CN116091645A - Method and device for generating virtual line segment of lane - Google Patents
Method and device for generating virtual line segment of lane Download PDFInfo
- Publication number
- CN116091645A CN116091645A CN202211742046.1A CN202211742046A CN116091645A CN 116091645 A CN116091645 A CN 116091645A CN 202211742046 A CN202211742046 A CN 202211742046A CN 116091645 A CN116091645 A CN 116091645A
- Authority
- CN
- China
- Prior art keywords
- virtual
- line
- lane
- line segment
- segment
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T11/00—2D [Two Dimensional] image generation
- G06T11/20—Drawing from basic elements, e.g. lines or circles
- G06T11/203—Drawing of straight lines or curves
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T1/00—General purpose image data processing
- G06T1/20—Processor architectures; Processor configuration, e.g. pipelining
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to a method and a device for generating a lane dotted line segment, wherein the method comprises the following steps: acquiring one or more lane isolation lines of a target lane, virtual-real change points of each lane isolation line and AI broken line segment data; extracting virtual-real change information from each lane isolation line and corresponding virtual-real change points; dividing virtual and real change points in each lane isolation line based on the virtual and real change information, and generating an initial virtual line segment; generating a broken line block and a bounding box of each initial broken line segment according to the direction of the lane isolation line; determining an associated lane isolation line of each initial virtual line segment according to the dotted line blocks and bounding boxes of each initial virtual line segment and the corresponding AI virtual line segments; and optimizing the shape of each initial virtual line segment according to the authenticity of each associated lane isolation line and the projection relation between each associated lane isolation line and each initial virtual line segment. The invention reduces the acquisition time and quality inspection time of the virtual line segments in the high-precision map, and greatly improves the manufacturing efficiency of the high-precision map.
Description
Technical Field
The invention belongs to the field of high-precision map data production, and particularly relates to a method and a device for generating a lane virtual line segment.
Background
The dashed line segment is a printed line of the type where the road lane markings are dashed, and is generally made up of several consecutive dashed line segments. In automatic driving, the vehicle uses vector elements for map matching positioning during running. The manual collection of the broken line segment needs to consume a large amount of time, and the data of the broken line segment generated by using the AI algorithm has the problems of poor precision, missing and the like, and needs to consume a large amount of manual time to take and carry out quality inspection modification and other works, so that the efficiency of high-precision map making is greatly influenced.
Disclosure of Invention
In order to improve the manufacturing efficiency of a broken line segment in the process of manufacturing a high-precision map, the first aspect of the invention provides a method for generating a lane broken line segment, which comprises the following steps: acquiring one or more lane isolation lines of a target lane, virtual-real change points of each lane isolation line and AI broken line segment data; extracting virtual-real change information from each lane isolation line and corresponding virtual-real change points, wherein the virtual-real change information comprises a shape and virtual-real attributes; dividing virtual-real change points in each lane isolation line based on the virtual-real change information, and generating one or more initial virtual line segments; generating a dotted line block and a bounding box of each initial virtual line segment according to the direction of the lane isolation line and the virtual-real change information of each initial virtual line segment; determining an associated lane isolation line of each initial virtual line segment according to the dotted line blocks and bounding boxes of each initial virtual line segment and the corresponding AI virtual line segments; and optimizing the shape of each initial virtual line segment according to the authenticity of each associated lane isolation line and the projection relation between each associated lane isolation line and each initial virtual line segment.
In some embodiments of the present invention, the generating the dashed line block and bounding box of each initial virtual line segment according to the direction of the lane-dividing line and the virtual-real variation information of each initial virtual line segment includes: translating left and right sides of the perpendicular line direction of each initial virtual line segment by a preset distance, and connecting the translated virtual line segments on the left side and the right side to obtain a virtual line block; and taking all extreme points of the dotted line block on the coordinate axis of the world coordinate system to generate a bounding box.
In some embodiments of the present invention, the determining the associated lane-isolation line of each initial virtual line segment according to the dashed line block and bounding box of each initial virtual line segment and the corresponding AI virtual line segment includes: 5, determining the midpoint of each AI virtual line segment and whether the Z value from the first point of the AI virtual line segment to the nearest virtual line block is in a preset interval; and taking the shape of the AI virtual line segment in the preset interval as a final virtual line segment, and taking the lane isolation line associated with the corresponding virtual line block as the lane isolation line associated with the final virtual line segment.
In some embodiments of the invention, the method is based on the authenticity of each associated lane isolation line and its
The optimizing of the shape of each initial virtual line segment according to the projection relation of the initial virtual line segment comprises the following steps: calculating the shortest distance dis from the first point of the virtual line segment to the lane isolation line; calculating other points of the virtual line segment except the first point
Projection lines reaching the lane isolation lines, and taking the shape points of which the distance from the projection points on each projection line extension line to the lane isolation lines is dis as the shape points of the virtual line segments; and calculating an included angle between the virtual line segment and the connecting line of the projection points on the lane isolation line, and adjusting the sequence of the virtual line segment according to the included angle.
Further, the method further comprises the following steps: if there is no real lane, then: taking the closest point of the distance from the head point and the tail point of the broken line section to the lane separation 5 in an offline manner; calculating the connection line according to the connection line of the closest point of the distance and the lane isolation line
The included angle between the line and the lane isolation line; and judging the association of the virtual line segment and the lane isolation line according to the magnitude of the included angle.
In the foregoing embodiment, the dividing the virtual-real change point in each lane isolation line based on the virtual-real change information, and generating one or more initial virtual line segments includes: traversing virtual and real change points in the off-line of each lane interval 0, and recording the shape information of each virtual and real change point and the distance between each virtual and real change point and a lane isolation line; determining one or more distance-based sorting sets in each lane isolation line according to shape information of a plurality of virtual-real change points and distances from the virtual-real change points to the lane isolation line; and dividing the lane isolation line according to the one or more distance-based sorting sets, and generating one or more initial virtual line segments.
5 a second aspect of the present invention provides an apparatus for lane-broken line segment generation, comprising: acquisition die
The block is used for acquiring one or more lane isolation lines of a target lane, virtual-real change points of each lane isolation line and AI broken line segment data; extracting virtual-real change information from each lane isolation line and corresponding virtual-real change points, wherein the virtual-real change information comprises a shape and virtual-real attributes; the generating module is used for dividing virtual-real change points in each lane isolation line based on the virtual-real change information and generating one or more initial virtual line segments; generating a dotted line block and a bounding box of each initial virtual line segment according to the direction of the lane isolation line and the virtual-real change information of each initial virtual line segment; the determining module is used for determining the associated lane isolation line of each initial virtual line segment according to the dotted line block and the bounding box of each initial virtual line segment and the corresponding AI virtual line segment; and the optimization module is used for optimizing the shape of each initial virtual line segment according to the authenticity of each associated lane isolation line and the projection relation between each associated lane isolation line and each initial virtual line segment.
In a third aspect of the present invention, there is provided an electronic apparatus comprising: one or more processors; and a storage device for storing one or more programs, which when executed by the one or more processors, cause the one or more processors to implement the lane-broken line segment generation method provided in the first aspect of the present invention.
In a fourth aspect of the present invention, there is provided a computer readable medium having stored thereon a computer program, wherein the computer program, when executed by a processor, implements the lane-broken-line segment generating method provided in the first aspect of the present invention.
The beneficial effects of the invention are as follows:
the invention reduces the acquisition time and quality inspection time of the virtual line segments in the high-precision map by combining the projection relation of the AI virtual line segments and the traditional virtual line segments, and greatly improves the manufacturing efficiency of the high-precision map.
Drawings
FIG. 1 is a basic flow diagram of a method of lane segment generation in some embodiments of the invention;
FIG. 2 is a flow chart of a method of generating a lane segment according to some embodiments of the present invention;
FIG. 3 is a schematic diagram of a lane-broken-line segment generating apparatus according to some embodiments of the present invention;
fig. 4 is a schematic structural diagram of an electronic device according to some embodiments of the present invention.
Detailed Description
The principles and features of the present invention are described below with reference to the drawings, the examples are illustrated for the purpose of illustrating the invention and are not to be construed as limiting the scope of the invention.
Referring to fig. 1 and 2, in a first aspect of the present invention, there is provided a method for generating a lane virtual line segment, including: s100, acquiring one or more lane isolation lines of a target lane, virtual-real change points of each lane isolation line and AI broken line segment data; extracting virtual-real change information from each lane isolation line and corresponding virtual-real change points, wherein the virtual-real change information comprises a shape and virtual-real attributes; s200, dividing virtual-real change points in each lane isolation line based on the virtual-real change information, and generating one or more initial virtual line segments; generating a dotted line block and a bounding box of each initial virtual line segment according to the direction of the lane isolation line and the virtual-real change information of each initial virtual line segment; s300, determining an associated lane isolation line of each initial virtual line segment according to the dotted line block and the bounding box of each initial virtual line segment and the corresponding AI virtual line segment; s400, optimizing the shape of each initial virtual line segment according to the authenticity of each associated lane isolation line and the projection relation between each associated lane isolation line and each initial virtual line segment.
It can be understood that the AI virtual line segments are obtained by identifying or dividing and reasoning the 3D point cloud or the image through a deep learning model.
In step S100 of the embodiment of the present disclosure, the dividing the virtual-actual change points in each lane isolation line based on the virtual-actual change information, and generating one or more initial virtual line segments includes: s101, traversing virtual and real change points in each lane isolation line, and recording shape information of each virtual and real change point and the distance between each virtual and real change point and each lane isolation line; specifically, lane departure line change point, AI broken line segment data are read from the database.
Then, valid information is extracted. The lane isolation lines only retain virtual-real, logical and shape information. And marking the first point of the lane isolation line as a virtual-real change point, and recording the attribute virtual-real, logic, shape and the distance from the first point of the lane isolation line as 0. And traversing the lane isolation line change point data, and taking the change type containing virtual-real change.
S102, determining one or more distance-based sorting sets in each lane isolation line according to shape information of a plurality of virtual-real change points and distances from the virtual-real change points to the lane isolation line; and collecting the virtual-real change information of the lane. And traversing the lane isolation line, internally traversing virtual and real change points of the lane isolation line, and recording the distance of the change points and the point shape information to form a set which can be ordered according to the distance.
S103, dividing the lane isolation lines according to the one or more distance-based sorting sets, and generating one or more initial virtual line segments. Specifically, traversing a set of virtual-real change point distance shapes of the lane isolation line, if the set contains n+1 points, dividing the lane isolation line from the 0 th point and the first point until the last line segment, only processing the first point attribute of the cutting line as a broken line, and recording the virtual-real, logic and shape of the first point of the cutting line as a pre-generated broken line segment.
In step S200 of some embodiments of the present invention, the generating the dashed line block and bounding box of each initial virtual line segment according to the direction of the lane-dividing line and the virtual-real variation information of each initial virtual line segment includes: s201, translating left and right sides of the perpendicular line direction of each initial virtual line segment by a preset distance, and connecting the translated virtual line segments on the left side and the right side to obtain a virtual line block; s202, taking all extreme points of the dotted line block on coordinate axes of a world coordinate system, and generating a bounding box.
Specifically, the segmentation logic of the virtual line segments. If the direction of the lane isolation line is from left to right, taking the closest projection point from the dividing point to the lane isolation line, and recording the point sequences at the left side and the right side of the lane isolation line. The pre-generated dotted line segment shape is: the first division point is taken as a starting point, the first division point is taken as a starting point at the right side point of the projection point of the lane isolation line, the middle part of the lane isolation line is taken as a middle point, the second division point is taken as an ending point at the left side point of the projection point of the lane isolation line, and the second division point is taken as an ending point. The vertical line of the pre-generated broken line segment is shifted by 0.35m to the left and right, the broken line segments on the left and right sides after the shifting are connected to form broken line blocks, and the associated lane isolation lines are recorded. And taking the maximum and minimum x and y (world coordinate system) of all the shape points of the dotted line block to generate a bounding box.
In step S300 of some embodiments of the present invention, the determining the associated lane-isolating line of each initial virtual line segment according to the dashed line block and bounding box of each initial virtual line segment and the corresponding AI virtual line segment includes: s301, determining the middle point of each AI virtual line segment and whether the Z value from the first point of the AI virtual line segment to the nearest virtual line block is in a preset interval; s302, taking the shape of an AI virtual line segment in a preset interval as a final virtual line segment, and taking a lane isolation line associated with a corresponding virtual line block as a lane isolation line associated with the final virtual line segment.
Specifically, AI dashed line segment-associated lane-separation lines are collected. And traversing the AI virtual line segment, collecting that the midpoint of the AI virtual line segment is in the range of the broken line block or the bounding box of the broken line block, and the Z value difference from the first point of the AI virtual line segment to the nearest point of the broken line block is less than 5 meters, taking the shape of the AI virtual line segment as a final virtual line segment, and collecting the lane isolation line associated with the corresponding broken line block as the lane isolation line associated with the final broken line segment. It will be appreciated that when only one lane departure line is associated with a dashed segment, then the lane departure line is the lane departure line associated with the dashed segment.
In step S400 of some embodiments of the present invention, the optimizing the shape of each initial virtual line segment according to the authenticity of each associated lane isolation line and the projection relationship thereof with each initial virtual line segment includes: s401, calculating the shortest distance dis from the first point of the virtual line segment to the lane isolation line; s402, calculating projection lines from other points of the virtual line segment except the first point to the lane isolation line, and taking a shape point with the distance dis from the projection point on each projection line extension line to the lane isolation line as the shape point of the virtual line segment; s403, calculating an included angle between the virtual line segment and a connecting line of projection points on the lane isolation line, and adjusting the sequence of the virtual line segment according to the included angle.
Specifically, the shortest distance from the first point of the virtual line segment to the lane isolation line is recorded as dis, projection lines from other points of the virtual line segment to the lane isolation line are calculated, and the shape point with the distance from the projection point on the projection line extension line to the lane isolation line being dis is taken as the shape point of the virtual line segment. And calculating the included angle between the virtual line segment and the connecting line of the projection point on the lane isolation line, and if the included angle exceeds 180 degrees, indicating that the virtual line segment is opposite to the lane isolation line, and carrying out reverse order adjustment on the virtual line segment. When a plurality of lanes exist and only one logic attribute is a real lane, the real lane is a lane associated with a broken line section;
further, the method further comprises the following steps: if there is no real lane, then: taking the closest point from the head point and the tail point of the broken line section to a lane isolation line; calculating an included angle between the connecting line and the lane isolation line according to the connecting line between the closest point of the distance and the lane isolation line; and judging the association of the virtual line segment and the lane isolation line according to the magnitude of the included angle. Specifically, when no real lane or multiple real lanes exist, the head and tail points of the dotted line segments are taken as closest points to the lane isolation lines, an included angle is calculated by combining the closest point connection lines and the lane isolation lines, and the included angles are collected and sequenced corresponding to the lane isolation lines; and filtering lane isolation lines inconsistent with the lane isolation lines, namely, the included angle is larger than 180. If one lane exists, associating the lanes; the shape optimization of the virtual line segment is the same as S403. If a plurality of lanes still exist, the first two lanes are taken for association; dotted segment shape optimization is seen at S404.
S404, optimizing the shape of the broken line segment. Calculating projection points from the head and tail points of the virtual line segment to the lane isolation line; if two projection points exist on the two lines, selecting the midpoint of the projection points of the first point of the two lines as the starting point of the broken line segment and the midpoint of the projection points of the last point as the tail point of the broken line segment; if there are two projection points on only one line, the dashed line segment shape is rounded up in step S403 based on the line; or there is only one proxel per line, no adjustment is made to the dashed segment shape.
In one embodiment of the invention, the data used in the invention is high-precision map three-dimensional data, stored in a Postgres database. The virtual line segment generation scheme is inexperienced after the lane isolation line, the virtual-real change point of the lane isolation line and the AI broken line block are completed manually, otherwise, the problems of broken line segment data deletion, inaccurate position matching and the like can be caused.
Step one: and reading lane separation lines, lane separation line change points and AI broken line segment data.
Step two: and marking the first point of the lane isolation line as a virtual-real change point, and collecting all virtual-real change points.
Step three: a broken line block is generated in conjunction with the lane departure line.
Step four: and combining the lane isolation line, the dotted line block and the AI dotted line segment to generate a final dotted line segment and the association relation between the dotted line segment and the lane isolation line.
Example 2
Referring to fig. 3, in a second aspect of the present invention, there is provided an apparatus 1 for lane-broken line segment generation, comprising: the acquisition module 11 is used for acquiring one or more lane isolation lines of a target lane, virtual-real change points of each lane isolation line and AI broken line segment data; extracting virtual-real change information from each lane isolation line and corresponding virtual-real change points, wherein the virtual-real change information comprises a shape and virtual-real attributes; the generating module 12 is configured to segment virtual-real change points in each lane isolation line based on the virtual-real change information, and generate one or more initial virtual line segments; generating a dotted line block and a bounding box of each initial virtual line segment according to the direction of the lane isolation line and the virtual-real change information of each initial virtual line segment; the determining module 13 is configured to determine an associated lane isolation line of each initial virtual line segment according to the dashed line block and the bounding box of each initial virtual line segment and the corresponding AI virtual line segment; the optimizing module 14 is configured to optimize the shape of each initial virtual line segment according to the authenticity of each associated lane isolation line and the projection relationship between the associated lane isolation line and each initial virtual line segment.
Further, the generating module 12 includes: the translation unit is used for translating the left and right preset distances in the vertical direction of each initial virtual line segment respectively, connecting the virtual line segments on the left side and the right side after translation, and obtaining a virtual line block; and the generating unit is used for taking all extreme points of the dotted line block on the coordinate axis of the world coordinate system and generating a bounding box.
Example 3
Referring to fig. 4, a third aspect of the present invention provides an electronic device, including: one or more processors; and storage means for storing one or more programs which, when executed by the one or more processors, cause the one or more processors to implement the method of the present invention in the first aspect.
The electronic device 500 may include a processing means (e.g., a central processing unit, a graphics processor, etc.) 501 that may perform various appropriate actions and processes in accordance with programs stored in a Read Only Memory (ROM) 502 or loaded from a storage 508 into a Random Access Memory (RAM) 503. In the RAM503, various programs and data required for the operation of the electronic apparatus 500 are also stored. The processing device 501, the ROM502, and the RAM503 are connected to each other via a bus 504. An input/output (I/O) interface 505 is also connected to bus 504.
The following devices may be connected to the I/O interface 505 in general: input devices 506 including, for example, a touch screen, touchpad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; an output device 507 including, for example, a Liquid Crystal Display (LCD), a speaker, a vibrator, and the like; storage 508 including, for example, a hard disk; and communication means 509. The communication means 509 may allow the electronic device 500 to communicate with other devices wirelessly or by wire to exchange data. While fig. 4 shows an electronic device 500 having various means, it is to be understood that not all of the illustrated means are required to be implemented or provided. More or fewer devices may be implemented or provided instead. Each block shown in fig. 4 may represent one device or a plurality of devices as needed.
In particular, according to embodiments of the present disclosure, the processes described above with reference to flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method shown in the flowcharts. In such an embodiment, the computer program may be downloaded and installed from a network via the communication means 509, or from the storage means 508, or from the ROM 502. The above-described functions defined in the methods of the embodiments of the present disclosure are performed when the computer program is executed by the processing device 501. It should be noted that the computer readable medium described in the embodiments of the present disclosure may be a computer readable signal medium or a computer readable storage medium or any combination of the two. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In an embodiment of the present disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. Whereas in embodiments of the present disclosure, the computer-readable signal medium may comprise a data signal propagated in baseband or as part of a carrier wave, with computer-readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection 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: electrical wires, fiber optic cables, RF (radio frequency), and the like, or any suitable combination of the foregoing.
The computer readable medium may be contained in the electronic device; or may exist alone 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:
computer program code for carrying out operations of embodiments of the present disclosure may be written in one or more programming languages, including an object oriented programming language such as Java, smalltalk, C ++, python and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (for example, through the Internet using an Internet service provider).
The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The foregoing description of the preferred embodiments of the invention is not intended to limit the invention to the precise form disclosed, and any such modifications, equivalents, and alternatives falling within the spirit and scope of the invention are intended to be included within the scope of the invention.
Claims (10)
1. A method of lane-line segment generation, comprising:
acquiring one or more lane isolation lines of a target lane, virtual-real change points of each lane isolation line and AI broken line segment data; extracting virtual-real change information from each lane isolation line and corresponding virtual-real change points, wherein the virtual-real change information comprises a shape and virtual-real attributes;
dividing virtual-real change points in each lane isolation line based on the virtual-real change information, and generating one or more initial virtual line segments; generating a dotted line block and a bounding box of each initial virtual line segment according to the direction of the lane isolation line and the virtual-real change information of each initial virtual line segment;
determining an associated lane isolation line of each initial virtual line segment according to the dotted line blocks and bounding boxes of each initial virtual line segment and the corresponding AI virtual line segments;
and optimizing the shape of each initial virtual line segment according to the authenticity of each associated lane isolation line and the projection relation between each associated lane isolation line and each initial virtual line segment.
2. The method for generating a virtual lane segment according to claim 1, wherein the generating a virtual line block and bounding box of each initial virtual line segment according to the direction of the lane-dividing line and the virtual-real variation information of each initial virtual line segment comprises:
translating left and right sides of the perpendicular line direction of each initial virtual line segment by a preset distance, and connecting the translated virtual line segments on the left side and the right side to obtain a virtual line block;
and taking all extreme points of the dotted line block on the coordinate axis of the world coordinate system to generate a bounding box.
3. The method of generating lane-line segments according to claim 1, wherein determining the associated lane-isolation line of each initial virtual line segment based on the dashed blocks and bounding boxes of each initial virtual line segment and the corresponding AI virtual line segment comprises:
determining the midpoint of each AI virtual line segment and whether the Z value from the first point of the AI virtual line segment to the nearest virtual line block is in a preset interval;
and taking the shape of the AI virtual line segment in the preset interval as a final virtual line segment, and taking the lane isolation line associated with the corresponding virtual line block as the lane isolation line associated with the final virtual line segment.
4. The method of generating a lane segment according to claim 1, wherein optimizing the shape of each initial segment according to the authenticity of each associated lane-isolating line and the projection relationship thereof with each initial segment comprises:
calculating the shortest distance dis from the first point of the virtual line segment to the lane isolation line;
calculating projection lines from other points of the virtual line segment except the first point to the lane isolation line, and taking the shape point with the distance dis from the projection point on each projection line extension line to the lane isolation line as the shape point of the virtual line segment;
and calculating an included angle between the virtual line segment and the connecting line of the projection points on the lane isolation line, and adjusting the sequence of the virtual line segment according to the included angle.
5. The method of lane segment generation according to claim 4, further comprising:
if there is no real lane, then:
taking the closest point from the head point and the tail point of the broken line section to a lane isolation line;
calculating an included angle between the connecting line and the lane isolation line according to the connecting line between the closest point of the distance and the lane isolation line;
and judging the association of the virtual line segment and the lane isolation line according to the magnitude of the included angle.
6. The method according to any one of claims 1 to 5, wherein the dividing virtual-real change points in each lane-dividing line based on the virtual-real change information, and generating one or more initial virtual line segments includes:
traversing virtual and real change points in each lane isolation line, and recording shape information of each virtual and real change point and the distance between each virtual and real change point and the lane isolation line;
determining one or more distance-based sorting sets in each lane isolation line according to shape information of a plurality of virtual-real change points and distances from the virtual-real change points to the lane isolation line;
and dividing the lane isolation line according to the one or more distance-based sorting sets, and generating one or more initial virtual line segments.
7. An apparatus for lane-line segment generation, comprising:
the acquisition module is used for acquiring one or more lane isolation lines of a target lane, virtual-real change points of each lane isolation line and AI broken line segment data; extracting virtual-real change information from each lane isolation line and corresponding virtual-real change points, wherein the virtual-real change information comprises a shape and virtual-real attributes;
the generating module is used for dividing virtual-real change points in each lane isolation line based on the virtual-real change information and generating one or more initial virtual line segments; generating a dotted line block and a bounding box of each initial virtual line segment according to the direction of the lane isolation line and the virtual-real change information of each initial virtual line segment;
the determining module is used for determining the associated lane isolation line of each initial virtual line segment according to the dotted line block and the bounding box of each initial virtual line segment and the corresponding AI virtual line segment;
and the optimization module is used for optimizing the shape of each initial virtual line segment according to the authenticity of each associated lane isolation line and the projection relation between each associated lane isolation line and each initial virtual line segment.
8. The apparatus for lane-broken segment generation according to claim 7, wherein the generation module includes:
the translation unit is used for translating the left and right preset distances in the vertical direction of each initial virtual line segment respectively, connecting the virtual line segments on the left side and the right side after translation, and obtaining a virtual line block;
and the generating unit is used for taking all extreme points of the dotted line block on the coordinate axis of the world coordinate system and generating a bounding box.
9. An electronic device, comprising: one or more processors; storage means for storing one or more programs which, when executed by the one or more processors, cause the one or more processors to implement the method of lane segment generation as claimed in any one of claims 1 to 6.
10. A computer readable medium having stored thereon a computer program, wherein the computer program when executed by a processor implements the method of lane segment generation according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211742046.1A CN116091645A (en) | 2022-12-29 | 2022-12-29 | Method and device for generating virtual line segment of lane |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211742046.1A CN116091645A (en) | 2022-12-29 | 2022-12-29 | Method and device for generating virtual line segment of lane |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116091645A true CN116091645A (en) | 2023-05-09 |
Family
ID=86207665
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211742046.1A Pending CN116091645A (en) | 2022-12-29 | 2022-12-29 | Method and device for generating virtual line segment of lane |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116091645A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117152299A (en) * | 2023-10-27 | 2023-12-01 | 腾讯科技（深圳）有限公司 | Lane dotted line rendering method, device, equipment, storage medium and program product |
-
2022
- 2022-12-29 CN CN202211742046.1A patent/CN116091645A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117152299A (en) * | 2023-10-27 | 2023-12-01 | 腾讯科技（深圳）有限公司 | Lane dotted line rendering method, device, equipment, storage medium and program product |
| CN117152299B (en) * | 2023-10-27 | 2024-02-20 | 腾讯科技（深圳）有限公司 | Lane dotted line rendering method, device, equipment, storage medium and program product |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115540896B (en) | Path planning method and device, electronic equipment and computer readable medium | |
| WO2021051344A1 (en) | Method and apparatus for determining lane lines in high-precision map | |
| CN114387319B (en) | Point cloud registration method, device, equipment and storage medium | |
| CN113377888A (en) | Training target detection model and method for detecting target | |
| EP4033208A2 (en) | Method and apparatus for correcting positioning information, electronic device and storage medium | |
| CN114003613A (en) | High-precision map lane line updating method and device, electronic equipment and storage medium | |
| JP2023002757A (en) | Method, device, and electronic apparatus for creating high precision map | |
| EP4170285A1 (en) | Method and apparatus for constructing three-dimensional map in high-definition map, device and storage medium | |
| JP2023036796A (en) | Positioning method and positioning device by lane line and characteristic point, electronic apparatus, storage medium, computer program, and autonomous driving vehicle | |
| CN114140759A (en) | High-precision map lane line position determining method and device and automatic driving vehicle | |
| CN116091645A (en) | Method and device for generating virtual line segment of lane | |
| CN114612616A (en) | Mapping method and device, electronic equipment and storage medium | |
| KR20220155947A (en) | High-precision map generation method and device, electronic equipment and storage medium | |
| CN113932796A (en) | High-precision map lane line generation method and device and electronic equipment | |
| CN112883236A (en) | Map updating method, map updating device, electronic equipment and storage medium | |
| CN115422316B (en) | Lane line data processing method and device, electronic device and storage medium | |
| CN115937449A (en) | High-precision map generation method and device, electronic equipment and storage medium | |
| JP7212709B2 (en) | MODELING ROUTE VERIFICATION METHOD, DEVICE, UNMANNED VEHICLE, AND STORAGE MEDIUM | |
| CN115790621A (en) | High-precision map updating method and device and electronic equipment | |
| CN115320642A (en) | Lane line modeling method and device, electronic equipment and automatic driving vehicle | |
| CN114492573A (en) | Map matching method and device based on relaxation iteration semantic features | |
| CN115168330A (en) | Data processing method, device, server and storage medium | |
| CN114049449A (en) | High-precision map road level calculation method and system | |
| CN115171094A (en) | Road element determination method, device, equipment and storage medium | |
| CN114036247A (en) | High-precision map data association method and device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |