Intersection area road network topology method and device, computer equipment and storage medium

Abstract

The invention relates to an intersection area road network topology method and device, computer equipment and a storage medium. According to the method, the vehicle track points are clustered to form the clustering vertexes, the clustering vertexes are connected to form the initial road-level road network topology, then whether the head and tail points of the path topology are communicated or not is recognized, and the communicated sub-graph area defined by the communicated head and tail points is screened out to serve as the intersection area. And all intersection vertexes in the sub-graph regions are communicated and combined into a cluster intersection vertex, so that the cluster intersection vertex can be accurately obtained only based on global vehicle trajectory data, the initial road-level road network topology is updated to form the road network topology of the intersection region, and the intersection region detection problem depending on the image is solved. A mathematical model is simple and efficient, later maintenance and iteration are facilitated, the output efficiency is high, full automation is achieved, manual intervention through a base map is not needed, the intersection area recognition efficiency is improved, and dependence on base map data is reduced.

Description

Technical Field

[0001] The present application relates to the technical field of road network topology, and in particular to a method, device, computer equipment and storage medium for road network topology in an intersection area. Background Art

[0002] The realization of the autonomous driving function of smart cars is mostly based on high-precision maps. The current industry hotspot is to use crowd-source data to build lane-level high-precision maps with fast updates and iterations. In order to build lane-level high-precision maps for fully autonomous driving, it is necessary to establish a road-level road network topology that provides information on the drivable area for autonomous driving, which provides crucial information for vehicle path planning. However, how to build a road network topology in intersections without lane lines and complex trajectories has become a key problem that needs to be solved urgently.

[0003] The current mainstream road-level network topology construction method is as follows: 1) The vehicle uploads the constructed local vector map fragments to the server cloud; 2) The server cloud performs mathematical modeling to align many local vector map fragments to obtain a global vector map; 3) Extract vehicle trajectory data from the global vector map, manually or relying on map supplier data, mark the intersection area and perform special processing, and then generate a global road-level network topology.

[0004] However, the current mainstream road-level network topology construction method has the following defects: it relies on manual data selection, which seriously reduces the production efficiency of road-level network topology; it relies on suppliers to provide base map data to report special areas, resulting in key omissions in the data application closed-loop process; manual data screening requires comparison with satellite base map data or reliance on street view data to determine intersection scenes. Summary of the invention

[0005] Based on this, it is necessary to provide a road network topology method, device, computer equipment and storage medium for intersection areas that can construct road network topology in intersection areas without lane lines and complex trajectories, in response to the technical problems of low efficiency of manual data screening and reliance on base map data in the current mainstream road-level road network topology construction method. The method converts the intersection area detection problem that relies on images into the problem of solving connected components in an undirected graph model, greatly improving the output efficiency of results while saving labor costs.

[0006] On the one hand, a method for determining a road network topology of an intersection area is provided, the method comprising:

[0007] Clustering trajectory points according to global vehicle trajectory data to form cluster vertices, and connecting the cluster vertices to form an initial road-level road network topology;

[0008] Classifying the cluster vertices into path vertices and intersection vertices;

[0009] Taking the sub-topology composed of the continuously connected path vertices as the path topology, obtaining the first and last points in the path topology, and establishing the vertices in the graph model with the first and last points;

[0010] Determine whether any two of the starting and ending points can be connected through the intersection vertex, and if so, establish a connectivity relationship between the corresponding two starting and ending points;

[0011] Clustering the vertices having a connectivity relationship in the graph model to form at least one connected subgraph region;

[0012] All intersection vertices in the connected subgraph area are merged into a cluster intersection vertex, the head and tail points are connected to the cluster intersection vertex, and the initial road-level network topology is updated to form an intersection area network topology.

[0013] In one embodiment, clustering trajectory points according to global vehicle trajectory data to form cluster vertices, and connecting the cluster vertices to form an initial road-level road network topology includes:

[0014] Extracting global vehicle trajectory data stored in the cloud, and mapping the trajectory points in the local vehicle trajectory data to each grid of the global map;

[0015] Taking the grid as the smallest unit, clustering the trajectory points in the grid to form cluster vertices;

[0016] According to the continuity of the global vehicle trajectory data, a connection relationship between the cluster vertices is established to form an initial road-level road network topology.

[0017] In one embodiment, establishing a connection relationship between the cluster vertices according to the continuity of the global vehicle trajectory data to form an initial road-level road network topology includes:

[0018] Acquire an extension direction of a global vehicle trajectory and a vehicle driving direction according to the global vehicle trajectory data;

[0019] Determining the adjacent connection relationship of the cluster vertices according to the extension direction of the global vehicle trajectory, and sequentially connecting the cluster vertices along the extension direction of the global vehicle trajectory to form a continuous vehicle trajectory;

[0020] The direction of the vehicle trajectory is determined according to the vehicle driving direction to form an initial road-level road network topology.

[0021] In one embodiment, determining the direction of the vehicle trajectory according to the vehicle driving direction to form an initial road-level road network topology includes:

[0022] Setting the cluster vertices as solid dots in the global map;

[0023] Setting a track connection line between two adjacent cluster vertices in each vehicle track, and determining the direction of the arrow of the track connection line according to the driving direction of the vehicle, wherein the direction of the arrow is the driving direction of the vehicle;

[0024] All vehicle trajectories are merged in the global map to form an initial road-level network topology.

[0025] In one embodiment, the classifying the cluster vertices into path vertices and intersection vertices comprises:

[0026] Obtaining the number of cluster vertices connected to each of the cluster vertices in the initial road-level road network topology;

[0027] If the number of connected cluster vertices is less than or equal to two, the corresponding cluster vertex is determined to be a path vertex;

[0028] If the number of connected cluster vertices is greater than two, the corresponding cluster vertex is determined to be an intersection vertex.

[0029] In one embodiment, the determining whether any two of the first and last points can be connected through the intersection vertex, and if connected, establishing a connectivity relationship between the corresponding two first and last points includes:

[0030] Arrange the first and last points in sequence according to their numbers, obtain the number m of the first and last points, and establish an m×m binary matrix;

[0031] In the binary matrix, there is a corresponding square between any two of the head and tail points, and the square is preset with a first value, and the first value indicates that the corresponding two head and tail points are not connected;

[0032] Determine whether any two of the head and tail points can be connected through the intersection vertex, and if so, modify the first value of the corresponding square in the binary matrix to a second value, where the second value indicates that the corresponding two head and tail points are connected;

[0033] According to the binarized matrix, a connecting edge is established between the two connected head and tail points in the graph model.

[0034] In one embodiment, clustering vertices having connectivity in the graph model to form at least one connected subgraph region comprises:

[0035] Acquire a plurality of path vertices connected by the connected edges in the graph model;

[0036] The multiple path vertices connected by the connecting edges are clustered, and an area surrounding all the multiple path vertices connected by the connecting edges is set as a connected subgraph area in the graph model.

[0037] In another aspect, a road network topology device for an intersection area is provided, the device comprising:

[0038] An initial road network topology module, used for clustering trajectory points according to global vehicle trajectory data to form cluster vertices, and connecting the cluster vertices to form an initial road-level road network topology;

[0039] A cluster vertex classification module, used for classifying the cluster vertices into path vertices and intersection vertices;

[0040] Setting a graph model vertex module, used to take the sub-topology composed of the continuously connected path vertices as the path topology, obtain the first and last points in the path topology, and establish the vertices in the graph model with the first and last points;

[0041] A vertex connectivity relationship management module is used to determine whether any two of the head and tail points can be connected through the intersection vertex, and if so, establish a connectivity relationship between the corresponding two head and tail points;

[0042] A connected subgraph region forming module is used to cluster the vertices having a connected relationship in the graph model to form at least one connected subgraph region;

[0043] The intersection area road network topology forming module is used to merge all the intersection vertices located in the connected subgraph area into a cluster intersection vertex, connect the head and tail points with the cluster intersection vertex, and update the initial road-level road network topology to form the intersection area road network topology.

[0044] In another aspect, a computer device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the following steps are implemented:

[0045] Clustering trajectory points according to global vehicle trajectory data to form cluster vertices, and connecting the cluster vertices to form an initial road-level road network topology;

[0046] Classifying the cluster vertices into path vertices and intersection vertices;

[0047] Taking the sub-topology composed of the continuously connected path vertices as the path topology, obtaining the first and last points in the path topology, and establishing the vertices in the graph model with the first and last points;

[0048] Determine whether any two of the starting and ending points can be connected through the intersection vertex, and if so, establish a connectivity relationship between the corresponding two starting and ending points;

[0049] Clustering the vertices having a connectivity relationship in the graph model to form at least one connected subgraph region;

[0050] All intersection vertices in the connected subgraph area are merged into a cluster intersection vertex, the head and tail points are connected to the cluster intersection vertex, and the initial road-level network topology is updated to form an intersection area network topology.

[0051] In another aspect, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0052] Clustering trajectory points according to global vehicle trajectory data to form cluster vertices, and connecting the cluster vertices to form an initial road-level road network topology;

[0053] Classifying the cluster vertices into path vertices and intersection vertices;

[0054] Taking the sub-topology composed of the continuously connected path vertices as the path topology, obtaining the first and last points in the path topology, and establishing the vertices in the graph model with the first and last points;

[0055] Determine whether any two of the starting and ending points can be connected through the intersection vertex, and if so, establish a connectivity relationship between the corresponding two starting and ending points;

[0056] Clustering the vertices having a connectivity relationship in the graph model to form at least one connected subgraph region;

[0057] All intersection vertices in the connected subgraph area are merged into a cluster intersection vertex, the head and tail points are connected to the cluster intersection vertex, and the initial road-level network topology is updated to form an intersection area network topology.

[0058] The above-mentioned intersection area road network topology method, device, computer equipment and storage medium first cluster vehicle trajectory points to form cluster vertices, connect the cluster vertices to form an initial road-level road network topology, then identify whether the head and tail points of the path topology are connected, screen out the connected subgraph area surrounded by the head and tail points as the intersection area, and merge all intersection vertices in the connected subgraph area into a cluster intersection vertex, so that cluster intersection vertices can be accurately obtained based only on global vehicle trajectory data, thereby updating the initial road-level road network topology to form the intersection area road network topology, and converting the image-dependent intersection area detection problem into the problem of solving connected components in an undirected graph model. The mathematical model is simple and efficient, which is conducive to later maintenance and iteration, has high output efficiency, is fully automated, does not require manual intervention through the base map, improves the intersection area recognition efficiency, and reduces the dependence on base map data. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0060] Figure 1 A schematic diagram of a flow chart of a road network topology method for an intersection area in one embodiment of the present application;

[0061] Figure 2 This is a schematic diagram of the structure of the initial road-level road network topology in one embodiment of the present application;

[0062] Figure 3 This is a schematic diagram of the structure of a binarization matrix in one embodiment of the present application;

[0063] Figure 4 This is a structural diagram of a graph model in one embodiment of the present application;

[0064] Figure 5 This is a schematic diagram of the structure of the road network topology in the intersection area in one embodiment of the present application;

[0065] Figure 6 This is a structural block diagram of a road network topology device in an intersection area in an embodiment of the present application;

[0066] Figure 7 This is a diagram of the internal structure of a computer device in one embodiment of the present application. DETAILED DESCRIPTION

[0067] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0068] In one embodiment, Figure 1 As shown, a road network topology method for an intersection area is provided, comprising the following steps:

[0069] Step S1, clustering trajectory points according to global vehicle trajectory data to form cluster vertices, and connecting the cluster vertices to form an initial road-level road network topology;

[0070] Step S2, classifying the cluster vertices into path vertices and intersection vertices;

[0071] Step S3, taking the sub-topology composed of the continuously connected path vertices as the path topology, obtaining the first and last points in the path topology, and establishing the vertices in the graph model with the first and last points;

[0072] Step S4, determining whether any two of the first and last points can be connected through the intersection vertex, and if so, establishing a connection relationship between the corresponding two first and last points;

[0073] Step S5, clustering the vertices having connectivity in the graph model to form at least one connected subgraph region;

[0074] Step S6, merging all intersection vertices in the connected subgraph area into a cluster intersection vertex, connecting the head and tail points to the cluster intersection vertex, and updating the initial road-level network topology to form an intersection area network topology.

[0075] Among them, the content of step S2-step S5 is to establish a graph model, and the content of step S6 is to solve the graph model, and the initial road-level road network topology is updated according to the graph model solution result. The global vehicle trajectory data contains all possible vehicle trajectory data, and the vehicle trajectory corresponding to each vehicle trajectory data does not overlap with the vehicle trajectory corresponding to the other vehicle trajectory data, that is, each vehicle trajectory data is data with the same vehicle trajectory.

[0076] Specifically, the result of solving the graph model is to obtain a clustered intersection vertex that merges all intersection vertices located in the connected subgraph area. By connecting the head and tail points with the clustered intersection vertex, the road network topology simplification processing of the intersection area can be achieved, and all intersection vertices at the edge of the intersection are integrated into a clustered intersection vertex for processing, which can simplify the road network topology.

[0077] This embodiment first clusters the vehicle trajectory points to form cluster vertices, connects the cluster vertices to form an initial road-level network topology, then identifies whether the beginning and end points of the path topology are connected, and selects a connected subgraph area surrounded by the connected beginning and end points as the intersection area. All intersection vertices in the connected subgraph area are merged into a cluster intersection vertex, so that cluster intersection vertices can be accurately obtained based only on global vehicle trajectory data, thereby updating the initial road-level network topology to form an intersection area network topology. By converting the image-dependent intersection area detection problem into a problem of solving connected components in an undirected graph model, the mathematical model is simple and efficient, which is conducive to later maintenance and iteration, has high output efficiency, is fully automated, and does not require manual intervention through the base map, thereby improving the intersection area recognition efficiency and reducing the dependence on base map data.

[0078] Specifically, merging all intersection vertices in the connected subgraph area into a clustered intersection vertex includes:

[0079] The coordinates of all intersection vertices in the connected subgraph area are obtained, and the center point of the connected subgraph area is used as the coordinates of the clustered intersection vertices.

[0080] In this embodiment, clustering trajectory points according to global vehicle trajectory data to form cluster vertices, and connecting the cluster vertices to form an initial road-level road network topology includes:

[0081] Extracting global vehicle trajectory data stored in the cloud, and mapping the trajectory points in the local vehicle trajectory data to each grid of the global map;

[0082] Taking the grid as the smallest unit, clustering the trajectory points in the grid to form cluster vertices;

[0083] According to the continuity of the global vehicle trajectory data, a connection relationship between the cluster vertices is established to form an initial road-level road network topology.

[0084] Among them, the global vehicle trajectory data stored in the cloud is to set the vehicle trajectories corresponding to multiple vehicle trajectory data in the global map, so as to align the positions of the vehicle trajectories corresponding to multiple vehicle trajectory data in the global map. Each grid of the global map is a globally unique grid of fixed size, so that only one cluster vertex can be clustered in each grid.

[0085] In this embodiment, establishing a connection relationship between the cluster vertices according to the continuity of the global vehicle trajectory data to form an initial road-level road network topology includes:

[0086] Acquire an extension direction of a global vehicle trajectory and a vehicle driving direction according to the global vehicle trajectory data;

[0087] Determining the adjacent connection relationship of the cluster vertices according to the extension direction of the global vehicle trajectory, and sequentially connecting the cluster vertices along the extension direction of the global vehicle trajectory to form a continuous vehicle trajectory;

[0088] The direction of the vehicle trajectory is determined according to the vehicle driving direction to form an initial road-level road network topology.

[0089] like Figure 2 As shown, Figure 2 The schematic diagram of the structure of the initial road-level network topology. The cluster vertices are represented by solid dots, the direction of the vehicle trajectory is represented by a trajectory connecting line, and the arrow of the trajectory connecting line points to the same direction as the vehicle's travel direction, that is, the same direction as the vehicle's trajectory. The cluster vertices are numbered to facilitate the subsequent representation of the first and last points in the path topology in the graph model.

[0090] In this embodiment, determining the direction of the vehicle trajectory according to the vehicle driving direction to form an initial road-level road network topology includes:

[0091] Setting the cluster vertices as solid dots in the global map;

[0092] Setting a track connection line between two adjacent cluster vertices in each vehicle track, and determining the direction of the arrow of the track connection line according to the driving direction of the vehicle, wherein the direction of the arrow is the driving direction of the vehicle;

[0093] All vehicle trajectories are merged in the global map to form an initial road-level network topology.

[0094] like Figure 2 In the figure, the sub-topology composed of the cluster vertices 1, 2, 3 or the cluster vertices 8, 9, 10 is called a path topology.

[0095] In this embodiment, classifying the cluster vertices into path vertices and intersection vertices includes:

[0096] Obtaining the number of cluster vertices connected to each of the cluster vertices in the initial road-level road network topology;

[0097] If the number of connected cluster vertices is less than or equal to two, the corresponding cluster vertex is determined to be a path vertex;

[0098] If the number of connected cluster vertices is greater than two, the corresponding cluster vertex is determined to be an intersection vertex.

[0099] like Figure 2In the figure, black vertices are path vertices, and white vertices are intersection vertices. Specifically, the arrow directions of the trajectory connection lines connecting each cluster vertex can also be counted. When one cluster vertex points to another cluster vertex, it is the out-degree, and when one cluster vertex is pointed to by the arrow of the trajectory connection line of another cluster vertex, it is the in-degree. Therefore, the classification rule for dividing the cluster vertices in the initial road-level topology graph into path vertices and intersection vertices is: vertices with out-degree or in-degree greater than 1 are classified as intersection vertices, and vertices with neither out-degree nor in-degree greater than 1 are classified as path vertices.

[0100] In this embodiment, the determining whether any two of the first and last points can be connected through the intersection vertex, and if connected, establishing a connectivity relationship between the corresponding two first and last points includes:

[0101] Arrange the first and last points in sequence according to their numbers, obtain the number m of the first and last points, and establish an m×m binary matrix;

[0102] In the binary matrix, there is a corresponding square between any two of the head and tail points, and the square is preset with a first value, and the first value indicates that the corresponding two head and tail points are not connected;

[0103] Determine whether any two of the head and tail points can be connected through the intersection vertex, and if so, modify the first value of the corresponding square in the binary matrix to a second value, where the second value indicates that the corresponding two head and tail points are connected;

[0104] According to the binarized matrix, a connecting edge is established between the two connected head and tail points in the graph model.

[0105] like Figure 3 As shown, Figure 3 It is a structural diagram of a binary matrix, taking the cluster vertices numbered 1, 2, 3, 4, 5, 6, and 7 as an example, wherein the cluster vertices numbered 1, 3, 5, and 6 are the head and tail points, and the intersection vertices arranged horizontally and vertically in the m×m binary matrix are numbered 1, 3, 5, and 6, cluster vertex 3 is connected to cluster vertex 5 through intersection vertex 4, and cluster vertex 5 is connected to cluster vertex 6 through intersection vertices 4 and 7, so the squares corresponding to cluster vertex 3 and cluster vertex 5 are set to the second value, and the squares corresponding to cluster vertex 5 and cluster vertex 6 are set to the second value.

[0106] like Figure 4As shown, the first and last points of the path vertices are the cluster vertex numbers 1, 3, 5, 6, 8, 10, 11, 13, 15, 16, 18, and 20. A connecting edge is established between the connected path vertex 3 and the path vertex 5, and a connecting edge is established between the connected path vertex 5 and the path vertex 6, and so on. The set path vertices 1, 10, 11, and 20 can be independently set, and the path vertices 3, 5, 6, 8, 13, 15, 16, and 18 form a road network.

[0107] Specifically, the first value is set to 0, and the square is set to the first value, which can be represented by white. The second value is set to 1, and the square is set to the second value, which can be represented by black.

[0108] In this embodiment, clustering the vertices having connectivity in the graph model to form at least one connected subgraph region includes:

[0109] Acquire a plurality of path vertices connected by the connected edges in the graph model;

[0110] The multiple path vertices connected by the connecting edges are clustered, and an area surrounding all the multiple path vertices connected by the connecting edges is set as a connected subgraph area in the graph model.

[0111] like Figure 4 As shown, path vertices 3, 5, 6, 8, 13, 15, 16, and 18 form multiple path vertices of the road network for clustering. Figure 4 The dashed box in represents the connected subgraph area. Clustering the vertices with connectivity in the graph model is to solve the connected components in the graph model, such as Figure 4 The connected subgraph area consists of the vertices contained in the dashed box.

[0112] The intersection vertices falling within the connected subgraph area are merged, that is, multiple intersection vertices are merged into one intersection vertex as a clustered intersection vertex to complete the intersection area identification. The intersection area road network topology formed by the updated road-level road network topology is as follows: Figure 5 shown.

[0113] It is worth noting that the present application is not unable to directly merge the vertices classified as intersections into one intersection vertex as a clustered intersection vertex. This is because the roads at some intersections are not connected. Therefore, it is necessary to limit the intersection vertices that fall within the connected subgraph area based on the connected subgraph area for merging. This can avoid the merging of unconnected intersection vertices and cause road network errors.

[0114] In the above-mentioned intersection area road network topology method, the vehicle trajectory points are first clustered to form cluster vertices, the cluster vertices are connected to form an initial road-level road network topology, and then it is identified whether the head and tail points of the path topology are connected, and the connected subgraph area surrounded by the connected head and tail points is screened out as the intersection area, and all intersection vertices in the connected subgraph area are merged into a cluster intersection vertex, so that the cluster intersection vertices can be accurately obtained based only on the global vehicle trajectory data, thereby updating the initial road-level road network topology to form the intersection area road network topology, and converting the image-dependent intersection area detection problem into the problem of solving the connected component in the undirected graph model. The mathematical model is simple and efficient, which is conducive to later maintenance and iteration, has high output efficiency, is fully automated, does not require manual intervention through the base map, improves the intersection area recognition efficiency, and reduces the dependence on the base map data.

[0115] In one embodiment, Figure 6 As shown, a road network topology device 100 for an intersection area is provided, comprising: an initial road network topology module 101, a clustering vertex classification module 102, a graph model vertex setting module 103, a vertex connectivity relationship management module 104, a connected subgraph area forming module 105 and an intersection area road network topology forming module 106.

[0116] The initial road network topology module 101 is used to cluster trajectory points according to global vehicle trajectory data to form cluster vertices, and connect the cluster vertices to form an initial road-level road network topology.

[0117] The cluster vertex classification module 102 is used to classify the cluster vertices into path vertices and intersection vertices.

[0118] The module 103 for setting graph model vertices is used to use the sub-topology composed of the continuously connected path vertices as the path topology, obtain the first and last points in the path topology, and establish the vertices in the graph model with the first and last points.

[0119] The vertex connectivity relationship management module 104 is used to determine whether any two of the head and tail points can be connected through the intersection vertex, and if so, establish a connectivity relationship between the corresponding two head and tail points.

[0120] The connected subgraph region forming module 105 is used to cluster the vertices having a connected relationship in the graph model to form at least one connected subgraph region.

[0121] The intersection area road network topology forming module 106 is used to merge all intersection vertices located in the connected subgraph area into a cluster intersection vertex, connect the head and tail points with the cluster intersection vertex, and update the initial road-level road network topology to form an intersection area road network topology.

[0122] In this embodiment, clustering trajectory points according to global vehicle trajectory data to form cluster vertices, and connecting the cluster vertices to form an initial road-level road network topology includes:

[0123] Extracting global vehicle trajectory data stored in the cloud, and mapping the trajectory points in the local vehicle trajectory data to each grid of the global map;

[0124] Taking the grid as the smallest unit, clustering the trajectory points in the grid to form cluster vertices;

[0125] According to the continuity of the global vehicle trajectory data, a connection relationship between the cluster vertices is established to form an initial road-level road network topology.

[0126] In this embodiment, establishing a connection relationship between the cluster vertices according to the continuity of the global vehicle trajectory data to form an initial road-level road network topology includes:

[0127] Acquire an extension direction of a global vehicle trajectory and a vehicle driving direction according to the global vehicle trajectory data;

[0128] Determining the adjacent connection relationship of the cluster vertices according to the extension direction of the global vehicle trajectory, and sequentially connecting the cluster vertices along the extension direction of the global vehicle trajectory to form a continuous vehicle trajectory;

[0129] The direction of the vehicle trajectory is determined according to the vehicle driving direction to form an initial road-level road network topology.

[0130] In this embodiment, determining the direction of the vehicle trajectory according to the vehicle driving direction to form an initial road-level road network topology includes:

[0131] Setting the cluster vertices as solid dots in the global map;

[0132] Setting a track connection line between two adjacent cluster vertices in each vehicle track, and determining the direction of the arrow of the track connection line according to the driving direction of the vehicle, wherein the direction of the arrow is the driving direction of the vehicle;

[0133] All vehicle trajectories are merged in the global map to form an initial road-level network topology.

[0134] In this embodiment, classifying the cluster vertices into path vertices and intersection vertices includes:

[0135] Obtaining the number of cluster vertices connected to each of the cluster vertices in the initial road-level road network topology;

[0136] If the number of connected cluster vertices is less than or equal to two, the corresponding cluster vertex is determined to be a path vertex;

[0137] If the number of connected cluster vertices is greater than two, the corresponding cluster vertex is determined to be an intersection vertex.

[0138] In this embodiment, the determining whether any two of the first and last points can be connected through the intersection vertex, and if connected, establishing a connectivity relationship between the corresponding two first and last points includes:

[0139] Arrange the first and last points in sequence according to their numbers, obtain the number m of the first and last points, and establish an m×m binary matrix;

[0140] In the binary matrix, there is a corresponding square between any two of the head and tail points, and the square is preset with a first value, and the first value indicates that the corresponding two head and tail points are not connected;

[0141] Determine whether any two of the head and tail points can be connected through the intersection vertex, and if so, modify the first value of the corresponding square in the binary matrix to a second value, where the second value indicates that the corresponding two head and tail points are connected;

[0142] According to the binarized matrix, a connecting edge is established between the two connected head and tail points in the graph model.

[0143] In this embodiment, clustering the vertices having connectivity in the graph model to form at least one connected subgraph region includes:

[0144] Acquire a plurality of path vertices connected by the connected edges in the graph model;

[0145] The multiple path vertices connected by the connecting edges are clustered, and an area surrounding all the multiple path vertices connected by the connecting edges is set as a connected subgraph area in the graph model.

[0146] In the above-mentioned intersection area road network topology device, the vehicle trajectory points are first clustered to form cluster vertices, the cluster vertices are connected to form an initial road-level road network topology, and then it is identified whether the head and tail points of the path topology are connected, and the connected subgraph area surrounded by the connected head and tail points is screened out as the intersection area, and all intersection vertices in the connected subgraph area are merged into a cluster intersection vertex, so that the cluster intersection vertices can be accurately obtained based only on the global vehicle trajectory data, thereby updating the initial road-level road network topology to form the intersection area road network topology, and by converting the image-dependent intersection area detection problem into the problem of solving the connected component in the undirected graph model, the mathematical model is simple and efficient, which is conducive to later maintenance and iteration, has high output efficiency, is fully automated, does not require manual intervention through the base map, improves the intersection area recognition efficiency, and reduces the dependence on the base map data.

[0147] For the specific definition of the intersection area road network topology device, please refer to the definition of the intersection area road network topology method above, which will not be repeated here. Each module in the above-mentioned intersection area road network topology device can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0148] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:

[0149] Clustering trajectory points according to global vehicle trajectory data to form cluster vertices, and connecting the cluster vertices to form an initial road-level road network topology;

[0150] Classifying the cluster vertices into path vertices and intersection vertices;

[0151] Taking the sub-topology composed of the continuously connected path vertices as the path topology, obtaining the first and last points in the path topology, and establishing the vertices in the graph model with the first and last points;

[0152] Determine whether any two of the starting and ending points can be connected through the intersection vertex, and if so, establish a connectivity relationship between the corresponding two starting and ending points;

[0153] Clustering the vertices having a connectivity relationship in the graph model to form at least one connected subgraph region;

[0154] All intersection vertices in the connected subgraph area are merged into a cluster intersection vertex, the head and tail points are connected to the cluster intersection vertex, and the initial road-level network topology is updated to form an intersection area network topology.

[0155] In one embodiment, the computer program further implements the following steps when executed by a processor:

[0156] The step of clustering the trajectory points according to the global vehicle trajectory data to form cluster vertices, and connecting the cluster vertices to form an initial road-level network topology comprises:

[0157] Extracting global vehicle trajectory data stored in the cloud, and mapping the trajectory points in the local vehicle trajectory data to each grid of the global map;

[0158] Taking the grid as the smallest unit, clustering the trajectory points in the grid to form cluster vertices;

[0159] According to the continuity of the global vehicle trajectory data, a connection relationship between the cluster vertices is established to form an initial road-level road network topology.

[0160] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0161] The step of establishing a connection relationship between the cluster vertices according to the continuity of the global vehicle trajectory data to form an initial road-level network topology includes:

[0162] Acquire an extension direction of a global vehicle trajectory and a vehicle driving direction according to the global vehicle trajectory data;

[0163] Determining the adjacent connection relationship of the cluster vertices according to the extension direction of the global vehicle trajectory, and sequentially connecting the cluster vertices along the extension direction of the global vehicle trajectory to form a continuous vehicle trajectory;

[0164] The direction of the vehicle trajectory is determined according to the vehicle driving direction to form an initial road-level road network topology.

[0165] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0166] Determining the direction of the vehicle trajectory according to the vehicle driving direction to form an initial road-level road network topology includes:

[0167] Setting the cluster vertices as solid dots in the global map;

[0168] Setting a track connection line between two adjacent cluster vertices in each vehicle track, and determining the direction of the arrow of the track connection line according to the driving direction of the vehicle, wherein the direction of the arrow is the driving direction of the vehicle;

[0169] All vehicle trajectories are merged in the global map to form an initial road-level network topology.

[0170] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0171] The classifying the cluster vertices into path vertices and intersection vertices comprises:

[0172] Obtaining the number of cluster vertices connected to each of the cluster vertices in the initial road-level road network topology;

[0173] If the number of connected cluster vertices is less than or equal to two, the corresponding cluster vertex is determined to be a path vertex;

[0174] If the number of connected cluster vertices is greater than two, the corresponding cluster vertex is determined to be an intersection vertex.

[0175] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0176] The step of determining whether any two of the first and last points can be connected via the intersection vertex, and if so, establishing a connectivity relationship between the corresponding two first and last points comprises:

[0177] Arrange the first and last points in sequence according to their numbers, obtain the number m of the first and last points, and establish an m×m binary matrix;

[0178] In the binary matrix, there is a corresponding square between any two of the head and tail points, and the square is preset with a first value, and the first value indicates that the corresponding two head and tail points are not connected;

[0179] Determine whether any two of the head and tail points can be connected through the intersection vertex, and if so, modify the first value of the corresponding square in the binary matrix to a second value, where the second value indicates that the corresponding two head and tail points are connected;

[0180] According to the binarized matrix, a connecting edge is established between the two connected head and tail points in the graph model.

[0181] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0182] The step of clustering the vertices having connectivity in the graph model to form at least one connected subgraph region comprises:

[0183] Acquire a plurality of path vertices connected by the connected edges in the graph model;

[0184] The multiple path vertices connected by the connecting edges are clustered, and an area surrounding all the multiple path vertices connected by the connecting edges is set as a connected subgraph area in the graph model.

[0185] For the specific limitations on the steps implemented when the computer program is executed by the processor, please refer to the limitations on the method for the road network topology of the intersection area above, which will not be repeated here.

[0186] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 7As shown. The computer device includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store intersection area road network topology data. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a road network topology method for an intersection area is implemented.

[0187] Those skilled in the art will understand that Figure 7 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0188] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the following steps when executing the computer program:

[0189] Clustering trajectory points according to global vehicle trajectory data to form cluster vertices, and connecting the cluster vertices to form an initial road-level road network topology;

[0190] Classifying the cluster vertices into path vertices and intersection vertices;

[0191] Taking the sub-topology composed of the continuously connected path vertices as the path topology, obtaining the first and last points in the path topology, and establishing the vertices in the graph model with the first and last points;

[0192] Determine whether any two of the starting and ending points can be connected through the intersection vertex, and if so, establish a connectivity relationship between the corresponding two starting and ending points;

[0193] Clustering the vertices having a connectivity relationship in the graph model to form at least one connected subgraph region;

[0194] All intersection vertices in the connected subgraph area are merged into a cluster intersection vertex, the head and tail points are connected to the cluster intersection vertex, and the initial road-level network topology is updated to form an intersection area network topology.

[0195] In one embodiment, when the processor executes the computer program, the following steps are also implemented:

[0196] The step of clustering the trajectory points according to the global vehicle trajectory data to form cluster vertices, and connecting the cluster vertices to form an initial road-level network topology comprises:

[0197] Extracting global vehicle trajectory data stored in the cloud, and mapping the trajectory points in the local vehicle trajectory data to each grid of the global map;

[0198] Taking the grid as the smallest unit, clustering the trajectory points in the grid to form cluster vertices;

[0199] According to the continuity of the global vehicle trajectory data, a connection relationship between the cluster vertices is established to form an initial road-level road network topology.

[0200] In one embodiment, when the processor executes the computer program, the following steps are also implemented:

[0201] The step of establishing a connection relationship between the cluster vertices according to the continuity of the global vehicle trajectory data to form an initial road-level network topology includes:

[0202] Acquire an extension direction of a global vehicle trajectory and a vehicle driving direction according to the global vehicle trajectory data;

[0203] Determining the adjacent connection relationship of the cluster vertices according to the extension direction of the global vehicle trajectory, and sequentially connecting the cluster vertices along the extension direction of the global vehicle trajectory to form a continuous vehicle trajectory;

[0204] The direction of the vehicle trajectory is determined according to the vehicle driving direction to form an initial road-level road network topology.

[0205] In one embodiment, when the processor executes the computer program, the following steps are also implemented:

[0206] Determining the direction of the vehicle trajectory according to the vehicle driving direction to form an initial road-level road network topology includes:

[0207] Setting the cluster vertices as solid dots in the global map;

[0208] Setting a track connection line between two adjacent cluster vertices in each vehicle track, and determining the direction of the arrow of the track connection line according to the driving direction of the vehicle, wherein the direction of the arrow is the driving direction of the vehicle;

[0209] All vehicle trajectories are merged in the global map to form an initial road-level network topology.

[0210] In one embodiment, when the processor executes the computer program, the following steps are also implemented:

[0211] The classifying the cluster vertices into path vertices and intersection vertices comprises:

[0212] Obtaining the number of cluster vertices connected to each of the cluster vertices in the initial road-level road network topology;

[0213] If the number of connected cluster vertices is less than or equal to two, the corresponding cluster vertex is determined to be a path vertex;

[0214] If the number of connected cluster vertices is greater than two, the corresponding cluster vertex is determined to be an intersection vertex.

[0215] In one embodiment, when the processor executes the computer program, the following steps are also implemented:

[0216] The step of determining whether any two of the first and last points can be connected via the intersection vertex, and if so, establishing a connectivity relationship between the corresponding two first and last points comprises:

[0217] Arrange the first and last points in sequence according to their numbers, obtain the number m of the first and last points, and establish an m×m binary matrix;

[0218] In the binary matrix, there is a corresponding square between any two of the head and tail points, and the square is preset with a first value, and the first value indicates that the corresponding two head and tail points are not connected;

[0219] Determine whether any two of the head and tail points can be connected through the intersection vertex, and if so, modify the first value of the corresponding square in the binary matrix to a second value, where the second value indicates that the corresponding two head and tail points are connected;

[0220] According to the binarized matrix, a connecting edge is established between the two connected head and tail points in the graph model.

[0221] In one embodiment, when the processor executes the computer program, the following steps are also implemented:

[0222] The step of clustering the vertices having connectivity in the graph model to form at least one connected subgraph region comprises:

[0223] Acquire a plurality of path vertices connected by the connected edges in the graph model;

[0224] The multiple path vertices connected by the connecting edges are clustered, and an area surrounding all the multiple path vertices connected by the connecting edges is set as a connected subgraph area in the graph model.

[0225] For the specific limitations on the steps implemented when the processor executes the computer program, please refer to the limitations on the method for the road network topology of the intersection area above, which will not be repeated here.

[0226] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0227] Clustering trajectory points according to global vehicle trajectory data to form cluster vertices, and connecting the cluster vertices to form an initial road-level road network topology;

[0228] Classifying the cluster vertices into path vertices and intersection vertices;

[0229] Taking the sub-topology composed of the continuously connected path vertices as the path topology, obtaining the first and last points in the path topology, and establishing the vertices in the graph model with the first and last points;

[0230] Determine whether any two of the starting and ending points can be connected through the intersection vertex, and if so, establish a connectivity relationship between the corresponding two starting and ending points;

[0231] Clustering the vertices having a connectivity relationship in the graph model to form at least one connected subgraph region;

[0232] All intersection vertices in the connected subgraph area are merged into a cluster intersection vertex, the head and tail points are connected to the cluster intersection vertex, and the initial road-level network topology is updated to form an intersection area network topology.

[0233] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0234] The step of clustering the trajectory points according to the global vehicle trajectory data to form cluster vertices, and connecting the cluster vertices to form an initial road-level network topology comprises:

[0235] Extracting global vehicle trajectory data stored in the cloud, and mapping the trajectory points in the local vehicle trajectory data to each grid of the global map;

[0236] Taking the grid as the smallest unit, clustering the trajectory points in the grid to form cluster vertices;

[0237] According to the continuity of the global vehicle trajectory data, a connection relationship between the cluster vertices is established to form an initial road-level road network topology.

[0238] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0239] The step of establishing a connection relationship between the cluster vertices according to the continuity of the global vehicle trajectory data to form an initial road-level network topology includes:

[0240] Acquire an extension direction of a global vehicle trajectory and a vehicle driving direction according to the global vehicle trajectory data;

[0241] Determining the adjacent connection relationship of the cluster vertices according to the extension direction of the global vehicle trajectory, and sequentially connecting the cluster vertices along the extension direction of the global vehicle trajectory to form a continuous vehicle trajectory;

[0242] The direction of the vehicle trajectory is determined according to the vehicle driving direction to form an initial road-level road network topology.

[0243] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0244] Determining the direction of the vehicle trajectory according to the vehicle driving direction to form an initial road-level road network topology includes:

[0245] Setting the cluster vertices as solid dots in the global map;

[0246] Setting a track connection line between two adjacent cluster vertices in each vehicle track, and determining the direction of the arrow of the track connection line according to the driving direction of the vehicle, wherein the direction of the arrow is the driving direction of the vehicle;

[0247] All vehicle trajectories are merged in the global map to form an initial road-level network topology.

[0248] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0249] The classifying the cluster vertices into path vertices and intersection vertices comprises:

[0250] Obtaining the number of cluster vertices connected to each of the cluster vertices in the initial road-level road network topology;

[0251] If the number of connected cluster vertices is less than or equal to two, the corresponding cluster vertex is determined to be a path vertex;

[0252] If the number of connected cluster vertices is greater than two, the corresponding cluster vertex is determined to be an intersection vertex.

[0253] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0254] The step of determining whether any two of the first and last points can be connected via the intersection vertex, and if so, establishing a connectivity relationship between the corresponding two first and last points comprises:

[0255] Arrange the first and last points in sequence according to their numbers, obtain the number m of the first and last points, and establish an m×m binary matrix;

[0256] In the binary matrix, there is a corresponding square between any two of the head and tail points, and the square is preset with a first value, and the first value indicates that the corresponding two head and tail points are not connected;

[0257] Determine whether any two of the head and tail points can be connected through the intersection vertex, and if so, modify the first value of the corresponding square in the binary matrix to a second value, where the second value indicates that the corresponding two head and tail points are connected;

[0258] According to the binarized matrix, a connecting edge is established between the two connected head and tail points in the graph model.

[0259] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0260] The step of clustering the vertices having connectivity in the graph model to form at least one connected subgraph region comprises:

[0261] Acquire a plurality of path vertices connected by the connected edges in the graph model;

[0262] The multiple path vertices connected by the connecting edges are clustered, and an area surrounding all the multiple path vertices connected by the connecting edges is set as a connected subgraph area in the graph model.

[0263] For the specific limitations on the steps implemented when the computer program is executed by the processor, please refer to the limitations on the method for the road network topology of the intersection area above, which will not be repeated here.

[0264] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0265] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0266] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A road network topology method for an intersection area, characterized in that: include: Clustering trajectory points according to global vehicle trajectory data to form cluster vertices, and connecting the cluster vertices to form an initial road-level road network topology; Classifying the cluster vertices into path vertices and intersection vertices; Taking the sub-topology composed of the continuously connected path vertices as the path topology, obtaining the first and last points in the path topology, and establishing the vertices in the graph model with the first and last points; Determine whether any two of the starting and ending points can be connected through the intersection vertex, and if so, establish a connectivity relationship between the corresponding two starting and ending points; Clustering the vertices having a connectivity relationship in the graph model to form at least one connected subgraph region; All intersection vertices in the connected subgraph area are merged into a cluster intersection vertex, the head and tail points are connected to the cluster intersection vertex, and the initial road-level network topology is updated to form an intersection area network topology.

2. The intersection area road network topology method according to claim 1, characterized in that: The step of clustering the trajectory points according to the global vehicle trajectory data to form cluster vertices, and connecting the cluster vertices to form an initial road-level network topology comprises: Extracting global vehicle trajectory data stored in the cloud, and mapping the trajectory points in the local vehicle trajectory data to each grid of the global map; Taking the grid as the smallest unit, clustering the trajectory points in the grid to form cluster vertices; According to the continuity of the global vehicle trajectory data, a connection relationship between the cluster vertices is established to form an initial road-level road network topology.

3. The intersection area road network topology method according to claim 2, characterized in that: The step of establishing a connection relationship between the cluster vertices according to the continuity of the global vehicle trajectory data to form an initial road-level network topology includes: Acquire an extension direction of a global vehicle trajectory and a vehicle driving direction according to the global vehicle trajectory data; Determining the adjacent connection relationship of the cluster vertices according to the extension direction of the global vehicle trajectory, and sequentially connecting the cluster vertices along the extension direction of the global vehicle trajectory to form a continuous vehicle trajectory; The direction of the vehicle trajectory is determined according to the vehicle driving direction to form an initial road-level road network topology.

4. The intersection area road network topology method according to claim 3, characterized in that: Determining the direction of the vehicle trajectory according to the vehicle driving direction to form an initial road-level road network topology includes: Setting the cluster vertices as solid dots in the global map; Setting a track connection line between two adjacent cluster vertices in each vehicle track, and determining the direction of the arrow of the track connection line according to the driving direction of the vehicle, wherein the direction of the arrow is the driving direction of the vehicle; All vehicle trajectories are merged in the global map to form an initial road-level network topology.

5. The intersection area road network topology method according to claim 1, characterized in that: The classifying the cluster vertices into path vertices and intersection vertices comprises: Obtaining the number of cluster vertices connected to each of the cluster vertices in the initial road-level road network topology; If the number of connected cluster vertices is less than or equal to two, the corresponding cluster vertex is determined to be a path vertex; If the number of connected cluster vertices is greater than two, the corresponding cluster vertex is determined to be an intersection vertex.

6. The intersection area road network topology method according to claim 1, characterized in that: The step of determining whether any two of the first and last points can be connected via the intersection vertex, and if so, establishing a connectivity relationship between the corresponding two first and last points comprises: Arrange the first and last points in sequence according to their numbers, obtain the number m of the first and last points, and establish an m×m binary matrix; In the binary matrix, there is a corresponding square between any two of the head and tail points, and the square is preset with a first value, and the first value indicates that the corresponding two head and tail points are not connected; Determine whether any two of the head and tail points can be connected through the intersection vertex, and if so, modify the first value of the corresponding square in the binary matrix to a second value, where the second value indicates that the corresponding two head and tail points are connected; According to the binarized matrix, a connecting edge is established between the two connected head and tail points in the graph model.

7. The intersection area road network topology method according to claim 6, characterized in that: The step of clustering the vertices having connectivity in the graph model to form at least one connected subgraph region comprises: Acquire a plurality of path vertices connected by the connected edges in the graph model; The multiple path vertices connected by the connecting edges are clustered, and an area surrounding all the multiple path vertices connected by the connecting edges is set as a connected subgraph area in the graph model.

8. A road network topology device for an intersection area, characterized in that: The device comprises: An initial road network topology module, used for clustering trajectory points according to global vehicle trajectory data to form cluster vertices, and connecting the cluster vertices to form an initial road-level road network topology; A cluster vertex classification module, used for classifying the cluster vertices into path vertices and intersection vertices; Setting a graph model vertex module, used to take the sub-topology composed of the continuously connected path vertices as the path topology, obtain the first and last points in the path topology, and establish the vertices in the graph model with the first and last points; A vertex connectivity relationship management module is used to determine whether any two of the head and tail points can be connected through the intersection vertex, and if so, establish a connectivity relationship between the corresponding two head and tail points; A connected subgraph region forming module is used to cluster the vertices having a connected relationship in the graph model to form at least one connected subgraph region; The intersection area road network topology forming module is used to merge all the intersection vertices located in the connected subgraph area into a cluster intersection vertex, connect the head and tail points with the cluster intersection vertex, and update the initial road-level road network topology to form the intersection area road network topology.

9. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images