A method and system for automatically generating the relationship between ground objects and road networks

Abstract

The present invention belongs to the technical field of electronic maps, and specifically provides a method and system for automatically generating the association relationship between ground objects and road networks, wherein the method includes: obtaining the total data of roads and ground objects; extracting the sub-data of relevant roads and relevant ground objects according to the needs of automatic driving, establishing a road network topology model, and constructing the geometric shapes of roads and ground objects; establishing a spatial index for the coordinate data of roads and ground objects, and retrieving all roads within a certain range near the ground objects; establishing the association relationship between ground objects and road networks according to the types of ground objects and the level of association with roads. The solution has high computational efficiency and adopts a spatial index mechanism, which can process large-scale map data and quickly calculate the association relationship between ground objects and road networks; the association relationship between ground objects and road networks is automatically generated throughout the entire process, without the need for manual intervention, effectively improving production efficiency and data accuracy.

Description

Technical Field

[0001] The present invention relates to the technical field of electronic maps, and more specifically, to a method and system for automatically generating association relationships between ground objects and road networks. Background Art

[0002] High-precision electronic maps mainly serve autonomous vehicles, providing lane-level planning and self-positioning assistance within road sections for autonomous vehicles. Different from traditional navigation electronic maps, high-precision electronic maps not only provide high-precision road and lane information, but also provide a large amount of ground object information, such as traffic signs, traffic lights, static obstacles, pedestrian crossings, etc. These ground object information helps to assist autonomous driving decisions and improve the autonomous driving experience. In the process of making high-precision electronic maps, roads and lanes in the real world need to be interrupted according to the road network model that meets the needs of autonomous driving. Roads and lanes are generally divided into several sections, and ground objects need to establish associations with the divided roads and lanes. Due to the large number of ground objects and the complex topology of the road network after segmentation, in the mapping process, if we rely on manual annotation or use the traditional nearest association method, there are defects such as low efficiency and low association accuracy. Therefore, it is necessary to provide an automatic and rapid generation method for the association between ground objects and road networks. Summary of the invention

[0003] The present invention needs to solve the technical problem of low efficiency in establishing the association relationship between ground objects and road networks in the prior art.

[0004] The present invention provides a method for automatically generating an association relationship between a ground object and a road network, comprising:

[0005] S1, obtain the total data of roads and ground objects;

[0006] S2, according to the requirements of autonomous driving, extract sub-data of relevant roads and related ground objects, establish a road network topology model, and construct the geometric shapes of roads and ground objects;

[0007] S3, establish a spatial index for the coordinate data of roads and ground objects, and retrieve all roads within a certain range near the ground objects;

[0008] S4, establishing an association relationship between the ground object and the road network according to the type of the ground object and the association level with the road.

[0009] Preferably, the S1 specifically includes:

[0010] Displaying a two-dimensional map corresponding to the high-precision map through an interface, and circling a required data range, a required route range, or a required administrative division range on the two-dimensional map according to user needs;

[0011] Select the map elements, attributes, output data format, version and processing operation information within the required range according to your needs.

[0012] Preferably, after S4, the step further includes:

[0013] S5, performing a logic self-check on the association relationship according to the type of the ground object, and then filtering and fine-tuning the association relationship;

[0014] S6, process special ground objects, add extended associated information as needed, further improve and enrich the associated relationship and output high-precision map data.

[0015] Preferably, the ground objects include ground interest surfaces, ground markers, static obstacles, road ancillary facilities, pole objects, traffic signs and traffic lights; the road includes road sections, and the road sections include lanes.

[0016] Preferably, the association relationship between the ground object and the road network includes:

[0017] All ground objects retrieved through the road section that are related to the road section or located on the road section or adjacent to the road section;

[0018] All ground objects retrieved through the lane are related to the lane or are located on the lane surface or are adjacent to the lane.

[0019] Preferably, the S4 specifically includes:

[0020] S41, a direction arrow is drawn up, and a road set R={R1, R2, R3, ..., Rn} near the direction arrow is retrieved through a spatial index, where each road in the road set may be associated with the direction arrow;

[0021] S42, respectively calculate whether all road sections under the road Rx (x=1, 2, ..., n) in the road set have a geometric overlap relationship with the direction arrows, and if so, find the road section R S , and then traverse the road section R S Check the lane below to see if there is a geometric overlap relationship between the lane and the direction arrow. If so, establish an association relationship.

[0022] Preferably, the S3 specifically includes: using a two-dimensional grid index to record all coordinate information corresponding to each road and each ground object in the grid.

[0023] The present invention provides a system for realizing a method for automatically generating an association relationship between a ground object and a road network, comprising:

[0024] The front-end interactive module is used to display graphically and two-dimensional map data, so that users can select the required data range; it is used to display supported map elements, attributes and functions, so that users can select corresponding map elements, attributes and functions;

[0025] The data preprocessing module is used to extract the required relevant map data and perform preprocessing, wherein the preprocessing process includes the construction of a road network model, the geometric construction of road network objects and ground objects, and the construction of spatial indexes of road network objects and ground objects;

[0026] The association relationship calculation module is used to calculate the association relationship between ground objects and roads, and different algorithms are used for processing according to the type of ground objects and the required level of association.

[0027] The present invention also provides an electronic device, comprising a memory and a processor, wherein the processor is used to implement the steps of a method for automatically generating an association relationship between ground objects and a road network when executing a computer management program stored in the memory.

[0028] The present invention also provides a computer-readable storage medium on which a computer management program is stored. When the computer management program is executed by a processor, the steps of the method for automatically generating the association relationship between ground objects and road networks are implemented.

[0029] Beneficial effects: The present invention provides a method and system for automatically generating the association relationship between ground objects and road networks, wherein the method includes: S1, obtaining the total data of roads and ground objects; S2, extracting the sub-data of relevant roads and relevant ground objects according to the needs of autonomous driving, establishing a road network topology model, and constructing the geometric shapes of roads and ground objects; S3, establishing a spatial index for the coordinate data of roads and ground objects, and retrieving all roads within a certain range near the ground objects; S4, establishing the association relationship between ground objects and road networks according to the type of ground objects and the level of association with roads. This solution realizes the automatic and rapid generation of the association relationship between ground objects and road networks in high-precision maps. It has high computational efficiency and adopts a spatial index mechanism, which can process a large range of map data and quickly calculate the association relationship between ground objects and road networks; the association relationship between ground objects and road networks is automatically generated throughout the entire process, with built-in logic self-checking and optimization algorithms, without the need for manual intervention throughout the process, effectively improving production efficiency and data accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 A flow chart of a method for automatically generating the relationship between ground objects and road networks provided by the present invention;

[0031] Figure 2 A schematic diagram of the hardware structure of a possible electronic device provided by the present invention;

[0032] Figure 3 A schematic diagram of the hardware structure of a possible computer-readable storage medium provided by the present invention;

[0033] Figure 4 A construction diagram of the association relationship between ground objects and road networks provided by the method for automatically generating the association relationship between ground objects and road networks provided by the present invention;

[0034] Figure 5 A specific implementation principle diagram of a method for automatically generating associations between ground objects and road networks provided by the present invention. DETAILED DESCRIPTION

[0035] The specific implementation of the present invention is further described in detail below in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0036] like Figure 1 As shown, an embodiment of the present invention provides a method and system for automatically generating an association relationship between a ground object and a road network, wherein the method includes:

[0037] S1, obtain the total data of roads and ground objects.

[0038] Specifically, the interface displays a two-dimensional map corresponding to the high-precision map, and the user circles the required data range, required route range, or required administrative division range on the two-dimensional map according to the needs. The user selects the required map elements, attribute categories, output data format and version, processing operations and other information according to the needs.

[0039] S2, according to the requirements of autonomous driving, extracts sub-data of relevant roads and related ground objects, establishes a road network topology model, and constructs the geometric shapes of roads and ground objects.

[0040] Specifically, according to the data range, map elements, and attribute categories specified in S1, extract the data information of relevant roads, lanes, and ground objects. According to the needs of autonomous driving or customer needs, process the above data information to establish a road network topology model. According to the needs of autonomous driving or customer needs, process the data information in 1) to establish a road network topology model. According to the needs of autonomous driving or customer needs, process the data information in 1) to establish a road network topology model.

[0041] S3, establish a spatial index for the coordinate data of roads and ground objects, and retrieve all roads within a certain range near the ground objects.

[0042] Specifically, according to the spatial index of roads and ground objects, several roads near the ground objects are retrieved. According to the type of ground objects and the level of association with roads, corresponding algorithms are used to preliminarily establish the association relationship between ground objects and road networks.

[0043] S4, according to the type of ground objects and the level of association with the road, establish the association between ground objects and the road network. This solution realizes the automatic and rapid generation of the association between ground objects and the road network in high-precision maps. Then the association is logically self-checked, and according to the results of the logical self-check, the association between ground objects and the road network calculated in S3 is filtered and fine-tuned. Finally, high-precision map data that meets user needs is output.

[0044] This solution has high computational efficiency and adopts a spatial index mechanism. It can process large-scale map data and quickly calculate the relationship between ground objects and road networks. The entire process automatically generates the relationship between ground objects and road networks, and has built-in logical self-checking and optimization algorithms. No human intervention is required throughout the process, effectively improving production efficiency and data accuracy.

[0045] The road network topology model includes: roads, road sections, and lanes, wherein a road is composed of several road sections, and a road section is composed of several lanes. Figure 2 As shown, road R1 consists of two road sections (road section 1 and roadsection 2), and the road section (R2 road section 1) consists of three lanes (lv1, lv2, lv3). The association relationship between ground objects and road networks mainly includes two types of association relationships: association to road sections and association to lanes. If a ground object is associated with a road section, all ground objects related to the road section, located on the road section, or adjacent to the road section can be retrieved through the road section, and vice versa. If a ground object is associated with a lane, all ground objects related to the lane, located on the lane surface, or adjacent to the lane can be retrieved through the lane, and vice versa.

[0046] In a specific implementation scenario, the specific method process is as follows:

[0047] 1. Obtain relevant data of roads, lanes, and ground objects.

[0048] 1.1) The two-dimensional map corresponding to the high-precision map is displayed through the interface. The user can circle the required data range, required route range or required administrative division range on the two-dimensional map according to the needs. If the user does not make a selection, the data of the full range will be obtained by default.

[0049] 1.2) The user selects the required map elements, attributes, output data format and version, processing operations and other information according to the needs. If the user does not make a selection, all map elements and attributes will be obtained by default.

[0050] 2. Preprocess relevant data of roads, lanes, and ground objects

[0051] 2.1) Extract data information of relevant roads, lanes, and ground objects according to the data range, map elements, and attribute categories specified in step 1.

[0052] 2.2) According to the needs of autonomous driving or customer needs, process the data information in 2.1) and establish a road network topology model. The road network topology model varies according to the needs of autonomous driving. After the road network topology model is constructed, the relationship between roads, road sections and lanes is also established.

[0053] 2.3) Combined with the road network model, the geometric shapes of road sections and lanes are constructed, which mainly include road section surface and lane surface objects.

[0054] 2.4) Construct the geometric shape of the ground object according to its type. Ground objects can be mainly divided into point-shaped objects, chain-shaped objects and surface-shaped objects.

[0055] 2.5) Establish spatial indexes for the coordinate data of roads and ground objects. Generally, after roads are processed, the amount of road network topology data is large, and the amount of ground object data is also large. For 1 kilometer of road data, the amount of ground object data of all elements can reach millions. In order to improve the computing efficiency, establish spatial indexes for all roads and ground objects to facilitate the retrieval of road information near ground objects and reduce the calculation scope. This example uses the improved two-dimensional grid index to record all the coordinate information corresponding to each road and each ground object in the grid.

[0056] 3. Preliminary establishment of the relationship between ground objects and road networks.

[0057] like Figure 4 The process shown and Figure 5 Schematic diagram shown.

[0058] 3.1) According to the spatial index of roads and ground objects, several roads near the ground objects are retrieved.

[0059] 3.2) According to the type of ground objects and their association level with roads, corresponding algorithms are used to preliminarily establish the association relationship between ground objects and road networks.

[0060] Specifically, take the calculation of the association relationship of planar features (directional arrows) as an example:

[0061] ① Through the spatial index, it can be retrieved that road R1 or road R2 may be associated with the direction arrow;

[0062] ② Calculate whether all road sections under road R1 or road R2 have a geometric overlap relationship with the direction arrows. If so, find the road section R S , then traverse RS Check whether there is a geometric overlap relationship with the direction arrow, and if so, establish an association relationship. In this example, the direction arrow is associated with lane lv2 under road section 1 of road R2.

[0063] There are differences in the algorithms for association relationships for different ground objects, but if the geometric types and association levels of the ground objects are consistent, the algorithms can basically be universal. Therefore, this method is universal.

[0064] Similarly, the chain-shaped feature (guardrail) is associated with road section 2 of road R1, and the point-shaped feature (rod) is associated with road section 1 of road R2.

[0065] 4. Optimize and adjust the relationship between ground objects and road networks.

[0066] 4.1) According to the type and function of the ground object, the association relationship calculated in step 3 needs to be logically self-checked. For example, in an area where there are upper and lower roads, the elevation difference between the ground object and the associated lane surface can be used to detect whether the ground object is associated with the lane of the correct level of road.

[0067] 4.2) According to the results of the logic self-check, filter and fine-tune the incorrect associations of the steps to establish the correct associations between the ground objects and the road network.

[0068] 4.3) Based on the results in 4.2), special ground objects are processed, and extended association information is added as needed to further improve and enrich the association relationship. For example, for traffic lights, the offset distance from the traffic light to the first point of the associated road section can be calculated based on the association relationship between the traffic light and the road section, thereby providing more abundant positioning information for the autonomous driving vehicle.

[0069] 4.4) Output high-precision map data that meets user needs.

[0070] The present invention also provides a system for realizing a method for automatically generating a relationship between ground objects and road networks, comprising:

[0071] The front-end interactive module is used to display graphically and two-dimensional map data, so that users can select the required data range; it is used to display supported map elements, attributes and functions, so that users can select corresponding map elements, attributes and functions;

[0072] The data preprocessing module is used to extract the required relevant map data and perform preprocessing, wherein the preprocessing process includes the construction of a road network model, the geometric construction of road network objects and ground objects, and the construction of spatial indexes of road network objects and ground objects;

[0073] The association relationship calculation module is used to calculate the association relationship between ground objects and roads, and different algorithms are used for processing according to the type of ground objects and the required level of association.

[0074] See also Figure 2 Schematic diagram of an electronic device provided by an embodiment of the present invention. Figure 2 As shown, an embodiment of the present invention provides an electronic device, including a memory 1310, a processor 1320, and a computer program 1311 stored in the memory 1310 and executable on the processor 1320. When the processor 1320 executes the computer program 1311, the following steps are implemented: S1, obtaining total data of roads and ground objects;

[0075] S2, according to the requirements of autonomous driving, extract sub-data of relevant roads and related ground objects, establish a road network topology model, and construct the geometric shapes of roads and ground objects;

[0076] S3, establish a spatial index for the coordinate data of roads and ground objects, and retrieve all roads within a certain range near the ground objects;

[0077] S4, establishing an association relationship between the ground object and the road network according to the type of the ground object and the association level with the road.

[0078] See also Figure 3 Schematic diagram of an embodiment of a computer-readable storage medium provided by the present invention. Figure 3 As shown, this embodiment provides a computer-readable storage medium 1400 on which a computer program 1411 is stored. When the computer program 1411 is executed by a processor, the following steps are implemented: S1, obtaining total data of roads and ground objects;

[0079] S2, according to the requirements of autonomous driving, extract sub-data of relevant roads and related ground objects, establish a road network topology model, and construct the geometric shapes of roads and ground objects;

[0080] S3, establish a spatial index for the coordinate data of roads and ground objects, and retrieve all roads within a certain range near the ground objects;

[0081] S4, establishing an association relationship between the ground object and the road network according to the type of the ground object and the association level with the road.

[0082] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0083] The present invention mainly solves the problem of fully automatic generation of the association relationship between ground objects and road networks in the process of high-precision electronic map production. Compared with the existing technology, it has the following advantages: 1) It covers all ground elements, including almost all ground objects related to autonomous driving. The association relationship generation method is universal and can be applied to newly emerging ground objects; 2) It has high computational efficiency and adopts a spatial indexing mechanism, which can process a large range of map data and quickly calculate the association relationship between ground objects and road networks; 3) It has high accuracy of association information. The association relationship between ground objects and road networks not only supports association to the road level, but also supports association to the road section level and lane level, which can effectively meet the high-precision requirements of autonomous driving; 4) The association relationship information between ground objects and road networks supports expansion and updating, and can provide richer association information according to the needs of autonomous driving; 5) The association relationship between ground objects and road networks is automatically generated throughout the entire process, with built-in logical self-checking and optimization algorithms, without the need for manual intervention throughout the process, effectively improving production efficiency and data accuracy.

[0084] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0085] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0086] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0087] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0088] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0089] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A method for automatically generating the relationship between ground objects and road networks, characterized in that: include: S1, obtain the total data of roads and ground objects; S2, according to the requirements of autonomous driving, extract sub-data of relevant roads and related ground objects, establish a road network topology model, and construct the geometric shapes of roads and ground objects; S3, establish a spatial index for the coordinate data of roads and ground objects, and retrieve all roads within a certain range near the ground objects; S4, establishing an association relationship between the ground object and the road network according to the type of the ground object and the association level with the road; The S4 specifically includes: S41, a direction arrow is drawn up, and a road set R={R1, R2, R3, ..., Rn} near the direction arrow is retrieved through a spatial index, where each road in the road set may be associated with the direction arrow; S42, respectively calculate whether all road sections under the road Rx (x=1, 2, ..., n) in the road set have a geometric overlap relationship with the direction arrows, and if so, find the road section R S , and then traverse the road section R S Check the lane below to see if there is a geometric overlap relationship between the lane and the direction arrow. If so, establish an association relationship.

2. The method for automatically generating the relationship between ground objects and road networks according to claim 1, characterized in that: The S1 specifically includes: Displaying a two-dimensional map corresponding to the high-precision map through an interface, and circling a required data range, a required route range, or a required administrative division range on the two-dimensional map according to user needs; Select the map elements, attributes, output data format, version and processing operation information within the required range according to your needs.

3. The method for automatically generating the relationship between ground objects and road networks according to claim 1, characterized in that: The S4 also includes: S5, performing a logic self-check on the association relationship according to the type of the ground object, and then filtering and fine-tuning the association relationship; S6, process special ground objects, add extended associated information as needed, further improve and enrich the associated relationship and output high-precision map data.

4. The method for automatically generating the relationship between ground objects and road networks according to claim 1, characterized in that: The ground objects include ground interest surfaces, ground markers, static obstacles, road ancillary facilities, pole objects, traffic signs and traffic lights; the road includes road sections, and the road sections include lanes.

5. The method for automatically generating the relationship between ground objects and road networks according to claim 4, characterized in that: The association relationship between the ground object and the road network includes: All ground objects retrieved through the road section that are related to the road section or located on the road section or adjacent to the road section; All ground objects retrieved through the lane are related to the lane or are located on the lane surface or are adjacent to the lane.

6. The method for automatically generating the relationship between ground objects and road networks according to claim 1, characterized in that: The S3 specifically includes: using a two-dimensional grid index to record all coordinate information corresponding to each road and each ground object in the grid.

7. A system for implementing the method for automatically generating the relationship between ground objects and road networks as claimed in any one of claims 1 to 6, characterized in that: include: The front-end interactive module is used to display graphically and 2D map data, so that users can select the required data range; Used to display supported map elements, attributes and functions, so that users can select corresponding map elements, attributes and functions; The data preprocessing module is used to extract the required relevant map data and perform preprocessing, wherein the preprocessing process includes the construction of a road network model, the geometric construction of road network objects and ground objects, and the construction of spatial indexes of road network objects and ground objects; The association relationship calculation module is used to calculate the association relationship between ground objects and roads, and uses different algorithms to process according to the type of ground objects and the required level of association; The association relationship calculation module is specifically used for: A direction arrow is drawn up, and a road set R={R1, R2, R3, ..., Rn} near the direction arrow is retrieved through a spatial index, where each road in the road set may be associated with the direction arrow; Calculate whether all road sections under the road set Rx (x = 1, 2, ..., n) have a geometric overlap relationship with the direction arrows. If so, find the road section R S , and then traverse the road section R S Check the lane below to see if there is a geometric overlap relationship between the lane and the direction arrow. If so, establish an association relationship.

8. An electronic device, characterized in that: It comprises a memory and a processor, wherein the processor is used to implement the steps of the method for automatically generating the association relationship between ground objects and road networks as described in any one of claims 1 to 6 when executing the computer management program stored in the memory.

9. A computer-readable storage medium, characterized in that: A computer management program is stored thereon, and when the computer management program is executed by a processor, the steps of the method for automatically generating the relationship between ground objects and road networks as described in any one of claims 1 to 6 are implemented.

Images