A lane line construction method and system
By preprocessing and resampling the trajectories of crowdsourced vehicles, a histogram is generated to find peak values, solving the problem of lane boundary construction in areas with no or missing lane markings, and realizing adaptive lane line construction.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- WUHAN ZHONGHAITING DATA TECH CO LTD
- Filing Date
- 2022-11-29
- Publication Date
- 2026-06-09
AI Technical Summary
In areas where there are no road markings or where markings are severely lacking, existing technologies cannot effectively construct lane boundaries.
By preprocessing the crowdsourced vehicle trajectories, selecting trajectory reference lines, generating perpendicular line segments and obtaining intersection points as resampled trajectory points, calculating distances and generating histograms, finding peak values, and constructing lane center lines and dividing lines.
In the absence of lane markings or when lane markings are missing, the system can adaptively construct lane boundaries, achieving effective lane line construction in a simple and practical process.
Smart Images
Figure CN115908630B_ABST
Abstract
Description
Technical Field
[0001] This invention belongs to the field of high-precision map production, and in particular relates to a method and system for constructing lane lines. Background Technology
[0002] When building high-precision maps using crowdsourced data collection, for structured roads with clear road markings, such as highways and urban expressways, complete lane boundaries and structured lanes can be constructed through operations such as perceptual extraction and inference of road markings. However, for areas with inadequate road infrastructure, such as unstructured roads without road markings or roads with severe marking loss due to road construction, it is impossible to extract sufficient lane markings as lane boundaries. Summary of the Invention
[0003] In view of this, embodiments of the present invention provide a lane line construction method and system to solve the problem of being unable to construct lane boundaries when road markings are severely missing.
[0004] In a first aspect of the present invention, a lane line construction method is provided, comprising:
[0005] Preprocess the trajectories of crowdsourced vehicles to filter trajectories of predetermined types;
[0006] Select a trajectory reference line, draw perpendicular line segments to the trajectory reference line at equal intervals along the vehicle's direction of travel, and obtain the intersection points of the perpendicular line segments and the crowdsourced vehicle trajectory as resampled trajectory points.
[0007] The distance between the resampled trajectory points and the trajectory reference line is statistically analyzed and a histogram is generated. Under a predetermined interval constraint, the peak value of the distribution of resampled trajectory points in the histogram is found.
[0008] The location of the trajectory point corresponding to the peak is taken as the lane center point. The lane center line is constructed based on the lane center point, and the center line of the adjacent lane center lines is taken as the lane dividing line.
[0009] In a second aspect of the present invention, a system for lane line construction is provided, comprising:
[0010] The preprocessing module is used to preprocess the trajectories of crowdsourced vehicles and filter trajectories of predetermined types.
[0011] The resampling module is used to select a trajectory reference line, draw perpendicular line segments to the trajectory reference line at equal intervals along the vehicle's direction of travel, and obtain the intersection points of the perpendicular line segments and the crowdsourced vehicle trajectory as resampling trajectory points.
[0012] The peak acquisition module is used to calculate the distance between resampled trajectory points and trajectory reference lines and generate a histogram, and to find the peak value of the resampled trajectory point distribution in the histogram under a predetermined interval constraint.
[0013] The module is used to take the location of the trajectory point corresponding to the peak as the lane center point, construct the lane center line based on the lane center point, and take the center line of the adjacent lane center lines as the lane dividing line.
[0014] In a third aspect of the present invention, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and executable by the processor, wherein the processor executes the computer program to implement the steps of the method as described in the first aspect of the present invention.
[0015] In a fourth aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the method provided in the first aspect of the present invention.
[0016] In this embodiment of the invention, resampling is performed based on the reference trajectory, and the lateral distance of the resampled trajectory points relative to the reference trajectory is recorded to generate a histogram. The peak value of the trajectory point distribution is obtained as the lane center, and the lane center line is generated. The centerline of the adjacent lane center lines is taken as the lane boundary line, thereby realizing the adaptive construction of lane boundary lines based on crowdsourced trajectory distribution. Even when lane markings are severely missing, lane lines can still be constructed, and the process is simple and practical. Attached Figure Description
[0017] To more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0018] Figure 1 This is a flowchart illustrating a lane line construction method according to an embodiment of the present invention.
[0019] Figure 2 This is a schematic diagram of a system for lane line construction provided in one embodiment of the present invention;
[0020] Figure 3 This is a schematic diagram of the structure of an electronic device provided in one embodiment of the present invention. Detailed Implementation
[0021] To make the objectives, features, and advantages of this invention more apparent and understandable, the technical solutions of the embodiments of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the embodiments described below are only some embodiments of this invention, and not all embodiments. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.
[0022] It should be understood that the terms "comprising" and other similar expressions in the specification, claims, and accompanying drawings of this invention are intended to cover a non-exclusive inclusion, such as a process, method, system, or apparatus that includes a series of steps or units and is not limited to the listed steps or units. Furthermore, "first" and "second" are used to distinguish different objects and are not intended to describe a specific order.
[0023] Please see Figure 1 A flowchart illustrating a lane line construction method provided in this embodiment of the invention includes:
[0024] S101. Preprocess the trajectory of crowdsourced vehicles and filter trajectories of predetermined types;
[0025] The system acquires trajectory data from crowdsourced vehicles traversing road sections without or with severely missing road markings, and processes this data. The predetermined trajectory type is considered an abnormal trajectory, such as trajectory reversal, trajectory drift, or trajectory with severe gaps.
[0026] Preferably, the foldback trajectory is filtered based on the trajectory angle;
[0027] A constrained Delaunay triangulation is constructed based on trajectory points, and the outer drifting trajectories are filtered by clustering based on the density of the longest point and vertices of the triangulation.
[0028] The foldback trajectory refers to a trajectory that folds back in the opposite direction of travel. This can be determined based on the trajectory direction (or heading angle), such as when the trajectory direction angle changes by more than 90°. The outer drift trajectory refers to a vehicle trajectory that drifts to either side of the current road. In this case, angle determination is inaccurate, and filtering is required based on Delaunay triangulation constraints, using density clustering of the vertices and long edges of the triangulation.
[0029] S102. Select a trajectory reference line, draw perpendicular line segments to the trajectory reference line at equal intervals along the vehicle's driving direction, and obtain the intersection points of the perpendicular line segments and the crowdsourced vehicle trajectory as resampled trajectory points.
[0030] The trajectory reference line is a relatively smooth trajectory selected from the crowdsourced trajectories. It can be selected manually or determined automatically by an algorithm.
[0031] For the selected trajectory reference line, along the vehicle's direction of travel, generate a relatively long vertical line segment (e.g., 30m) at equal intervals (e.g., L=1m). Take the intersection of the vertical line segment and the crowdsourced trajectory line as the resampling point of each trajectory line, and record the lateral distance of the resampling trajectory point on the vertical line segment relative to the reference line.
[0032] S103. Calculate the distance between the resampled trajectory points and the trajectory reference line and generate a histogram. Find the peak value of the distribution of resampled trajectory points in the histogram under the predetermined interval constraint.
[0033] The distance between the resampled trajectory point and the trajectory reference line refers to the lateral distance between the resampled trajectory point and the equally divided points of the trajectory reference line on the vertical segment. The histogram is a histogram of the lateral distance distribution.
[0034] Specifically, the resampled trajectory points on each vertical line segment are used as a frame of data for the vehicle's driving direction. In each frame of data, a histogram distribution with a predetermined interval granularity is generated based on the lateral distance of all trajectory points in the current frame.
[0035] The predetermined interval constraint is set based on the road width, typically 2.5m. The peak value of the trajectory distribution is found on the histogram distribution data using an interval distance constraint of K = 2.5m. The interval distance constraint K ensures the minimum lateral distance between two peak values, which is also the minimum width of the constrained lane, preventing invalid or abnormal lanes.
[0036] S104. Take the location of the trajectory point corresponding to the peak as the lane center point, construct the lane center line based on the lane center point, and take the center line of the adjacent lane center lines as the lane dividing line.
[0037] The peak value of the trajectory distribution is the lane center. Based on the peak points of multiple consecutive frames, the lane center line is generated. The centerline of the adjacent lane center lines is taken as the lane dividing line, i.e., the lane line.
[0038] Considering that not every frame of data can extract the peak values of the trajectory distribution of all lanes, the data of multiple consecutive frames does not need to be continuous from the start to the end of the road, but only a certain length of continuous frames is required. This scheme can be easily embedded into the area where local perception markings are missing.
[0039] Preferably, when the vehicle-mounted camera detects road markings, it prioritizes using the detected road markings as lane dividing lines.
[0040] In this embodiment, trajectory data from a crowdsourcing scenario is used to supplement lane information in scenarios with missing road markings without increasing additional collection costs. This solves the lane construction problem in scenarios with no road markings or severely missing markings. At the same time, it is implemented using multi-frame data resampled along the road driving direction, which can extract some frame data results as lane supplementation in scenarios with local missing markings. The application has strong scalability and embeddability, making it convenient to provide a reference for lane line construction in road sections with missing markings.
[0041] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.
[0042] Figure 2 This is a schematic diagram of a system for constructing lane lines according to an embodiment of the present invention. The system includes:
[0043] Preprocessing module 210 is used to preprocess the trajectory of crowdsourced vehicles and filter trajectories of a predetermined type;
[0044] The preprocessing module 210 includes:
[0045] The first filtering unit is used to filter the foldback trajectory based on the trajectory angle;
[0046] The second filtering unit is used to construct a constrained Delaunay triangulation based on trajectory points, and to filter the outer drifting trajectory by clustering according to the density of the long points and vertices of the triangulation.
[0047] The resampling module 220 is used to select a trajectory reference line, draw perpendicular line segments to the trajectory reference line at equal intervals along the vehicle's driving direction, and obtain the intersection points of the perpendicular line segments and the crowdsourced vehicle trajectory as resampling trajectory points.
[0048] Peak acquisition module 230 is used to count the distance between resampled trajectory points and trajectory reference lines and generate a histogram, and to find the peak value of the distribution of resampled trajectory points in the histogram under a predetermined interval constraint;
[0049] The step of statistically analyzing the distance between the resampled trajectory points and the trajectory reference line and generating a histogram includes:
[0050] The resampled trajectory points on each vertical line segment are used as a frame of data for the vehicle's driving direction. In each frame of data, a histogram distribution with a predetermined interval granularity is generated based on the lateral distance of all trajectory points in the current frame.
[0051] The construction module 240 is used to take the trajectory point position corresponding to the peak as the lane center point, construct the lane center line based on the lane center point, and take the center axis of the adjacent lane center lines as the lane dividing line.
[0052] Preferably, the building module 240 further includes:
[0053] The perception module is used to prioritize the perceived road markings as lane dividing lines when the vehicle-mounted camera detects them.
[0054] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working process of the system and modules described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.
[0055] Figure 3 This is a schematic diagram of an electronic device according to an embodiment of the present invention. The electronic device is used for constructing lane markings. Figure 3 As shown, the electronic device 3 of this embodiment includes: a memory 310, a processor 320, and a system bus 330. The memory 310 includes an executable program 3101 stored thereon. As those skilled in the art will understand, Figure 3 The electronic device structure shown does not constitute a limitation on the electronic device and may include more or fewer components than shown, or combine certain components, or have different component arrangements.
[0056] The following is combined Figure 3 A detailed introduction to each component of the electronic device:
[0057] The memory 310 can be used to store software programs and modules. The processor 320 executes various functional applications and data processing of the electronic device by running the software programs and modules stored in the memory 310. The memory 310 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, application programs required for at least one function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the electronic device (such as cached data), etc. In addition, the memory 310 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device.
[0058] The memory 310 contains an executable program 3101 for a network request method. This executable program 3101 can be divided into one or more modules / units, which are stored in the memory 310 and executed by the processor 320 to perform tasks such as lane marking construction. Each module / unit can be a series of computer program instruction segments capable of performing a specific function, describing the execution process of the computer program 3101 in the electronic device 4. For example, the computer program 3101 can be divided into functional modules such as a preprocessing module, a resampling module, a peak acquisition module, and a construction module.
[0059] The processor 320 is the control center of the electronic device. It connects various parts of the electronic device via various interfaces and lines. By running or executing software programs and / or modules stored in the memory 310, and by calling data stored in the memory 310, it performs various functions and processes data, thereby monitoring the overall status of the electronic device. Optionally, the processor 320 may include one or more processing units; preferably, the processor 320 may integrate an application processor and a modem processor, wherein the application processor mainly handles the operating system, application programs, etc., and the modem processor mainly handles wireless communication. It is understood that the modem processor may also not be integrated into the processor 320.
[0060] The system bus 330 is used to connect various functional components within the computer, transmitting data, address, and control information. Its type can be, for example, a PCI bus, an ISA bus, or a CAN bus. Instructions from the processor 320 are transmitted to the memory 310 via the bus, and the memory 310 sends data back to the processor 320. The system bus 330 is responsible for data and instruction exchange between the processor 320 and the memory 310. Of course, the system bus 330 can also connect to other devices, such as network interfaces and display devices.
[0061] In this embodiment of the invention, the executable program executed by the processing 320 of the electronic device includes:
[0062] Preprocess the trajectories of crowdsourced vehicles to filter trajectories of predetermined types;
[0063] Select a trajectory reference line, draw perpendicular line segments to the trajectory reference line at equal intervals along the vehicle's direction of travel, and obtain the intersection points of the perpendicular line segments and the crowdsourced vehicle trajectory as resampled trajectory points.
[0064] The distance between the resampled trajectory points and the trajectory reference line is statistically analyzed and a histogram is generated. Under a predetermined interval constraint, the peak value of the distribution of resampled trajectory points in the histogram is found.
[0065] The location of the trajectory point corresponding to the peak is taken as the lane center point. The lane center line is constructed based on the lane center point, and the center line of the adjacent lane center lines is taken as the lane dividing line.
[0066] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and modules described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.
[0067] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.
[0068] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims
1. A method for constructing lane lines, characterized in that, include: Preprocess the trajectories of crowdsourced vehicles to filter trajectories of predetermined types; Select a trajectory reference line, draw perpendicular line segments to the trajectory reference line at equal intervals along the vehicle's direction of travel, and obtain the intersection points of the perpendicular line segments and the crowdsourced vehicle trajectory as resampled trajectory points. The distance between the resampled trajectory points and the trajectory reference line is statistically analyzed and a histogram is generated. Under a predetermined interval constraint, the peak value of the distribution of resampled trajectory points in the histogram is found. The step of statistically analyzing the distance between the resampled trajectory points and the trajectory reference line and generating a histogram includes: The resampled trajectory points on each vertical line segment are used as a frame of data for the vehicle's driving direction. In each frame of data, a histogram distribution with a predetermined interval granularity is generated based on the lateral distance of all trajectory points in the current frame. The location of the trajectory point corresponding to the peak is taken as the lane center point. The lane center line is constructed based on the lane center point, and the center line of the adjacent lane center lines is taken as the lane dividing line.
2. The method according to claim 1, characterized in that, The preprocessing of crowdsourced vehicle trajectories, filtering trajectories of predetermined types, includes: Filtering of the turning trajectory based on the trajectory angle; A constrained Delaunay triangulation is constructed based on trajectory points, and the outer drifting trajectories are filtered by clustering based on the density of the longest point and vertices of the triangulation.
3. The method according to claim 1, characterized in that, The step of using the trajectory point location corresponding to the peak as the lane center point, constructing the lane center line based on the lane center point, and using the center axis of the adjacent lane center lines as the lane dividing line also includes: When the vehicle-mounted camera detects road markings, it prioritizes using the detected road markings as lane dividers.
4. A system for lane line construction, characterized in that, include: The preprocessing module is used to preprocess the trajectories of crowdsourced vehicles and filter trajectories of predetermined types. The resampling module is used to select a trajectory reference line, draw perpendicular line segments to the trajectory reference line at equal intervals along the vehicle's direction of travel, and obtain the intersection points of the perpendicular line segments and the crowdsourced vehicle trajectory as resampling trajectory points. The peak acquisition module is used to calculate the distance between resampled trajectory points and trajectory reference lines and generate a histogram, and to find the peak value of the resampled trajectory point distribution in the histogram under a predetermined interval constraint. The step of statistically analyzing the distance between the resampled trajectory points and the trajectory reference line and generating a histogram includes: The resampled trajectory points on each vertical line segment are used as a frame of data for the vehicle's driving direction. In each frame of data, a histogram distribution with a predetermined interval granularity is generated based on the lateral distance of all trajectory points in the current frame. The module is used to take the location of the trajectory point corresponding to the peak as the lane center point, construct the lane center line based on the lane center point, and take the center line of the adjacent lane center lines as the lane dividing line.
5. The system according to claim 4, characterized in that, The preprocessing module includes: The first filtering unit is used to filter the foldback trajectory based on the trajectory angle; The second filtering unit is used to construct a constrained Delaunay triangulation based on trajectory points, and to filter the outer drifting trajectory by clustering according to the density of the long points and vertices of the triangulation.
6. The system according to claim 4, characterized in that, The building module also includes: The perception module is used to prioritize the perceived road markings as lane dividing lines when the vehicle-mounted camera detects them.
7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of a lane line construction method as described in any one of claims 1 to 3.
8. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed, it implements the steps of a lane line construction method as described in any one of claims 1 to 3.