A high-precision map heterogeneous data fusion method and device

Abstract

The application relates to a high-precision map heterogeneous data fusion method and device, which comprises the following steps: acquiring high-precision map data of expressways, fast roads and urban roads; standardizing the high-precision map data of the expressways, the fast roads and the urban roads to obtain multiple pieces of standard-consistent high-precision map data; performing road matching on the multiple pieces of standard-consistent high-precision map data, and performing cutting according to the matched road data; and fusing the multiple pieces of standard-consistent high-precision map data based on the cut road data through spatial indexing. Through standardization and fusion of the expressway, fast road and urban road data, the adaptability problem caused by multi-map switching when driving from a high-speed road into an urban area is solved, and the adaptability and automation degree of the data are improved.

Description

Technical Field

[0001] This invention belongs to the field of high-precision map production technology, specifically relating to a method and apparatus for high-precision map heterogeneous data fusion. Background Technology

[0002] High-precision electronic maps primarily serve autonomous vehicles, providing lane-level planning and vehicle positioning assistance within road segments. However, current data standards differ between highway and urban surveying, and these data are stored in separate, physically disconnected databases. Currently, intelligent driving or assisted driving systems transition from highways to urban areas, and urban intelligent driving solutions still rely on high-speed intelligent driving solutions. Urban NOA (Navigational Operating Aid) requires high-precision maps to provide beyond-line-of-sight representation and perception supplementation capabilities, thus creating a demand for high-precision urban maps in addition to those for highway systems. Summary of the Invention

[0003] To achieve seamless switching of NOA (Noise of Access) between highways and urban areas in high-precision maps, a first aspect of this invention provides a method for fusing heterogeneous high-precision map data, comprising: acquiring high-precision map data of highways, expressways, and urban roads; standardizing the high-precision map data of highways, expressways, and urban roads to obtain multiple sets of standardized high-precision map data; performing road matching on the multiple sets of standardized high-precision map data and segmenting the matched road data; and fusing the multiple sets of standardized high-precision map data using spatial indexing based on the segmented road data.

[0004] In some embodiments of the present invention, the step of performing road matching on the multiple sets of standardized high-precision map data and segmenting the matched road data includes: establishing a spatial index based on road location information; retrieving each road through the spatial index to obtain the matching relationship between each road and its neighboring roads; and segmenting the road data in each set of standardized high-precision map data based on the matching relationship between each road and its neighboring roads.

[0005] Furthermore, the step of segmenting the road data in each set of standardized high-precision map data based on the matching relationship between each road and its neighboring roads includes: generating one or more difference points based on the matching relationship between each road and its neighboring roads; constructing one or more cutting lines according to the validity of the difference points; and segmenting the road data in each set of standardized high-precision map data based on the cutting lines.

[0006] In some embodiments of the present invention, the fusion of multiple standardized high-precision map data based on the segmented road data and using a spatial index includes: constructing a road spatial index based on the segmented road data; aggregating the segmented starting dead-end roads and ending dead-end roads respectively; fusing the aggregated starting dead-end road data and ending dead-end road data based on the road spatial index; and fusing the road topology, lane topology, and ground features in the multiple standardized high-precision map data according to the fused road information.

[0007] Furthermore, the process of fusing the collected starting point dead-end road data and ending point dead-end road data also includes: verifying the fused dead-end road data and ending point dead-end road data.

[0008] In the above embodiments, the standardization of the high-precision map data of the highways, expressways, and urban roads to obtain multiple sets of high-precision map data with consistent standards includes: extracting relevant road, lane, and ground object data from the high-precision map data of the highways, expressways, and urban roads; and standardizing the road, lane, and ground object data according to a preset standard to obtain multiple sets of high-precision map data with consistent standards.

[0009] A second aspect of the present invention provides a high-precision map heterogeneous data fusion device, comprising: an acquisition module for acquiring high-precision map data of highways, expressways, and urban roads; a standardization module for standardizing the high-precision map data of highways, expressways, and urban roads to obtain multiple sets of standardized high-precision map data; a cutting module for performing road matching on the multiple sets of standardized high-precision map data and cutting the road data according to the matched road data; and a fusion module for fusing the multiple sets of standardized high-precision map data based on the cut road data and using spatial indexing.

[0010] Furthermore, the cutting module includes: a building unit, used to build a spatial index based on road location information; a matching unit, used to retrieve each road through the spatial index to obtain the matching relationship between each road and its neighboring roads; and a cutting unit, used to cut the road data in each set of standardized high-precision map data based on the matching relationship between each road and its neighboring roads.

[0011] A third aspect of the present invention provides an electronic device comprising: one or more processors; and a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the high-precision map heterogeneous data fusion method provided in the first aspect of the present invention.

[0012] In a fourth aspect, the present invention provides a computer-readable medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the high-precision map heterogeneous data fusion method provided in the first aspect of the present invention.

[0013] The beneficial effects of this invention are:

[0014] This invention relates to a method and apparatus for high-precision map heterogeneous data fusion. The method includes: acquiring high-precision map data of highways, expressways, and urban roads; standardizing the high-precision map data of highways, expressways, and urban roads to obtain multiple sets of standardized high-precision map data; performing road matching on the multiple sets of standardized high-precision map data and segmenting the matched road data; and fusing the multiple sets of standardized high-precision map data using spatial indexing based on the segmented road data.

[0015] As can be seen, this invention solves the problem of switching between multiple maps for intelligent driving from highways to urban areas. Compared with existing technologies, it has the following main advantages: 1) It can quickly adapt to and unify the standards and specifications of highways and urban areas. Currently, there are many map vendors on the market with varying standards, update frequencies, and map quality and accuracy. Data standardization allows all participants to create and use maps in the same way. These standards and specifications include, but are not limited to, map coverage, map quality, and update rate; 2) It solves the adaptability problem caused by switching between multiple maps when intelligent driving enters urban areas from highways. It can provide beyond-line-of-sight expression and perception supplementation capabilities on high-precision maps in urban NOA, enabling NOA functionality in all scenarios; 3) It automatically generates a single map throughout the entire process, with built-in logic self-checking and optimization algorithms, requiring no manual intervention throughout the process, effectively improving production efficiency and data accuracy. Attached Figure Description

[0016] Figure 1 This is a schematic diagram of the basic process of the high-precision map heterogeneous data fusion method in some embodiments of the present invention;

[0017] Figure 2 This is a schematic diagram illustrating the specific process of the high-precision map heterogeneous data fusion method in some embodiments of the present invention;

[0018] Figure 3 This is a schematic diagram of a high-precision map and urban map fast fusion and matching algorithm in some embodiments of the present invention;

[0019] Figure 4 This is a schematic diagram illustrating the differences between high-precision fast maps and urban maps in some embodiments of the present invention.

[0020] Figure 5This is a timing diagram of the algorithm for rapidly fusing high-precision, high-speed maps and urban maps to generate cutting lines in some embodiments of the present invention;

[0021] Figure 6 This is a schematic diagram of a high-precision map and urban map fast fusion algorithm in some embodiments of the present invention;

[0022] Figure 7 This is a schematic diagram of the structure of a high-precision map heterogeneous data fusion device in some embodiments of the present invention;

[0023] Figure 8 This is a schematic diagram of the structure of an electronic device in some embodiments of the present invention. Detailed Implementation

[0024] The principles and features of the present invention are described below with reference to the accompanying drawings. The examples given are only for explaining the present invention and are not intended to limit the scope of the present invention.

[0025] refer to Figure 1 and Figure 2 In a first aspect, the present invention provides a method for fusing heterogeneous high-precision map data, comprising: S100. acquiring high-precision map data of highways, expressways, and urban roads; S200. standardizing the high-precision map data of highways, expressways, and urban roads to obtain multiple sets of standardized high-precision map data; S300. performing road matching on the multiple sets of standardized high-precision map data and segmenting the matched road data; S400. fusing the multiple sets of standardized high-precision map data based on the segmented road data using spatial indexing.

[0026] In step S100 of some embodiments of the present invention, high-precision map data of highways, expressways, and urban roads are acquired. Specifically, this includes:

[0027] S101. The interface displays a two-dimensional map corresponding to the high-precision map. Users can define the required data range, route range, or administrative division range on the two-dimensional map according to their needs. If the user does not make a selection, the complete range of data is retrieved by default.

[0028] S102. The user selects the required map elements, attributes, output data format and version, processing operations, etc., according to their needs. If the user does not make a selection, all map elements and attributes will be retrieved by default.

[0029] To improve the fusion speed of heterogeneous data, high-precision map data for highways, expressways, and urban roads must meet the following requirements: 1. They must possess basic high-precision geographic feature data with complete scope, feature types, and attributes; 2. All heterogeneous data must conform to real-world scenarios, and the data should avoid significant discrepancies in timeliness; 3. Data overlap is required at fusion junctions, and this overlap must not be at intersections (including lane addition zones); 4. All intersections in the source data must be fully constructed with consistent definitions, and there should be no structural changes to intersections (e.g., changes in entry / exit routes / intersection splitting into multiple intersections); 5. All heterogeneous data must possess elevation information, and the elevation error must not exceed the meter level.

[0030] Therefore, it is necessary to standardize heterogeneous data. In step S200 of some embodiments of the present invention, the standardization of the high-precision map data of highways, expressways, and urban roads to obtain multiple sets of high-precision map data with consistent standards includes:

[0031] S201. Extract relevant road, lane, and ground object data from the high-precision map data of the expressway, expressway, and urban roads; specifically, extract relevant road, lane, and ground object data information for both expressways and urban roads according to the data range, map features, and attribute categories specified in step S100.

[0032] S202. Standardize the data of the road, lane, and ground objects according to preset standards to obtain multiple sets of high-precision map data with consistent standards. Specifically, according to the needs of autonomous driving or customer requirements, standardize the data information in step S201 to form two sets of consistent data information.

[0033] refer to Figure 3 In step S300 of some embodiments of the present invention, the step of performing road matching on the multiple sets of standardized high-precision map data and segmenting the road data according to the matched road data includes:

[0034] S301. Establish a spatial index based on road location information; specifically, after road processing, the amount of road network topology data is generally large. For example, the total data volume for 1 km of roads can reach millions of elements. To improve computational efficiency, a spatial index is established for all roads to facilitate the retrieval of road information near existing roads and narrow the computational scope. This example uses an STR Tree to establish the spatial index, a tree-like data structure for spatial storage, enabling fast and efficient spatial searches.

[0035] S302. Retrieve each road using the spatial index to obtain the matching relationship between each road and its neighboring roads; specifically, based on the road spatial index, retrieve several roads that share a common area with each road.

[0036] S303. Based on the matching relationship between each road and its neighboring roads, the road data in each set of standardized high-precision map data is segmented. Specifically, for roads with matching relationships, the next step of segmentation is performed if the following conditions are met:

[0037] ① The Hausdorff distance between matched roads is less than 5 meters (the error value can be adjusted according to the actual data scenario). ② The elevation difference between matched roads is less than 3 meters. ③ The heading angle between matched roads is greater than 90°.

[0038] refer to Figure 4 and Figure 5 Furthermore, in step S303, the process of segmenting the road data in each set of standardized high-precision map data based on the matching relationship between each road and its neighboring roads includes:

[0039] S3031. Based on the matching relationship between each road and its neighboring roads, generate one or more difference points; specifically, obtain difference points from the obtained road matching relationships, traverse all roads, check whether there are unmatched intervals in the roads, and if so, generate a difference point at that position.

[0040] In step S3032, one or more cutting lines are constructed based on the validity of the difference points. The specific cutting process includes: advancing along the road according to the difference points, moving one meter at a time, and constructing a cutting line.

[0041] ①The road is inside the intersection.

[0042] ②The cutting line is too close to the beginning and end points, less than 0.8 meters.

[0043] ③ The cutting point is in a non-ordinary interval.

[0044] ④ The number of lanes in the section where the cutting point is located is inconsistent.

[0045] ⑤ The search distance exceeds the limit: 500 meters.

[0046] If conditions ① and ⑤ are met, the search is terminated; if any one of conditions ②, ③, or ④ is met, the search is continued, and step S3031 is repeated.

[0047] S3033. Based on the cutting lines, cut the road data in each set of standardized high-precision map data. Cut the road network information according to the cutting lines constructed in step S3032, and discard dead-end roads and duplicate roads in overlapping areas according to the difference points obtained in step S3031 and the matching relationships in steps S301 to S303.

[0048] refer to Figure 6 In some embodiments of the present invention, step S400, the fusion of multiple standardized high-precision map data based on the cut road data using spatial indexing includes:

[0049] S401. Based on the segmented road data, construct a road spatial index; specifically, construct a road spatial index for the two segments of data. It should be noted that these two segments of data can be adjusted to multiple segments as needed, without affecting the description of the technical solution in this application.

[0050] S402. Collect the starting dead-end roads and ending dead-end roads after the cutting respectively; specifically, collect the starting dead-end roads and ending dead-end roads of the two datasets respectively.

[0051] S403. Based on the road spatial index, the collected starting point dead-end road data and ending point dead-end road data are fused respectively; specifically, the ending point dead-end roads of expressways collected in step S402 are traversed, and the starting point dead-end roads of urban roads covered by them are obtained using the spatial index obtained in S401; the ending point dead-end roads of expressways collected in step S402 are traversed, and the ending point dead-end roads of urban roads covered by them are obtained using the spatial index obtained in S401.

[0052] Furthermore, after fusing the collected starting point dead-end road data and ending point dead-end road data, the process further includes: S404. Verifying the fused dead-end road data and ending point dead-end road data. Specifically, the verification of the fusion conditions in S402 and S403 is as follows: ① The difference in heading angle between roads is greater than 90°; ② The average elevation of the road overlap is less than 3 meters.

[0053] S405. Based on the fused road information, the road topology, lane topology, and ground features from multiple standardized high-precision map data sets are fused. Specifically, the road topology, lane topology, and ground features are fused for the obtained road information to be fused.

[0054] Ultimately, the output is a high-precision map data fusion that meets the user's needs.

[0055] Example 2

[0056] refer to Figure 7In a second aspect, the present invention provides a high-precision map heterogeneous data fusion device 1, comprising: an acquisition module 11 for acquiring high-precision map data of highways, expressways, and urban roads; a standardization module 12 for standardizing the high-precision map data of highways, expressways, and urban roads to obtain multiple sets of standardized high-precision map data; a cutting module 13 for performing road matching on the multiple sets of standardized high-precision map data and cutting the matched road data; and a fusion module 14 for fusing the multiple sets of standardized high-precision map data based on the cut road data using spatial indexing.

[0057] Furthermore, the cutting module 13 includes: an establishment unit for establishing a spatial index based on road location information; a matching unit for retrieving each road through the spatial index to obtain the matching relationship between each road and its neighboring roads; and a cutting unit for cutting the road data in each set of standardized high-precision map data based on the matching relationship between each road and its neighboring roads.

[0058] Example 3

[0059] refer to Figure 8 In a third aspect, the present invention provides an electronic device comprising: one or more processors; and a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the high-precision map heterogeneous data fusion method of the first aspect of the present invention.

[0060] Electronic device 500 may include a processing unit (e.g., a central processing unit, a graphics processing unit, etc.) 501, which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 502 or a program loaded from storage device 508 into random access memory (RAM) 503. The RAM 503 also stores various programs and data required for the operation of electronic device 500. The processing unit 501, ROM 502, and RAM 503 are interconnected via bus 504. An input / output (I / O) interface 505 is also connected to bus 504.

[0061] Typically, the following devices can be connected to I / O interface 505: input devices 506 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 507 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 508 including, for example, hard disks; and communication devices 509. Communication device 509 allows electronic device 500 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 8An electronic device 500 with various devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively. Figure 8 Each box shown can represent a device or multiple devices as needed.

[0062] Specifically, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 509, or installed from a storage device 508, or installed from a ROM 502. When the computer program is executed by a processing device 501, it performs the functions defined in the methods of embodiments of this disclosure. It should be noted that the computer-readable medium described in embodiments of this disclosure can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In embodiments of this disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in connection with an instruction execution system, apparatus, or device. In embodiments of this disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. Program code contained on a computer-readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0063] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device. The aforementioned computer-readable medium carries one or more computer programs, which, when executed by the electronic device, cause the electronic device to:

[0064] Computer program code for performing the operations of embodiments of this disclosure can be written in one or more programming languages ​​or a combination thereof. Programming languages ​​include object-oriented programming languages—such as Java, Smalltalk, C++, and Python—and conventional procedural programming languages—such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0065] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0066] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for fusing heterogeneous data in high-precision maps, characterized in that, include: Acquire high-precision map data of highways, expressways, and urban roads; The high-precision map data of the highways, expressways and urban roads are standardized to obtain multiple sets of high-precision map data with consistent standards. Road matching is performed on the multiple sets of high-precision map data with consistent standards, and the matched road data is then segmented. Based on the segmented road data, the multiple sets of standardized high-precision map data are fused using spatial indexing; The process of fusing multiple standardized high-precision map data based on the segmented road data using spatial indexing includes: Based on the segmented road data, a road spatial index is constructed; The starting dead-end roads and ending dead-end roads after the cutting are collected separately; Based on the road space index, the collected starting point dead-end road data and ending point dead-end road data are fused together respectively; Based on the merged road information, the road topology, lane topology, and ground features from multiple standardized high-precision map data are fused.

2. The high-precision map heterogeneous data fusion method according to claim 1, characterized in that, The process of matching roads among the multiple sets of standardized high-precision map data and segmenting the matched road data includes: Establish a spatial index based on road location information; The spatial index is used to retrieve the matching relationship between each road and its neighboring roads. Based on the matching relationship between each road and its neighboring roads, the road data in each set of standardized high-precision map data is segmented.

3. The high-precision map heterogeneous data fusion method according to claim 2, characterized in that, The process of segmenting road data in each set of standardized high-precision map data based on the matching relationship between each road and its neighboring roads includes: Based on the matching relationship between each road and its neighboring roads, generate one or more difference points; Based on the validity of the difference points, construct one or more cutting lines; Based on the cutting lines, road data in each set of standardized high-precision map data is cut.

4. The high-precision map heterogeneous data fusion method according to claim 3, characterized in that, The process of fusing the collected starting point dead-end road data and ending point dead-end road data also includes: The merged dead-end road data and the terminal dead-end road data are verified.

5. The high-precision map heterogeneous data fusion method according to claim 1, characterized in that, The standardization of the high-precision map data of highways, expressways, and urban roads yields multiple sets of standardized high-precision map data, including: Extract data on relevant roads, lanes, and ground objects from the high-precision map data of the highways, expressways, and urban roads; According to preset standards, the data of the roads, lanes and ground objects are standardized to obtain multiple sets of high-precision map data with consistent standards.

6. A high-precision map heterogeneous data fusion apparatus that applies the high-precision map heterogeneous data fusion method as described in any one of claims 1-5, characterized in that, include: The acquisition module is used to acquire high-precision map data of highways, expressways, and urban roads. The standardization module is used to standardize the high-precision map data of the highways, expressways and urban roads to obtain multiple sets of high-precision map data with consistent standards. The cutting module is used to perform road matching on the multiple sets of high-precision map data with consistent standards, and to cut the roads based on the matched road data. The fusion module is used to fuse multiple sets of standardized high-precision map data based on the segmented road data and through spatial indexing.

7. The high-precision map heterogeneous data fusion device according to claim 6, characterized in that, The cutting module includes: Establish a unit for creating a spatial index based on road location information; The matching unit is used to retrieve each road through the spatial index and obtain the matching relationship between each road and its neighboring roads; The cutting unit is used to cut road data in each set of standardized high-precision map data based on the matching relationship between each road and its neighboring roads.

8. An electronic device, comprising: One or more processors; A storage device for storing one or more programs, which, when executed by one or more processors, cause the one or more processors to implement the high-precision map heterogeneous data fusion method as described in any one of claims 1 to 5.

9. A computer-readable medium having a computer program stored thereon, wherein, When the computer program is executed by the processor, it implements the high-precision map heterogeneous data fusion method as described in any one of claims 1 to 5.

Images