CN114120631A - Method and device for constructing dynamic high-precision map and traffic cloud control platform - Google Patents
Method and device for constructing dynamic high-precision map and traffic cloud control platform Download PDFInfo
- Publication number
- CN114120631A CN114120631A CN202111267215.6A CN202111267215A CN114120631A CN 114120631 A CN114120631 A CN 114120631A CN 202111267215 A CN202111267215 A CN 202111267215A CN 114120631 A CN114120631 A CN 114120631A
- Authority
- CN
- China
- Prior art keywords
- data
- dynamic
- traffic
- map
- precision
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0108—Measuring and analyzing of parameters relative to traffic conditions based on the source of data
- G08G1/0112—Measuring and analyzing of parameters relative to traffic conditions based on the source of data from the vehicle, e.g. floating car data [FCD]
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/28—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network with correlation of data from several navigational instruments
- G01C21/30—Map- or contour-matching
- G01C21/32—Structuring or formatting of map data
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0108—Measuring and analyzing of parameters relative to traffic conditions based on the source of data
- G08G1/0116—Measuring and analyzing of parameters relative to traffic conditions based on the source of data from roadside infrastructure, e.g. beacons
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0137—Measuring and analyzing of parameters relative to traffic conditions for specific applications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/09—Arrangements for giving variable traffic instructions
- G08G1/095—Traffic lights
-
- 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
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Automation & Control Theory (AREA)
- Traffic Control Systems (AREA)
Abstract
The embodiment of the invention provides a method and a device for constructing a dynamic high-precision map and a traffic cloud control platform. In the embodiment of the invention, the absolute coordinates of each traffic element (such as a vehicle, a pedestrian, a road sign and the like) are obtained by fusing multi-source sensor data, so that the coordinates obtained by a single sensor are more accurate. In addition, the embodiment of the invention can also obtain dynamic traffic situation data by analyzing the data of the multi-source sensor, and can simulate more comprehensive and real traffic conditions by combining the absolute coordinate information and the dynamic traffic situation data. Furthermore, the method can update the high-precision map data in real time based on the update of the multi-source sensor data to obtain the 3D dynamic high-precision map which is updated in real time and dynamically changed. In the embodiment of the invention, the dynamically updated 3D dynamic high-precision map can be displayed in real time through the traffic cloud control platform, and the traffic cloud control platform can provide traffic control information for users.
Description
Technical Field
The embodiment of the invention relates to the technical field of information processing, in particular to a method and a device for constructing a dynamic high-precision map and a traffic cloud control platform.
Background
In the related technology, the main high-precision positioning strategy mostly adopts a method of combining GNSS/RTK and a high-precision map, but the problem of road positioning error in some scenes still exists. Although the accuracy of positioning can be improved by combining the feature matching positioning method, the existing feature matching positioning method cannot achieve the accuracy required in the vehicle-road cooperative system. At present, a method for constructing and displaying a dynamic high-precision map in real time is lacked, and a decision cannot be made according to the current real traffic environment.
Therefore, a method for constructing a real-time dynamic high-precision map is needed.
Disclosure of Invention
The embodiment of the invention provides a method and a device for constructing a dynamic high-precision map and a traffic cloud control platform, which are used for constructing a real-time dynamic high-precision map and obtaining a digital twin traffic cloud control platform.
The first aspect of the embodiments of the present invention provides a method for constructing a dynamic high-precision map, where the method includes:
acquiring multi-source sensor data in real time, wherein the multi-source sensor data at least comprises data acquired by a vehicle-mounted sensor and a roadside sensor;
analyzing the multi-source sensor data to obtain dynamic traffic situation data, wherein the dynamic traffic situation data at least comprises the following components: traffic congestion degree identification data, abnormal traffic incident identification data and traffic flow identification data;
correlating and fusing the multi-source sensor data to obtain high-precision original data;
carrying out coordinate transformation on the high-precision original data to obtain absolute coordinate information corresponding to the high-precision original data;
adding the absolute coordinate information and the dynamic traffic situation data to a pre-established 2D static high-precision map to complete the initial scanning of the 3D dynamic high-precision map;
updating the 3D dynamic high-precision map data based on the dynamic update of the multi-source sensor data to obtain a dynamically updated 3D dynamic high-precision map;
and displaying the dynamically updated 3D dynamic high-precision map in real time through a traffic cloud control platform, and providing traffic control information in real time.
Optionally, the performing coordinate transformation on the high-precision raw data to obtain absolute coordinate information corresponding to the high-precision raw data includes:
performing point cloud semantic segmentation on the high-precision original data to filter out non-map element data in the high-precision original data;
carrying out coordinate transformation on the filtered map element data to obtain absolute coordinate information corresponding to the map element data;
adding the absolute coordinate information to a pre-established 2D static high-precision map, comprising:
and adding absolute coordinate information corresponding to the map element data to a pre-established 2D static high-precision map.
Optionally, the adding the absolute coordinate information corresponding to the map element data to a pre-established 2D static high-precision map includes:
adopting multi-resolution octree map representation, and adding absolute coordinate information corresponding to the map element data to a pre-established 2D static high-precision map;
the map element data corresponding to the map element with the smaller volume is represented by octree nodes expanded to a leaf node layer, and the map element data corresponding to the map element with the larger volume is represented by octree nodes expanded to a non-leaf node layer.
Optionally, the updating the 3D dynamic high-precision map data based on the dynamic updating of the multi-source sensor data to obtain a dynamically updated 3D dynamic high-precision map includes:
updating the motion entity data in the 3D dynamic high-precision map data based on the updating frequency of high-degree dynamic data in the multi-source sensor data;
updating traffic signal data in the 3D dynamic high-precision map data based on the updating frequency of semi-dynamic data in the multi-source sensor data;
updating traffic facility data in the 3D dynamic high-precision map data based on the updating frequency of semi-static data in the multi-source sensor data;
and updating the 2D static high-precision map data in the 3D dynamic high-precision map data based on the updating frequency of continuous static data in the multi-source sensor data.
Optionally, the traffic control information is provided in real time through a traffic cloud control platform, and includes at least one of:
real-time traffic situation information is issued to the vehicles through a traffic cloud control platform;
performing road cooperative management based on the dynamically updated 3D dynamic high-precision map through a traffic cloud control platform;
and sending control information to the traffic signal lamp through the traffic cloud control platform.
A second aspect of the embodiments of the present invention provides an apparatus for constructing a dynamic high-precision map, where the apparatus includes:
the data acquisition module is used for acquiring multi-source sensor data in real time, wherein the multi-source sensor data at least comprises data acquired by a vehicle-mounted sensor and a roadside sensor;
an analysis module, configured to analyze the multi-source sensor data to obtain dynamic traffic situation data, where the dynamic traffic situation data at least includes: traffic congestion degree identification data, abnormal traffic incident identification data and traffic flow identification data;
the fusion module is used for correlating and fusing the multi-source sensor data to obtain high-precision original data;
the coordinate transformation module is used for carrying out coordinate transformation on the high-precision original data to obtain absolute coordinate information corresponding to the high-precision original data;
the initial scanning module is used for adding the absolute coordinate information and the dynamic traffic situation data to a pre-established 2D static high-precision map to complete the initial scanning of the 3D dynamic high-precision map;
the dynamic updating module is used for updating the 3D dynamic high-precision map data based on the dynamic updating of the multi-source sensor data to obtain a dynamically updated 3D dynamic high-precision map;
and the display module is used for displaying the dynamically updated 3D dynamic high-precision map in real time through a traffic cloud control platform and providing traffic control information in real time.
Optionally, the coordinate transformation module includes:
the filtering submodule is used for performing point cloud semantic segmentation on the high-precision original data so as to filter out non-map element data in the high-precision original data;
the coordinate transformation submodule is used for carrying out coordinate transformation on the map element data obtained after filtering to obtain absolute coordinate information corresponding to the map element data;
and the initial scanning module is also used for adding the absolute coordinate information corresponding to the map element data to a pre-established 2D static high-precision map.
Optionally, the initial scanning module includes:
the adding submodule is used for adopting multi-resolution octree map representation and adding absolute coordinate information corresponding to the map element data to a pre-established 2D static high-precision map;
the map element data corresponding to the map element with the smaller volume is represented by octree nodes expanded to a leaf node layer, and the map element data corresponding to the map element with the larger volume is represented by octree nodes expanded to a non-leaf node layer.
Optionally, the dynamic update module includes:
the first dynamic updating module submodule is used for updating the motion entity data in the 3D dynamic high-precision map data based on the updating frequency of high-degree dynamic data in the multi-source sensor data;
the second dynamic updating module submodule is used for updating traffic signal data in the 3D dynamic high-precision map data based on the updating frequency of semi-dynamic data in the multi-source sensor data;
the third dynamic updating module submodule is used for updating the traffic facility data in the 3D dynamic high-precision map data based on the updating frequency of semi-static data in the multi-source sensor data;
and the fourth dynamic update module submodule is used for updating the 2D static high-precision map data in the 3D dynamic high-precision map data based on the update frequency of continuous static data in the multi-source sensor data.
Optionally, the display module comprises at least one of:
the real-time traffic situation information issuing sub-module is used for issuing real-time traffic situation information to the vehicles through the traffic cloud control platform;
the road cooperative management submodule carries out road cooperative management on the basis of the dynamically updated 3D dynamic high-precision map through a traffic cloud control platform;
and the control submodule is used for sending control information to the traffic signal lamp through the traffic cloud control platform.
A third aspect of the embodiments of the present invention provides a traffic cloud control platform, which displays a dynamic high-precision map constructed by the steps in any one of the methods for constructing a dynamic high-precision map according to the first aspect of the present invention in real time, and provides traffic control information in real time.
In the embodiment of the invention, the absolute coordinates of each traffic element can be obtained by acquiring the data of the multi-source sensor in real time and fusing the data, meanwhile, the traffic situation data can be obtained by analyzing the data of the multi-source sensor, and the absolute coordinates and the traffic situation data of each traffic element can be reflected on a high-precision map.
In the embodiment of the invention, the absolute coordinates of each traffic element (such as a vehicle, a pedestrian, a road sign and the like) are obtained by fusing multi-source sensor data, so that the coordinates obtained by a single sensor are more accurate. In addition, the embodiment of the invention can also obtain dynamic traffic situation data by analyzing the data of the multi-source sensor, and can simulate more comprehensive and real traffic conditions by combining the absolute coordinate information and the dynamic traffic situation data. Furthermore, the method can update the high-precision map data in real time based on the update of the multi-source sensor data to obtain the 3D dynamic high-precision map which is updated in real time and dynamically changed.
In the embodiment of the invention, the dynamically updated 3D dynamic high-precision map can be displayed in real time through the traffic cloud control platform, and the traffic cloud control platform can provide traffic control information for users. Therefore, traffic situation awareness can be achieved through the traffic cloud control platform, digital traffic control can be performed, second-level real-time traffic information service can be provided for users, active safety control of vehicles and road cooperative management are achieved, and more efficient, convenient and safe traffic management and service are achieved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments of the present invention will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to these drawings without inventive labor.
FIG. 1 is a flow chart of a method of constructing a dynamic high precision map in accordance with an embodiment of the present invention;
FIG. 2 is a flow chart of a method of determining absolute coordinate information in accordance with an embodiment of the present invention;
FIG. 3 is a flow chart of a method of constructing a high precision map in accordance with an embodiment of the present invention;
fig. 4 is a block diagram of an apparatus for constructing a dynamic high-precision map according to an embodiment of the present invention.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.
Referring to fig. 1, a flowchart of a method for constructing a dynamic high-precision map according to an embodiment of the present invention is shown. The method specifically comprises the following steps:
s101, multi-source sensor data are obtained in real time, and the multi-source sensor data at least comprise data collected by a vehicle-mounted sensor and a roadside sensor.
In the embodiment of the invention, the multi-source sensor data can be obtained in real time through the road side routing node, and the data is uploaded to the server so as to perform data processing such as analysis, fusion and updating of the data.
In the embodiment of the present invention, the vehicle-mounted sensor mainly includes: and the navigation positioning system (GNSS) is used for acquiring vehicle positioning information, fusing the vehicle positioning information with data acquired by the roadside sensor, accurately positioning the vehicle position and analyzing the vehicle position to obtain dynamic traffic situation data. .
In an embodiment of the present invention, the roadside sensor mainly includes: the laser radar and the camera are used for acquiring lane-level vehicle track data, fusing the lane-level vehicle track data with data acquired by the vehicle-mounted sensor, accurately positioning the position of a vehicle, and analyzing the lane-level vehicle track data to obtain dynamic traffic situation data.
And S102, analyzing the multi-source sensor data to obtain dynamic traffic situation data.
Wherein the dynamic traffic situation data comprises at least: traffic congestion degree identification data, abnormal traffic incident identification data, and traffic flow identification data.
In the embodiment of the invention, a traffic state representation model taking a lane level as a main part and a road network level as an auxiliary part can be constructed based on real-time traffic original data, and then the lane-level congestion degree is identified by adopting an algorithm, so that the lane-level traffic element and the traffic congestion degree are identified.
The video event can be used as a data source, fusion calculation is carried out by combining lane level traffic states, the absolute position of the vehicles and the relative position between the vehicles are obtained and used as video event identification characteristics, the video event identification and the congestion identification are combined to determine the abnormal traffic event, and lane level abnormal event identification is realized.
And key points can be positioned and dynamic vehicle information can be extracted through a road topological structure and multi-dimensional space-time traffic information, so that the traffic flow identification of key nodes of the lane is realized.
And S103, correlating and fusing the multi-source sensor data to obtain high-precision original data.
In the embodiment of the invention, high-precision original data can be obtained by adopting a decision-level data fusion method based on joint probability based on a target association algorithm of nearest neighbor matching.
In the embodiment of the present invention, the step of associating the multi-source sensor data specifically includes:
the method comprises the following steps: and establishing a correlation gate for the multi-sensor observation data, and determining a correlation threshold, wherein the correlation gate can be rectangular or elliptical.
Step two: and filtering by using the correlation threshold to filter out obviously irrelevant observation data.
Step three: and calculating the weighted Euclidean distance between the filtered observation data, and determining the similarity between the observation data.
Step four: a correlation matrix is established based on similarities between the observed data.
Step five: and (4) correlating the multi-sensor observation data by using a nearest neighbor matching method to obtain a correlation pair.
In the embodiment of the invention, a target association algorithm based on nearest neighbor matching is adopted, the operation amount of the association process is small, the hardware is easy to realize, and the target association algorithm is suitable for target tracking systems in sparse targets and clutter environments.
In the embodiment of the present invention, the joint probability refers to a probability that a plurality of conditions are included and all the conditions are satisfied at the same time. The decision-level data fusion method specifically comprises the following steps: firstly, the attribute description is carried out on each data, and then the results are fused to obtain the fused attribute description of the target or the environment. The decision-level data fusion method has the advantages of strong fault tolerance, good openness, short processing time, low data requirement and strong analysis capability.
And S104, carrying out coordinate transformation on the high-precision original data to obtain absolute coordinate information corresponding to the high-precision original data.
In the embodiment of the invention, the longitude and latitude and height information of each traffic element can be obtained from high-precision original data, and then the longitude and latitude and height information is converted into absolute coordinates under a Cartesian coordinate system by using horizontal axis Mercator projection (UTM). The longitude and the latitude lines form a coordinate network on the spherical surface, the longitude and latitude coordinates on the spherical surface can be expressed as coordinates under a rectangular coordinate system through the projection of the horizontal axis mercator, and the conversion formula is as follows:
t＝tanB
wherein l and B are longitude and latitude of a certain point respectively; xBThe length of the meridian at the point latitude; r is the earth radius.
And S105, adding the absolute coordinate information and the dynamic traffic situation data to a pre-established 2D static high-precision map, and finishing the initial scanning of the 3D dynamic high-precision map.
In the embodiment of the invention, the traffic condition can be analyzed in real time through absolute coordinate information and dynamic traffic situation data, dynamic traffic element data are obtained, and the data are added to the pre-established 2D static high-precision map.
The pre-established 2D static high-precision map comprises building data, environment data, road data and the like.
And S106, updating the 3D dynamic high-precision map data based on the dynamic update of the multi-source sensor data to obtain a dynamically updated 3D dynamic high-precision map.
In the embodiment of the invention, the construction of the simulation model of the intelligent traffic complex scene can be realized through the implementation methods of digital twin modeling, data interface communication and real-time synchronous simulation, and the 3D dynamic high-precision map is generated.
In a preferred embodiment, the step S106 includes:
updating the motion entity data in the 3D dynamic high-precision map data based on the updating frequency of high-degree dynamic data in the multi-source sensor data;
updating traffic signal data in the 3D dynamic high-precision map data based on the updating frequency of semi-dynamic data in the multi-source sensor data;
updating traffic facility data in the 3D dynamic high-precision map data based on the updating frequency of semi-static data in the multi-source sensor data;
and updating the 2D static high-precision map data in the 3D dynamic high-precision map data based on the updating frequency of continuous static data in the multi-source sensor data.
In the embodiment of the present invention, different update frequencies are used for different types of map data, for example: the update frequency of the highly dynamic kinematic entity data is less than 100 milliseconds; the updating frequency of the semi-dynamic traffic signal data is less than 1 minute; the updating frequency of the semi-static traffic facility data is less than 1 hour; the update frequency of the continuously static 2D static high-precision map data is less than one month.
In the embodiment of the invention, different updating frequencies are adopted for different types of map data, so that the updating data volume is more consistent with the actual situation, a large amount of invalid data updating is avoided, the data communication volume can be saved, and the data processing volume can also be saved.
And S107, displaying the dynamically updated 3D dynamic high-precision map in real time through a traffic cloud control platform, and providing traffic control information in real time.
In the embodiment of the invention, the road and vehicle targets can be extracted by combining with the urban real-time traffic images on the basis of the 3D dynamic high-precision map and adopting a target detection technology based on deep learning, and the road and vehicle targets are parameterized and modeled by using a 3D modeling tool and are integrated into a three-dimensional environment. The method realizes the one-to-one mapping of the digital twin environment and the real environment, and constructs a digital twin traffic cloud control platform applied to the smart traffic.
In a preferred embodiment, the traffic control information is provided in real time through a traffic cloud control platform, and the traffic control information includes at least one of the following:
real-time traffic situation information is issued to the vehicles through a traffic cloud control platform;
performing road cooperative management based on the dynamically updated 3D dynamic high-precision map through a traffic cloud control platform;
and sending control information to the traffic signal lamp through the traffic cloud control platform.
In the embodiment of the invention, the traffic cloud control platform can form functions of traffic incident monitoring, digital traffic management, traffic signal control, public-oriented provision of second-level accompanying travel service and the like by integrating traffic data resources, and realizes active safety control of vehicles and road cooperative management.
Referring to fig. 2, a flow chart of a method of determining absolute coordinate information in an embodiment of the present invention is shown, including the steps of:
s201, performing point cloud semantic segmentation on the high-precision original data to filter out non-map element data in the high-precision original data.
In the embodiment of the invention, a point cloud semantic segmentation method based on a full Convolution neural Network (FCN) is used for filtering non-map elements of high-precision original data, and adding map element points to a map by combining an NDT (normalized difference test) registration algorithm, so that high-frequency high-precision positioning under an urban road is realized.
And S202, carrying out coordinate transformation on the map element data obtained after filtering to obtain absolute coordinate information corresponding to the map element data.
In the embodiment of the invention, the longitude and latitude and height information of the obtained map elements can be converted into absolute coordinates in a Cartesian coordinate system through horizontal axis mercator projection (UTM).
And S203, adding absolute coordinate information corresponding to the map element data to a pre-established 2D static high-precision map.
In the embodiment of the invention, absolute coordinate information corresponding to map element data obtained by transformation can be added to a pre-established 2D static high-precision map.
The step S203 specifically includes:
and adopting multi-resolution octree map representation, and adding absolute coordinate information corresponding to the map element data to a pre-established 2D static high-precision map.
The map element data corresponding to the map element with the smaller volume is represented by octree nodes expanded to a leaf node layer, and the map element data corresponding to the map element with the larger volume is represented by octree nodes expanded to a non-leaf node layer.
In the embodiment of the invention, a multi-resolution octree map representation mode is adopted, and the positioning efficiency can be improved by setting different resolutions for the ground and obstacles in the map.
In an octree, when a child node of a block is occupied or unoccupied, it is not necessary to expand the node. For example: for the ground in the map, the information is always the same, most octree nodes do not need to be expanded to the leaf level, and the storage space can be reduced. While for the ground, where obstacles appear, when obstacle information is added to the map, most octree nodes are spread out to the leaf level because the actual objects are small. Therefore, by setting different processing methods for map elements with different volumes, the storage space can be greatly reduced, and the positioning efficiency is improved.
Referring to fig. 3, a flowchart of a method for constructing a high-precision map in the embodiment of the present invention is shown, including the following steps:
s1 (not shown in the figure), acquiring and fusing multi-source sensor data to obtain high-precision original fused data; and acquiring and analyzing the data of the multi-source sensor to obtain dynamic traffic situation data.
This step is similar to the above steps S101-S103 and will not be described again here.
S2, performing point cloud semantic segmentation on the high-precision original data to filter out non-map element data in the high-precision original data.
Specifically, a point cloud semantic segmentation method based on a full Convolution neural Network (FCN) is used for carrying out non-map element filtering optimization on high-precision original data, and map element points are added into a 2D static high-precision map by combining an NDT (normalized difference test) registration algorithm, so that high-precision positioning under urban roads is realized, and a three-dimensional dynamic high-precision map with non-map elements filtered is constructed.
S3, transforming the longitude and latitude and height information of each map element into absolute coordinates in a cartesian coordinate system through horizontal axis mercator projection (UTM).
And S4, adding the absolute coordinate information and the dynamic traffic situation data to a pre-established 2D static high-precision map, and finishing the initial scanning of the 3D dynamic high-precision map.
And S5, aiming at the problem of indoor scene signal loss in underground parking lots and the like, map optimization map building is carried out by using a Pose-Graph algorithm to obtain a high-precision map.
Specifically, after the initial scanning is completed, the Pose of each frame is optimized through the Pose-Graph, and the Pose Graph optimization is performed to unify all the generated poses into a globally consistent configuration. Because the original position may have deviation from the real position, the points are directly spliced to have errors, after the points are discretized, all the points are aligned and adjusted to the accurate position through pose optimization, and the accurate high-precision map is ensured to be formed.
Based on the same invention concept, the embodiment of the invention provides a device for constructing a dynamic high-precision map. Referring to fig. 4, fig. 4 is a schematic diagram of an apparatus for constructing a dynamic high-precision map according to an embodiment of the present invention. As shown in fig. 4, the apparatus includes:
the data acquisition module 401 is configured to acquire multi-source sensor data in real time, where the multi-source sensor data at least includes data acquired by a vehicle-mounted sensor and a roadside sensor;
an analysis module 402, configured to analyze the multi-source sensor data to obtain dynamic traffic situation data, where the dynamic traffic situation data at least includes: traffic congestion degree identification data, abnormal traffic incident identification data and traffic flow identification data;
a fusion module 403, configured to correlate and fuse the multi-source sensor data to obtain high-precision original data;
a coordinate transformation module 404, configured to perform coordinate transformation on the high-precision original data to obtain absolute coordinate information corresponding to the high-precision original data;
an initial scanning module 405, configured to add the absolute coordinate information and the dynamic traffic situation data to a pre-established 2D static high-precision map, so as to complete initial scanning of the 3D dynamic high-precision map;
a dynamic update module 406, configured to update 3D dynamic high-precision map data based on dynamic update of the multi-source sensor data, so as to obtain a dynamically updated 3D dynamic high-precision map;
and the display module 407 is configured to display the dynamically updated 3D dynamic high-precision map in real time through a traffic cloud control platform, and provide traffic control information in real time.
Optionally, the coordinate transformation module 404 includes:
the filtering submodule is used for performing point cloud semantic segmentation on the high-precision original data so as to filter out non-map element data in the high-precision original data;
the coordinate transformation submodule is used for carrying out coordinate transformation on the map element data obtained after filtering to obtain absolute coordinate information corresponding to the map element data;
the initial scanning module 405 is further configured to add absolute coordinate information corresponding to the map element data to a pre-established 2D static high-precision map.
Optionally, the initial scanning module 405 includes:
the adding submodule is used for adopting multi-resolution octree map representation and adding absolute coordinate information corresponding to the map element data to a pre-established 2D static high-precision map;
the map element data corresponding to the map element with the smaller volume is represented by octree nodes expanded to a leaf node layer, and the map element data corresponding to the map element with the larger volume is represented by octree nodes expanded to a non-leaf node layer.
Optionally, the dynamic update module 406 includes:
the first dynamic updating module submodule is used for updating the motion entity data in the 3D dynamic high-precision map data based on the updating frequency of high-degree dynamic data in the multi-source sensor data;
the second dynamic updating module submodule is used for updating traffic signal data in the 3D dynamic high-precision map data based on the updating frequency of semi-dynamic data in the multi-source sensor data;
the third dynamic updating module submodule is used for updating the traffic facility data in the 3D dynamic high-precision map data based on the updating frequency of semi-static data in the multi-source sensor data;
and the fourth dynamic update module submodule is used for updating the 2D static high-precision map data in the 3D dynamic high-precision map data based on the update frequency of continuous static data in the multi-source sensor data.
Optionally, the display module 407 includes at least one of:
the real-time traffic situation information issuing sub-module is used for issuing real-time traffic situation information to the vehicles through the traffic cloud control platform;
the road cooperative management submodule carries out road cooperative management on the basis of the dynamically updated 3D dynamic high-precision map through a traffic cloud control platform;
and the control submodule is used for sending control information to the traffic signal lamp through the traffic cloud control platform.
A third aspect of the embodiments of the present invention provides a traffic cloud control platform, which displays a dynamic high-precision map constructed by the steps in any one of the methods for constructing a dynamic high-precision map according to the first aspect of the present invention in real time, and provides traffic control information in real time.
For the device embodiment, since it is basically similar to the method embodiment, the description is simple, and for the relevant points, refer to the partial description of the method embodiment.
The embodiments in the present specification are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, apparatus, or computer program product. Accordingly, embodiments of the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
Embodiments of the present invention are described with reference to flowchart illustrations and/or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing terminal to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing terminal to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing terminal to cause a series of operational steps to be performed on the computer or other programmable terminal to produce a computer implemented process such that the instructions which execute on the computer or other programmable terminal provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications of these embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the embodiments of the invention.
Finally, it should also be noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or terminal that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or terminal. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or terminal that comprises the element.
The method, the device and the traffic cloud control platform for constructing the dynamic high-precision map provided by the invention are introduced in detail, a specific example is applied in the text to explain the principle and the implementation mode of the invention, and the description of the embodiment is only used for helping to understand the method and the core idea of the invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.
Claims (10)
1. A method of constructing a dynamic high-precision map, the method comprising:
acquiring multi-source sensor data in real time, wherein the multi-source sensor data at least comprises data acquired by a vehicle-mounted sensor and a roadside sensor;
analyzing the multi-source sensor data to obtain dynamic traffic situation data, wherein the dynamic traffic situation data at least comprises the following components: traffic congestion degree identification data, abnormal traffic incident identification data and traffic flow identification data;
correlating and fusing the multi-source sensor data to obtain high-precision original data;
carrying out coordinate transformation on the high-precision original data to obtain absolute coordinate information corresponding to the high-precision original data;
adding the absolute coordinate information and the dynamic traffic situation data to a pre-established 2D static high-precision map to complete the initial scanning of the 3D dynamic high-precision map;
updating the 3D dynamic high-precision map data based on the dynamic update of the multi-source sensor data to obtain a dynamically updated 3D dynamic high-precision map;
and displaying the dynamically updated 3D dynamic high-precision map in real time through a traffic cloud control platform, and providing traffic control information in real time.
2. The method of claim 1, wherein performing coordinate transformation on the high-precision raw data to obtain absolute coordinate information corresponding to the high-precision raw data comprises:
performing point cloud semantic segmentation on the high-precision original data to filter out non-map element data in the high-precision original data;
carrying out coordinate transformation on the filtered map element data to obtain absolute coordinate information corresponding to the map element data;
adding the absolute coordinate information to a pre-established 2D static high-precision map, comprising:
and adding absolute coordinate information corresponding to the map element data to a pre-established 2D static high-precision map.
3. The method according to claim 2, wherein the adding absolute coordinate information corresponding to the map element data to a pre-established 2D static high-precision map comprises:
adopting multi-resolution octree map representation, and adding absolute coordinate information corresponding to the map element data to a pre-established 2D static high-precision map;
the map element data corresponding to the map element with the smaller volume is represented by octree nodes expanded to a leaf node layer, and the map element data corresponding to the map element with the larger volume is represented by octree nodes expanded to a non-leaf node layer.
4. The method of claim 1, wherein the updating 3D dynamic high-precision map data based on the dynamic updating of the multi-source sensor data to obtain a dynamically updated 3D dynamic high-precision map comprises:
updating the motion entity data in the 3D dynamic high-precision map data based on the updating frequency of high-degree dynamic data in the multi-source sensor data;
updating traffic signal data in the 3D dynamic high-precision map data based on the updating frequency of semi-dynamic data in the multi-source sensor data;
updating traffic facility data in the 3D dynamic high-precision map data based on the updating frequency of semi-static data in the multi-source sensor data;
and updating the 2D static high-precision map data in the 3D dynamic high-precision map data based on the updating frequency of continuous static data in the multi-source sensor data.
5. The method according to any one of claims 1 to 4, wherein the traffic control information is provided in real time by a traffic cloud control platform, and the method comprises at least one of the following steps:
real-time traffic situation information is issued to the vehicles through a traffic cloud control platform;
performing road cooperative management based on the dynamically updated 3D dynamic high-precision map through a traffic cloud control platform;
and sending control information to the traffic signal lamp through the traffic cloud control platform.
6. An apparatus for constructing a dynamic high-precision map, the apparatus comprising:
the data acquisition module is used for acquiring multi-source sensor data in real time, wherein the multi-source sensor data at least comprises data acquired by a vehicle-mounted sensor and a roadside sensor;
an analysis module, configured to analyze the multi-source sensor data to obtain dynamic traffic situation data, where the dynamic traffic situation data at least includes: traffic congestion degree identification data, abnormal traffic incident identification data and traffic flow identification data;
the fusion module is used for correlating and fusing the multi-source sensor data to obtain high-precision original data;
the coordinate transformation module is used for carrying out coordinate transformation on the high-precision original data to obtain absolute coordinate information corresponding to the high-precision original data;
the initial scanning module is used for adding the absolute coordinate information and the dynamic traffic situation data to a pre-established 2D static high-precision map to complete the initial scanning of the 3D dynamic high-precision map;
the dynamic updating module is used for updating the 3D dynamic high-precision map data based on the dynamic updating of the multi-source sensor data to obtain a dynamically updated 3D dynamic high-precision map;
and the display module is used for displaying the dynamically updated 3D dynamic high-precision map in real time through a traffic cloud control platform and providing traffic control information in real time.
7. The apparatus of claim 6, wherein the coordinate transformation module comprises:
the filtering submodule is used for performing point cloud semantic segmentation on the high-precision original data so as to filter out non-map element data in the high-precision original data;
the coordinate transformation submodule is used for carrying out coordinate transformation on the map element data obtained after filtering to obtain absolute coordinate information corresponding to the map element data;
and the initial scanning module is also used for adding the absolute coordinate information corresponding to the map element data to a pre-established 2D static high-precision map.
8. The apparatus of claim 7, wherein the initial scanning module comprises:
the adding submodule is used for adopting multi-resolution octree map representation and adding absolute coordinate information corresponding to the map element data to a pre-established 2D static high-precision map;
the map element data corresponding to the map element with the smaller volume is represented by octree nodes expanded to a leaf node layer, and the map element data corresponding to the map element with the larger volume is represented by octree nodes expanded to a non-leaf node layer.
9. The apparatus of claim 6, wherein the dynamic update module comprises:
the first dynamic updating module submodule is used for updating the motion entity data in the 3D dynamic high-precision map data based on the updating frequency of high-degree dynamic data in the multi-source sensor data;
the second dynamic updating module submodule is used for updating traffic signal data in the 3D dynamic high-precision map data based on the updating frequency of semi-dynamic data in the multi-source sensor data;
the third dynamic updating module submodule is used for updating the traffic facility data in the 3D dynamic high-precision map data based on the updating frequency of semi-static data in the multi-source sensor data;
and the fourth dynamic update module submodule is used for updating the 2D static high-precision map data in the 3D dynamic high-precision map data based on the update frequency of continuous static data in the multi-source sensor data.
10. A traffic cloud control platform, characterized in that the traffic cloud control platform displays a dynamic high-precision map constructed by the method for constructing a dynamic high-precision map according to any one of claims 1 to 5 in real time and provides traffic control information in real time.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111267215.6A CN114120631B (en) | 2021-10-28 | 2021-10-28 | Method and device for constructing dynamic high-precision map and traffic cloud control platform |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111267215.6A CN114120631B (en) | 2021-10-28 | 2021-10-28 | Method and device for constructing dynamic high-precision map and traffic cloud control platform |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114120631A true CN114120631A (en) | 2022-03-01 |
| CN114120631B CN114120631B (en) | 2023-03-24 |
Family
ID=80377460
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111267215.6A Active CN114120631B (en) | 2021-10-28 | 2021-10-28 | Method and device for constructing dynamic high-precision map and traffic cloud control platform |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114120631B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115840404A (en) * | 2022-12-21 | 2023-03-24 | 浙江大学 | Cloud control automatic driving system based on automatic driving special road network and digital twin map |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN109341706A (en) * | 2018-10-17 | 2019-02-15 | 张亮 | A kind of production method of the multiple features fusion map towards pilotless automobile |
| CN109709593A (en) * | 2018-12-28 | 2019-05-03 | 国汽(北京)智能网联汽车研究院有限公司 | Join automobile mounted terminal platform based on " cloud-end " tightly coupled intelligent network |
| CN111554088A (en) * | 2020-04-13 | 2020-08-18 | 重庆邮电大学 | Multifunctional V2X intelligent roadside base station system |
| CN111928862A (en) * | 2020-08-10 | 2020-11-13 | 廊坊和易生活网络科技股份有限公司 | Method for constructing semantic map on line by fusing laser radar and visual sensor |
| WO2020248614A1 (en) * | 2019-06-10 | 2020-12-17 | 商汤集团有限公司 | Map generation method, drive control method and apparatus, electronic equipment and system |
| CN112382085A (en) * | 2020-10-20 | 2021-02-19 | 华南理工大学 | System and method suitable for intelligent vehicle traffic scene understanding and beyond visual range perception |
| CN112434119A (en) * | 2020-11-13 | 2021-03-02 | 武汉中海庭数据技术有限公司 | High-precision map production device based on heterogeneous data fusion |
| CN113419245A (en) * | 2021-06-23 | 2021-09-21 | 北京易航远智科技有限公司 | Real-time mapping system and mapping method based on V2X |
-
2021
- 2021-10-28 CN CN202111267215.6A patent/CN114120631B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN109341706A (en) * | 2018-10-17 | 2019-02-15 | 张亮 | A kind of production method of the multiple features fusion map towards pilotless automobile |
| CN109709593A (en) * | 2018-12-28 | 2019-05-03 | 国汽(北京)智能网联汽车研究院有限公司 | Join automobile mounted terminal platform based on " cloud-end " tightly coupled intelligent network |
| WO2020248614A1 (en) * | 2019-06-10 | 2020-12-17 | 商汤集团有限公司 | Map generation method, drive control method and apparatus, electronic equipment and system |
| CN111554088A (en) * | 2020-04-13 | 2020-08-18 | 重庆邮电大学 | Multifunctional V2X intelligent roadside base station system |
| CN111928862A (en) * | 2020-08-10 | 2020-11-13 | 廊坊和易生活网络科技股份有限公司 | Method for constructing semantic map on line by fusing laser radar and visual sensor |
| CN112382085A (en) * | 2020-10-20 | 2021-02-19 | 华南理工大学 | System and method suitable for intelligent vehicle traffic scene understanding and beyond visual range perception |
| CN112434119A (en) * | 2020-11-13 | 2021-03-02 | 武汉中海庭数据技术有限公司 | High-precision map production device based on heterogeneous data fusion |
| CN113419245A (en) * | 2021-06-23 | 2021-09-21 | 北京易航远智科技有限公司 | Real-time mapping system and mapping method based on V2X |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115840404A (en) * | 2022-12-21 | 2023-03-24 | 浙江大学 | Cloud control automatic driving system based on automatic driving special road network and digital twin map |
| CN115840404B (en) * | 2022-12-21 | 2023-11-03 | 浙江大学 | Cloud control automatic driving system based on automatic driving special road network and digital twin map |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114120631B (en) | 2023-03-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wong et al. | Mapping for autonomous driving: Opportunities and challenges | |
| US20240005167A1 (en) | Annotating high definition map data with semantic labels | |
| US10891497B2 (en) | Traffic boundary mapping | |
| KR20200121274A (en) | Method, apparatus, and computer readable storage medium for updating electronic map | |
| US11590989B2 (en) | Training data generation for dynamic objects using high definition map data | |
| CN112069856A (en) | Map generation method, driving control method, device, electronic equipment and system | |
| US11514682B2 (en) | Determining weights of points of a point cloud based on geometric features | |
| US11367208B2 (en) | Image-based keypoint generation | |
| CN113034566B (en) | High-precision map construction method and device, electronic equipment and storage medium | |
| WO2021007117A1 (en) | Generating training data for deep learning models for building high definition maps | |
| CN114509065B (en) | Map construction method, system, vehicle terminal, server and storage medium | |
| CN113989451A (en) | High-precision map construction method and device and electronic equipment | |
| CN113392169A (en) | High-precision map updating method and device and server | |
| US20230121226A1 (en) | Determining weights of points of a point cloud based on geometric features | |
| Eggert et al. | Driving situation analysis with relational local dynamic maps (R-LDM) | |
| CN114120631B (en) | Method and device for constructing dynamic high-precision map and traffic cloud control platform | |
| Lucks et al. | Improving trajectory estimation using 3D city models and kinematic point clouds | |
| KR102384429B1 (en) | Method for discriminating the road complex position and generating the reinvestigation path in road map generation | |
| CN113227713A (en) | Method and system for generating environment model for positioning | |
| CN114543788A (en) | Multi-layer global perception map construction method and system universal to structural unstructured environment | |
| Liu et al. | Extracting campus’ road network from walking gps trajectories | |
| McQuat | Feature extraction workflows for urban mobile-terrestrial LIDAR data | |
| Jin et al. | An Object Association Matching Method Based on V2I System | |
| CN114693574B (en) | Unmanned simulation scene generation method and equipment | |
| US20240127603A1 (en) | Unified framework and tooling for lane boundary annotation |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |