CN115668333A - Electronic map generation method and device, computer equipment and storage medium - Google Patents

Electronic map generation method and device, computer equipment and storage medium Download PDF

Info

Publication number
CN115668333A
CN115668333A CN202080099129.6A CN202080099129A CN115668333A CN 115668333 A CN115668333 A CN 115668333A CN 202080099129 A CN202080099129 A CN 202080099129A CN 115668333 A CN115668333 A CN 115668333A
Authority
CN
China
Prior art keywords
track
track unit
unit
path
current
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202080099129.6A
Other languages
Chinese (zh)
Inventor
李煊
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
DeepRoute AI Ltd
Original Assignee
DeepRoute AI Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by DeepRoute AI Ltd filed Critical DeepRoute AI Ltd
Publication of CN115668333A publication Critical patent/CN115668333A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
    • G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
    • G09B29/00—Maps; Plans; Charts; Diagrams, e.g. route diagram

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Business, Economics & Management (AREA)
  • Educational Administration (AREA)
  • Educational Technology (AREA)
  • General Physics & Mathematics (AREA)
  • Image Analysis (AREA)
  • Instructional Devices (AREA)

Abstract

An electronic map generation method, an electronic map generation device, a computer device and a storage medium comprise: acquiring a path track; determining a current sequence track unit in the path track and at least one preorder track unit positioned in front of the current sequence track unit according to the arrangement sequence; screening a matching track unit matched with the current sequence track unit from at least one preorder track unit according to the spatial position information of the current sequence track unit and the spatial position information of the preorder track units; acquiring the hierarchy information of the matching track units, and performing hierarchy marking on the current sequential track units based on the hierarchy information; determining a next sequential track unit according to the arrangement sequence, and taking the next sequential track unit as a current sequential track unit for iteration until the last sequential track unit; and generating the electronic map based on the track units marked with the hierarchical information. By adopting the method, the accuracy of the electronic map can be improved.

Description

Electronic map generation method and device, computer equipment and storage medium Technical Field
The application relates to an electronic map generation method, an electronic map generation device, computer equipment and a storage medium.
Background
With the development of science and technology, electronic maps have become an indispensable tool in life. The existing electronic map generation method can be generally divided into several steps of data acquisition, data preprocessing, map generation, semantic information extraction, data post-processing and the like.
In urban roads, many levels of travel spaces such as viaducts, underground parking lots, and the like are often present.
However, at present, the preprocessing process of the three-dimensional data acquired by the multi-level driving space is not accurate, so that the accuracy of the electronic map is influenced.
Disclosure of Invention
According to various embodiments disclosed in the present application, an electronic map method, an apparatus, a computer device, and a storage medium are provided.
An electronic map generation method, comprising:
acquiring a path track; the path trajectory comprises at least one trajectory unit; the track unit comprises acquisition time and space position information; the path track is obtained by sequencing at least one track unit according to the acquisition time;
determining a current sequence track unit in the path track and at least one preorder track unit positioned in front of the current sequence track unit according to the arrangement sequence;
screening a matching track unit matched with the current sequence track unit from the at least one preorder track unit according to the spatial position information of the current sequence track unit and the spatial position information of the preorder track units;
acquiring the level information of the matching track units, and marking the level of the current sequential track units based on the level information;
determining a next sequential track unit according to the arrangement sequence, and taking the next sequential track unit as a current sequential track unit for iteration until the last sequential track unit;
and generating the electronic map based on the track units marked with the hierarchical information.
An electronic map generation apparatus, characterized in that the apparatus comprises:
the path track acquisition module is used for acquiring a path track; the path trajectory comprises at least one trajectory unit; the track unit comprises acquisition time and space position information; the path track is obtained by sequencing at least one track unit according to the acquisition time;
the hierarchical marking module is used for determining a current sequence track unit in the path track and at least one preorder track unit positioned in front of the current sequence track unit according to the arrangement sequence; screening a matching track unit matched with the current sequence track unit from the at least one preorder track unit according to the spatial position information of the current sequence track unit and the spatial position information of the preorder track units; acquiring the hierarchy information of the matching track units, and performing hierarchy marking on the current sequential track units based on the hierarchy information; determining a next sequential track unit according to the arrangement sequence, and taking the next sequential track unit as a current sequential track unit for iteration until the last sequential track unit;
and the electronic map generating module is used for generating an electronic map based on the track unit marked with the hierarchy information.
A computer device comprising a memory and one or more processors, the memory having stored therein computer-readable instructions that, when executed by the processors, cause the one or more processors to perform the steps of:
acquiring a path track; the path trajectory comprises at least one trajectory unit; the track unit comprises acquisition time and space position information; the path track is obtained by sequencing at least one track unit according to the acquisition time;
determining a current sequence track unit in the path track and at least one preorder track unit positioned in front of the current sequence track unit according to the arrangement sequence;
screening a matching track unit matched with the current sequence track unit from the at least one preorder track unit according to the spatial position information of the current sequence track unit and the spatial position information of the preorder track units;
acquiring the hierarchy information of the matching track units, and performing hierarchy marking on the current sequential track units based on the hierarchy information;
determining a next sequential track unit according to the arrangement sequence, and performing iteration by taking the next sequential track unit as a current sequential track unit until a final sequential track unit;
and generating the electronic map based on the track units marked with the hierarchical information.
One or more non-transitory computer-readable storage media storing computer-readable instructions that, when executed by one or more processors, cause the one or more processors to perform the steps of:
acquiring a path track; the path trajectory comprises at least one trajectory unit; the track unit comprises acquisition time and space position information; the path track is obtained by sequencing at least one track unit according to the acquisition time;
determining a current sequence track unit in the path track and at least one preorder track unit positioned in front of the current sequence track unit according to the arrangement sequence;
screening a matching track unit matched with the current sequence track unit from the at least one preorder track unit according to the spatial position information of the current sequence track unit and the spatial position information of the preorder track units;
acquiring the level information of the matching track units, and marking the level of the current sequential track units based on the level information;
determining a next sequential track unit according to the arrangement sequence, and taking the next sequential track unit as a current sequential track unit for iteration until the last sequential track unit;
and generating the electronic map based on the track units marked with the hierarchical information.
The details of one or more embodiments of the application are set forth in the accompanying drawings and the description below. Other features and advantages of the application will be apparent from the description and drawings, and from the claims.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required to be used in the embodiments will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a diagram of an application scenario of a method for generating an electronic map according to an embodiment;
FIG. 2 is a schematic flow chart diagram of a method for electronic map generation in one embodiment;
FIG. 3A is a schematic aerial view of a spatial coordinate system according to an embodiment;
FIG. 3B is a three-dimensional schematic diagram of a spatial coordinate system in one embodiment;
FIG. 4 is a schematic flow chart of generating an electronic map based on a grid map according to an embodiment;
FIG. 5 is a block diagram of an electronic map generation apparatus in one embodiment;
FIG. 6 is a block diagram of an electronic map generating apparatus in another embodiment;
FIG. 7 is a block diagram of a computer device in one embodiment.
Detailed Description
In order to make the technical solutions and advantages of the present application more clearly understood, the present application is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
The electronic map generation method provided by the application can be applied to the application environment shown in fig. 1. Wherein the mapping cart 102 communicates with the server 104 over a network. The mapping vehicle 102 refers to a vehicle that is equipped with various sensors and collects field data based on the various sensors. The mapping vehicle 102 collects the track units, sends the collected track units to the server 104, and the server 104 preprocesses the track units and generates an electronic map based on the preprocessed track units. The server 104 may be implemented as a stand-alone server or a server cluster composed of a plurality of servers.
In one embodiment, as shown in fig. 2, an electronic map generation method is provided, which is described by taking the method as an example applied to the server in fig. 1, and includes the following steps:
s202, acquiring a path track; the path trajectory comprises at least one trajectory unit; the track unit comprises acquisition time and space position information; the path trajectory is obtained by sequencing at least one trajectory unit according to the acquisition time.
The track unit is a data collection set acquired by various sensors installed in the surveying and mapping vehicle. The track unit comprises space position information, a three-dimensional point cloud image, and acquisition time for acquiring the space position information and the three-dimensional point cloud information. The spatial position information refers to the position coordinates of the surveying and mapping vehicle in a Cartesian coordinate system; the three-dimensional point cloud image is point cloud data acquired by a laser sensor erected on the surveying and mapping vehicle; the acquisition time refers to the time point when the mapping vehicle acquires the spatial position information and the three-dimensional point cloud image. It is easy to understand that the acquisition time of the spatial position information in the same track unit is consistent with the acquisition time of the three-dimensional point cloud image.
Specifically, a laser sensor and a Global Positioning System (GPS) Positioning System may be pre-erected on the surveying and mapping vehicle, the laser sensor transmits a detection signal to the driving area according to a preset acquisition frequency, and a signal reflected by an object in the driving area is compared with the detection signal to obtain surrounding environment data, and a three-dimensional point cloud image is generated based on the environment data; and determining the longitude and latitude coordinates and the altitude of the current position by the GPS according to the same preset acquisition frequency, and converting the longitude and latitude coordinates and the altitude of the current position into spatial position information.
When the surveying vehicle receives a data acquisition instruction sent by the server, the surveying vehicle controls the GPS to determine the longitude and latitude coordinates and the altitude of the current position, establishes a space coordinate system by taking the center of a laser sensor erected on the surveying vehicle as an origin, and converts the longitude and latitude coordinates and the altitude of the current position into three-dimensional space position coordinates in the space coordinate system. Referring to fig. 3, as shown in fig. 3, the established spatial coordinate system takes the center of the laser sensor mounted on the surveying vehicle as the origin; a horizontal plane horizontal to the ground is taken as a reference plane (namely, the horizontal plane horizontal to the ground is taken as an XOY plane); taking an axis horizontal to the motion direction of the surveying and mapping vehicle as a Y axis; taking an axis which is in the reference plane, passes through the origin and is perpendicular to the Y axis as the X axis; the axis passing through the origin and perpendicular to the reference plane is taken as the Z-axis. FIG. 3A is a schematic aerial view of a spatial coordinate system according to an embodiment. FIG. 3B is a three-dimensional diagram of a spatial coordinate system according to one embodiment. It is easy to understand that, before receiving a data acquisition stop instruction sent by a server, the GPS positioning system converts the longitude and latitude coordinates and the altitude with reference to the spatial coordinates established when receiving the data acquisition instruction.
Meanwhile, when a data acquisition instruction sent by the server is received, the surveying and mapping vehicle controls the laser sensor to acquire surrounding environment data, and a three-dimensional point cloud image is generated based on the surrounding environment data. When acquiring the three-dimensional point cloud image and the spatial position information acquired at the same moment, the mapping vehicle integrates the acquisition time of the three-dimensional point cloud image, the spatial position information, the three-dimensional point cloud image and the spatial position information to obtain a track unit, and at least one track unit acquired in the acquisition time period is sent to the server.
Further, the server receives at least one track unit acquired in the acquisition time period, and sorts the received at least one track unit based on the acquisition time in the track unit to obtain a path track. For example, when a mapping vehicle travels through a multi-storey parking lot within an acquisition period, the mapping vehicle acquires spatial position information of the mapping vehicle in the multi-storey parking lot and a three-dimensional point cloud image of the multi-storey parking lot according to a preset acquisition frequency, and combines the spatial position information, the three-dimensional point cloud image and acquisition time into a track unit. After the collection is finished, the mapping vehicle sequences the plurality of track units according to the ascending sequence of the collection time to obtain the path track in the multilayer parking lot.
In one embodiment, because errors may occur in the acquisition frequencies of the GPS positioning system and the laser sensor, the spatial positioning information and the three-dimensional point cloud image whose acquisition time difference is within a preset difference range may also be combined into the same track unit, and the acquisition time of the spatial positioning information or the acquisition time of the three-dimensional point cloud image may be used as the acquisition time in the track unit. For example, when the acquisition time of the spatial positioning information a is a, the acquisition time of the three-dimensional point cloud image B is B, and when the time difference between a and B is smaller than a preset time threshold, the trajectory unit is obtained by combining a, B and a.
In one embodiment, the spatial position information is often inaccurate due to satellite signal occlusion, resulting in ghosting of the generated electronic map. In order to improve the accuracy of the spatial position information, the spatial position information acquired by the GPS positioning system may be optimized by using calculations such as a direct method, an optical flow method, a kalman filter, and a map optimization.
S204, determining a current sequence track unit in the path track and at least one preamble track unit positioned before the current sequence track unit according to the arrangement sequence.
The preorder track unit refers to data with the acquisition time before the acquisition time of the current sequential track unit.
Specifically, after the track units are sorted based on the acquisition time to obtain the path track, the server traverses the track units except the track unit positioned at the head in the path track, takes the track unit in the current traversal order as the current order track unit, and takes the data positioned before the current order track unit in the path track as the pre-order track unit, and thus, the data is sequenced to the last order track unit. For example, upon initiating a traversal of the track units in the path track, the server takes the track units in the second order of the path track as current order track units and the track units in the first order as preamble track units. For another example, when traversing to a track unit in the path track in the third order, the server takes the track unit in the third order as the current-order track unit and takes both the first-order track unit and the second-order track unit as the preceding track units.
S206, according to the space position information of the current sequence track unit and the space position information of the preorder track units, screening out a matching track unit matched with the current sequence track unit from at least one preorder track unit.
Specifically, the server extracts spatial position information in a current sequence track unit and spatial position information in each preorder track unit, the spatial position information in the current sequence track unit is respectively matched with the spatial position information in each preorder track unit, and when at least one preorder point data has a preorder track unit which is successfully matched, the server takes the preorder track unit which is successfully matched as a matching track unit. For example, the preceding track units in which the distance between the X axes and the distance between the Y axes are both smaller than a preset distance threshold and the distance between the Z axes is greater than a preset distance threshold are used as matching track units.
In one embodiment, the spatial location information includes horizontal and vertical coordinates; according to the space position information of the current sequence track unit and the space position information of the preorder track units, screening out a matching track unit matched with the current sequence track unit from at least one preorder track unit, and the method comprises the following steps: determining the horizontal distance between the current sequential track unit and different preorder track units according to the horizontal plane coordinates; according to the vertical coordinate, determining the vertical distance between the current sequential track unit and different preorder track units; and screening out a matching track unit matched with the current sequential track unit from at least one preorder track unit according to the horizontal spacing and the vertical spacing.
Wherein, the horizontal plane refers to an XOY plane in a space coordinate system; x refers to the X axis in a spatial coordinate system; y refers to the Y axis in the space coordinate system; o refers to the origin in the spatial coordinate system. The horizontal plane coordinates refer to the coordinates of the location of the mapping vehicle in the XOY plane. The vertical coordinate refers to the Z-axis coordinate in the spatial coordinate system. For example, when the spatial position coordinate of the mapping vehicle in the spatial coordinate system is (x, y, z), (x, y) is the horizontal plane coordinate; (z) is the vertical coordinate.
Specifically, the server extracts the horizontal plane coordinates in the current sequential track unit and the horizontal plane coordinates in each preceding track unit respectively, and extracts the horizontal plane coordinates according to a preset formula
Figure PCTCN2020105790-APPB-000001
And calculating the horizontal distance between the current sequential track unit and different preorder track units. Wherein x is a The X-axis coordinate value in the horizontal plane coordinate of the current sequential track unit, namely the X-axis coordinate value in the space information in the current sequential track unit; x is a radical of a fluorine atom b The X-axis coordinate value in the horizontal plane coordinate of the preamble track unit, namely the X-axis coordinate value in the space information in the preamble track unit; y is a Y-axis coordinate values in horizontal plane coordinates of the current sequential track units, i.e., X-axis coordinate values in spatial information in the current sequential track units, Y b The coordinate value of the Y axis in the horizontal plane coordinate of the preamble track unit, that is, the coordinate value of the Y axis in the space information of the preamble track unit.
For example, the horizontal plane coordinate at the current sequential track unit is (x) 1 ，y 1 ) The horizontal plane coordinate of the A preamble track unit is (x) 2 ，y 2 ) The horizontal plane coordinate of the B preamble track unit is (x) 3 ，y 3 ) Then, the current sequential track unit is associated with A
Figure PCTCN2020105790-APPB-000002
Further, the server extracts the vertical coordinate in the current sequential track unit and extracts the vertical coordinate in each of the preceding track units separatelyAnd according to a predetermined formula | z a -z b And l, calculating the vertical distance between the current sequential track unit and different preorder track units. Wherein z is a The coordinate value of the Z axis in the space information in the current sequential track unit is the vertical coordinate of the current sequential track unit; z is a radical of b Means the vertical coordinate value of the preamble track unit, i.e. the Z-axis coordinate value in the spatial information in the preamble track unit.
For example, the vertical coordinate at the current sequential track unit is (z) 1 ) The vertical coordinate of the A-preamble track unit is (z) 2 ) The vertical coordinate of the B preamble track unit is (z) 3 ) The vertical spacing between the current sequential track unit and the pre-A track unit is | z 1 -z 2 I, the vertical distance between the current sequential track unit and the B pre-sequence track unit is | z 1 -z 3 |。
Further, the server screens out matching track units from at least one preorder track unit according to the horizontal distance between the current order track unit and each preorder track unit and the vertical distance between the current order track unit and each preorder track unit.
In one embodiment, screening out matching track units matching a current sequential track unit from at least one preceding track unit according to a horizontal spacing and a vertical spacing comprises: and taking the preorder track unit with the horizontal distance and the vertical distance meeting the preset conditions as a matching track unit.
Specifically, when the horizontal distance between the current sequential track unit and each preorder track unit and the vertical distance between the current sequential track unit and each preorder track unit are obtained, the server takes the preorder track units with the horizontal distances smaller than a preset horizontal threshold and the vertical distances larger than a preset vertical threshold as matching track units. When the horizontal distance between the current track unit and the preorder track unit is smaller than a preset horizontal threshold value and the vertical distance is larger than a preset vertical threshold value, it is indicated that the surveying and mapping vehicle is located in the same driving space, such as in the same parking lot, or in the same viaduct at the collecting time of the current sequence track unit and the collecting time of the matching track unit, and the height of the surveying and mapping vehicle at the collecting time of the current sequence track unit is not consistent with the height of the surveying and mapping vehicle at the collecting time of the matching track unit, such as the surveying and mapping vehicle is located on the upper layer of the viaduct at the collecting time of the current sequence track unit and is located on the lower layer of the viaduct at the collecting time of the matching track unit.
For example, in the above example, when the preset horizontal threshold is r and the preset vertical threshold is h, the spatial position information of the current sequential track unit is (x) 1 ,y 1 ,z 1 ) A preamble unit spatial position information is (x) 2 ,y 2 ,z 2 ) And the spatial position information of the B preamble track unit is (x) 3 ,y 3 ,z 3 )，
Figure PCTCN2020105790-APPB-000003
|z 1 -z 2 |＞h，|z 1 -z 3 And when the | is less than h, the server takes the A preamble track unit as a matching track unit matched with the current sequence track unit.
In one embodiment, the preset horizontal threshold value and the preset vertical threshold value may be freely set according to the requirements, for example, the preset horizontal threshold value may be set according to the lane width in the driving path, and the preset vertical threshold value may be set according to the floor height in the driving space.
By determining the spatial position information of each track unit, a matching track unit which is in the same driving space as the current sequential track unit but has inconsistent height values can be determined based on the spatial position information, so that the level information of the current sequential track unit can be marked subsequently based on the level information of the matching track unit.
And S208, acquiring the hierarchy information of the matched track units, and performing hierarchy marking on the current sequential track units based on the hierarchy information.
The level information is information for identifying a level where the current position is located, for example, the floor where the current surveying vehicle is located may be determined based on the level information, and the current surveying vehicle may also be determined on an upper level of the viaduct or a lower level of the viaduct based on the level information; the hierarchy information may specifically be a hierarchy identification.
Specifically, when the path trajectory is obtained, the server sets initial hierarchy information for all trajectory units in the path trajectory, that is, the server sets the hierarchy information of all trajectory units in the path trajectory to the same initial value, for example, the server sets the hierarchy identifiers of all trajectory units in the path trajectory to 0. And when the hierarchy information of the matching track units is obtained, the server modifies the initial hierarchy information of the current sequential track units based on the hierarchy information of the matching track units.
In one embodiment, when it is determined based on the spatial position information that the Z-axis coordinate value of the current sequential track unit is greater than the Z-axis coordinate value of the matching track unit, the server increases the hierarchy information of the matching track unit and takes the increased hierarchy information as the hierarchy information of the current sequential track unit. For example, in the above example, when the mapping vehicle performs data acquisition for a multi-layer parking lot, when | z 1 -z 2 H, and z 1 -z 2 And when the track unit is more than 0, indicating that the running space of the surveying vehicle is higher than the form space of the surveying vehicle when the track unit is matched, namely indicating that the parking lot floor of the surveying vehicle when the track unit is matched is higher than the parking lot floor of the surveying vehicle when the track unit is matched, acquiring the level identification of the matched track unit by the server, correspondingly increasing the acquired level identification, and taking the increased level identification as the level identification of the current sequential track path.
And when the Z-axis coordinate value of the current sequential track unit is smaller than the Z-axis coordinate value of the matching track unit, the server reduces the hierarchy information of the matching track unit, and takes the reduced hierarchy information as the hierarchy information of the current sequential track unit.
And S210, determining a next sequential track unit according to the arrangement sequence, and performing iteration by taking the next sequential track unit as a current sequential track unit until a last sequential track unit.
Specifically, after the server determines the hierarchical information of the current sequential track unit, the server takes a track unit adjacent to the current sequential track unit and behind the current sequential track unit as a next sequential track unit and takes the next sequential track unit as the current sequential track unit, and returns to the step of determining at least one preceding track unit before the current sequential track unit until the last sequential track unit.
And S212, generating the electronic map based on the track unit marked with the hierarchy information.
Specifically, the server groups the track units in the path track according to the hierarchy information, and groups the track units with the same hierarchy information into one group to obtain at least one group of track units. And the server acquires the grid map template corresponding to each group of track unit groups and projects the track units in the track unit groups into the corresponding grid map template, so that each grid image in the grid map template is rendered to obtain the grid map. The grid map is composed of M rows and N columns of grid images with the same size, and M and N are positive integers; the related information of the grid map includes: the number of rows and columns of the grid map, the unit pixel length of the grid map, and the horizontal pixels and the vertical pixels of each grid image in the grid map, wherein the unit pixel length of the grid map is used for representing the physical length represented by one pixel in the grid map, for example, the meaning of the unit pixel length of 3 cm in the grid map is that the physical length represented by each pixel in the grid map is 3 cm. The grid map template refers to a grid map with unrendered grid images, for example, the grid map template may be a grid map formed by combining a plurality of blank grid images.
Further, the server inputs the rendered grid map into the trained semantic recognition model, and semantic information in the grid map is extracted through the semantic recognition model. The semantic information refers to traffic information in a grid map. Traffic information includes, but is not limited to, at least one of: road shape information, road grade information, road curvature information, road direction information, lane width information, crash barrier information, road edge information, lane line information, flow leader information, and the like.
Furthermore, the server loads the semantic information into the corresponding grid map to obtain the electronic map corresponding to each hierarchical track unit group. For example, when the server generates a grid map a corresponding to the a track unit group and generates a grid map B corresponding to the B track unit group, the server extracts semantic information a in the grid map a and semantic information B in the grid map B based on the semantic recognition model, loads the semantic information a to the grid map a to obtain an electronic map a corresponding to the a track unit group, and loads the semantic information B to the grid map B to obtain an electronic map B corresponding to the B track unit group.
In one embodiment, the server combines the electronic maps corresponding to the track unit groups to obtain the electronic map in the multi-level space.
In this embodiment, by acquiring the path track, the current sequential track unit and the preamble track unit may be determined according to the arrangement order of each track unit in the path track; the spatial position information of the current sequential track unit and the spatial position information of the preorder track unit can be obtained by determining the current sequential track unit and the preorder track unit, and a matching track unit matched with the current sequential track unit is screened from the preorder track according to the determined spatial position information; by determining the matched matching track units, the hierarchy marking can be performed on the track units in the current sequence according to the hierarchy information of the matching track units, and thus the track units in the path track are iterated, so that the hierarchy marking of each track unit in the path track is realized, and the corresponding electronic map can be generated according to the track units marked with the hierarchy information. Because the hierarchical information is added to all the track units in the path track, in the process of generating the electronic map, when the three-dimensional track units acquired aiming at the multi-level driving space are reduced into two-dimensional data, the overlapped track units after being reduced in dimension can be distinguished according to the hierarchical information, so that the overlapping probability of the generated electronic map caused by overlapping of the track units is reduced, and the accuracy of the electronic map is improved.
In one embodiment, obtaining hierarchy information of matching track units, and performing hierarchy marking on a current sequential track unit based on the hierarchy information comprises: when at least two matching track units exist, screening out a target track unit from the at least two matching track units according to the spatial position information of the matching track units; acquiring the level information of a target track unit; and carrying out hierarchical marking on the current sequential track unit according to the hierarchical information of the target track unit.
Specifically, when the matching track unit is obtained, the server counts the number value of the obtained matching track unit. When two or more matching track units matching with the current sequence track unit exist, the server extracts the vertical coordinate in each matching track unit, calculates the absolute value of each vertical coordinate, and takes the matching track unit with the maximum absolute value as the target track unit. And the server acquires the hierarchy information of the target track unit and marks the hierarchy of the current sequential track unit according to the hierarchy information of the target track unit.
In this embodiment, the target track unit is screened from the multiple matching track units, so that the server can directly adjust the level information of the current sequential track unit according to the level information of the target track unit, and thus, the determination efficiency of the level information of the current sequential track unit is improved.
In one embodiment, the spatial location information includes vertical coordinates; the hierarchy information is a hierarchy identifier; according to the hierarchical information of the target track points, hierarchical marking is carried out on the current sequential track points, and the method comprises the following steps: when the vertical coordinate of the current sequential track unit is determined to be larger than that of the target track unit, increasing the level identification of the target track unit; and carrying out hierarchy marking on the current sequential track unit based on the increased hierarchy identification.
Specifically, the server extracts the vertical sitting in the spatial position information in the target trajectory unitAnd extracting a vertical coordinate in the spatial position information in the current sequential track unit, when the vertical coordinate of the current sequential track unit is greater than that of the target track unit, acquiring a level identification of the target track unit and a preset increasing amplitude value by the server, increasing the level identification of the target track unit based on the increasing amplitude value, and taking the increased level identification as the level identification of the current sequential track unit. For example, at the level of the target track unit, the mark is l 1 When the added amplitude is l, the level mark l of the current sequence track unit 2 Is l is 1 + l, the level identification of the target track unit remains unchanged as l 1 。
In this embodiment, when the vertical coordinate of the current sequential track unit is greater than the vertical coordinate of the target track unit, it indicates that the spatial position of the surveying and mapping vehicle is higher than the spatial position of the target track unit at the acquisition time of the current sequential track unit, and at this time, the level identifier of the current sequential track unit can be quickly obtained only by correspondingly increasing the level identifier of the target track unit, so that the determination efficiency of the level identifier of the current sequential track unit is greatly improved.
In one embodiment, the electronic map generating method further includes: when the vertical coordinate of the current sequential track unit is smaller than that of the target track unit, reducing the level identification of the target track unit; and taking the reduced level identification as the level mark of the current sequential track unit.
Specifically, the server extracts the vertical coordinate in the spatial position information in the target track unit and extracts the vertical coordinate in the spatial position information in the current sequence track unit, and when the vertical coordinate of the current sequence track unit is smaller than the vertical coordinate of the target track unit, the server indicates that the surveying and mapping vehicle is located at a spatial position lower than the spatial position of the surveying and mapping vehicle at the collecting time of the current sequence track unit. At this time, the server acquires the level identification of the target track unit and a preset reduction amplitude, reduces the level identification of the target track unit based on the reduction amplitude, and reduces the level identificationAs the hierarchy identification of the current sequential track unit. For example, at the level of the target track unit, denoted as l 1 When the amplitude is reduced to be l, the level mark l of the current sequence track unit 2 Is l is 1 L, the hierarchical identification of the target track unit remains unchanged as l 1 。
In this embodiment, when the vertical coordinate of the current sequential track unit is smaller than the vertical coordinate of the target track unit, the level identifier of the current sequential track unit can be quickly obtained only by correspondingly reducing the level identifier of the target track unit, so that the determination efficiency of the level identifier of the current sequential track unit is improved.
In one embodiment, the electronic map is generated based on the track unit marked with the hierarchical information, and the method comprises the following steps:
s402, acquiring parameter information for generating the grid map.
S404, grouping the track units in the path track according to the hierarchy information to obtain at least one track unit group.
And S406, generating a grid map corresponding to each track unit group according to the parameter information.
And S408, generating an electronic map according to the grid map corresponding to each track unit group.
The track unit comprises a three-dimensional point cloud image acquired by a laser sensor aiming at a driving area. The three-dimensional point cloud image includes three-dimensional coordinates and reflection values of the three-dimensional point data. The three-dimensional coordinates of the three-dimensional point data are coordinate values of reflection points in a driving area in a space coordinate system obtained through laser scanning. The reflection values comprise color values and/or luminance values. For example, the reflectance values may be the three primary colors in a color mode; the reflectance values may also be hue values, saturation values and lightness values in the color mode; the reflection value can also be a hue value, a saturation value and a brightness value in the color mode.
The parameter information includes the number of rows and columns of the grid map, the unit pixel length of the grid map, and the horizontal pixels and the vertical pixels of each grid image in the grid map.
Specifically, the server groups each track unit in the path track, takes the track unit with the same layer level information as a track unit group, and acquires preset parameter information for generating the grid map. The server traverses each track unit group, generates a grid map corresponding to each track unit group according to the parameter information, and synthesizes the grid maps corresponding to each track unit group to obtain the grid map of the path track. And the server inputs the grid map corresponding to the path track into a pre-trained semantic recognition model, and generates an electronic map of the path track based on the semantic recognition model. The semantic recognition model is a machine learning model capable of extracting semantic information from the grid map.
More specifically, the server determines the track unit group in the current traversal order, generates parameter information of the grid map, and generates a grid map template corresponding to the track unit group in the current traversal order according to the parameter information. And traversing each track unit in the track unit group in the current traversal order by the server, and projecting the track unit to the grid map template to obtain the grid map corresponding to the current traversal order.
The server determines a track unit of the current traversal order in the track unit group of the current traversal order, and determines the position information of each three-dimensional point data in the grid map template according to the parameter information and the three-dimensional coordinates of each three-dimensional point data in the three-dimensional point cloud image in the track unit of the current traversal order, for example, the three-dimensional coordinates of the current three-dimensional point data are (x) 4 ，y 4 ，z 4 ) When the position information in the corresponding grid map template is M 4 Line N 4 And (4) columns. The server determines a grid image which has the same position information as the current three-dimensional point data in the grid map template, and renders the grid image with the same position information according to the reflection value in the current three-dimensional point data, so that the three-dimensional point data is projected to the two-dimensional grid map template. The server sequentially projects the three-dimensional point data in the three-dimensional point cloud image to the grid map template, so that the current traversal sequence track unit is projected toAnd (5) grid map templates.
In this embodiment, the track units in the path track are grouped by the hierarchical information, and the track units with the same hierarchical information can be divided into the same group, so that the track units at the same hierarchical level can be projected into the same grid map template, and thus, the probability of overlapping of the track units due to loss of height information when the track units acquired by aiming at the multi-hierarchical driving space are projected into a two-dimensional grid map can be reduced, and the accuracy of the grid map is further improved.
In one embodiment, generating an electronic map according to the grid map corresponding to each track unit group comprises: respectively inputting the grid maps corresponding to each track unit group into a pre-trained semantic recognition model to obtain semantic information corresponding to each grid map; and generating an electronic map according to the semantic information corresponding to each grid map.
Specifically, the server stores a trained semantic recognition model in advance. When the grid map corresponding to each track unit group is generated, the server inputs the grid map into the semantic recognition model, extracts semantic information in the grid map based on the semantic recognition model, and loads the semantic information into the corresponding grid map to obtain the electronic map corresponding to each track unit group. For example, when the server extracts lane width information from the grid map corresponding to the a track unit group and road edge information from the grid map corresponding to the B track unit group based on the semantic recognition model, the server loads the lane width information into the grid map corresponding to the a track unit group to obtain an electronic map corresponding to the a track unit group; and loading the road edge information into the grid map corresponding to the track unit B to obtain the electronic map corresponding to the track unit B. Furthermore, the server integrates the electronic maps loaded with the semantic information to obtain the electronic map of the path track.
In the embodiment, because the semantic information in the grid map can be accurately identified through the pre-trained semantic identification model, the electronic map generated based on the semantic information is more accurate.
In one embodiment, the electronic map generation method includes: when more than one path track is acquired in the acquisition time period, the acquisition time of each track unit in the more than one path track is determined; determining time offset corresponding to each of more than one path track according to the acquisition time of each track unit in the more than one path track; modifying the acquisition time of the track points in the corresponding path track according to the time offset; and combining more than one path track according to the modified acquisition time to obtain a combined path track.
Since the trace units in the path trace need to be sorted according to the acquisition time before hierarchical marking. When the server receives a plurality of path tracks acquired by a plurality of mapping vehicles in the same acquisition time period, a plurality of track units in the plurality of path tracks are overlapped in acquisition time, so that the plurality of path tracks are combined, and jump can be generated in the space position of the combined path track. In order to avoid that the acquisition time of the track units in the combined path track is not overlapped, the combined path track is ensured to be continuous in time and space, and the acquisition time of the track units acquired by different modified mapping vehicles can be correspondingly modified.
Specifically, when path tracks sent by a plurality of mapping vehicles are received in an acquisition period, the server performs progressive sequencing on the path tracks to obtain a track sequence. The method for sorting the path tracks may be freely set according to the requirement, for example, the path tracks are sorted according to the time point of receiving the path tracks. Wherein, the plurality of mapping vehicles are two or more than two mapping vehicles; the plurality of path trajectories means two or more path trajectories. And the server traverses the path tracks in the track sequence according to the arrangement sequence, and determines the path track in the current traversal sequence and the preorder path track before the path track in the current traversal sequence. The server determines the maximum acquisition time of the track unit in each preorder path track, and determines the time offset of the current traversal sequence path track according to the maximum acquisition time of the track unit in each preorder path track, so that the server determines the time offset corresponding to each path track in sequence. The server modifies the acquisition time of the corresponding path trajectory based on the time offset.
Further, the server sequences the track units in the multiple path tracks according to the modified acquisition time, so that more than one path track is combined to obtain a combined path track.
In this embodiment, the time offset corresponding to each path track is determined, and the acquisition time of the track unit is modified based on the time offset, so that the combined path tracks are continuous in time, and a corresponding electronic map can be subsequently generated based on the time-continuous path tracks.
In one embodiment, determining the time offset corresponding to each of more than one path trajectory according to the acquisition time of each trajectory point in the more than one path trajectory includes: sequencing more than one path track according to the acquisition time of the track units in more than one path track to obtain a track sequence; traversing the track sequence according to the arrangement sequence; when at least one preorder track path positioned before the current traversal sequence track path exists in the track sequence, acquiring the maximum acquisition time in each preorder track path; and determining the time offset of the track path of the current traversal sequence according to the maximum acquisition time.
Specifically, when more than one path track is obtained, the server obtains the minimum acquisition time in each path track, and sorts the more than one path track according to the minimum acquisition time to obtain a track sequence. For example, the server sorts more than one path trajectory in ascending order according to the minimum acquisition time to obtain a trajectory sequence. And traversing the path tracks in the track sequence by the server according to the arrangement sequence. The server determines the path tracks of the current traversal sequence and all the preorder path tracks before the current traversal sequence, and adds the maximum acquisition time in each preorder path track to obtain the time offset of the current traversal sequence. And after the time offset of each path track is obtained, the server correspondingly modifies the acquisition time of the track unit in the path track according to the time offset. It is readily understood that when the current traversal sequential path trajectory does not have a preceding path trajectory, the current traversal sequential path trajectory does not have a time offset.
For example, when the server receives a path track a, a path B, and a path track C in 0 to 10 seconds, where the acquisition time of each track unit in the path track a is [1,3,5,7], the acquisition time of each track unit in the path track B is [2,4,6,8], and the acquisition time of each track unit in the path C is [3,5,7,9], the server sorts the path track a, the path track B, and the path track C according to the minimum acquisition time value in each path track, so as to obtain a track sequence.
The server takes the maximum acquisition time 7 in the path track A as the time offset of the path track; and superposing the maximum acquisition time 7 in the path track A and the maximum acquisition time 8 in the path track B to obtain the time offset of the path track C. The server increases the acquisition time of the track units in the track of the path B by 7 to obtain the modified acquisition time [9,11,13,15]; and increasing the acquisition time of each trajectory unit in the C-path trajectory by 15 to obtain modified acquisition times [18,20,22,24]. And the server combines the path track A, the path track B and the path track C according to the modified acquisition time, so that the acquisition time of each track unit in the combined path track is [1,3,5,7,9,11,13,15,18,20,22 and 24], and the server performs data processing on the combined path track based on the electronic map generation method to obtain an electronic map corresponding to the combined path track.
In this embodiment, by determining the time offset, the acquisition time of the path trajectory may be modified subsequently based on the time offset, and the path trajectory may be merged based on the modified acquisition time.
In one embodiment, when the server sorts more than one path track according to the acquisition time of the track units in more than one path track to obtain a track sequence, the server traverses the track sequence according to the sorting order. The server determines a current traversal sequence path track and a preorder path track which is adjacent to the current traversal sequence path track and is positioned before the current traversal sequence path track, takes the maximum acquisition time in the preorder path track as the time offset of the current traversal sequence path track, and modifies the acquisition time of each track unit in the current traversal sequence path track based on the determined time offset. And the server determines the next sequential path track according to the arrangement sequence, takes the next sequential path track as the current traversal sequential path track, and returns to the step of determining a preorder path track which is adjacent to and before the current traversal sequential path track until the final sequential path track. Further, the server merges the path trajectories after the acquisition time is modified to obtain merged path trajectories.
It should be understood that although the steps in the flowcharts of fig. 2 and 4 are shown in sequence as indicated by the arrows, the steps are not necessarily performed in sequence as indicated by the arrows. The steps are not limited to being performed in the exact order illustrated and, unless explicitly stated herein, may be performed in other orders. Moreover, at least some of the steps in fig. 2 and 4 may include multiple sub-steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of performing the sub-steps or stages is not necessarily sequential, but may be performed alternately or alternately with other steps or at least some of the sub-steps or stages of other steps.
In one embodiment, as shown in fig. 5, there is provided an electronic map generating apparatus 500, including: a path trajectory acquisition module 502, a hierarchy marking module 504, and a map generation module 506.
A path trajectory acquisition module 502, configured to acquire a path trajectory; the path trajectory comprises at least one trajectory unit; the track unit comprises acquisition time and space position information; the path track is obtained by sequencing at least one track unit according to the acquisition time;
a hierarchical marking module 504, configured to determine, according to the arrangement order, a current order track unit in the path track and at least one preceding order track unit located before the current order track unit; screening a matching track unit matched with the current sequence track unit from at least one preorder track unit according to the spatial position information of the current sequence track unit and the spatial position information of the preorder track units; acquiring the hierarchy information of the matching track units, and performing hierarchy marking on the current sequential track units based on the hierarchy information; determining a next sequential track unit according to the arrangement sequence, and taking the next sequential track unit as a current sequential track unit for iteration until the last sequential track unit;
and a map generating module 506, configured to generate an electronic map based on the track units labeled with the hierarchical information.
In one embodiment, as shown in FIG. 6, the hierarchical tagging module 504 further comprises a matching track unit determination module 5041 for determining a horizontal spacing between a current sequential track unit and a different preceding track unit based on horizontal plane coordinates; according to the vertical coordinate, determining the vertical distance between the current sequential track unit and different preorder track units; and screening out matched track units matched with the current sequence track units from at least one preorder track unit according to the horizontal spacing and the vertical spacing.
In one embodiment, the matching track unit determination module 5041 is further configured to use a preceding track unit with a horizontal spacing and a vertical spacing meeting a preset condition as the matching track unit.
In one embodiment, the hierarchical marking module 504 further includes a target track unit determination module 5042, configured to, when there are at least two matching track units, screen out a target track unit from the at least two matching track units according to the spatial location information of the matching track units; acquiring the level information of a target track unit; and carrying out hierarchical marking on the current sequential track unit according to the hierarchical information of the target track unit.
In one embodiment, the target trajectory unit determination module 5042 is further operable to increase the hierarchical identification of the target trajectory unit when it is determined that the vertical coordinate of the current sequential trajectory unit is greater than the vertical coordinate of the target trajectory unit; and taking the increased level identification as the level mark of the current sequential track unit.
In one embodiment, the target trajectory unit determination module 5042 is further operable to decrease the level identification of the target trajectory unit when the vertical coordinate of the current sequential trajectory unit is determined to be less than the vertical coordinate of the target trajectory unit; and taking the reduced level identification as the level mark of the current sequential track unit.
In one embodiment, the map generation module 506 further includes a grid map generation module 5061, configured to obtain parameter information for generating a grid map; grouping the track units in the path track according to the hierarchy information to obtain at least one track unit group; generating a grid map corresponding to each track unit group according to the parameter information; and generating an electronic map according to the grid map corresponding to each track unit group.
In an embodiment, the grid map generating module 5061 is further configured to input the grid map corresponding to each trajectory unit group into a pre-trained semantic recognition model, so as to obtain semantic information corresponding to each grid map; and generating the electronic map according to the semantic information corresponding to each grid map.
In one embodiment, the electronic map generating apparatus 500 further includes a merging module 508, configured to determine a collecting time of each track unit in more than one path track when more than one path track is collected in the collecting time period; determining time offset corresponding to each of more than one path track according to the acquisition time of each track unit in the more than one path track; modifying the acquisition time of the track points in the corresponding path track according to the time offset; and combining more than one path track according to the modified acquisition time to obtain a combined path track.
In an embodiment, the merging module 508 is further configured to sort the more than one path trajectory according to the acquisition time of the trajectory unit in the more than one path trajectory, so as to obtain a trajectory sequence; traversing the track sequence according to the arrangement sequence; when at least one preorder track path positioned before the current traversal sequence track path exists in the track sequence, acquiring the maximum acquisition time in each preorder track path; and determining the time offset of the track path of the current traversal sequence according to the maximum acquisition time.
In one embodiment, a computer device is provided, which may be a server, and the internal structure thereof may be as shown in fig. 7. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer readable instructions, and a database. The internal memory provides an environment for the operating system and execution of computer-readable instructions in the non-volatile storage medium. The database of the computer device is used for storing electronic map data. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer readable instructions, when executed by a processor, implement an electronic map generation method.
It will be appreciated by those skilled in the art that the configuration shown in fig. 7 is a block diagram of only a portion of the configuration associated with the present application, and is not intended to limit the computing device to which the present application may be applied, and that a particular computing device may include more or fewer components than shown, or may combine certain components, or have a different arrangement of components.
A computer device comprising a memory and one or more processors, the memory having stored therein computer-readable instructions, which, when executed by the processors, cause the one or more processors to carry out the steps of the above-described method embodiments.
One or more non-transitory computer-readable storage media storing computer-readable instructions which, when executed by one or more processors, cause the one or more processors to perform the steps in the above-described method embodiments.
Those skilled in the art will appreciate that all or part of the processes of the methods of the embodiments described above can be implemented by hardware related to computer readable instructions, which can be stored in a non-volatile computer readable storage medium, and when executed, the computer readable instructions can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database or other medium used in the embodiments provided herein can include non-volatile and/or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), rambus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
All possible combinations of the technical features in the above embodiments may not be described for the sake of brevity, but should be considered as being within the scope of the present disclosure as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.

Claims (20)

  1. An electronic map generation method, comprising:
    acquiring a path track; the path trajectory comprises at least one trajectory unit; the track unit comprises acquisition time and space position information; the path track is obtained by sequencing at least one track unit according to the acquisition time;
    determining a current sequence track unit in the path track and at least one preorder track unit positioned in front of the current sequence track unit according to the arrangement sequence;
    screening out a matching track unit matched with the current sequence track unit from the at least one preorder track unit according to the spatial position information of the current sequence track unit and the spatial position information of the preorder track units;
    acquiring the hierarchy information of the matching track units, and performing hierarchy marking on the current sequential track units based on the hierarchy information;
    determining a next sequential track unit according to the arrangement sequence, and taking the next sequential track unit as a current sequential track unit for iteration until the last sequential track unit;
    and generating the electronic map based on the track units marked with the hierarchical information.
  2. The method of claim 1, wherein the spatial location information comprises horizontal plane coordinates and vertical coordinates; the method for screening out the matching track unit matched with the current sequence track unit from the at least one preorder track unit according to the spatial position information of the current sequence track unit and the spatial position information of the preorder track unit comprises the following steps:
    determining the horizontal distance between the current sequential track unit and different preorder track units according to the horizontal plane coordinates;
    determining the vertical distance between the current sequential track unit and different preorder track units according to the vertical coordinate;
    and screening out a matching track unit matched with the current sequential track unit from the at least one preorder track unit according to the horizontal spacing and the vertical spacing.
  3. The method of claim 2, wherein said screening out matching track units from said at least one preceding track unit that match a current sequential track unit based on horizontal spacing and vertical spacing comprises:
    and taking the preorder track unit with the horizontal distance and the vertical distance meeting the preset conditions as a matching track unit.
  4. The method as claimed in claim 1, wherein said obtaining hierarchical information of the matching track unit, and hierarchically marking a current sequential track unit based on the hierarchical information comprises:
    when at least two matching track units exist, screening out a target track unit from the at least two matching track units according to the spatial position information of the matching track units;
    acquiring the level information of the target track unit;
    and carrying out hierarchical marking on the current sequential track unit according to the hierarchical information of the target track unit.
  5. The method of claim 4, wherein the spatial location information comprises vertical coordinates; the hierarchy information is a hierarchy identifier; and the step of carrying out hierarchical marking on the current sequential track points according to the hierarchical information of the target track unit comprises the following steps:
    increasing the level identification of the target track unit when it is determined that the vertical coordinate of the current sequential track unit is greater than the vertical coordinate of the target track unit;
    and taking the increased level identification as the level mark of the current sequential track unit.
  6. The method of claim 5, further comprising:
    when the vertical coordinate of the current sequential track unit is determined to be smaller than the vertical coordinate of the target track unit, reducing the level identification of the target track unit;
    and taking the reduced level identification as the level mark of the current sequential track unit.
  7. The method of claim 1, wherein generating the electronic map based on the track unit labeled with the hierarchical information comprises:
    acquiring parameter information for generating a grid map;
    grouping the track units in the path track according to the hierarchy information to obtain at least one track unit group;
    generating a grid map corresponding to each track unit group according to the parameter information;
    and generating an electronic map according to the grid map corresponding to each track unit group.
  8. The method according to claim 7, wherein the generating an electronic map according to the grid map corresponding to each track unit group comprises:
    respectively inputting the grid map corresponding to each track unit group into a pre-trained semantic recognition model to obtain semantic information corresponding to each grid map;
    and generating the electronic map according to the semantic information corresponding to each grid map.
  9. The method according to any one of claims 1-8, further comprising:
    when more than one path track is acquired in an acquisition time period, determining the acquisition time of each track unit in the more than one path track;
    determining time offsets corresponding to the more than one path tracks according to the acquisition time of each track unit in the more than one path tracks;
    according to the time offset, modifying the acquisition time of the track points in the corresponding path track;
    and combining more than one path track according to the modified acquisition time to obtain a combined path track.
  10. The method according to claim 9, wherein determining the time offset corresponding to each of the more than one path tracks according to the acquisition time of each track point in the more than one path tracks comprises:
    sequencing the more than one path track according to the acquisition time of the track units in the more than one path track to obtain a track sequence;
    traversing the track sequence according to the arrangement sequence;
    when at least one preorder track path positioned before the current traversal sequence track path exists in the track sequence, acquiring the maximum acquisition time in each preorder track path;
    and determining the time offset of the track path of the current traversal sequence according to the maximum acquisition time.
  11. An electronic map generation apparatus, characterized in that the apparatus comprises:
    the path track acquisition module is used for acquiring a path track; the path trajectory comprises at least one trajectory unit; the track unit comprises acquisition time and space position information; the path track is obtained by sequencing at least one track unit according to the acquisition time;
    the hierarchical marking module is used for determining a current sequence track unit in the path track and at least one preorder track unit positioned in front of the current sequence track unit according to the arrangement sequence; screening out a matching track unit matched with the current sequence track unit from the at least one preorder track unit according to the spatial position information of the current sequence track unit and the spatial position information of the preorder track units; acquiring the level information of the matching track units, and marking the level of the current sequential track units based on the level information; determining a next sequential track unit according to the arrangement sequence, and taking the next sequential track unit as a current sequential track unit for iteration until the last sequential track unit;
    and the map generation module is used for generating the electronic map based on the track unit marked with the hierarchy information.
  12. The apparatus of claim 11, wherein the spatial location information comprises horizontal plane coordinates and vertical coordinates; the level marking module comprises a matching track unit determining module which is used for determining the horizontal distance between the current sequential track unit and different preorder track units according to the horizontal plane coordinates; determining the vertical distance between the current sequential track unit and different preorder track units according to the vertical coordinate; and screening out matched track units matched with the track units in the current sequence from the at least one preorder track unit according to the horizontal spacing and the vertical spacing.
  13. The apparatus according to claim 12, wherein the matching track unit determining module is further configured to use a preceding track unit with a horizontal distance and a vertical distance meeting a preset condition as the matching track unit.
  14. A computer device comprising a memory and one or more processors, the memory having stored therein computer-readable instructions that, when executed by the one or more processors, cause the one or more processors to perform the steps of:
    acquiring a path track; the path trajectory comprises at least one trajectory unit; the track unit comprises acquisition time and space position information; the path track is obtained by sequencing at least one track unit according to the acquisition time;
    determining a current sequence track unit in the path track and at least one preorder track unit positioned in front of the current sequence track unit according to the arrangement sequence;
    screening a matching track unit matched with the current sequence track unit from the at least one preorder track unit according to the spatial position information of the current sequence track unit and the spatial position information of the preorder track units;
    acquiring the hierarchy information of the matching track units, and performing hierarchy marking on the current sequential track units based on the hierarchy information;
    determining a next sequential track unit according to the arrangement sequence, and performing iteration by taking the next sequential track unit as a current sequential track unit until a final sequential track unit;
    and generating the electronic map based on the track units marked with the hierarchical information.
  15. The computer device of claim 14, wherein the spatial location information comprises horizontal plane coordinates and vertical coordinates; the processor, when executing the computer readable instructions, further performs the steps of:
    determining the horizontal distance between the current sequential track unit and different preorder track units according to the horizontal plane coordinates;
    determining the vertical distance between the current sequential track unit and different preorder track units according to the vertical coordinate;
    and screening out matched track units matched with the track units in the current sequence from the at least one preorder track unit according to the horizontal spacing and the vertical spacing.
  16. The computer device of claim 15, wherein the processor, when executing the computer readable instructions, further performs the steps of:
    and taking the preorder track unit with the horizontal distance and the vertical distance meeting the preset conditions as a matching track unit.
  17. The computer device of claim 14, wherein the processor, when executing the computer readable instructions, further performs the steps of:
    when at least two matching track units exist, screening out a target track unit from the at least two matching track units according to the spatial position information of the matching track units;
    acquiring the level information of the target track unit;
    and carrying out hierarchical marking on the current sequential track unit according to the hierarchical information of the target track unit.
  18. One or more non-transitory computer-readable storage media storing computer-readable instructions that, when executed by one or more processors, cause the one or more processors to perform the steps of:
    acquiring a path track; the path trajectory comprises at least one trajectory unit; the track unit comprises acquisition time and space position information; the path track is obtained by sequencing at least one track unit according to the acquisition time;
    determining a current sequence track unit in the path track and at least one preorder track unit positioned in front of the current sequence track unit according to the arrangement sequence;
    screening out a matching track unit matched with the current sequence track unit from the at least one preorder track unit according to the spatial position information of the current sequence track unit and the spatial position information of the preorder track units;
    acquiring the hierarchy information of the matching track units, and performing hierarchy marking on the current sequential track units based on the hierarchy information;
    determining a next sequential track unit according to the arrangement sequence, and taking the next sequential track unit as a current sequential track unit for iteration until the last sequential track unit;
    and generating the electronic map based on the track units marked with the hierarchical information.
  19. The storage medium of claim 18, wherein the spatial location information includes horizontal plane coordinates and vertical coordinates; the computer readable instructions when executed by the processor further perform the steps of:
    determining the horizontal distance between the current sequential track unit and different preorder track units according to the horizontal plane coordinates;
    according to the vertical coordinate, determining the vertical distance between the current sequential track unit and different preorder track units;
    and screening out matched track units matched with the track units in the current sequence from the at least one preorder track unit according to the horizontal spacing and the vertical spacing.
  20. The storage medium of claim 19, wherein the computer readable instructions, when executed by the processor, further perform the steps of:
    and taking the preorder track unit with the horizontal distance and the vertical distance meeting the preset conditions as a matching track unit.
CN202080099129.6A 2020-07-30 2020-07-30 Electronic map generation method and device, computer equipment and storage medium Pending CN115668333A (en)

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2020/105790 WO2022021209A1 (en) 2020-07-30 2020-07-30 Electronic map generation method and apparatus, computer device, and storage medium

Publications (1)

Publication Number Publication Date
CN115668333A true CN115668333A (en) 2023-01-31

Family

ID=80036950

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202080099129.6A Pending CN115668333A (en) 2020-07-30 2020-07-30 Electronic map generation method and device, computer equipment and storage medium

Country Status (2)

Country Link
CN (1) CN115668333A (en)
WO (1) WO2022021209A1 (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117789444A (en) * 2022-09-19 2024-03-29 北京初速度科技有限公司 Parking lot data matching method, device, equipment, medium and vehicle

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102313556B (en) * 2010-07-01 2014-04-02 北京四维图新科技股份有限公司 Method and device for matching paths on round island
CN107545833B (en) * 2016-06-24 2019-09-24 高德信息技术有限公司 A kind of road method for drafting and device
US10474340B2 (en) * 2016-08-18 2019-11-12 Mapbox, Inc. Providing graphical indication of label boundaries in digital maps
CN106643779B (en) * 2016-09-29 2019-07-19 合肥工业大学 A kind of path drawing generating method based on improved connection graph traversal algorithm
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

Also Published As

Publication number Publication date
WO2022021209A1 (en) 2022-02-03
WO2022021209A9 (en) 2022-11-03

Similar Documents

Publication Publication Date Title
US10198632B2 (en) Survey data processing device, survey data processing method, and survey data processing program
CN111448478B (en) System and method for correcting high-definition maps based on obstacle detection
JP6595182B2 (en) Systems and methods for mapping, locating, and attitude correction
WO2018068653A1 (en) Point cloud data processing method and apparatus, and storage medium
JP5168601B2 (en) Own vehicle position recognition system
CN102208013B (en) Landscape coupling reference data generation system and position measuring system
WO2018020954A1 (en) Database construction system for machine-learning
JP5388082B2 (en) Stationary object map generator
CN114930401A (en) Point cloud-based three-dimensional reconstruction method and device and computer equipment
JP2012208525A (en) Stationary object map generation device
CN111256687A (en) Map data processing method and device, acquisition equipment and storage medium
US20230071794A1 (en) Method and system for building lane-level map by using 3D point cloud map
CN111753639B (en) Perception map generation method, device, computer equipment and storage medium
Kellner et al. Road curb detection based on different elevation mapping techniques
CN112800938B (en) Method and device for detecting occurrence of side rockfall of unmanned vehicle
CN116734828A (en) Determination of road topology information, electronic map data processing method and electronic equipment
US11982752B2 (en) GPS error correction method through comparison of three-dimensional HD-maps in duplicate area
CN114593739B (en) Vehicle global positioning method and device based on visual detection and reference line matching
CN115439621A (en) Three-dimensional map reconstruction and target detection method for coal mine underground inspection robot
CN117576652A (en) Road object identification method and device, storage medium and electronic equipment
CN113865581A (en) Closed scene positioning method based on multi-level map
CN115668333A (en) Electronic map generation method and device, computer equipment and storage medium
WO2020118623A1 (en) Method and system for generating an environment model for positioning
CN112698315B (en) Mobile equipment positioning system, method and equipment
JP2022028588A (en) Position acquisition device

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