CN118628998A

CN118628998A - Lane line processing method, lane line processing device, vehicle, storage medium and program product

Info

Publication number: CN118628998A
Application number: CN202411096333.9A
Authority: CN
Inventors: 刘子明
Original assignee: Xiaomi Automobile Technology Co Ltd
Current assignee: Xiaomi Automobile Technology Co Ltd
Priority date: 2024-08-09
Filing date: 2024-08-09
Publication date: 2024-09-10

Abstract

The disclosure relates to a lane line processing method, a lane line processing device, a vehicle, a storage medium and a program product, and relates to the technical field of automatic driving, comprising: acquiring at least two lane lines; the at least two lane lines are lane lines obtained by different modes; removing target lane lines from the at least two lane lines to obtain at least two lane lines to be matched; the device for acquiring the at least two lane lines is positioned at one side of a non-crossing boundary, the target lane line is positioned at the other side of the non-crossing boundary, and the non-crossing boundary is a boundary which the device cannot pass through; and matching the at least two lane lines to be matched to obtain matched lane lines. By using the lane line processing method provided by the disclosure, the accuracy of lane line matching can be improved, and the accuracy of equipment positioning is further improved.

Description

Lane line processing method, lane line processing device, vehicle, storage medium and program product

Technical Field

The present disclosure relates to the field of automatic driving technologies, and in particular, to a lane line processing method, a lane line processing device, a vehicle, a storage medium, and a program product.

Background

Currently, in an automatic driving scene of a vehicle, the position of the vehicle on a road can be judged by identifying a lane line where the vehicle is located, so that the vehicle is prevented from deviating from the lane.

In the related art, the lane line where the vehicle is located can be identified, but the accuracy of the identified lane line is low, so that the accuracy of automatic driving judgment of the vehicle based on the lane line with low accuracy is reduced, and dangerous automatic driving conditions occur.

Disclosure of Invention

To overcome the problems in the related art, the present disclosure provides a lane line processing method, apparatus, vehicle, storage medium, and program product.

According to a first aspect of an embodiment of the present disclosure, there is provided a lane line processing method, including:

acquiring at least two lane lines; the at least two lane lines are lane lines obtained in different modes;

Removing target lane lines from the at least two lane lines to obtain at least two lane lines to be matched; the device for acquiring the at least two lane lines is positioned at one side of a non-crossing boundary, the target lane line is a lane line positioned at the other side of the non-crossing boundary, and the non-crossing boundary is a boundary through which the device cannot pass;

and matching the at least two lane lines to be matched to obtain matched lane lines.

Optionally, the at least two lane lines include a first lane line and a second lane line acquired in two different manners, and the target lane line includes a first target lane line and a second target lane line; the removing the target lane line from the at least two lane lines to obtain at least two lane lines to be matched includes:

and removing the first target lane line from the first lane line to obtain a first lane line to be matched, and removing the second target lane line from the second lane line to obtain a second lane line to be matched.

Optionally, the removing the first target lane line from the first lane line to obtain a first lane line to be matched includes:

and removing the first target lane line positioned at the other side of the non-crossing boundary from the first lane line to obtain the first lane line to be matched.

Optionally, the removing the second target lane line from the second lane line to obtain a second lane line to be matched includes:

and removing a second target lane line corresponding to the first target lane line from the second lane line to obtain the second lane line to be matched.

Optionally, the matching the at least two lane lines to be matched to obtain matched lane lines includes:

Reserving lane line segments, of which the distance between the lane lines and the equipment is smaller than a preset distance, on the at least two lane lines;

And matching at least two lane line segments to obtain matched lane lines.

Optionally, the reserving the lane line segment with the distance between the at least two lane lines and the device smaller than the preset distance includes:

And reserving the lane line segments on the at least two lane lines, the distance between the lane line segments and the equipment is smaller than the preset distance under the condition that the error between the at least two lane lines is larger than the preset error.

Optionally, the method further comprises:

Reserving a lane line which is positioned at the other side of the crossing boundary in the at least two lane lines; wherein the device that obtains the at least two lane lines is located on one side of the strainable boundary, which is a boundary through which the device can pass.

Optionally, the lane lines to be matched include at least one first lane line to be matched and at least one second lane line to be matched; the step of matching the at least two lane lines to be matched to obtain matched lane lines comprises the following steps:

Respectively matching the at least one first lane line to be matched with the at least one second lane line to be matched to obtain the weight between the at least one first lane line to be matched and the at least one second lane line to be matched;

And obtaining the matched lane lines after matching according to the weights.

Optionally, the at least two lane lines include two lane lines, one of the two lane lines is a lane line acquired by the image acquisition device, and the other lane line is a lane line acquired from the map.

According to a second aspect of the embodiments of the present disclosure, there is provided a lane line processing apparatus including:

The acquisition module is configured to acquire at least two lane lines; the at least two lane lines are lane lines obtained in different modes;

the removing module is configured to remove the target lane lines from the at least two lane lines to obtain at least two lane lines to be matched; the device for acquiring the at least two lane lines is positioned at one side of a non-crossing boundary, the target lane line is a lane line positioned at the other side of the non-crossing boundary, and the non-crossing boundary is a boundary through which the device cannot pass;

the matching module is configured to match the at least two lane lines to be matched to obtain matched lane lines.

According to a third aspect of embodiments of the present disclosure, there is provided a vehicle comprising:

A processor;

A memory for storing processor-executable instructions;

wherein the processor is configured to:

The steps of the lane line processing method provided in the first aspect of the embodiment of the present disclosure are executed.

According to a fourth aspect of the disclosed embodiments, there is provided a computer-readable storage medium having stored thereon computer program instructions which, when executed by a processor, implement the steps of the lane line processing method provided by the first aspect of the disclosed embodiments.

According to a fifth aspect of embodiments of the present disclosure, there is provided a computer program product comprising a computer program which, when executed by a processor, implements the steps of the lane line processing method provided by the first aspect of embodiments of the present disclosure.

The technical scheme provided by the embodiment of the disclosure can comprise the following beneficial effects:

The remaining lane lines are matched by removing lane lines located on the other side of the non-crossing boundary from at least two lane lines. According to the first aspect, lane lines to be matched, which are positioned on one side of a non-crossing boundary, can be reserved in the lane lines obtained in at least two ways, and the lane lines to be matched, which are positioned on the same side of the non-crossing boundary and are obtained in at least two ways, are matched, so that the situation that the lane lines on two sides of the non-crossing boundary are matched is avoided, the situation of mismatching is reduced, the accuracy of the matched lane lines is higher, and then the automatic driving safety of equipment is guaranteed. In the second aspect, the target lane lines on the other side of the non-crossing boundary are removed, so the number of lane lines to be matched for matching is reduced, thereby enabling faster matching speed and faster output of the device position.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the disclosure and together with the description, serve to explain the principles of the disclosure.

Fig. 1 is a flow chart illustrating steps of a lane line processing method according to an exemplary embodiment.

Fig. 2 is a logic diagram illustrating a lane line processing method according to an exemplary embodiment.

FIG. 3 is a schematic diagram of a lane line on the left and right sides of a non-crossing boundary, according to an example embodiment.

Fig. 4 is a schematic diagram illustrating a hungarian match according to an exemplary embodiment.

Fig. 5 is a schematic diagram showing weights derived from a hungarian match, according to an example embodiment.

Fig. 6 is a schematic diagram showing a map of lane lines acquired by the image acquisition device to form lane lines B on the map, according to an exemplary embodiment.

FIG. 7 is a schematic diagram showing errors between perceived lane lines and map lane lines, according to an example embodiment.

FIG. 8 is a schematic diagram illustrating a lane line that may cross left and right sides of a boundary, according to an example embodiment.

Fig. 9 is a block diagram illustrating a lane line processing apparatus according to an exemplary embodiment.

Fig. 10 is a block diagram of a vehicle, according to an exemplary embodiment.

Detailed Description

Reference will now be made in detail to exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated. The implementations described in the following exemplary examples are not representative of all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with some aspects of the present disclosure as detailed in the accompanying claims.

The implementations described below in some examples of the disclosure are not representative of all implementations consistent with the disclosure. Rather, they are merely examples of apparatus and methods consistent with some aspects of the present disclosure as detailed in the accompanying claims.

It should be noted that, all actions for acquiring signals, information or data in the present disclosure are performed under the condition of conforming to the corresponding data protection rule policy of the country of the location and obtaining the authorization given by the owner of the corresponding device.

In the related art, the device can be positioned based on a satellite positioning technology (Global Positioning System, GPS), but the satellite positioning technology has lower precision, and when the device is under a shielding object such as a viaduct or a tunnel, satellite signals are shielded or reflected, so that the position of the device cannot be accurately positioned; or when the device is in severe weather conditions, the device position may not be accurately obtained using satellite positioning techniques as well.

Inertial sensors (Inertial Measurement Unit, IMU) may also be used to acquire device position, but the device position measured by the inertial sensors may accumulate errors over time, which may lead to a gradual decrease in the accuracy of the acquired device position as the device is operated for a long period of time.

The lane line provided by the high-definition map and the lane line acquired by the image acquisition device can be matched, and then the equipment position is analyzed based on the matched lane line, but the lane line provided by the high-definition map and the lane line acquired by the image acquisition device are in mismatching, so that the position of the finally obtained lane line is inaccurate, the equipment position obtained based on the inaccurate lane line is also inaccurate, and the automatic driving is controlled based on the inaccurate equipment position, so that the safety is lower.

Based on this, the present disclosure proposes a lane line processing method, and fig. 1 is a flowchart of a lane line processing method according to an exemplary embodiment, as shown in fig. 1, including the following steps.

In step S11, at least two lane lines are acquired.

Optionally, the at least two lane lines include two lane lines, the two lane lines being lane lines obtained in two different manners.

For example, one of the two types of lane lines is a lane line acquired by the image acquisition device, and the other of the two types of lane lines is a lane line acquired from a high-precision map.

The image capturing device is a device configured on the apparatus for capturing environmental information around the apparatus, and may be a camera, a video camera, or the like, and the apparatus may be a movable apparatus such as a vehicle, a robot, a bicycle, a motorcycle, or the like. The image acquisition device not only can identify lane lines around the equipment, but also can identify environmental information such as marks and traffic signs on the ground, and the lanes where the equipment is located can be analyzed based on the lane lines, the marks, the traffic signs and the other environmental information, so that the equipment position is located.

The high-precision map is used for providing environmental information around a running road where the device is currently located, the environmental information including topological relations between roads, road components and road attributes. The topological relation can be information of interconnection between roads; the road parts comprise lane lines, traffic signals, road signs and the like of the road; the road attribute includes lane width, road surface material, etc.

Alternatively, the lane lines may be acquired by the image acquisition device, or the lane lines provided by the map may be acquired, so as to obtain two kinds of lane lines.

In step S12, the target lane line is removed from the at least two lane lines, so as to obtain at least two lane lines to be matched.

The target lane line is a lane line positioned at the other side of the non-crossing boundary, and the equipment for acquiring at least two lane lines is positioned at the one side of the non-crossing boundary.

For example, referring to FIG. 3, the box in FIG. 3 represents a non-crossing boundary, to the right of which is a device that obtains at least two lane lines, such as a vehicle; to the left of the non-crossing boundary is the target lane line.

The non-crossing boundary is a boundary through which the device cannot pass, such as a hard boundary of a flower bed, fence, stone pier, water horse, green belt, cliff, wall, etc., that blocks the device from crossing from one side of the non-crossing boundary to the other side of the non-crossing boundary.

Alternatively, the at least two lane lines include a lane line located on one side of the non-crossing boundary and a target lane line located on the other side of the non-crossing boundary, so that the target lane line located on the other side of the non-crossing boundary can be removed from the at least two lane lines, while the lane line located on one side of the non-crossing boundary is reserved, and the lane line on one side of the non-crossing boundary is taken as the lane line to be matched.

In the related art, since the satellite positioning technology and the inertial sensor are used to acquire the device position, there is an error between the satellite positioning technology and the device position acquired by the inertial sensor.

Based on this, can match the lane line that the high-definition map provided with the lane line that image acquisition device gathered, utilize the lane line after the matching to obtain the equipment position, but this scheme has following defect:

First defect: if the number of lane lines provided by the high-precision map is greater than the number of lane lines acquired by the image acquisition device, the matching speed is reduced, and the situation of matching errors is likely to occur, so that errors exist in the analyzed equipment positions.

For example, if the number of lane lines provided by the high-precision map is 10, the number of lane lines collected by the image collecting device is 4, at this time, the lane lines provided by the 10 high-precision map are respectively matched with the lane lines collected by the 4 image collecting devices one by one, and the number of matched lane lines is more, so that the matching speed is slow, and therefore, the equipment position cannot be provided in time.

In addition, if the 10 lane lines provided by the high-precision map include not only the lane line located at one side of the non-crossing boundary, but also the lane line located at the other side of the non-crossing boundary, the 4 lane lines collected by the image collecting device are located at one side of the non-crossing boundary, and because the lane lines are similar, the lane lines provided by the high-precision map and located at the other side of the non-crossing boundary may be successfully matched with the lane lines collected by the image collecting device, so that the two lane lines which are not identical lane lines are fused, the finally obtained lane lines are wrong, and the equipment position obtained based on the wrong lane lines also has errors.

Referring to fig. 3, since the distance between the lane line on the other side of the non-crossing boundary and the lane line on the other side of the non-crossing boundary is larger, if the lane line on the other side of the non-crossing boundary and the lane line on the other side of the non-crossing boundary are mismatched into the same lane line, a center lane line between the two lane lines is calculated, and the center lane line is used to analyze the device position, which can definitely cause a larger error in the analyzed device position.

Second defect: if the number of the lane lines acquired by the image acquisition device is larger than that provided by the high-precision map, the situation that the matching speed is slow and the matching is wrong can also exist.

For example, if the number of lane lines collected by the image collecting device is 5, the number of lane lines provided by the high-precision map is 2, at this time, the lane lines collected by the 5 image collecting devices are respectively matched with the lane lines provided by the 2 high-precision maps one by one, and the number of matched lane lines is more, so that the matching speed is slow, and therefore, the equipment position cannot be provided in time.

Moreover, if the 5 lane lines collected by the image collecting device include not only the lane line located at one side of the non-crossing boundary but also the lane line located at the other side of the non-crossing boundary, the 2 lane lines provided by the high-precision map are located at one side of the non-crossing boundary, and because the lane lines are similar, the lane lines located at the other side of the non-crossing boundary and the lane lines located at one side of the non-crossing boundary provided by the high-precision map may be successfully matched, and then a center lane line between the lane line located at the other side of the non-crossing boundary and the lane line located at one side of the non-crossing boundary is calculated, which results in that the center lane line obtained finally is wrong, and the equipment position obtained based on the wrong lane line also has errors.

It can be seen that matching at least two lane lines with a large number of different lane lines may occur in case of mismatching.

In the embodiment of the disclosure, the target lane line positioned at the other side of the non-crossing boundary is removed from at least two lane lines, so that the lane line to be matched positioned at the other side of the non-crossing boundary of the at least two lane lines, namely, the lane line positioned at the side of the equipment is reserved. Referring to fig. 3, lane lines collected by the image collecting device and lane lines provided by the map on the left side of the non-crossing boundary are removed, and lane lines collected by the image collecting device and lane lines provided by the map on the right side of the non-crossing boundary are reserved.

In the first aspect, after the target lane line on the other side of the non-crossing boundary is removed from at least two lane lines, the lane lines to be matched on the one side of the non-crossing boundary in the at least two lane lines are matched with each other, so that the number of the matched lane lines is reduced, and after the number of the matched lane lines is reduced, quick matching can be performed, and the position of the output device can be responded timely.

For example, in at least two types of lane lines, the number of lane lines acquired by the image acquisition device is 4, and the number of lane lines provided by the high-precision map is 10, then the target lane line positioned at the other side of the non-crossing boundary is removed from the lane lines acquired by the image acquisition device and the lane lines provided by the high-precision map, and the lane line to be matched positioned at the one side of the non-crossing boundary is reserved. After the target lane lines which do not cross the other side of the boundary are removed, the number of lane lines to be matched in the lane lines acquired by the image acquisition device is 4, and the number of lane lines to be matched in the lane lines provided by the high-precision map is also 4, the number of lane lines to be matched is reduced from 40 times of matching to 16 times of matching, the matching number is greatly reduced, and therefore the equipment positions can be timely output.

In the second aspect, after the lane line to be matched on one side of the non-crossing boundary is reserved from the at least two lane lines, the lane line to be matched on one side of the non-crossing boundary is matched, and the lane line to be matched on the other side of the non-crossing boundary is not matched, so that the matching error is reduced.

For example, referring to fig. 3, the lane lines to be matched on the same side of the non-crossing boundary are matched, and since the distance between the two lane lines to be matched on the same side of the non-crossing boundary is smaller, the error of the new lane line obtained after the two lane lines to be matched on the basis of the smaller distance is smaller, thereby ensuring the accuracy of the obtained lane line, and further, the position of the device analyzed on the basis of the lane line with relatively higher accuracy is more accurate.

In step S13, the at least two lane lines to be matched are matched, so as to obtain matched lane lines.

Referring to fig. 2, a hungarian matching method may be used to match at least two lane lines to be matched, so as to obtain matched lane lines.

Illustratively, the at least two lane lines to be matched comprise at least one first lane line to be matched and at least one second lane line to be matched; the at least one first lane line to be matched and the at least one second lane line to be matched can be respectively matched, so that weight between the at least one first lane line to be matched and the at least one second lane line to be matched is obtained; and obtaining the matched lane lines after matching according to the weights.

The obtaining of the matched lane lines based on the weights comprises the following steps: for each first lane line to be matched in at least one first lane line to be matched, respectively calculating the weight between the first lane line to be matched and at least one second lane line to be matched, screening out a lane line combination which enables the sum of the weights between the at least one first lane line to be matched and the at least one second lane line to be matched to reach the maximum, and providing at least one group of matched lane lines under the lane line combination.

For example, referring to fig. 4 and 5, at least one first lane line to be matched includes four lane lines L1 to L4, at least one second lane line to be matched includes three lane lines R1 to R3, weights between the four lane lines L1 to L4 and the three lane lines R1 to R3 may be calculated respectively, so as to obtain a weight table as shown in fig. 5; traversing all the weights to obtain a lane line combination capable of enabling the sum of the weights to reach the maximum, and as shown in fig. 5, the lane line combination capable of enabling the sum of the weights to reach the maximum between the four first lane lines to be matched of L1 to L4 and the three second lane lines to be matched of R1 to R3 is as follows: the first lane line to be matched L1 and the second lane line to be matched R2, the first lane line to be matched L2 and the second lane line to be matched R3, and the first lane line to be matched L3 and the second lane line to be matched R2, wherein the weight between the first lane line to be matched L1 and the second lane line to be matched R2 is 10, the weight between the first lane line to be matched L2 and the second lane line to be matched R1 is 6, the weight between the first lane line to be matched L3 and the second lane line to be matched R3 is 8, the weight obtained finally is 24, and the sum of the maximum weights is the maximum weight.

Then, after the matched lane line combination is obtained, a center lane line between the first lane line to be matched L1 and the second lane line to be matched R2 is calculated, and the center lane line is used as a new lane line after the first lane line to be matched L1 and the second lane line to be matched R2 are fused, and similarly, the method is also used for the rest of lane line combinations, and no further description is provided herein.

Optionally, for the weight between the first lane line to be matched and the second lane line to be matched, the weight between the first lane line to be matched and the second lane line to be matched may be obtained according to the first weight between the first lane line to be matched and the second weight between the first lane line to be matched and the second lane line to be matched.

The first weight between the first lane line to be matched and the second lane line to be matched is obtained through the following scheme: calculating a plurality of distances from a plurality of target points on the first lane to be matched to the second lane to be matched, and taking the average value of the plurality of distances as a distance average value; and obtaining a first weight according to the distance average value, wherein the distance average value is inversely proportional to the first weight.

Wherein the first weight may be obtained using a reciprocal distance weight scheme (INVERSE DISTANCE WEIGHTING, IDW) or a gaussian distance weight scheme.

For example, if the reciprocal weighting scheme is adopted, the calculation formula is as follows:

in the above-mentioned formula(s), Is a first weight that is to be applied to the first substrate,Is the distance average.

For example, if a gaussian distance weighting scheme is used, the calculation formula is as follows:

in the above-mentioned formula(s), Is a first weight that is to be applied to the first substrate,Is the distance from the ith target point to the second lane line to be matched; u is the distance average; Is the standard deviation of the multiple distances.

From the above formula, the smaller the average value of the distance is, the larger the first weight is, and the more the first lane line to be matched and the second lane line to be matched can represent the same lane line.

The second weight may be obtained according to the consistency of the attribute between the first lane line to be matched and the second lane line to be matched.

The attribute similarity includes the color and type between the first lane line to be matched and the second lane line to be matched.

If the color similarity and the type of the first lane line to be matched and the second lane line to be matched are different, the second weight is smaller than or equal to the first threshold value; if the color and the type of the first lane line to be matched are consistent with those of the second lane line to be matched, the second weight is larger than the first threshold value and smaller than the second threshold value; if the colors and types of the first lane line to be matched and the second lane line to be matched are the same, the second weight is larger than a second threshold value.

For example, the first threshold may be 0 and the second threshold may be 70%, which may be set according to actual conditions, which is not limited by the present disclosure.

Optionally, obtaining the weight between the first lane line to be matched and the second lane line to be matched according to the first weight and the second weight includes: and taking the sum of the first weight and the second weight as the weight between the first lane line to be matched and the second lane line to be matched.

It can be understood that, in any embodiment of the present disclosure, the lane line to be matched on the side not crossing the boundary refers to the lane line on the side not crossing the boundary with the device currently moving, and is also the lane line of the driving road on which the device is located; the target lane line on the other side of the non-crossing boundary refers to a lane line on the side of the non-crossing boundary where the device does not have current movement, and also a lane line of a reverse road of the driving road on which the device is located.

By the technical scheme, the lane lines positioned on the other side of the non-crossing boundary are removed from at least two lane lines, and the rest lane lines are matched.

According to the first aspect, lane lines to be matched, which are positioned on one side of a non-crossing boundary, can be reserved in the lane lines obtained in at least two ways, and the lane lines to be matched, which are positioned on the same side of the non-crossing boundary and are obtained in at least two ways, are matched, so that the situation that the lane lines on two sides of the non-crossing boundary are matched is avoided, the situation of mismatching is reduced, the accuracy of the matched lane lines is higher, and then the automatic driving safety of equipment is guaranteed.

In the second aspect, the target lane lines on the other side of the non-crossing boundary are removed, so the number of lane lines to be matched for matching is reduced, thereby enabling faster matching speed and faster output of the device position.

In the third aspect, the target lane line which is not on the other side of the crossing boundary, namely the lane line to be matched on the side without the current running device is removed, and the current running device does not cross the non-crossing boundary to the target lane line on the other side, and the running device on the other side of the non-crossing boundary does not cross the non-crossing boundary to the lane line where the current running device is located, so that even if the target lane line is removed, the matching fusion is not carried out on the target lane line, and the driving safety of the device is not influenced.

An exemplary embodiment related to the above step S12 for explaining an exemplary scheme of removing the target lane line in a different scene is described below.

The lane lines comprise a first lane line and a second lane line, the first target lane line can be removed from the first lane line to obtain a first lane line to be matched, and the second target lane line is removed from the second lane line to obtain a second lane line to be matched.

Optionally, removing a first target lane line located at the other side of the non-crossing boundary from the first lane line to obtain the first lane line to be matched, and removing a second target lane line corresponding to the first target lane line from the second lane line to obtain the second lane line to be matched.

The first lane line is a lane line acquired by the image acquisition device, and the corresponding second lane line is a lane line provided by a map; the first lane line is a lane line provided by a map, and the corresponding second lane line is a lane line acquired by the image acquisition device.

If the first lane line is the lane line acquired by the image acquisition device and the corresponding second lane line is the lane line provided by the map, the first target lane line is the target lane line positioned on the other side of the non-crossing boundary in the first lane line acquired by the image acquisition device, and the second lane line is the target lane line positioned on the other side of the non-crossing boundary in the second lane line provided by the map.

Otherwise, if the first lane line is a lane line provided by the map and the corresponding second lane line is a lane line acquired by the image acquisition device, the first target lane line is a target lane line positioned on the other side of the non-crossing boundary in the first lane line provided by the map, and the second lane line is a target lane line positioned on the other side of the non-crossing boundary in the second lane line acquired by the image acquisition device.

In the first scenario, taking the first lane line as the lane line acquired by the image acquisition device, the second lane line is the lane line provided by the map as an example.

The first target lane line positioned at the other side of the non-crossing boundary can be removed from the first lane line acquired by the image acquisition device, and the second target lane line corresponding to the first target lane line in the second lane line provided by the map is removed.

The second target lane line corresponding to the first target lane line is a lane line that is the same lane line as the first target lane line.

Referring to fig. 6, when the image capturing device captures the image information on the other side of the non-crossing boundary, the image capturing device is affected by the non-crossing boundary, the first target lane line in the image information on the other side of the non-crossing boundary captured by the image capturing device is not clear, after the first target lane line which is not clear is projected into the map, the distance error between the first target lane line (lane line B in fig. 6) and the corresponding second target lane line (lane line a in fig. 6) is larger, for example, the distance error may reach 1m to 3m, if the first target lane line and the second target lane line are matched, the second target lane line captured by the image capturing device is assumed to be accurate, and if the distance error between the first target lane line and the second target lane line which are captured by the image capturing device is not accurate, the new lane line calculated after the matching is 3m, the new lane line should be located between the first target lane line and the second target lane line, the new lane line and the accurate second target lane line are different by 1.5m, for example, and if the error between the new lane line and the second target lane line is also calculated to be greater, the error can be controlled to be greater, and the error can be controlled to the error.

In the embodiment of the disclosure, after the first target lane line is removed, the second target lane line matched with the first target lane line is also removed synchronously, for example, as shown in fig. 6, after the lane line B is removed, the corresponding lane line a is also removed, so that the error data is prevented from being matched, the problem of low equipment positioning caused by the error data is avoided, and the equipment is prevented from being controlled to run on the error lane by mistake.

Through the first scene, under the condition that a first target lane line positioned at the other side of the non-crossing boundary exists in the first lane lines acquired by the image acquisition device, the first target lane line which is not clear at the other side of the non-crossing boundary can be removed, so that a matching error caused by the first target lane line which is not clear is avoided; and the second target lane lines corresponding to the first target lane lines are removed, so that the number of the first lane lines acquired by the image acquisition device and the number of the second lane lines provided by the map can be kept consistent, and mismatching caused by inconsistent numbers is reduced.

In the second scenario, taking the first lane line as the lane line acquired by the map providing, the second lane line is the lane line acquired by the image acquisition device as an example.

The first target lane line positioned at the other side of the non-crossing boundary can be removed from the first lane line provided by the map, and the second target lane line corresponding to the first target lane line in the second lane lines acquired by the image acquisition device is removed.

The map defines whether the boundary between roads can be crossed, for example, hard boundaries such as fences, flower beds, water horses, cliffs, green belts and the like are non-crossing boundaries which cannot be crossed, and lane lines which are sprayed manually are crossing boundaries which can be crossed. When the non-crossing boundary exists in the environment information of the equipment provided by the map, the first target lane line positioned at the other side of the non-crossing boundary can be removed from the first lane line provided by the map, and the second target lane line corresponding to the first target lane line in the second lane line acquired by the image acquisition device can be removed.

Through the second scene, under the condition that a first target lane line positioned at the other side of the non-crossing boundary exists in a first lane line provided by the map, the first target lane line positioned at the other side of the non-crossing boundary can be removed, and a second target lane line corresponding to the first target lane line is correspondingly removed, so that the quantity of the first lane line provided by the map and the quantity of the second lane lines acquired by the image acquisition device can be kept consistent as much as possible, and the situation of mismatching caused by inconsistent quantity is reduced.

An exemplary embodiment related to the above step S13 for paraphrasing and intercepting part of lane lines of at least two kinds of lane lines for matching is described below, which includes the following steps.

(1) And reserving lane line segments, wherein the distance between the lane line segments and the equipment is smaller than a preset distance, on the at least two lane lines.

Optionally, if the error between the at least two lane lines is greater than a preset error, lane line segments on the at least two lane lines with a distance from the device smaller than a preset distance are reserved.

Optionally, if the error between the lane line collected by the image collecting device and the lane line provided by the high-precision map is smaller than or equal to the preset error, determining whether the lane line collected by the image collecting device and the lane line provided by the high-precision map are located at the other side of the non-crossing boundary, and if not, performing hungarian matching on the lane lines collected by the image collecting device and the lane line provided by the high-precision map, so as to obtain the matched lane line.

The error between the at least two lane lines may be an included angle or a distance between the at least two lane lines, and if the included angle between the at least two lane lines is greater than a preset included angle, it is indicated that the error between the at least two lane lines is greater than the preset error; or the distance between at least two lane lines is larger than the threshold distance, which means that the error between at least two lane lines is larger than the preset error.

Referring to fig. 7, taking a vehicle as an example, an image capturing device on the vehicle captures a lane line in front of the vehicle, when the vehicle bumps up and down due to an uneven road surface, the capturing view angle of the image capturing device is different, when the vehicle body is in a horizontal state and the vehicle head is in a lifted state, the capturing view angle of the image capturing device is different, so that the lane line captured by the image capturing device on the vehicle when the vehicle body is in a horizontal state is different from the lane line captured by the vehicle head when the vehicle head is lifted, at this time, if the lane line captured by the vehicle head is mapped onto a map, an included angle error is formed between the lane line captured by the map, and the error gradually increases along with the direction away from the vehicle, and referring to fig. 7, the distance between the perceived lane line captured by the image capturing device when the vehicle head is lifted and the map lane line provided by the map gradually increases along the direction away from the vehicle.

Based on the method, the lane line segments, of which the distance between at least two kinds of lane lines and the equipment is greater than or equal to the preset distance, can be removed under the condition that the error between at least two kinds of lane lines is greater than the preset error, so that the lane line segments of which the distance between at least two kinds of lane lines and the equipment is smaller than the preset distance are reserved.

Taking the preset distance of 7.5m as an example, removing the lane line segment outside the distance equipment of 7.5m on the sensing lane line and the map lane line, reserving the lane line segment within the distance equipment of 7.5m on the sensing lane line and the map lane line, and carrying out matching fusion on the lane line segment within the distance equipment of 7.5m on the sensing lane line and the map lane line.

(2) And matching at least two lane line segments to obtain matched lane lines.

Through the technical scheme, although errors exist between at least two collected lane lines, lane line segments with the distance between the lane line segments and the equipment being smaller than the preset distance can be reserved, and the errors between the lane line segments are smaller, so that the errors of the lane lines obtained after matching and fusion are smaller.

The present disclosure is presented below in relation to exemplary embodiments for interpreting an exemplary scenario in the event that a boundary is identified as being a traversable boundary, comprising:

The straddlable boundary is a soft boundary that can be spanned by a manually sprayed double solid line, double dashed line, single solid line, single dashed line, etc. device.

Referring to fig. 8, in the case that the environment information around the device has a crossing boundary, the road information on the other side of the crossing boundary is not blocked, and the image capturing device can capture a clear lane line on the other side of the crossing boundary, so that the lane line on the other side of the crossing boundary among the lane lines captured by the image capturing device can be retained, and meanwhile, the lane line on the other side of the crossing boundary among the lane lines provided by the retaining map is correspondingly retained.

It can be appreciated that, in any embodiment of the present disclosure, a lane line crossing a side of a boundary refers to a lane line crossing a side of a boundary having a device that is currently moving, and also is a lane line of a driving road on which the device is located; the lane line crossing the other side of the boundary refers to the lane line crossing the side of the boundary where the device that does not have current movement is also the lane line of the reverse road of the travel road where the device is located.

It can be understood that the lane lines provided by the map are lane lines of the road on which the device is driving, and the range of the lane lines which can be provided by the image acquisition device is larger, so that not only the lane lines of the road on which the device is driving, but also the lane lines which can cross the reverse road on the other side of the boundary can be provided, and therefore, the number of the lane lines which are acquired by the image acquisition device may be larger than the number of the lane lines provided by the map.

According to the technical scheme, in the first aspect, the running equipment on the other side of the crossing boundary can influence the running of the running equipment on the one side of the crossing boundary, so that the lane lines acquired by the image acquisition device on the other side of the crossing boundary can be reserved and combined with the lane lines provided by the map to provide more complete lane line information around the vehicle, and the auxiliary equipment can run safely on the current lane; in the second aspect, although the number of the lane lines acquired by the image acquisition device is larger than that provided by the map, the lane lines acquired by the image acquisition device are clear, so that the accuracy in matching can be improved, and the occurrence of mismatching caused by the number or unclear problems is reduced.

Fig. 9 is a block diagram illustrating a lane line processing apparatus according to an exemplary embodiment. Referring to fig. 9, the lane line processing apparatus 900 includes: an acquisition module 910, a removal module 920, and a matching module 930.

An acquisition module 910 configured to acquire at least two lane lines; the at least two lane lines are lane lines obtained in different modes;

A removing module 920, configured to remove the target lane line from the at least two lane lines, so as to obtain at least two lane lines to be matched; the device for acquiring the at least two lane lines is positioned at one side of a non-crossing boundary, the target lane line is a lane line positioned at the other side of the non-crossing boundary, and the non-crossing boundary is a boundary through which the device cannot pass;

And the matching module 930 is configured to match the at least two lane lines to be matched to obtain matched lane lines.

Optionally, the at least two lane lines include a first lane line and a second lane line acquired in two different manners, and the target lane line includes a first target lane line and a second target lane line; the removing module 920 is further configured to remove the first target lane line from the first lane line to obtain a first lane line to be matched, and remove the second target lane line from the second lane line to obtain a second lane line to be matched.

Optionally, the removing module 920 includes:

and the first removing submodule is configured to remove the first target lane line positioned at the other side of the non-crossing boundary from the first lane line, so as to obtain the first lane line to be matched.

Optionally, the removing module 920 includes:

and the second removing sub-module is configured to remove a second target lane line corresponding to the first target lane line from the second lane line, so as to obtain the second lane line to be matched.

Optionally, the matching module 930 includes:

A reserving submodule configured to reserve lane line segments on the at least two lane lines, wherein the distance between the lane line segments and the equipment is smaller than a preset distance;

And the matching sub-module is configured to match at least two lane line segments to obtain matched lane lines.

Optionally, the reservation sub-module is further configured to reserve a lane line segment on the at least two lane lines with a distance from the device smaller than a preset distance, if the error between the at least two lane lines is larger than a preset error.

Optionally, the lane line processing apparatus 900 includes:

A reservation module configured to reserve a lane line located at the other side of the spanable boundary among the at least two lane lines; wherein the device that obtains the at least two lane lines is located on one side of the strainable boundary, which is a boundary through which the device can pass.

Optionally, the lane lines to be matched include at least one first lane line to be matched and at least one second lane line to be matched; the matching module 930 includes:

The matching sub-module is configured to match the at least one first lane line to be matched with the at least one second lane line to be matched respectively, so as to obtain the weight between the at least one first lane line to be matched and the at least one second lane line to be matched;

and the calculation sub-module is configured to obtain matched lane lines according to the weights.

The specific manner in which the various modules perform the operations in the apparatus of the above embodiments have been described in detail in connection with the embodiments of the method, and will not be described in detail herein.

The present disclosure also provides a computer-readable storage medium having stored thereon computer program instructions which, when executed by a processor, implement the steps of the lane-line processing method provided by the present disclosure.

Fig. 10 is a block diagram of a vehicle 1000, according to an exemplary embodiment. For example, the vehicle 1000 may be a hybrid vehicle, or may be a non-hybrid vehicle, an electric vehicle, a fuel cell vehicle, or other type of vehicle. The vehicle 1000 may be an autonomous vehicle, a semi-autonomous vehicle, or a non-autonomous vehicle.

Referring to fig. 10, a vehicle 1000 may include various subsystems, such as an infotainment system 1010, a perception system 1020, a decision control system 1030, a drive system 1040, and a computing platform 1050. Wherein the vehicle 1000 may also include more or fewer subsystems, and each subsystem may include multiple components. In addition, interconnections between each subsystem and between each component of the vehicle 1000 may be achieved by wired or wireless means.

In some embodiments, the infotainment system 1010 may include a communication system, an entertainment system, a navigation system, and the like.

The sensing system 1020 may include several sensors for sensing information of the environment surrounding the vehicle 1000. For example, the sensing system 1020 may include a global positioning system (which may be a GPS system, a beidou system, or other positioning system), an inertial measurement unit (inertial measurement unit, IMU), a lidar, millimeter wave radar, an ultrasonic radar, and a camera device.

Decision control system 1030 may include a computing system, a vehicle controller, a steering system, a throttle, and a braking system.

The drive system 1040 may include components that provide powered movement of the vehicle 1000. In one embodiment, the drive system 1040 may include an engine, an energy source, a transmission, and wheels. The engine may be one or a combination of an internal combustion engine, an electric motor, an air compression engine. The engine is capable of converting energy provided by the energy source into mechanical energy.

Some or all of the functions of the vehicle 1000 are controlled by the computing platform 1050. The computing platform 1050 may include at least one processor 1051 and memory 1052, the processor 1051 may execute instructions 1053 stored in the memory 1052.

Processor 1051 may be any conventional processor, such as a commercially available CPU. The processor may also include, for example, an image processor (Graphic Process Unit, GPU), a field programmable gate array (Field Programmable GATE ARRAY, FPGA), a System On Chip (SOC), an Application SPECIFIC INTEGRATED Circuit (ASIC), or a combination thereof.

Memory 1052 may be implemented by any type of volatile or nonvolatile memory device or combination thereof, such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disk.

In addition to instructions 1053, memory 1052 may store data such as road maps, route information, vehicle position, direction, speed, and the like. The data stored by memory 1052 may be used by computing platform 1050.

In an embodiment of the present disclosure, the processor 1051 may execute instructions 1053 to perform all or part of the steps of the lane line processing method described above.

In an exemplary embodiment, a non-transitory computer readable storage medium is also provided, such as a memory 1052, including instructions executable by the processor 1051 to perform the lane line processing method described above. For example, the non-transitory computer readable storage medium may be ROM, random Access Memory (RAM), CD-ROM, magnetic tape, floppy disk, optical data storage device, etc.

In another exemplary embodiment, a computer program product is also provided, which comprises a computer program executable by a programmable apparatus, the computer program having code portions for performing the lane line processing method described above when being executed by the programmable apparatus.

Those of skill in the art will further appreciate that the various illustrative logical blocks (illustrative logical block) and steps (steps) described in connection with the embodiments of the application may be implemented by electronic hardware, computer software, or combinations of both. Whether such functionality is implemented as hardware or software depends upon the particular application and design requirements of the overall system. Those skilled in the art may implement the described functionality in varying ways for each particular application, but such implementation is not to be understood as beyond the scope of the embodiments of the present application.

It is to be understood that the present disclosure is not limited to the precise arrangements and instrumentalities shown in the drawings, and that various modifications and changes may be effected without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Although terms such as "first," "second," and "third" may be used herein to describe various elements, components, regions, layers or sections, these elements, components, regions, layers or sections are not limited by these terms. Rather, these terms are only used to distinguish one component, part, region, layer or section from another component, part, region, layer or section. Thus, a first component, part, region, layer or section discussed in examples described herein could also be termed a second component, part, region, layer or section without departing from the teachings of the examples. In addition, the terms "first," "second," are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In the description herein, the meaning of "plurality" means at least two, e.g., two, three, etc., unless specifically defined otherwise.

Claims

1. A lane line processing method, characterized by comprising:

2. The method of claim 1, wherein the at least two lane lines comprise a first lane line and a second lane line acquired in two different ways, the target lane line comprising a first target lane line and a second target lane line; the removing the target lane line from the at least two lane lines to obtain at least two lane lines to be matched includes:

3. The method of claim 2, wherein the removing the first target lane line from the first lane line to obtain a first lane line to be matched comprises:

4. The method of claim 2, wherein the removing the second target lane line from the second lane line to obtain a second lane line to be matched comprises:

5. The method of claim 1, wherein the matching the at least two lane lines to be matched to obtain a matched lane line comprises:

And matching at least two lane line segments to obtain matched lane lines.

6. The method of claim 5, wherein the reserving lane line segments on the at least two lane lines that are less than a preset distance from the device comprises:

7. The method according to claim 1, wherein the method further comprises:

8. The method of claim 1, wherein the lane lines to be matched comprise at least one first lane line to be matched and at least one second lane line to be matched; the step of matching the at least two lane lines to be matched to obtain matched lane lines comprises the following steps:

And obtaining the matched lane lines after matching according to the weights.

9. The method according to any one of claims 1 to 8, wherein the at least two lane lines include two lane lines, one of the two lane lines is a lane line acquired by the image acquisition device, and the other lane line is a lane line acquired from a map.

10. A lane line processing apparatus, comprising:

11. A vehicle, characterized by comprising:

A processor;

A memory for storing processor-executable instructions;

wherein the processor is configured to:

the method of any one of claims 1 to 9.

12. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 9.

13. A computer program product comprising a computer program which, when executed by a processor, implements the steps of the method of any one of claims 1 to 9.