CN116164727A - Intersection surface generation method, intersection surface generation device, electronic device, storage medium and program product - Google Patents
Intersection surface generation method, intersection surface generation device, electronic device, storage medium and program product Download PDFInfo
- Publication number
- CN116164727A CN116164727A CN202211677734.4A CN202211677734A CN116164727A CN 116164727 A CN116164727 A CN 116164727A CN 202211677734 A CN202211677734 A CN 202211677734A CN 116164727 A CN116164727 A CN 116164727A
- Authority
- CN
- China
- Prior art keywords
- intersection
- lane
- lane line
- target
- line groups
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/38—Electronic maps specially adapted for navigation; Updating thereof
- G01C21/3804—Creation or updating of map data
- G01C21/3807—Creation or updating of map data characterised by the type of data
- G01C21/3815—Road data
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A30/00—Adapting or protecting infrastructure or their operation
- Y02A30/60—Planning or developing urban green infrastructure
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Automation & Control Theory (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Traffic Control Systems (AREA)
Abstract
The application provides a method and a device for generating an intersection surface, electronic equipment, a storage medium and a program product, and belongs to the technical field of vehicles. The method comprises the following steps: clustering a plurality of lane line groups in a region where a target intersection is located to obtain a plurality of target lane line groups in the target intersection, wherein the lane line groups comprise a plurality of lane mark lines, and the lane mark lines comprise at least one of lane lines and lane center lines; constructing a convex hull corresponding to the target intersection based on the end points of each lane marking line in the plurality of target lane marking lines, wherein the end points are the head points or the tail points of the lane marking lines in the target intersection, and the convex hull is the smallest polygon surrounding the end points of all the lane marking lines in the target intersection; sequencing all endpoints in the convex hull; and determining a closed graph formed by sequentially connecting all endpoints in the convex hull as an intersection surface of the target intersection. The intersection surface determined based on the end points of the plurality of target lane line groups in the target intersection is more accurate, and the real form of the target intersection surface can be restored.
Description
Technical Field
The present invention relates to the field of vehicle technologies, and in particular, to a method and apparatus for generating an intersection, an electronic device, a storage medium, and a program product.
Background
The intersection surface in the navigation map is used for representing a space region where the intersection is located, so that base map data at the intersection can be provided for a navigation engine, the visual effect of a navigation interface is enhanced, meanwhile, data support can be provided for decision making of automatic driving at the intersection, vehicles are prevented from running beyond the intersection range, the probability of occurrence of accidents at the intersection is reduced, and the safety of automatic driving is improved.
In the related art, the method for generating the intersection surface comprises the following steps: obtaining all roads of a current intersection, generating extension edges of each road, and further connecting all extension edges of the current intersection to form an end-to-end closed loop, so as to obtain an intersection surface of the intersection.
However, the extended edges of the road cannot accurately describe the actual width of the road, resulting in inaccurate intersection faces being generated, and the intersection faces in the real scene cannot be restored.
Disclosure of Invention
The embodiment of the application provides an intersection face generating method, an intersection face generating device, electronic equipment, a storage medium and a program product. The technical scheme is as follows:
In a first aspect, there is provided an intersection face generating method, the method including:
clustering a plurality of lane line groups in a region where a target intersection is located to obtain a plurality of target lane line groups in the target intersection, wherein the lane line groups comprise a plurality of lane mark lines, and the lane mark lines comprise at least one of lane boundary lines and lane center lines;
constructing a convex hull corresponding to the target intersection based on the end points of the lane marking lines in the target lane line groups, wherein the end points are the head points or the tail points of the lane marking lines in the target intersection, and the convex hull is the smallest polygon surrounding the end points of all the lane marking lines in the target intersection;
sequencing all the endpoints in the convex hull;
and determining a closed graph formed by sequentially connecting all the endpoints in the convex hull as an intersection surface of the target intersection.
In another possible implementation manner, the clustering the multiple lane line groups in the area where the target intersection is located to obtain multiple target lane line groups in the target intersection includes:
dividing the lane line groups into a plurality of intersection inner lane line groups and a plurality of intersection outer lane line groups based on the position information of the endpoints of each lane line identification line in the lane line groups;
Clustering at least two lane line groups in the intersections with the same end points in each intersection of the area based on the position information of the end points of each lane marking line in the lane line groups in the intersections to obtain a plurality of lane line groups in each intersection of the area;
and acquiring a plurality of target lane line groups in the target intersection from the lane line groups in each intersection of the region.
In another possible implementation manner, the dividing the lane line groups into the inner lane line groups and the outer lane line groups based on the position information of the end points of each lane line identification line in the lane line groups includes:
taking the traffic flow direction as a reference direction, and if the end point of each lane marking line in any lane line group is positioned before a stop line or after a zebra crossing of the intersection relative to the traffic flow direction, determining that the lane line group belongs to an intersection external lane line group;
and if the end point of each lane marking line in the lane line group is positioned behind a stop line or in front of a zebra crossing of the intersection relative to the traffic direction, determining that the lane line group belongs to the lane line group in the intersection.
In another possible implementation manner, the constructing a convex hull corresponding to the target intersection based on the end points of each lane identification line in the plurality of target lane line groups includes:
dividing a plurality of target lane line groups into a lane line group set of an entering intersection and a lane line group set of an exiting intersection according to the relation between the traffic flow direction of each target lane line group and the target intersection;
acquiring the tail point of each lane marking line in each target lane group in the driving-in intersection lane line group set, and acquiring the head point of each lane marking line in each target lane group in the driving-out intersection lane line group set;
and constructing a minimum polygon surrounding all tail points and all head points based on all tail points corresponding to the lane line set of the entrance intersection and all head points corresponding to the lane line set of the exit intersection, and taking the minimum polygon as a convex hull corresponding to the target intersection.
In another possible implementation manner, the sorting the endpoints in the convex hull includes:
determining the geometric center of the convex hull according to the position information of each endpoint in the convex hull;
And sequencing the endpoints in the convex hull according to the position information of the geometric center and the position information of each endpoint.
In another possible implementation manner, the sorting the endpoints in the convex hull according to the location information of the geometric center and the location information of each endpoint includes:
calculating an included angle between a connecting line of the geometric center and each endpoint and a preset direction according to the position information of the geometric center and the position information of each endpoint;
and sequencing the endpoints in the convex hulls according to the included angle sequence.
In a second aspect, there is provided an intersection face generating device, the device comprising:
the clustering module is used for clustering a plurality of lane line groups in the area where the target intersection is located to obtain a plurality of target lane line groups in the target intersection, wherein the lane line groups comprise a plurality of lane mark lines, and the lane mark lines comprise at least one of lane boundary lines and lane center lines;
the construction module is used for constructing a convex hull corresponding to the target intersection based on the end points of the lane marking lines in the target lane line groups, wherein the end points are the head points or the tail points of the lane marking lines in the target intersection, and the convex hull is the smallest polygon surrounding the end points of all the lane marking lines in the target intersection;
The sequencing module is used for sequencing all the endpoints in the convex hull;
and the determining module is used for determining a closed graph formed by sequentially connecting the endpoints in the convex hull as an intersection surface of the target intersection.
In another possible implementation manner, the clustering module is configured to divide the lane line groups into a plurality of lane line groups inside the intersection and a plurality of lane line groups outside the intersection based on position information of endpoints of each of the lane line identification lines in the plurality of lane line groups; clustering at least two lane line groups in the intersections with the same end points in each intersection of the area based on the position information of the end points of each lane marking line in the lane line groups in the intersections to obtain a plurality of lane line groups in each intersection of the area; and acquiring a plurality of target lane line groups in the target intersection from the lane line groups in each intersection of the region.
In another possible implementation manner, the clustering module is configured to determine that the lane line group belongs to an intersection external lane line group if an endpoint of each lane marking line in any lane line group is located before a stop line or after a zebra crossing of the intersection with respect to the traffic direction; and if the end point of each lane marking line in the lane line group is positioned behind a stop line or in front of a zebra crossing of the intersection relative to the traffic direction, determining that the lane line group belongs to the lane line group in the intersection.
In another possible implementation manner, the construction module is configured to divide the multiple target lane line groups into a set of lane line groups of an entrance road junction and a set of lane line groups of an exit road junction according to a relationship between a traffic direction of each of the target lane line groups and the target road junction; acquiring the tail point of each lane marking line in each target lane group in the driving-in intersection lane line group set, and acquiring the head point of each lane marking line in each target lane group in the driving-out intersection lane line group set; and constructing a minimum polygon surrounding all tail points and all head points based on all tail points corresponding to the lane line set of the entrance intersection and all head points corresponding to the lane line set of the exit intersection, and taking the minimum polygon as a convex hull corresponding to the target intersection.
In another possible implementation manner, the sorting module is configured to determine a geometric center of the convex hull according to position information of each endpoint in the convex hull; and sequencing the endpoints in the convex hull according to the position information of the geometric center and the position information of each endpoint.
In another possible implementation manner, the sorting module is configured to calculate an included angle between a connection line between the geometric center and each endpoint and a preset direction according to the position information of the geometric center and the position information of each endpoint; and sequencing the endpoints in the convex hulls according to the included angle sequence.
In a third aspect, an electronic device is provided, where the electronic device includes a memory and a processor, where at least one computer program is stored in the memory, and the at least one computer program is loaded and executed by the processor to implement the intersection surface generating method according to the first aspect.
In a fourth aspect, there is provided a computer readable storage medium having stored therein at least one computer program capable of implementing the intersection face generating method according to the first aspect when executed by a processor.
In a fifth aspect, there is provided a computer program product comprising a computer program capable of implementing the intersection surface generation method according to the first aspect when executed by a processor.
The beneficial effects that technical scheme that this application embodiment provided brought are:
the lane line groups in the area where the target intersection is located are clustered to obtain a plurality of target lane line groups in the target intersection, the plurality of target lane line groups are each lane line group in the target intersection in a real scene, the width of each road to which the target intersection leads can be represented, further, according to the end points of each lane identification line in the plurality of target lane line groups, a convex hull corresponding to the target intersection is determined, the convex hull is the smallest polygon surrounding the end points of all lane identification lines in the target intersection, and the intersection range of the target intersection can be indicated. The convex hull is generally larger than the actual intersection surface of the target intersection, and in order to determine the intersection surface of the target intersection with higher accuracy, all endpoints in the convex hull are ordered, and a closed graph is obtained by sequentially connecting all endpoints, so that the closed graph is used as the intersection surface of the target intersection. Compared with the way of connecting all the expansion edges of the road, the generated intersection surface is more accurate, and the real road scene can be restored.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed 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 application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of an intersection face generating method provided in an embodiment of the present application;
FIG. 2 is a modeling diagram of an intersection surface provided in an embodiment of the present application;
FIG. 3 is a schematic view of a set of lanes of an entry intersection provided in an embodiment of the present application;
FIG. 4 is a schematic view of a lane line set for driving off an intersection according to an embodiment of the present disclosure;
fig. 5 is a schematic diagram of a convex hull corresponding to an intersection according to an embodiment of the present application;
FIG. 6 is a flowchart of another method for generating an intersection surface according to an embodiment of the present application;
fig. 7 is a schematic structural diagram of an intersection face generating device according to an embodiment of the present application;
fig. 8 shows a block diagram of an electronic device according to an exemplary embodiment of the present application.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the present application more apparent, the embodiments of the present application will be described in further detail below with reference to the accompanying drawings.
It will be understood that, as used in the embodiments of the present application, the terms "each," "plurality," and "any" and the like, a plurality includes two or more, each refers to each of the corresponding plurality, and any refers to any of the corresponding plurality. For example, the plurality of words includes 10 words, and each word refers to each of the 10 words, and any word refers to any one of the 10 words.
Information (including but not limited to user equipment information, user personal information, etc.), data (including but not limited to data for analysis, stored data, presented data, etc.), and signals referred to herein are user-authorized or fully authorized by parties, and the collection, use, and processing of relevant data requires compliance with relevant laws and regulations and standards of the relevant country and region.
Before executing the embodiments of the present application, the terms related to the embodiments of the present application will be explained first.
The intersection refers to an intersection without continuous boundary lines on the road surface of the urban road, and does not comprise an up-down ramp.
A lane boundary (lane boundary) is a road traffic marking for separating traffic flows traveling in the same direction, and common lane boundaries include a white solid line, a white broken line, huang Shixian, and the like.
The lane (lane) is a communication area on the road for vehicles to travel, and is composed of lane boundary lines, including a slow lane, a fast lane, a motor vehicle lane, a non-motor vehicle lane and the like.
The lane center line (lane center) is a broken line in the middle of the lane boundary line between the left and right sides, and is used to guide the vehicle to reasonably and moderately travel in the lane.
Convex hull (convex hull) refers to the convex hull where, for a given set Y, all convex set intersections S containing Y are referred to as Y in a real vector space.
The centroid is the geometric center of the convex hull. The geometric center or centroid of an object X in n-dimensional space is the intersection of all hyperplanes dividing X into equal parts. In brief, the geometric center is the average of all points in X. If the mass of an object is evenly distributed, the center of gravity is the geometric center of the object.
Along with the development of intelligent terminals and internet technologies, the information system based on the navigation map has a larger and larger role in traffic auxiliary guidance, so that people are more and more dependent on the navigation map when traveling, and meanwhile, higher requirements are also put forward on the definition of the navigation map. In order to meet the use demands of people, high-precision maps are gradually developed. The compiling of the high-precision map depends on the high-precision map data, but the acquisition and the processing of the high-precision map data require high cost and great investment, and no mature high-precision navigation product is marketed at present. Instead, the high-precision road is an excess product. The high-precision road is used as a component part of the high-precision navigation map, so that a clearer navigation road can be provided. Because the complexity of roads in all places is generally high, especially, crisscrossed crossroads, the road definition and the presentation effect of the crossroads in the navigation map play an important role in guiding people to pass correctly.
However, as noted in the background art, an intersection face generated by connecting the expanded sides of the intersection cannot accurately describe the actual width of the road, resulting in an insufficient accuracy of the generated intersection face. In order to generate a more accurate intersection surface, the method provided by the embodiment of the application obtains a plurality of target lane line groups in the target intersection by clustering each lane line group in the area where the target intersection is located, further constructs a convex hull corresponding to the target intersection based on the end points of each lane identification line (including at least one of a lane central line and a lane boundary line) in the plurality of target lane line groups, and further determines the sequence of the end points in the convex hull based on the included angle between the connecting line of the end points in the convex hull and the centroid of the convex hull and the preset direction, sequentially connects the end points in the convex hull to obtain a closed graph, and further takes the closed graph as the intersection surface of the target intersection.
The intersection surface generation method provided by the embodiment of the application can be executed by electronic equipment, the electronic equipment has stronger computing capability, and can be a server, for example, an independent physical server, a cluster or a distributed system formed by a plurality of physical servers, and a cloud server for providing cloud services, a cloud database, cloud computing, cloud functions, cloud storage, basic cloud computing services such as big data and an artificial intelligent platform; the electronic device may also be a terminal, for example, a vehicle-mounted device, a notebook computer, a desktop computer, or the like.
The embodiment of the application provides a method for generating an intersection, taking an electronic device to execute the embodiment of the application as an example, referring to fig. 1, the method provided by the embodiment of the application includes:
101. clustering a plurality of lane line groups in the area where the target intersection is located to obtain a plurality of target lane line groups in the target intersection.
The target intersection is an intersection which needs to generate an intersection surface. The region where the target intersection is located may be determined according to a map pair of the navigation map, for example, the map pair of the navigation map including the target intersection may be taken as the region where the target intersection is located. The map frame refers to paper carrying a navigation map, and the size of the map frame can be specified in a map drawing standard.
The lane line group comprises a plurality of lane marking lines, and the lane marking lines comprise at least one of lane lines, lane center lines and the like, namely, the lane marking lines can be lane boundary lines, lane center lines, lane boundary lines and lane center lines.
In the embodiment of the application, a plurality of lane line groups in the area where the target intersection is located can be obtained from the navigation map. The number of the lane marking lines included in each lane line group can be the same or different, and the number of the lane marking lines included in each lane line group depends on the number of the lane marking lines on an actual road. Since the number of the lane marking lines included in each lane line group is identical to the number of the lane marking lines included in the road in the real scene, the form of the road in the real scene can be restored based on the acquired lane line groups.
The above-mentioned only obtains a plurality of lane line groups from the area where the target intersection is located, and because the area includes a plurality of intersections including the target intersection, it is necessary to determine which intersection the lane line groups specifically belong to by a clustering method.
In the embodiment of the application, clustering is performed on a plurality of lane line groups in an area where a target intersection is located to obtain a plurality of target lane line groups in the target intersection, and the method comprises the following steps:
1011. the plurality of lane line groups are divided into a plurality of intersection inner lane line groups and a plurality of intersection outer lane line groups based on position information of endpoints of each lane line identification line in the plurality of lane line groups.
The end point is the head point or the tail point of the lane marking line. The end point of any lane marking is specifically the first point of the lane marking or the last point of the lane marking, and can be determined according to the relationship between the lane marking and the stop line or the zebra crossing. If the lane marking is cut off by the stop line, an end point formed when the lane marking is cut off by the stop line is a tail point; if the lane marking is cut by the zebra stripes, the end point formed when the lane marking is cut by the zebra stripes is the head point. The position information of the endpoint may be position information of the endpoint in the navigation map, for example, position coordinates in a coordinate system in which the navigation map is located, or the like.
The plurality of lane line groups comprise an inner lane line group of the intersection and an outer lane line group of the intersection according to whether the lane line groups are positioned in the intersection or not. The lane line group in the intersection is a lane line group positioned in the intersection, namely, each lane mark line included in the lane line group is positioned in the intersection area; the lane line group outside the intersection is a lane line group outside the intersection, that is, the lane line group comprises a plurality of lane marking lines outside the intersection area. For example, each of the entering lane line groups and each of the exiting lane line groups shown in fig. 2 are intersection outer lane line groups. The lane line groups crisscrossed in the middle of fig. 3 and 4 are the lane line groups in the intersections.
Specifically, based on the position information of the end point of each lane line identification line in the plurality of lane line groups, the plurality of lane line groups are divided into a plurality of intersection inner lane line groups and a plurality of intersection outer lane line groups, including:
for any lane line group, taking the vehicle flow direction as a reference direction, and if the end point of each lane mark line in the lane line group is positioned before a stop line of an intersection or after a zebra crossing relative to the vehicle flow direction, determining that the lane line group belongs to an intersection external lane line group;
and if the end point of each lane marking line in the lane line group is positioned behind a stop line or in front of a zebra crossing of the intersection relative to the traffic direction, determining that the lane line group belongs to the lane line group in the intersection.
1012. Based on the position information of the end point of each lane marking line in the lane line groups in the intersections, clustering at least two lane line groups in the intersections with the same end point in each intersection in the area to obtain the lane line groups in each intersection in the area.
Setting an inner lane line group of any non-clustered intersection as a first lane line group, and according to the position information of the end point of each lane marking line in the lane line group and the position information of the end point of each lane marking line in other inner lane line groups of the intersection, the electronic equipment acquires the inner lane line group of the intersection with the end point of any lane marking line identical to the end point of any lane marking line in the first lane line group from the inner lane line groups of other non-clustered intersections, and the acquired inner lane line group of the intersection is called a second lane line group, so that the first lane line group and the second lane line group are clustered, then acquires the inner lane line group of the intersection with the end point of any lane marking line identical to the end point of any lane marking line in the second lane line group from the inner lane line groups of other non-clustered intersections, and repeatedly executing the processes until all the inner lane line groups of the intersection are traversed, and then a plurality of lane line groups in one intersection can be obtained. And then, acquiring any lane line group in the intersection from the lane line groups in the non-clustered intersection, clustering the lane line groups in the intersection according to the clustering process of the first lane line group until all lane line groups in the intersection are clustered, and finally obtaining a plurality of lane line groups in a plurality of intersections.
In order to facilitate understanding the above clustering process, multiple sets may be preset in the embodiment of the present application, which are sets G1, G2, G3, and G4, respectively. Wherein, G1 is a set formed by a plurality of lane line groups in the crossing, and the number of elements in G1 at the initial moment (i.e. when not clustered) is the same as the total number of the lane line groups in the crossing; g2 is a matched set and is used for storing clustered lane line groups in a plurality of intersections, the number of elements in the initial time set is 0, and G2 is an empty set; g3 is a result set, the number of G3 is the same as the number of intersections, the number of elements in the initial time set G3 is 0, and G3 is an empty set; and G4 is a temporary result set, which is used for temporarily storing clustered lane line groups in a certain intersection, wherein the number of elements in the initial time set G4 is 0, and G4 is an empty set.
Firstly, randomly selecting an intersection inner lane line group from G1 when clustering is started, and placing the intersection inner lane line group into G4 and then placing the intersection inner lane line group into G2 because the intersection inner lane line group is no longer in G2;
judging whether an intersection inner lane line group which is the same as the head point or the tail point of any lane marking line in the intersection inner lane line group in G4 exists in the intersection inner lane line group which is not in G2, if so, putting the intersection inner lane line group in G4, and then putting the intersection inner lane line group in G2;
And thirdly, repeating the second step until the lane line groups in each intersection in G1 are traversed.
Fourth, through the first step to the third step, if the obtained G4 is a non-empty set, it is indicated that the elements in G4 are a plurality of lane line groups in one intersection, then the elements in G4 are added into G3, and G4 is emptied, and the fifth step is continuously performed to obtain the lane line group in the next intersection;
fifth, repeating the first to fourth steps until the elements in G1 and G2 are the same, wherein all lane line groups in the area are matched, and each G3 comprises a plurality of lane line groups in an intersection.
1013. And acquiring a plurality of target lane line groups in the target intersection from the plurality of lane line groups in each intersection of the region.
Based on the plurality of lane line groups in each intersection of the region, the plurality of target lane line groups in the target intersection can be obtained according to the attribute information of the target intersection. The attribute information includes position information of the target intersection, and the like. For example, a plurality of in-intersection lane line groups adjacent to the target intersection may be determined based on the position information of the target intersection, and a plurality of lane line groups included in a set to which the immediately adjacent plurality of in-intersection lane line groups belong may be further taken as the plurality of target lane line groups.
102. And constructing a convex hull corresponding to the target intersection based on the end points of each lane mark line in the plurality of target lane line groups.
The end point is the head point or the tail point of the lane marking line in the target intersection. The convex hull is the smallest polygon that encloses the endpoints of all lane markings within the target intersection. Based on the end points of each lane marking line in the plurality of target lane line groups, constructing a convex hull corresponding to the target intersection, wherein the method can be adopted as follows:
1021. dividing a plurality of target lane line groups into a lane line group set of an entrance crossing and a lane line group set of an exit crossing according to the relation between the traffic direction of each target lane line group and the target crossing.
In the embodiment of the application, the lane line groups can be divided into the lane line group of the entering intersection and the lane line group of the exiting intersection according to the relation between the traffic direction and the intersection. If the plurality of lane line sets are a plurality of intersection outer lane line sets, for any intersection outer lane line set, if an end point of each lane marking line in the intersection outer lane line set is a first point of entering the intersection, dividing the intersection outer lane line set into an entrance intersection lane line set outside the intersection, wherein the entrance intersection lane line set outside the intersection comprises at least one intersection outer lane line set, such as the plurality of entrance lane line sets included in the intersection shown in fig. 2; if the end point of each lane marking line in the outer lane line of the intersection is the tail point of the driving-out intersection, the outer lane line group of the intersection is divided into a driving-out intersection lane line group set outside the intersection, and the driving-out intersection lane line group set outside the intersection comprises at least one outer lane line group of the intersection, such as a plurality of driving-out lane line groups included in the intersection shown in fig. 2.
For any target lane line group, according to the vehicle flow direction indicated by the target lane line group, if the end point of each lane mark line in the target lane line group is the tail point of the entering intersection, dividing the target lane line group into a lane line group set of the entering intersection; and if the end point of each lane marking line in the target lane line group is the starting point of the driving-off intersection, dividing the target lane line group into a lane line group set of the driving-off intersection. And after the operation is carried out on the plurality of target lane line groups, finally obtaining a lane line group set of the entrance road and a lane line set of the exit road.
1022. The method comprises the steps of obtaining the tail point of each lane marking line in each target lane group in the driving-in intersection lane line set, and obtaining the head point of each lane marking line in each target lane group in the driving-out intersection lane line set.
For a set of lane lines of an entrance intersection, the tail point of each lane mark line in each target lane line set is the tail point of the entrance target intersection through the lane mark line, so that the range of the target intersection can be described; for each set of lane lines of the departure intersection, the first point of each lane marking line in each target lane line set is the first point of the departure intersection through the lane marking line, so that the range of the target intersection can be described, and therefore, the intersection surface of the target intersection can be determined by acquiring the tail point of each lane marking line in each target lane line in the set of lane lines of the departure intersection and the first point of each lane marking line in each target lane line in the set of lane lines of the departure intersection.
For the lane line set of the entrance road, the electronic equipment acquires the tail points of each lane mark line in each target lane line set in the lane line set of the entrance road, and a plurality of tail points shown in fig. 3 can be obtained; for the set of lane lines of the driving-out intersection, the electronic device obtains the first point of each lane mark line in each target lane line set, and a plurality of first points shown in fig. 4 can be obtained.
1023. And constructing a minimum polygon surrounding all tail points and all head points based on all tail points corresponding to the lane line set of the entering intersection and all head points corresponding to the lane line set of the exiting intersection, and taking the minimum polygon as a convex hull corresponding to the target intersection.
Based on each tail point corresponding to the lane line set of the entering intersection and each head point corresponding to the lane line set of the exiting intersection, the electronic equipment constructs a minimum polygon which can surround all tail points in the lane line set of the entering intersection and can surround all head points in the lane line set of the exiting intersection, and then the minimum polygon is used as a convex hull corresponding to the target intersection.
103. And sequencing all endpoints in the convex hull.
The convex hull constructed in the step 102 is a minimum polygon surrounding the tail points and the head points of all lane marking lines in the target intersection, the area of the convex hull is larger than the actual intersection surface of the target intersection, and in order to more accurately determine the intersection surface of the target intersection, the electronic device can sort all the endpoints in the convex hull, and further obtain the actual intersection surface of the target intersection by sequentially connecting all the endpoints.
When the electronic device orders all endpoints in the convex hull, the following method can be adopted:
1031. and determining the geometric center of the convex hull according to the position information of each endpoint in the convex hull.
The electronic equipment acquires the position information of each endpoint in the convex hull, and calculates the gravity center position of the convex hull according to the position information of each endpoint in the convex hull, wherein the gravity center position of the convex hull is the geometric center of the convex hull.
1032. And sequencing the endpoints in the convex hull according to the position information of the geometric center and the position information of each endpoint.
According to the position information of the geometric center and the position information of each endpoint, when the electronic equipment sorts the endpoints in the convex hull, the following method can be adopted:
the first step is to calculate the included angle between the connecting line of the geometric center and each endpoint and the preset direction according to the position information of the geometric center and the position information of each endpoint.
The preset direction may be the north direction or the like. For any endpoint, the electronic device subtracts the corresponding coordinate of the geometric center from the position coordinate of the endpoint to obtain the relative coordinate of the endpoint relative to the geometric center, further calculates the sine value of the included angle between the connecting line of the geometric center and the endpoint and the preset direction based on the relative coordinate, and then obtains the included angle between the connecting line of the geometric center and the endpoint and the preset direction by calculating the inverse trigonometric function.
Setting the coordinates of the geometric center as (x 1 ，y 1 ) The coordinates of the end points are (x 2 ，y 2 ) The relative coordinates of the end point with respect to the geometric center are (x) 2 -x 1 ，y 2 -y 1 ) The sine value of the included angle between the connecting line of the geometric center and the end point and the preset direction is tan (y 2 -y 1 /x 2 -x 1 ) The included angle between the geometric center and the connecting line of the end point and the preset direction is argtan (y 2 -y 1 /x 2 -x 1 )。
And secondly, sequencing all endpoints in the convex hull according to the included angle sequence.
The electronic equipment can sort all endpoints in the convex hull according to the order of the included angles from small to large, and can sort all endpoints in the convex hull according to the order of the included angles from large to small.
104. And determining a closed graph formed by sequentially connecting all endpoints in the convex hull as an intersection surface of the target intersection.
And sequentially connecting all the endpoints in the convex hull according to the determined sequence, and finally connecting the head point and the tail point to obtain a closed graph, wherein the closed graph is the intersection surface of the target intersection. The intersection surface generated as shown in fig. 5 is the closed graphic area in fig. 5.
The intersection surface generation process is described in detail below with reference to fig. 6.
The method comprises the steps of firstly, obtaining a plurality of lane line groups in a region where a target intersection is located, and clustering the plurality of lane line groups to obtain a plurality of target lane line groups in the target intersection;
Secondly, constructing convex hulls corresponding to target intersections based on endpoints of a plurality of target lane line groups;
thirdly, sequencing all endpoints in the convex hull;
and fourthly, sequentially connecting all endpoints in the convex hull to obtain a closed graph, wherein the closed graph is the intersection surface of the target intersection.
According to the method provided by the embodiment of the application, the lane line groups in the area where the target intersection is located are clustered to obtain the plurality of target lane line groups in the target intersection, the plurality of target lane line groups are each lane line group in the target intersection in a real scene, the width of each road to which the target intersection leads can be represented, further, according to the end points of each lane identification line in the plurality of target lane line groups, the convex hull corresponding to the target intersection is determined, and the convex hull is the smallest polygon surrounding the end points of all the lane identification lines in the target intersection, so that the intersection range of the target intersection can be indicated. The convex hull is generally larger than the actual intersection surface of the target intersection, and in order to determine the intersection surface of the target intersection with higher accuracy, all endpoints in the convex hull are ordered, and a closed graph is obtained by sequentially connecting all endpoints, so that the closed graph is used as the intersection surface of the target intersection. Compared with the way of connecting all the expansion edges of the road, the generated intersection surface is more accurate, and the real road scene can be restored.
Referring to fig. 7, a schematic structural diagram of an intersection surface generating device according to an embodiment of the present application is provided, where the device may be implemented by software, hardware, or a combination of both, and may be all or a part of an electronic device, and the device includes:
the clustering module 701 is configured to cluster a plurality of lane line groups in an area where a target intersection is located, so as to obtain a plurality of target lane line groups in the target intersection, where the lane line groups include a plurality of lane identification lines, and the lane identification lines include at least one of a lane boundary line and a lane center line;
the construction module 702 is configured to construct a convex hull corresponding to the target intersection based on an end point of each lane marking in the plurality of target lane marking groups, where the end point is a first point or a last point of the lane marking in the target intersection, and the convex hull is a minimum polygon surrounding end points of all lane markings in the target intersection;
a sorting module 703, configured to sort each endpoint in the convex hull;
and the determining module 704 is used for determining the closed graph formed by sequentially connecting all the endpoints in the convex hull as the intersection surface of the target intersection.
In another possible implementation manner, the clustering module 701 is configured to divide the plurality of lane line groups into a plurality of lane line groups inside the intersection and a plurality of lane line groups outside the intersection based on the position information of the end point of each lane line identification line in the plurality of lane line groups; clustering at least two lane line groups in each intersection with the same end point in the area based on the position information of the end point of each lane marking line in the lane line groups in the plurality of intersections to obtain a plurality of lane line groups in each intersection in the area; and acquiring a plurality of target lane line groups in the target intersection from the plurality of lane line groups in each intersection of the region.
In another possible implementation manner, the clustering module 701 is configured to determine that the lane line group belongs to an outer lane line group of the intersection if the end point of each lane marking line in any lane line group is located before a stop line of the intersection or after a zebra crossing with respect to the traffic direction; and if the end point of each lane marking line in the lane line group is positioned behind a stop line or in front of a zebra crossing of the intersection relative to the traffic direction, determining that the lane line group belongs to the lane line group in the intersection.
In another possible implementation manner, the construction module 702 is configured to divide the multiple target lane line groups into a set of lane line groups of the entrance road junction and a set of lane line groups of the exit road junction according to a relationship between a traffic direction of each target lane line group and the target road junction; acquiring the tail point of each lane marking line in each target lane group in the lane line set of the driving-in intersection, and acquiring the head point of each lane marking line in each target lane group in the lane line set of the driving-out intersection; and constructing a minimum polygon surrounding all tail points and all head points based on all tail points corresponding to the lane line set of the entering intersection and all head points corresponding to the lane line set of the exiting intersection, and taking the minimum polygon as a convex hull corresponding to the target intersection.
In another possible implementation, the sorting module 703 is configured to determine a geometric center of the convex hull according to the position information of each endpoint in the convex hull; and sequencing the endpoints in the convex hull according to the position information of the geometric center and the position information of each endpoint.
In another possible implementation manner, the sorting module 703 is configured to calculate an included angle between a connection line between the geometric center and each endpoint and a preset direction according to the position information of the geometric center and the position information of each endpoint; and sequencing all endpoints in the convex hull according to the included angle sequence.
In summary, in the device provided by the embodiment of the present application, the lane line groups in the area where the target intersection is located are clustered to obtain multiple target lane line groups in the target intersection, where the multiple target lane line groups are each lane line group in the target intersection in the real scene, so that the width of each road to which the target intersection leads can be represented, and further, according to the end point of each lane identification line in the multiple target lane line groups, a convex hull corresponding to the target intersection is determined, and the convex hull is the smallest polygon surrounding the end points of all the lane identification lines in the target intersection, so that the intersection range of the target intersection can be indicated. The convex hull is generally larger than the actual intersection surface of the target intersection, and in order to determine the intersection surface of the target intersection with higher accuracy, all endpoints in the convex hull are ordered, and a closed graph is obtained by sequentially connecting all endpoints, so that the closed graph is used as the intersection surface of the target intersection. Compared with the way of connecting all the expansion edges of the road, the generated intersection surface is more accurate, and the real road scene can be restored.
Fig. 8 shows a block diagram of an electronic device 800 according to an exemplary embodiment of the present application. Generally, the electronic device 800 includes: a processor 801 and a memory 802.
The processor 801 may be implemented in at least one hardware form of DSP (Digital Signal Processing ), FPGA (Field-Programmable Gate Array, field programmable gate array), PLA (Programmable Logic Array ). The processor 801 may also include a main processor, which is a processor for processing data in an awake state, also referred to as a CPU (Central Processing Unit ), and a coprocessor; a coprocessor is a low-power processor for processing data in a standby state. In some embodiments, the processor 801 may integrate a GPU (Graphics Processing Unit, image processor) for rendering and rendering of content required to be displayed by the display screen. In some embodiments, the processor 801 may also include an AI (Artificial Intelligence ) processor for processing computing operations related to machine learning.
Of course, the electronic device described above may necessarily also include other components, such as input/output interfaces, communication components, and the like. The input/output interface provides an interface between the processor and a peripheral interface module, which may be an output device, an input device, etc. The communication component is configured to facilitate wired or wireless communication between the electronic device and other devices, and the like.
Those skilled in the art will appreciate that the structure shown in fig. 8 is not limiting and that more or fewer components than shown may be included or certain components may be combined or a different arrangement of components may be employed.
The embodiment of the application provides a computer readable storage medium, wherein at least one computer program is stored in the computer readable storage medium, and the at least one computer program can realize an intersection surface generation method when being executed by a processor.
The methods in this application may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer programs or instructions. When the computer program or instructions are loaded and executed on a computer, the processes or functions described herein are performed in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, a network device, a user device, a core network device, OAM (Operation Administration and Maintenance, operations administration maintenance), or other programmable apparatus. The computer program or instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another computer readable storage medium, for example, the computer program or instructions may be transmitted from one website site, computer, server, or data center to another website site, computer, server, or data center by wired or wireless means. The computer readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that integrates one or more available media. The usable medium may be a magnetic medium, e.g., floppy disk, hard disk, tape; but also optical media such as digital video discs; but also semiconductor media such as solid state disks. The computer readable storage medium may be volatile or nonvolatile storage medium, or may include both volatile and nonvolatile types of storage medium.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, which are not repeated herein.
The above embodiments are only for illustrating the technical solution of the present application, and are not limiting thereof; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the corresponding technical solutions.
Claims (10)
1. An intersection face generating method, which is characterized by comprising the following steps:
clustering a plurality of lane line groups in a region where a target intersection is located to obtain a plurality of target lane line groups in the target intersection, wherein the lane line groups comprise a plurality of lane mark lines, and the lane mark lines comprise at least one of lane boundary lines and lane center lines;
constructing a convex hull corresponding to the target intersection based on the end points of the lane marking lines in the target lane line groups, wherein the end points are the head points or the tail points of the lane marking lines in the target intersection, and the convex hull is the smallest polygon surrounding the end points of all the lane marking lines in the target intersection;
Sequencing all the endpoints in the convex hull;
and determining a closed graph formed by sequentially connecting all the endpoints in the convex hull as an intersection surface of the target intersection.
2. The method of claim 1, wherein clustering the plurality of lane line groups in the area of the target intersection to obtain the plurality of target lane line groups in the target intersection comprises:
dividing the lane line groups into a plurality of intersection inner lane line groups and a plurality of intersection outer lane line groups based on the position information of the endpoints of each lane line identification line in the lane line groups;
clustering at least two lane line groups in the intersections with the same end points in each intersection of the area based on the position information of the end points of each lane marking line in the lane line groups in the intersections to obtain a plurality of lane line groups in each intersection of the area;
and acquiring a plurality of target lane line groups in the target intersection from the lane line groups in each intersection of the region.
3. The method of claim 2, wherein the dividing the plurality of lane line groups into a plurality of inner-crossing lane line groups and a plurality of outer-crossing lane line groups based on the position information of the end points of each of the lane line identification lines in the plurality of lane line groups comprises:
Taking the traffic flow direction as a reference direction, and if the end point of each lane marking line in any lane line group is positioned before a stop line or after a zebra crossing of the intersection relative to the traffic flow direction, determining that the lane line group belongs to an intersection external lane line group;
and if the end point of each lane marking line in the lane line group is positioned behind a stop line or in front of a zebra crossing of the intersection relative to the traffic direction, determining that the lane line group belongs to the lane line group in the intersection.
4. The method of claim 1, wherein the constructing a convex hull corresponding to the target intersection based on the end points of each of the lane markings in the plurality of target lane groups comprises:
dividing a plurality of target lane line groups into a lane line group set of an entering intersection and a lane line group set of an exiting intersection according to the relation between the traffic flow direction of each target lane line group and the target intersection;
acquiring the tail point of each lane marking line in each target lane group in the driving-in intersection lane line group set, and acquiring the head point of each lane marking line in each target lane group in the driving-out intersection lane line group set;
And constructing a minimum polygon surrounding all tail points and all head points based on all tail points corresponding to the lane line set of the entrance intersection and all head points corresponding to the lane line set of the exit intersection, and taking the minimum polygon as a convex hull corresponding to the target intersection.
5. The method of claim 1, wherein said ordering each of said endpoints in said convex hull comprises:
determining the geometric center of the convex hull according to the position information of each endpoint in the convex hull;
and sequencing the endpoints in the convex hull according to the position information of the geometric center and the position information of each endpoint.
6. The method of claim 5, wherein said ordering each of said endpoints in said convex hull based on location information of said geometric center and location information of each of said endpoints, comprises:
calculating an included angle between a connecting line of the geometric center and each endpoint and a preset direction according to the position information of the geometric center and the position information of each endpoint;
and sequencing the endpoints in the convex hulls according to the included angle sequence.
7. An intersection face generating device, characterized in that the device comprises:
The clustering module is used for clustering a plurality of lane line groups in the area where the target intersection is located to obtain a plurality of target lane line groups in the target intersection, wherein the lane line groups comprise a plurality of lane mark lines, and the lane mark lines comprise at least one of lane boundary lines and lane center lines;
the construction module is used for constructing a convex hull corresponding to the target intersection based on the end points of the lane marking lines in the target lane line groups, wherein the end points are the head points or the tail points of the lane marking lines in the target intersection, and the convex hull is the smallest polygon surrounding the end points of all the lane marking lines in the target intersection;
the sequencing module is used for sequencing all the endpoints in the convex hull;
and the determining module is used for determining a closed graph formed by sequentially connecting the endpoints in the convex hull as an intersection surface of the target intersection.
8. An electronic device comprising a memory and a processor, wherein the memory stores at least one computer program that is loaded and executed by the processor to implement the intersection surface generation method of any one of claims 1 to 6.
9. A computer-readable storage medium, wherein at least one computer program is stored in the computer-readable storage medium, and when executed by a processor, the at least one computer program is capable of implementing the intersection surface generation method according to any one of claims 1 to 6.
10. A computer program product, characterized in that it comprises a computer program which, when executed by a processor, is capable of implementing the intersection surface generation method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211677734.4A CN116164727A (en) | 2022-12-26 | 2022-12-26 | Intersection surface generation method, intersection surface generation device, electronic device, storage medium and program product |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211677734.4A CN116164727A (en) | 2022-12-26 | 2022-12-26 | Intersection surface generation method, intersection surface generation device, electronic device, storage medium and program product |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116164727A true CN116164727A (en) | 2023-05-26 |
Family
ID=86419256
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211677734.4A Pending CN116164727A (en) | 2022-12-26 | 2022-12-26 | Intersection surface generation method, intersection surface generation device, electronic device, storage medium and program product |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116164727A (en) |
-
2022
- 2022-12-26 CN CN202211677734.4A patent/CN116164727A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111123920A (en) | Method and device for generating automatic driving simulation test scene | |
| US20210381846A1 (en) | Methods and apparatuses for navigation guidance and establishing a three-dimensional real scene model, device and medium | |
| CN111554105B (en) | Intelligent traffic identification and statistics method for complex traffic intersection | |
| WO2021051346A1 (en) | Three-dimensional vehicle lane line determination method, device, and electronic apparatus | |
| US10030982B2 (en) | Generalising topographical map data | |
| CN112233240A (en) | Three-dimensional vector data slicing method and device of three-dimensional vector map and electronic equipment | |
| CN111859178A (en) | Method and system for recommending boarding points | |
| CN110969592A (en) | Image fusion method, automatic driving control method, device and equipment | |
| CN111295569A (en) | System and method for generating road map | |
| CN114758086B (en) | Method and device for constructing urban road information model | |
| CN112328880A (en) | Geographical region clustering method and device, storage medium and electronic equipment | |
| CN114863047A (en) | Intersection virtual line drawing method and device, electronic equipment and computer program product | |
| US20230159052A1 (en) | Method for processing behavior data, method for controlling autonomous vehicle, and autonomous vehicle | |
| CN116164727A (en) | Intersection surface generation method, intersection surface generation device, electronic device, storage medium and program product | |
| CN115540880A (en) | Navigation path matching method and device, electronic equipment and storage medium | |
| CN115661444A (en) | Image processing method, device, equipment, storage medium and product | |
| CN115857685A (en) | Perception algorithm data closed-loop method and related device | |
| CN115631476A (en) | Lane data processing method, system, electronic device and storage medium | |
| JP7070531B2 (en) | Urban structure design equipment and urban structure design program | |
| CN110795977B (en) | Traffic signal identification method and device, storage medium and electronic equipment | |
| CN113763522A (en) | Map rendering method, device, equipment and medium | |
| CN116465394B (en) | Road network structure generation method and device based on vehicle track data | |
| CN116718181B (en) | Map generation method, map generation device, electronic equipment and storage medium | |
| CN115641430B (en) | Method, device, medium and computer equipment for determining interest surface | |
| CN114328594B (en) | Method and device for judging running path of vehicle, storage medium and terminal |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |