WO2020232648A1 - Lane line detection method, electronic device and storage medium - Google Patents

Abstract

Provided in the embodiments of the present invention are a lane line detection method, an electronic device and a storage medium. The method comprises: acquiring an observed lane line observed online, wherein the observed lane line is a lane line observed and acquired by a sensor carried on a vehicle; matching, within a preset local range, the observed lane line and a high-definition map lane line; and determining a detected lane line according to a matching result. Thus, the reliability of a high-definition map lane line is determined by means of a relatively reliable nearby observed lane line, the problem of the observed lane line having low precision and being blocked is fixed by means of the far high-definition map lane line, and a highly precise and highly reliable detected lane line is finally obtained.

Description

Lane line detection method, electronic equipment and storage medium Technical field

The embodiments of the present invention relate to the technical field of intelligent driving, and in particular to a detection method of lane lines, electronic equipment and storage media.

Background technique

With the development of smart driving, in order to improve the safety of smart driving, it is necessary to check the lane lines on the road. The current lane line inspection method is the online observer, that is, the visual navigation system is used to find the position of the lane line in the road image from the captured road image, and then the lane line inspection is realized.

However, the method of online observation of the lane line is affected by the accuracy of the visual sensor. The lane line is more accurate in the close range. The farther the lane line is from the vehicle, the lower the accuracy and the less reliable it is. At the same time, if there are vehicles or obstacles in the field of view of the camera sensor, the detection result of the lane line is not accurate.

Summary of the invention

The embodiment of the present invention provides a lane line detection method, electronic equipment and storage medium to realize accurate detection of the lane line.

In the first aspect, an embodiment of the present application provides a method for detecting lane lines, including:

Acquiring an observation lane line for online observation, where the observation lane line is a lane line obtained through observation by a sensor mounted on the vehicle;

Matching the observation lane line and the high-precision map lane line within a preset local area to obtain a matching result;

According to the matching result, the detection lane line is determined.

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

Memory, used to store computer programs;

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

Acquiring an observation lane line for online observation, where the observation lane line is a lane line obtained through observation by a sensor mounted on the vehicle;

Matching the observation lane line and the high-precision map lane line within a preset local area to obtain a matching result;

According to the matching result, the detected lane line is determined by the observation lane line and the high-precision map lane line.

In a third aspect, an embodiment of the present application provides a vehicle including: a vehicle body and the electronic device according to any one of the second aspects installed on the vehicle body.

In a fourth aspect, an embodiment of the present application provides a vehicle including: a vehicle body and the electronic device of any one of the second aspect installed on the vehicle body.

In a fifth aspect, an embodiment of the present application provides a computer storage medium in which a computer program is stored, and the computer program implements the lane line detection method described in any one of the first aspect when the computer program is executed.

The lane line detection method, electronic equipment, and storage medium provided by the embodiments of the present application obtain the observation lane line observed online, and the observation lane line is the lane line obtained through the observation of the sensor mounted on the vehicle; Matching the observation lane line and the high-precision map lane line within a local range of, to obtain a matching result; and determining the detection lane line according to the matching result. In this way, it is judged whether there are positioning offset, outdated and other problems with the lane line of the HD map through the more reliable observation lane line nearby. If the reliability of the lane line of the HD map is high, use the remote HD map lane line to repair the observation. The problem of low accuracy of lane lines and obscured lane lines will eventually obtain high-precision and high-reliability detection lane lines. Based on the high-precision detection lane lines, the vehicle can plan the state of intelligent driving of the vehicle, such as lane change, deceleration or parking Realize accurate guidance to intelligent driving, thereby improving the safety of intelligent driving.

Description of the drawings

In order to explain the embodiments of the present invention or the technical solutions in the prior art more clearly, the following will briefly introduce the drawings used in the description of the embodiments or the prior art. Obviously, the drawings in the following description These are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative work.

FIG. 1 is a schematic diagram of an application scenario involved in an embodiment of this application;

2 is a flowchart of a method for detecting lane lines provided by an embodiment of the application;

FIG. 3 is a flowchart of a method for detecting lane lines according to an embodiment of the application;

FIG. 4 is a schematic diagram of an electronic device provided by an embodiment of this application;

FIG. 5 is a schematic structural diagram of a vehicle provided by an embodiment of the application;

Fig. 6 is a schematic diagram of the structure of a vehicle provided by an embodiment of the application.

Detailed ways

In order to make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be described clearly and completely in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments It is a part of the embodiments of the present invention, not all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative work shall fall within the protection scope of the present invention.

The method of the embodiment of the present invention is applicable to technical fields such as computer vision and intelligent driving, 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.

During intelligent driving, the vehicle needs to obtain a local lane line map, which is used to plan and formulate a vehicle driving plan and predict the trend of other vehicles. Among them, the real-time construction of fused local information using on-board sensors is called Online Measurement.

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

During intelligent driving, the vehicle can also obtain its own current absolute position, and read the pre-manually collected, modeled, and labeled high-precision map (HD Map) around the vehicle from the database according to the absolute position. Among them, the lane lines marked on the high-precision map (that is, the lane lines on the high-precision map) can also be used to plan and formulate vehicle driving plans and predict the trend of other vehicles.

In smart driving, using the observation lane line alone has the following problems: Affected by the accuracy of the sensor, the lane line is more accurate in close proximity, and the lane line farther from the vehicle has lower accuracy and less credibility; if the sensor’s field of view is in memory When vehicles, obstacles, etc. are blocked, the visual range of the lane line will be greatly reduced, causing difficulties in planning the vehicle driving plan.

When using HD map lane lines alone in intelligent driving, there are the following problems: the accuracy of HD map is affected by vehicle positioning, and vehicle positioning is offset, and the reliability of the entire HD map lane line will be greatly reduced; High-precision maps are time-sensitive. After road construction and diversion, if the high-precision maps cannot be updated in time, the reliability of the lane lines of the high-precision maps will be greatly reduced.

The lane line detection method provided by the embodiments of the application uses the fusion of the high-precision map lane line and the observation lane line, and judges whether the high-precision map lane line has a location based on the nearby (ie, the area close to the vehicle) more reliable observation lane line For problems such as offset and obsolescence, if the reliability of the high-precision map lane line is high, the high-precision map lane line in the distance (that is, the area away from the vehicle) is used to repair the problem of low accuracy and obscuration of the observed lane line.

FIG. 1 is a schematic diagram of an application scenario involved in an embodiment of this application. It should be noted that the application scenario of an embodiment of this application includes but is not limited to that shown in FIG. 1. As shown in Fig. 1, the smart driving vehicle is equipped with sensors such as monocular or binocular cameras. During the driving of the smart driving vehicle, the sensor can collect the surrounding environment, for example, collecting environmental images, which include road images. The vehicle can recognize the lane line according to the collected environmental images, obtain the observation lane line for online observation, and match the observation lane line with the high-precision map lane line within a preset local range to determine the final detection lane line. Judge whether the HD map lane line has positioning offset and outdated problems through the more credible observation lane line nearby. If the reliability of the HD map lane line is high, then use the distant HD map lane line to repair the observation lane The problem of low line accuracy and obscuration leads to a high-precision and high-reliability detection 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, decelerating or stopping, etc., which can realize accurate guidance for intelligent driving, thereby improving the safety of intelligent driving.

The technical solutions of the present invention will be described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments.

FIG. 2 is a flowchart of a method for detecting lane lines according to an embodiment of the application. As shown in FIG. 2, the method of the embodiment of the application includes:

S101. Obtain an observation lane line observed online, where the observation lane line is a lane line obtained through observation by a sensor mounted on a vehicle.

The execution subject of the embodiments 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. The detection device can be integrated in any electronic device as a part of the electronic device. Optionally, the detection device may also be a separate electronic device.

The electronic device may be a vehicle-mounted device, for example, an advanced driving assistance device.

The embodiment of the present application is described by taking an example where the execution subject is an electronic device.

Optionally, the sensor may specifically be a three-dimensional detection device and a vision sensor, etc. or a combination thereof. The vision sensor may be an imaging device. The point cloud sensor includes lidar and Time Of Flight (TOF) ranging detection. Equipment, depth vision sensor and high resolution millimeter wave radar, etc. 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-lens camera, where the multi-lens camera includes two or more cameras.

It should be noted that the observation lane line is only a naming of the lane line obtained through the observation of the sensor mounted on the vehicle. It is optional and can also be named according to actual needs.

The electronic device in the embodiment of the application is in communication connection with the sensor.

In an 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 to identify lane lines in the road images as observation lane lines. Then, the sensor sends the observation lane line to the electronic device.

In another example, the above S101 may be that the electronic device acquires environmental data around the vehicle, such as a road image, through the sensor mounted on the vehicle, and then the electronic device performs lanes on the road image. Line detection to obtain the observation lane line. Specifically, the sensor sends the real-time collected road image around the vehicle to the electronic device, and the electronic device processes the road image around the vehicle sent by the sensor to obtain the observation lane line for online observation.

Optionally, the above-mentioned observation lane line may be recognized and obtained according to an existing image recognition method, for example, the environmental data collected by the sensor (such as a road image) is input into a trained neural network, and the neural network outputs the observation lane line.

S102. Match the observation lane line and the high-precision map lane line within a preset local area to obtain a matching result.

According to the above steps, after the observation lane line is obtained, the observation lane line is matched with the HD map lane line to obtain the matching result. Specifically, the observation lane line and the HD map lane line are performed within a preset local range. Match, get the matching result.

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

The aforementioned preset local range can be any range obtained from the observation lane line according to actual needs.

Optionally, the above-mentioned preset local range may be a local range close to the vehicle. Since the accuracy of the observation lane line in the local range close to the vehicle is high, in this way, a more accurate observation lane line is used to determine whether the high-precision map lane line is The existence of positioning offset and outdated problems can improve the accurate judgment of the reliability of the lane line of the high-precision map.

S103: Determine the detection lane line according to the matching result.

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

In an example, the observed lane line or the high-precision map lane line is used as the detected lane line according to the matching result obtained in the foregoing steps.

For example, in a preset local area, if the matching result between the observed lane line and the HD map lane line is greater than the first preset value, the HD map is reliable. In this way, the HD map lane line can be used as the detection lane line. If the matching result of the observation 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 observation lane line is used as the detection lane line for driving guidance. Wherein, the first preset value is greater than the third preset value, and both the first preset value and the third preset value are set according to actual needs, which is not limited in this embodiment.

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

For example, in a preset local area, if the matching result between the observation lane line and the HD map lane line is greater than the second preset value, the observation lane line and the HD map lane line are merged into a lane line, and the merged The lane line as the detection lane line. Among them, the second preset value is set according to actual needs, which is not limited in this embodiment.

Optionally, another method may be used to determine the detected lane line based on the matching result through the observation lane line and the high-precision map lane line.

Optionally, the electronic device is communicatively connected with the intelligent driving system, and the electronic device can send the determined detection lane line to the intelligent driving system, so that the intelligent driving system can perform intelligent driving control of the vehicle according to the detected lane line.

The lane line detection method provided by the embodiment of the present application obtains the observation lane line observed online, and the observation lane line is the lane line obtained through the observation of the sensor mounted on the vehicle; within a preset local range, The observation lane line and the high-precision map lane line are matched to obtain a matching result; and the detection lane line is determined according to the matching result. In this way, it is judged whether there are positioning offset, outdated and other problems with the lane line of the HD map through the more reliable observation lane line nearby. If the reliability of the lane line of the HD map is high, use the remote HD map lane line to repair the observation. The problem of low accuracy of lane lines and obscured lane lines will eventually obtain high-precision and high-reliability detection lane lines. Based on the high-precision detection lane lines, the vehicle can plan the state of intelligent driving of the vehicle, such as changing lanes, decelerating or parking, etc. Realize accurate guidance to intelligent driving, thereby improving the safety of intelligent driving.

FIG. 3 is a flowchart of a method for detecting lane lines according to an embodiment of the application. On the basis of the foregoing embodiment, the method of the embodiment of the application includes:

S201: Acquire at least one high-precision map lane line from the high-precision map according to the position information of the vehicle.

The electronic device obtains the current position information of the vehicle from the positioning module of the vehicle, and obtains at least one high-definition map lane line near the vehicle from the high-definition map according to the position information of the vehicle.

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

In a preset local area, the observation lane line is matched with at least one high-precision map lane line, and the matching process includes but is not limited to the following methods.

In a possible embodiment, the foregoing S202 may include:

Step A1, from the at least one high-precision map lane line, obtain at least one high-precision map lane line closest to the observation lane line.

Step A2, within the preset local area, match each HD map lane line of the observation lane line with at least one HD map lane line closest to the observation lane line.

Specifically, from at least one high-precision map lane line, at least one high-precision map lane line closest to the observation lane line is obtained. In a preset local area, matching each of the high-precision map lane lines of the observation lane line and at least one high-precision map lane line closest to the observation lane line.

Exemplarily, select the head point of the feature point of the observation lane line a, select the K points closest to the head point from the feature points of all high-precision map lane lines, and use the lane line where the K points are located as the distance Observe the nearest K high-precision map lane lines. Then, select a high-precision map lane line b from the K high-precision map lane lines, and set the initial matching degree S=0 between the high-precision map lane line b and the observation lane line a. 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 between PA and PB, and then set S=S+D. Select the next feature point of PA and PB along the 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 compare the matching at this time The degree S is determined as the matching degree between the observation lane line a and the high-precision map lane line b.

By repeating the above steps, the matching degree between each of the K HD map lane lines and the observation lane line can be determined. According to the matching degree, a high-precision map lane line is selected from K high-precision map lane lines, merged with the observation lane line, and the detection lane line is determined.

Optionally, the observation lane line and the characteristic points on the high-precision map lane line are all collected along the direction of the lane line at a preset collection interval, for example, at equal intervals.

In a possible embodiment, the foregoing S202 may include:

Step B1, for each high-precision map lane line, acquire multiple feature points on the observation lane line and multiple feature points on the high-precision map lane line within the preset local range.

Step B2: Determine the degree of matching between each feature point on the observation lane line and each feature point on the high-precision map lane line.

Step B3: According to the degree of matching between each feature point on the observation lane line and each feature point on the high-precision map lane line, determine one of the observation lane line and the high-precision map lane line The degree of match between.

In this embodiment, both the input high-precision map lane line and the observation lane line can be regarded as a collection of points in the local space. These points are too dense, and the computational cost for matching is too large. Firstly, the curve is fitted to the point set of the observation lane line and each high-precision map lane line, and then sampling is performed according to the traveling direction of the lane line on the fitting curve of the observation lane line and the high-precision map lane line, such as sampling at equal intervals, to get The feature point set of the observed lane line and the feature point set of each high-precision map lane line are used for subsequent matching operations.

Take a high-precision map lane line c as an example to obtain multiple feature points of the high-precision map lane line c and multiple feature points of the observation lane line a. Among them, the feature points of the high-precision map lane line c and the observation lane line The feature points of a correspond one to one. Determine the degree of matching between each feature point on the observation lane line a and each feature point on the high-precision map lane line c. Then, according to 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, the matching degree between the observation lane line a and the high-precision map lane line c is determined. For example, the sum of 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 is determined as the difference between the observation lane line a and the high-precision map lane line c suitability.

S203. According to the degree of matching between the observed lane line and the at least one high-precision map lane line, one of the at least one high-precision map lane line is selected as a target high-precision map lane line.

According to the above steps, the degree of matching between the observation lane line and at least one HD map lane line can be determined. In this way, at least one HD map lane line can be selected according to the degree of matching between the observation lane line and at least one HD map lane line A 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. There is no restriction on this.

Optionally, the high-precision map lane line with the highest matching degree with the observation lane line among at least one high-precision map lane line is taken as the target high-precision map lane line.

S204. Fusion of the observed lane line and the target high-precision map lane line to determine the detected lane line.

According to the above steps, after the target high-precision map lane line is obtained, the observation lane line and the target high-precision map lane line are merged into one lane line as the detection lane line.

In a possible implementation manner, fusing the observation lane line with the target high-precision map lane line in S204 may include:

Step C: Combine the feature points on the observation lane line with the feature points on the target high-precision map lane line.

In this step, the feature points of the observation lane line and the feature points of the target HD map lane line are merged one by one into one feature point. For example, the observation lane line includes feature point 1 and feature point 2, and the target HD map lane line includes Feature point 3 and feature point 4, where 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 combined into one feature point, For example, the average of the location information of feature point 1 and feature point 2 is used as the location information of the combined feature point, and feature point 2 and feature point 4 are combined into one feature point, for example, the positions of feature point 2 and feature point 4 The average value of the information is used as the position information of the combined feature points, and the combined feature points form a new lane line as the detected lane line.

In a possible implementation manner, the above step C includes:

Step C1, according to the weight of the feature points on the observation lane line and the weight of the feature points on the target HD map lane line, compare the feature points on the observation lane line to the target HD map lane line The feature points on the above are merged.

In this step, when merging, the weights of the feature points of the observed lane line are different from the weights of the feature points of the target high-precision map. In this way, the weight of the feature points on the observed lane line and the target high-precision map The weights of the feature points on the lane line are combined with the feature points on the observation lane line and the target high-precision map lane line. Optionally, the weight of each feature point mentioned above should be set according to actual needs.

Optionally, within the preset local area, the weight of the feature point on the observation lane line is greater than the weight of the feature point on the target high-precision map lane line; and/or, in the preset In a range outside the 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.

Due to the high accuracy of the observation lane line in the preset local range (that is, the near car range), in the near car range, the weight of the feature points on the observation lane line is greater than the features on the target high-precision map lane line The weight of the points can improve the accuracy of the merged detection lane line within the range of the near car. In the range outside the preset local range (that is, within the range of the distant vehicle), the HD map lane line has high accuracy. Therefore, in the range of the distant vehicle, the weight of the feature points on the observation lane line is smaller than the target HD map. The weight of the feature points on the lane line can improve the accuracy of the merged detection lane line in the range of the far vehicle, thereby improving the accuracy and reliability of the detection lane line.

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

S2001. Determine the degree of position deviation between the observed lane line and the target high-precision map lane line.

S2002: When the position deviation is less than or equal to a preset position value, merge the observation lane line with the target high-precision map lane line.

In order to further improve the accuracy of detecting lane lines, in some embodiments, the credibility of the above-mentioned target high-precision map lane lines is also evaluated.

Within the range of a close car, the observation lane line can be considered to be more accurate, so the position deviation between the observation lane line and the target HD map lane line can be used to measure the credibility of the HD map. Specifically, the position deviation between the observation lane line and the target HD map lane line can be determined according to the location information of each feature point of the observation lane line and the location information of each feature point of the target HD map lane line. For example, the sum of the difference between the location information of each feature point of the observed lane line and the location information of each feature point of the target high-precision map lane line is taken as the difference between the observed lane line and the target high-precision map lane line The degree of position deviation.

When the position deviation between the observation lane line and the target HD map lane line is less than or equal to the preset position value, it indicates that the HD map lane line is reliable. At this time, the above step S204 is executed to change the observation lane line to the target High-precision map lane lines are merged into a detection lane line.

In a possible implementation manner, the foregoing S2002 includes:

Step D: Determine the position deviation between the observed lane line and the target high-precision map lane line according to the degree of matching between the feature points of the observation lane line and the target high-precision map lane line degree.

For example, the sum of the matching degrees between the characteristic points of the observed lane line and the target high-precision map lane line may be used to determine the positional deviation between the observed lane line and the target high-precision map lane line.

In the method for detecting lane lines provided by the embodiments of the present application, at least one high-precision map lane line is obtained from the high-precision map according to the position information of the vehicle, and within a preset local range, the observation lane line is compared with The at least one high-precision map lane line is matched, and one of the at least one high-precision map lane line is selected as the target high-precision map according to the degree of matching between the observation lane line and the at least one high-precision map lane line The lane line is to merge the observation lane line and the target high-precision map lane line to determine the detection lane line. In this way, the most reliable target HD map lane line is selected from at least one HD map lane line through the more reliable nearby observation lane line, and then the target HD map lane line is used to repair the low accuracy observation lane Finally, a high-precision and high-reliability detection lane line is obtained. The vehicle plans the intelligent driving state of the vehicle according to the high-precision detection lane line, which can realize accurate guidance for intelligent driving, thereby improving the safety of intelligent driving.

FIG. 4 is a schematic diagram of an electronic device provided by an embodiment of the application. As shown in FIG. 12, the electronic device 200 of the embodiment of the application is installed on a vehicle, and the electronic device 200 includes at least one memory 210 and At least one processor 220. Among them, the memory 210 is used to store a computer program; the processor 220 is used to execute the computer program.

The processor 220, when executing the computer program, acquires the observation lane line observed online, the observation lane line is the lane line obtained through the observation of the sensor 230 mounted on the vehicle; within a preset local range, The observation lane line is matched with the high-precision map lane line to obtain a matching result; and the detection lane line is determined according to the matching result.

Optionally, the above-mentioned sensor 230 may be arranged on the electronic device 200 or on a vehicle, and the sensor 230 is in communication connection with the electronic device 200.

The electronic device of the embodiment of the present application may be used to execute the technical solution of the method embodiment shown above, and its implementation principles and technical effects are similar, and will not be repeated here.

In a possible implementation manner, the processor 220 is specifically configured to determine a detection lane line according to the matching result, through the observation lane line and the high-precision map lane line.

In a possible implementation manner, the processor 200 is specifically configured to obtain a road image of the surrounding environment of the vehicle through the sensor 230 mounted on the vehicle; and perform lane line detection on the road image To obtain the observation lane line.

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

In a possible implementation manner, before the processor 220 matches the observation lane line with the high-precision map lane line, the processor 220 is further configured to: according to the position information of the vehicle, from the high Acquiring at least one high-precision map lane line on the fine map; the matching the observation lane line and the high-precision map lane line within a preset local range includes: matching the The observation lane line is matched with the at least one high-precision map lane line.

In a possible implementation manner, the processor 220 is specifically configured to obtain at least one HD map lane line that is closest to the observation lane line from the at least one HD map lane line; In a preset local area, matching each of the high-precision map lane lines among the observation lane line and at least one high-definition map lane line closest to the observation lane line.

In a possible implementation manner, the processor 220 is specifically configured to acquire multiple feature points on the observation lane line within the preset local range for each high-precision map lane line and Multiple feature points on the lane line of the high-precision map; determine the degree of matching between each feature point on the observation lane line and each feature point on the lane line of the high-precision map; according to the observation The degree of matching between each feature point on the lane line and each feature point on the lane line of the high-precision map determines the degree of matching between the observed lane line and the lane line of the high-precision map.

In a possible implementation manner, the processor 220 is specifically configured to compare the matching degree between each feature point on the observation lane line and each feature point on the high-precision map lane line And are determined as the degree of matching between the observation lane line and the high-precision map lane line.

In a possible implementation, the processor 220 is specifically configured to select from the at least one HD map lane line according to the degree of matching between the observation lane line and the at least one HD map lane line One is used as a target high-precision map lane line; the observation lane line is merged with the target high-precision map lane line to determine the detection lane line.

In a possible implementation manner, before the processor 220 merges the observation lane line with the target high-precision map lane line,

The processor 220 is further configured to determine the degree of position deviation between the observation lane line and the target high-precision map lane line; when the position deviation degree is less than or equal to the preset position value, the observation lane line Fusion with the target high-precision map lane line.

In a possible implementation manner, the processor 220 is specifically configured to determine the observation lane according to the matching degree between the feature points of the observation lane line and the target high-precision map lane line. The degree of position deviation between the line and the target high-precision map lane line.

In a possible implementation manner, 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.

In a possible implementation manner, the processor 220 is specifically configured to combine the observed weights of the feature points on the lane lines and the weights of the feature points on the target high-precision map The feature points on the lane line are merged with the feature points on the lane line of the target high-precision map.

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

Optionally, the observation lane line and the feature points on the high-precision map lane line are all collected along the direction of the lane line according to a preset collection interval.

The electronic device of the embodiment of the present application may be used to execute the technical solution of the method embodiment shown above, and its implementation principles and technical effects are similar, and will not be repeated here.

FIG. 5 is a schematic structural diagram of a vehicle provided by an embodiment of the application. As shown in FIG. 5, a vehicle 50 of this embodiment includes a body 51 and an electronic device 52 installed on the body 51.

The electronic device 52 may be the electronic device shown in FIG. 4, and the electronic device 52 is used for lane line detection.

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

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.

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.

The embodiment of the present application does not limit the installation position of the electronic device 52 on the body 51, which is specifically determined according to actual needs.

The vehicle of the embodiment of the present application may be used to implement the technical solution of the above-mentioned embodiment of the lane line detection method, and its implementation principles and technical effects are similar, and will not be repeated here.

FIG. 6 is a schematic structural diagram of a vehicle provided by an embodiment of the application. As shown in FIG. 6, the vehicle 60 of this embodiment includes a vehicle body 61 and an electronic device 62 installed on the vehicle body 61.

The electronic device 62 may be the electronic device shown in FIG. 4, and the electronic device 62 is used for lane line detection.

Optionally, the vehicle 60 in this embodiment may be a ship, automobile, bus, railway vehicle, aircraft, railway locomotive, scooter, bicycle, etc.

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

The vehicles in the embodiments of the present application can be used to implement the technical solutions of the above-mentioned embodiment of the lane line detection method, and the implementation principles and technical effects are similar, and will not be repeated here.

Further, when at least a 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 for storing the computer software instructions for the lane line detection above When it runs on a computer, the computer can execute various possible lane line detection methods in the foregoing method embodiments. When the computer-executable instructions are loaded and executed on the computer, the processes or functions described in the embodiments of the present application can be generated in whole or in part. The computer instructions may be stored in a computer storage medium, or transmitted from one computer storage medium to another computer storage medium, and the transmission may be transmitted to another by wireless (such as cellular communication, infrared, short-range wireless, microwave, etc.) Website site, computer, server or data center for transmission. The computer storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server or data center integrated with one or more available media. The usable medium may be a magnetic medium (for example, a floppy disk, a hard disk, a magnetic tape), an optical medium (for example, a DVD), or a semiconductor medium (for example, an SSD).

The embodiment of the present invention also provides a computer storage medium, the computer storage medium stores program instructions, and the program execution may include part or all of the steps of the lane line detection method in the foregoing embodiments.

A person of ordinary skill in the art can understand that all or part of the steps in the above method embodiments can be implemented by a program instructing relevant hardware. The foregoing program can be stored in a computer readable storage medium. When the program is executed, it is executed. Including the steps of the foregoing method embodiment; and the foregoing storage medium includes: read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic disks or optical disks, etc., which can store program codes Medium.

Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand: It is still possible to modify the technical solutions described in the foregoing embodiments, or equivalently replace some or all of the technical features; these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the technical solutions of the embodiments of the present invention range.

Claims (33)

1. A method for detecting lane lines, which is characterized in that it includes:

   Acquiring an observation lane line for online observation, where the observation lane line is a lane line obtained through observation by a sensor mounted on the vehicle;

   Matching the observation lane line and the high-precision map lane line within a preset local area to obtain a matching result;

   According to the matching result, the detection lane line is determined.
2. The method according to claim 1, wherein the determining a detection lane line according to the matching result comprises:

   According to the matching result, the detected lane line is determined by the observation lane line and the high-precision map lane line.
3. The method according to claim 1 or 2, characterized in that said acquiring the observation lane line observed online comprises:

   Acquiring a road image of the surrounding environment of the vehicle through the sensor mounted on the vehicle;

   Performing lane line detection on the road image to obtain the observation lane line.
4. The method according to claim 2, wherein the preset local range is a local range close to the vehicle.
5. The method according to claim 4, characterized in that, before matching the observation lane line and the high-precision map lane line, the method further comprises:

   Acquiring at least one high-precision map lane line from the high-precision map according to the location information of the vehicle;

   The matching the observation lane line and the high-precision map lane line within a preset local range includes: matching the observation lane line and the at least one high-precision map lane within the preset local area Line to match.
6. The method according to claim 5, wherein the matching of the observation lane line with the at least one high-precision map lane line within a preset local range comprises:

   From the at least one high-precision map lane line, acquiring at least one high-precision map lane line closest to the observation lane line;

   Within the preset local area, matching each of the high-definition map lane lines of the observation lane line and at least one high-definition map lane line closest to the observation lane line.
7. The method according to claim 5, wherein the matching the observation lane line with the at least one high-precision map lane line within a preset local range comprises:

   For each high-precision map lane line, within the preset local range, acquire multiple feature points on the observation lane line and multiple feature points on the high-precision map lane line;

   Determining the degree of matching between each feature point on the observation lane line and each feature point on the high-precision map lane line;

   According to the degree of matching between each feature point on the observation lane line and each feature point on the high-precision map lane line, determine the match between the observation lane line and the high-precision map lane line degree.
8. The method according to claim 7, characterized in that said determining the degree of matching between each feature point on the observation lane line and each feature point on the high-precision map lane line The degree of matching between the observed lane line and the lane line of the high-precision map includes:

   The sum of the matching degree between each feature point on the observation lane line and each feature point on the high-precision map lane line is determined as the difference between the observation lane line and the high-precision map lane line The degree of match between.
9. The method according to any one of claims 6-8, wherein the determining a detection lane line according to the matching result through the observation lane line and the high-precision map lane line comprises:

   According to the degree of matching between the observation 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 a target high-precision map lane line;

   The observation lane line and the target high-precision map lane line are merged to determine the detection lane line.
10. The method according to claim 9, characterized in that, before fusing the observation lane line with the target high-precision map lane line, the method further comprises:

    Determining the degree of position deviation between the observation lane line and the target high-precision map lane line;

    When the position deviation is less than or equal to the preset position value, the observation lane line and the target high-precision map lane line are merged.
11. The method according to claim 10, wherein the determining the position deviation between the observation lane line and the target high-precision map lane line comprises:

    Determine the degree of position deviation between the observed lane line and the target high-precision map lane line according to the degree of matching between the feature points of the observed lane line and the target high-precision map lane line.
12. The method according to any one of claims 9-11, wherein the fusing the observation lane line with the target high-precision map lane line comprises:

    The feature points on the observation lane line and the feature points on the target high-precision map lane line are merged.
13. The method according to claim 12, wherein the merging the feature points on the observation lane line with the feature points on the target high-precision map lane line comprises:

    According to the weights of the feature points on the observation lane line and the weights of the feature points on the target HD map lane line, the feature points on the observation lane line are compared with the features on the target HD map lane line Click to merge.
14. The method according to claim 13, wherein, within the preset local area, the weight of the feature point on the observation lane line is greater than the weight of the feature point on the target high-precision map lane line; and /Or, in a range outside the preset local range, the weight of the feature point on the observation lane line is less than the weight of the feature point on the target high-precision map lane line.
15. The method according to any one of claims 7-14, wherein the observation lane line and the feature points on the high-precision map lane line are all along the direction of the lane line according to a preset collection Collected at intervals.
16. An electronic device, characterized in that it comprises:

    Memory, used to store computer programs;

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

    Acquiring an observation lane line for online observation, where the observation lane line is a lane line obtained through observation by a sensor mounted on the vehicle;

    Matching the observation lane line and the high-precision map lane line within a preset local area to obtain a matching result;

    According to the matching result, the detected lane line is determined by the observation lane line and the high-precision map lane line.
17. The electronic device according to claim 16, wherein:

    The processor is specifically configured to determine a detected lane line through the observation lane line and the high-precision map lane line according to the matching result.
18. The electronic device according to claim 16 or 17, wherein:

    The processor is specifically configured to obtain a road image of the surrounding environment of the vehicle through the sensor mounted on the vehicle; perform lane line detection on the road image to obtain the observation lane line.
19. The electronic device according to claim 17, wherein the preset local range is a local range close to the vehicle.
20. The electronic device according to claim 19, wherein, before the processor matches the observation lane line with the high-precision map lane line, the processor is further configured to:

    Acquiring at least one high-precision map lane line from the high-precision map according to the location information of the vehicle;

    The matching the observation lane line and the high-precision map lane line within a preset local range includes: matching the observation lane line and the at least one high-precision map lane within the preset local area Line to match.
21. The electronic device according to claim 20, wherein:

    The processor is specifically configured 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; The observation lane line is matched with each high-precision map lane line in the at least one high-precision map lane line closest to the observation lane line.
22. The electronic device according to claim 20, wherein:

    The processor is specifically configured to, for each high-precision map lane line, obtain multiple feature points on the observation lane line and multiple lane lines on the high-precision map within the preset local range. Feature points; determine the degree of matching between each feature point on the observation lane line and each feature point on the high-precision map lane line; according to each feature point on the observation lane line and the The degree of matching between each feature point on the lane line of the high-precision map determines the degree of matching between the observation lane line and the lane line of the high-precision map.
23. The electronic device according to claim 22, wherein:

    The processor 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 observation lane line and The degree of matching between lane lines of the high-precision map.
24. The electronic device according to any one of claims 21-23, wherein:

    The processor is specifically configured to select one of the at least one HD map lane line as a target HD map lane line according to the degree of matching between the observation lane line and the at least one HD map lane line; The observation lane line is fused with the target high-precision map lane line to determine the detection lane line.
25. The electronic device according to claim 24, wherein the processor is further configured to: before fusing the observation lane line with the target HD map lane line:

    Determining the degree of position deviation between the observation lane line and the target high-precision map lane line;

    When the position deviation is less than or equal to the preset position value, the observation lane line and the target high-precision map lane line are merged.
26. The electronic device according to claim 25, wherein:

    The processor is specifically configured to determine the observation lane line and the target HD map lane line according to the degree of matching between the feature points of the observation lane line and the target HD map lane line The degree of position deviation between.
27. The electronic device according to any one of claims 24-26, wherein:

    The processor 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.
28. The electronic device according to claim 27, wherein:

    The processor is specifically configured to compare the feature points on the observation lane line with the target according to the weight of the feature points on the observation lane line and the weight of the feature points on the target high-precision map lane line. The feature points on the lane line of the high-precision map are merged.
29. The electronic device according to claim 28, wherein within the preset local area, the weight of the feature point on the observation lane line is greater than the weight of the feature point on the target high-precision map lane line; And/or, in a range outside the preset local range, the weight of the feature point on the observation lane line is less than the weight of the feature point on the target high-precision map lane line.
30. The electronic device according to any one of claims 22-29, wherein the observation lane line and the feature points on the high-precision map lane line are all along the direction of the lane line according to a preset The collection interval is collected.
31. A vehicle, characterized by comprising: a vehicle body and the electronic device according to any one of claims 16-30 installed on the vehicle body.
32. A vehicle, characterized by comprising: a vehicle body and the electronic device according to any one of claims 16-30 installed on the vehicle body.
33. A computer storage medium, characterized in that a computer program is stored in the storage medium, and the computer program, when executed, realizes the lane line detection method according to any one of claims 1-15.

Images