Road network topological graph generation method and device, electronic equipment and storage medium

By dividing and extending boundaries, clustering trajectory data, and establishing topological reference points, the method generates accurate and reliable road network topology maps, resolving inconsistencies in larger area mappings.

CN119066446APending Publication Date: 2024-12-03ZHEJIANG GEELY HLDG GRP CO LTD +1
View PDF 3 Cites 0 Cited by

Patent Information

Application Number
CN202410959787.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-17
Publication Date
2024-12-03

AI Technical Summary

Technical Problem

Existing methods for generating road network topology maps for larger areas result in inconsistent boundaries and node inconsistencies when merging sub-area maps, leading to reduced accuracy.

Method used

The method involves dividing the target area into sub-areas, performing boundary extension operations to combine each area with adjacent regions, clustering trajectory data to establish topological reference points, and generating a topology map based on these points, ensuring self-consistency and accuracy.

Benefits of technology

This approach improves data processing efficiency and ensures accurate, reliable road network topology maps by addressing boundary inconsistencies and enhancing the generation of topological reference points.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119066446A_ABST
    Figure CN119066446A_ABST
Patent Text Reader

Abstract

The invention provides a road network topological graph generation method and device, electronic equipment and a storage medium, and relates to the technical field of computers. The method comprises the following steps: dividing a target area into a plurality of sub-target areas, and obtaining track data contained in each sub-target area; boundary expansion operation is executed on each first area to obtain a boundary expansion area corresponding to the first area; performing clustering operation on each boundary expansion region to obtain at least one target class cluster, and taking each target class cluster in the first region as a topological reference point; and obtaining a topological reference point set according to the topological reference points, and generating a road network topological graph based on the topological reference point set. By determining the boundary expansion area and clustering the trajectory data contained in the boundary expansion area, reliable external reference is provided for generation of the topological reference points corresponding to the sub-target areas, self-consistency of the topological reference points near the boundary can be ensured, and the accuracy of the road network topological graph is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a method, device, electronic device and storage medium for generating a road network topology map. Background Art

[0002] With the continuous development of technologies such as autonomous driving, the accuracy requirements for electronic maps such as road network topology maps are gradually increasing. When facing the task of generating road network topology maps for larger areas, due to the extremely large data scale, in order to reduce data pressure and improve processing efficiency, the larger area is usually divided into multiple smaller sub-areas to facilitate targeted data processing of different sub-areas, and then generate the road network topology map corresponding to each sub-area.

[0003] However, after the existing method is used to generate the road network topology map corresponding to each sub-area, in the process of boundary docking and fusion of the road network topology maps corresponding to each sub-area, the boundaries between multiple road network topology maps are usually not self-consistent, which can easily lead to problems such as road discontinuity and node inconsistency in the fused road network topology map, making it difficult to ensure the accuracy of the road network topology map. Summary of the invention

[0004] The problem solved by the present invention is how to improve the accuracy of the road network topology map.

[0005] In order to solve the above problems, the present invention provides a method for generating a road network topology map, comprising:

[0006] Divide the target area into a plurality of sub-target areas, and obtain the trajectory data contained in each of the sub-target areas;

[0007] Performing a boundary extension operation on each first region respectively, wherein one first region corresponds to one sub-target region, and the boundary extension operation includes combining the first region and at least a portion of the sub-target region adjacent to the first region to obtain a boundary extension region corresponding to the first region;

[0008] Performing a clustering operation on each of the boundary extension areas respectively, wherein the clustering operation includes clustering the trajectory data contained in the boundary extension area to obtain at least one target cluster, and taking each of the target clusters located in the first area as a topological reference point;

[0009] A topological reference point set of the target area is obtained according to all the topological reference points, and a road network topology map corresponding to the target area is generated based on the topological reference point set.

[0010] Optionally, combining the first area and at least a portion of the sub-target area adjacent to the first area to obtain a boundary extension area corresponding to the first area includes:

[0011] The first area is combined with the second area to obtain the boundary extension area, wherein the second area includes each sub-target area corresponding to the eight neighborhoods of the first area.

[0012] Optionally, before performing the clustering operation on each of the boundary extension areas respectively, the method further includes:

[0013] The target area is grid-divided in a preset coordinate system to obtain a trajectory grid set corresponding to each sub-target area; wherein each trajectory grid set includes at least one trajectory grid, each trajectory grid includes at least one trajectory segment, and each trajectory segment corresponds to a segment of trajectory data in one of the trajectory data.

[0014] Optionally, each of the track segments includes a plurality of track points and a longitude and latitude position corresponding to each of the track points; after obtaining the track grid set corresponding to each of the sub-target areas, the method further includes:

[0015] The longitude and latitude positions corresponding to each of the track points in the track grid set are converted into coordinate positions in the preset coordinate system.

[0016] Optionally, clustering the trajectory data contained in the boundary extension area includes:

[0017] Clustering the trajectory segments in each trajectory grid in the boundary extension area according to a preset strategy to obtain at least one trajectory group in each trajectory grid;

[0018] The trajectory groups in the first grid and the second grid are clustered according to the preset strategy, wherein one of the first grids corresponds to one of the trajectory grids in the boundary extension area, and the second grids are the trajectory grids corresponding to the eight neighborhoods of the first grid.

[0019] Optionally, the trajectory segment includes multiple types of trajectory information; and the preset strategy includes:

[0020] Clustering the trajectory segments whose similarity with respect to the first type of trajectory information in the trajectory grid exceeds a first preset threshold into one of the trajectory groups;

[0021] Clustering disconnected trajectory groups whose similarity about the second type of trajectory information in the first grid and the second grid exceeds a second preset threshold into one target cluster, wherein the trajectory information of the trajectory group includes the trajectory information of the corresponding trajectory segment.

[0022] Optionally, generating a road network topology map corresponding to the target area based on the topology reference point set includes:

[0023] The topological relationship between each of the topological reference points in the topological reference point set is determined according to the trajectory data, and the road network topology map is generated based on the topological reference points and the topological relationship.

[0024] When facing the task of generating a road network topology map of a larger target area, the present invention can divide the target area into multiple sub-target areas, which is conducive to reducing the difficulty of data processing and improving data processing efficiency. At the same time, obtaining the trajectory data contained in each of the sub-target areas is conducive to providing a reliable reference basis for the subsequent generation of topological reference points corresponding to each sub-target area. In the present invention, a first area corresponds to a sub-target area. First, a boundary extension operation is performed on each first area respectively, which is conducive to the parallel generation of the boundary extension area corresponding to each sub-target map. At the same time, the boundary extension operation in the present invention includes combining the first area and at least part of the sub-target area adjacent to the first area, which is conducive to analyzing the correlation between the boundary of the first area and the sub-target area adjacent to it, and providing a reliable external information reference for the subsequent generation of the corresponding topological reference point at the boundary of each first area. Secondly, in the present invention, a clustering operation is performed on each boundary extension area respectively, which is conducive to the parallel processing of the trajectory data in the boundary extension area corresponding to each first area, and further improves the generation efficiency of the topological reference point set corresponding to the overall target area. At the same time, the boundary extension area obtained by performing the boundary extension operation on the first area includes at least part of the sub-target area adjacent to the first area, and accordingly, the boundary extension area can include part of the trajectory data of the sub-target area adjacent to the first area. Thus, when performing clustering operations on each boundary extension area respectively, it can be ensured that the adjacent external trajectory data can be effectively referenced when generating the target cluster near the boundary of the first area, which is conducive to breaking the data limitations when processing the first area alone, and improving the accuracy and reliability of the corresponding topological reference points at the boundary of the first area. Since the topological reference points at the corresponding boundary of each first area refer to the adjacent external trajectory data when generating, each target cluster located in the first area is used as a topological reference point respectively, and after obtaining the topological reference point set of the target area according to all the topological reference points, there is no need to perform special processing on the topological reference points at the boundaries of different first areas (i.e. corresponding to different sub-target areas), and the self-consistency of the topological reference points at the boundary position can be ensured. In this way, the road network topology map corresponding to the target area is generated based on the topological reference point set, and the problems such as the conflict of topological reference points at the boundaries of multiple sub-target maps when merging can be avoided, which is conducive to improving the accuracy and reliability of the road network topology map corresponding to the target area.

[0025] The present invention also provides a device for generating a road network topology map, comprising:

[0026] A division module, which is used to divide the target area into multiple sub-target areas and obtain the trajectory data contained in each of the sub-target areas;

[0027] an expansion module, configured to perform a boundary expansion operation on each first region respectively, wherein one first region corresponds to one sub-target region, and the boundary expansion operation includes combining the first region and at least a part of the sub-target region adjacent to the first region to obtain a boundary expansion region corresponding to the first region;

[0028] A clustering module, configured to perform a clustering operation on each of the boundary extension areas, wherein the clustering operation includes clustering the trajectory data contained in the boundary extension area to obtain at least one target cluster, and taking each of the target clusters located in the first area as a topological reference point;

[0029] A generating module is used to obtain a topological reference point set of the target area according to all the topological reference points, and to generate a road network topology map corresponding to the target area based on the topological reference point set.

[0030] The advantages of the device for generating a road network topology map provided by the present invention and the method for generating a topology map are basically the same as those of the prior art, and will not be described in detail here.

[0031] The present invention also provides an electronic device, comprising a memory and a processor;

[0032] The memory is used to store computer programs;

[0033] The processor is used to implement the method for generating a road network topology map as described above when executing the computer program.

[0034] The advantages of the electronic device provided by the present invention and the method for generating the road network topology map are basically the same as those of the prior art, and will not be repeated here.

[0035] The present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the method for generating a road network topology map as described above is implemented.

[0036] The advantages of the computer-readable storage medium provided by the present invention and the method for generating the road network topology map are basically the same as those of the prior art and will not be elaborated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 A schematic diagram of a process for generating a road network topology map according to an embodiment of the present invention;

[0038] Figure 2 A schematic diagram of the positional relationship between sub-target areas in an embodiment of the present invention;

[0039] Figure 3A schematic diagram of a flow chart of parallel processing of each sub-target area according to an embodiment of the present invention;

[0040] Figure 4 is a schematic diagram of a trajectory grid set according to an embodiment of the present invention;

[0041] Figure 5 It is a schematic diagram of the existing trajectory grid division method;

[0042] Figure 6 Schematic diagram of a method for dividing a trajectory grid according to an embodiment of the present invention;

[0043] Figure 7 A schematic diagram of the positional relationship between the first grid and the second grid in the boundary extension area according to an embodiment of the present invention;

[0044] Figure 8 A schematic diagram of a flow chart of a method for generating a road network topology map according to another embodiment of the present invention;

[0045] Fig. 9 A schematic diagram of the structure of a device for generating a road network topology map according to an embodiment of the present invention;

[0046] Fig.10 Schematic diagram of the structure of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0047] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below in conjunction with the accompanying drawings. Although certain embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be interpreted as being limited to the embodiments described herein. On the contrary, these embodiments are provided to provide a more thorough and complete understanding of the present invention. It should be understood that the drawings and embodiments of the present invention are only for exemplary purposes and are not intended to limit the scope of protection of the present invention.

[0048] It should be understood that the various steps described in the method embodiments of the present invention may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present invention is not limited in this respect.

[0049] The term "including" and its variations used in this document are open inclusions, that is, "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one other embodiment"; the term "some embodiments" means "at least some embodiments"; the term "optionally" means "optional embodiments". Relevant definitions of other terms will be given in the following description. It should be noted that the concepts of "first", "second", etc. mentioned in the present invention are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0050] It should be noted that the modifications of "one" and "plurality" mentioned in the present invention are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0051] like Figure 1 As shown, a method for generating a road network topology map provided by an embodiment of the present invention includes:

[0052] S1: Divide the target area into multiple sub-target areas, and obtain the trajectory data contained in each sub-target area.

[0053] Specifically, the target area referred to in this embodiment represents the area where the road network topology map needs to be constructed, which can be divided into multiple sub-target areas (such as dividing the target area into grids, and each grid unit can correspond to a sub-target area). The trajectory data referred to in this embodiment may include the driving trajectory corresponding to the vehicle when it is driving in the sub-target area, for example, the driving trajectory composed of a longitude and latitude trajectory point set obtained by a GPS or Beidou positioning device.

[0054] This embodiment divides the target area into multiple sub-target areas, which is conducive to reducing the difficulty of data processing and improving data processing efficiency in the task of generating a road network topology map for a larger target area. At the same time, obtaining the trajectory data contained in each of the sub-target areas is conducive to providing a reliable reference basis for the subsequent generation of topological reference points corresponding to each sub-target area.

[0055] S2: performing a boundary extension operation on each first region respectively, wherein one first region corresponds to one sub-target region, and the boundary extension operation includes combining the first region and at least part of the sub-target region adjacent to the first region to obtain a boundary extension region corresponding to the first region.

[0056] Specifically, in this embodiment, one first region corresponds to one sub-target region, and a sub-target region adjacent to the first region may represent a sub-target region having the same boundary as the first region. Figure 2 As shown, the target area can be divided into 9 sub-target areas of the same area, 1-9 (for ease of understanding and description, each sub-target area is represented by a corresponding number). Assuming that the sub-target area numbered 5 is taken as the first area, the sub-target areas adjacent to the first area can be the sub-target areas corresponding to the four neighborhoods of the first area, that is, the sub-target areas numbered 2, 4, 6, and 8.

[0057] In one embodiment, the boundary extension operation includes combining the first region and at least a portion of the sub-target region adjacent to the first region. Figure 2 The boundary extension area corresponding to the sub-target area numbered 5 (i.e., the first area) can include half of the area corresponding to the sub-target areas numbered 2, 4, 6, and 8, that is, the sub-target area numbered 5 is combined with half of the sub-target areas numbered 2, 4, 6, and 8 respectively to obtain the boundary extension area corresponding to the first area.

[0058] In this embodiment, one first area corresponds to one sub-target area, that is, any sub-target area can be used as the first area, and the boundary extension operation is performed on each first area to obtain the boundary extension area corresponding to the first area, which is conducive to the parallel generation of boundary extension areas corresponding to multiple sub-target maps and improves the generation efficiency of the topological reference point set corresponding to the overall target area. At the same time, the boundary extension operation in this embodiment includes combining the first area and at least part of the sub-target area adjacent to the first area, which is conducive to analyzing the correlation between the boundary of the first area and the sub-target area adjacent to it, and providing reliable external information reference for the subsequent generation of topological reference points corresponding to each first area boundary.

[0059] S3: performing a clustering operation on each boundary extension area respectively, wherein the clustering operation includes clustering the trajectory data contained in the boundary extension area to obtain at least one target cluster, and taking each target cluster located in the first area as a topological reference point.

[0060] Specifically, in this embodiment, the boundary extension area includes the first area and the sub-target area adjacent to the first area at least partially overlaps. It can be seen that the boundary extension area contains all the trajectory data corresponding to the first area, and part of the trajectory data of the sub-target area adjacent to the first area (for ease of understanding and expression, it is recorded as boundary reference trajectory data). In this embodiment, a method for clustering trajectory data can be set in advance. For example, the trajectory data corresponding to the first area and the trajectory features corresponding to the boundary reference trajectory data can be obtained in segments, and the trajectory features are clustered based on the similarity of the trajectory features. Assuming that the trajectory data includes a driving trajectory and a captured image corresponding to the driving trajectory, the field of view corresponding to each segment of trajectory data and the captured image in each segment of boundary reference trajectory data can be extracted. On this basis, different segments of trajectory data with a degree of overlap of the field of view greater than a preset overlap rate threshold (such as 70%) can be clustered into a target cluster, and multiple target clusters in the boundary extension area can be obtained. On this basis, each target cluster located in the first area is used as a topological reference point, and each topological reference point corresponding to the first area can be obtained.

[0061] In one embodiment, each sub-target area may be processed in parallel. Figure 3 As shown, assuming that the target area is divided into Q 1 To Q N If there are N sub-target areas in total, the N sub-target areas can be used as the first area at the same time, and the boundary extension operation can be performed on each first area respectively. On this basis, clustering operations can be performed on each boundary extension area respectively to obtain at least one target cluster corresponding to each boundary extension area. Parallel processing is helpful to improve the generation efficiency of the road network topology map corresponding to the target area. Optionally, after obtaining at least one target cluster corresponding to each boundary extension area, other target clusters except the first area in the boundary extension area can be deleted, that is, only each target cluster located in the first area is saved as each topological reference point of the first area. While ensuring the reliability, accuracy, and self-consistency of the topological reference points at the boundary of the first area, it is also helpful to reduce redundant data and reduce computing power overhead.

[0062] In this embodiment, for each boundary extension area, clustering is performed on the trajectory data contained in the boundary extension area, which is conducive to realizing parallel processing of trajectory data in the boundary extension area corresponding to multiple sub-target maps, and further improving the generation efficiency of the topological reference point set corresponding to the overall target area. At the same time, the boundary extension area contains part of the trajectory data of the sub-target area adjacent to the first area, and clustering the trajectory data contained in the boundary extension area to obtain multiple target clusters is conducive to breaking the data limitations of each first area and improving the accuracy and reliability of the topological reference points corresponding to the boundary of the first area.

[0063] S4: Obtain a topological reference point set of the target area according to all topological reference points, and generate a road network topology map corresponding to the target area based on the topological reference point set.

[0064] Specifically, after performing clustering operations on each boundary extension area to obtain at least one target cluster, only each target cluster located in the first area is selected as a topological reference point, which is equivalent to obtaining a sub-topological reference point set corresponding to the first area. For each sub-target area, the above process can be performed independently at the same time to obtain a sub-topological reference point set corresponding to each first area. On this basis, each sub-topological reference point set can be mapped to the target area according to the position of each first area in the target area, and the topological reference point set corresponding to the target area can be obtained.

[0065] In one embodiment, for the target map, after generating its topological reference point set, the corresponding road network topology map can be generated according to each topological reference point. For example, the connection relationship between the corresponding topological reference points in the area where each road section is located can be determined according to the distribution of each road section in the target area. Assuming that there is a first topological reference point at the end point of section A, and there is a second topological reference point at the end point of section B, and section A and section B intersect near the end point, the first topological reference point can be connected with the second topological point to obtain the topological relationship between the topological reference points, and then the road network topology map corresponding to the target area is generated.

[0066] When facing the task of generating a road network topology map of a larger target area, this embodiment can divide the target area into multiple sub-target areas, which is conducive to reducing the difficulty of data processing and improving data processing efficiency. At the same time, obtaining the trajectory data contained in each of the sub-target areas is conducive to providing a reliable reference basis for the subsequent generation of topological reference points corresponding to each sub-target area. In this embodiment, a first area corresponds to a sub-target area. First, a boundary extension operation is performed on each first area respectively, which is conducive to the parallel generation of the boundary extension area corresponding to each sub-target map. At the same time, the boundary extension operation in this embodiment includes combining the first area and at least part of the sub-target area adjacent to the first area, which is conducive to analyzing the correlation between the boundary of the first area and the sub-target area adjacent to it, and providing a reliable external information reference for the subsequent generation of the corresponding topological reference point at the boundary of each first area. Secondly, in this embodiment, a clustering operation is performed on each boundary extension area respectively, which is conducive to the parallel processing of the trajectory data in the boundary extension area corresponding to each first area, and further improves the generation efficiency of the topological reference point set corresponding to the overall target area. At the same time, the boundary extension area obtained by performing the boundary extension operation on the first area includes at least part of the sub-target area adjacent to the first area, and accordingly, the boundary extension area can include part of the trajectory data of the sub-target area adjacent to the first area. Thus, when performing clustering operations on each boundary extension area respectively, it can be ensured that the adjacent external trajectory data can be effectively referenced when generating the target cluster near the boundary of the first area, which is conducive to breaking the data limitations when processing the first area alone, and improving the accuracy and reliability of the corresponding topological reference points at the boundary of the first area. Since the topological reference points at the corresponding boundary of each first area refer to the adjacent external trajectory data when generating, each target cluster located in the first area is used as a topological reference point respectively, and after obtaining the topological reference point set of the target area according to all the topological reference points, there is no need to perform special processing on the topological reference points at the boundaries of different first areas (i.e. corresponding to different sub-target areas), and the self-consistency of the topological reference points at the boundary position can be ensured. In this way, the road network topology map corresponding to the target area is generated based on the topological reference point set, and the problems such as the conflict of topological reference points at the boundaries of multiple sub-target maps when merging can be avoided, which is conducive to improving the accuracy and reliability of the road network topology map corresponding to the target area.

[0067] Optionally, combining the first area and at least part of the sub-target area adjacent to the first area to obtain a boundary extension area corresponding to the first area includes:

[0068] The first area is combined with the second area to obtain a boundary extension area, wherein the second area includes each sub-target area corresponding to the eight neighborhoods of the first area.

[0069] Specifically, in this embodiment, multiple sub-target areas may be distributed in a grid in the target area. Assuming that the first area is a rectangle, the sub-target areas corresponding to the eight neighborhoods of the first area may include four sub-target areas that are collinear with the four boundaries corresponding to the first area, and four sub-target areas that share vertices with the four vertices of the first area. Figure 2 As shown, assuming that the sub-target area numbered 5 is the first area, then correspondingly, the sub-target areas numbered 1-4 and 6-9 are the sub-target areas corresponding to the eight neighborhoods of the first area, and the second area includes the sub-target areas numbered 1-4 and 6-9. Therefore, the sub-target areas numbered 1-9 can be combined to obtain the boundary extension area corresponding to the first area.

[0070] In this embodiment, since the second area includes the sub-target areas corresponding to the eight neighborhoods of the first area, it can be seen that the boundary extension area obtained by combining the first area with the second area can provide a more comprehensive reference basis for the trajectory data processing of each first area, which is conducive to further improving the reliability of the target cluster at the boundary corresponding to the first area, thereby improving the accuracy of the road network topology map.

[0071] Optionally, before performing the clustering operation on each boundary extension area respectively, the method further includes:

[0072] The target area is grid-divided in a preset coordinate system to obtain a trajectory grid set corresponding to each sub-target area; wherein each trajectory grid set includes at least one trajectory grid, each trajectory grid includes at least one trajectory segment, and each trajectory segment corresponds to a segment of trajectory data in a trajectory data.

[0073] Specifically, in this embodiment, each trajectory segment corresponds to a segment of trajectory data in a trajectory data, and each trajectory grid includes at least one trajectory segment. For example, after the target area is grid-divided, a segment of trajectory data including trajectory data A and trajectory data B in a certain grid can be recorded as trajectory segment A and trajectory segment B respectively, and the grid can be used as a trajectory grid. Each trajectory grid in the target area that contains at least one trajectory segment can constitute a trajectory grid set. Figure 4 As shown, each grid in the trajectory grid set includes a trajectory segment of at least one trajectory data.

[0074] Optionally, after obtaining the grid set corresponding to each sub-target area, the grids including the trajectory segments can be screened out and used as the trajectory grids. For example, the grids that do not contain the trajectory segments in the sub-target area can be eliminated, and the remaining trajectory grids can constitute the trajectory grid set.

[0075] In this embodiment, before clustering the trajectory data contained in the boundary extension area, it is necessary to divide the target area into grids in a preset coordinate system, which is conducive to avoiding problems such as overlapping or missing grids of different sub-target areas when using different independent coordinate systems to divide each sub-target area into grids. For example, suppose the target area is divided into two sub-target areas, which are respectively recorded as the first sub-target area and the second sub-target area. Figure 5 As shown, the existing trajectory grid division method is in the first coordinate system X 1 O 1 Y 1 The first sub-target area is meshed in the second coordinate system X 2 O 2 Y 2 If the second sub-target area is grid-divided in the grid system, the grid parts of the first sub-target area and the second sub-target area at the corresponding boundary may overlap. In this embodiment, the target area is grid-divided in a unified preset coordinate system, which is equivalent to completing the overall grid division of each sub-target area at the same time in a unified preset coordinate system. For example, Figure 6 As shown, it is assumed that the target area is divided into two sub-target areas, which are respectively recorded as the first sub-target area and the second sub-target area. 3 O 3 Y 3 The overall grid division of the target area is equivalent to completing the grid division of the first sub-target area and the second sub-target area at the same time in a unified coordinate system, which is conducive to avoiding the occurrence of grid overlap or omission at the boundary of different sub-target areas, and further ensuring the reliability, accuracy and self-consistency of the topological reference points at the boundary positions of the sub-target areas.

[0076] Optionally, each trajectory segment includes a plurality of trajectory points and a latitude and longitude position corresponding to each trajectory point; after obtaining a trajectory grid set corresponding to each sub-target area, the following is further included:

[0077] The longitude and latitude positions corresponding to each track point in the track grid set are converted into coordinate positions in the preset coordinate system.

[0078] Specifically, in this embodiment, the trajectory data may include multiple trajectory points and the longitude and latitude positions corresponding to each trajectory point. The longitude and latitude positions corresponding to the trajectory points may be the longitude and latitude positions that the vehicle passes at a certain moment when traveling in the sub-target area (such as can be obtained using a GPS device).

[0079] In this embodiment, since the earth is a sphere, the same longitude difference will correspond to different distances at different latitudes, which is not conducive to reflecting the actual position relationship and distance relationship between different trajectory points. This embodiment can use the conversion relationship between the spherical coordinate system and the Cartesian coordinate system to achieve the conversion of longitude and latitude positions to coordinate positions, and then convert the longitude and latitude positions corresponding to each trajectory point in the trajectory segment into coordinate positions in a preset coordinate system, which is conducive to further improving the accuracy of the road network topology map. Optionally, before the target area is gridded, the longitude and latitude positions corresponding to each trajectory point in the trajectory data can be converted into coordinate positions in a preset coordinate system.

[0080] Optionally, clustering the trajectory data contained in the boundary extension area includes:

[0081] Clustering the trajectory segments in each trajectory grid in the boundary extension area according to a preset strategy to obtain at least one trajectory group in each trajectory grid;

[0082] The trajectory groups in the first grid and the second grid are clustered according to a preset strategy, wherein one first grid corresponds to one trajectory grid in the boundary extension area, and the second grid is each trajectory grid corresponding to the eight neighborhoods of the first grid.

[0083] Specifically, a trajectory grid usually contains at least one trajectory segment, and for the road network topology map construction task, when obtaining trajectory data that can fully cover the road network of the sub-target area, the vehicle often passes through a certain section of the same road (such as a trunk road) multiple times. Correspondingly, there will be multiple trajectory segments corresponding to multiple trajectory data in some trajectory grids. In this case, according to the preset strategy, the trajectory segments in each trajectory grid in the boundary extension area can be clustered respectively to obtain at least one trajectory group in each trajectory grid. For example, the direction and distance of each trajectory segment in the trajectory grid can be obtained, and one of the trajectory segments in the trajectory grid is selected as the target trajectory segment, and the remaining trajectory segments are the trajectory segments to be matched, which can constitute a set of trajectory segments to be matched. On this basis, the trajectory segments can be clustered once, including selecting the trajectory segments to be matched in the set of trajectory segments to be matched whose direction deviation with the target trajectory segment is lower than the preset deviation threshold, and / or whose distance deviation is lower than the preset distance threshold, and clustering them with the target trajectory segment to obtain a trajectory group. After removing the trajectory segments in the trajectory group, a to-be-matched trajectory segment can be selected from the remaining to-be-matched trajectory segment set as the target trajectory segment, and the step of clustering the trajectory segments is returned until the entire to-be-matched trajectory segment set is traversed.

[0084] In one embodiment, clustering the trajectory segments in the trajectory grid to obtain at least one trajectory group in each trajectory grid is helpful to reduce the complexity of data and improve the efficiency of trajectory data processing and analysis. On this basis, each trajectory grid in the boundary extension area can be used as a first grid, and accordingly, each trajectory grid corresponding to the eight neighborhoods of the first grid can be used as a second grid, and the trajectory groups in the first grid and the second grid are clustered according to a preset strategy. For example, Figure 7 As shown, assuming that the sub-target area numbered 5 is the first area, the sub-target areas numbered 1-4 and 6-9 are the second area, and the boundary extension area corresponding to the first area includes nine sub-target areas numbered 1-9. Assume that each sub-target area is divided into nine grids, and each grid contains multiple trajectory segments of multiple trajectory data, that is, each sub-target area corresponds to nine trajectory grids. First, the trajectory segments in the 81 trajectory grids in the boundary extension area are clustered respectively to obtain at least one trajectory group in each trajectory grid. On this basis, for each trajectory grid in the boundary extension area, it can be used as the first grid. Take the trajectory grid numbered M in the figure as an example, and use it as the first grid. Each trajectory grid corresponding to the eight neighborhoods of the first grid can be used as the second grid, that is, a total of eight trajectory grids from N1 to N8 are the second grids. On this basis, the trajectory groups in the first grid and the second grid can be clustered according to a preset strategy. For example, for any trajectory group in the trajectory grid numbered M, the target field of view corresponding to the trajectory group can be obtained (for example, the field of view corresponding to the captured image pre-associated with any trajectory segment in the trajectory group can be used as the target field of view), and the field of view to be matched corresponding to each trajectory group in each second grid can be obtained respectively. On this basis, the trajectory group whose similarity between the field of view to be matched and the target field of view in the second grid exceeds a preset overlap threshold (such as 80%) can be selected and clustered with the target trajectory group into a target cluster.

[0085] In this embodiment, the trajectory segments in the trajectory grid are clustered to obtain at least one trajectory group in each trajectory grid, which can realize the classification simplification of the information carried by the trajectory segments in the trajectory grid, which is conducive to reducing the pressure of data processing. On this basis, the trajectory groups in the first grid and the second grid are clustered according to the preset strategy, which is conducive to exploring the relationship between the information carried by adjacent trajectory grids while further classifying and simplifying the data. In particular, for the trajectory grid at the boundary of the sub-target area, the various trajectory grids corresponding to its eight neighborhoods are clustered, which is conducive to improving the reliability of the generation of topological points at the boundary position, deeply exploring the correlation between the trajectory groups in the trajectory grids inside and outside the boundary of the first area, and improving the self-consistency between the topological reference points at the boundary positions of different sub-target areas.

[0086] Optionally, the trajectory segment includes multiple types of trajectory information; the preset strategies include:

[0087] Clustering the trajectory segments whose similarity with respect to the first type of trajectory information in the trajectory grid exceeds a first preset threshold into a trajectory group;

[0088] Clustering disconnected trajectory groups whose similarity of the second type of trajectory information in the first grid and the second grid exceeds a second preset threshold into a target cluster, wherein the trajectory information of the trajectory group includes the trajectory information of the corresponding trajectory segment.

[0089] Specifically, in this embodiment, the trajectory data may include multiple types of trajectory information, and a segment of trajectory data, i.e., a trajectory segment, may also carry corresponding trajectory information. For example, the trajectory data may include the orientation information of the trajectory point (which may be determined based on the shooting direction of the shooting device provided on the vehicle), the field of view information (which may be determined based on the image corresponding to the shooting of the shooting device provided on the vehicle), and the shooting time information (which may be determined based on the timestamp corresponding to the longitude and latitude position recorded by the GPS positioning device provided in the vehicle). Accordingly, the trajectory segment may include the orientation information of the trajectory point, the field of view information, and the shooting time information. It should be understood that the first type of trajectory information and the second type of trajectory information referred to in this embodiment may be the same or different. For example, in this embodiment, the first type of trajectory information and the second type of trajectory information may both be field of view information. Accordingly, the first preset threshold and the second preset threshold referred to in this embodiment may be the same or different, and both may be set in advance. Preferably, in this embodiment, the second preset threshold is higher than the first preset threshold, which is conducive to improving the reliability of the target cluster.

[0090] In one embodiment, the trajectory segments whose similarity with respect to the first type of trajectory information in the trajectory grid exceeds a first preset threshold are clustered into a trajectory group, and the trajectory information of the trajectory group can correspond to the trajectory information of the trajectory segment accordingly. For example, assuming that trajectory segment A, trajectory segment B, and trajectory segment C all correspond to the field of view information (such as captured images), and the similarity between trajectory segments B and C and the field of view corresponding to trajectory segment A exceeds a first preset threshold (such as the similarity of the image exceeds 80%), then trajectory segments A, B, and C can be clustered into a trajectory group A. Correspondingly, the trajectory group can correspond to the field of view information corresponding to trajectory segments A, B, and C, and trajectory group B can be obtained in the same way. Then, assuming that trajectory group A is the first grid and trajectory group B is the second grid, when clustering the first grid and the second grid, clustering can be performed based on the trajectory information corresponding to any trajectory segment in each trajectory group, or clustering can be performed based on the average value of the trajectory information corresponding to each trajectory segment in the trajectory group. For example, assuming that the similarity between the field of view information corresponding to track segment A in track group A and the field of view information corresponding to track segment D in track group B exceeds 80%, and any track segment in track group A is not connected to any track segment in track group B, then track group A and track group B can be clustered into one target cluster.

[0091] In this embodiment, clustering the trajectory segments in the trajectory grid into trajectory groups is conducive to the preliminary condensation of the information carried by the trajectory segments with similar characteristics in the same trajectory grid. On this basis, the trajectory groups whose similarity with respect to the second type of trajectory information in the first grid and the second grid exceeds the second preset threshold and are not connected are clustered into a target cluster. On the basis of further condensing and simplifying the information carried by the trajectory groups with similar characteristics in adjacent trajectory grids, it is also conducive to avoiding the problem that the topological reference points generated subsequently are difficult to reflect the actual distribution of the road network after clustering the trajectory groups with high similarity and connection, and further improving the accuracy and reliability of the topological reference points.

[0092] Optionally, generating a road network topology map corresponding to the target area based on the topology reference point set includes:

[0093] The topological relationship between each topological reference point in the topological reference point set is determined according to the trajectory data, and a road network topology map is generated based on the topological reference points and the topological relationship.

[0094] Specifically, in this embodiment, after obtaining the topological reference point corresponding to each first area (that is, after obtaining all the topological reference points), each topological reference point can be mapped and integrated into the target area according to the position of each first area to obtain the overall topological reference point set corresponding to the target area. On this basis, the topological relationship between the topological reference points in the topological reference point set can be determined based on the trajectory data. For example, the trajectory data may include a driving path, and whether there is a connectivity relationship between different topological reference points can be determined based on whether the driving paths corresponding to different topological reference points are continuous. If so, it can be determined that the topological relationship between the two is a connectivity relationship, and then the connectivity relationship between different topological points is converted into an edge connecting two topological reference points in the road network topology map to obtain the road network topology map.

[0095] In this embodiment, the topological relationship between the topological reference points corresponding to each sub-target area can be obtained according to the trajectory data corresponding to each sub-target area. Preferably, since the trajectory data in this embodiment has undergone multi-level clustering simplification, the trajectory data corresponding to each sub-target area can be obtained at the same time to determine the topological relationship between the topological reference points in the overall target area, and further ensure the reliability of the topological relationship between different topological reference points near the boundary positions corresponding to different sub-target areas, without using a complex boundary fusion algorithm, the accuracy of the overall road network topology map of the target area can be improved.

[0096] For example, Figure 8 As shown, a method for generating a road network topology map is further introduced with a specific embodiment, and the method includes:

[0097] (1) Divide the target area into multiple sub-target areas, and obtain the trajectory data contained in each sub-target area;

[0098] (2) dividing the target area into grids in a preset coordinate system to obtain a trajectory grid set corresponding to each sub-target area; wherein each trajectory grid includes at least one trajectory segment;

[0099] (3) converting the longitude and latitude positions corresponding to each track point in the track grid into coordinate positions in a preset coordinate system;

[0100] (4) performing a boundary extension operation on each first region respectively, wherein one first region corresponds to one sub-target region, and the boundary extension operation includes combining the first region and at least a portion of the sub-target region adjacent to the first region to obtain a boundary extension region corresponding to the first region;

[0101] (5) clustering the trajectory segments in each trajectory grid in the boundary extension area according to a preset strategy to obtain at least one trajectory group in each trajectory grid;

[0102] (6) clustering the trajectory groups in the first grid and the second grid according to a preset strategy to obtain at least one target cluster; wherein one first grid corresponds to one trajectory grid in the boundary extension area, and the second grid is each trajectory grid corresponding to the eight neighborhoods of the first grid;

[0103] (7) taking each target cluster located in the first area as a topological reference point;

[0104] (8) obtaining a topological reference point set of the target area according to all topological reference points;

[0105] (9) Determine the topological relationship between the topological reference points in the topological reference point set according to the trajectory data, and generate a road network topology map based on the topological reference points and the topological relationship.

[0106] like Fig. 9 As shown, an embodiment of the present invention provides a device 90 for generating a road network topology map, comprising:

[0107] A division module 91, which is used to divide the target area into multiple sub-target areas and obtain the trajectory data contained in each of the sub-target areas;

[0108] An expansion module 92, configured to perform a boundary expansion operation on each first region, wherein one first region corresponds to one sub-target region, and the boundary expansion operation includes combining the first region and at least a part of the sub-target region adjacent to the first region to obtain a boundary expansion region corresponding to the first region;

[0109] A clustering module 93, which is used to perform a clustering operation on each of the boundary extension areas, wherein the clustering operation includes clustering the trajectory data contained in the boundary extension area to obtain at least one target cluster, and taking each of the target clusters located in the first area as a topological reference point;

[0110] The generating module 94 is used to obtain a topological reference point set of the target area according to all the topological reference points, and generate a road network topology map corresponding to the target area based on the topological reference point set.

[0111] The technical effects that can be produced by the device for generating a road network topology map and the method for generating a road network topology map provided in this embodiment are basically the same, and will not be described in detail here.

[0112] like Fig.10 As shown, an electronic device 100 provided by an embodiment of the present invention includes a memory 110 and a processor 120; the memory 110 is used to store a computer program; the processor 120 is used to implement the method for generating a road network topology map as described above when executing the computer program.

[0113] In other words, an electronic device 100 includes a memory 110 and a processor 120 coupled to the memory 110; the memory 110 is configured to store a computer program; and the processor 120 is configured to perform the following operations when executing the computer program:

[0114] Divide the target area into a plurality of sub-target areas, and obtain the trajectory data contained in each of the sub-target areas;

[0115] Performing a boundary extension operation on each first region respectively, wherein one first region corresponds to one sub-target region, and the boundary extension operation includes combining the first region and at least a portion of the sub-target region adjacent to the first region to obtain a boundary extension region corresponding to the first region;

[0116] Performing a clustering operation on each of the boundary extension areas respectively, wherein the clustering operation includes clustering the trajectory data contained in the boundary extension area to obtain at least one target cluster, and taking each of the target clusters located in the first area as a topological reference point;

[0117] A topological reference point set of the target area is obtained according to all the topological reference points, and a road network topology map corresponding to the target area is generated based on the topological reference point set.

[0118] The electronic device 100 includes a computing unit, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) or a computer program loaded from a storage unit into a random access memory (RAM). In the RAM, various programs and data required for the operation of the device can also be stored. The computing unit, ROM, and RAM are connected to each other via a bus. An input / output (I / O) interface is also connected to the bus.

[0119] The electronic device 100 and the method for generating a road network topology map provided in this embodiment can produce substantially the same technical effects, which will not be described in detail herein.

[0120] An embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the method for generating a road network topology map as described above is implemented.

[0121] In other words, a non-volatile computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor performs the following operations:

[0122] Divide the target area into a plurality of sub-target areas, and obtain the trajectory data contained in each of the sub-target areas;

[0123] Performing a boundary extension operation on each first region respectively, wherein one first region corresponds to one sub-target region, and the boundary extension operation includes combining the first region and at least a portion of the sub-target region adjacent to the first region to obtain a boundary extension region corresponding to the first region;

[0124] Performing a clustering operation on each of the boundary extension areas respectively, wherein the clustering operation includes clustering the trajectory data contained in the boundary extension area to obtain at least one target cluster, and taking each of the target clusters located in the first area as a topological reference point;

[0125] A topological reference point set of the target area is obtained according to all the topological reference points, and a road network topology map corresponding to the target area is generated based on the topological reference point set.

[0126] The computer-readable storage medium provided in this embodiment has substantially the same technical effect as that produced by the method for generating a road network topology map, and will not be described in detail herein.

[0127] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the storage medium can be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc. In the present application, the unit described as a separate component may or may not be physically separated, and the component displayed as a unit may or may not be a physical unit, that is, it may be located in one place, or it may be distributed on multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the embodiment of the present invention. In addition, each functional unit in each embodiment of the present invention can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of a software functional unit.

[0128] Although the present invention is disclosed as above, the protection scope of the present invention is not limited thereto. Those skilled in the art may make various changes and modifications without departing from the spirit and scope of the present invention, and these changes and modifications will fall within the protection scope of the present invention.

Claims

1. A method for generating a road network topology map, It is characterized in that include: Divide the target area into multiple sub-target areas, and obtain the trajectory data contained in each of the sub-target areas; Performing a boundary extension operation on each first region respectively, wherein one first region corresponds to one sub-target region, and the boundary extension operation includes combining the first region and at least a portion of the sub-target region adjacent to the first region to obtain a boundary extension region corresponding to the first region; Performing a clustering operation on each of the boundary extension areas respectively, wherein the clustering operation includes clustering the trajectory data contained in the boundary extension area to obtain at least one target cluster, and taking each of the target clusters located in the first area as a topological reference point; A topological reference point set of the target area is obtained according to all the topological reference points, and a road network topology map corresponding to the target area is generated based on the topological reference point set.

2. The method for generating a road network topology map according to claim 1, It is characterized in that The combining the first area and at least a part of the sub-target area adjacent to the first area to obtain a boundary extension area corresponding to the first area includes: The first area is combined with the second area to obtain the boundary extension area, wherein the second area includes each sub-target area corresponding to the eight neighborhoods of the first area.

3. The method for generating a road network topology map according to claim 1, It is characterized in that Before performing the clustering operation on each of the boundary extension areas respectively, the method further includes: The target area is grid-divided in a preset coordinate system to obtain a trajectory grid set corresponding to each sub-target area; wherein each trajectory grid set includes at least one trajectory grid, each trajectory grid includes at least one trajectory segment, and each trajectory segment corresponds to a segment of trajectory data in one of the trajectory data.

4. The method for generating a road network topology map according to claim 3, It is characterized in that Each of the track segments includes a plurality of track points and a longitude and latitude position corresponding to each of the track points; After obtaining the trajectory grid set corresponding to each sub-target area, the method further includes: The longitude and latitude positions corresponding to each of the track points in the track grid set are converted into coordinate positions in the preset coordinate system.

5. The method for generating a road network topology map according to claim 3, It is characterized in that The clustering of the trajectory data contained in the boundary extension area includes: Clustering the trajectory segments in each trajectory grid in the boundary extension area according to a preset strategy to obtain at least one trajectory group in each trajectory grid; The trajectory groups in the first grid and the second grid are clustered according to the preset strategy, wherein one of the first grids corresponds to one of the trajectory grids in the boundary extension area, and the second grids are the trajectory grids corresponding to the eight neighborhoods of the first grid.

6. The method for generating a road network topology map according to claim 5, It is characterized in that The trajectory segments include multiple types of trajectory information; the preset strategies include: Clustering the trajectory segments whose similarity with respect to the first type of trajectory information in the trajectory grid exceeds a first preset threshold into one of the trajectory groups; Clustering disconnected trajectory groups whose similarity about the second type of trajectory information in the first grid and the second grid exceeds a second preset threshold into one target cluster, wherein the trajectory information of the trajectory group includes the trajectory information of the corresponding trajectory segment.

7. The method for generating a road network topology map according to claim 1, It is characterized in that The generating a road network topology map corresponding to the target area based on the topology reference point set includes: The topological relationship between each of the topological reference points in the topological reference point set is determined according to the trajectory data, and the road network topology map is generated based on the topological reference points and the topological relationship.

8. A device for generating a road network topology map, It is characterized in that include: A division module, which is used to divide the target area into multiple sub-target areas and obtain the trajectory data contained in each of the sub-target areas; an expansion module, configured to perform a boundary expansion operation on each first region respectively, wherein one first region corresponds to one sub-target region, and the boundary expansion operation includes combining the first region and at least a part of the sub-target region adjacent to the first region to obtain a boundary expansion region corresponding to the first region; A clustering module, which is used to perform a clustering operation on each of the boundary extension areas, wherein the clustering operation includes clustering the trajectory data contained in the boundary extension area to obtain at least one target cluster, and taking each of the target clusters located in the first area as a topological reference point; A generating module is used to obtain a topological reference point set of the target area according to all the topological reference points, and to generate a road network topology map corresponding to the target area based on the topological reference point set.

9. An electronic device, It is characterized in that including memory and processor; The memory is used to store computer programs; The processor is used to implement the method for generating a road network topology map as described in any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, It is characterized in that The storage medium stores a computer program, and when the computer program is read and executed by a processor, the method for generating a road network topology map according to any one of claims 1 to 7 is implemented.

Citation Information

Patent Citations

  • Road network map generation method and device, electronic equipment and computer readable storage medium

    CN111898648A

  • Road network skeleton generation method and device, electronic equipment and storage medium

    CN116150296A

  • Creating a logical route network in parking areas

    WO2024022740A1