CN114842107A - High-precision map generation method based on satellite map - Google Patents
High-precision map generation method based on satellite map Download PDFInfo
- Publication number
- CN114842107A CN114842107A CN202210352873.3A CN202210352873A CN114842107A CN 114842107 A CN114842107 A CN 114842107A CN 202210352873 A CN202210352873 A CN 202210352873A CN 114842107 A CN114842107 A CN 114842107A
- Authority
- CN
- China
- Prior art keywords
- information
- road
- road information
- method based
- generation method
- 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
- G06T11/206—Drawing of charts or graphs
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/13—Satellite images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/182—Network patterns, e.g. roads or rivers
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/09—Arrangements for giving variable traffic instructions
- G08G1/0962—Arrangements for giving variable traffic instructions having an indicator mounted inside the vehicle, e.g. giving voice messages
- G08G1/0968—Systems involving transmission of navigation instructions to the vehicle
- G08G1/0969—Systems involving transmission of navigation instructions to the vehicle having a display in the form of a map
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Evolutionary Computation (AREA)
- Remote Sensing (AREA)
- Health & Medical Sciences (AREA)
- Radar, Positioning & Navigation (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Astronomy & Astrophysics (AREA)
- Processing Or Creating Images (AREA)
- Instructional Devices (AREA)
Abstract
A high-precision map generation method based on a satellite map automatically identifies relevant road information by using the existing satellite map and generates a file in a high-precision map format through a small amount of manual marking. A new method is provided for the manufacture of the high-precision map, and the acquisition and manufacture cost and the manual marking cost can be greatly reduced.
Description
Technical Field
The invention relates to the field of intelligent driving, in particular to a high-precision map generation method based on a satellite map.
Background
At present, with the rapid development of intelligent driving, the importance of high-precision maps is concerned more and more, but a large gap still exists between the manufacturing and application requirements of high-precision maps, which is mainly expressed as follows: the acquisition equipment is high in cost, low in acquisition efficiency, and difficult to update and maintain, and a large amount of manual processing is needed.
Disclosure of Invention
In order to overcome the defects of the technology, the invention provides the high-precision map generation method based on the satellite map, which reduces the acquisition, manufacturing and manufacturing cost and the manual labeling cost.
The technical scheme adopted by the invention for overcoming the technical problems is as follows:
A high-precision map generation method based on a satellite map comprises the following steps:
a) loading a satellite map image with a scale of N meters;
b) performing semantic segmentation on the image to obtain road information and vehicle information on the road;
c) filling images of the shielded areas in the road information by using a GAN network, completing the road information and generating a road information ID;
d) sampling lane lines of the road information after completion to obtain a point set after the lane lines are scattered, calculating the GPS longitude and latitude and the corresponding MGRS coordinates of each point in the point set according to the satellite map image in the step a), and manually marking traffic lights and traffic sign information in the point set;
e) traversing the lanes in the road information intersection area after completion, and generating virtual connected road network information according to the steering identification of the lane and the traffic regulation;
f) and storing the point set information, the traffic lights, the traffic signboards and the virtual connected road network information into files meeting the standards of the Lanelet 2.
Preferably, the value of N in step a) is 30 m.
Preferably, the SegNet model or the DeepLabV3 model is used to semantically segment the image in step b).
Further, the road information intersection area in the step e) is an intersection or a T-shaped intersection.
The invention has the beneficial effects that: relevant road information is automatically identified by using the existing satellite map, and a file in a high-precision map format is generated through a small amount of manual marking. A new method is provided for the manufacture of the high-precision map, and the acquisition and manufacture cost and the manual marking cost can be greatly reduced.
Drawings
FIG. 1 is a flow chart of the method of the present invention.
Detailed Description
The invention is further described below with reference to fig. 1.
A high-precision map generation method based on a satellite map comprises the following steps:
a) the satellite map image is loaded at a scale of N meters.
b) Semantic Segmentation (Semantic Segmentation) is performed on the image to obtain road information and vehicle information on the road.
c) The blocked area in the road information is image-filled using a GAN (countermeasure generation) network, and the road information is completed to generate a road information ID.
d) Sampling the lane lines of the completed road information to obtain a point set after the lane lines are scattered, calculating the GPS longitude and latitude and the corresponding MGRS (military grid system) coordinates of each point in the point set according to the satellite map image in the step a), and manually marking traffic lights and traffic sign information (comprising the unique ID, the GPS and the converted MGRS coordinates) in the point set.
e) Traversing the lanes in the Road information intersection area after completion, and generating virtual connected Network (Road Network) information (lane connected relation and the like) according to the steering mark of the lane and traffic regulation.
f) And storing the point set information, the traffic lights, the traffic signboards and the virtual connected road network information into a file meeting the standard of Lanelet2 (an open-source high-precision map data storage format).
Relevant road information is automatically identified by using the existing satellite map, and a file in a high-precision map format is generated through a small amount of manual marking. A new method is provided for the manufacture of the high-precision map, and the acquisition and manufacture cost and the manual marking cost can be greatly reduced.
Preferably, the value of N in step a) is 30 m.
Preferably, the SegNet model or the DeepLabV3 model is used to semantically segment the image in step b).
Further, the road information intersection area in the step e) is an intersection or a T-shaped intersection, and whether the intersection belongs to a related lane of the intersection area is judged according to whether the lane extension line, the stop line and the pedestrian crossing are intersected.
Finally, it should be noted that: although the present invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that changes may be made in the embodiments and/or equivalents thereof without departing from the spirit and scope of the invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (4)
1. A high-precision map generation method based on a satellite map is characterized by comprising the following steps:
a) loading a satellite map image with a scale of N meters;
b) performing semantic segmentation on the image to obtain road information and vehicle information on the road;
c) filling images of the shielded areas in the road information by using a GAN network, completing the road information and generating a road information ID;
d) sampling lane lines of the road information after completion to obtain a point set after the lane lines are scattered, calculating the GPS longitude and latitude and the corresponding MGRS coordinates of each point in the point set according to the satellite map image in the step a), and manually marking traffic lights and traffic sign information in the point set;
e) traversing the lanes in the road information intersection area after completion, and generating virtual connected road network information according to the steering identification of the lane and the traffic regulation;
f) and storing the point set information, the traffic lights, the traffic signboards and the virtual connected road network information into files meeting the standards of the Lanelet 2.
2. The high-precision map generation method based on the satellite map according to claim 1, characterized in that: the value of N in step a) is 30 meters.
3. The high-precision map generation method based on the satellite map according to claim 1, characterized in that: in step b), the SegNet model or the DeepLabV3 model is used for semantic segmentation of the image.
4. The high-precision map generation method based on the satellite map according to claim 1, characterized in that: the road information crossing area in the step e) is an intersection or a T-shaped intersection.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210352873.3A CN114842107A (en) | 2022-04-06 | 2022-04-06 | High-precision map generation method based on satellite map |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210352873.3A CN114842107A (en) | 2022-04-06 | 2022-04-06 | High-precision map generation method based on satellite map |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114842107A true CN114842107A (en) | 2022-08-02 |
Family
ID=82563043
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210352873.3A Pending CN114842107A (en) | 2022-04-06 | 2022-04-06 | High-precision map generation method based on satellite map |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114842107A (en) |
-
2022
- 2022-04-06 CN CN202210352873.3A patent/CN114842107A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107229690B (en) | Dynamic High-accuracy map datum processing system and method based on trackside sensor | |
| CN109446369B (en) | Interaction method and system for semi-automatic image annotation | |
| CN111797001A (en) | Method for constructing automatic driving simulation test model based on SCANeR | |
| US20210004021A1 (en) | Generating training data for deep learning models for building high definition maps | |
| CN103177577B (en) | Dynamic traffic information service providing method based on map layer overlapping | |
| CN103411619B (en) | A kind of three-dimensional road generation system and method | |
| CN113033029A (en) | Automatic driving simulation method and device, electronic equipment and storage medium | |
| EP3706072A1 (en) | Method, apparatus, and system for detecting degraded ground paint in an image | |
| US20100082564A1 (en) | Spatial Index for Locating Geographic Data Parcels Stored on Physical Storage Media | |
| CN115063978B (en) | Bus arrival time prediction method based on digital twins | |
| CN110838153B (en) | Method for making modern inland river electronic channel chart based on ArcGIS system and application | |
| CN110118564A (en) | A kind of data management system, management method, terminal and the storage medium of high-precision map | |
| CN104281746A (en) | Method for generating traffic safety road characteristic graphs on basis of point-cloud | |
| CN113010793A (en) | Method, device, equipment, storage medium and program product for map data processing | |
| CN105787445A (en) | Method and system for automatically extracting rod-shaped objects in vehicular laser scanning data | |
| CN109101743A (en) | A kind of construction method of high-precision road net model | |
| US20240169743A1 (en) | Vehicle positioning method and device based on environment matching, vehicle and storage medium | |
| CN114440905B (en) | Method and device for constructing intermediate layer, electronic equipment and storage medium | |
| CN117853904A (en) | Road disease detection method, device, equipment, medium and system | |
| CN113496182B (en) | Road extraction method and device based on remote sensing image, storage medium and equipment | |
| CN112414416A (en) | ADAS map data system based on four-level automatic driving high precision | |
| CN114842107A (en) | High-precision map generation method based on satellite map | |
| CN115375864B (en) | Unmanned aerial vehicle-based high-speed railway completion acceptance method | |
| CN115062445A (en) | Simulation scene construction method and system based on natural driving data | |
| CN113744360A (en) | Method and system for automatically generating road element grids by high-precision map data |
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 |