CN113701770A - High-precision map generation method and system - Google Patents

High-precision map generation method and system Download PDF

Info

Publication number
CN113701770A
CN113701770A CN202110808588.3A CN202110808588A CN113701770A CN 113701770 A CN113701770 A CN 113701770A CN 202110808588 A CN202110808588 A CN 202110808588A CN 113701770 A CN113701770 A CN 113701770A
Authority
CN
China
Prior art keywords
precision map
road
data
global high
global
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
Application number
CN202110808588.3A
Other languages
Chinese (zh)
Inventor
陈睿
雷雨
宁佳萌
孙斯怡
田镇洋
郭婷
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Xidian University
Original Assignee
Xidian University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Xidian University filed Critical Xidian University
Priority to CN202110808588.3A priority Critical patent/CN113701770A/en
Publication of CN113701770A publication Critical patent/CN113701770A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • GPHYSICS
    • G01MEASURING; TESTING
    • G01CMEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34Route searching; Route guidance
    • G01C21/3453Special cost functions, i.e. other than distance or default speed limit of road segments
    • G01C21/3492Special cost functions, i.e. other than distance or default speed limit of road segments employing speed data or traffic data, e.g. real-time or historical

Landscapes

  • Engineering & Computer Science (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Automation & Control Theory (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Traffic Control Systems (AREA)

Abstract

The invention discloses a high-precision map generation method and a high-precision map generation system, wherein the method comprises the following steps: acquiring state information of each road section of a road to be detected through a device arranged on the road to be detected; performing fusion processing on the state information of each road section to obtain a plurality of local high-precision map data; and splicing the local high-precision map data to obtain global high-precision map data. Compared with the traditional vehicle acquisition mode, the high-precision map generation method provided by the invention greatly reduces the time required for acquiring data, provides more timely, reliable and accurate high-precision map information for the automatic driving vehicle, and ensures the driving safety.

Description

High-precision map generation method and system
Technical Field
The invention belongs to the technical field of automatic driving, and particularly relates to a high-precision map generation method and system.
Background
Navigation path planning is an important technique in automated driving research. With the rapid development of the automatic driving technology, the planning of the navigation path depends on a high-precision map more and more, and the higher the precision of the high-precision map is, the more precise the planning of the navigation path is. Therefore, high-precision maps have become an essential part of the realization of unmanned and intelligent traffic.
At present, the existing high-precision map data acquisition method usually needs to repeatedly drive a data acquisition vehicle for multiple times according to the same route through manual driving, then high-precision map acquisition data is obtained, a high-precision map is finally drawn, and a user loads the map and then performs navigation by combining a positioning device.
However, the existing vehicle collection method is relatively labor-consuming and material-consuming, the period from the map data collection to the map updating is long, and a survey blind area exists, so that the generated map is not accurate enough. In addition, when the road surface has an emergency, such as the situations of animal invasion, object throwing, debris flow, road collapse and the like, and the partial lanes cannot normally pass, the map generated by the existing method cannot respond in time, so that vehicles about to pass through the road section can be informed in advance, and the conditions of road congestion and queuing cannot be fed back to the user quickly. The automatic driving vehicle has high precision on the road state information, and if the feedback is not timely, early warning cannot be performed in advance, so that great threat is caused to the road driving safety.
Disclosure of Invention
In order to solve the above problems in the prior art, the present invention provides a high-precision map generation method and system.
The technical problem to be solved by the invention is realized by the following technical scheme:
a high-precision map generation method, comprising:
acquiring state information of each road section of a road to be detected through a device arranged on the road to be detected;
performing fusion processing on the state information of each road section to obtain a plurality of local high-precision map data;
and splicing the local high-precision map data to obtain global high-precision map data.
In one embodiment of the present invention, further comprising:
and updating the pre-stored original global high-precision map according to the global high-precision map data.
In one embodiment of the present invention, the state information of the road section includes road sign information, traffic state information, abnormal road surface information, climate information, and road traffic abnormal event information.
In an embodiment of the present invention, updating a pre-stored original global high-precision map according to the global high-precision map data includes:
comparing and analyzing the global high-precision map data at the current moment with the pre-stored original global high-precision map to obtain the difference between the global high-precision map data and the original global high-precision map;
and (4) performing superposition correction on the different points on the original global high-precision map so as to update the original global high-precision map.
In one embodiment of the present invention, further comprising: and marking danger information on the obtained global high-precision map when the global high-precision map is updated.
Another embodiment of the present invention also provides a high-precision map generating system, including:
the roadside sensing module is arranged on the road to be detected and used for acquiring the state information of each road section of the road to be detected;
the data fusion module is connected with the roadside sensing module and used for carrying out fusion processing on the state information of each road section to obtain a plurality of local high-precision map data;
and the map generation module is connected with the data fusion module and used for splicing the local high-precision map data to obtain global high-precision map data.
In one embodiment of the invention, the system further comprises:
and the map updating module is connected with the map generating module and used for updating the pre-stored original global high-precision map according to the global high-precision map data.
In an embodiment of the present invention, the roadside sensing module includes a camera and a radar, and the camera and the radar respectively collect state information of each road section from different dimensions.
In one embodiment of the invention, the map update module comprises:
the comparison unit is used for comparing and analyzing the global high-precision map data at the current moment with the pre-stored original global high-precision map to obtain the difference between the global high-precision map data and the original global high-precision map;
and the updating unit is used for performing superposition correction on the difference on the original global high-precision map so as to update the original global high-precision map.
In one embodiment of the present invention, the map update module further comprises:
and the marking unit is used for marking danger information on the obtained global high-precision map when the global high-precision map is updated.
The invention has the beneficial effects that:
1. according to the high-precision map generation method, the road state information data are collected in real time through the device arranged on the road to be detected, the collected data are fused, and the high-precision map data are finally formed;
2. the high-precision map generation method provided by the invention has the advantages that the generated high-precision map is updated in real time, and the dangerous information is marked in time, so that the problems of traffic accidents or inconvenient travelling caused by untimely update of high-precision map data and inaccurate data information are effectively solved, and the cost for using a special high-precision map measuring vehicle and manually generating the high-precision map by secondary treatment is reduced or avoided;
3. the high-precision map generation method provided by the invention can be used for randomly arranging the device for acquiring the road section state information on the required road section according to the actual requirement, thereby greatly avoiding or even eliminating the survey blind area and further improving the accuracy of map generation.
The present invention will be described in further detail with reference to the accompanying drawings and examples.
Drawings
Fig. 1 is a schematic flow chart of a high-precision map generation method according to an embodiment of the present invention;
fig. 2 is a block diagram of a high-precision map generation system according to an embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to specific examples, but the embodiments of the present invention are not limited thereto.
Example one
Referring to fig. 1, fig. 1 is a schematic flow chart of a high-precision map generating method according to an embodiment of the present invention, which specifically includes:
s1: and acquiring the state information of each road section of the road to be detected through a device arranged on the road to be detected.
Specifically, the present embodiment may respectively collect the state information of a plurality of road segments of a certain road to be detected according to the actual situation. For example, a plurality of collecting devices are arranged on a road section with complex terrain or large pedestrian volume for intensive collection, and a road section with flat road and simple surrounding environment is simply collected. In addition, the acquisition period can be set according to needs, for example, intensive acquisition is carried out in the peak period of driving.
According to the generation method of the high-precision map, the device for acquiring the road section state information can be randomly arranged on the required road section according to actual needs, so that a survey blind area is greatly avoided or even eliminated, and the accuracy of generating the map is further improved.
Further, in order to increase samples to reflect real road state information as much as possible, sampling from different dimensions may be performed, for example, image information acquisition may be performed using a camera, three-dimensional point cloud data acquisition may be performed using a radar system, or information acquisition such as temperature and humidity may be performed using other sensors.
In the present embodiment, the state information of the link includes road sign information, traffic state information, abnormal road surface information, climate information, and road traffic abnormal event information. Wherein the road sign information at least includes: traffic sign information, traffic light information, lane line data information; the traffic state information includes: information of smooth, light congestion, moderate congestion and severe congestion; the abnormal road surface information includes at least: icing, collapse and pollution of road surface; the road traffic abnormal event information includes: whether there are group events, whether there are dangerous animals, whether there are sprinkles, whether there are temporary traffic control, whether there are road maintenance construction or other dangerous situations that influence normal road traffic appear, group events include: gathering, touring, demonstrating, terrorist violent activities and the like, and generating original data information of two dimensions of radar data and video data, wherein the original data information comprises road sign information, traffic state information, abnormal road surface information, climate information and road traffic abnormal event information of a current road section.
S2: and performing fusion processing on the state information of each road section to obtain a plurality of local high-precision map data.
After the state information of a plurality of different road sections is obtained in step 1, the state information of each road section needs to be fused in real time to obtain high-precision map data of the current road section, which is also called local high-precision map data.
Further, in the embodiment, data obtained from different dimensions are fused by an intelligent algorithm to generate initial high-precision map data including road sign information, traffic state information, abnormal road surface information, climate information and road traffic abnormal event information of the current road section.
Step S2 will be described in detail below by taking data collected by the fusion radar system and the camera system as an example.
Firstly, a radar system and a camera system respectively collect data aiming at an observation road section, then feature extraction and pattern recognition processing are carried out on output data of each sensor, targets are accurately related according to categories, and finally data of all sensors of the same target are integrated by utilizing a fusion algorithm.
Specifically, an image fusion strategy is adopted, namely vision is taken as a main body, image feature transformation is carried out on the overall information output by the radar system, and then fusion is carried out on the overall information and the image output of the camera system. And more particularly to spatial fusion and temporal fusion. Establishing a coordinate conversion relation among a radar coordinate system, a three-dimensional world coordinate system, a camera coordinate system, an image coordinate system and a pixel coordinate system, and converting a measuring point in the radar coordinate system into a pixel coordinate system corresponding to the camera through the coordinate system to realize the spatial fusion of the measuring point and the pixel coordinate system; the millimeter wave radar and the vision fusion system can synchronously acquire data in time, can realize time fusion, and can finish the common sampling of data of one frame of radar and vision fusion when the camera acquires one frame of image by taking the sampling rate of the camera as a reference so as to ensure the time synchronization of the radar data and the camera data.
S3: and splicing the local high-precision map data to obtain global high-precision map data.
Specifically, the obtained local high-precision map data are integrated and analyzed to obtain global high-precision map data reflecting complete road information at the current moment.
More specifically, feature points of overlapped parts of a plurality of local high-precision maps are extracted and matched by using an SIFT feature point matching algorithm to obtain a plurality of matched point pairs, and error matching is removed. The RANSAC algorithm and the matched features are then used to fit an image transformation matrix by which the image is affine transformed. And finally, splicing the images, and fusing the overlapped parts to obtain the global high-precision map.
According to the generation method of the high-precision map, the road state information data are collected in real time through the device arranged on the road to be detected, the collected data are fused, and finally the high-precision map data are formed.
Further, after step S3, the method further includes:
s4: and updating the pre-stored original global high-precision map according to the global high-precision map data.
Because the environment of the road to be measured changes at any time, the state information of each road section needs to be regularly acquired, the global high-precision map is updated according to the state information, and the specific updating period can be determined by the data acquisition period
Specifically, step S4 includes:
s41: and comparing and analyzing the global high-precision map data at the current moment with the pre-stored original global high-precision map to find out the difference between the global high-precision map data and the original global high-precision map.
S42: and (4) performing superposition correction on the different points on the original global high-precision map so as to update the original global high-precision map.
The method comprises the steps of extracting position information of a plurality of target elements from a global high-precision map at the current moment and a pre-stored original global high-precision map respectively, carrying out differential comparison on the position information of the target elements and the position information of the target elements to obtain a deviation corresponding to the position of each target element, determining the position of the target element to be updated according to the position deviation value if the position deviation value is larger than a preset proportional threshold, and updating the original global high-precision map data based on new position information.
When updating the global high-accuracy map, it is necessary to mark danger information on the obtained global high-accuracy map.
For example, in the process of performing comparison and update, the marking unit performs image recognition and analysis on a plurality of target elements to be updated, finds that a dangerous event which seriously affects the subsequent vehicle traffic, such as road collapse or sudden car accident, occurs, generates a dangerous early warning, and performs dangerous marking on a map.
Thus, the latest global high-precision map is obtained. The latest high-precision map with the danger marks is uploaded to a cloud platform and then forwarded to each automatic driving automobile by the cloud platform for calling, so that the problems of traffic accidents or inconvenient travelling caused by untimely updating of high-precision map data and inaccurate data information are effectively avoided, and the driving safety of automatic driving is improved; in addition, the cost expense of using a special high-precision map measuring vehicle and manually secondarily processing the generated high-precision map is reduced or avoided.
In another embodiment of the invention, the danger information can be directly marked on the global high-precision map obtained after each splicing processing and uploaded to the cloud platform, and then the danger information is forwarded to each automatic driving automobile by the cloud platform for calling.
In addition, the latest high-precision map obtained after updating can be stored in the system database to replace the original high-precision map, the system can continuously update and perfect itself, and the change of the current road section can be adjusted in time, so that the generated brand-new high-precision map has more accurate data and higher precision, and is more suitable for being used by automatic driving vehicles.
Example two
On the basis of the first embodiment, the present embodiment provides a high-precision map generating system, which can be used to implement the method steps provided by the first embodiment.
Specifically, referring to fig. 2, fig. 2 is a block diagram of a high-precision map generating system according to an embodiment of the present invention, which includes:
the roadside sensing module 1 is arranged on the road to be detected and used for collecting the state information of each road section of the road to be detected;
the data fusion module 2 is connected with the roadside sensing module 1 and used for carrying out fusion processing on the state information of each road section to obtain a plurality of local high-precision map data;
and the map generation module 3 is connected with the data fusion module 2 and used for splicing the local high-precision map data to obtain global high-precision map data.
And the map updating module 4 is connected with the map generating module 3 and used for updating the pre-stored original global high-precision map according to the global high-precision map data.
In this embodiment, the roadside sensing module 1 includes a camera 11 and a radar 12, and the camera 11 and the radar 12 respectively collect state information of each road section from different dimensions.
Further, the map update module 4 includes:
a comparing unit 41, configured to compare and analyze the global high-precision map data at the current time with a pre-stored original global high-precision map to obtain a difference between the global high-precision map data and the original global high-precision map;
and the updating unit 42 is used for performing superposition correction on the different points on the original global high-precision map so as to update the original global high-precision map.
The high-precision map generation system provided by the embodiment has the following working process:
the road side sensing modules are densely deployed beside roads and are used for collecting all road sign information, traffic state information, abnormal road surface information, climate information and road traffic abnormal event information of the current road section in real time. The roadside sensing module transmits the acquired data to the data fusion module, the data fusion module fuses radar data and video data to generate local high-precision map data and transmits the local high-precision map data to the map generation module, the map generation module firstly fuses all received local high-precision maps to generate high-precision map data reflecting the complete road information at the current moment, then the high-precision map data reflecting the complete road information at the current moment is compared with the original high-precision map of the road stored in the system for analysis, and the changed parts are superposed and corrected on the original high-precision map of the road to generate a brand new high-precision map.
Further, the map update module 4 further includes:
and a marking unit 43, configured to mark danger information on the obtained global high-precision map when the global high-precision map is updated.
Specifically, when a traffic accident or other dangerous events happen suddenly on a certain road section to influence normal road traffic, the roadside sensing module can quickly acquire dangerous information data, the dangerous information data are fused by the data fusion module and then sent to the map generation module, the dangerous information is marked on a new high-precision map, the high-precision map with the marks is uploaded to the cloud platform, and the high-precision map with the marks is forwarded to each automatic driving automobile by the cloud platform for calling, so that the automatic driving automobiles passing through the road section can be subjected to path re-planning, and traffic jam or new traffic accidents are avoided.
The foregoing is a more detailed description of the invention in connection with specific preferred embodiments and it is not intended that the invention be limited to these specific details. For those skilled in the art to which the invention pertains, several simple deductions or substitutions can be made without departing from the spirit of the invention, and all shall be considered as belonging to the protection scope of the invention.

Claims (10)

1. A high-precision map generation method is characterized by comprising the following steps:
acquiring state information of each road section of a road to be detected through a device arranged on the road to be detected;
performing fusion processing on the state information of each road section to obtain a plurality of local high-precision map data;
and splicing the local high-precision map data to obtain global high-precision map data.
2. The high-precision map generation method according to claim 1, further comprising:
and updating the pre-stored original global high-precision map according to the global high-precision map data.
3. The high-precision map generation method according to claim 1, wherein the state information of the link includes road sign information, traffic state information, abnormal road surface information, climate information, and road traffic abnormal event information.
4. The high-precision map generation method according to claim 2, wherein updating the pre-stored original global high-precision map according to the global high-precision map data comprises:
comparing and analyzing the global high-precision map data at the current moment with the pre-stored original global high-precision map to obtain the difference between the global high-precision map data and the original global high-precision map;
and (4) performing superposition correction on the different points on the original global high-precision map so as to update the original global high-precision map.
5. The high-precision map generation method according to claim 4, further comprising: and marking danger information on the obtained global high-precision map when the global high-precision map is updated.
6. A high precision map generation system, comprising:
the roadside sensing module (1) is arranged on the road to be detected and used for collecting the state information of each road section of the road to be detected;
the data fusion module (2) is connected with the roadside sensing module (1) and is used for carrying out fusion processing on the state information of each road section to obtain a plurality of local high-precision map data;
and the map generation module (3) is connected with the data fusion module (2) and is used for splicing the local high-precision map data to obtain global high-precision map data.
7. The high precision map generation system of claim 1, further comprising:
and the map updating module (4) is connected with the map generating module (3) and is used for updating the pre-stored original global high-precision map according to the global high-precision map data.
8. The high-precision map generation system according to claim 1, wherein the roadside perception module (1) comprises a camera (11) and a radar (12), and the camera (11) and the radar (12) respectively collect state information of each road section from different dimensions.
9. A high precision map generation system according to claim 1, characterized in that the map update module (4) comprises:
the comparison unit (41) is used for comparing and analyzing the global high-precision map data at the current moment with the pre-stored original global high-precision map to obtain the difference between the global high-precision map data and the original global high-precision map;
and the updating unit (42) is used for performing superposition correction on the different points on the original global high-precision map so as to update the original global high-precision map.
10. A high precision map generation system according to claim 1, wherein the map update module (4) further comprises:
and a marking unit (43) for marking danger information on the obtained global high-precision map when the global high-precision map is updated.
CN202110808588.3A 2021-07-16 2021-07-16 High-precision map generation method and system Pending CN113701770A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110808588.3A CN113701770A (en) 2021-07-16 2021-07-16 High-precision map generation method and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110808588.3A CN113701770A (en) 2021-07-16 2021-07-16 High-precision map generation method and system

Publications (1)

Publication Number Publication Date
CN113701770A true CN113701770A (en) 2021-11-26

Family

ID=78648841

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110808588.3A Pending CN113701770A (en) 2021-07-16 2021-07-16 High-precision map generation method and system

Country Status (1)

Country Link
CN (1) CN113701770A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114413914A (en) * 2022-01-18 2022-04-29 上汽通用五菱汽车股份有限公司 Precision improving method and system for high-precision map and computer readable storage medium

Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20110060483A (en) * 2009-11-30 2011-06-08 주식회사 제일엔지니어링종합건축사사무소 Classify the road traffic danger grade method and appatatus and system using forward road state information, traffic state information and vehicle's velocity information
CN106441319A (en) * 2016-09-23 2017-02-22 中国科学院合肥物质科学研究院 System and method for generating lane-level navigation map of unmanned vehicle
CN107229690A (en) * 2017-05-19 2017-10-03 广州中国科学院软件应用技术研究所 Dynamic High-accuracy map datum processing system and method based on trackside sensor
CN108010360A (en) * 2017-12-27 2018-05-08 中电海康集团有限公司 A kind of automatic Pilot context aware systems based on bus or train route collaboration
WO2019139243A1 (en) * 2018-01-15 2019-07-18 에스케이텔레콤 주식회사 Apparatus and method for updating high definition map for autonomous driving
US20200149896A1 (en) * 2018-11-09 2020-05-14 GM Global Technology Operations LLC System to derive an autonomous vehicle enabling drivable map
CN111220154A (en) * 2020-01-22 2020-06-02 北京百度网讯科技有限公司 Vehicle positioning method, device, equipment and medium
CN111583630A (en) * 2020-04-10 2020-08-25 河北德冠隆电子科技有限公司 Brand-new road high-precision map rapid generation system and method based on space-time trajectory reconstruction
WO2020224305A1 (en) * 2019-05-07 2020-11-12 北京市商汤科技开发有限公司 Method and apparatus for device positioning, and device
CN112069856A (en) * 2019-06-10 2020-12-11 商汤集团有限公司 Map generation method, driving control method, device, electronic equipment and system
CN112960000A (en) * 2021-03-15 2021-06-15 新石器慧义知行智驰(北京)科技有限公司 High-precision map updating method and device, electronic equipment and storage medium

Patent Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20110060483A (en) * 2009-11-30 2011-06-08 주식회사 제일엔지니어링종합건축사사무소 Classify the road traffic danger grade method and appatatus and system using forward road state information, traffic state information and vehicle's velocity information
CN106441319A (en) * 2016-09-23 2017-02-22 中国科学院合肥物质科学研究院 System and method for generating lane-level navigation map of unmanned vehicle
CN107229690A (en) * 2017-05-19 2017-10-03 广州中国科学院软件应用技术研究所 Dynamic High-accuracy map datum processing system and method based on trackside sensor
CN108010360A (en) * 2017-12-27 2018-05-08 中电海康集团有限公司 A kind of automatic Pilot context aware systems based on bus or train route collaboration
WO2019139243A1 (en) * 2018-01-15 2019-07-18 에스케이텔레콤 주식회사 Apparatus and method for updating high definition map for autonomous driving
US20200149896A1 (en) * 2018-11-09 2020-05-14 GM Global Technology Operations LLC System to derive an autonomous vehicle enabling drivable map
WO2020224305A1 (en) * 2019-05-07 2020-11-12 北京市商汤科技开发有限公司 Method and apparatus for device positioning, and device
CN112069856A (en) * 2019-06-10 2020-12-11 商汤集团有限公司 Map generation method, driving control method, device, electronic equipment and system
CN111220154A (en) * 2020-01-22 2020-06-02 北京百度网讯科技有限公司 Vehicle positioning method, device, equipment and medium
CN111583630A (en) * 2020-04-10 2020-08-25 河北德冠隆电子科技有限公司 Brand-new road high-precision map rapid generation system and method based on space-time trajectory reconstruction
CN112960000A (en) * 2021-03-15 2021-06-15 新石器慧义知行智驰(北京)科技有限公司 High-precision map updating method and device, electronic equipment and storage medium

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
余卓渊;闾国年;张夕宁;贾远信;周成虎;葛咏;吕可晶;: "全息高精度导航地图:概念及理论模型", 地球信息科学学报, no. 04 *
李帅帅;鲍晨;沈勇;: "路面不平度识别与地图匹配在车辆定位中的应用", 汽车零部件, no. 01 *
陆哲元;: "基于高精地图的车路协同智能交通系统", 中国公共安全, no. 11 *

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114413914A (en) * 2022-01-18 2022-04-29 上汽通用五菱汽车股份有限公司 Precision improving method and system for high-precision map and computer readable storage medium

Similar Documents

Publication Publication Date Title
CN107643086B (en) Vehicle positioning method, device and system
RU2654502C2 (en) System and method for remote vehicle monitoring
CN110009765B (en) Scene format conversion method of automatic driving vehicle scene data system
US10620317B1 (en) Lidar-based high definition map generation
CN109641589B (en) Route planning for autonomous vehicles
US10423841B2 (en) Abnormality detection device and abnormality detection method
CN112074885A (en) Lane sign positioning
US10553117B1 (en) System and method for determining lane occupancy of surrounding vehicles
DE112020004931T5 (en) SYSTEMS AND METHODS FOR DETERMINING ROAD SAFETY
KR102001659B1 (en) Method and apparatus for providing camera calibration for vehicles
JP2006208223A (en) Vehicle position recognition device and vehicle position recognition method
CN110942623B (en) Auxiliary traffic accident handling method and system
CN112700470A (en) Target detection and track extraction method based on traffic video stream
CN113508277A (en) Lane marker location and fusion
CN111354222A (en) Driving assisting method and system
JP4775658B2 (en) Feature recognition device, vehicle position recognition device, navigation device, feature recognition method
CN111506069B (en) All-weather all-ground crane obstacle identification system and method
CN113071500A (en) Method and device for acquiring lane line, computer equipment and storage medium
DE102022131625A1 (en) CURB-BASED FEATURE EXTRACTION FOR RADAR LOCALIZATION AND LANE DETECTION
KR101544854B1 (en) Method for providing real time traffic information around vehicle and traffic information system using the same
EP3721371B1 (en) Method for position determination for a vehicle, controller and vehicle
CN113701770A (en) High-precision map generation method and system
CN112562061A (en) Driving vision enhancement system and method based on laser radar image
EP2945138A1 (en) Method and apparatus for providing information data about entities along a route taken by a vehicle
CN113378719B (en) Lane line identification method, lane line identification device, computer 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