Method and device for generating lane dashed line segments

Abstract

The present invention relates to a method and device for generating lane dashed line segments, comprising: obtaining one or more lane dividers of a target lane, virtual-real change points of each lane divider, and AI dashed line segment data; extracting virtual-real change information from each lane divider and its corresponding virtual-real change point; segmenting the virtual-real change points within each lane divider based on the virtual-real change information and generating initial dashed line segments; generating dashed line blocks and bounding boxes for each initial dashed line segment according to the direction of the lane divider; determining the associated lane divider of each initial dashed line segment based on the dashed line blocks and bounding boxes of each initial dashed line segment and the corresponding AI dashed line segment; and optimizing the shape of the initial dashed line segment based on the authenticity of each associated lane divider and its projective relationship with each initial dashed line segment. The present invention reduces the acquisition time and quality inspection time of dashed line segments in high-precision maps, greatly improving the efficiency of high-precision map production.

Description

Technical Field

[0001] The present invention belongs to the field of high-precision map data production, and in particular relates to a method and device for generating lane dashed line segments. Background Art

[0002] Dashed lines are printed dashed lines used in road lane markings and are typically composed of several continuous dashed segments. In autonomous driving, vehicles use vector features for map matching and positioning while driving. Manually collecting dashed line segments is time-consuming, while dashed line segment data generated using AI algorithms suffers from poor accuracy and missing data, requiring significant manual effort for quality inspection and modification, significantly impacting the efficiency of high-precision map production. Summary of the Invention

[0003] In order to improve the efficiency of producing dotted line segments in the process of high-precision map production, a first aspect of the present invention provides a method for generating lane dotted line segments, including: obtaining one or more lane separation lines of the target lane, the virtual-real change point of each lane separation line and AI dotted line segment data; extracting virtual-real change information from each lane separation line and its corresponding virtual-real change point, the virtual-real change information including shape and virtual-real attributes; segmenting the virtual-real change points within each lane separation line based on the virtual-real change information, and generating one or more initial dotted line segments; generating a dotted line block and a bounding box for each initial dotted line segment according to the direction of the lane separation line and each initial dotted line segment and its virtual-real change information; determining the associated lane separation line of each initial dotted line segment according to the dotted line block and the bounding box of each initial dotted line segment and the corresponding AI dotted line segment; optimizing the shape of the initial dotted line segment according to the authenticity of each associated lane separation line and its projection relationship with each initial dotted line segment.

[0004] In some embodiments of the present invention, generating a dotted line block and a bounding box for each initial dotted line segment based on the direction of the lane separation line, and each initial dotted line segment and its virtual-real change information includes: translating each initial dotted line segment to the left and right by a preset distance in the vertical direction, connecting the dotted line segments on the left and right sides after translation, and obtaining a dotted line block; taking all extreme points of the dotted line block on the coordinate axes of the world coordinate system to generate a bounding box.

[0005] In some embodiments of the present invention, determining the associated lane isolation line of each initial dotted line segment based on the dotted block and bounding box of each initial dotted line segment, and the corresponding AI dotted line segment includes: 5 determining whether the midpoint of each AI dotted line segment and the Z value from the first point of the AI ​​dotted line segment to the nearest dotted line block are within a preset interval; taking the shape of the AI ​​dotted line segment within the preset interval as the final dotted line segment, and taking the corresponding dotted line block associated lane isolation line as the final dotted line segment associated lane isolation line.

[0006] In some embodiments of the present invention, the authenticity of each associated lane separation line and its

[0007] The projection relationship with each initial dotted line segment, optimizing the shape of the initial dotted line segment includes: calculating the shortest distance dis from the first point of the dotted line segment to the lane isolation line; calculating the distance between the other points of the dotted line segment except the first point

[0008] The projection line to the lane isolation line is taken, and the shape point with a distance dis from the projection point on the extension line of each projection line to the lane isolation line is taken as the shape point of the dotted line segment; the angle between the dotted line segment and the line connecting the projection points on the lane isolation line is calculated, and the order of the dotted line segments is adjusted according to the angle.

[0009] Furthermore, the method further includes: if there is no real lane, then: taking the closest point from the beginning and end points of the dotted line to the lane separation line; calculating the distance between the closest point and the lane separation line according to the line connecting the closest point and the lane separation line.

[0010] The angle between the dashed line segment and the lane separation line is determined; and the association between the dashed line segment and the lane separation line is determined according to the size of the angle.

[0011] In the above embodiment, the segmentation of the virtual-real change points within each lane separation line based on the virtual-real change information and the generation of one or more initial dotted line segments includes: traversing the virtual-real change points within each lane separation line, and recording the shape information of each virtual-real change point and its distance to the lane separation line; determining one or more distance-based sorting sets within each lane separation line based on the shape information of multiple virtual-real change points and their distances to the lane separation line; segmenting the lane separation line based on the one or more distance-based sorting sets, and generating one or more initial dotted line segments.

[0012] The second aspect of the present invention provides a device for generating lane dashed line segments, comprising: obtaining a model

[0013] A block is used to obtain one or more lane separation lines of the target lane, the virtual-real change point of each lane separation line and the AI ​​dotted line segment data; the virtual-real change information is extracted from each lane separation line and its corresponding virtual-real change point, and the virtual-real change information includes shape and virtual-real attributes; a generation module is used to segment the virtual-real change points in each lane separation line based on the virtual-real change information and generate one or more initial dotted line segments; according to the direction of the lane separation line and each initial dotted line segment and its virtual-real change information, a dotted line block and a bounding box are generated for each initial dotted line segment; a determination module is used to determine the associated lane separation line of each initial dotted line segment based on the dotted line block and the bounding box of each initial dotted line segment and the corresponding AI dotted line segment; an optimization module is used to optimize the shape of the initial dotted line segment according to the authenticity of each associated lane separation line and its projection relationship with each initial dotted line segment.

[0014] The third aspect of the present invention provides an electronic device, comprising: one or more processors; a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the lane dashed line segment generation method provided in the first aspect of the present invention.

[0015] A fourth aspect of the present invention provides a computer-readable medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the lane dashed line segment generation method provided in the first aspect of the present invention is implemented.

[0016] The beneficial effects of the present invention are:

[0017] The present invention reduces the acquisition time and quality inspection time of dotted line segments in high-precision maps by combining the projection relationship between AI dotted line segments and traditional dotted line segments, thereby greatly improving the production efficiency of high-precision maps. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 A schematic diagram of a basic flow chart of a method for generating lane dashed line segments in some embodiments of the present invention;

[0019] Figure 2 A schematic diagram of a specific process of a method for generating lane dashed line segments in some embodiments of the present invention;

[0020] Figure 3 Schematic diagram of the structure of a lane dashed line segment generating device in some embodiments of the present invention;

[0021] Figure 4 Schematic diagram of the structure of an electronic device in some embodiments of the present invention. DETAILED DESCRIPTION

[0022] The principles and features of the present invention are described below with reference to the accompanying drawings. The examples given are only used to explain the present invention and are not used to limit the scope of the present invention.

[0023] refer to Figure 1 and Figure 2 In a first aspect of the present invention, a method for generating lane dashed line segments is provided, comprising: S100. obtaining one or more lane separation lines of a target lane, virtual-real change points of each lane separation line, and AI dashed line segment data; extracting virtual-real change information from each lane separation line and its corresponding virtual-real change point, wherein the virtual-real change information includes shape and virtual-real attributes; S200. segmenting the virtual-real change points within each lane separation line based on the virtual-real change information, and generating one or more initial dashed line segments; generating a dashed line block and a bounding box for each initial dashed line segment according to the direction of the lane separation line and each initial dashed line segment and its virtual-real change information; S300. determining the associated lane separation line of each initial dashed line segment according to the dashed line block and the bounding box of each initial dashed line segment, and the corresponding AI dashed line segment; S400. optimizing the shape of the initial dashed line segment according to the authenticity of each associated lane separation line and its projection relationship with each initial dashed line segment.

[0024] It can be understood that the AI ​​dotted line segment is obtained by recognizing or segmenting the 3D point cloud or image through a deep learning model.

[0025] In step S100 of the embodiment of the present disclosure, the segmentation of the virtual-real change points within each lane isolation line based on the virtual-real change information and the generation of one or more initial dotted line segments include: S101. Traversing the virtual-real change points within each lane isolation line, and recording the shape information of each virtual-real change point and its distance to the lane isolation line; specifically, reading the lane isolation line, lane isolation line change point, and AI dotted line segment data from the database.

[0026] Then, extract the valid information. For lane dividers, only the virtual-real, logical, and shape information is retained. Mark the first point of the lane divider as the virtual-real change point, recording the virtual-real, logical, and shape attributes, and setting the distance to the first point of the lane divider to 0. Traverse the lane divider change point data and select those whose change type includes a virtual-real change.

[0027] S102. Based on the shape information of multiple virtual-real change points and their distances to the lane dividers, determine one or more distance-based sorted sets within each lane divider; collect lane virtual-real change information. Traverse the lane dividers, traverse the virtual-real change points within the lane dividers, and record the distances and shape information of the change points to form a set that can be sorted by distance.

[0028] S103. Segment the lane divider based on the one or more distance-based sorted sets and generate one or more initial dashed line segments. Specifically, traverse the lane divider virtual-real change point distance shape set. If the set contains N+1 points, segment the lane divider starting from the 0th point and the first point until the last line segment. Only process the first point of the segmenting line with a dashed attribute, and record the virtual-real, logical, and shape of the first point of the segmenting line as the pre-generated dashed line segment.

[0029] In step S200 of some embodiments of the present invention, generating a dotted line block and a bounding box for each initial dotted line segment based on the direction of the lane separation line, and each initial dotted line segment and its virtual-real change information includes: S201. translating each initial dotted line segment to the left and right by a preset distance in the vertical direction, connecting the dotted line segments on the left and right sides after translation, and obtaining a dotted line block; S202. Taking all extreme points of the dotted line block on the coordinate axes of the world coordinate system to generate a bounding box.

[0030] Specifically, the segmentation logic of the dotted line segment. If the direction of the lane separation line is from left to right, take the segmentation point to the nearest projection point of the lane separation line, and record the point sequence on the left and right sides of the lane separation line. The shape of the pre-generated dotted line segment is: take the first segmentation point as the starting point, the first segmentation point is on the right side of the lane separation line projection point as the starting point, the middle part of the lane separation line is the middle point, the second segmentation point is on the left side of the lane separation line projection point as the end point. The vertical line of the pre-generated dotted line segment is translated 0.35m to the left and right in the distance direction, and the dotted line segments on the left and right sides after translation are connected to form a dotted line block, and the associated lane separation line is recorded. Take the maximum and minimum x, y (world coordinate system) of all the shape points of the dotted line block to generate a bounding box.

[0031] In step S300 of some embodiments of the present invention, determining the associated lane isolation line of each initial dotted line segment based on the dotted block and bounding box of each initial dotted line segment, and the corresponding AI dotted line segment includes: S301. Determining whether the midpoint of each AI dotted line segment and the Z value from the first point of the AI ​​dotted line segment to the nearest dotted line block are within a preset interval; S302. Taking the shape of the AI ​​dotted line segment within the preset interval as the final dotted line segment, and taking the corresponding dotted line block associated lane isolation line as the final dotted line segment associated lane isolation line.

[0032] Specifically, the lane separation lines associated with the AI ​​dashed line segments are collected. The AI ​​dashed line segments are traversed, and the midpoints of the AI ​​dashed line segments are collected. The midpoints of the AI ​​dashed line segments are within the dashed line block or the bounding box of the dashed line block, and the Z value difference between the first point of the AI ​​dashed line segment and the nearest point of the dashed line block is less than 5 meters. This shape is used as the final dashed line segment, and the lane separation lines associated with the corresponding dashed line block are collected as the final dashed line segment associated lane separation lines. It is understood that when a dashed line segment has only one associated lane separation line, that lane separation line is the lane separation line associated with the dashed line segment.

[0033] In step S400 of some embodiments of the present invention, the optimization of the shape of the initial dotted line segment based on the authenticity of each associated lane separation line and its projection relationship with each initial dotted line segment includes: S401. Calculating the shortest distance dis from the first point of the dotted line segment to the lane separation line; S402. Calculating the projection lines of other points of the dotted line segment except the first point to the lane separation line, and taking the shape points on the extension line of each projection line with a distance dis from the lane separation line as the shape points of the dotted line segment; S403. Calculating the angle between the dotted line segment and the line connecting the projection points on the lane separation line, and adjusting the order of the dotted line segments according to the angle.

[0034] Specifically, the shortest distance from the first point of the dashed line segment to the lane divider is recorded as dis, and the projection line from the other points of the dashed line segment to the lane divider is calculated. The shape point on the extended projection line with the distance dis from the projection point to the lane divider is taken as the shape point of the dashed line segment. Calculate the angle between the dashed line segment and the line connecting the projection point on the lane divider. If it exceeds 180°, it means that the dashed line segment and the lane divider are in opposite directions, and the dashed line segment is adjusted in reverse order. When there are multiple lanes and only one lane has a logical attribute of real, then the real lane is the lane associated with the dashed line segment;

[0035] Furthermore, it also includes: if there is no real lane, then: take the nearest point of the first and last points of the dashed line segment to the lane separation line; calculate the angle between the line and the lane separation line based on the line connecting the nearest point and the lane separation line; and determine the association between the dashed line segment and the lane separation line based on the size of the angle. Specifically, when there is no real lane or multiple real lanes, take the nearest point of the first and last points of the dashed line segment to the lane separation line, calculate the angle based on the line connecting the nearest points and the lane separation line, and collect and sort the lane separation lines corresponding to the angle; filter out lane separation lines with inconsistent directions, that is, those with angles greater than 180. If there is a lane, associate the lane; the dashed line segment shape optimization is the same as S403. If there are still multiple lanes, take the first two lanes for association; the dashed line segment shape optimization is shown in S404.

[0036] S404. Optimize the shape of the dashed line segment. Calculate the projection points of the dashed line segment's first and last points onto the lane divider. If two projection points exist on two lines, select the midpoint of the projection of the first point of the two lines as the dashed line segment's starting point, and the midpoint of the projection of the last point of the two lines as the dashed line segment's ending point. If only one line has two projection points, adjust the dashed line segment shape based on that line, referring to step S403. If each line has only one projection point, no adjustment is made to the dashed line segment shape.

[0037] In one embodiment of the present invention, the data used in the present invention is high-precision Figure 3Dimensional data is stored in a Postgres database. The generation of dashed line segment solutions is essential after the manual completion of lane dividers, lane divider virtual-real transition points, and AI dashed line blocks. Failure to do so may result in missing dashed line segment data and inaccurate position matching.

[0038] Step 1: Read lane dividers, lane divider change points, and AI dashed line segment data.

[0039] Step 2: Mark the first point of the lane separation line as the virtual-real change point and collect all virtual-real change points.

[0040] Step 3: Generate a dotted line block based on the lane separation line.

[0041] Step 4: Combine the lane separation line, dashed line block, and AI dashed line segment to generate the final dashed line segment and the relationship between the dashed line segment and the lane separation line.

[0042] Example 2

[0043] refer to Figure 3 In a second aspect of the present invention, a device 1 for generating lane dashed line segments is provided, comprising: an acquisition module 11 for acquiring one or more lane separation lines of a target lane, virtual-real change points of each lane separation line, and AI dashed line segment data; extracting virtual-real change information from each lane separation line and its corresponding virtual-real change point, wherein the virtual-real change information includes shape and virtual-real attributes; a generation module 12 for segmenting the virtual-real change points within each lane separation line based on the virtual-real change information, and generating one or more initial dashed line segments; generating a dashed line block and a bounding box for each initial dashed line segment according to the direction of the lane separation line and each initial dashed line segment and its virtual-real change information; a determination module 13 for determining the associated lane separation line of each initial dashed line segment based on the dashed line block and the bounding box of each initial dashed line segment, and the corresponding AI dashed line segment; an optimization module 14 for optimizing the shape of the initial dashed line segment according to the authenticity of each associated lane separation line and its projection relationship with each initial dashed line segment.

[0044] Furthermore, the generation module 12 includes: a translation unit, which is used to translate each initial dotted line segment to the left and right by a preset distance in the vertical direction, connect the dotted line segments on the left and right sides after translation, and obtain a dotted line block; a generation unit, which is used to take all extreme points of the dotted line block on the coordinate axis of the world coordinate system to generate a bounding box.

[0045] Example 3

[0046] refer to Figure 4According to the third aspect of the present invention, an electronic device is provided, comprising: one or more processors; a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method according to the first aspect of the present invention.

[0047] The electronic device 500 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 501, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 502 or a program loaded from a storage device 508 into a random access memory (RAM) 503. Various programs and data required for the operation of the electronic device 500 are also stored in the RAM 503. The processing device 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0048] Typically, the following devices may be connected to the I / O interface 505: an input device 506 including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 507 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 508 including, for example, a hard disk, etc.; and a communication device 509. The communication device 509 may allow the electronic device 500 to communicate with other devices wirelessly or by wire to exchange data. Figure 4 The electronic device 500 is shown with various devices, but it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed instead. Figure 4 Each block shown in the figure may represent one device, or may represent multiple devices as needed.

[0049] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication device 509, or installed from the storage device 508, or installed from the ROM 502. When the computer program is executed by the processing device 501, the above-mentioned functions defined in the method of the embodiment of the present disclosure are executed. It should be noted that the computer-readable medium described in the embodiment of the present disclosure can be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection having one or more conductors, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In embodiments of the present disclosure, a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In embodiments of the present disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal may take a variety of forms, including, but not limited to, an electromagnetic signal, an optical signal, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transfer a program for use by or in conjunction with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wire, optical cable, RF (radio frequency), etc., or any suitable combination thereof.

[0050] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device. The computer-readable medium carries one or more computer programs, which, when executed by the electronic device, cause the electronic device to:

[0051] Computer program code for performing the operations of embodiments of the present disclosure may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, Python, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0052] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or a part of code, and the module, program segment, or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should be noted that each box in the block diagram and / or flowchart, and the combination of the boxes in the block diagram and / or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0053] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for generating lane dashed line segments, characterized in that: include: Obtain one or more lane dividers of the target lane, the virtual / real change points of each lane divider, and AI dashed line segment data; Extracting virtual-real change information from each lane separation line and its corresponding virtual-real change point, wherein the virtual-real change information includes shape and virtual-real attributes; Segmenting the virtual-real change points within each lane separation line based on the virtual-real change information, and generating one or more initial dotted line segments; Generate a dotted line block and bounding box for each initial dotted line segment based on the direction of the lane divider and the information about each initial dotted line segment and its virtual-real change. Determine the associated lane separation line for each initial dashed line segment based on the dashed block and bounding box of each initial dashed line segment and the corresponding AI dashed line segment; According to the authenticity of each associated lane separation line and its projection relationship with each initial dashed line segment, the shape of the initial dashed line segment is optimized.

2. The method for generating lane dashed line segments according to claim 1, characterized in that: Generating a dotted line block and a bounding box for each initial dotted line segment according to the direction of the lane separation line and each initial dotted line segment and its virtuality-reality change information includes: Each initial dotted line segment is translated to the left and right by a preset distance in the perpendicular direction, and the dotted line segments on the left and right sides after translation are connected to obtain a dotted line block; Take all the extreme points of the dotted block on the coordinate axis of the world coordinate system and generate a bounding box.

3. The method for generating lane dashed line segments according to claim 1, characterized in that: Determining the associated lane isolation line of each initial dotted line segment based on the dotted line block and bounding box of each initial dotted line segment and the corresponding AI dotted line segment includes: Determine whether the midpoint of each AI dashed line segment and the Z value from the first point of the AI ​​dashed line segment to the nearest dashed line block are within the preset range; The shape of the AI ​​dotted line segment within the preset interval is used as the final dotted line segment, and the corresponding dotted line block associated lane isolation line is used as the final dotted line segment associated lane isolation line.

4. The method for generating lane dashed line segments according to claim 1, characterized in that: Optimizing the shape of the initial dashed line segment according to the authenticity of each associated lane separation line and its projection relationship with each initial dashed line segment includes: Calculate the shortest distance dis from the first point of the dashed line segment to the lane separation line; Calculate the projection lines of the dashed line segment from all points except the first point to the lane divider, and take the shape point with a distance dis from the projection point on the extended line of each projection line to the lane divider as the shape point of the dashed line segment; The angle between the dashed line segment and the line connecting the projection points on the lane divider is calculated, and the order of the dashed line segments is adjusted according to the angle.

5. The method for generating lane dashed line segments according to claim 4, characterized in that: Also includes: If there is no real lane, then: Take the closest point between the first and last points of the dashed line segment and the lane separation line; Calculating the angle between the line connecting the closest point and the lane dividing line; The association between the dotted line segment and the lane separation line is determined based on the size of the included angle.

6. The method for generating lane dashed line segments according to any one of claims 1 to 5, characterized in that: The segmenting of the virtual-real change points within each lane separation line based on the virtual-real change information and generating one or more initial dotted line segments includes: Traverse the virtual-real change points within each lane separation line and record the shape information of each virtual-real change point and its distance to the lane separation line; Determine one or more distance-based sorting sets within each lane separation line based on shape information of multiple virtual-real change points and their distances to the lane separation lines; The lane divider is segmented according to the one or more distance-based sorted sets, and one or more initial dashed line segments are generated.

7. A device for generating lane dashed line segments, characterized in that: include: An acquisition module is used to obtain one or more lane separation lines of the target lane, the virtual-real change points of each lane separation line, and AI dotted line segment data; Extracting virtual-real change information from each lane separation line and its corresponding virtual-real change point, wherein the virtual-real change information includes shape and virtual-real attributes; A generation module, configured to segment the virtual-real change points within each lane separation line based on the virtual-real change information, and generate one or more initial dotted line segments; Generate a dotted line block and bounding box for each initial dotted line segment based on the direction of the lane divider and the information about each initial dotted line segment and its virtual-real change. A determination module, configured to determine an associated lane separation line for each initial dashed line segment based on the dashed line block and bounding box of each initial dashed line segment and the corresponding AI dashed line segment; The optimization module is used to optimize the shape of the initial dashed line segment according to the authenticity of each associated lane separation line and its projection relationship with each initial dashed line segment.

8. The device for generating lane dashed line segments according to claim 7, characterized in that: The generation module includes: A translation unit is used to translate each initial dashed line segment to the left and right by a preset distance in the perpendicular direction, and connect the dashed line segments on the left and right sides after translation to obtain a dashed line block; The generation unit is used to obtain all extreme points of the dotted line block on the coordinate axis of the world coordinate system and generate a bounding box.

9. An electronic device comprising: one or more processors; A storage device for storing one or more programs, when the one or more programs are executed by the one or more processors, so that the one or more processors implement the method for generating lane dashed line segments as described in any one of claims 1 to 6.

10. A computer-readable medium having a computer program stored thereon, wherein: When the computer program is executed by a processor, the method for generating lane dashed line segments according to any one of claims 1 to 6 is implemented.

Images