CN112432650B - High-precision map data acquisition method, vehicle control method and device - Google Patents
High-precision map data acquisition method, vehicle control method and device Download PDFInfo
- Publication number
- CN112432650B CN112432650B CN202011303991.2A CN202011303991A CN112432650B CN 112432650 B CN112432650 B CN 112432650B CN 202011303991 A CN202011303991 A CN 202011303991A CN 112432650 B CN112432650 B CN 112432650B
- Authority
- CN
- China
- Prior art keywords
- data
- representation
- acquisition
- time
- track
- 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.)
- Active
Links
Images
Classifications
-
- 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
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W60/00—Drive control systems specially adapted for autonomous road vehicles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Engineering & Computer Science (AREA)
- Remote Sensing (AREA)
- Radar, Positioning & Navigation (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Theoretical Computer Science (AREA)
- Human Computer Interaction (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Navigation (AREA)
Abstract
The application provides a method for acquiring high-precision map data, a vehicle control method and equipment, wherein the method comprises the steps of acquiring the representation data of road elements and the track time of acquisition track points, wherein the representation data are generated according to original data, the acquisition track points are the track points for acquiring the original data, the representation data of the road elements and the track time of acquisition track points are matched, the acquisition time of the representation data is obtained, the acquisition time of the representation data is used for identifying the freshness of the road elements in the high-precision map data, the map data with acquisition time information can be further obtained, and the use reliability of the map data is improved.
Description
Technical Field
The embodiment of the application relates to the technical field of geographic information, in particular to a method for acquiring high-precision map data, a vehicle control method and equipment.
Background
The high-precision map making is divided into an inner industry and an outer industry, wherein the outer industry refers to a process of continuously collecting data of mobile measuring equipment in a mobile state, and the inner industry refers to a process of processing the continuously collected data to make a high-precision map product.
The mobile measurement device acquires map data such as point clouds, images and track points. The image and the point cloud are preprocessed separately in combination with the trajectory points, for example: preprocessing such as semantic segmentation and depth map extraction is performed on the image, and aggregation processing, classification processing, resolving processing and the like are performed on the point cloud. And then carrying out fusion processing on the preprocessed image and the point cloud to generate vectorized map data. The vectorized map data can reflect the position information of each road element on the acquired road and the attribute information of each road element. The attribute information includes: road element type, road element color, etc.
However, the map data generated in the related art cannot reflect the data acquisition time, resulting in unstable reliability of use of the map data.
Disclosure of Invention
The embodiment of the application provides a method for acquiring high-precision map data, a vehicle control method and equipment, and aims to solve the problem that the reliability of map data is low because map data generated in the prior art cannot reflect data acquisition time.
In a first aspect, the present application provides a method for acquiring high-precision map data, including:
acquiring the representation data of road elements and the track time of acquisition track points, wherein the representation data is generated according to the original data, and the acquisition track points are the track points for acquiring the original data;
matching the representation data of the road elements with the track time of the acquisition track points to obtain the acquisition time of the representation data; the collection time of the presentation data is used to identify the freshness of the road elements in the high-definition map data.
Optionally, the collecting track point is a track point of original data collected by field measurement equipment, and the matching between the representing data of the road element and the track time of the collecting track point to obtain the collecting time of the representing data includes:
determining a representation line associated with the road element corresponding to the representation data according to the track points of the field measurement equipment;
matching the track time with a representation line associated with a road element corresponding to the representation data, and determining the acquisition time of the representation line;
and acquiring the acquisition time of the representation data according to the acquisition time of the representation line associated with the road element corresponding to the representation data.
Optionally, determining a representation line associated with the road element corresponding to the representation data according to the track point of the field measurement device specifically includes:
determining the driving direction of the field measurement equipment and the road acquired by the field measurement equipment according to the track points;
and determining the representation line associated with the road element corresponding to the representation data from the incoming representation line and the outgoing representation line of the road acquired by the field measurement equipment according to the driving direction of the field measurement equipment.
Optionally, matching the track time with a representation line associated with the road element corresponding to the representation data, and determining the acquisition time of the representation line includes:
matching the key nodes of the representation line with the acquisition track points to obtain a matching result;
acquiring acquisition time of the key nodes according to the matching result and the track time;
acquiring acquisition time of the representation line according to the acquisition time of the key node.
Optionally, obtaining the acquisition time of the key node according to the matching result and the track time includes:
when the key node matches the plurality of acquisition track points, the latest track time is selected from the track times of the plurality of acquisition track points as the acquisition time of the key node.
Optionally, obtaining the acquisition time of the representation line according to the acquisition time of the key node includes:
if the number of the key nodes with the same acquisition time reaches a first preset value, taking the acquisition time of the key nodes with the same acquisition time as the acquisition time of the representation line;
and if the number of the key nodes with the same acquisition time is smaller than a first preset value, selecting the latest acquisition time from the acquisition times of all the key nodes as the acquisition time of the representation line.
Optionally, the collecting track point is a track point of original data collected by an external source device, and the matching between the representing data of the road element and the track time of the collecting track point to obtain the collecting time of the representing data includes:
and if the distance between the road element corresponding to the data and the track point of the exogenous equipment is within the preset distance threshold, the acquisition time of the data is track time.
Optionally, the vectorized map data identifying the freshness of the road elements is generated from the collection time of the representation data and the representation data, and the vectorized map data is used for generating the high-precision map data.
In a second aspect, the present application provides a vehicle control method, including:
extracting representation data of road elements and acquisition time of the representation data from the high-precision map data;
and when the acquisition time is later than a preset time threshold, controlling the automatic driving of the vehicle according to the representation data.
In a fourth aspect, the present application provides an electronic device, comprising:
a memory for storing a program;
a processor for executing a program stored in the memory, the processor being configured to execute the high-precision map data acquisition method according to the first aspect and the optional aspects when the program is executed; or alternatively
A processor for executing a program stored in the memory, the processor being configured to execute the vehicle control method according to the first aspect and the optional aspects when the program is executed.
The application provides a method for acquiring high-precision map data, a vehicle control method and equipment, wherein track time of each acquisition track point is synchronously acquired when data of a road element are acquired, when the representation data of the road element are acquired according to the acquired data of the road element, the representation data and the track time can be matched to acquire the representation data acquisition time, the acquisition time of the representation data is used for identifying freshness of the road element in the high-precision map data, further reliability of the map data can be judged through the acquisition time, whether the high-precision map data can truly reflect actual conditions of a road can be determined, and reliability in a map data use process is improved. In addition, the representation line associated with the road element corresponding to the representation data is determined according to the acquisition track point, so that the time of the representation line is determined according to the track time of the acquisition track point, and the representation data of each road element is determined according to the acquisition time of the representation line, so that the matching of the representation data with huge data quantity and the acquisition track point is realized, and the data matching calculation amount and the matching time can be effectively reduced.
Drawings
Fig. 1 is a flow chart of a method for obtaining high-precision map data according to an embodiment of the present application;
fig. 2 is a schematic diagram of a method for obtaining high-precision map data according to another embodiment of the present application;
fig. 3 is an effect schematic diagram of a method for acquiring high-precision map data according to another embodiment of the present application;
FIG. 4 is a flow chart of a vehicle control method according to another embodiment of the present disclosure;
fig. 5 is a schematic structural diagram of a data generating device according to another embodiment of the present application;
fig. 6 is a schematic structural diagram of an electronic device according to another embodiment of the present application.
Detailed Description
For the purposes of making the objects, technical solutions and advantages of the embodiments of the present application more clear, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is apparent that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present disclosure.
The high-precision map making is divided into an inner industry and an outer industry, wherein the outer industry refers to a process of continuously collecting data of mobile measuring equipment in a mobile state, and the inner industry refers to a process of processing the continuously collected data to make a high-precision map product.
The mobile measurement device acquires map data such as point clouds, images and track points. The image and the point cloud are preprocessed separately in combination with the trajectory points, for example: preprocessing such as semantic segmentation and depth map extraction is performed on the image, and aggregation processing, classification processing, resolving processing and the like are performed on the point cloud. And then carrying out fusion processing on the preprocessed image and the point cloud to generate vectorized map data. The vectorized map data can reflect the position information of each road element on the acquired road and the attribute information of each road element. The attribute information includes: road element type, road element color, etc.
However, the map data generated in the prior art cannot reflect the data acquisition time, resulting in low reliability of use of the map data.
The application provides a method for acquiring high-precision map data, a vehicle control method and a device, and aims to provide map data with data acquisition time information. The inventive concept of the present application is: and acquiring the track time of the acquisition track point when acquiring the data of the road elements, and matching the track time with the data of the road elements to obtain the map data with the acquisition time information. Compared with the representation data, the data quantity of the collected track points is smaller, when the track time is matched with the representation data of the road elements, the collection time of the representation lines associated with the road elements corresponding to the representation data is determined according to the track time of each collected track point, and therefore the data matching calculation quantity can be reduced. After acquisition time of each representation line is obtained, acquisition of the representation data can be determined according to association relations between the representation lines of the road and the representation data of each road element, and matching of the representation data of the road element and track time is achieved.
As shown in fig. 1, an embodiment of the present application provides a method for obtaining high-precision map data, where the method is applied to an electronic device, for example: a computer device. The method comprises the following steps:
s101, acquiring the representation data of the road elements and acquiring the track time of the track points.
The road element is an object located on a road, and includes a road indication line, a sign on the road, facilities on the road, and the like. For example: lane lines, road boundary lines, signs, sign bars, printed signs, bus stop boards, curbs, guardrails, and the like.
The representation data is generated from raw data, which may be collected by a map data producer using a mobile measurement device. But also the raw data provided by a third party, for example: third party vehicles with sensors, especially vision sensors.
Each frame of original data comprises track time for collecting track points and collected data. The collected data is data of the collected road elements. The data may be point cloud, image, etc. The acquisition track point refers to a running track of the mobile measurement device in the process of acquiring data, namely the acquisition track point and the data of the road elements are synchronously acquired.
The representation data of the road elements refers to the presentation data of the road elements in the high-definition map. The road element acquisition data are obtained by processing the acquired data of the road element. The presentation data can be obtained by existing processing means. When the acquired data are point clouds and images, clustering, identifying and classifying the point clouds and resolving the point clouds. And meanwhile, preprocessing such as denoising, recognition and classification processing and the like are performed on the image data. And matching the processed point cloud with the image to obtain the representation data of the road elements. The representation data may be vectorized data.
For example: when the road element is a road, the obtained representation data of the road includes lane lines, boundary lines, reference lines, direction data, and the like.
S102, matching the representation data of the road elements with the track time of the acquisition track points to obtain the acquisition time of the representation data.
The acquisition data of the acquisition track points and the road elements are synchronously acquired. The position of the road element is extracted from the representation data of the road element. According to the distance between the position of the acquisition track point and the position of the road element, the acquisition track point is matched with the road element, and then the track time of the acquisition track point is matched with the representation data of the road element, so that the acquisition time of each representation data can be obtained.
The acquisition time of each presentation data can be used to make high-precision map data. The vectorized map data can be obtained according to the collection time of the representation data and the representation data, and then the vectorized map data is subjected to data conversion, compiling and other processing to obtain high-precision map data, wherein the collection time of the representation data in the high-precision map data can identify the freshness of road elements in the high-precision map data.
In the method for acquiring high-precision map data provided by the embodiment of the application, the acquisition data and the acquisition track points are synchronously acquired, so that the acquisition track points and the representation data generated by the acquisition data can be matched, the acquisition data of the representation data of each road element can be obtained, further, the map data with the acquisition time information can be obtained, whether the high-precision map data can truly reflect the actual condition of a road or not can be determined, and the use reliability of the map data is improved.
The method for acquiring high-precision map data according to another embodiment of the present application, which is applied to an electronic device, for example, is described below in conjunction with data acquired by a map data producer: a computer device. The method comprises the following steps:
s201, obtaining the representation data of the road elements and acquiring the track time of the track points.
When the map data producer collects the data of the road elements for the first time by using the field measurement equipment, namely when no historical data exists to construct map data, corresponding representation data is directly generated according to the data of the road elements.
When the map data producer collects the road element data again, that is, updates the map data, the representation data of the road element is generated from the collected data of the road element. And finding updated area data in the historical map data, and replacing the historical data of the updated area with the acquired data to obtain the representation data of the road elements in the whole map area.
S203, matching the representation data of the road elements with the track time of the acquisition track points to obtain the acquisition time of the representation data.
The step of acquiring the track points is to acquire the track points of the original data by the field measurement device, as shown in fig. 2, and the step of matching the representation data of the road elements with the track time of the track points to acquire the map data specifically includes: determining a representation line associated with the road element corresponding to the representation data according to the track point of the field measurement equipment, matching the track time with the representation line associated with the road element corresponding to the representation data to determine the acquisition time of the representation line, and obtaining the acquisition time of the representation data according to the acquisition time of the representation line associated with the road element corresponding to the representation data.
The road representation lines include lane lines, boundary lines, reference lines, center lines, and the like. The direction of travel of the road indicated by the indication line is defined as the direction of travel of the road indicated by the indication line, and the direction of travel of the road indicated by the indication line is defined as the direction of travel. Taking the reference line as an example, the reference line is divided into a forward reference line and a backward reference line.
And determining the driving direction of the field measurement equipment and the road acquired by the field measurement equipment according to the track points. And determining the representation line associated with the road element corresponding to the representation data from the incoming representation line and the outgoing representation line of the road acquired by the field measurement equipment according to the driving direction of the field measurement equipment.
When the running mode of the field measurement device is the same as the direction of the coming representation line of the road, the representation line bit of the road associated with the road element corresponding to the representation data is used for representing the coming representation line. When the running mode of the field measurement device is opposite to the direction of the coming representation line of the road, the representation line bit of the road associated with the road element corresponding to the representation data is used for representing the line.
The position information of the road representation line may be represented by the position information of the key node of the road representation line. The key nodes may be equal points, inflection points, etc. of the road representation line. And determining a matching relationship between the representing data and the track time of the acquisition track point according to the position information of the representing line of the road associated with the road element corresponding to the representing data and the position information of the acquisition track point.
The positions of a plurality of key nodes representing the line and the positions of acquisition trajectory points are acquired. And matching the key nodes with the track time according to the positions of the acquisition track points and the key node positions of the representation lines to obtain the acquisition time of a plurality of key nodes. Acquiring acquisition time of the representation line according to the acquisition time of the plurality of key nodes.
After the position of each key node and the position of the acquisition track point are obtained, the distance between the key node and the acquisition track point is calculated. And if the distance between the key node and the acquisition track point is within the preset distance threshold, matching the key node with the acquisition track point, and setting the track time of the acquisition track point as the acquisition time of the key node.
The acquiring the acquisition time of the representation line according to the acquisition time of the plurality of key nodes specifically comprises the following steps: and if the number of the key nodes with the same acquisition time reaches a first preset value, setting the acquisition time of the key nodes with the same acquisition time as the acquisition time of the representation line. And if the number of the key nodes with the same acquisition time is smaller than a first preset value, selecting the latest acquisition time from the acquisition times of all the key nodes as the acquisition time of the representation line. The first preset value may be set to 2.
For example: the road representation line has 3 key points, labeled as point a, point B and point C. By matching the acquisition track points with the key points, the acquisition time of the point A and the point B is 2 months and 20 days, and the acquisition time of the point C is 2 months and 21 days. And if the acquisition time of the point A and the acquisition time of the point B are the same, the acquisition time of the road representation line is 2 months and 21 days.
Also for example: by matching the acquisition track points with the key points, the acquisition time of the point A is 2 months and 20 days, the acquisition time of the point B is 2 months and 22 days, and the acquisition time of the point C is 2 months and 21 days. And if the same key node does not exist and the acquisition time of the point B is up to date, the acquisition time of the road representation line is 2 months and 22 days.
When the acquisition track points are matched with key nodes of the road representation line, the joint nodes are matched with a plurality of track points, and then when a plurality of acquisition times are corresponding, the latest acquisition time is selected from the plurality of acquisition times to serve as the acquisition time of the key nodes.
The preferable representation line is a road reference line, and after acquisition time of the road reference line is obtained, the acquisition time of the road element can be determined through association relationship between the road element and the reference line.
In the method for acquiring high-precision map data provided by the embodiment of the application, aiming at the map data producer, the collected data of each road representation line can be acquired by adopting a way of matching the collected track points with the road representation lines, compared with the way that the collected track points are directly matched with the representation data of each road element, the quantity of the matched data is greatly reduced, the relevance between the road representation lines and the representation data of the road elements is further realized, the collection time of the representation lines associated with each road element is given to the representation data, and the matching of the representation data of the road elements and the track time is realized.
The method for acquiring high-precision map data according to another embodiment of the present application is described below with reference to third party acquired data, and the method is applied to an electronic device, for example: a computer device. The method comprises the following steps:
s301, acquiring the representation data of the road elements and acquiring the track time of the track points.
After the original data acquired by the external source equipment are obtained, the original data are processed to obtain the representation data of the road elements, and the acquisition track points and the track time of the acquisition track points in the original data are extracted.
S302, matching the representation data of the road elements with the track time of the acquisition track points to obtain the acquisition time of the representation data.
The method comprises the steps that because the data amount of original data acquired by the external source equipment is small, the representing data and the acquisition track points are directly matched, namely, the positions of road elements corresponding to the representing data and the positions of the acquisition track points are acquired, and when the distance between the positions of the road elements and the positions of the acquisition track points is within a preset distance threshold, the track time is set to be the acquisition time of the representing data.
The method includes comparing the representation data of the road element with existing vectorized map data, if the existing vectorized map data is the same as the representation data from the external source device, then updating the vectorized map data is not needed, and if the existing vectorized map data is different from the representation data from the external source device, then updating the existing vectorized map data by using the representation data from the external source device.
In the method for acquiring high-precision map data provided by the embodiment of the application, because the data volume of the road elements obtained by the external source equipment is smaller, the representation data of the road elements are directly matched with the acquisition track points, the map data with acquisition time information can be obtained, and the use reliability of the map data is improved.
A method for acquiring high-precision map data according to another embodiment of the present application is described below with reference to an example, and includes the following steps:
s401, acquiring multi-frame original data of the road elements.
The original data is acquired from two sources, namely, the map data producer acquires the data on site by using a mobile measuring device with laser, camera and other equipment, and acquires the acquired data of road elements such as real-world roads, roadside facilities and the like. The other is to acquire visual sensor data in real time through intelligent automobile equipment with a sensor. The two types of acquired data include vehicle type trajectories, and GNSS (english full name: global Navigation Satellite System) data are generally used. As shown in table 1, the vehicle model trajectory data recorded in the computer includes the trajectory position point and the GNSS time.
TABLE 1 vehicle model trajectory data
S402, obtaining the representation data of the road elements according to the collected data of the road elements in each frame of data.
The collected data of the road elements are processed to obtain the representation data, which is shown in table 2, and the freshness information field is reserved in table 2. When the acquisition time of the representation data is obtained by matching the representation data with the track time, the acquisition time information and the freshness information source can be filled in table 2.
Table 2 data representing road elements
S403, matching the representation data of the road elements with the track time of the acquisition track points to obtain the acquisition time of the representation data.
The process of obtaining map data is described below in connection with data collected by a map data producer and data collected by a third party, respectively.
The method comprises the steps of acquiring data of a map data producer, wherein when the acquired track points are matched with key points of a road representation line, pre-matching is performed. Namely, the acquisition track points are matched with the representation lines, and then the acquisition track points are matched with the building nodes of the representation lines.
The pre-matching is accomplished as follows. And obtaining an interest area of the road, wherein the interest area is an area formed by the road and extending a preset distance from the road boundary outwards transversely. Typically extending 5 meters. The maximum height of the region of interest within the road boundary is 10 meters from the road surface. The maximum height of the region of interest outside the road boundary is 20 meters from the ground.
And determining the road where the acquisition track point is located according to the coordinate information of the acquisition track point and the interest area range, and completing the matching of the acquisition track point and the road. When the track points are matched with the road, the track travel direction can be obtained through track time of the track points, and when the track travel direction of the track points is consistent with the road reference line marking direction, the track can be confirmed to be completely matched with the road. When the reference lines are inconsistent, the reference lines in the other direction are selected for matching.
And acquiring key nodes of the representation line, taking a reference line as an example, traversing the starting point, the middle point and the end point according to the road direction, and taking the key nodes as key nodes. Labeled link1-n1, link2-n2, link3-n3. And constructing an area with the radius being a preset radius threshold value by taking a key node of the road reference line as a center. At a lane width of 3m, a radius threshold of 10m may be configured. Searching the nearest track point in the radius threshold range, assigning the time information of the track point to the corresponding key node, wherein the same key node has a plurality of acquisition times, and taking the newer time information as the acquisition time of the key node. Table 3 may be constructed to record the acquisition times of the critical nodes.
TABLE 3 time of acquisition of key nodes
And determining the acquisition time of the reference line according to the acquisition time of the key node. The method comprises the following steps:
when the number of the key nodes with the same acquisition time reaches 2, the acquisition time of the reference line is the acquisition time of the key nodes with the same acquisition time, and meanwhile, the data acquisition source information is assigned.
When the time information of the key nodes of the road reference line is different, the latest acquisition time is taken as the acquisition of the reference line, and the acquisition data set source information of the corresponding time is assigned.
And according to the association information of other elements and the reference line, assigning the time of the corresponding reference line to the other elements, and simultaneously assigning and collecting source information.
And assigning the track time to the representation data of the change element in the process of automatically identifying the change data aiming at the data acquired by the third party. When triggering automatic updating to the original high-precision map, the data, the time information and the data acquisition source information are synchronously updated to the original high-precision map.
In addition, the updated road element is marked as "update", and each time the road element is automatically updated, the road element is emptied and marked again. In order to express high-precision map freshness, it is necessary to refresh time for the area elements that have not changed. The refreshing method is the same as the method for the map data producer to obtain the map data, and will not be described here again.
After the acquisition time of the changed and unchanged representation data is updated, checking whether the time information of the same element assigned for a plurality of times exists, if so, reporting errors, and carrying out manual checking and confirmation.
As shown in fig. 3, when map data is used, the acquisition time and the data source of the representation data of the road elements can be checked by selecting the road elements on the display interface. After the traffic plate is selected, the traffic plate can be checked, the acquisition time of the traffic plate is 2020, 2 months and 1 day, and the traffic plate is sourced from a crowdsourcing updated data source.
In the method for acquiring high-precision map data provided by the embodiment of the application, the acquisition track points and the representation data generated by the acquisition data can be matched, so that the map data with acquisition time information can be obtained, and the use reliability of the map data is improved.
Another embodiment of the present application provides a method for acquiring high-precision map data, where an execution subject is an electronic device such as a server, a personal computer, etc., and the method includes the following steps:
s501, acquiring the representation data of the road elements and acquiring the track time of the track points.
S502, obtaining the representation data of the road elements according to the collected data of the road elements in each frame of data.
S503, matching the representation data of the road elements with the track time of the acquisition track points to obtain the acquisition time of the representation data.
Among them, S501 to S503 have been described in detail in the above embodiments, and are not described here.
S504, generating vectorization map data for identifying the freshness of the road elements according to the acquisition time of the representation data and the representation data.
After acquisition time of the representation data of each road element is obtained, vectorization processing is performed on the representation data of the road element and the acquisition time of the representation data to obtain vectorized map data.
After the vectorized map data is obtained, the vectorized map data is subjected to data conversion, encoding and other processes to obtain high-precision map data.
According to the map data acquisition method, the vectorized map data are generated according to the acquisition time of the representation data and the representation data, the obtained vectorized map data can reflect freshness information of each road element, and the use reliability of the map data is improved.
As shown in fig. 4, another embodiment of the present application provides a vehicle control method, which is applied to a vehicle terminal. The method comprises the following steps:
s601, extracting the representation data of the road elements and the acquisition time of the representation data from the high-precision map data.
Wherein the high-precision map data is obtained according to the method for obtaining high-precision map data provided by the above embodiment. The vehicle terminal can locally load the high-precision map data and can transmit the high-precision map data in real time through the map server.
After the high-precision map data is obtained, the representation data of the road elements and the acquisition time of the representation data are extracted from the high-precision map data to perform automatic driving control according to the representation data and the acquisition time.
S602, judging whether the acquisition time is later than a preset time threshold, if so, entering S603, otherwise, entering S604.
The earlier the acquisition time is, the worse the consistency between the actual condition of the road and the high-precision map data is. On the contrary, the closer the acquisition time is, the better the consistency between the actual road condition and the high-precision map data is.
And S603, controlling the automatic driving of the vehicle according to the representation data when the acquisition time is later than a preset time threshold.
If the acquisition time is later than a preset time threshold, namely the use reliability of the map data is high, the vehicle enters an automatic driving mode. That is, a control command is generated based on the presentation data, and the vehicle is controlled to automatically drive based on the control command.
S604, stopping controlling the vehicle to enter an automatic driving mode when the acquisition time is earlier than or equal to a preset time threshold.
When the acquisition time is earlier than or equal to a preset time threshold, namely the map data is low in use reliability, the vehicle is controlled to exit from the automatic driving mode.
In the vehicle control method provided by the embodiment of the application, when the acquisition time of the map data is earlier than or equal to the preset time threshold, the vehicle is controlled to automatically drive, and the automatic driving reliability is improved.
As shown in fig. 5, another embodiment of the present application provides a map data generating apparatus, including:
a first obtaining module 701, configured to obtain representation data of a road element and a track time of an acquisition track point, where the representation data is generated according to original data, and the acquisition track point is a track point for acquiring the original data;
the first processing module 702 is configured to match the representation data of the road element with the track time of the acquisition track point, so as to obtain the acquisition time of the representation data; the collection time of the presentation data is used to identify the freshness of the road elements in the high-definition map data.
Optionally, the acquisition track point is a track point where the field measurement device acquires raw data, and the first processing module 702 is specifically configured to:
determining a representation line associated with the road element corresponding to the representation data according to the track points of the field measurement equipment;
matching the track time with a representation line associated with a road element corresponding to the representation data, and determining the acquisition time of the representation line;
and acquiring the acquisition time of the representation data according to the acquisition time of the representation line associated with the road element corresponding to the representation data.
Optionally, the first processing module 702 is specifically configured to:
determining the driving direction of the field measurement equipment and the road acquired by the field measurement equipment according to the track points;
and determining the representation line associated with the road element corresponding to the representation data from the incoming representation line and the outgoing representation line of the road acquired by the field measurement equipment according to the driving direction of the field measurement equipment.
Optionally, the first processing module 702 is specifically configured to:
matching the key nodes of the representation line with the acquisition track points to obtain a matching result;
acquiring acquisition time of the key nodes according to the matching result and the track time;
acquiring acquisition time of the representation line according to the acquisition time of the key node.
Optionally, the first processing module 702 is specifically configured to:
when the key node matches the plurality of acquisition track points, the latest track time is selected from the track times of the plurality of acquisition track points as the acquisition time of the key node.
Optionally, the first processing module 702 is specifically configured to:
if the number of the key nodes with the same acquisition time reaches a first preset value, taking the acquisition time of the key nodes with the same acquisition time as the acquisition time of the representation line;
and if the number of the key nodes with the same acquisition time is smaller than a first preset value, selecting the latest acquisition time from the acquisition times of all the key nodes as the acquisition time of the representation line.
Optionally, the acquisition track point is a track point where the external device acquires the original data, and the first processing module 702 is further configured to:
and if the distance between the road element corresponding to the data and the track point of the exogenous equipment is within the preset distance threshold, the acquisition time of the data is track time.
Optionally, the first processing module 702 is further configured to:
and generating vectorized map data for identifying the freshness of the road elements according to the acquisition time of the representation data and the representation data, wherein the vectorized map data is used for generating high-precision map data.
Another embodiment of the present application provides a vehicle control apparatus including:
a second acquisition module for extracting the representation data of the road elements and the acquisition time of the representation data from the high-precision map data;
and the second acquisition module is used for controlling the automatic driving of the vehicle according to the representation data when the acquisition time is later than a preset time threshold.
As shown in fig. 6, an electronic device 800 provided in another embodiment of the present application includes: a memory 803 and a processor 804.
A memory 803 for storing computer-executable instructions;
a processor 804 for executing computer-executable instructions stored in a memory to implement the steps executed by the high-precision map data acquisition method or the vehicle control method in the above-described embodiment. Reference may be made specifically to the foregoing high-precision map data acquisition method or the related description in the vehicle control method embodiment.
Alternatively, the memory 803 may be separate or integrated with the processor 804. When the memory 803 is provided separately, the client device further comprises a bus for connecting the memory 803 and the processor 804.
When the electronic device is used for running the vehicle control method, the electronic device is a vehicle terminal or a vehicle including the vehicle terminal.
The embodiment of the application also provides a computer readable storage medium, wherein computer execution instructions are stored in the computer readable storage medium, and when a processor executes the computer execution instructions, the method for acquiring the high-precision map data or the method for controlling the vehicle, which are executed by the electronic equipment, are realized.
Those of ordinary skill in the art will appreciate that: all or part of the steps for implementing the method embodiments described above may be performed by hardware associated with program instructions. The foregoing program may be stored in a computer readable storage medium. The program, when executed, performs steps including the method embodiments described above; and the aforementioned storage medium includes: various media that can store program code, such as ROM, RAM, magnetic or optical disks.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present application.
Claims (10)
1. A method for acquiring high-precision map data, comprising:
acquiring representation data of road elements and track time of acquisition track points, wherein the representation data is generated according to original data, the acquisition track points are track points for acquiring the original data, each frame of original data comprises track time for acquiring the track points and acquisition data, the acquisition data is data of the acquired road elements, and the acquisition track points and the acquisition data of the road elements are synchronously acquired;
matching the representation data of the road elements with the track time of the acquisition track points to obtain the acquisition time of the representation data; the acquisition time of the representation data is used to identify the freshness of the road elements in the high-precision map data.
2. The method according to claim 1, wherein the acquiring the track point is a track point of acquiring the raw data by a field measurement device, and matching the representation data of the road element with a track time of the acquiring the track point to obtain the acquisition time of the representation data includes:
determining a representation line associated with the road element corresponding to the representation data according to the track point of the field measurement equipment;
matching the track time with a representation line associated with the road element corresponding to the representation data, and determining the acquisition time of the representation line;
and acquiring the acquisition time of the representation data according to the acquisition time of the representation line associated with the road element corresponding to the representation data.
3. The method according to claim 2, wherein determining the representation line associated with the road element corresponding to the representation data according to the track point of the field measurement device specifically comprises:
determining the driving direction of the field measurement equipment and the road acquired by the field measurement equipment according to the track points;
and determining a representation line associated with the road element corresponding to the representation data from the incoming representation line and the outgoing representation line of the road acquired by the field measurement equipment according to the driving direction of the field measurement equipment.
4. The method of claim 2, wherein matching the track time with a representation line associated with a road element to which the representation data corresponds, and determining the collection time of the representation line, comprises:
matching the key nodes of the representation line with the acquisition track points to obtain a matching result;
acquiring acquisition time of the key nodes according to the matching result and the track time;
and acquiring the acquisition time of the representation line according to the acquisition time of the key node.
5. The method of claim 4, wherein obtaining the acquisition time of the key node based on the matching result and the trajectory time comprises:
and when the key node is matched with a plurality of acquisition track points, selecting the latest track time from the track time of the acquisition track points as the acquisition time of the key node.
6. The method of claim 4, wherein obtaining the acquisition time of the representation line from the acquisition time of the key node comprises:
if the number of the key nodes with the same acquisition time reaches a first preset value, taking the acquisition time of the key nodes with the same acquisition time as the acquisition time of the representation line;
and if the number of the key nodes with the same acquisition time is smaller than a first preset value, selecting the latest acquisition time from the acquisition times of all the key nodes as the acquisition time of the representation line.
7. The method according to claim 1, wherein the acquiring the track point is a track point of the original data acquired by the external device, and the matching the representation data of the road element with the track time of the acquiring the track point to obtain the acquisition time of the representation data includes:
and if the distance between the road element corresponding to the representation data and the track point of the exogenous equipment is within a preset distance threshold, the acquisition time of the representation data is the track time.
8. The method according to any one of claims 1 to 7, further comprising:
and generating vectorized map data for identifying the freshness of the road elements according to the acquisition time of the representation data and the representation data, wherein the vectorized map data is used for generating the high-precision map data.
9. A vehicle control method characterized by comprising:
extracting representation data of road elements and acquisition time of the representation data from high-precision map data; wherein the high-precision map data is obtained according to the high-precision map data acquisition method as set forth in claim 1;
and when the acquisition time is later than a preset time threshold, controlling the automatic driving of the vehicle according to the representation data.
10. An electronic device, comprising:
a memory for storing a program;
a processor for executing the program stored in the memory, the processor being configured to execute the high-precision map data acquisition method according to any one of claims 1 to 8 when the program is executed; or alternatively
The processor is configured to execute the program stored in the memory, and when the program is executed, the processor is configured to execute the vehicle control method as set forth in claim 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011303991.2A CN112432650B (en) | 2020-11-19 | 2020-11-19 | High-precision map data acquisition method, vehicle control method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011303991.2A CN112432650B (en) | 2020-11-19 | 2020-11-19 | High-precision map data acquisition method, vehicle control method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112432650A CN112432650A (en) | 2021-03-02 |
| CN112432650B true CN112432650B (en) | 2023-07-07 |
Family
ID=74692729
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011303991.2A Active CN112432650B (en) | 2020-11-19 | 2020-11-19 | High-precision map data acquisition method, vehicle control method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112432650B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114111814A (en) * | 2021-10-21 | 2022-03-01 | 北京百度网讯科技有限公司 | High-precision map data processing method and device, electronic equipment and storage medium |
| CN114187412B (en) * | 2021-11-11 | 2024-03-22 | 北京百度网讯科技有限公司 | High-precision map generation method and device, electronic equipment and storage medium |
| CN114705180B (en) * | 2022-06-06 | 2023-03-24 | 中汽创智科技有限公司 | Data correction method, device and equipment for high-precision map and storage medium |
| CN116182794A (en) * | 2023-04-25 | 2023-05-30 | 智道网联科技(北京)有限公司 | High-precision map road surface height generation method and device, electronic equipment and storage medium |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP5064870B2 (en) * | 2007-04-17 | 2012-10-31 | 株式会社日立製作所 | Digital road map generation method and map generation system |
| US10359295B2 (en) * | 2016-09-08 | 2019-07-23 | Here Global B.V. | Method and apparatus for providing trajectory bundles for map data analysis |
| CN108694882B (en) * | 2017-04-11 | 2020-09-22 | 百度在线网络技术（北京）有限公司 | Method, device and equipment for labeling map |
| CN109635052B (en) * | 2018-10-31 | 2023-02-28 | 阿波罗智能技术(北京)有限公司 | Point cloud data processing method and device and storage medium |
| CN111380543B (en) * | 2018-12-29 | 2023-05-05 | 沈阳美行科技股份有限公司 | Map data generation method and device |
-
2020
- 2020-11-19 CN CN202011303991.2A patent/CN112432650B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN112432650A (en) | 2021-03-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112432650B (en) | High-precision map data acquisition method, vehicle control method and device | |
| US20200393265A1 (en) | Lane line determination for high definition maps | |
| US8811748B2 (en) | Collaborative feature extraction system for three dimensional datasets | |
| US11590989B2 (en) | Training data generation for dynamic objects using high definition map data | |
| US11367208B2 (en) | Image-based keypoint generation | |
| CN110287276A (en) | High-precision map updating method, device and storage medium | |
| CN112380317B (en) | High-precision map updating method and device, electronic equipment and storage medium | |
| US10928819B2 (en) | Method and apparatus for comparing relevant information between sensor measurements | |
| US20210004021A1 (en) | Generating training data for deep learning models for building high definition maps | |
| CN113034566B (en) | High-precision map construction method and device, electronic equipment and storage medium | |
| CN111427904B (en) | High-precision map data updating method and device and electronic equipment | |
| CN113358125B (en) | Navigation method and system based on environment target detection and environment target map | |
| EP3968609A1 (en) | Control method, vehicle, and server | |
| EP4273501A1 (en) | Method, apparatus, and computer program product for map data generation from probe data imagery | |
| EP4202365A1 (en) | Method, apparatus, and computer program product for identifying and correcting lane geometry in map data | |
| CN115344655A (en) | Method and device for finding change of feature element, and storage medium | |
| CN113392169A (en) | High-precision map updating method and device and server | |
| CN114625744A (en) | Updating method and device of electronic map | |
| CN111651547B (en) | Method and device for acquiring high-precision map data and readable storage medium | |
| CN113496182A (en) | Road extraction method and device based on remote sensing image, storage medium and equipment | |
| KR102384429B1 (en) | Method for discriminating the road complex position and generating the reinvestigation path in road map generation | |
| CN115790655A (en) | Update vector quality evaluation method, electronic device, and program product | |
| Wang et al. | GPS trajectory-based segmentation and multi-filter-based extraction of expressway curbs and markings from mobile laser scanning data | |
| JP6224343B2 (en) | Server apparatus, information processing method, information processing system, and information processing program | |
| US20230358566A1 (en) | Method, apparatus, and computer program product for map geometry generation based on object detection |
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 |