A cross-lane line detection method, electronic equipment and storage medium

Abstract

The application discloses a cross-lane line detection method, an electronic device and a storage medium. The method comprises the following steps: determining a feature point set of each lane line contained in a target image and a fitting straight line of each lane line; determining whether each lane line satisfies a preset detection condition based on the feature point set and the fitting straight line of each lane line; taking the lane line satisfying the preset detection condition as a target lane line; and obtaining a cross detection result of any two target lane lines based on the fitting straight line of the target lane line, wherein the cross detection result comprises a target intersection point between any two target lane lines and / or a cross type. In the foregoing manner, the application can accurately detect the intersection point and the cross type of any two lane lines.

Description

Technical Field

[0001] This application relates to the field of autonomous driving technology, and in particular to a method for detecting cross lane lines, an electronic device, and a storage medium. Background Technology

[0002] Lane markings are widely present on common roads such as urban areas, elevated roads, and highways. Lane markings often intersect at lane forks, merging points, and median strips. If left unaddressed, this can impair the lane marking perception capabilities of autonomous driving systems, thereby affecting vehicle route planning and control.

[0003] Currently, the detection of intersecting lane lines can be broadly divided into two categories. One method involves using navigation maps and the vehicle's own information to determine the existence of the intersection. This method relies on third-party navigation data and has high requirements for the accuracy of the navigation map, making it complex and costly. The other method uses object detection tasks to detect information acquired by the vehicle's own sensors to obtain intersection information. This method is also costly, and the accuracy of the detection results is low due to the complexity of intersection conditions, such as the presence of marked guide strips and unmarked lane merging. Summary of the Invention

[0004] The main technical problem addressed by this application is to provide a method, electronic device, and storage medium for detecting intersecting lane lines, which can accurately detect the intersection point and intersection type of any two lane lines, while reducing detection costs.

[0005] To address the aforementioned technical problems, the first aspect of this application provides a method for detecting intersecting lane lines. This method includes: determining a feature point set for each lane line in a target image and a fitted straight line for each lane line; determining whether each lane line meets preset detection conditions based on the feature point set and fitted straight line; selecting lane lines that meet the preset detection conditions as target lane lines; and obtaining an intersection detection result for any two target lane lines based on the fitted straight line of the target lane lines, wherein the intersection detection result includes the target intersection point and / or intersection type between any two target lane lines.

[0006] To address the aforementioned technical problems, a second aspect of this application provides an electronic device comprising: a memory and a processor coupled to each other, the memory storing program instructions; and the processor executing the program instructions stored in the memory to implement the method provided in the first aspect.

[0007] To address the aforementioned technical problems, a third aspect of this application provides a computer-readable storage medium for storing program instructions that can be executed to implement the method provided in the first aspect.

[0008] The beneficial effects of this application are as follows: Unlike existing technologies, after determining the feature point set and fitted straight line for each lane line, this application can determine whether each lane line meets the preset detection conditions based on these features and fitted straight lines. Intersection detection is only performed on target lane lines that meet the preset detection conditions, reducing computational load and costs. Furthermore, based on the fitted straight lines of the target lane lines, the intersection detection results of any two target lane lines can be obtained without introducing a target detection task, thus reducing detection costs. The intersection detection results include the target intersection point and / or intersection type between any two target lane lines. In summary, this application can accurately detect the intersection point and intersection type of any two lane lines while reducing detection costs. Attached Figure Description

[0009] Figure 1 This is a flowchart illustrating the first embodiment of the cross lane line detection method provided in this application;

[0010] Figure 2 This is a schematic diagram of one embodiment of determining the first and last reference points of lane lines provided in this application;

[0011] Figure 3 This is a flowchart illustrating step S14 of the first embodiment of the cross lane line detection method provided in this application;

[0012] Figure 4 This is a schematic diagram of the lane line pair according to the first embodiment provided in this application;

[0013] Figure 5 This is a schematic diagram of the second embodiment of the lane line provided in this application;

[0014] Figure 6 This is a schematic diagram of the third embodiment of the lane line provided in this application;

[0015] Figure 7 This is a schematic diagram of the fourth embodiment of the lane line provided in this application;

[0016] Figure 8 This is a schematic diagram of the framework of one embodiment of the electronic device provided in this application;

[0017] Figure 9 This is a schematic diagram of a framework of one embodiment of the computer-readable storage medium provided in this application. Detailed Implementation

[0018] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0019] It should be noted that the embodiments of this application contain descriptions involving "first," "second," etc., which are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined with "first" or "second" may explicitly or implicitly include at least one of that feature.

[0020] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0021] Please see Figure 1 and Figure 2 , Figure 1 This is a flowchart illustrating the first embodiment of the cross lane line detection method provided in this application. Figure 2 This is a schematic diagram of an embodiment of determining the first and last endpoints of a lane line provided in this application; the method includes:

[0022] S11: Determine the feature point set for each lane line in the target image and the fitted straight line for each lane line.

[0023] In one embodiment, the target image can be obtained by semantic segmentation of an initial image, which can be a photograph taken of the road ahead while the vehicle is in motion. The target image can contain at least two lane lines. A pixel-by-pixel scan and spatial transformation are performed on the target image to obtain a feature point set for each lane line. The feature point set for each lane line can be a three-dimensional point set of the centerline of each lane line, and the spatial transformation can be a perspective transformation. Specifically, the target image can be scanned in a preset direction, such as from the upper left to the lower right. Pixels that undergo category conversion are the edge points of the lane lines. The category conversion can be a conversion from a non-lane line category to a lane line category. The first pixel converted from a non-lane line to a lane line is matched with the second pixel converted from a lane line to a non-lane line. The third pixel between the successfully matched first and second pixels is the two-dimensional image space point of the lane line in the current row or column. Perspective transformation is used to convert the two-dimensional space point set of each lane line into a three-dimensional space point set, which is then used as the feature point set of each lane line.

[0024] For each lane's feature point set, at least two fitting line reference points are selected from the feature point set. Using these two reference points, a straight line is fitted to determine the fitted line of the lane. The at least two fitting line reference points can be any points in the lane's feature point set. In one specific embodiment, two fitting line reference points can be selected from the lane's feature point set. These two reference points are the first and last reference points of the lane, respectively. The first and last reference points are the two feature points corresponding to the two endpoints of the lane's feature point set and the coincident point set. The coincident point set consists of the coincident projection points of the lane's first projection point set on the second preset axis and the coincident projection points of the associated lane's second projection point set on the second preset axis. The associated lane and the lane belong to the same lane pair.

[0025] Specifically, the lane line is designated as the first lane line, and the associated lane line is designated as the second lane line. The first feature point set of the first lane line and the second feature point set of the second lane line are obtained respectively. The target image is obtained after semantic segmentation of the initial image. The initial image is assumed to be a photograph taken of the road ahead while the vehicle is in motion. Therefore, a coordinate system can be established with the vehicle as the origin and the vehicle's direction of travel as the Y-axis, such as... Figure 2As shown. The first and second feature point sets are projected onto a second preset axis, which can be either the X-axis or the Y-axis. The resulting first projected point set and second projected point set are obtained. The overlapping projection points in the first and second projected point sets form a coincident point set. Several first feature points corresponding to the coincident point set are obtained from the first feature point set. Two first feature points corresponding to the two endpoints of the coincident point set are selected from these first feature points. The first feature point closer to the origin is used as the first reference point of the first lane line, and the first feature point farther from the origin is used as the tail reference point of the first lane line. Similarly, several second feature points corresponding to the coincident point set are obtained from the second feature point set. Two second feature points corresponding to the two endpoints of the coincident point set are selected from these second feature points. The second feature point closer to the origin is used as the first reference point of the second lane line, and the second feature point farther from the origin is used as the tail reference point of the second lane line.

[0026] The reason for selecting the first and last reference points of the lane lines as the reference points for fitting the straight line is that the first and last endpoints of the three-dimensional point set of the lane lines are easily affected by distortion, and the lane intersection information will gradually weaken as the distance increases; therefore, selecting the overlapping part that best represents the lane intersection information as the judgment basis can eliminate the interference of unnecessary information.

[0027] After obtaining the first and last reference points of the lane line, the third distance between the first and last reference points in the Y direction and the fourth distance in the X direction can be obtained. The quotient of the third and fourth distances is used as the slope of the fitted line of the lane line. The difference between the coordinate value of the first reference point in the Y direction and a first value is used as the intercept of the fitted line of the lane line. The first value is the product of the coordinate value of the first reference point in the X direction and the slope of the fitted line of the lane line. Specifically, the linear equation of the fitted line of the lane line can be obtained using the following formula.

[0028]

[0029] Bias i =BasisStartY i -Grad i *BasisStartX i

[0030] Line i :y=Grad i *+Bias i

[0031] Wherein, the coordinates of the first reference point of the i-th lane line are (BasisStartXi, BasisStartYi), and the coordinates of the last reference point of the lane line are (BasisEndXi, BasisEndYi). i Let Bias be the slope of the fitted straight line for the i-th lane. I Let be the intercept of the fitted straight line for the i-th lane.

[0032] S12: Based on the feature point set and fitted straight line of each lane line, determine whether each lane line meets the preset detection conditions.

[0033] In one embodiment, it can be determined in advance whether each lane line meets the preset detection conditions. If it does not meet the conditions, the lane line will not be detected, thereby reducing the number of lane lines to be detected and improving detection efficiency.

[0034] Specifically, for each lane line, at least one of the following judgments can be performed. In one specific embodiment, it can be determined whether the number of feature points in the feature point set of the lane line is greater than a first preset value. If it is greater, the judgment is considered successful. Understandably, the first preset value can be set as needed and is not limited here.

[0035] In one specific implementation, it can be determined whether a first distance between the first endpoint and the last endpoint of the lane line is greater than a second preset value. If it is greater, the determination is considered successful. Understandably, the second preset value can be set as needed and is not limited here. The first endpoint and the last endpoint are the two endpoints of the lane line. Assuming that the target image is captured in the direction of the vehicle's movement, with the vehicle as the origin, the feature point closest to the origin in the feature point set of the lane line is the first endpoint of the lane line, and the feature point farthest from the origin is the last endpoint of the lane line.

[0036] In one specific implementation, it is determined whether the first coordinate value of the tail endpoint of the first related lane line corresponding to the lane line on the second preset axis is less than the second coordinate value of the tail endpoint of the second related lane line corresponding to the lane line on the second preset axis, and whether the first coordinate value is greater than the third coordinate value of the head endpoint of the second related lane line corresponding to the lane line on the second preset axis. One of the first and second related lane lines is a lane line, and the other is an associated lane line belonging to the same lane line pair as the lane line. The lane line pair consists of any two lane lines in the target image. If both related lane lines pass the determination, the target intersection point and intersection type between these two related lane lines can be further determined. The second preset axis can be either the X-axis or the Y-axis. The determination is considered successful when the first coordinate value of the tail endpoint of the first related lane line on the second preset axis is less than the second coordinate value of the tail endpoint of the second related lane line on the second preset axis, and the first coordinate value is greater than the third coordinate value of the head endpoint of the second related lane line on the second preset axis.

[0037] In one specific implementation, it is determined whether the second distance of the lane line is less than a third preset value, and whether the slope difference between the lane line and the associated lane line is greater than a fourth preset value. The second distance is the distance between the first reference point and / or the last reference point of the first associated lane line corresponding to the lane line and the fitted straight line of the corresponding second associated lane line. Specifically, for two lane lines in a lane line pair, either one is defined as the first associated lane line, and the other is the associated lane line (i.e., the second associated lane line). If the distance between the first reference point and / or the last reference point of the first associated lane line and the fitted straight line of the second associated lane line is less than the third preset value, and the slope difference between the first associated lane line and the second associated lane line is greater than the fourth preset value, then the determination is considered successful. The slope difference can be the absolute value of the difference in slopes. The third and fourth preset values ​​can be set as needed and are not limited here. The first reference point and the last reference point are two feature points corresponding to the two endpoints of the feature point set and the coincidence point set of the first related lane line, respectively. The coincidence point set consists of the coincidence projection points of the first projection point set of the first related lane line on the second preset axis and the second projection point set of the second related lane line on the second preset axis. Please refer to the above description for the method of determining the first reference point and the last reference point, which will not be repeated here.

[0038] The distance between the first reference point of the first relevant lane line and the fitted line of the second relevant lane line, and the distance between the last reference point of the first relevant lane line and the fitted line of the second relevant lane line, can be calculated using the following formulas.

[0039]

[0040]

[0041] Among them, DistanceA2B STARt DistanceA2B is the distance between the first reference point of the first relevant lane line and the fitted straight line of the second relevant lane line. enD Grad is the distance between the tail reference point of the first relevant lane line and the fitted straight line of the second relevant lane line. B Bias is the slope of the fitted straight line of the second relevant lane line. B The intercept of the fitted straight line of the second related lane line is given, and the coordinates of the first reference point of the first related lane line are (BasisStartX). A BasisStartY A The coordinates of the tail reference point of the first relevant lane line are (BasisEndX). A BasisEndY A ).

[0042] In one specific implementation, it is determined whether the second distance of the lane line is less than a third preset value, and whether the absolute value of the difference between the two second distances is greater than a fifth preset value. The two second distances are the distance between the first reference point of the first related lane line and the fitted line of the corresponding second related lane line, and the distance between the tail reference point of the first related lane line and the fitted line of the corresponding second related lane line. If both are true, the determination passes.

[0043] Understandably, any one or more of the above five judgments can be selectively executed. In response to all executed judgments passing, it is determined that the lane line meets the preset detection conditions. If a judgment is made on a lane line pair and the judgment passes, then both lane lines contained in the lane line pair meet the preset detection conditions.

[0044] S13: Use lane lines that meet the preset detection conditions as target lane lines.

[0045] S14: Based on the fitted straight line of the target lane line, obtain the intersection detection result of any two target lane lines. The intersection detection result includes the target intersection point and / or intersection type between any two target lane lines.

[0046] In one embodiment, the target intersection point of any two target lane lines can be determined based on the feature point set of the target lane lines and the fitted straight line of the target lane lines; and / or, the fitted intersection point of any two target lane lines can be determined based on the fitted straight line of any two target lane lines, and the intersection type of any two target lane lines can be determined based on the fitted intersection point and the corresponding first and last endpoints of each of the two target lane lines; wherein the first and last endpoints of each target lane line are feature points in the feature point set of the lane lines.

[0047] The above method, after determining the feature point set and fitted straight line for each lane, can determine whether each lane meets the preset detection conditions based on these conditions. Intersection detection is only performed on target lanes that meet the preset conditions, reducing computational load and cost. Furthermore, based on the fitted straight line of the target lanes, the intersection detection results of any two target lanes can be obtained without introducing a target detection task, further reducing detection costs. The intersection detection results include the target intersection point and / or intersection type between any two target lanes. In summary, this application can accurately detect the intersection point and intersection type of any two lanes while reducing detection costs.

[0048] Please see Figure 3-7 , Figure 3 This is a flowchart illustrating step S14 of the first embodiment of the cross lane line detection method provided in this application. Figure 4 This is a schematic diagram of the first embodiment of the lane line configuration provided in this application. Figure 5 This is a schematic diagram of the second embodiment of the lane line configuration provided in this application. Figure 6 This is a schematic diagram of the third embodiment of the lane line provided in this application. Figure 7 This is a schematic diagram of the fourth embodiment of the lane line pair provided in this application; this embodiment is used to determine the target intersection point between any two target lane lines, and step S14 may include:

[0049] S341: For any two target lane lines, obtain the first and last endpoints of each target lane line from the feature point set of the two target lane lines as the target first endpoint and target last endpoint.

[0050] S342: Determine the fitting intersection point of the two target lane lines based on the fitted straight lines of the two target lane lines.

[0051] In one embodiment, the fitting intersection point of the two target lane lines can be determined by the slope and intercept of the fitted straight line. Specifically, the fitting intersection point can be obtained using the following formula.

[0052]

[0053]

[0054] Wherein, the coordinates of the fitted intersection point are (LineCrossPointX, LineCrossPointY), Grad A Let Grad be the slope of target lane line A. b Bias is the slope of the target lane line B. ABias is the intercept of target lane line A. B The intercept of the target lane line A.

[0055] S343: Determine the first coordinate difference between the first endpoint of each target and the fitting intersection point on the first preset axis; and the second coordinate difference between the tail endpoint of each target and the fitting intersection point on the first preset axis.

[0056] Wherein, the first preset axis is the X-axis direction, and the first coordinate difference is the difference between the X coordinate value of the target's first endpoint and the X coordinate value of the fitted intersection point. Similarly, the second coordinate difference is the difference between the X coordinate value of the target's last endpoint and the X coordinate value of the fitted intersection point.

[0057] S344: Determine the target intersection point based on the differences between the first coordinates and the differences between the second coordinates.

[0058] In one embodiment, the target intersection point is one of the target tail endpoints. In a specific embodiment, each first coordinate difference and each second coordinate difference is less than a first value, and the target tail endpoint far from the fitted intersection point is taken as the target intersection point. Figure 4 The target end point of target lane line B is taken as the target intersection point. In another specific embodiment, all first coordinate differences are less than the second value, and only one second coordinate difference is less than the third value; the target end point whose second coordinate difference is less than the third value is taken as the target intersection point. Figure 5 Take the target end point of target lane line B as the target intersection point.

[0059] In another embodiment, the target intersection point is one of the target starting points; in a specific embodiment, in response to each first coordinate difference and each second coordinate difference being greater than a first value, the target starting point farthest from the fitted intersection point is taken as the target intersection point. Figure 6 The target starting point of target lane line B is taken as the target intersection point. In another specific embodiment, in response to all second coordinate differences being greater than the second value, and only one first target difference being greater than the third value, the target starting point where the second target difference is greater than the third value is taken as the target intersection point. Figure 7 The target starting point of target lane line B is taken as the target intersection point.

[0060] in, Figure 4-7 This is a coordinate system established with the vehicle as the origin and the vehicle's direction of travel as the X-axis. Understandably, the first, second, and third values ​​can be set by the user, and in a specific implementation, the first, second, and third values ​​are all zero.

[0061] Furthermore, in another embodiment of step S14 of the first embodiment of the cross lane detection method provided in this application, determining the cross type of any two target lane lines based on the fitted intersection point and the corresponding first and last endpoints of each of the two target lane lines may include:

[0062] If the coordinate difference between the first and last endpoints of any two target lane lines and the fitted intersection point on the first preset axis is less than the fourth value, then the intersection type of any two target lane lines is greater than type (e.g., Figure 4 If the coordinate difference between the first and last endpoints of any two target lane lines and the fitted intersection point on the first preset axis is greater than the fourth value, then the intersection type of any two target lane lines is less than type (e.g., Figure 6 If, among the coordinate differences between the first and last endpoints of any two target lane lines and the fitted intersection point on the first preset axis, only one of these differences is less than or greater than the fourth value, then the intersection type of any two target lane lines is Y-type (e.g., ...). Figure 5 and Figure 7 ),in, Figure 5 Specifically, it can belong to the ">—" type. Figure 6 Specifically, it can belong to the "-<" type.

[0063] The above method can detect intersecting lane lines using only information obtained from the vehicle's own sensors, so the cost is relatively low. Furthermore, the above method does not require the introduction of new deep learning tasks, resulting in low computational overhead. Since the above method is based on lane line detection results for lane line intersection detection, it can handle different types of lane line intersection situations, such as lane line intersection areas without obvious markings, and provide accurate information on the intersection lines and the location of the intersection points.

[0064] Please see Figure 8 , Figure 8 This is a schematic diagram of one embodiment of the electronic device provided in this application.

[0065] The electronic device 80 includes a memory 81 and a processor 82 coupled to each other. The memory 81 stores program instructions, and the processor 82 executes the program instructions to implement the steps in any of the above method embodiments. Specifically, the electronic device 80 may include, but is not limited to, desktop computers, laptops, servers, mobile phones, tablets, etc., and is not limited thereto.

[0066] Specifically, processor 82 controls itself and memory 81 to implement the steps in any of the above method embodiments. Processor 82 can also be referred to as a CPU (Central Processing Unit). Processor 82 may be an integrated circuit chip with signal processing capabilities. Processor 82 can also be a general-purpose processor, digital signal processor (DSP), application-specific integrated circuit (ASIC), field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. A general-purpose processor can be a microprocessor or any conventional processor. Furthermore, processor 82 can be implemented using integrated circuit chips.

[0067] Please see Figure 9 , Figure 9 This is a schematic diagram illustrating an embodiment of the computer-readable storage medium provided in this application. The computer-readable storage medium 90 stores program instructions 91, which, when executed by a processor, are used to implement the steps in any of the above method embodiments.

[0068] The computer-readable storage medium 90 can specifically be a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, or a medium that can store computer programs. Alternatively, it can be a server that stores the computer program, which can send the stored computer program to other devices for execution or can also run the stored computer program itself.

[0069] In the several embodiments provided in this application, it should be understood that the disclosed methods and apparatus can be implemented in other ways. For example, the apparatus implementations described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0070] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0071] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0072] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute all or part of the steps of the methods of various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0073] The above description is merely an embodiment of this application and does not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. A method for detecting intersecting lane lines, characterized in that, The method includes: Determine the feature point set of each lane line contained in the target image and the fitted straight line for each lane line; Based on the feature point set and the fitted straight line for each lane line, determine whether each lane line meets the preset detection conditions; The lane lines that meet the preset detection conditions are taken as the target lane lines; Based on the fitted straight line of the target lane line, obtain the intersection detection result of any two target lane lines, and the intersection detection result includes the target intersection point and / or intersection type between any two target lane lines. The step of determining whether each lane line meets the preset detection conditions based on the feature point set and the fitted straight line for each lane line includes: For each lane line, perform at least one of the following checks: Determine whether the number of feature points in the feature point set of the lane line is greater than a first preset value; Determine whether the first distance between the first endpoint and the last endpoint of the lane line is greater than a second preset value, wherein the first endpoint and the last endpoint are the two endpoints of the lane line; Determine whether the first coordinate value of the tail end point of the first related lane line corresponding to the lane line on the second preset axis is less than the second coordinate value of the tail end point of the second related lane line corresponding to the lane line on the second preset axis, and whether the first coordinate value is greater than the third coordinate value of the head end point of the second related lane line corresponding to the lane line on the second preset axis. One of the first related lane line and the second related lane line is the lane line, and the other is an associated lane line that belongs to the same lane line pair as the lane line. Determine whether the second distance of the lane line is less than a third preset value, and whether the slope difference between the lane line and the associated lane line is greater than a fourth preset value. The second distance is the distance between the first reference point and / or the tail reference point of the first associated lane line corresponding to the lane line and the fitted straight line of the corresponding second associated lane line. The first reference point and the tail reference point are two feature points corresponding to the two endpoints of the feature point set and the coincidence point set of the first associated lane line, respectively. The coincidence point set is composed of the coincidence projection points of the first projection point set of the first associated lane line on the second preset axis and the second projection point set of the second associated lane line on the second preset axis. If all the judgments executed pass, it is determined that the lane line meets the preset detection conditions.

2. The method according to claim 1, characterized in that, The step of obtaining the intersection detection result of any two target lane lines based on the fitted straight line of the target lane lines includes: Based on the feature point set of the target lane line and the fitted straight line of the target lane line, determine the target intersection point of any two target lane lines; and / or, Based on the fitted straight lines of any two target lane lines, determine the fitted intersection point of the two target lane lines, and based on the fitted intersection point and the corresponding first and last endpoints of the two target lane lines, determine the intersection type of the two target lane lines.

3. The method according to claim 2, characterized in that, The step of determining the target intersection point of any two target lane lines based on the feature point set of the target lane lines and the fitted straight line of the target lane lines includes: For any two target lane lines, the first endpoint and the last endpoint of each target lane line are obtained from the feature point set of the two target lane lines respectively as the target first endpoint and the target last endpoint. Based on the fitted straight lines of the two target lane lines, determine the fitted intersection point of the two target lane lines; Determine the first coordinate difference between each target's first endpoint and the fitting intersection point along the first preset axis; and the second coordinate difference between each target's last endpoint and the fitting intersection point along the first preset axis; The target intersection point is determined based on the differences between the first coordinates and the differences between the second coordinates.

4. The method according to claim 3, characterized in that, The target intersection point is one of the target tail endpoints; The step of determining the target intersection point based on each of the first coordinate differences and each of the second coordinate differences includes: In response to each of the first coordinate differences and each of the second coordinate differences being less than a first value, the target tail endpoint that is far from the fitted intersection point is taken as the target intersection point; Alternatively, in response to each of the first coordinate differences being less than the second value, and only one of the second coordinate differences being less than the third value, the target tail endpoint where the second coordinate difference is less than the third value is taken as the target intersection point.

5. The method according to claim 3, characterized in that, The target intersection point is one of the target's starting points; The step of determining the target intersection point based on each of the first coordinate differences and each of the second coordinate differences includes: In response to each of the first coordinate differences and each of the second coordinate differences being greater than the first value, the target starting point that is far away from the fitted intersection point is taken as the target intersection point; Alternatively, in response to each of the second coordinate differences being greater than the second value, and only one of the first coordinate differences being greater than the third value, the target starting point where the second coordinate difference is greater than the third value is taken as the target intersection point.

6. The method according to claim 2, characterized in that, The intersection type of any two target lane lines is determined based on the fitted intersection point and the corresponding first and last endpoints of each of the two target lane lines, including any one of the following: If the coordinate difference between the first and last endpoints of any two target lane lines and the fitted intersection point on the first preset axis is less than the fourth value, then the intersection type of any two target lane lines is greater than type. If the coordinate difference between the first and last endpoints of any two target lane lines and the fitted intersection point on the first preset axis is greater than the fourth value, then the intersection type of any two target lane lines is less than type. If, among the coordinate differences between the first and last endpoints of any two target lane lines and the fitted intersection point on the first preset axis, only one of the coordinate differences is less than or greater than the fourth value, then the intersection type of any two target lane lines is Y type.

7. The method according to claim 1, characterized in that, Determining the fitted straight line for each lane line includes: Select at least two reference points for fitting a straight line from the set of feature points of the lane line; The fitted straight line of the lane line is determined using the at least two fitted straight line reference points.

8. The method according to claim 7, characterized in that, There are two reference points for the fitted straight line, which are the first reference point and the last reference point of the lane line. The first reference point and the last reference point are two feature points corresponding to the two endpoints of the feature point set and the coincidence point set of the lane line, respectively. The coincidence point set is composed of the coincidence projection points of the first projection point set of the lane line on the second preset axis and the second projection point set of the associated lane line on the second preset axis. The associated lane line and the lane line belong to the same lane line pair.

9. The method according to claim 1, characterized in that, The determination of the feature point set for each lane line contained in the target image includes: The target image is subjected to pixel scanning and spatial transformation to obtain the feature point set of each lane line contained in the target image; wherein, the target image is obtained by semantic segmentation of the initial image.

10. An electronic device, characterized in that, The device includes a memory and a processor that are coupled to each other; The memory stores program instructions; The processor is used to execute program instructions stored in the memory to implement the method according to any one of claims 1-9.

11. A computer-readable storage medium, characterized in that, The computer-readable storage medium is used to store program instructions that can be executed to implement the method as described in any one of claims 1-9.

Images