Lane line change detection method, device and computer readable storage medium

By matching the initial point of the lane line point set and the target point and its neighboring points, the similarity of lane line lines is calculated, and the problem of large consumption of lane line change detection resources in the prior art is solved, and efficient lane line change detection is achieved.

CN114758321BActive Publication Date: 2024-11-26ZHIDAO NETWORK TECH (BEIJING) CO LTD
View PDF 3 Cites 0 Cited by

Patent Information

Application Number
CN202210451992.4
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-04-27
Publication Date
2024-11-26
Estimated Expiration
2042-04-27

AI Technical Summary

Technical Problem

When detecting changes in lane lines in the prior art, mechanical comparison sampling points lead to high computing resources consumption and high complexity, making it difficult to efficiently detect changes in lane lines.

Method used

By obtaining the current actual lane line and target lane line of the target road, discrete it into a point set, and match the current point and the target point from the initial point, including the points to be matched and their neighborhood points, calculate the similarity to judge the change of the lane line from the initial point. , reduce the number of comparisons and calculation complexity.

Benefits of technology

This reduces the computing resource consumption during detection, improves the computing speed, and achieves more efficient lane line change detection.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114758321B_ABST
    Figure CN114758321B_ABST
Patent Text Reader

Abstract

The present application relates to a lane line change detection method, device and computer-readable storage medium. The method includes: obtaining the current actual lane line and the target lane line of the target road; discretizing the current actual lane line and the target lane line to obtain a first point set corresponding to the current actual lane line and a second point set corresponding to the target lane line respectively; starting from the initial point of the first point set, matching the current point in the first point set with the target point in the second point set; if the current point in the first point set matches the target point in the second point set successfully, then calculating the similarity between the current actual lane line and the target lane line according to the target point in the first point set that matches successfully with the second point set; if the difference is greater than a preset threshold, it is determined that the lane line of the target road corresponding to the target lane line has changed, wherein the difference is the value obtained by subtracting the similarity between the current actual lane line and the target lane line from 1. The technical solution of the present application can reduce the consumption of computing resources during detection.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of autonomous driving, and in particular to a method, device and computer-readable storage medium for detecting lane line changes. Background Art

[0002] With the development of technology and the reduction of costs, driverless cars have gradually entered the practical stage, and driverless cars are becoming increasingly popular in people's travel activities. The lane lines in the map database provide a certain guarantee for the safe driving of people and vehicles. However, due to the changes in the actual lane lines, the lane lines in the map database must also be updated synchronously, which involves the detection method of lane line changes. In the related technology, the current actual lane line and the target lane line, that is, the lane line where the target road in the map database matches the current lane line, are sampled, and then the sampling points on the two lane lines are compared. If the number of matching points on the two lane lines exceeds the preset threshold, the lane line has not changed, otherwise, the lane line has changed. Although the above-mentioned related technologies can detect changes in lane lines, mechanical comparison of sampling points will result in greater resource consumption. Summary of the invention

[0003] In order to solve or partially solve the problems existing in the related art, the present application provides a lane line change detection method, device and computer-readable storage medium, which can reduce the consumption of computing resources during detection.

[0004] The first aspect of the present application provides a method for detecting lane line changes, comprising:

[0005] Acquire a current actual lane line and a target lane line of a target road, wherein the target lane line is a lane line of the target road in a map database that matches the current lane line;

[0006] Discretizing the current actual lane line and the target lane line to obtain a first point set corresponding to the current actual lane line and a second point set corresponding to the target lane line, respectively;

[0007] Starting from the initial point of the first point set, matching the current point in the first point set with the target point in the second point set, the target point in the second point set including the to-be-matched point in the second point set and the point on the target lane line corresponding to the neighborhood of the to-be-matched point, the to-be-matched point being the point in the second point set with the same abscissa as that in the first point set when the discretization is performed;

[0008] If the current point in the first point set matches the target point in the second point set successfully, then calculating the similarity between the current actual lane line and the target lane line according to the target points in the first point set that match successfully with the second point set;

[0009] If the difference is greater than a preset threshold, it is determined that the lane line of the target road corresponding to the target lane line has changed, and the difference is a value obtained by subtracting 1 from the similarity between the current actual lane line and the target lane line.

[0010] A second aspect of the present application provides a lane line change detection device, comprising:

[0011] An acquisition module, used to acquire a current actual lane line and a target lane line of a target road, wherein the target lane line is a lane line of the target road that matches the current lane line in a map database;

[0012] A discretization module, used for discretizing the current actual lane line and the target lane line, and obtaining a first point set corresponding to the current actual lane line and a second point set corresponding to the target lane line respectively;

[0013] a matching module, configured to match a current point in the first point set with a target point in the second point set starting from an initial point of the first point set, wherein the target point in the second point set includes a point to be matched in the second point set and a point on the target lane line corresponding to a neighborhood of the point to be matched, and the point to be matched is a point in the second point set with the same horizontal coordinate as that in the first point set when the discretization is performed;

[0014] a calculation module, configured to calculate the similarity between the current actual lane line and the target lane line according to the target points in the first point set that successfully match the target points in the second point set, if the current point in the first point set matches the target point in the second point set successfully;

[0015] A determination module is used to determine that a lane line of the target road corresponding to a target lane line has changed if the difference is greater than a preset threshold, and the difference is a value obtained by subtracting 1 from the similarity between the current actual lane line and the target lane line.

[0016] A third aspect of the present application provides an electronic device, including:

[0017] Processor; and

[0018] The memory stores executable codes thereon, and when the executable codes are executed by the processor, the processor is caused to execute the method as described above.

[0019] A fourth aspect of the present application provides a computer-readable storage medium having executable code stored thereon. When the executable code is executed by a processor of an electronic device, the processor is caused to execute the method as described above.

[0020] The technical solution provided by the present application may include the following beneficial effects: unlike the related art, which requires mechanical comparison of all sampling points on the two lane lines when detecting lane line changes, in the embodiment of the present application, the comparison object of the current point in the first point set is only the point to be matched in the second point set and the point on the target lane line corresponding to the neighborhood of the point to be matched. The number of comparisons is much smaller than that of the related art, and the calculation complexity is also much smaller than that of the related art. Therefore, the technical solution of the present application is superior to the related art in calculation speed, and the consumption of computing resources is also much smaller than that of the related art.

[0021] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The above and other objects, features and advantages of the present application will become more apparent by describing in more detail exemplary embodiments of the present application in conjunction with the accompanying drawings, wherein the same reference numerals generally represent the same components in the exemplary embodiments of the present application.

[0023] Figure 1 is a flow chart of a method for detecting lane line changes provided in an embodiment of the present application;

[0024] Figure 2 The present application provides a schematic diagram of matching the current actual lane line of the target road acquired in real time with the lane line of the map database to obtain the target lane line;

[0025] Figure 3 It is a schematic diagram provided by an embodiment of the present application of taking the current actual lane line of the target road as a reference curve and dynamically adjusting the sampling interval according to the curvature of the reference curve to sample the current actual lane line and the target lane line;

[0026] Figure 4a It is a schematic diagram provided by an embodiment of the present application of matching a current point in the first point set with a target point in the second point set starting from an initial point in the first point set;

[0027] Figure 4b is a schematic diagram of matching a current point in the first point set with a target point in the second point set, starting from an initial point in the first point set, provided by another embodiment of the present application;

[0028] Figure 4c It is the heading angle of the current point in the first point set at the current actual lane line or the heading angle of the target point in the second point set at the target lane line provided in the embodiment of the present application;

[0029] Figure 5 is a schematic diagram of the structure of a lane line change detection device provided in an embodiment of the present application;

[0030] Figure 6 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0031] The embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although the embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided to make the present application more thorough and complete, and to fully convey the scope of the present application to those skilled in the art.

[0032] The terms used in this application are for the purpose of describing specific embodiments only and are not intended to limit this application. The singular forms of "a", "said" and "the" used in this application and the appended claims are also intended to include plural forms unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more associated listed items.

[0033] It should be understood that although the terms "first", "second", "third", etc. may be used in this application to describe various information, this information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of this application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of this application, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined.

[0034] Unmanned driving has gradually entered the practical stage, and unmanned vehicles are becoming increasingly popular in people's travel activities. The lane lines in the map database provide a certain guarantee for the safe driving of people and vehicles. Due to the changes in the actual lane lines, the lane lines in the map database must also be updated synchronously, which involves the detection method of lane line changes. In the related technology, the current actual lane line and the target lane line, that is, the lane line where the target road in the map database matches the current lane line, are sampled, and then the sampling points on the two lane lines are compared. If the number of matching points on the two lane lines exceeds the preset threshold, the lane line has not changed, otherwise, the lane line has changed. Although the above-mentioned related technology can detect the change of the lane line, however, mechanically comparing the sampling points will bring about a large resource consumption. Specifically, if M points are sampled for the current actual lane line, and N points are sampled for the target lane line (that is, the lane line where the target road in the map database matches the current lane line), the complexity of the above-mentioned related technology is O(M*N), and the consumption of computing resources is large.

[0035] In response to the above problems, an embodiment of the present application provides a method for detecting lane line changes, which can reduce the consumption of computing resources during detection.

[0036] The technical solution of the embodiments of the present application is described in detail below with reference to the accompanying drawings.

[0037] See also Figure 1 , is a flow chart of a lane line change detection method according to an embodiment of the present application, which mainly includes steps S101 to S105, as described below:

[0038] Step S101: Acquire the current actual lane line and the target lane line of the target road, wherein the target lane line is the lane line of the target road in the map database that matches the current lane line.

[0039] Here, the target road refers to a road where it is necessary to detect whether the lane line has changed. The target lane line is the lane line that matches the current lane line of the target road in the map database, and the map database is a database that stores lane line information of various roads. As an embodiment of the present application, obtaining the current actual lane line and the target lane line of the target road can be: collecting the lane line data of the target road in real time to obtain the current actual lane line of the target road; matching the current actual lane line of the target road with the lane line in the map database to obtain the target lane line. In the above embodiment, real-time collection of lane line data of the target road can be carried out by mounting a device for collecting lane line data on a vehicle, the vehicle travels on the target road, and the device collects lane line data of the target road in real time, thereby obtaining the current actual lane line of the target road.

[0040] As mentioned above, since the map database is a database that stores lane line information of various roads, when the lane line data of the target road is collected in real time, the current actual lane line of the target road collected in real time can be matched with the lane line of the map database to obtain the target lane line. The specific method may be: positioning the vehicle to obtain the polygonal area to which the vehicle's driving trajectory belongs; traversing the map database with the polygonal area as a comparison object to obtain the target area; traversing the lane line data of the target area with the vehicle's driving trajectory in the polygonal area as a comparison object to obtain the target lane line, wherein the vehicle here is the vehicle equipped with a device for collecting lane line data in real time mentioned in the aforementioned embodiment. For example, if the polygonal area to which the vehicle's driving trajectory belongs is a rectangular area, such as Figure 2As shown, when a vehicle equipped with a device for collecting lane line data in real time is driving on a target road, the vehicle can be positioned by a positioning module such as a global positioning system (GPS) to obtain the rectangular area to which the vehicle's driving trajectory belongs. Since the rectangular area to which the vehicle's driving trajectory belongs has been positioned, the map database is traversed with the rectangular area as a comparison object to obtain a target area that matches the rectangular area, that is, an area in the map database with the same position and / or range as the rectangular area. Finally, the lane line data of the target area is traversed with the vehicle's driving trajectory in the rectangular area as a comparison object, which is equivalent to matching the lane lines in the map database in a smaller range. It should be noted that, in the embodiment of the present application, traversing the map database with the rectangular area as the comparison object is obviously a larger-scale comparison or traversal. Compared with traversing the map database with the rectangular area as the comparison object, traversing the lane line data of the target area with the driving trajectory of the vehicle in the rectangular area as the comparison object is a smaller-scale comparison or traversal. The purpose of this smaller-scale comparison or traversal is only to find the lane line in the map database that is roughly the same as the current actual lane line, or, only to find the lane line in the map database that is the same as the current actual lane line as a whole. As for the more microscopic comparison, it is a task to be completed in subsequent operations. For example, for Figure 2 For example, the target lane line in the map database that matches the current actual lane line should be lane line 1 rather than lane line 2. The more subtle differences between the current actual lane line and lane line 1 are the tasks to be completed in subsequent operations.

[0041] Step S102: discretizing the current actual lane line and the target lane line of the target road to obtain a first point set corresponding to the current actual lane line and a second point set corresponding to the target lane line, respectively.

[0042] As an embodiment of the present application, the current actual lane line and the target lane line of the discretized target road are obtained by uniformly sampling the current actual lane line and the target lane line at a preset sampling interval to obtain the first point set corresponding to the current actual lane line and the second point set corresponding to the target lane line. Compared with the subsequent embodiments that sample the current actual lane line and the target lane line of the target road at a variable sampling interval, the current actual lane line and the target lane line of the target road are uniformly sampled at a preset sampling interval (or a fixed sampling interval) here, and the sampling method is single, and the corresponding algorithm will be relatively simple. As for the size of the preset sampling interval, it can be set according to actual needs. In principle, if the data accuracy of the electronic map is required to be high, a smaller sampling interval needs to be set, and vice versa, a smaller sampling interval can be set.

[0043] As another embodiment of the present application, the current actual lane line and the target lane line of the discretized target road are respectively obtained to obtain the first point set corresponding to the current actual lane line and the second point set corresponding to the target lane line. It can also be: taking the current actual lane line or the target lane line as a reference curve, determining the curvature of the reference curve; dynamically adjusting the sampling interval according to the curvature of the reference curve to sample the current actual lane line and the target lane line of the target road, respectively obtaining the first point set corresponding to the current actual lane line and the second point set corresponding to the target lane line. Unlike the above-mentioned embodiment, which uses a preset sampling interval (or a fixed sampling interval) to uniformly sample the current actual lane line and the target lane line of the target road, this embodiment is equivalent to dynamic interval sampling. Sampling the current actual lane line and the target lane line with a dynamic sampling interval or different sampling intervals is based on the fact that, if the curvature of the curve is greater, that is, the greater the degree of curvature of the curve, a larger sampling interval is used to sample the curve and then compare it, and it may be obtained that the two curves are actually the same, but the two curves are not the same. Therefore, in order to prevent the occurrence of matching errors, the embodiment of the present application uses a dynamically adjusted sampling interval to sample the current actual lane line and the target lane line. In the above embodiment, the curvature of the reference curve can be determined by cutting the reference curve into segments to obtain at least two curve segments; and determining the curvature of the reference curve according to the degree of curve change between adjacent curve segments in the at least two curve segments. Specifically, the connection points between adjacent curve segments can be determined; the tangent angles of the adjacent curve segments at the connection points are calculated; if the difference between the tangent angles of the adjacent curve segments at the connection points is larger, the curvature of the two adjacent curve segments is larger, and vice versa, the curvature of the two adjacent curve segments is smaller. The difference between the tangent angles of the curve segments at the connection points is calculated for all the curve segments obtained by cutting the reference curve into segments in the above manner, thereby determining the curvature of each curve segment on the reference curve.

[0044] After determining the curvature of the reference curve in the above manner, the current actual lane line and the target lane line of the target road are sampled by dynamically adjusting the sampling interval according to the curvature of the reference curve, and respectively obtaining a first point set corresponding to the current actual lane line and a second point set corresponding to the target lane line. Specifically, it can be: comparing the curvature of any section of the reference curve with a preset curvature threshold; if the curvature of any section of the curve is greater than the preset curvature threshold, the current actual lane line and the target lane line of the target road are sampled at the first preset sampling interval; conversely, if the curvature of any section of the curve is not greater than the preset curvature threshold, the current actual lane line and the target lane line of the target road are sampled at the second preset sampling interval, where the first preset sampling interval is smaller than the second preset sampling interval. Figure 3As shown (black dots represent sampling points), it is an example of taking the current actual lane line of the target road as a reference curve and dynamically adjusting the sampling interval according to the curvature of the reference curve to sample the current actual lane line and the target lane line.

[0045] Step S103: Starting from the initial point of the first point set, the current point in the first point set is matched with the target point in the second point set, wherein the target point in the second point set includes the point to be matched in the second point set and the point on the target lane line corresponding to the neighborhood of the point to be matched, and the point to be matched is the point in the second point set with the same horizontal coordinate as that in the first point set when discretization is performed.

[0046] Considering that the current actual lane line and the target lane line of the target road are two-dimensional images, when matching the current point in the first point set with the target point in the second point set, the current actual lane line and the target lane line of the target road can be placed in a two-dimensional coordinate system for investigation. When the current actual lane line and the target lane line of the target road are placed in a two-dimensional coordinate system, the points to be matched in the second point set obtained after discretization in step S102 are the points in the second point set with the same horizontal coordinates as those in the first point set when discretization is performed. As an embodiment of the present application, starting from the initial point of the first point set, matching the current point in the first point set with the target point in the second point set can be: calculating the distance between the current point in the first point set and the target point in the second point set; calculating the heading angle of the current point in the first point set at the current actual lane line and the heading angle of the target point in the second point set at the target lane line; if the distance between the current point in the first point set and the target point in the second point set is less than a preset distance threshold, and the absolute difference between the heading angle of the current point in the first point set at the current actual lane line and the heading angle of the target point in the second point set at the target lane line is less than a preset angle difference, then it is determined that the current point in the first point set and the target point in the second point set are successfully matched, wherein the heading angle of the current point in the first point set at the current actual lane line or the heading angle of the target point in the second point set at the target lane line is defined as an angle formed by a sampling point and a line connecting two adjacent sampling points before and after the sampling point on the curve, with the sampling point as the vertex, such as Figure 4c As shown, assuming that the current point in the first point set is point P, and on the current actual lane line, the two adjacent sampling points before and after point P are point Q and point R respectively, then the heading angle of point P is ∠QPR.

[0047] like Figure 4aAs shown, it is a schematic diagram of matching the current point in the first point set with the target point in the second point set provided by an embodiment of the present application. Assuming that P in the figure is the current point in the first point set, P′ is the point to be matched in the second point set, and ΔF1 is the neighborhood corresponding to point P′ on the target lane line. If the distance between point P and other points in the neighborhood of point P′ or point P′ (assuming point P′1, not shown in the figure) is less than a preset distance threshold, and the absolute difference between the heading angle of point P on the current actual lane line and the heading angle of point P′ or point P′1 on the target lane line is less than the preset angle difference, it is determined that point P is successfully matched with point P′ or point P′1. After point P is successfully matched with point P′ or point P′1, it can move to point Q in the first point set, and match point Q with the target point in the second point set, i.e., the point to be matched in the second point set, i.e., point Q′, or other points in the neighborhood ΔF2 corresponding to point Q′ on the target lane line (assuming it is point Q′1, not shown in the figure). The specific method is the same as the method for matching point P with point P′ or point P′1, and the technical scheme for matching point P with point P′ or point P′1 in the aforementioned embodiment can be referred to; in the aforementioned embodiment, point P and point P′, point P and point P′1, point Q and point Q′, or point Q and point Q′1 respectively constitute a point pair. If the current actual lane line and the target lane line of the target road are both discretized into N sampling points, then according to the matching method of the prior art, i.e., each time one sampling point of the current actual lane line navigation is matched with the N sampling points on the target lane line, the computational complexity is O(N*N), and from the aforementioned embodiment, Figure 4a It can be seen from the example matching method that if the method provided in the embodiment of the present application is followed, because each time only the current point in the first point set needs to be matched with the target point in the second point set (the point to be matched in the second point set and the point on the target lane line corresponding to the neighborhood of the point to be matched) , the minimum computational complexity is O(N). The significant reduction in computational complexity not only means an increase in the computational speed, but also means a significant reduction in the consumption of computing resources.

[0048] In the above embodiment, if the current point in the first point set does not match the target point in the second point set successfully, then the current point in the first point set can be matched with a predetermined number of target points after the point in the second point set that does not match the current point successfully. If the current point in the first point set matches any point in the other predetermined number of target points in the second point set (referred to as K points), then the point after the current point in the first point set is matched with the K points; if the current point in the first point set does not match the other predetermined number of target points in the second point set successfully, then the point after the current point in the first point set can be matched with a predetermined number of target points in the second point set. Figure 4bAs shown, assuming that point P3 in the first point set is not successfully matched with point P3' in the second point set and the points in the neighborhood ΔF3 of point P3', then an attempt can be made to match point P3 with a predetermined number of points after point P3' in the second point set, for example, 6 target points, namely, point P4', point P5', point P6', point P7', point P8', point P9' and the points in their neighborhood. If point P3 in the first point set is successfully matched with point P4', point P5', point P6', point P7', point P8', point P9' and any point in their neighborhood, for example, point P5' in the second point set, then a point after the current point in the first point set, namely point P4, is matched with point P5' and the points in the neighborhood ΔF5 of point P5' (the neighborhood ΔF5 of point P5' is not shown in the figure). The specific matching method is the same as the matching method of point P with point P' or other points in the neighborhood of point P' in the aforementioned embodiment. Please refer to the relevant description of the aforementioned embodiment, which will not be repeated here. If point P3 in the first point set is not successfully matched with points P4', P5', P6', P7', P8', P9' and points in their neighborhood in the second point set, then you can try to match point P4 in the first point set with any point P4', P5', P6', P7', P8', P9' and any point in their neighborhood in the second point set. The specific matching method is the same as the matching method of point P with point P' or other points in the neighborhood of point P' in the aforementioned embodiment. Please refer to the relevant description of the aforementioned embodiment, which will not be repeated here.

[0049] It should be noted that, in the above embodiment, when detecting whether the lane line changes, the geometric attributes of the current actual lane line and the target lane line of the target road are mainly considered, and the attributes of the actual lane line are various, and the attribute changes of these lane lines also mean that the lane line changes. Therefore, the method of the above embodiment may also include: obtaining the attribute information of the current actual lane line and the target lane line; determining the attribute change information of the lane line of the target road according to the attribute information of the current actual lane line and the attribute information of the target lane line, wherein the attribute information of the current actual lane line or the target lane line includes at least one of the following attributes: color attribute, virtual attribute and thickness attribute. As for the specific method of obtaining the attribute information of the current actual lane line and the target lane line, it can be obtained by using various image sensors, such as monocular cameras, binocular cameras, depth cameras or laser radars, and determining the attribute change information of the lane line of the target road according to the attribute information of the current actual lane line and the attribute information of the target lane line can be specifically after collecting the attribute information of the current actual lane line and the attribute information of the target lane line, extracting feature information in the image, and determining whether the attribute of the lane line of the target road changes according to the target recognition algorithm.

[0050] Step S104: If the current point in the first point set matches the target point in the second point set successfully, then the similarity between the current actual lane line and the target lane line is calculated based on the target point in the first point set that matches the target point in the second point set successfully.

[0051] Specifically, if the current actual lane line and the target lane line of the target road are uniformly sampled at a preset sampling interval when discretizing the current actual lane line and the target lane line, then the point where the current point in the first point set matches the target point in the second point set can be simply regarded as a successfully matched point pair, and the percentage of the number of points in the first point set or the second point set is calculated, and the percentage is used as the similarity between the current actual lane line and the target lane line of the target road. If the current actual lane line and the target lane line of the target road are sampled by dynamically adjusting the sampling interval according to the curvature of the reference curve (the current actual lane line or the target lane line of the target road) when discretizing the current actual lane line and the target lane line, then the point where the current point in the first point set matches the target point in the second point set can be regarded as a successfully matched point pair, and the percentage of the length of the arc between the points in the first point set corresponding to the points in the first point set relative to the length of the target road is calculated, or the percentage of the length of the arc between the points in the second point set corresponding to the points in the second point set relative to the length of the target road is calculated, and the percentage is used as the similarity between the current actual lane line and the target lane line of the target road.

[0052] Step S105: If the difference is greater than a preset threshold, it is determined that the lane line of the target road corresponding to the target lane line has changed, wherein the difference is 1 minus the value obtained by subtracting the similarity between the current actual lane line and the target lane line.

[0053] For example, assuming that the similarity between the current actual lane line and the target lane line is S according to the calculation method of the above embodiment, the difference (denoted as ΔS) obtained by 1-S is compared with the preset threshold. If ΔS is greater than the preset threshold, it means that there are too many sampling points where the current actual lane line of the target road and the target lane line cannot match, so it is determined that the lane line of the target road corresponding to the target lane line has changed.

[0054] From the above Figure 1 It can be seen from the example lane line change detection method that, unlike the related technology, when detecting lane line changes, it is necessary to mechanically compare all the sampling points on the two lane lines. In the embodiment of the present application, the comparison object of the current point in the first point set is only the point to be matched in the second point set and the point in the target lane line corresponding to the neighborhood of the point to be matched. The number of comparisons is much smaller than that of the related technology, and the calculation complexity is also much smaller than that of the related technology. Therefore, the technical solution of the present application is superior to the related technology in terms of calculation speed, and the consumption of computing resources is also much smaller than that of the related technology.

[0055] Corresponding to the aforementioned application function implementation method embodiment, the present application also provides a lane line change detection device, electronic device and corresponding embodiments.

[0056] See also Figure 5 , is a schematic diagram of the structure of a lane line change detection device shown in an embodiment of the present application. For ease of description, only the parts related to the embodiment of the present application are shown. Figure 5 The exemplary lane line change detection device mainly includes an acquisition module 501, a discretization module 502, a matching module 503, a calculation module 504 and a determination module 505, wherein:

[0057] An acquisition module 501 is used to acquire a current actual lane line and a target lane line of a target road, wherein the target lane line is a lane line of the target road in a map database that matches the current lane line;

[0058] A discretization module 502 is used to discretize the current actual lane line and the target lane line of the target road, and obtain a first point set corresponding to the current actual lane line of the target road and a second point set corresponding to the target lane line respectively;

[0059] A matching module 503 is used to match the current point in the first point set with the target point in the second point set starting from the initial point of the first point set, wherein the target point in the second point set includes the point to be matched in the second point set and the point on the target lane line corresponding to the neighborhood of the point to be matched, and the point to be matched is the point in the second point set with the same horizontal coordinate as that in the first point set when discretization is performed;

[0060] A calculation module 504 is used to calculate the similarity between the current actual lane line and the target lane line according to the target point that successfully matches between the first point set and the second point set if the current point in the first point set and the target point in the second point set are matched successfully;

[0061] The determination module 505 is used to determine that the lane line of the target road corresponding to the target lane line has changed if the difference is greater than a preset threshold, wherein the difference is a value obtained by subtracting 1 from the similarity between the current actual lane line and the target lane line.

[0062] Optionally, Figure 5 The exemplary acquisition module 501 may include a collection unit and a matching unit, wherein:

[0063] A collection unit, used to collect lane line data of the target road in real time to obtain the current actual lane line of the target road;

[0064] The matching unit is used to match the current actual lane line of the target road with the lane line in the map database to obtain the target lane line.

[0065] Optionally, the matching unit in the above example may include a positioning unit, a first traversal unit, and a second traversal unit, wherein:

[0066] A positioning unit, used to locate the vehicle and obtain a polygonal area to which the vehicle's driving track belongs, wherein the vehicle is equipped with a device for collecting lane line data in real time;

[0067] The first traversal unit is used to traverse the map database by taking the polygonal area to which the vehicle's driving track belongs as a comparison object to obtain a target area matching the polygonal area;

[0068] The second traversal unit is used to traverse the lane line data of the target area by taking the driving track of the vehicle in the polygonal area to which the driving track of the vehicle belongs as a comparison object to obtain the target lane line.

[0069] Optionally, Figure 5 The example discretization module 502 may include a first sampling unit for uniformly sampling the current actual lane line and the target lane line of the target road at a preset sampling interval to obtain a first point set corresponding to the current actual lane line and a second point set corresponding to the target lane line, respectively.

[0070] Optionally, Figure 5 The exemplary discretization module 502 may include a first determination unit and a second sampling unit, wherein:

[0071] A first determining unit, configured to determine the curvature of a reference curve by taking a current actual lane line or a target lane line of a target road as a reference curve;

[0072] The second sampling unit is used to dynamically adjust the sampling interval according to the curvature of the reference curve to sample the current actual lane line and the target lane line, and obtain a first point set corresponding to the current actual lane line and a second point set corresponding to the target lane line respectively.

[0073] Optionally, the first determination unit in the above example may include a segmentation unit and a curvature determination unit, wherein:

[0074] A segmentation unit, used for cutting the reference curve into segments to obtain at least two curve segments;

[0075] The curvature determination unit is used to determine the curvature of the reference curve according to the degree of curve change between adjacent curve segments in at least two curve segments.

[0076] Optionally, the second sampling unit in the above example may include a comparison unit and a dynamic sampling unit, wherein:

[0077] A comparison unit, used for comparing the curvature of any section of the reference curve with a preset curvature threshold;

[0078] A dynamic sampling unit is used to sample the current actual lane line and the target lane line of the target road at a first preset sampling interval if the curvature of any section of the reference curve is greater than a preset curvature threshold; otherwise, the current actual lane line and the target lane line of the target road are sampled at a second preset sampling interval, wherein the first preset sampling interval is smaller than the second preset sampling interval.

[0079] Optionally, Figure 5 The exemplary matching module 503 may include a first calculation unit, a second calculation unit, and a second determination unit, wherein:

[0080] A first calculation unit, used to calculate the distance between the current point in the first point set and the target point in the second point set;

[0081] A second calculation unit is used to calculate the heading angle of the current point in the first point set on the current actual lane line and the heading angle of the target point in the second point set on the target lane line;

[0082] The second determination unit is used to determine that the current point in the first point set and the target point in the second point set are successfully matched if the distance between the current point in the first point set and the target point in the second point set is less than a preset distance threshold, and the absolute difference between the heading angle of the current point in the first point set on the current actual lane line and the heading angle of the target point in the second point set on the target lane line is less than a preset angle difference.

[0083] Optionally, Figure 5 The exemplary device may further include an attribute acquisition module and an attribute change acquisition module, wherein:

[0084] An attribute acquisition module is used to obtain the attribute information of the current actual lane line and the target lane line of the target road;

[0085] The attribute change acquisition module is used to determine the attribute change information of the lane line of the target road according to the attribute information of the current actual lane line of the target road and the attribute information of the target lane line.

[0086] Optionally, the attribute information of the lane line in the above example includes at least one of the following attributes: color attribute, virtuality attribute and thickness attribute.

[0087] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated again here.

[0088] Figure 6 It is a schematic diagram of the structure of an electronic device shown in an embodiment of the present application.

[0089] See also Figure 6 , the electronic device 600 includes a memory 610 and a processor 620 .

[0090] The processor 620 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc.

[0091] The memory 610 may include various types of storage units, such as system memory, read-only memory (ROM), and permanent storage devices. Among them, ROM can store static data or instructions required by the processor 620 or other modules of the computer. The permanent storage device may be a readable and writable storage device. The permanent storage device may be a non-volatile storage device that does not lose the stored instructions and data even after the computer is powered off. In some embodiments, the permanent storage device uses a large-capacity storage device (such as a magnetic or optical disk, flash memory) as a permanent storage device. In some other embodiments, the permanent storage device may be a removable storage device (such as a floppy disk, optical drive). The system memory may be a readable and writable storage device or a volatile readable and writable storage device, such as a dynamic random access memory. The system memory may store some or all instructions and data required by the processor at run time. In addition, the memory 610 may include any combination of computer-readable storage media, including various types of semiconductor storage chips (such as DRAM, SRAM, SDRAM, flash memory, programmable read-only memory), and disks and / or optical disks may also be used. In some embodiments, the memory 610 may include a readable and / or writable removable storage device, such as a laser disc (CD), a read-only digital versatile disc (such as a DVD-ROM, a double-layer DVD-ROM), a read-only Blu-ray disc, an ultra-density optical disc, a flash memory card (such as an SD card, a mini SD card, a Micro-SD card, etc.), a magnetic floppy disk, etc. The computer-readable storage medium does not include carrier waves and transient electronic signals transmitted wirelessly or wired.

[0092] The memory 610 stores executable codes, and when the executable codes are processed by the processor 620 , the processor 620 can execute part or all of the above-mentioned methods.

[0093] In addition, the method according to the present application may also be implemented as a computer program or a computer program product, which includes computer program code instructions for executing some or all of the steps in the above method of the present application.

[0094] Alternatively, the present application can also be implemented as a computer-readable storage medium (or non-transitory machine-readable storage medium or machine-readable storage medium) on which executable code (or computer program or computer instruction code) is stored. When the executable code (or computer program or computer instruction code) is executed by a processor of an electronic device (or server, etc.), the processor executes part or all of the steps of the above-mentioned method according to the present application.

[0095] The embodiments of the present application have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and changes will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A method for detecting lane line changes, characterized in that: The method comprises: Acquire the current actual lane line and the target lane line of the target road, wherein the target lane line is the lane line of the target road in the map database that matches the current lane line; wherein the method comprises: collecting the lane line data of the target road in real time to obtain the current actual lane line of the target road; positioning the vehicle to obtain the polygonal area to which the driving track of the vehicle belongs, wherein the vehicle is a vehicle equipped with a device for collecting the lane line data in real time; traversing the map database with the polygonal area as a comparison object to obtain the target area that matches the polygonal area; traversing the lane line data of the target area with the driving track of the vehicle in the polygonal area as a comparison object to obtain the target lane line; Discretizing the current actual lane line and the target lane line to obtain a first point set corresponding to the current actual lane line and a second point set corresponding to the target lane line, respectively; Starting from the initial point of the first point set, matching the current point in the first point set with the target point in the second point set, the target point in the second point set including the to-be-matched point in the second point set and the point on the target lane line corresponding to the neighborhood of the to-be-matched point, the to-be-matched point being the point in the second point set with the same abscissa as that in the first point set when the discretization is performed; If the current point in the first point set matches the target point in the second point set successfully, then calculating the similarity between the current actual lane line and the target lane line according to the target points in the first point set that match successfully with the second point set; If the difference is greater than a preset threshold, it is determined that the lane line of the target road corresponding to the target lane line has changed, and the difference is a value obtained by subtracting 1 from the similarity between the current actual lane line and the target lane line.

2. The method for detecting lane line changes according to claim 1, characterized in that: The discretizing the current actual lane line and the target lane line to obtain a first point set corresponding to the current actual lane line and a second point set corresponding to the target lane line, respectively, includes: The current actual lane line and the target lane line are uniformly sampled at a preset sampling interval to obtain a first point set corresponding to the current actual lane line and a second point set corresponding to the target lane line, respectively.

3. The method for detecting lane line changes according to claim 1, characterized in that: The discretizing the current actual lane line and the target lane line to obtain a first point set corresponding to the current actual lane line and a second point set corresponding to the target lane line, respectively, includes: Taking the current actual lane line or the target lane line as a reference curve, determining the curvature of the reference curve; The current actual lane line and the target lane line are sampled by dynamically adjusting the sampling interval according to the curvature of the reference curve, so as to obtain a first point set corresponding to the current actual lane line and a second point set corresponding to the target lane line respectively.

4. The method for detecting lane line changes according to claim 3, characterized in that: The determining the curvature of the reference curve comprises: Cut the reference curve into segments to obtain at least two curve segments; The curvature of the reference curve is determined according to a degree of curve change between adjacent curve segments in the at least two curve segments.

5. The method for detecting lane line changes according to claim 4, characterized in that: The dynamically adjusting the sampling interval according to the curvature of the reference curve to sample the current actual lane line and the target lane line includes: Comparing the curvature of any section of the reference curve with a preset curvature threshold; If the curvature of any section of the curve is greater than the preset curvature threshold, the current actual lane line and the target lane line are sampled at a first preset sampling interval; otherwise, the current actual lane line and the target lane line are sampled at a second preset sampling interval, and the first preset sampling interval is smaller than the second preset sampling interval.

6. The method for detecting lane line changes according to claim 1, characterized in that: The matching of the current point in the first point set with the target point in the second point set starting from the initial point of the first point set includes: Calculate the distance between the current point in the first point set and the target point in the second point set; Calculate the heading angle of the current point in the first point set at the current actual lane line and the heading angle of the target point in the second point set at the target lane line; If the distance between the current point in the first point set and the target point in the second point set is less than a preset distance threshold, and the absolute difference between the heading angle of the current point in the first point set in the current actual lane line and the heading angle of the target point in the second point set in the target lane line is less than a preset angle difference, then it is determined that the current point in the first point set and the target point in the second point set are matched successfully.

7. The method for detecting lane line changes according to any one of claims 1 to 6, characterized in that: The method further comprises: Acquire attribute information of the current actual lane line and the target lane line; According to the attribute information of the current actual lane line and the attribute information of the target lane line, attribute change information of the lane line of the target road is determined.

8. The method for detecting lane line changes according to claim 7, characterized in that: The lane line attribute information includes at least one of the following attributes: color attribute, virtuality attribute, and thickness attribute.

9. A lane line change detection device, characterized in that: The device comprises: An acquisition module is used to acquire the current actual lane line and the target lane line of the target road, wherein the target lane line is the lane line of the target road in the map database that matches the current lane line; wherein the module comprises: collecting the lane line data of the target road in real time to obtain the current actual lane line of the target road; positioning the vehicle to obtain the polygonal area to which the driving track of the vehicle belongs, wherein the vehicle is a vehicle equipped with a device for collecting the lane line data in real time; traversing the map database with the polygonal area as a comparison object to obtain the target area that matches the polygonal area; traversing the lane line data of the target area with the driving track of the vehicle in the polygonal area as a comparison object to obtain the target lane line; A discretization module, used for discretizing the current actual lane line and the target lane line, and obtaining a first point set corresponding to the current actual lane line and a second point set corresponding to the target lane line respectively; a matching module, configured to match a current point in the first point set with a target point in the second point set starting from an initial point of the first point set, wherein the target point in the second point set includes a point to be matched in the second point set and a point on the target lane line corresponding to a neighborhood of the point to be matched, and the point to be matched is a point in the second point set with the same horizontal coordinate as that in the first point set when the discretization is performed; a calculation module, configured to calculate the similarity between the current actual lane line and the target lane line according to the target points in the first point set that successfully match the target points in the second point set, if the current point in the first point set matches the target point in the second point set successfully; A determination module is used to determine that a lane line of the target road corresponding to a target lane line has changed if the difference is greater than a preset threshold, and the difference is a value obtained by subtracting 1 from the similarity between the current actual lane line and the target lane line.

10. An electronic device, characterized in that: include: processor; as well as A memory having executable codes stored thereon, which, when executed by the processor, causes the processor to execute the method according to any one of claims 1 to 8.

11. A computer-readable storage medium having executable codes stored thereon, which, when executed by a processor of an electronic device, causes the processor to execute the method according to any one of claims 1 to 8.

Citation Information

Patent Citations

  • Lane keeping method and device

    CN107826109A

  • Vehicle driving state control method and device, computer equipment and storage medium

    CN111688683A

  • Lane line detection method, electronic device and storage medium

    WO2020232648A1