accuracy and the less reliable they are; if there are vehicles, obstacles and other obstructions within the sensor's field of view, the visible range of the lane lines will be greatly reduced, making it difficult to plan the vehicle's driving plan.

[0032] During intelligent driving, using HD map lane lines alone will result in the following problems: the accuracy of the HD map is affected by the vehicle positioning. If the vehicle positioning is offset, the credibility of the entire HD map lane lines will be greatly reduced; HD maps are time-sensitive. After road construction or diversion, if the HD map cannot be updated in time, the credibility of the HD map lane lines will be greatly reduced.

[0033] The lane line detection method provided in the embodiment of the present application, by fusing the high-precision map lane lines and the observed lane lines, determines whether the high-precision map lane lines have problems such as positioning offset and obsolescence through the more reliable observed lane lines in the vicinity (i.e., the area close to the vehicle). If the reliability of the high-precision map lane lines is high, the high-precision map lane lines in the distance (i.e., the area far away from the vehicle) are used to repair the problems of low accuracy and occlusion of the observed lane lines.

[0034] Figure 1 This is a schematic diagram of an application scenario involved in the embodiment of the present application. It should be noted that the application scenario of the embodiment of the present application includes but is not limited to Figure 1 As shown. Figure 1 As shown, the intelligent driving vehicle is equipped with sensors such as monocular or binocular cameras. When the intelligent driving vehicle is driving, the sensor can collect the surrounding environment, such as collecting environmental images, which include road images. The vehicle can identify the lane line based on the collected environmental image, obtain the observed lane line for online observation, and match the observed lane line with the high-precision map lane line within a preset local range to determine the final detection lane line. The high-precision map lane line is judged by the more reliable observation lane line in the vicinity to determine whether there are positioning offsets, outdated and other problems. If the high-precision map lane line is highly reliable, the high-precision map lane line in the distance is used to repair the low accuracy and obstruction of the observed lane line, and finally obtain the high-precision and high-reliability detection lane line. The vehicle plans the state of the vehicle's intelligent driving according to the high-precision detection lane line, such as changing lanes, slowing down or parking, etc., which can achieve accurate guidance for intelligent driving, thereby improving the safety of intelligent driving.

[0035] The technical solution of the present invention is described in detail with specific embodiments below. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.

[0036] Figure 2A flowchart of a lane line detection method provided in an embodiment of the present application is shown in FIG. Figure 2 As shown, the method of the embodiment of the present application includes:

[0037] S101. Acquire an observed lane line observed online, where the observed lane line is a lane line observed and acquired by a sensor mounted on a vehicle.

[0038] The execution subject of the embodiment of the present application is a device with a lane line detection function, such as a lane line detection device, hereinafter referred to as a detection device, which can be integrated into any electronic device as a part of the electronic device. Optionally, the detection device can also be a separate electronic device.

[0039] The electronic device may be a vehicle-mounted device, such as an advanced driver assistance device.

[0040] The embodiments of the present application are described by taking an electronic device as an example.

[0041] Optionally, the sensor may be a three-dimensional detection device and a visual sensor, or a combination thereof. The visual sensor may be an imaging device, and the point cloud sensor may include a laser radar, a time of flight ranging detection device, a depth vision sensor, and a high-resolution millimeter wave radar. Exemplarily, the embodiment of the present application takes the sensor as an imaging device as an example, such as a monocular camera or a multi-camera, wherein the multi-camera includes two or more cameras.

[0042] It should be noted that the observed lane line is just a name for the lane line observed by the sensor mounted on the vehicle. Optionally, other names can be used according to actual needs.

[0043] The electronic device in the embodiment of the present application is communicatively connected with the sensor.

[0044] In one example, the above S101 may be that the electronic device obtains the lane line observed online from the sensor. Specifically, the sensor collects environmental data around the vehicle in real time, such as collecting road images around the vehicle. At the same time, the sensor processes the collected road images and identifies the lane lines in the road images as observed lane lines. Then, the sensor sends the observed lane lines to the electronic device.

[0045] In another example, the above S101 may be that the electronic device obtains environmental data around the vehicle, such as a road image, through the sensor mounted on the vehicle, and then the electronic device performs lane line detection on the road image to obtain the observed lane line. Specifically, the sensor sends the road image around the vehicle collected in real time to the electronic device, and the electronic device processes the road image around the vehicle sent by the sensor to obtain the observed lane line observed online.

[0046] Optionally, the above-mentioned observed lane lines can be obtained by identifying according to an existing image recognition method. For example, environmental data (such as road images) collected by a sensor is input into a trained neural network, and the neural network outputs the observed lane lines.

[0047] S102: Match the observed lane lines with the high-precision map lane lines within a preset local range to obtain a matching result.

[0048] According to the above steps, after the observed lane line is obtained, the observed lane line is matched with the high-precision map lane line to obtain a matching result. Specifically, the observed lane line is matched with the high-precision map lane line within a preset local range to obtain a matching result.

[0049] Among them, the high-precision map lane lines are obtained from the high-precision map.

[0050] The above-mentioned preset local range can be any range obtained from the observation lane line according to actual needs.

[0051] Optionally, the above-mentioned preset local range can be a local range close to the vehicle. Since the accuracy of the observed lane lines in the local range close to the vehicle is higher, using more accurate observed lane lines to determine whether there are problems such as positioning offset and obsolescence in the high-precision map lane lines can improve the accurate judgment of the reliability of the high-precision map lane lines.

[0052] S103: Determine the detected lane line according to the matching result.

[0053] The detection lane line is determined by the observation lane line and the high-precision map lane line.

[0054] In one example, according to the matching results obtained in the above steps, the observed lane line or the high-precision map lane line is used as the detected lane line.

[0055] For example, within a preset local range, if the matching result between the observed lane line and the high-precision map lane line is greater than the first preset value, it means that the high-precision map is reliable, so the high-precision map lane line can be used as the detection lane line. If the matching result between the observed lane line and the high-precision map lane line is less than the third preset value, it means that the high-precision map lane line is unreliable, and the observed lane line is used as the detection lane line for driving guidance. Among them, the first preset value is greater than the third preset value, and the first preset value and the third preset value are both set according to actual needs, and this embodiment does not limit it.

[0056] In another example, the above S103 may include: determining the detection lane line through the observation lane line and the high-precision map lane line according to the matching result.

[0057] For example, within a preset local range, if the matching result between the observed lane line and the high-precision map lane line is greater than a second preset value, the observed lane line and the high-precision map lane line are fused into one lane line, and the fused lane line is used as the detected lane line. The second preset value is set according to actual needs and is not limited in this embodiment.

[0058] Optionally, the detection lane line may be determined based on the matching result by using the observed lane line and the high-precision map lane line according to other methods.

[0059] Optionally, the electronic device is communicatively connected to an intelligent driving system, and the electronic device can send the determined detected lane line to the intelligent driving system, so that the intelligent driving system can perform intelligent driving control on the vehicle according to the detected lane line.

[0060] The lane line detection method provided in the embodiment of the present application obtains the observed lane line observed online, wherein the observed lane line is the lane line observed and obtained by the sensor mounted on the vehicle; within a preset local range, the observed lane line is matched with the high-precision map lane line to obtain a matching result; and the detected lane line is determined according to the matching result. In this way, the high-precision map lane line is judged whether there are positioning offsets, outdated problems, etc. through the more reliable observed lane line in the vicinity. If the reliability of the high-precision map lane line is high, the high-precision map lane line in the distance is used to repair the low accuracy and obstruction of the observed lane line, and finally obtains a high-precision and high-reliability detected lane line. The vehicle plans the state of the vehicle's intelligent driving according to the high-precision detected lane line, such as changing lanes, slowing down or parking, etc., which can achieve accurate guidance of intelligent driving, thereby improving the safety of intelligent driving.

[0061] Figure 3 A flowchart of a lane line detection method provided in an embodiment of the present application. Based on the above embodiment, the method in the embodiment of the present application includes:

[0062] S201. Obtain at least one high-precision map lane line from a high-precision map according to the position information of the vehicle.

[0063] The electronic device obtains the current position information of the vehicle from the positioning module of the vehicle, and obtains at least one high-precision map lane line near the vehicle from the high-precision map based on the vehicle's position information.

[0064] S202: Match the observed lane line with the at least one high-precision map lane line within a preset local range.

[0065] Within a preset local range, the observed lane line is matched with at least one lane line on a high-precision map, and the matching process includes but is not limited to the following methods.

[0066] In a possible embodiment, the above S202 may include:

[0067] Step A1: From the at least one high-precision map lane line, obtain at least one high-precision map lane line that is closest to the observation lane line.

[0068] Step A2: within the preset local range, match the observation lane line with each high-precision map lane line of at least one high-precision map lane line closest to the observation lane line.

[0069] Specifically, at least one high-precision map lane line that is closest to the observation lane line is obtained from at least one high-precision map lane line, and within a preset local range, the observation lane line is matched with each high-precision map lane line in the at least one high-precision map lane line that is closest to the observation lane line.

[0070] Exemplarily, the head point of the feature point of the observed lane line a is selected, and the K points closest to the head point are selected from the feature points of all high-precision map lane lines, and the lane lines where these K points are located are taken as the K high-precision map lane lines closest to the observed lane line. Next, a high-precision map lane line b is selected from the K high-precision map lane lines, and the initial matching degree S of the high-precision map lane line b and the observed lane line a is set to 0. Take the first feature point PB of the high-precision map lane line b and the first feature point PA of the observed lane line a, calculate the matching degree D of PA and PB, and then set S=S+D. Select the next feature point of PA and PB along the forward direction of the lane line, repeat the above steps until the feature point matching of the observed lane line a or the high-precision map lane line b is completed, determine the matching degree S at this time, and determine the matching degree S at this time as the matching degree of the observed lane line a and the high-precision map lane line b.

[0071] Repeat the above steps to determine the matching degree between each HD map lane line and the observed lane line in the K HD map lane lines. According to the matching degree, select a HD map lane line from the K HD map lane lines and merge it with the observed lane line to determine the detected lane line.

[0072] Optionally, the feature points on the observed lane line and the high-precision map lane line are collected along the direction of the lane line at a preset collection interval, such as equal-interval collection.

[0073] In a possible embodiment, the above S202 may include:

[0074] Step B1: for each high-precision map lane line, within the preset local range, obtain multiple feature points on the observation lane line and multiple feature points on the high-precision map lane line.

[0075] Step B2: Determine the degree of match between each feature point on the observed lane line and each feature point on the high-precision map lane line.

[0076] Step B3: Determine the degree of matching between the observation lane line and the high-precision map lane line based on the degree of matching between each feature point on the observation lane line and each feature point on the high-precision map lane line.

[0077] In this embodiment, the input high-precision map lane line and the observed lane line can be considered as a set of points in the local space. These points are too dense, and the computational cost for matching is too high. First, a curve is fitted to the point set of the observed lane line and each high-precision map lane line, and then samples are taken on the fitted curve of the observed lane line and the high-precision map lane line according to the direction of the lane line, such as equidistant sampling, to obtain a set of feature points of the observed lane line and a set of feature points of each high-precision map lane line for subsequent matching operations.

[0078] Taking a high-precision map lane line c as an example, multiple feature points of the high-precision map lane line c and multiple feature points of the observation lane line a are obtained, wherein the feature points of the high-precision map lane line c correspond one-to-one to the feature points of the observation lane line a. Determine the matching degree between each feature point on the observation lane line a and each feature point on the high-precision map lane line c. Then, based on the matching degree between each feature point on the observation lane line a and each feature point on the high-precision map lane line c, determine the matching degree between the observation lane line a and the high-precision map lane line c. For example, the sum of the matching degrees between each feature point on the observation lane line a and each feature point on the high-precision map lane line c is determined as the matching degree between the observation lane line a and the high-precision map lane line c.

[0079] S203. Select one of the at least one high-precision map lane lines as a target high-precision map lane line based on a degree of matching between the observed lane line and the at least one high-precision map lane line.

[0080] According to the above steps, the matching degree between the observed lane line and at least one high-precision map lane line can be determined. In this way, according to the matching degree between the observed lane line and at least one high-precision map lane line, one is selected from at least one high-precision map lane line as the target high-precision map lane line. For example, a high-precision map lane line whose matching degree meets a preset matching degree is determined as the target high-precision map lane line, wherein the preset matching degree is determined according to actual needs, and the embodiments of the present application are not limited to this.

[0081] Optionally, the high-precision map lane line with the highest matching degree with the observed lane line among at least one high-precision map lane line is used as the target high-precision map lane line.

[0082] S204: Fuse the observed lane line with the target high-precision map lane line to determine the detected lane line.

[0083] According to the above steps, after obtaining the target high-precision map lane line, the observed lane line and the target high-precision map lane line are merged into one lane line as the detection lane line.

[0084] In a possible implementation, the fusion of the observed lane line with the target high-precision map lane line in S204 may include:

[0085] Step C: Merge the feature points on the observed lane line with the feature points on the target high-precision map lane line.

[0086] In this step, the feature points of the observed lane line and the feature points of the target high-precision map lane line are merged one by one into one feature point. For example, the observed lane line includes feature point 1 and feature point 2, and the target high-precision map lane line includes feature point 3 and feature point 4, wherein along the lane line direction, feature point 1 corresponds to feature point 3, and feature point 2 corresponds to feature point 4. In this way, feature point 1 and feature point 3 can be merged into one feature point, for example, the average value of the position information of feature point 1 and feature point 2 is used as the position information of the merged feature point, and feature point 2 and feature point 4 are merged into one feature point, for example, the average value of the position information of feature point 2 and feature point 4 is used as the position information of the merged feature point, and the merged feature points constitute a new lane line as the detected lane line.

[0087] In a possible implementation, the above step C includes:

[0088] Step C1: Merge the feature points on the observation lane line with the feature points on the target high-precision map lane line according to the weights of the feature points on the observation lane line and the weights of the feature points on the target high-precision map lane line.

[0089] In this step, when merging, the weights of the feature points of the observed lane line and the weights of the feature points of the target high-precision map lane line are different. In this way, the feature points on the observed lane line can be merged with the feature points on the target high-precision map lane line according to the weights of the feature points on the observed lane line and the weights of the feature points on the target high-precision map lane line. Optionally, the weights of the above feature points should be set according to actual needs.

[0090] Optionally, within the preset local range, the weight of the feature points on the observation lane line is greater than the weight of the feature points on the target high-precision map lane line; and / or, within a range outside the preset local range, the weight of the feature points on the observation lane line is less than the weight of the feature points on the target high-precision map lane line.

[0091] Since the accuracy of the observed lane line is high within the preset local range (i.e., the near-vehicle range), the weight of the feature points on the observed lane line is greater than the weight of the feature points on the target high-precision map lane line within the near-vehicle range, which can improve the accuracy of the merged detected lane line within the near-vehicle range. In the range outside the preset local range (i.e., the far-vehicle range), the accuracy of the high-precision map lane line is high. Therefore, in the far-vehicle range, the weight of the feature points on the observed lane line is less than the weight of the feature points on the target high-precision map lane line, which can improve the accuracy of the merged detected lane line within the far-vehicle range, thereby improving the accuracy and reliability of the detected lane line.

[0092] In some embodiments, before S204, the method of the embodiment of the present application further includes:

[0093] S2001. Determine the position deviation between the observed lane line and the target high-precision map lane line.

[0094] S2002: When the position deviation is less than or equal to a preset position value, the observed lane line is merged with the target high-precision map lane line.

[0095] In order to further improve the accuracy of lane line detection, in some embodiments, the credibility of the lane lines obtained from the target high-precision map is also evaluated.

[0096] In the near-vehicle range, the observed lane line can be considered to be relatively accurate, so the position deviation between the observed lane line and the target high-precision map lane line can be used to measure the credibility of the high-precision map. Specifically, the position deviation between the observed lane line and the target high-precision map lane line can be determined based on the position information of each feature point of the observed lane line and the position information of each feature point of the target high-precision map lane line. For example, the sum of the differences between the position information of each feature point of the observed lane line and the position information of each feature point of the target high-precision map lane line is used as the position deviation between the observed lane line and the target high-precision map lane line.

[0097] When the position deviation between the observed lane line and the target high-precision map lane line is less than or equal to the preset position value, it means that the high-precision map lane line is reliable. At this time, the above step S204 is executed again to merge the observed lane line and the target high-precision map lane line into a detected lane line.

[0098] In a possible implementation, the above S2002 includes:

[0099] Step D: Determine the position deviation between the observed lane line and the target high-precision map lane line based on the matching degree between the feature points of the observed lane line and the feature points on the target high-precision map lane line.

[0100] For example, the position deviation between the observed lane line and the target high-precision map lane line may be determined by summing the matching degrees between the feature points of the observed lane line and the feature points on the target high-precision map lane line.

[0101] The lane line detection method provided in the embodiment of the present application obtains at least one high-precision map lane line from the high-precision map according to the position information of the vehicle, matches the observed lane line with the at least one high-precision map lane line within a preset local range, selects one from the at least one high-precision map lane line as the target high-precision map lane line according to the matching degree between the observed lane line and the at least one high-precision map lane line, fuses the observed lane line with the target high-precision map lane line, and determines the detected lane line. In this way, a target high-precision map lane line with the highest credibility is selected from at least one high-precision map lane line through a relatively credible observed lane line in the vicinity, and then the target high-precision map lane line is used to repair the low-precision observed lane line, and finally a high-precision and high-reliability detected lane line is obtained. The vehicle plans the state of intelligent driving of the vehicle according to the high-precision detected lane line, which can achieve accurate guidance of intelligent driving, thereby improving the safety of intelligent driving.

[0102] Figure 4 A schematic diagram of an electronic device provided in an embodiment of the present application, such as Figure 4As shown, the electronic device 200 of the embodiment of the present application is arranged on a vehicle, and the electronic device 200 includes at least one memory 210 and at least one processor 220. The memory 210 is used to store a computer program; the processor 220 is used to execute the computer program.

[0103] When executing the computer program, the processor 220 obtains the observed lane line observed online, where the observed lane line is the lane line observed and obtained by the sensor 230 mounted on the vehicle; matches the observed lane line with the high-precision map lane line within a preset local range to obtain a matching result; and determines the detection lane line based on the matching result.

[0104] Optionally, the sensor 230 may be disposed on the electronic device 200 or on the vehicle, and the sensor 230 is communicatively connected with the electronic device 200 .

[0105] The electronic device of the embodiment of the present application can be used to execute the technical solution of the method embodiment shown above, and its implementation principle and technical effect are similar, which will not be repeated here.

[0106] In a possible implementation, the processor 220 is specifically configured to determine the detected lane line through the observed lane line and the high-precision map lane line according to the matching result.

[0107] In a possible implementation, the processor 200 is specifically configured to obtain a road image of the vehicle's surrounding environment through the sensor 230 mounted on the vehicle; and perform lane line detection on the road image to obtain the observed lane line.

[0108] Optionally, the preset local range is a local range close to the vehicle.

[0109] In a possible implementation, before matching the observed lane line with the high-precision map lane line, the processor 220 is further used to: obtain at least one high-precision map lane line from the high-precision map based on the position information of the vehicle; matching the observed lane line with the high-precision map lane line within a preset local range includes: matching the observed lane line with the at least one high-precision map lane line within a preset local range.

[0110] In a possible implementation, the processor 220 is specifically used to obtain at least one high-precision map lane line that is closest to the observation lane line from the at least one high-precision map lane line; within the preset local range, match the observation lane line with each high-precision map lane line in the at least one high-precision map lane line that is closest to the observation lane line.

[0111] In a possible implementation, the processor 220 is specifically used to obtain, for each high-precision map lane line, multiple feature points on the observation lane line and multiple feature points on the high-precision map lane line within the preset local range; determine the matching degree between each feature point on the observation lane line and each feature point on the high-precision map lane line; and determine the matching degree between the observation lane line and the high-precision map lane line based on the matching degree between each feature point on the observation lane line and each feature point on the high-precision map lane line.

[0112] In a possible implementation, the processor 220 is specifically configured to determine the sum of the matching degrees between each feature point on the observation lane line and each feature point on the high-precision map lane line as the matching degree between the observation lane line and the high-precision map lane line.

[0113] In a possible implementation, the processor 220 is specifically used to select one of the at least one high-precision map lane lines as the target high-precision map lane line based on the matching degree between the observed lane line and the at least one high-precision map lane line; and fuse the observed lane line with the target high-precision map lane line to determine the detected lane line.

[0114] In a possible implementation, before the processor 220 fuses the observed lane line with the target high-precision map lane line,

[0115] The processor 220 is also used to: determine the position deviation between the observed lane line and the target high-precision map lane line; when the position deviation is less than or equal to a preset position value, merge the observed lane line with the target high-precision map lane line.

[0116] In a possible implementation, the processor 220 is specifically used to determine the position deviation between the observed lane line and the target high-precision map lane line based on the matching degree between the feature points of the observed lane line and the feature points on the target high-precision map lane line.

[0117] In a possible implementation, the processor 220 is specifically configured to merge the feature points on the observation lane line with the feature points on the target high-precision map lane line.

[0118] In a possible implementation, the processor 220 is specifically used to merge the feature points on the observation lane line with the feature points on the target high-precision map lane line according to the weights of the feature points on the observation lane line and the weights of the feature points on the target high-precision map lane line.

[0119] In a possible implementation, within the preset local range, the weight of the feature points on the observation lane line is greater than the weight of the feature points on the target high-precision map lane line; and / or, within a range outside the preset local range, the weight of the feature points on the observation lane line is less than the weight of the feature points on the target high-precision map lane line.

[0120] Optionally, the feature points on the observed lane line and the high-precision map lane line are collected along the direction of the lane line at a preset collection interval.

[0121] The electronic device of the embodiment of the present application can be used to execute the technical solution of the method embodiment shown above, and its implementation principle and technical effect are similar, which will not be repeated here.

[0122] Figure 5 A schematic diagram of the structure of a vehicle provided in an embodiment of the present application, such as Figure 5 As shown, the vehicle 50 of this embodiment includes: a vehicle body 51 and an electronic device 52 installed on the vehicle body 51 .

[0123] The electronic device 52 may be Figure 4 The electronic device 52 shown is used for detecting lane lines.

[0124] Optionally, the electronic device 52 is mounted on the roof of the vehicle body 51, and the sensor is mounted on the vehicle body to collect environmental data around the vehicle, such as road images.

[0125] Optionally, the electronic device 52 is installed on the front windshield of the vehicle body 51 , or the electronic device 52 is installed on the rear windshield of the vehicle body 51 .

[0126] Optionally, the electronic device 52 is installed on the front of the vehicle body 51 , or the electronic device 52 is installed on the rear of the vehicle body 51 .

[0127] The embodiment of the present application does not limit the installation position of the electronic device 52 on the vehicle body 51, and the installation position is determined according to actual needs.

[0128] The vehicle of the embodiment of the present application can be used to execute the technical solution of the lane line detection method embodiment shown above, and its implementation principle and technical effect are similar, which will not be repeated here.

[0129] Figure 6 A schematic diagram of the structure of a vehicle provided in an embodiment of the present application, such as Figure 6 As shown, the vehicle 60 of this embodiment includes: a vehicle body 61 and an electronic device 62 installed on the vehicle body 61 .

[0130] The electronic device 62 may be Figure 4 The electronic device shown, the electronic device 62 is used for detecting lane lines.

[0131] Optionally, the vehicle 60 of this embodiment may be a ship, a car, a bus, a railway vehicle, an aircraft, a railway locomotive, a scooter, a bicycle, etc.

[0132] Optionally, the electronic device 62 can be installed at the front, rear or middle of the vehicle body 61. The embodiment of the present application does not limit the installation position of the electronic device 62 on the vehicle body 61, which is determined according to actual needs.

[0133] The vehicle of the embodiment of the present application can be used to execute the technical solution of the lane line detection method embodiment shown above, and its implementation principle and technical effect are similar, which will not be repeated here.

[0134] Furthermore, when at least part of the functions of the lane line detection method in the embodiment of the present application is implemented by software, the embodiment of the present application also provides a computer storage medium, which is used to store computer software instructions for the lane line detection, and when it is run on a computer, the computer can execute various possible lane line detection methods in the above method embodiment. When the computer execution instructions are loaded and executed on the computer, the process or function described in the embodiment of the present application can be generated in whole or in part. The computer instructions can be stored in a computer storage medium, or transmitted from one computer storage medium to another computer storage medium, and the transmission can be transmitted to another website, computer, server or data center by wireless (such as cellular communication, infrared, short-range wireless, microwave, etc.). The computer storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more available media. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a tape), an optical medium (for example, a DVD), or a semiconductor medium (for example, an SSD), etc.

[0135] A computer storage medium is also provided in an embodiment of the present invention. The computer storage medium stores program instructions. When the program is executed, it may include some or all steps of the lane line detection method in the above embodiments.

[0136] Those skilled in the art can understand that all or part of the steps of implementing the above method embodiments can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiments; and the aforementioned storage medium includes: read-only memory (ROM), random access memory (RAM), magnetic disk or optical disk, etc. Various media that can store program codes.

[0137] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A lane line detection method, characterized in that: include: Acquire an observed lane line observed online, where the observed lane line is a lane line observed and acquired by a sensor mounted on the vehicle; Matching the observed lane line with the high-precision map lane line within a preset local range to obtain a matching result; the preset local range is a local range close to the vehicle; Determine the detection lane line according to the matching result; If the matching result is greater than a first preset value, the high-precision map lane line is used as the detection lane line; if the matching result is less than a third preset value, the observed lane line is used as the detection lane line; the first preset value is greater than the third preset value; and / or, If the matching result is greater than a second preset value, determining the detection lane line through the observed lane line and the high-precision map lane line according to the matching result; Wherein, determining the detection lane line through the observation lane line and the high-precision map lane line includes: The observed lane line and the high-precision map lane line are merged to obtain the detected lane line.

2. The method according to claim 1, characterized in that: The obtaining of online observed lane lines includes: Acquiring a road image of the vehicle's surroundings through the sensor mounted on the vehicle; Perform lane line detection on the road image to obtain the observed lane line.

3. The method according to claim 1, characterized in that Before matching the observed lane line with the high-precision map lane line, the method further includes: Acquire at least one high-precision map lane line from a high-precision map according to the position information of the vehicle; The matching of the observed lane line and the high-precision map lane line within a preset local range includes: matching the observed lane line with the at least one high-precision map lane line within a preset local range.

4. The method according to claim 3, characterized in that Matching the observed lane line with the at least one high-precision map lane line within a preset local range includes: From the at least one high-precision map lane line, obtaining at least one high-precision map lane line that is closest to the observation lane line; Within the preset local range, the observation lane line is matched with each high-precision map lane line of at least one high-precision map lane line closest to the observation lane line.

5. The method according to claim 3, characterized in that: The matching of the observed lane line with the at least one high-precision map lane line within a preset local range includes: For each high-precision map lane line, within the preset local range, a plurality of feature points on the observation lane line and a plurality of feature points on the high-precision map lane line are obtained; Determine a degree of match between each feature point on the observed lane line and each feature point on the high-precision map lane line; The matching degree between the observation lane line and the high-precision map lane line is determined according to the matching degree between each feature point on the observation lane line and each feature point on the high-precision map lane line.

6. The method according to claim 5, characterized in that The determining the matching degree between the observed lane line and the high-precision map lane line according to the matching degree between each feature point on the observed lane line and each feature point on the high-precision map lane line includes: The sum of the matching degrees between each feature point on the observation lane line and each feature point on the high-precision map lane line is determined as the matching degree between the observation lane line and the high-precision map lane line.

7. The method according to any one of claims 4 to 6, characterized in that: The determining the detection lane line through the observed lane line and the high-precision map lane line according to the matching result includes: According to the matching degree between the observed lane line and the at least one high-precision map lane line, selecting one of the at least one high-precision map lane line as the target high-precision map lane line; The observed lane line is merged with the target high-precision map lane line to determine the detected lane line.

8. The method according to claim 7, characterized in that Before fusing the observed lane line with the target high-precision map lane line, the method further includes: Determine the position deviation between the observed lane line and the target high-precision map lane line; When the position deviation is less than or equal to the position preset value, the observed lane line is merged with the target high-precision map lane line.

9. The method according to claim 8, characterized in that The determining of the position deviation between the observed lane line and the target high-precision map lane line includes: The position deviation between the observed lane line and the target high-precision map lane line is determined according to the matching degree between the feature points of the observed lane line and the feature points on the target high-precision map lane line.

10. The method according to claim 7, characterized in that The fusing the observed lane line with the target high-precision map lane line includes: The feature points on the observed lane line are merged with the feature points on the target high-precision map lane line.

11. The method according to claim 10, characterized in that The merging of the feature points on the observed lane line with the feature points on the target high-precision map lane line includes: The feature points on the observation lane line are merged with the feature points on the target high-precision map lane line according to the weights of the feature points on the observation lane line and the weights of the feature points on the target high-precision map lane line.

12. The method according to claim 11, characterized in that Within the preset local range, the weight of the feature points on the observation lane line is greater than the weight of the feature points on the target high-precision map lane line; and / or, within a range outside the preset local range, the weight of the feature points on the observation lane line is less than the weight of the feature points on the target high-precision map lane line.

13. The method according to claim 5, characterized in that The feature points on the observed lane line and the high-precision map lane line are collected along the direction of the lane line according to a preset collection interval.

14. An electronic device, characterized in that: include: Memory for storing computer programs; The processor is used to execute the computer program, specifically to execute: obtaining an observed lane line observed online, wherein the observed lane line is a lane line observed and obtained by a sensor mounted on the vehicle; Matching the observed lane line with the high-precision map lane line within a preset local range to obtain a matching result; the preset local range is a local range close to the vehicle; Determine the detection lane line according to the matching result; If the matching result is greater than a first preset value, the high-precision map lane line is used as the detection lane line; if the matching result is less than a third preset value, the observed lane line is used as the detection lane line; the first preset value is greater than the third preset value; and / or, If the matching result is greater than a second preset value, determining the detection lane line through the observed lane line and the high-precision map lane line according to the matching result; Wherein, determining the detection lane line through the observation lane line and the high-precision map lane line includes: The observed lane line and the high-precision map lane line are merged to obtain the detected lane line.

15. The electronic device according to claim 14, characterized in that: The processor is specifically used to obtain a road image of the vehicle's surrounding environment through the sensor mounted on the vehicle; and perform lane line detection on the road image to obtain the observed lane line.

16. The electronic device according to claim 14, characterized in that: Before the processor matches the observed lane line with the high-precision map lane line, the processor is further used to: Acquire at least one high-precision map lane line from a high-precision map according to the position information of the vehicle; The matching of the observed lane line and the high-precision map lane line within a preset local range includes: matching the observed lane line with the at least one high-precision map lane line within a preset local range.

17. The electronic device according to claim 16, characterized in that: The processor is specifically used to obtain at least one high-precision map lane line that is closest to the observation lane line from the at least one high-precision map lane line; and within the preset local range, match the observation lane line with each high-precision map lane line in the at least one high-precision map lane line that is closest to the observation lane line.

18. The electronic device according to claim 16, characterized in that: The processor is specifically configured to obtain, for each high-precision map lane line, a plurality of feature points on the observation lane line and a plurality of feature points on the high-precision map lane line within the preset local range; and determine a matching degree between each feature point on the observation lane line and each feature point on the high-precision map lane line; The matching degree between the observation lane line and the high-precision map lane line is determined according to the matching degree between each feature point on the observation lane line and each feature point on the high-precision map lane line.

19. The electronic device according to claim 18, characterized in that: The processor is specifically used to determine the sum of the matching degrees between each feature point on the observation lane line and each feature point on the high-precision map lane line as the matching degree between the observation lane line and the high-precision map lane line.

20. The electronic device according to any one of claims 17 to 19, characterized in that: The processor is specifically used to select one of the at least one high-precision map lane lines as a target high-precision map lane line based on a matching degree between the observed lane line and the at least one high-precision map lane line; and fuse the observed lane line with the target high-precision map lane line to determine the detected lane line.

21. The electronic device according to claim 20, characterized in that: Before fusing the observed lane line with the target high-precision map lane line, the processor is further used to: Determine the position deviation between the observed lane line and the target high-precision map lane line; When the position deviation is less than or equal to the position preset value, the observed lane line is merged with the target high-precision map lane line.

22. The electronic device according to claim 21, characterized in that: The processor is specifically used to determine the position deviation between the observed lane line and the target high-precision map lane line according to the matching degree between the feature points of the observed lane line and the feature points on the target high-precision map lane line.

23. The electronic device according to claim 21, characterized in that: The processor is specifically used to merge the feature points on the observation lane line with the feature points on the target high-precision map lane line.

24. The electronic device according to claim 23, characterized in that: The processor is specifically used to merge the feature points on the observation lane line with the feature points on the target high-precision map lane line according to the weights of the feature points on the observation lane line and the weights of the feature points on the target high-precision map lane line.

25. The electronic device according to claim 24, characterized in that: Within the preset local range, the weight of the feature points on the observation lane line is greater than the weight of the feature points on the target high-precision map lane line; and / or, within a range outside the preset local range, the weight of the feature points on the observation lane line is less than the weight of the feature points on the target high-precision map lane line.

26. The electronic device according to claim 18, characterized in that: The feature points on the observed lane line and the high-precision map lane line are collected along the direction of the lane line according to a preset collection interval.

27. A vehicle, characterized in that: include: A vehicle body and an electronic device as claimed in any one of claims 14 to 26 installed on the vehicle body.

28. A means of transport, characterized in that: include: A vehicle body and the electronic device according to any one of claims 14 to 26 mounted on the vehicle body.

29. A computer storage medium, characterized in that The storage medium stores a computer program, and when the computer program is executed, the lane line detection method according to any one of claims 1 to 13 is implemented.

Images