CN111739323B

CN111739323B - Method and device for acquiring intersection information

Info

Publication number: CN111739323B
Application number: CN202010196216.5A
Authority: CN
Inventors: 张陈毓; 于冲; 熊伟
Original assignee: Tencent Technology Shenzhen Co Ltd
Current assignee: Tencent Technology Shenzhen Co Ltd
Priority date: 2020-03-19
Filing date: 2020-03-19
Publication date: 2022-08-12
Anticipated expiration: 2040-03-19
Also published as: CN111739323A

Abstract

The embodiment of the application provides a method and a device for acquiring intersection information, relates to the technical field of communication and maps, and is used for improving the acquisition quality of the intersection information. The method comprises the following steps: determining a target road section of the intersection, which is faced with the traffic direction in each road section outside the intersection, and each driving direction of the target road section according to road network data of the intersection; acquiring intersection information corresponding to a target travelable direction in each travelable direction of the target road section; and matching the obtained intersection information to the target road section.

Description

Method and device for acquiring intersection information

Technical Field

The embodiment of the invention relates to the technical field of computers, in particular to a method and a device for acquiring intersection information.

Background

The appearance of the electronic map brings great convenience to daily life of people. On one hand, the user can utilize the electronic map to search for travel routes, such as bus routes, subway routes, vehicle travel routes, and the like; on the other hand, the user can know other information related to the geographic position by referring to the map, for example, besides the geographic position, the user can know the products, services, contact information and the like provided by some businesses located at the corresponding geographic position in the map.

The geographic base map is the core of an electronic map, can be regarded as an electronic version of a traditional paper map, and supports functions of zooming in and out, address inquiry, path planning and the like besides map display. In the daily use process, a certain place is inquired, and the data content of the geographic base map is used for inquiring the path between two places.

A part of the geographic base map data is acquired through real acquisition, a vehicle runs along a road, a camera records road real scenes, and real scene information is acquired once for one road section. A one-way one-time acquisition strategy is generally adopted during intersection position acquisition, when the number of vehicle lanes at an intersection is large, the conditions of intersection information blurring or missing acquisition, shielding of other vehicles and the like are easy to occur, the acquired intersection information is incomplete, and the quality is low.

Disclosure of Invention

The embodiment of the application provides a method and a device for acquiring intersection information, which are used for improving the acquisition quality of the intersection information.

On one hand, the embodiment of the application provides a method for acquiring intersection information, which comprises the following steps:

determining a target road section of which the traffic direction faces to the intersection and each drivable direction of the target road section in each road section outside the intersection according to road network data of the intersection;

acquiring intersection information corresponding to a target travelable direction in each travelable direction of the target road section;

and matching the obtained intersection information to the target road section.

In one aspect, an embodiment of the present application provides an apparatus for acquiring intersection information, including:

the device comprises a determining unit and a judging unit, wherein the determining unit is used for determining a target road section of which the traffic direction faces to an intersection in each road section outside the intersection and each travelable direction of the target road section according to road network data of the intersection;

the acquisition unit is used for acquiring intersection information corresponding to a target drivable direction in each drivable direction of the target road section;

and the matching unit is used for matching the obtained intersection information to the target road section.

Optionally, the road network data includes road segment data passing through the intersection and node data of the intersection;

the determining unit is specifically configured to:

determining the passing mode of the road sections outside each intersection according to the road section data;

determining the passing direction of the road section outside the intersection according to the passing mode of the road section outside the intersection and the relationship between the end point of the road section outside the intersection and the node of the intersection;

and determining a target road section from the road section outside the intersection towards the intersection from the traffic direction.

Optionally, the passing mode of the road section outside the intersection comprises forward passing, reverse passing or bidirectional passing; the determining unit is specifically configured to:

for any road section outside the intersection, if the passing mode of the road section outside the intersection is forward passing, determining the terminal point of the road section outside the intersection; when the terminal point of the road section outside the intersection is determined to be the node of the intersection according to the node data of the intersection, determining that the passing direction of the road section outside the intersection faces the intersection;

if the passing mode of the road section outside the intersection is reverse passing, determining the starting point of the road section outside the intersection; when the starting point of the road section outside the intersection is determined to be the node of the intersection according to the node data of the intersection, determining that the passing direction of the road section outside the intersection faces the intersection;

and if the passing mode of the road sections outside the intersection is determined to be bidirectional passing or the passing mode of the road sections outside the intersection in the road network data is not determined, determining that the passing direction of the road sections outside the intersection faces the intersection.

Optionally, the determining unit is further configured to:

establishing a road section communication relation of the target road section according to a passing direction, wherein one road section communication relation comprises the communication relation among the target road section, N road sections in the road openings and the exit road section of the target road section, and N is an integer greater than or equal to 0; the exit road section is an outer road section of the intersection with the passing direction back to the intersection;

and determining the travelable direction of the target road section according to the road section communication relation, wherein one road section communication relation corresponds to one travelable direction.

Optionally, the determining unit is further configured to:

determining a turning road section of the target road section, and taking an intersection outer road section with a passing direction back to the intersection except the turning road section as an exit section to be selected of the target road section, wherein the turning road section is an intersection outer road section with the passing direction parallel to and opposite to that of the target road section;

taking an exit road section to be selected, which is in passable connectivity with the target road section, as an exit road section of the target road section;

for each exit road section of the target road section, determining N intra-road section between the target road section and the exit road section;

and establishing a road section communication relation among the target road section, the N road sections in the road openings and the outlet road section.

Optionally, the direction of travel of the target road segment includes a left-turn direction, a straight-going direction, or a right-turn direction; the intersection information is vehicle acquisition information;

the obtaining unit is specifically configured to:

determining a target road section, an exit road section and an intersection inner road section which are contained in a target road section communication relation corresponding to the target travelable direction;

determining a vehicle running track corresponding to the target road section communication relation;

determining vehicle acquisition information corresponding to the vehicle running track from the acquired information;

and respectively matching the corresponding vehicle acquisition information with the target road section, the exit road section and the road section in the intersection.

Optionally, the determining unit is further configured to:

determining the number of lanes contained in the road section outside each intersection;

and taking the road sections outside the intersection with the number of lanes greater than or equal to the lane threshold value as the target road sections.

In one aspect, an embodiment of the present application provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and capable of running on the processor, where the processor implements any of the steps of the intersection information acquisition method when executing the computer program.

In one aspect, the present application provides a computer-readable storage medium, which stores a computer program executable by a computer device, and when the program runs on the computer device, the computer device is caused to execute the steps of any one of the above-mentioned intersection information acquisition methods.

According to the method for acquiring the intersection information, the passing direction of the road sections outside each intersection of the intersection is determined according to the road network data of the intersection. And determining a target road section from the road sections outside the intersection towards the intersection from the passing direction, and determining each driving direction of the target road section. Intersection information corresponding to a target travelable direction among the respective travelable directions of the target section may be acquired corresponding to the target section, and the acquired intersection information may be matched to the target section. Generally, the target link includes a plurality of directions to be traveled, and corresponding intersection information can be obtained for each direction to be traveled. Therefore, for the target road section, the times of acquiring the intersection information correspond to the number of the travelable directions, namely the intersection information is acquired for multiple times, and the multiple acquisition of the intersection information is realized. Further, when the vehicle travels on a road section outside the intersection, a lane is generally selected or a travel position in the road section outside the intersection is selected according to the travel direction of the vehicle at the intersection. Therefore, the intersection information corresponds to the travelable direction, and is acquired through the vehicle routes in different directions, so that the acquisition range is larger, the whole target road section is more effectively covered, the problem of intersection information blurring or missing acquisition caused by vehicle shielding in the primary acquisition process is avoided, the integrity of the intersection information is improved, and the quality of the intersection information is improved.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise.

Fig. 1 is a schematic diagram of a road network according to an embodiment of the present disclosure;

fig. 2 is a schematic view of an intersection according to an embodiment of the present application;

fig. 3 is a schematic diagram illustrating comparison of acquisition quality of one-way one-time acquisition corresponding to different lane numbers according to an embodiment of the present application;

fig. 4 is a schematic diagram of an acquisition system architecture of intersection information according to an embodiment of the present application;

fig. 5 is a schematic flowchart of a method for acquiring intersection information according to an embodiment of the present application;

FIG. 6 is a schematic lane view of a target road segment according to an embodiment of the present disclosure;

fig. 7 is a schematic diagram of a junction according to an embodiment of the present application;

fig. 8 is a schematic diagram of a five-way intersection provided in the present application;

fig. 9 is a schematic diagram of an architecture of a system for collecting intersection information according to an embodiment of the present application;

fig. 10 is a schematic diagram of an intersection information acquisition device according to an embodiment of the present application;

fig. 11 is a schematic structural diagram of a computer device according to an embodiment of the present application.

Detailed Description

In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

For convenience of understanding, terms referred to in the embodiments of the present application are explained below:

an electronic map: i.e., digital maps, are maps that are stored and referred to digitally using computer technology. The method for storing information in electronic map generally uses vector image storage, and the map scale can be enlarged, reduced or rotated without affecting the display effect.

Road: the motor vehicles can pass through the passage between two adjacent intersections, and the roads can have a single passing direction or two opposite passing directions, such as roads 1-11 shown in fig. 1, wherein the arrow in fig. 1 indicates the passing direction of each road. A road may consist of one or more lanes.

Road section: (link) in the electronic map, the route is expressed by a sequence of links. In the map data, a road is divided into segments of several tens of meters to several kilometers in length, each segment is called a link, and is given a globally unique ID. Thus, a route in the map is a sequence of all segments in the route. The road with two opposite passing directions in the embodiment of the application comprises two road sections, and each road section corresponds to one passing direction.

Lane: the partitioned areas in the roadway on which a single longitudinal vehicle travels, such as lanes 1-8 in fig. 5.

And (4) crossing: connecting the areas of different roads. As shown in fig. 1, taking intersection 1 as an example, intersection 1 is connected with lanes 1-4.

And (3) node: end points of road segments or points representing connection relationships between road segments. As shown in fig. 2, points N1, N2, N3, N4 are intersection nodes of intersection 1.

Road section in the road junction: the segments between the intersection nodes. As shown in fig. 2, v, x, y, z are the intra-road segment.

The road section outside the intersection: in the section between two intersections, as shown in fig. 2, a, b, c, d, e, f, g, and h are the sections outside the intersection, and the sections outside the intersection include an entrance section and an exit section.

An inlet road section: for an intersection, a road segment entering the intersection; for example, as shown in fig. 2, the segments a, c, e, g are entry segments with respect to the intersection 1.

Exit section: for a road junction, the road junction is a road section which drives out of the road junction; for example, as shown in fig. 2, the segments b, d, f, h are exit segments with respect to the intersection 1.

And (3) intersection information: in a commercial electronic map, a part of road drawing depends on real acquisition, the real acquisition does not refer to measurement acquisition in mapping, but needs to be driven on the spot to run along the road, a camera is used for recording road real scenes, speed limit signs, guideboards and the like are mainly shot, and then editing is carried out, and the running position information is recorded by depending on a GPS. The intersection information in the embodiment of the application is the information acquired at the intersection position. The intersection information comprises vehicle information, traffic restriction information and the like, and the lane information comprises information such as a plurality of lanes on the current road section, the position of a left-turn lane, the number of lanes on a straight-going lane and the like; traffic restriction information such as traffic sign information of speed limit boards, no-go signs, etc.

In the specific practice process, the geographic base map data of the electronic map mainly includes roads, POIs (points of interest, commercial maps mainly collect things related to the life information of people such as restaurants, hotels, gas stations and washrooms), administrative regions, rivers, greenbelts, residential areas and the like. In the commercial map, roads support path planning and POI support address searching, and the two parts are the key points of the commercial map. The road data is partially acquired by real, and partially sketched by using remote sensing images, wherein the real acquisition does not refer to measurement acquisition in mapping, but needs to be driven on the spot to run along the road, road real scenes are recorded by a camera, speed limit signs, guideboards and the like are mainly shot, and then the road data is edited and the running position information is recorded by depending on a GPS. POI data also depends on real-time acquisition, and the data in the part is updated faster and in large quantity, and a crowd-sourced acquisition mode is more promising.

One-way one-time acquisition is adopted when information acquisition is carried out at the intersection, and straight-going acquisition is generally carried out, namely, a vehicle runs along a straight-going lane to shoot an intersection live-action. One-way one-time acquisition has the following problems: when the intersection is wide, intersection information at a position far away from the camera equipment is not easy to be shot, and the conditions of fuzzy shooting, incomplete acquisition or missed acquisition can occur; the number of lanes at the intersection is large, and other vehicles easily shield the acquisition vehicle, so that information acquisition is influenced.

Fig. 3 shows the acquisition quality of a one-way one-time acquisition for different lane numbers. As shown in fig. 3, the intersection information collection quality reaches 94.87% in both lanes, but the intersection information collection quality decreases straight as the number of lanes increases. The intersection information acquisition quality is 81.43% in the case of three lanes and 71.76% in the case of four lanes. The total intersection information acquisition quality is 79.90%. The specific influence is mainly caused by the fact that the vehicle shelters elements or the elements with too far distance cause blurring, the proportion of the elements with too far distance is rapidly increased along with the increase of the number of lanes, and meanwhile, the influence of the vehicle shelters is also increased linearly.

Based on the above problems, embodiments of the present application provide a method for acquiring intersection information, which issues acquisition tasks corresponding to each direction according to different driving directions of a target road segment of an intersection, for example, issues acquisition tasks of left turn, straight run, and right turn for the same target road segment, thereby realizing multiple acquisition or matching of intersection information, and also relates to vehicle driving routes in different driving directions, so that the acquisition range is wider, the whole target road segment can be covered, and the quality of intersection information acquired at one time can be improved.

Some brief descriptions are given below to application scenarios to which the technical solution of the embodiment of the present application can be applied, and it should be noted that the application scenarios described below are only used for describing the embodiment of the present application and are not limited. In specific implementation, the technical scheme provided by the embodiment of the application can be flexibly applied according to actual needs.

To further illustrate the technical solutions provided by the embodiments of the present application, the following detailed description is made with reference to the accompanying drawings and the detailed description. Although the embodiments of the present application provide method operation steps as shown in the following embodiments or figures, more or fewer operation steps may be included in the methods based on conventional or non-inventive efforts. In steps where no necessary causal relationship exists logically, the order of execution of the steps is not limited to that provided by the embodiments of the present application.

Fig. 4 is a schematic diagram of a driving route selection system according to an embodiment of the present disclosure. The system comprises at least one vehicle 401, an acquisition device 402, a data processing device 403.

The collection device 402 may be a mobile terminal device such as a mobile phone, a Personal Computer (PC), a tablet computer (PAD), a Personal Digital Assistant (PDA), a notebook computer, an intelligent wearable device (e.g., an intelligent watch and an intelligent bracelet), or a car navigator. The sensors in the collecting device 402 can collect longitude and latitude coordinate data of ground objects in a map coordinate system, such as lane separation lines, road separation lines, stop lines, road surface marks (such as turning marks of the road surface), rising marks (such as speed limit and prohibition information), isolation belts, guard rails, traffic lights and the like, in a real road by sensing the environment of the real ground objects. The sensors may include one or more of a lidar, a millimeter wave radar, a camera, a Global Navigation Satellite System (GNSS), and an Inertial Measurement Unit (IMU). The sensor can be configured on a mobile terminal device such as a motor vehicle, a mobile phone, and the like, and the acquisition device 402 in the embodiment of the present application can be configured on a vehicle 401 for acquiring intersection information, for example, the acquisition device 402 is a vehicle data recorder on the vehicle; the capture device 402 may also be a user handheld device, with the user capturing in a vehicle. The data collected by the collection device 402 may be stored in different databases, such as a radar database and a picture database, according to the data type.

The data processing device 403 includes, but is not limited to, an electronic device such as a desktop computer, a mobile phone, a mobile computer, a tablet computer, and the like, and may include a server, which may be a server cluster or a single server. The server 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 basic cloud computing services such as cloud service, a cloud database, cloud computing, a cloud function, cloud storage, network service, cloud communication, middleware service, domain name service, security service, CDN, and a big data and artificial intelligence platform.

The data processing device 403 may also be a cloud computing module, which is a computing model that distributes computing tasks over a large pool of computers, enabling various application systems to obtain computing power, storage space, and information services as needed. The network that provides the resources is referred to as the "cloud". Resources in the "cloud" appear to the user as being infinitely expandable and available at any time, available on demand, expandable at any time, and paid for on-demand.

The data processing device 403 acquires the intersection data acquired by the acquisition device 402, and matches the intersection data to the corresponding target road segment. The acquisition device 402 can directly transmit the intersection data to the data processing device 403, the acquisition device 402 can also store the intersection information into a database, and the data processing device 403 can obtain the intersection information from the database.

In an alternative embodiment, a database may be provided, and the database may be used to store road network data and intersection information, such as positioning data of each vehicle, position data of lanes, and the like. The database can be a cloud database, which refers to a storage system that integrates a large number of storage devices (storage devices are also called storage nodes) of different types in a network through application software or application interfaces to cooperatively work through functions such as cluster application, grid technology, distributed storage file system and the like, and provides data storage and service access functions to the outside. In this embodiment, the data processing device 403 may access the cloud database through an access structure of the cloud database.

Acquisition device 402 and data processing device 403 may be communicatively coupled via one or more networks. The network may be a wired network or a Wireless network, for example, the Wireless network may be a mobile cellular network, or may be a Wireless-Fidelity (WIFI) network, or may also be other possible networks, which is not limited in this embodiment of the present invention.

In an alternative embodiment, the acquisition device 402 and the data processing device 403 may be connected via a car networking, for example, via bluetooth technology, and the wireless technology connects the acquisition device 402 and the data processing device 403 to the car networking for data interaction.

In an alternative embodiment, the collecting devices 402 in the plurality of vehicles respectively collect intersection information of different target road sections and store the intersection information in the database. The database also stores road network data. The data processing device 403 acquires road network data from the database, determines a target road segment and each drivable direction of the target road segment based on the road network data, then acquires intersection information corresponding to each drivable direction of the target road segment from the database, and matches the intersection information to the corresponding target road segment.

In another alternative embodiment, the data processing device 403 obtains road network data from a database, and determines the target road segment and each drivable direction of the target road segment according to the road network data. The data processing device 403 generates multiple collection tasks for the intersection according to the intersection-external road segments included in the intersection and multiple drivable directions of each intersection-external road segment, and issues the collection tasks to the task library, where each collection task corresponds to one drivable direction of one target road segment. The acquisition device 402 acquires the acquisition task from the task library, acquires intersection information of the target road section according to the requirement of the acquisition task, and sends the intersection information to the data processing device 403. The data processing device 403 adsorbs the intersection information to the corresponding target road segments, and if all the target road segments are successfully adsorbed and the collected information is determined to be valid, the collection task is determined to be qualified.

Of course, the method provided in the embodiment of the present application is not limited to be used in the application scenario shown in fig. 1, and may also be used in other possible application scenarios, and the embodiment of the present application is not limited. The functions that can be implemented by each device in the application scenario shown in fig. 1 will be described in the following method embodiments, and will not be described in detail herein.

To further illustrate the technical solutions provided by the embodiments of the present application, the following detailed description is made with reference to the accompanying drawings and the detailed description. Although the embodiments of the present application provide the method operation steps as shown in the following embodiments or figures, more or less operation steps may be included in the method based on the conventional or non-inventive labor. In steps where no necessary causal relationship exists logically, the order of execution of the steps is not limited to that provided by the embodiments of the present application.

The following describes the technical solution provided in the embodiment of the present application with reference to the application scenario shown in fig. 4.

Referring to fig. 5, an embodiment of the present application provides a method for acquiring intersection information, including the following steps:

step 501, according to road network data of the intersection, determining a target road section of the intersection, in which the traffic direction faces the intersection, in each road section outside the intersection, and each drivable direction of the target road section.

Generally, a road network is divided into a road section area and an intersection area, the intersection area includes an outer intersection road section and an inner intersection road section, the outer intersection road section includes an inlet road section and an outlet road section, wherein the inlet road section is a road section facing the intersection in a passing direction, and the outlet road section is a road section facing away from the intersection in the passing direction.

In a real intersection, in order to facilitate passing, generally speaking, the width of an entrance road section of an intersection region is wider, and the problem of lower intersection information acquisition quality caused by wider road surface or more lanes is more likely to occur. Therefore, the embodiment of the application mainly takes the inlet road section as the target road section.

On the other hand, since a vehicle enters the intersection through the entrance section, it is general to select a lane according to the driving direction of the vehicle at the intersection, or to select a driving position in a section outside the intersection, for example, if the driving direction of the vehicle is a left turn, the vehicle is general to select a position of the entrance section near the left side for driving. Therefore, the embodiment of the application also needs to determine each travelable direction of the target road segment.

Step 502, intersection information corresponding to the target travelable direction in each travelable direction of the target road segment is obtained.

The intersection information comprises lane information, traffic restriction information and the like, wherein the lane information comprises information such as a plurality of lanes on a current road section, positions of left-turn lanes, a plurality of lanes of a straight lane and the like; traffic restriction information such as traffic sign information of speed limit boards, no-go signs, etc.

In the specific implementation process, the intersection information corresponds to each driving direction of the target road section, so that the intersection information corresponding to different driving directions is different. For example, when the drivable direction is a right turn, the intersection information is mainly information that the entrance road section is close to the right side; when the driving direction is straight, the intersection information is mainly the information of the middle position of the entrance road section.

And step 503, matching the obtained intersection information to the target road section.

According to the method for acquiring the intersection information, the passing direction of the road sections outside each intersection of the intersection is determined according to the road network data of the intersection. And determining a target road section from the road sections outside the intersection towards the intersection from the passing direction, and determining each driving direction of the target road section. Intersection information corresponding to a target travelable direction among the respective travelable directions of the target section may be acquired corresponding to the target section, and the acquired intersection information may be matched to the target section. Generally, the target link includes a plurality of travelable directions, and corresponding intersection information can be acquired for each travelable direction. Therefore, for the target road section, the obtained times of the intersection information correspond to the number of the travelable directions, namely the intersection information is obtained for multiple times, and the multiple collection of the intersection information is realized. Further, when the vehicle travels on a road section outside the intersection, a lane is generally selected or a travel position in the road section outside the intersection is selected according to the travel direction of the vehicle at the intersection. Therefore, the intersection information corresponds to the driving direction, and is acquired through the vehicle driving routes in different directions, so that the acquisition range is larger, the whole target road section is more effectively covered, the intersection information is prevented from being fuzzy or missed due to vehicle shielding in the primary acquisition process, the integrity of the intersection information is improved, and the quality of the intersection information is improved.

In an alternative embodiment, any one of the inlet road sections of the intersection may be used as a target road section, the travelable direction of the target road section is determined, corresponding intersection information is determined according to each travelable direction, and the obtained intersection information is matched to the target road section.

In another alternative embodiment, each entrance road segment of the intersection may also be used as a target road segment, and the intersection information acquisition process is executed, so that the intersection information is matched to the road segment corresponding to the intersection.

For a certain intersection, the road network data includes road data passing through the intersection and node data of the intersection. In general, the link data includes the type of a link (i.e., the link is an outside-intersection link or an inside-intersection link), the direction of passage of the link, the start position of the link, the end position of the link, and the like. The node data includes the positions of the nodes of the intersection, and the like.

On one hand, the passing direction of the road sections outside each intersection is determined according to the road network data, and then the target road section is determined. Generally, in order to facilitate passing, the width of an entrance road section of an intersection area is wider, and the problem of lower intersection information acquisition quality caused by wider road surface or more lanes is more likely to occur. Therefore, the embodiment of the application mainly takes the inlet road section as the target road section.

On the other hand, the embodiment of the application also determines the travelable direction of the target road segment according to the road network data. When a vehicle enters the intersection through the entrance road section, a lane of the entrance road section is generally selected or a driving position in the entrance road section is selected according to the driving direction of the vehicle at the intersection, so that the positions of the vehicle in the entrance road section are different corresponding to different driving directions of the target road section, and the intersection information acquired by the vehicle is different. Crossing information at different positions is matched to a target road section, so that the whole road can be better covered, and the acquisition quality of the crossing information is improved.

How to determine the target road segment and the direction in which the target road segment can travel is described in detail below.

In the embodiment of the application, the entrance road section is taken as the target road section, and the entrance road section is the road section outside the intersection with the passing direction facing the intersection. In an alternative embodiment, the passing direction of the road section outside the intersection can be determined according to the passing mode of the road section outside the intersection and the relation between the end point of the road section outside the intersection and the intersection node.

Specifically, a target road section of the intersection, of which the traffic direction faces to the intersection, in each road section outside the intersection is determined by the following method:

Wherein the end points of the road segment comprise a start point and an end point. The passing mode of the road section indicates the relation between the passing direction of the road section and the end point of the road section. The passing mode of the road section comprises forward passing, reverse passing or bidirectional passing, wherein the passing mode of the road section is forward passing, and the passing direction of the road section is from the starting point to the end point of the road section. If the passing mode of the road section is reverse passing, the passing direction of the road section is indicated to point to the starting point from the end point of the road section.

In general, the road network data includes identification data and description information of a route pattern of a link. For example, the direction indicates the traffic pattern of the link, and the value of the direction is used to identify different traffic patterns. Specifically, when the passing mode of the road section is bidirectional passing, the direction is 1; when the passing mode of the road section is forward passing, the direction is 2; when the passing mode of the road section is reverse passing, the direction is 3; when the passing mode of the road sections in the road network data is uncertain, the direction is 0. Therefore, the passing mode of the road section outside the intersection can be directly determined according to the road section data. For example, in the implementation process, if the direction value is determined to be 2, it indicates that the passing mode of the corresponding road section is forward passing.

And determining the passing directions of all road sections outside the intersection according to the road section data and the node data, determining an entrance road section with the passing direction facing the intersection from the passing directions, and determining a target road section from the entrance road section. Further, for the road sections outside the intersection with different passing modes, the mode of determining the passing direction of the road sections is different in the embodiment of the present application, and the following description is provided respectively.

And judging the passing mode of the road section outside the intersection according to the road section data aiming at the road section outside any intersection.

If the passing mode of the road section outside the intersection is forward passing, determining the terminal point of the road section outside the intersection;

and when the terminal point of the road section outside the intersection is determined to be the node of the intersection according to the node data of the intersection, determining the passing direction of the road section outside the intersection as the direction of the intersection.

In a specific implementation process, the road section data includes position data of a starting point and an ending point of the road section. Generally, the starting point and the end point of the link are associated with the passing direction of the link, and in the case where the passing manner of the link is forward passing, the passing direction of the link is directed from the starting point of the link to the end point of the link. Therefore, the passing direction of the link can be determined by determining whether the start point or the end point of the link is a node of the intersection.

Specifically, whether the end point of the road section outside the intersection is the node of the intersection can be judged according to the node data of the intersection. If so, determining that the passing direction of the road section outside the intersection faces the intersection, wherein the road section outside the intersection is an entrance road section of the intersection; if not, the passing direction of the road section outside the intersection is considered to be opposite to the intersection, and the road section outside the intersection is the exit road section of the intersection. Therefore, when the end point of the road section outside the intersection is the node of the intersection, the road section outside the intersection can be used as the target road section.

In a special case, the direction of travel of the road section may also be opposite to the direction from the starting point to the end point of the road section, in which case the direction of travel of the road section is directed from the end point of the road section to the starting point of the road section, and in the present embodiment, the route of such a road section is considered to be in a reverse direction.

Considering the situation that the road section outside the intersection is reverse traffic, determining the traffic direction of the road section outside the intersection according to the traffic mode of the road section outside the intersection and the relation between the end point of the road section outside the intersection and the node of the intersection, and further comprising the following steps:

if the passing mode of the road section outside the intersection is reverse passing, determining the starting point of the road section outside the intersection;

and when the starting point of the road section outside the intersection is determined to be the node of the intersection according to the node data of the intersection, determining that the passing direction of the road section outside the intersection faces the intersection.

In the specific implementation process, before determining the end point of the road section outside the intersection, the passing mode of the road section outside the intersection needs to be judged, if the passing mode is reverse passing, the direction that the starting point of the road section outside the intersection points to the end point is opposite to the passing direction of the road section, and therefore the mode of determining whether the road section outside the intersection is an entrance road section is opposite to the mode of determining whether the road section outside the intersection is a forward passing road section. Specifically, whether the starting point of the road section outside the intersection is the node of the intersection is judged. If so, determining that the passing direction of the road section outside the intersection faces the intersection, wherein the road section outside the intersection is an entrance road section of the intersection; if not, the passing direction of the road section outside the intersection is considered to be opposite to the intersection, and the road section outside the intersection is the exit road section of the intersection. Therefore, when the traffic mode of the road section outside the intersection is reverse traffic and the starting point is the node of the intersection, the road section outside the intersection can be used as the target road section.

In another special case, the road section may also be a two-way traffic, or the road network data does not include the road section, in which case, to avoid data omission, the road section is used as both the entrance road section and the exit road section of the intersection. Therefore, when the passing mode of the road section outside the intersection is bidirectional passing or the passing mode of the road section outside the intersection in the road network data is not determined, the passing direction of the road section outside the intersection is determined to be towards the intersection.

In the embodiment of the application, whether each road section outside the intersection is an inlet road section or an outlet road section is distinguished according to the passing mode of the road sections outside the intersection. And determining each driving direction of the target road section by taking the inlet road section as the target road section.

In an alternative embodiment, the direction of travel of the inlet section may be determined according to the communication relationship between the inlet section and the outlet section. The determining each travelable direction of the target road section according to the road network data of the intersection comprises the following steps:

establishing a road section communication relation of a target road section according to a passing direction, wherein one road section communication relation comprises the communication relation among the target road section, N road sections in the road openings and the outlet road section of the target road section, and N is an integer greater than or equal to 0; the exit road section is an outer road section of the intersection with the passing direction back to the intersection;

and determining the drivable directions of the target road sections according to the road section communication relations, wherein one road section communication relation corresponds to one drivable direction.

In the specific implementation process, all the intersection external road sections of the intersection are divided into an exit road section or an entrance road section according to the process. And aiming at each inlet road section, a connection relation can be established with any outlet road section. In some connection relations, the inlet road section can be directly communicated with the outlet road section, and at the moment, the road section communication relation does not need to include the road section in the road section; in some connection relations, the inlet road section cannot be directly communicated with the outlet road section, so that the road section communication relation also needs to comprise one or more road sections in the road.

For a link connectivity, a direction of travel of the target link may be determined. One possible driving direction of the target road section corresponds to one acquisition of the intersection information. Therefore, one target road section can correspond to multiple times of intersection information acquisition and different driving directions, and the driving positions of vehicles on the target road section are different, so that the range of the multiple times of intersection information acquisition can completely cover the target road section, and the quality and the integrity of the acquired information are greatly improved.

Further, if the target road section is each entrance road section of the intersection, the range of the multiple intersection information acquisition covers the range of the whole intersection. Compared with the method and the device for acquiring the intersection information only in the straight-going direction, the intersection information acquired in the embodiment of the application is wider in range and higher in quality.

The intersection in fig. 2 is taken as an example for explanation. As shown in fig. 2, the intersection 1 includes 4 intersection internal sections, 4 entrance sections and 4 exit sections, i.e., v, x, y and z, entrance sections a, c, e and g, and exit sections b, d, f and h. If the road section a is the target road section, the road section a may form an association relationship with all exit road sections, which are a- > b, a- > d, a- > f and a- > h, respectively. The other inlet sections c, e and g can also form corresponding association relations respectively. For a-d, a-f and a-h in the association relationship, the inlet section a cannot be directly communicated with the outlet section, so the section communication relationship also needs to include the section inside the road.

For example, for the association relationship a- > d, an intra-road section x is also required between the inlet road section a and the outlet road section d to form the communication of the road sections, so the corresponding road section communication relationship is a- > x- > d. For the association relation a- > f, the road sections x and y in the intersection are also needed between the inlet road section a and the outlet road section f to form the communication of the road sections, so the corresponding road section communication relation is a- > x- > y- > f. For the association relation a- > h, the road sections x, y and z in the intersection are needed between the inlet road section a and the outlet road section h to form the communication of the road sections, so the corresponding road section communication relation is a- > x- > y- > z- > h. In summary, the connection relations of the road sections corresponding to the intersection 1 are a- > b, a- > x- > d, a- > x- > y- > f, a- > x- > y- > z- > h. Correspondingly, the number N of road sections in the road section included in the road section communication relation is respectively 0, 1, 2 and 3.

The above-mentioned one link communication relationship corresponds to one travelable direction of the entrance link a. For example, the road section connectivity relationship a- > b corresponds to a right turn direction, the road section connectivity relationship a- > x- > d corresponds to a straight direction, the road section connectivity relationship a- > x- > y- > f corresponds to a left turn direction, and the road section connectivity relationship a- > x- > y- > z- > h corresponds to a turn direction.

The following describes a link connectivity establishment procedure for a target link.

Firstly, determining a turning road section of a target road section, and taking an off-road section with a passing direction opposite to an intersection except the turning road section as an exit section to be selected of the target road section, wherein the turning road section is the off-road section with the passing direction parallel to and opposite to the passing direction of the target road section.

Specifically, the off-intersection road segment, which has a traffic direction parallel to and opposite to the traffic direction of the target road segment, is a u-turn road segment of the target road segment, and the u-turn road segment corresponds to the u-turn direction of the target road segment. Generally, if the driving direction of the vehicle is a turning direction, the driving position of the vehicle at the target link coincides with the left-turn direction of the target link.

Fig. 6 shows a lane diagram of a target road segment. As shown in fig. 6, the lane corresponding to the left turn direction in the target link is lane 1, and the lane corresponding to the turn around direction is also lane 1.

Furthermore, the turning direction corresponds to the intersection inner road section of the intersection, and is also overlapped with the intersection inner road section corresponding to the straight direction and the left-turning direction. Therefore, in order to avoid repeated data acquisition, the intersection outer road section in the turning direction is deleted, and the intersection outer road sections with the other passing directions back to the intersection are used as the candidate exit road sections of the target road section.

Still taking fig. 2 as an example, that is, in all the road sections outside the intersection, the road section h is an exit road section of the target road section a corresponding to the u-turn direction, in all the association relations, a- > h is deleted, and the rest of the association relations of the target road section a are retained, so that the road sections b, d, and f are taken as the exit road sections to be selected of the target road section a.

And secondly, taking the exit road section to be selected, which has the communication with the target road section as a passable exit road section of the target road section.

Specifically, the connectivity between the exit road segment and the target road segment is also recorded in the road network data. In an alternative embodiment, the connectivity between the exit road segment and the target road segment may be identified using different numbers or letters, etc. For example, 1 indicates the connectivity as passable, and 0 indicates the connectivity as unviewable.

It is necessary to ensure communication between the target section to the exit section, i.e., the traveling direction is not prohibited. Still taking fig. 2 as an example, if the target road segment a is set to be not right-turnable, the association relationship a- > b is not passable, that is, the association relationship between the to-be-selected exit road segment b and the target road segment a is deleted, and the exit road segment of the target road segment a includes road segments d and f.

And thirdly, determining N intra-road-section road sections between the target road section and the exit road section aiming at each exit road section of the target road section.

For example, for target road segment a and exit road segment d, 1 intra-intersection road segment, i.e., road segment x, is determined. For target road segment a and exit road segment f, 2 intra-road segments, i.e., road segment x and road segment y, are determined.

And finally, establishing a road section communication relation among the target road section, the N road sections in the road openings and the outlet road section. And then the target road section is passed through the target road section, the N road sections in the crossroads are passed through the target road section, and the target road section is passed through the outlet road section, so that the road section communication relation of the target road section is formed. For example, in the above process, for the target segment a, a- > x- > d, a- > x- > y- > f may be formed, and the two segments are in a connected relationship.

Furthermore, the intersection information is vehicle acquisition information, and the vehicle acquisition information is not only matched with the target road section, but also matched with the corresponding intersection internal road section and the corresponding intersection outlet road section. For a typical intersection, the direction of travel of the target road segment typically includes a left turn direction, a straight direction, or a right turn direction. The method for acquiring intersection information corresponding to the target travelable direction in each travelable direction of the target road segment comprises the following steps:

determining a vehicle running track corresponding to the communication relation with the target road section;

determining vehicle acquisition information corresponding to a vehicle running track from the acquired information;

and matching the corresponding vehicle acquisition information with the target road section, the exit road section and the road section in the intersection respectively.

In the specific implementation process, the corresponding vehicle running track can be determined according to the target road section, the exit road section and the road section in the intersection which are contained in the road section communication relation of the target road section. The road section communication relation can be determined firstly, the vehicle runs according to the specific road section in the road section communication relation to obtain the vehicle running track, and then the vehicle running track and the specific road section are directly corresponding to each other.

The vehicle can also acquire intersection information of different intersections in advance, obtain vehicle running tracks when the vehicle runs, store all the vehicle running tracks in the database, and match corresponding vehicle running tracks from the database after determining the connection relation of the target road sections. The target road section communication relation and the vehicle running track can be matched according to a road adsorption algorithm, and the specific road adsorption algorithm is not repeated here.

The intersections in the above embodiments are intersections. For other types of intersections, the intersection information acquisition mode of the embodiment of the application is also applicable. For example, with the three-way intersection 5 shown in fig. 7, in a case where it is confirmed that the connectivity between the target link p and the exit link is both passable, two travelable directions as shown by the broken lines in the figure may be established for the target link p. For another example, in the case where it is confirmed that the connectivity between the target link q and the exit link is passable at the five-branch road junction 6 shown in fig. 8, 4 travelable directions as shown by the broken lines in the figure can be established for the target link q.

Further, the problem of high acquisition cost occurs when the number of lanes is small and the acquisition frequency is too many, and therefore, the acquisition cost and the acquisition quality of intersection information acquisition need to be balanced. The embodiment of the application further comprises:

determining the number of lanes contained in each road section outside each intersection;

and taking the road sections outside the intersection with the number of lanes greater than or equal to the lane threshold value as target road sections.

Specifically, table 1 shows the evaluation results of cost increase and quality improvement when multiple acquisitions are performed at a multi-lane intersection in a certain city.

TABLE 1

Acquisition strategy	Increase in cost	Mass enhancement
			The number of lanes is more than or equal to 2, and multiple collection is carried out	12.83％	15.08％
The number of lanes is more than or equal to 3 for multiple collection	3.65％	14.30％
			The number of lanes is more than or equal to 4 for multiple collection	0.71％	9.28％

As can be seen from Table 1, the cost of multiple acquisitions when the number of lanes is equal to or greater than 3 is reduced by 9.18% compared to the number of lanes equal to or greater than 2, but the quality is reduced by less than 1%. And compared with the number of the lanes being more than or equal to 4, the number of the lanes being more than or equal to 3, the cost is increased by 2.94%, and the quality is improved by 5.02%. Therefore, when the number of lanes is more than or equal to 3, the multiple-time acquisition strategy of the road junction is relatively reasonable, namely the lane threshold value can be set to 3.

Table 2 shows the comparison of the acquisition quality and cost of intersection information acquisition with different acquisition times and possible driving directions.

TABLE 2

Acquisition strategy	Collection quality (%)	Cost increase (%)	Mass gain (%)
				Unidirectional acquisition	76.13％
Two-way collection	83.19％	1.17％	7.06％
				Multi-directional acquisition	89.93％	2.33％	13.80％

As can be seen from Table 2, compared with the unidirectional collection, the cost is increased by 1.17% and the quality is improved by 7.06% when the unidirectional collection is carried out in two directions. Compared with unidirectional acquisition, the cost is increased by 2.33% and the quality is improved by 13.8% during multidirectional acquisition. In the intersection acquisition strategy implemented by the application, the acquisition times are determined according to the direction of the passable road, and the acquisition times of most intersections are 2-3.

According to the method for acquiring the intersection information, the intersection information corresponds to the driving direction and is acquired through the vehicle driving routes in different directions, so that the acquisition range is larger, the whole target road section is more effectively covered, the problem that the intersection information is fuzzy or missed due to vehicle shielding in the primary acquisition process is avoided, the integrity of the intersection information is improved, and the quality of the intersection information is improved.

For better explaining the embodiment of the present application, the method for acquiring intersection information provided by the embodiment of the present application is described below with reference to a specific implementation scenario, in the method of the embodiment of the present application, an intersection is an intersection as shown in fig. 2. The specific process is shown in fig. 9, and includes:

step 901, obtaining road network data of the intersection, and determining an intersection outer road section of the intersection according to the road network data.

Step 902, traversing each intersection external road section of the crossroads, judging the passing mode of the intersection external road section, and if the passing mode is forward passing, executing step 903; if the passing mode is reverse passing, go to step 904; if the passing mode is bidirectional passing or the passing mode cannot be determined, step 905 is executed and step 906 is executed.

Step 903, judging whether the end point of the road section outside the intersection is a node of the intersection, if so, executing step 905; otherwise, step 906 is performed.

Step 904, judging whether the starting point of the road section outside the intersection is the node of the intersection, if so, executing step 905; otherwise, step 906 is performed.

And step 905, taking the road section outside the intersection as an entrance road section.

And step 906, taking the road section outside the intersection as an exit road section.

Step 907, determining the number of lanes contained in the inlet road section, and taking any inlet road section with the number of lanes larger than the lane threshold value as a target road section.

Step 908, traverse each exit segment, delete the exit segment for the target segment in the turn around direction.

In step 909, the exit road segment with the connectivity as no-pass with the target road segment is deleted.

Step 910, determining an intersection internal road section between the target road section and the exit road section, and establishing a road section communication relationship.

And step 911, determining a vehicle running track corresponding to the communication relation of each road section, and determining vehicle acquisition information corresponding to the vehicle running track from the acquired information.

And 912, matching the corresponding vehicle acquisition information with the target road section, the exit road section and the road section in the intersection respectively.

Based on the above embodiments, referring to fig. 10, an embodiment of the present application provides an intersection information acquisition device, including:

a determining unit 1001, configured to determine, according to road network data of an intersection, a target road segment of the intersection, and each possible driving direction of the target road segment, where a passing direction of the road segment outside each intersection of the intersection faces the intersection;

an obtaining unit 1002, configured to obtain intersection information corresponding to a target drivable direction in each drivable direction of the target road segment;

a matching unit 1003, configured to match the obtained intersection information to the target road segment.

the determining unit 1001 is specifically configured to:

Optionally, the passing mode of the road section outside the intersection comprises forward passing, reverse passing or bidirectional passing; the determining unit 1001 is specifically configured to:

Optionally, the determining unit 1001 is further configured to:

taking an exit road section to be selected, which is passable in connectivity with the target road section, as an exit road section of the target road section;

the obtaining unit 1002 is specifically configured to:

Optionally, the determining unit 1001 is further configured to:

Based on the same technical concept, the embodiment of the present application provides a computer device, as shown in fig. 11, including at least one processor 1101 and a memory 1102 connected to the at least one processor, where a specific connection medium between the processor 1101 and the memory 1102 is not limited in the embodiment of the present application, and the processor 1101 and the memory 1102 are connected through a bus in fig. 11 as an example. The bus may be divided into an address bus, a data bus, a control bus, etc.

In the embodiment of the present application, the memory 1102 stores instructions executable by the at least one processor 1101, and the at least one processor 1101 may execute the steps included in the trajectory data processing method by executing the instructions stored in the memory 1102.

The processor 1101 is a control center of the computer device, and may connect various parts of the terminal device by using various interfaces and lines, and obtain the client address by executing or executing instructions stored in the memory 1102 and calling data stored in the memory 1102. Optionally, the processor 1101 may include one or more processing units, and the processor 1101 may integrate an application processor and a modem processor, wherein the application processor mainly handles an operating system, a positioning target interface, an application program, and the like, and the modem processor mainly handles wireless communication. It will be appreciated that the modem processor described above may not be integrated into the processor 1101. In some embodiments, the processor 1101 and the memory 1102 may be implemented on the same chip, or in some embodiments, they may be implemented separately on separate chips.

The processor 1101 may be a general purpose processor such as a Central Processing Unit (CPU), a digital signal processor, an Application Specific Integrated Circuit (ASIC), a field programmable gate array or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof, configured to implement or perform the methods, steps, and logic blocks disclosed in the embodiments of the present Application. A general purpose processor may be a microprocessor or any conventional processor or the like. The steps of a method disclosed in connection with the embodiments of the present application may be directly implemented by a hardware processor, or may be implemented by a combination of hardware and software modules in a processor.

Memory 1102, which is a non-volatile computer-readable storage medium, may be used to store non-volatile software programs, non-volatile computer-executable programs, and modules. The Memory 1102 may include at least one type of storage medium, and may include, for example, a flash Memory, a hard disk, a multimedia card, a card-type Memory, a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a Programmable Read Only Memory (PROM), a Read Only Memory (ROM), a charged Erasable Programmable Read Only Memory (EEPROM), a magnetic Memory, a magnetic disk, an optical disk, and so on. The memory 1102 is any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer, but is not limited to such. The memory 1102 in the embodiments of the present application may also be circuitry or any other device capable of performing a storage function to store program instructions and/or data.

Based on the same technical concept, embodiments of the present application provide a computer-readable storage medium storing a computer program executable by a computer device, which, when the program is run on the computer device, causes the computer device to execute the steps of the trajectory data processing method.

The computer-readable storage medium may be any available medium or data storage device that can be accessed by a computer, including but not limited to magnetic memory (e.g., floppy disks, hard disks, magnetic tape, magneto-optical disks (MOs), etc.), optical memory (e.g., CDs, DVDs, BDs, HVDs, etc.), and semiconductor memory (e.g., ROMs, EPROMs, EEPROMs, non-volatile memory (NAND FLASH), Solid State Disks (SSDs)), etc.

As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention 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 invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams 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.

While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the invention.

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

Claims

1. A method for collecting intersection information is characterized by comprising the following steps:

determining road sections outside each intersection of the intersections according to road network data of the intersections, wherein the road network data comprises road section data passing through the intersections and node data of the intersections;

traversing the outer road sections of each intersection, and respectively executing the following operations:

for any road section outside the intersection, if the passing mode of the road section outside the intersection is forward passing, determining the terminal point of the road section outside the intersection, and when the terminal point of the road section outside the intersection is determined to be the node of the intersection according to the node data of the intersection, taking the road section outside the intersection as an entrance road section, otherwise, taking the road section outside the intersection as an exit road section;

if the passing mode of the road section outside the intersection is reverse passing, determining the starting point of the road section outside the intersection, and taking the road section outside the intersection as an inlet road section when the starting point of the road section outside the intersection is determined to be the node of the intersection according to the node data of the intersection, or taking the road section outside the intersection as an outlet road section;

if the passing mode of the road section outside the intersection is determined to be bidirectional passing or the passing mode of the road section outside the intersection is not determined, taking the road section outside the intersection as an entrance road section and an exit road section;

taking any one of the determined inlet road sections with the number of lanes larger than the threshold value of the lanes as a target road section;

traversing each exit road section, deleting an exit road section which is a turn road section aiming at the target road section, and deleting an exit road section which is not allowed to pass and has connectivity with the target road section, wherein the turn road section is an off-intersection road section of which the passing direction is parallel to and opposite to that of the target road section;

determining N road sections in the road between the target road section and each exit road section of the target road section, and establishing the connection relation of all the road sections of the target road section; wherein, one road section communication relation comprises the communication relation among the target road section, N road sections in the road openings and the exit road section of the target road section, N is an integer which is more than or equal to 0, and one road section communication relation corresponds to one travelable direction;

determining each drivable direction of the target road section according to the communication relation of each road section;

determining a target road section, an exit road section and an intersection inner road section which are contained in a target road section communication relation corresponding to a plurality of target travelable directions in each travelable direction; determining a vehicle running track corresponding to the target road section communication relation; determining intersection information corresponding to the vehicle running track from the acquired information; wherein, the intersection information is: the system comprises real acquisition information used for road drawing in an electronic map, wherein the intersection information is vehicle acquisition information;

and matching the obtained intersection information to the target road section.

2. The method of claim 1, wherein traversing each exit segment, deleting an exit segment for which the target segment is a u-turn segment, and deleting an exit segment for which connectivity to the target segment is no-pass comprises:

determining a turning road section of the target road section, and taking an exit road section except the turning road section as an exit road section to be selected of the target road section, wherein the exit road section is an off-intersection road section with a passing direction back to the intersection;

and taking the exit road section to be selected, which has the connectivity of being passable with the target road section, as the exit road section of the target road section.

3. The method of claim 1, wherein the direction of travel of the target road segment comprises a left turn direction, a straight direction, or a right turn direction.

4. An apparatus for collecting intersection information, the apparatus comprising:

the system comprises a determining unit, a judging unit and a judging unit, wherein the determining unit is used for determining road sections outside each intersection of the intersections according to road network data of the intersections, and the road network data comprises road section data passing through the intersections and node data of the intersections;

determining each travelable direction of the target road section according to the communication relation of the road sections;

the acquisition unit is used for determining a target road section, an exit road section and an intersection inner road section which are contained in the communication relation of each target road section corresponding to a plurality of target drivable directions in each drivable direction; determining a vehicle running track corresponding to the communication relation of each target road section; determining intersection information corresponding to the vehicle running track from the acquired information; wherein, the intersection information is: the system comprises real acquisition information used for road drawing in an electronic map, wherein the intersection information is vehicle acquisition information;

5. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the steps of the method of any of claims 1 to 3 are performed when the program is executed by the processor.

6. A computer-readable storage medium, in which a computer program is stored which is executable by a computer device, and which, when run on the computer device, causes the computer device to carry out the steps of the method as claimed in any one of claims 1 to 3.