CN116150296A

CN116150296A - Road network skeleton generation method and device, electronic equipment and storage medium

Info

Publication number: CN116150296A
Application number: CN202310189485.2A
Authority: CN
Inventors: 李忠恩; 陈尧; 谢珍兰
Original assignee: Zhejiang Geely Holding Group Co Ltd; Ningbo Geely Automobile Research and Development Co Ltd
Current assignee: Zhejiang Geely Holding Group Co Ltd; Ningbo Geely Automobile Research and Development Co Ltd
Priority date: 2023-02-24
Filing date: 2023-02-24
Publication date: 2023-05-23

Abstract

The application relates to the technical field of automatic driving, in particular to a road network skeleton generation method, a device, electronic equipment and a storage medium, which are used for improving the accuracy of road network skeleton generation. The method comprises the following steps: acquiring each track data corresponding to a target map area; dividing the obtained track data into track groups, and respectively converting the track groups into a corresponding node in the directed graph; determining a communication relation between track groups based on the running information of the track data contained in the track groups, and converting the communication relation between the two track groups into directed edges between two corresponding nodes in the directed graph; and obtaining the intersection skeleton, the road skeleton and the road network topological relation corresponding to the target map area based on each node in the directed graph and the directed edges among the nodes. Thus, based on massive track data, a directed graph is established, and based on the directed graph, a road network skeleton is generated, so that the accuracy of the road network skeleton is improved.

Description

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

Technical Field

The present disclosure relates to the field of autopilot technologies, and in particular, to a method and an apparatus for generating a road network skeleton, an electronic device, and a storage medium.

Background

High-precision maps are also called high-precision maps, and are one of core technologies in the technical field of automatic driving. At present, numerous functional developments of intelligent vehicle autopilot are based on high-precision maps, and the development of the high-precision maps directly influences the safety and the precision of autopilot. Compared with a navigation electronic map, the high-precision map can provide road conditions at the level of lanes, the precision reaches the level of centimeters, the updating frequency of elements is higher, the data model is finer, and the automatic driving vehicle can be helped to better avoid potential risks. Currently, road data is generally fused based on a road network skeleton, a high-precision map is generated, and the road network skeleton is established as an important part of the generation of the high-precision map.

In the prior art, when a road network skeleton is established, manual annotation is usually carried out on a point cloud map or a semantic map in a manual annotation mode, so that the road network skeleton is established.

However, when the road network skeleton is generated in this way in the related art, because the manual labeling needs to rely on professional literacy of professionals, road nodes labeled by different professionals are different, resulting in inaccurate generated road network skeleton, for example, when labeling experience of professionals is insufficient, there may be cases of labeling errors.

In view of this, in the related art, the accuracy of the road network skeleton generation needs to be further improved.

Disclosure of Invention

The embodiment of the application provides a road network skeleton generation method, a device, electronic equipment and a storage medium, so as to improve the accuracy of road network skeleton generation.

The specific technical scheme provided by the embodiment of the application is as follows:

in a first aspect, a method for generating a road network skeleton is provided, including:

acquiring each track data corresponding to the target map region, wherein each track data comprises: the driving track of the corresponding vehicle in the target map area;

dividing the obtained track data into track groups, and respectively converting the track groups into a corresponding node in the directed graph; the similarity between the track data contained in each track group reaches a similarity threshold;

determining a communication relation between track groups based on the running information of the track data contained in the track groups, and converting the communication relation between the two track groups into directed edges between two corresponding nodes in the directed graph;

and obtaining the intersection skeleton, the road skeleton and the road network topological relation corresponding to the target map area based on each node in the directed graph and the directed edges among the nodes.

Optionally, dividing the obtained track data into track groups includes:

dividing a target map area according to a preset area dividing mode to obtain a sub-area grid set corresponding to the target map area;

screening out each track grid from the subarea grid set, wherein each track grid comprises at least one section of track data in the track data;

for each track grid, the following operations are performed: clustering each segment of track data with similarity reaching a first similarity threshold value in a track grid to obtain at least one target class cluster;

and respectively taking each obtained target cluster as a corresponding track group.

Optionally, the driving information of each piece of track data includes at least: the corresponding running time of the corresponding track data;

determining a communication relationship between the track groups based on the travel information of the track data included in the track groups, including:

for each track group, the following operations are performed:

if the first track data contained in one track group is continuous with the second track data contained in the other track group, and the running time corresponding to the second track data is before the running time corresponding to the first track data, determining that the track group corresponding to the second track data is precursor communication of the track group corresponding to the first track data;

If the first track data contained in one track group is continuous with the second track data contained in the other track group, and the running time of the second track data is after the running time of the first track data, determining that the track group corresponding to the second track data is the subsequent communication of the track group corresponding to the first track data.

Optionally, converting the communication relationship between the two connected track groups into a directed edge between two corresponding nodes in the directed graph includes:

for each track group, the following operations are performed:

taking one track group as a first track group, taking one track group which is communicated with a first track group precursor as a second track group, and converting a communication relation between the first track group and the second track group into a directed edge between two corresponding nodes in the directed graph, wherein the direction of the directed edge points to the node corresponding to the first track group from the node corresponding to the second track group;

and taking one track group as a first track group, taking one track group which is communicated with the first track group later as a third track group, and converting the communication relation between the first track group and the third track group into a directed edge between two corresponding nodes in the directed graph, wherein the direction of the directed edge points to the node corresponding to the third track group from the node corresponding to the first track group.

Optionally, after converting the communication relationship between the two connected track groups into the directed edges between the corresponding two nodes in the directed graph, the method further includes:

combining all nodes in the directed graph based on the similarity among all track groups to obtain new all nodes;

for each node currently contained in the directed graph, the following operations are respectively executed: if the degree of departure of a node is greater than a first degree threshold, or the degree of arrival of a node is greater than a first degree threshold, determining that the node is the first node, wherein the degree of departure of a node is the number of directed edges taking the node as a starting point, and the degree of arrival of a node is the number of directed edges taking the node as an ending point;

and merging the obtained first nodes which are communicated in the first node set into a corresponding second node.

Optionally, merging each node in the directed graph based on the similarity between each track group to obtain each new node, including:

for each track grid, the following operations are performed: clustering all the track groups which are not communicated and have the similarity reaching a second similarity threshold value in one track grid and the eight adjacent track grids to obtain at least one track group cluster;

And merging all nodes corresponding to all track groups belonging to the same track group class cluster in the directed graph into a corresponding new node.

Optionally, based on each node in the directed graph and the directed edges between each node, obtaining the intersection skeleton, the road skeleton and the road network topological relation corresponding to the target map area includes:

determining road nodes and intersection nodes in the directed graph based on the exit degree and the entrance degree of each node in the directed graph;

generating an intersection skeleton corresponding to the target map area based on the track groups corresponding to the intersection nodes;

generating a road skeleton corresponding to the target map area based on the track groups corresponding to the road nodes respectively;

and generating a road network topological relation corresponding to the target map area based on the communication relation corresponding to the directed edges among the nodes.

Optionally, determining the road node and the intersection node in the directed graph based on the exit degree and the entrance degree of each node in the directed graph includes:

for each node in the directed graph, the following operations are respectively executed:

if the exit degree of one node is greater than the second exit degree threshold value, or the entrance degree of one node is greater than the second entrance degree threshold value, determining that the one node is an intersection node;

And if the output degree of one node is not greater than the second output degree threshold value and the input degree of one node is not greater than the second input degree threshold value, determining that one node is a road node.

In a second aspect, a road network skeleton generating device is provided, including:

the acquisition module is used for acquiring each piece of track data corresponding to the target map area, wherein each piece of track data comprises: the driving track of the corresponding vehicle in the target map area;

the grouping module is used for dividing the obtained track data into track groups and respectively converting the track groups into a corresponding node in the directed graph; the similarity between the track data contained in each track group reaches a similarity threshold;

the first processing module is used for determining the communication relation between the track groups based on the running information of the track data contained in the track groups and converting the communication relation between the two communicated track groups into directed edges between the two corresponding nodes in the directed graph;

the generation module is used for obtaining the intersection skeleton, the road skeleton and the road network topological relation corresponding to the target map area based on each node in the directed graph and the directed edges among the nodes.

Optionally, when dividing the obtained track data into track groups, the grouping module is further configured to:

the first processing module is further configured to, when determining a connection relationship between the track groups based on the travel information of the track data included in the track groups:

for each track group, the following operations are performed:

Optionally, when converting the communication relationship between the two connected track groups into a directed edge between two corresponding nodes in the directed graph, the first processing module is further configured to:

for each track group, the following operations are performed:

Optionally, after converting the communication relationship between the two connected track groups into the directed edges between the corresponding two nodes in the directed graph, the apparatus further includes a second processing module, where the second processing module is configured to:

Optionally, based on the similarity between the track groups, merging the nodes in the directed graph, and when obtaining each new node, the second processing module is further configured to:

Optionally, based on each node in the directed graph and the directed edges between each node, obtaining an intersection skeleton, a road skeleton and a road network topological relation corresponding to the target map area, wherein the generating module is further configured to:

Optionally, the generating module is further configured to determine a road node and an intersection node in the directed graph based on the outbound degree and the inbound degree of each node in the directed graph, where the intersection node is configured to:

In a third aspect, there is provided an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the method of any of the first aspects when the program is executed.

In a fourth aspect, there is provided a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the method of any of the first aspects above.

In the embodiment of the application, the service device acquires track data corresponding to the target map area from the terminal device, divides the acquired track data into track groups, converts each track group into a corresponding node in the directed graph, determines a communication relationship between the track groups based on running information of the track data contained in each track group, converts the communication relationship between the two communicated track groups into directed edges between the corresponding two nodes in the directed graph, and obtains an intersection skeleton, a road skeleton and a road network topological relationship corresponding to the target map area based on each node in the directed graph and the directed edges between the nodes. Therefore, based on massive track data, nodes and directed edges of the directed graph are established, and the intersection nodes and the road nodes are determined according to the number of the directed edges of each node, so that the intersection skeleton, the road skeleton and the road network topological relation corresponding to the target map area are generated, errors of manual marking can be avoided, and the accuracy of road network skeleton generation is improved.

Drawings

Fig. 1 is a schematic view of an application scenario in an embodiment of the present application;

fig. 2 is a schematic flow chart of a road network skeleton generating method in an embodiment of the present application;

FIG. 3 is a schematic diagram of a track group converted into a corresponding node in a directed graph according to an embodiment of the present application;

FIG. 4 is a schematic flow chart of obtaining each track group in the embodiment of the present application;

fig. 5 is a schematic diagram of a sub-region grid set corresponding to a target map region in an embodiment of the present application;

FIG. 6 is a schematic diagram of a track grid in an embodiment of the present application;

FIG. 7 is a schematic diagram of obtaining at least one target cluster corresponding to a track grid in an embodiment of the present application;

FIG. 8 is a schematic diagram of a track set obtained in an embodiment of the present application;

FIG. 9 is a schematic flow chart of determining a communication relationship between track groups according to an embodiment of the present application;

FIG. 10 is a schematic diagram of determining a communication relationship between track groups according to an embodiment of the present application;

FIG. 11 is a schematic flow chart of determining directed edges in a directed graph according to an embodiment of the present application;

FIG. 12 is a schematic diagram of determining directed edges in a directed graph in an embodiment of the present application;

FIG. 13 is a schematic flow chart of node optimization in an embodiment of the present application;

FIG. 14 is a flow chart of obtaining new nodes according to an embodiment of the present application;

FIG. 15 is a schematic diagram of obtaining at least one cluster of track groups in an embodiment of the present application;

FIG. 16 is a schematic diagram of obtaining a second node according to an embodiment of the present application;

FIG. 17 is a schematic flow chart of obtaining a road network skeleton in an embodiment of the present application;

FIG. 18 is a schematic flow chart of determining road nodes and intersection nodes in a directed graph according to an embodiment of the present application;

FIG. 19 is a schematic diagram of determining road nodes and intersection nodes in a directed graph in an embodiment of the present application;

FIG. 20 is a schematic diagram of a road network skeleton in an embodiment of the present application;

fig. 21 is a schematic structural diagram of a road network skeleton generating device in an embodiment of the present application;

fig. 22 is a schematic structural diagram of an electronic device in an embodiment of the present application.

Detailed Description

The following description of the technical solutions in the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings in the embodiments of the present application, and it is apparent that the described embodiments are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present disclosure.

Some of the terms in the embodiments of the present application are explained below to facilitate understanding by those skilled in the art.

(1) Directed graph: consists of a set of nodes and a set of directed edges, each directed edge connecting an ordered pair of nodes.

(2) Degree of egress of node: the number of directed edges starting from the node.

(3) Degree of entry of node: the number of directed edges ending with the node.

The preferred embodiments of the present application will be described in detail with reference to the accompanying drawings.

Fig. 1 is a schematic view of an application scenario in an embodiment of the present application. The application scenario is a schematic diagram of an embodiment of the application. In the application scenario diagram, the service device 110 is included, and the terminal device 120 (including the terminal device 1201, the terminal device 1202 …, and the terminal device 120 n) is included. The service device 110 receives each track data sent by the terminal device 120, the service device 110 divides each track data into each track group, converts each track group into a corresponding node in the directed graph, then determines a communication relationship between each track group based on the running information of each track data contained in each track group, converts the communication relationship between two communicated track groups into a directed edge between two corresponding nodes in the directed graph, and finally obtains a road network skeleton corresponding to the target map area based on each node in the directed graph and the directed edge between each node.

The service device 110 may be an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, or a cloud server providing cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, a content delivery network (Content Delivery Network, CDN), basic cloud computing services such as big data and an artificial intelligent platform. The terminal device 120 and the service device 110 may be directly or indirectly connected through wired or wireless communication, which is not limited herein.

The terminal device 120 may be a mobile phone, a portable computer, etc. carried by the driver during driving of the vehicle, or may be a device with a positioning function, which is disposed in the vehicle, and the application is not limited herein.

Based on the foregoing embodiments, referring to fig. 2, a flow chart of a method for generating a road network skeleton in an embodiment of the present application is shown, which specifically includes:

step 20: and acquiring each track data corresponding to the target map area.

Wherein each piece of trajectory data includes: and the corresponding vehicle is on the running track in the target map area.

In the embodiment of the application, the service device acquires each track data corresponding to the target map area from the terminal device.

Step 21: dividing the obtained track data into track groups, and respectively converting the track groups into a corresponding node in the directed graph.

Wherein, the similarity between each track data contained in each track group reaches a similarity threshold value.

In the embodiment of the application, after each track data is obtained, each track data is divided to obtain each track group, and each track group is converted into a corresponding node in the directed graph.

For example, referring to fig. 3, for a schematic diagram of a track group converted into a corresponding node in a directed graph in the embodiment of the present application, it is assumed that each obtained track group includes: track group A, track group B, track group C, track group A is converted into node A in the directed graph, track group B is converted into node B in the directed graph, track group C is converted into node C in the directed graph.

Specifically, in the embodiment of the present application, when step 21 is performed, the obtained trajectory data needs to be divided into trajectory groups, as shown in fig. 4, which is a schematic flow chart of obtaining each trajectory group in the embodiment of the present application, and the following details of the specifically performed operations are described with reference to fig. 4:

Step 210: dividing the target map area according to a preset area dividing mode to obtain a subarea grid set corresponding to the target map area.

In the embodiment of the application, a reference point is selected from a target map area as an origin, a plane coordinate system is established, and the target map area is segmented according to a preset grid size, so that a sub-area grid set corresponding to the target map area is obtained.

The preset grid size may be determined according to practical situations, which is not limited in the embodiment of the present application.

For example, referring to fig. 5, which is a schematic diagram of a sub-region grid set corresponding to a target map region in the embodiment of the present application, assuming that a reference point selected in the target map region is a point at the lower left corner and the grid size is 20m×20m, a plane coordinate system is established with the point at the lower left corner as the origin, and the target map region is divided into sub-region grids according to grids of 20m×20m.

Step 211: and screening out each track grid from the subarea grid set.

Wherein each track grid comprises at least one track data section.

In the embodiment of the present application, after obtaining the sub-region grid set, the following operations are performed for each sub-region grid: judging whether a sub-area grid contains one section of track data in at least one section of track data, and if the sub-area grid contains one section of track data in at least one section of track data, taking the sub-area grid as a track grid.

For example, referring to fig. 6, a schematic diagram of each track grid in the embodiment of the present application is shown, where the sub-area grid 1 does not include a segment of track data in one track data, the sub-area grid 2 includes a segment of track data in multiple track data, and the sub-area grid 2 is screened out as one track grid.

Step 212: for each track grid, the following operations are performed: and clustering each segment of track data with similarity reaching a first similarity threshold value in one track grid to obtain at least one target class cluster.

In the embodiment of the present application, after each track grid is screened out from the sub-area grid set, the following operations are performed for each track grid: clustering is carried out based on the similarity between the track data of each segment in one track grid, each segment of track data with the similarity reaching a first similarity threshold value is aggregated into a target class cluster, and at least one target class cluster corresponding to the track grid is obtained.

For example, referring to fig. 7, in this embodiment, a schematic diagram of obtaining at least one target cluster corresponding to one track grid is shown, clustering is performed based on field of view similarity between each segment of track data in one track grid, field of view similarity between track data a and track data c is 0.71, field of view similarity between track data a and track data d is 0.73, field of view similarity between track data c and track data d is 0.72, and track data a, c, d with field of view similarity greater than a first similarity threshold value of 0.7 are aggregated into one target cluster.

The track orientation information, the observable field of view range and the shooting device coordinate information of each track point of track data corresponding to a vehicle can be acquired through shooting devices with shooting functions installed in the vehicle, and the field of view similarity between the two track data is determined based on the track orientation information, the observable field of view range and the shooting device coordinate information.

Step 213: and respectively taking each obtained target cluster as a corresponding track group.

In the embodiment of the present application, after each target class cluster is obtained, the following operations are executed for each target class cluster: one target class cluster is taken as one track group.

For example, referring to fig. 8, for a schematic diagram of obtaining a track group in the embodiment of the present application, assume that each target class cluster includes: and the target class cluster A, the target class cluster B and the target class cluster C are used as a track group A, the target class cluster B is used as a track group B and the target class cluster C is used as a track group C.

Step 22: and determining the communication relation between the track groups based on the running information of the track data contained in the track groups, and converting the communication relation between the two communicated track groups into directed edges between the corresponding two nodes in the directed graph.

Wherein, the driving information of each piece of track data at least comprises: and the corresponding running time of the corresponding track data.

Specifically, in the embodiment of the present application, when executing step 22, it is necessary to determine the communication relationship between the track groups based on the running information of the track data included in each track group, referring to fig. 9, which is a schematic flow chart for determining the communication relationship between the track groups in the embodiment of the present application, and the following detailed description of the specifically executed operation is given with reference to fig. 9:

step 220: judging whether the first track data contained in one track group is continuous with the second track data contained in the other track group, if yes, executing step 221, otherwise, executing step 224.

Step 221: judging whether the running time corresponding to the second track data is before the running time corresponding to the first track data, if yes, executing step 222, otherwise, executing step 223.

Step 222: and determining that the track group corresponding to the second track data is precursor communication of the track group corresponding to the first track data.

In this embodiment, it is determined whether first track data included in one track group is continuous with second track data included in another track group, if the first track data included in one track group is continuous with the second track data included in another track group, it is determined whether a running time corresponding to the second track data is before a running time corresponding to the first track data, and if the running time corresponding to the second track data is before the running time corresponding to the first track data, it is determined that the track group corresponding to the second track data is precursor communication of the track group corresponding to the first track data.

Wherein the first track data contained in one track group is any one track data in the track group, and the second track data contained in the other track group is any one track data in the track group.

For example, referring to fig. 10, in order to determine a communication relationship between each track group in the embodiment of the present application, it is assumed that track data a included in track group a and track data f included in track group B are continuous, and a driving time of track data a is 11:40, the travel time of the trajectory data f is 11:39, determining that the track group B corresponding to the track data f is precursor communication of the track group a corresponding to the track data a before the running time corresponding to the track data a.

The running time corresponding to the track data may be an average value of running times of each track point included in the track data, or may be a running time of a start track point or a stop track point included in the track data, which is not limited in the embodiment of the present application.

Step 223: and determining that the track group corresponding to the second track data is the subsequent communication of the track group corresponding to the first track data.

In this embodiment, it is determined whether first track data included in one track group is continuous with second track data included in another track group, if the first track data included in one track group is continuous with the second track data included in another track group, it is determined whether a running time corresponding to the second track data is before a running time corresponding to the first track data, and if the running time corresponding to the second track data is after the running time corresponding to the first track data, it is determined that the track group corresponding to the second track data is subsequent communication of the track group corresponding to the first track data.

For example, as shown in fig. 10, it is assumed that the track data a included in the track group a and the track data h included in the track group C are continuous, and the travel time of the track data a is 11:40, the travel time of the trajectory data h is 11:41, determining that the track group C corresponding to the track data h is the subsequent communication of the track group a corresponding to the track data a after the running time corresponding to the track data a.

Step 224: it is determined that there is no communication between the two track groups.

In this embodiment, it is determined whether first track data included in one track group is continuous with second track data included in another track group, and if the first track data included in the one track group is discontinuous with the second track data included in the other track group, it is determined that the two track groups are not continuous with each other.

For example, as shown in fig. 10, if any one of the track data included in the track group a is discontinuous with any one of the track data included in the track group D, it is determined that the track group a and the track group D are not in communication.

Specifically, in the embodiment of the present application, when step 22 is performed, the communication relationship between two connected track groups needs to be converted into a directed edge between two corresponding nodes in the directed graph, and referring to fig. 11, a schematic flow diagram of determining the directed edge in the directed graph in the embodiment of the present application is shown, and in the following, with reference to fig. 11, a detailed description is given of a specific performed operation:

For each track group, the following operations are respectively executed:

step 225: and taking one track group as a first track group, taking one track group which is in precursor communication with the first track group as a second track group, and converting the communication relation between the first track group and the second track group into a directed edge between two corresponding nodes in the directed graph.

The direction of the directed edge points to the node corresponding to the first track group from the node corresponding to the second track group.

In the embodiment of the application, after the communication relation between the track groups is obtained, one track group is used as a first track group, one track group which is in precursor communication with the first track group is used as a second track group, and the communication relation between the first track group and the second track group is converted into a directed edge between a node corresponding to the first track group and a node corresponding to the second track group in the directed graph.

For example, referring to fig. 12, for determining a directed edge schematic diagram in a directed graph in the embodiment of the present application, it is assumed that a track group B is a precursor communication of a track group a, where the track group a corresponds to a node a in the directed graph, and the track group B corresponds to a node B in the directed graph, so that a communication relationship between the track group a and the track group B is converted into a directed edge between the node a and the node B in the directed graph, and a direction of the directed edge is directed to the node a by the node B.

Step 226: and taking one track group as a first track group, taking one track group which is communicated with the first track group subsequently as a third track group, and converting the communication relation between the first track group and the third track group into a directed edge between two corresponding nodes in the directed graph.

The direction of the directed edge points to the node corresponding to the third track group from the node corresponding to the first track group.

In the embodiment of the application, after the communication relation between the track groups is obtained, one track group is used as a first track group, one track group which is communicated with the first track group subsequently is used as a third track group, and the communication relation between the first track group and the third track group is converted into a directed edge between a node corresponding to the first track group and a node corresponding to the third track group in the directed graph.

For example, as shown in fig. 12, assume that the track group C is a subsequent connection of the track group a, the track group a corresponds to the node a in the directed graph, the track group C corresponds to the node C in the directed graph, and the connection relationship between the track group a and the track group C is converted into a directed edge between the node a and the node C in the directed graph, and the direction of the directed edge is directed to the node a by the node C.

Further, in the embodiment of the present application, after converting the communication relationship between two connected track groups into the directed edges between the corresponding two nodes in the directed graph, optimizing each node in the directed graph based on the similarity between each track group, referring to fig. 13, which is a schematic flow diagram of node optimization in the embodiment of the present application, with reference to fig. 13, the following details of specifically executed operations are described below:

Step 1300: and merging all nodes in the directed graph based on the similarity among all the track groups to obtain new all the nodes.

Specifically, in performing step 1300, the service apparatus specifically performs the following operations. Referring to fig. 14, a flow chart of obtaining new nodes in the embodiment of the present application is shown, and the following details of the specific operations performed with reference to fig. 14 are described below:

step 1300-1: for each track grid, the following operations are performed: clustering the track groups which are not communicated and have the similarity reaching a second similarity threshold value in one track grid and the eight adjacent track grids to obtain at least one track group cluster.

In the embodiment of the present application, the following operations are performed for each track grid, respectively: clustering is carried out based on the similarity between each track group in one track grid and the eight adjacent track grids, the similarity reaches a second similarity threshold, and the track groups which are not communicated are aggregated into track group clusters.

For example, referring to fig. 15, in an embodiment of the present application, for obtaining at least one track group cluster, an eight-neighborhood track grid of track grid 1 is taken, where the eight-neighborhood track grid of track grid 1 includes: the

track grids

2, 3, 4, 5, 6, 7, 8 and 9 are clustered based on the field of view similarity between each track group in the track grid 1 and each track group in its eight neighborhood track grids, the field of view similarity between track group a in the track grid 1 and track group D in the track grid 2 is 0.81 and not connected, the field of view similarity between track group a in the track grid 1 and track group E in the track grid 5 is 0.83 and not connected, the field of view similarity between track group D in the track grid 2 and track group E in the track grid 5 is 0.82 and not connected, and the field of view similarity is greater than a second similarity threshold value of 0.8 and the not connected track groups a, E and F are clustered into one track group class cluster.

The view similarity between the two track groups may be determined through the view similarity between the respective track data in the two track groups, or the view similarity between the two track groups may be determined through the view similarity average value between the track data included in the two track groups, which is not limited in the embodiment of the present application.

Step 1300-2: and merging all nodes corresponding to all track groups belonging to the same track group class cluster in the directed graph into a corresponding new node.

In this embodiment of the present application, after obtaining at least one track group cluster, the following operations are performed for the at least one track group cluster, respectively: and merging the nodes corresponding to the track groups in one track group class cluster to generate a new node in the directed graph.

For example, as shown in fig. 15, a track group cluster includes a track group a, a track group B, and a track group C, and a node a corresponding to the track group a, a node E corresponding to the track group E, and a node F corresponding to the track group F are combined into a new node.

For each node currently contained in the directed graph, the following operations are respectively executed:

step 1301: whether the outbound degree of a node is greater than a first outbound degree threshold is determined, or whether the inbound degree of a node is greater than a first inbound degree threshold is determined, and if so, step 1302 is performed.

The outgoing degree of one node is the number of directed edges taking one node as a starting point, and the incoming degree of one node is the number of directed edges taking one node as an ending point.

Step 1302: one node is determined to be a first node.

In this embodiment, it is determined whether an outbound degree of a node is greater than a first outbound degree threshold, or whether an inbound degree of a node is greater than a first inbound degree threshold, and if the outbound degree of a node is greater than the first outbound degree threshold, or the inbound degree of the node is greater than the first inbound degree threshold, it is determined that the node is the first node.

The first out-degree threshold may be 1, and the first in-degree threshold may be 1, which is not limited in the embodiment of the present application.

For example, assuming that the first threshold of the degree of departure is 1, the degree of departure of a node is 1, and the degree of entrance of a node is 2, the degree of entrance of the node is greater than the first threshold of the degree of departure, and the node is determined to be the first node.

Step 1303: and merging the obtained first nodes which are communicated in the first node set into a corresponding second node.

In the embodiment of the present application, each obtained first node is used as a first node set, and each first node communicated in the first node set is combined to generate a corresponding second node.

For example, referring to fig. 16, in the embodiment of the present application, a schematic diagram of a second node is obtained, and it is assumed that a first node a in a first node set communicates with a first node b, the first node a communicates with a first node c, the first node b communicates with the first node c, and the first node a, the first node b, and the first node c are combined to generate a corresponding second node.

Therefore, based on the input degree and the output degree of each node, the corresponding nodes in the direction are combined, the optimization of the nodes is realized, and the accuracy of the road network skeleton can be improved.

Step 23: and obtaining the intersection skeleton, the road skeleton and the road network topological relation corresponding to the target map area based on each node in the directed graph and the directed edges among the nodes.

In the embodiment of the application, each node in the directed graph and the directed edges among the nodes are converted into the road network skeleton corresponding to the target map area and output.

Specifically, in executing step 23, the service apparatus specifically performs the following operations. Referring to fig. 17, which is a schematic flow chart of obtaining a road network skeleton in the embodiment of the present application, the following details of the specific operations performed with reference to fig. 17 are described below:

Step 230: and determining the road nodes and the intersection nodes in the directed graph based on the exit degree and the entrance degree of each node in the directed graph.

Specifically, in performing step 230, the service apparatus specifically performs the following operations. Referring to fig. 18, which is a schematic flow chart of determining a road node and an intersection node in a directed graph in the embodiment of the present application, a detailed description of a specific implementation operation is described below with reference to fig. 18:

for each current node in the directed graph, the following operations are respectively executed:

step 2300: judging whether the output degree of one node is greater than a second output degree threshold value or whether the input degree of one node is greater than a second input degree threshold value, if so, executing step 2301, and if not, executing step 2302.

Step 2301: and determining one node as an intersection node.

In the embodiment of the application, whether the exit degree of one node is larger than a second exit degree threshold value or not is judged, or whether the entrance degree of one node is larger than a second entrance degree threshold value or not is judged, if the exit degree of one node is larger than the second exit degree threshold value or the entrance degree of one node is larger than the second entrance degree threshold value, then one node is determined to be an intersection node.

The second out-degree threshold may be 1, and the second in-degree threshold may be 1, which is not limited in the embodiment of the present application.

For example, referring to fig. 19, in an embodiment of the present application, a schematic diagram of determining a road node and an intersection node in a directed graph is shown, and assuming that a second exit threshold is 1, a second entrance threshold is 1, an exit of the node 1 is 4, and an entrance of one node is 4, then the entrance of the node 1 is greater than the second entrance threshold, the exit of the node 1 is greater than the second exit threshold, and the node is determined to be the intersection node.

Step 2302: one node is determined to be a road node.

In the embodiment of the application, whether the output degree of one node is larger than a second output degree threshold value or not is judged, or whether the input degree of one node is larger than a second input degree threshold value or not is judged, if the output degree of one node is not larger than the second output degree threshold value, and the input degree of one node is not larger than the second input degree threshold value, then one node is determined to be a road node.

For example, as shown in fig. 19, assuming that the second exit threshold is 1, the second entrance threshold is 1, the exit of the node 2 is 1, and the entrance of one node is 1, the entrance of the node 2 is not greater than the second entrance threshold, the exit of the node 2 is not greater than the second exit threshold, and it is determined that the node 2 is a road node.

Step 231: and generating an intersection skeleton corresponding to the target map area based on the track groups corresponding to the intersection nodes.

In the embodiment of the application, after each intersection node is obtained, the track group corresponding to each intersection node is converted into the intersection skeleton corresponding to the target map area.

For example, referring to fig. 20, which is a schematic diagram of a road network skeleton in the embodiment of the present application, each track group corresponding to the intersection node 1 is converted into an intersection skeleton corresponding to the target map area.

Step 232: and generating a road skeleton corresponding to the target map area based on the track groups corresponding to the road nodes.

In the embodiment of the application, after each road node is obtained, the track group corresponding to each road node is converted into the road skeleton corresponding to the target map area.

For example, as shown in fig. 20, each track group corresponding to the road node 2 is converted into a road skeleton corresponding to the target map area.

Step 233: and generating a road network topological relation corresponding to the target map area based on the communication relation corresponding to the directed edges among the nodes.

In the embodiment of the application, the communication relation corresponding to the directed edges among the nodes is converted into the road network topological relation corresponding to the target map area.

Further, in the embodiment of the application, after the intersection skeleton, the road skeleton and the road network topological relation corresponding to the target map area are generated, the boundary position of the road skeleton and the intersection skeleton can be updated according to the change of the included angle information of the track data reaching different intersections at the intersections, so that a more accurate intersection boundary is obtained.

Optionally, in the embodiment of the present application, finer nodes may be generated inside the road skeleton and the intersection skeleton according to equal intervals, so as to form a new road skeleton and an intersection skeleton for output.

Based on the same inventive concept, the embodiment of the present application further provides a road network skeleton generating device, referring to fig. 21, which is a schematic structural diagram of the road network skeleton generating device in the embodiment of the present application, and specifically includes:

the acquiring module 2101 is configured to acquire each piece of track data corresponding to the target map area, where each piece of track data includes: the driving track of the corresponding vehicle in the target map area;

the grouping module 2102 is used for dividing the obtained track data into track groups and respectively converting the track groups into a corresponding node in the directed graph; the similarity between the track data contained in each track group reaches a similarity threshold;

the first processing module 2103 is used for determining a communication relation between each track group based on the running information of each track data contained in each track group and converting the communication relation between the two communicated track groups into a directed edge between two corresponding nodes in the directed graph;

the generating module 2104 is configured to obtain an intersection skeleton, a road skeleton and a road network topological relation corresponding to the target map area based on each node in the directed graph and the directed edges between each node.

Optionally, when dividing the obtained track data into track groups, the grouping module 2102 is further configured to:

the first processing module 2103 is further configured to, when determining a communication relationship between the track groups based on traveling information of each track data included in each track group:

for each track group, the following operations are performed:

Optionally, when converting the communication relationship between the two connected track groups into a directed edge between the corresponding two nodes in the directed graph, the first processing module 2103 is further configured to:

for each track group, the following operations are performed:

Optionally, after converting the communication relationship between the two connected track groups into the directed edges between the corresponding two nodes in the directed graph, the apparatus further includes a second processing module, where the second processing module 2105 is configured to:

Optionally, based on the similarity between the track groups, when merging the nodes in the directed graph to obtain new nodes, the second processing module 2105 is further configured to:

Optionally, based on each node in the directed graph and the directed edges between each node, the generating module 2104 is further configured to:

Optionally, based on the degree of departure and degree of ingress of each node in the directed graph, determining a road node and an intersection node in the directed graph, the generating module 2104 is further configured to:

Based on the above embodiments, referring to fig. 22, a schematic structural diagram of an electronic device in an embodiment of the present application is shown.

Embodiments of the present application provide an electronic device that may include a processor 2210 (Center Processing Unit, CPU), a memory 2220, an input device 2230, an output device 2240, and the like, where the input device 2230 may include a keyboard, a mouse, a touch screen, and the like, and the output device 2240 may include a display device, such as a liquid crystal display (Liquid Crystal Display, LCD), a Cathode Ray Tube (CRT), and the like.

The memory 2220 may include Read Only Memory (ROM) and Random Access Memory (RAM), and provides the processor 2210 with program instructions and data stored in the memory 2220. In the embodiment of the present application, the memory 2220 may be used to store a program of any of the road network skeleton generation methods in the embodiment of the present application.

The processor 2210 is configured to execute any of the road network skeleton generating methods according to the embodiments of the present application by calling the program instructions stored in the memory 2220, and the processor 2210 is configured to execute the obtained program instructions.

Based on the above embodiments, in the embodiments of the present application, there is provided a computer readable storage medium having stored thereon a computer program, which when executed by a processor, implements the road network skeleton generation method in any of the above method embodiments.

It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

It will be apparent to those skilled in the art that various modifications and variations can be made in the present application without departing from the spirit or scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the claims and the equivalents thereof, the present application is intended to cover such modifications and variations.

Claims

1. The road network skeleton generation method is characterized by comprising the following steps of:

determining a communication relation between the track groups based on the running information of the track data contained in the track groups, and converting the communication relation between the two communicated track groups into directed edges between the two corresponding nodes in the directed graph;

2. The method of claim 1, wherein the dividing the obtained trajectory data into trajectory groups comprises:

dividing the target map area according to a preset area dividing mode to obtain a sub-area grid set corresponding to the target map area;

Screening out each track grid from the subarea grid set, wherein each track grid comprises at least one section of track data in track data;

for each track grid, the following operations are respectively executed: clustering each segment of track data with similarity reaching a first similarity threshold value in a track grid to obtain at least one target class cluster;

3. The method according to claim 1 or 2, wherein the travel information of each piece of trajectory data includes at least: the corresponding running time of the corresponding track data;

the determining the communication relationship between the track groups based on the running information of the track data included in the track groups includes:

for each track group, the following operations are respectively executed:

4. A method according to claim 3, wherein said translating the communication relationship between two connected sets of trajectories into directed edges between corresponding two nodes in the directed graph comprises:

for each track group, the following operations are respectively executed:

taking one track group as a first track group, taking one track group which is in precursor communication with the first track group as a second track group, and converting a communication relation between the first track group and the second track group into a directed edge between two corresponding nodes in the directed graph, wherein the direction of the directed edge points to the node corresponding to the first track group from the node corresponding to the second track group;

and taking one track group as a first track group, taking one track group which is communicated with the first track group later as a third track group, and converting the communication relation between the first track group and the third track group into a directed edge between two corresponding nodes in the directed graph, wherein the direction of the directed edge points to a node corresponding to the third track group from a node corresponding to the first track group.

5. The method according to claim 1 or 2, wherein after said converting the communication relation between the two connected track groups into the directed edges between the respective two nodes in the directed graph, the method further comprises:

combining all nodes in the directed graph based on the similarity among all the track groups to obtain new all the nodes;

for each node currently contained in the directed graph, the following operations are respectively executed: if the outgoing degree of one node is greater than a first outgoing degree threshold value, or the incoming degree of the one node is greater than a first incoming degree threshold value, determining the one node as the first node, wherein the outgoing degree of the one node is the number of directed edges taking the one node as a starting point, and the incoming degree of the one node is the number of directed edges taking the one node as an ending point;

6. The method of claim 5, wherein merging nodes in the directed graph based on the similarities between the trace groups to obtain new nodes comprises:

For each track grid, the following operations are respectively executed: clustering all the track groups which are not communicated and have the similarity reaching a second similarity threshold value in one track grid and the eight adjacent track grids to obtain at least one track group cluster;

7. The method according to claim 1 or 2, wherein the obtaining, based on each node in the directed graph and the directed edges between each node, the intersection skeleton, the road skeleton, and the road network topology corresponding to the target map area includes:

determining road nodes and intersection nodes in the directed graph based on the exit and entrance degrees of the nodes in the directed graph;

8. The method of claim 7, wherein the determining the road nodes and the intersection nodes in the directed graph based on the degree of egress and ingress of each node in the directed graph comprises:

if the exit degree of one node is greater than a second exit degree threshold value, or the entrance degree of the one node is greater than the second entrance degree threshold value, determining the one node as an intersection node;

and if the output degree of one node is not greater than the second output degree threshold value and the input degree of the one node is not greater than the second input degree threshold value, determining the one node as a road node.

9. A road network skeleton generation device, characterized by comprising:

the grouping module is used for dividing the obtained track data into track groups and converting the track groups into corresponding nodes in the directed graph respectively; the similarity between the track data contained in each track group reaches a similarity threshold;

10. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the steps of the method of any of claims 1-8 when the program is executed by the processor.

11. A computer-readable storage medium having stored thereon a computer program, characterized by: the computer program implementing the steps of the method of any of claims 1-8 when executed by a processor.