Data processing method and apparatus, and storage medium

Abstract

The application provides a data processing method and device and a storage medium, and relates to the technical field of map data processing. The method comprises the following steps: obtaining mark-precision original data of surrounding roads of a target intersection from a mark-precision original data set of the target intersection, wherein the surrounding roads comprise roads entering and / or exiting the intersection; generating edges of the surrounding roads according to road widths and road center lines in the mark-precision original data of the surrounding roads; constructing connecting lines of the edges of the surrounding roads; and generating intersection surface data of the target intersection based on at least the connecting lines of the edges of the surrounding roads. The application can improve the accuracy of the obtained intersection surface.

Description

Technical Field

[0001] This application relates to map data processing technology, and more particularly to a data processing method, apparatus and storage medium. Background Technology

[0002] Intersections are crucial navigation action points and also locations where users are prone to deviating from their intended path. Furthermore, intersections contain additional information that affects driving operations, such as zebra crossings, stop lines, and lanes for early left turns. Therefore, as navigation evolves from road-level to lane-level, the level of map detail increases. Taking intersections as an example, it's necessary to model intersections based on intersection surface rendering data to clearly and accurately present intersection information to the user during lane-level navigation. This includes displaying road connections, additional information, and drawing turning actions at intersections.

[0003] Due to limitations in the production cost and update frequency of high-precision maps, some intersection surface rendering data is currently generated based on standard-precision map data for that intersection. Because standard-precision map data itself has limited precision, the quality of intersection surface rendering data generated from it is often low, frequently resulting in discrepancies between the intersection model constructed from the rendered data and the actual intersection. Therefore, improving the quality of intersection surface rendering data is a problem that needs to be solved by those skilled in the art. Summary of the Invention

[0004] This application provides a data processing method, apparatus, and storage medium that can improve the accuracy of the generated intersection surface, and thus improve the accuracy of the rendering data based on the intersection surface.

[0005] In a first aspect, this application provides a data processing method, the method comprising:

[0006] From the target intersection's standard and refined raw dataset, obtain the standard and refined raw data of the surrounding roads of the target intersection, including roads leading into and / or exiting the intersection;

[0007] Based on the road width and road centerline in the standard original data of the surrounding roads, generate the edge lines of the surrounding roads;

[0008] Construct connecting lines for the edges of adjacent surrounding roads;

[0009] The intersection surface data of the target intersection is generated based at least on the connecting lines of the edges of the surrounding roads.

[0010] Optionally, constructing the connecting lines of the adjacent edges of the surrounding roads specifically includes:

[0011] Based on the endpoints of the center lines of the surrounding roads, the surrounding roads are sorted, where the endpoints are those connecting to the intersection.

[0012] Based on the order of the surrounding roads, obtain the adjacency relationship of the edges of the surrounding roads;

[0013] Based on the parallelism of the edges of the adjacent surrounding roads, a connecting line is constructed for the edges of the adjacent surrounding roads.

[0014] Optionally, sorting the surrounding roads based on the endpoints of their centerlines specifically includes:

[0015] Based on the endpoints of the road centerline, a convex polygon with the endpoints of the road centerline as vertices is obtained;

[0016] The sorting order of the surrounding roads is obtained using the convex shape.

[0017] Optionally, obtaining the sorting order of the surrounding roads using the convex polygon specifically includes:

[0018] Move the boundary of the convex polygon outward from the intersection so that the center line of the surrounding road intersects with the convex polygon;

[0019] Starting from any intersection point, sort the intersection points according to a preset rotation direction;

[0020] The order of the intersection points is used as the order of the surrounding roads.

[0021] Optionally, constructing a connecting line for the edges of adjacent surrounding roads based on the parallelism of their edges includes:

[0022] For any two adjacent perimeter roads, determine whether the parallelism between the two adjacent perimeter roads is less than or equal to a preset threshold.

[0023] If the parallelism of the edges of two adjacent surrounding roads is greater than the preset threshold, then the edges of the two adjacent surrounding roads are extended to obtain the intersection of the edges of the two adjacent surrounding roads, and a connecting line of the edges of the two adjacent surrounding roads is generated based on the intersection and the endpoints of the edges.

[0024] If the parallelism of the edges of two adjacent surrounding roads is less than or equal to the preset threshold, then a connecting line of the edges of the two adjacent surrounding roads is generated according to the direction of the edges and the endpoints of the edges.

[0025] Optionally, if the target intersection further includes internal roads within the intersection, the method further includes:

[0026] From the standard and refined raw dataset of the target intersection, obtain the standard and refined raw data of the roads inside the target intersection;

[0027] Based on the road width and road centerline in the original data of the roads inside the intersection, generate the edge lines of the roads inside the intersection;

[0028] Construct a connecting line between the edge line of the internal road at the intersection and the edge line of the surrounding roads;

[0029] The generation of intersection surface data for the target intersection, based at least on the connecting lines of the edges of the surrounding roads, specifically includes:

[0030] The intersection surface data of the target intersection is generated based on the connecting lines of the edges of the surrounding roads and the connecting lines between the edges of the surrounding roads and the internal roads of the intersection.

[0031] Optionally, constructing the connecting line between the edge line of the internal road at the intersection and the edge lines of the surrounding roads includes:

[0032] Determine the two intersection points of the edge lines of the two adjacent surrounding roads and the target edge line, wherein the target edge line is the edge line closest to the endpoint of the surrounding roads;

[0033] If the order of the intersection points is consistent with the order of the two adjacent surrounding roads, then based on the intersection points and the endpoints of the edges of the two adjacent surrounding roads, a connection line is generated between the edges of the two adjacent surrounding roads and the edges of the roads inside the intersection.

[0034] If the order of the intersection points is opposite to the order of the two adjacent surrounding roads, then the intersection point of the edges of the two adjacent surrounding roads is obtained, and the connecting line of the edges of the two adjacent surrounding roads is generated based on the intersection point and the endpoints of the edges.

[0035] Optionally, after constructing the connecting lines of the adjacent edges of the surrounding roads, the method further includes:

[0036] If both sides of the surrounding road are connected by a connecting line, and the deviation between the endpoints of the connecting lines of the two sides is greater than or equal to a preset deviation, then the endpoint of the connecting line of one side is used as a reference to adjust the endpoint of the connecting line of the other side.

[0037] Secondly, this application provides a data processing method, the method comprising:

[0038] From the target intersection's standard and refined raw dataset, obtain the standard and refined raw data of the surrounding roads of the target intersection, including roads leading into and / or exiting the intersection;

[0039] Based on the endpoints of the road centerlines in the original data of the surrounding roads, a convex polygon with the endpoints of the road centerlines as vertices is obtained;

[0040] The sorting order of the surrounding roads is obtained using the convex shape.

[0041] Optionally, obtaining the sorting order of the surrounding roads using the convex polygon includes:

[0042] Move the boundary of the convex polygon outward from the intersection so that the center line of the surrounding road intersects with the convex polygon;

[0043] Starting from any intersection point, sort the intersection points according to a preset rotation direction;

[0044] The order of the intersection points is used as the order of the surrounding roads.

[0045] Thirdly, this application provides a data processing apparatus, the apparatus comprising:

[0046] The acquisition module is used to acquire the standard and refined raw data of the surrounding roads of the target intersection from the standard and refined raw dataset of the target intersection, wherein the surrounding roads include roads that enter and / or exit the intersection;

[0047] The first processing module is used to generate the edge lines of the surrounding roads based on the road width and road centerline in the standard original data of the surrounding roads;

[0048] A construction module is used to construct the connecting lines of the adjacent edges of the surrounding roads;

[0049] The second processing module is used to generate intersection surface data of the target intersection based at least on the connecting lines of the edges of the surrounding roads.

[0050] Fourthly, this application provides a data processing apparatus, the apparatus comprising:

[0051] The acquisition module is used to acquire the standard and refined raw data of the surrounding roads of the target intersection from the standard and refined raw dataset of the target intersection, wherein the surrounding roads include roads that enter and / or exit the intersection;

[0052] The first processing module is used to obtain a convex polygon with the endpoint of the road centerline as the vertex based on the endpoint of the road centerline in the original data of the surrounding roads.

[0053] The second processing module is used to obtain the sorting order of the surrounding roads using the convex polygon.

[0054] Fifthly, this application provides an electronic device, including: a processor and a memory; the processor and the memory are communicatively connected;

[0055] The memory stores computer-executed instructions;

[0056] The processor executes computer execution instructions stored in the memory to implement the method as described in any one of the first aspects, or the method as described in any one of the second aspects.

[0057] Fourthly, this application provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any of the first aspects, or the method as described in any of the second aspects.

[0058] Fifthly, this application provides a computer program product, including a computer program that, when executed by a processor, implements the method described in any one of the first aspects, or the method described in any one of the second aspects.

[0059] The data processing method, apparatus, and storage medium provided in this application can obtain the standard raw data of the surrounding roads connected to the target intersection based on the standard raw dataset of the target intersection. After constructing the edges of each surrounding road, it can generate connecting lines between adjacent edges of the surrounding roads. Thus, by sequentially connecting the connecting lines of the edges of each surrounding road to generate the intersection surface of the target intersection, the intersection surface can be a complete polygonal region without gaps. Therefore, the method provided in this application is applicable to obtaining intersection surface rendering data for any intersection. That is, regardless of whether the width, shape, or number of surrounding roads connected to the intersection is consistent, the method of this application can be used to construct a complete intersection surface without gaps, improving the accuracy of intersection surface construction and thus improving the accuracy of the obtained intersection surface rendering data, expanding the applicable intersection scenarios of the method. Attached Figure Description

[0060] To more clearly illustrate the technical solutions in this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0061] Figure 1 This is a schematic diagram of an intersection;

[0062] Figure 2This is a schematic diagram of an intersection after road vectorization.

[0063] Figure 3 A flowchart illustrating a data processing method provided in an embodiment of this application;

[0064] Figure 4 A flowchart illustrating a process for obtaining precise raw data of surrounding roads at a target intersection, as provided in an embodiment of this application.

[0065] Figure 5 A schematic diagram of a first type of intersection provided for embodiments of this application. Figure 1 ;

[0066] Figure 6 A schematic diagram of a first type of intersection provided for embodiments of this application. Figure 2 ;

[0067] Figure 7 A schematic diagram illustrating a process for constructing a connection line between adjacent edges of the surrounding roads, provided in an embodiment of this application;

[0068] Figure 8 A schematic diagram of a first type of intersection provided for embodiments of this application. Figure 3 ;

[0069] Figure 9 A schematic diagram of a first type of intersection provided for embodiments of this application. Figure 4 ;

[0070] Figure 10 A schematic diagram illustrating another process for constructing a connection line between adjacent edges of the surrounding roads, provided as an embodiment of this application;

[0071] Figure 11 A schematic diagram of a second type of intersection provided in an embodiment of this application;

[0072] Figure 12 A schematic diagram of a first type of intersection provided for embodiments of this application. Figure 5 ;

[0073] Figure 13 A schematic diagram illustrating the process of constructing a connection line between the edge line of an internal road at an intersection and the edge lines of surrounding roads, provided as an embodiment of this application;

[0074] Figure 14 A schematic diagram of a third type of intersection provided in the embodiments of this application. Figure 1 ;

[0075] Figure 15 A schematic diagram of a third type of intersection provided in the embodiments of this application. Figure 2 ;

[0076] Figure 16A schematic diagram of a fourth type of intersection provided in an embodiment of this application;

[0077] Figure 17 A schematic diagram of a first type of intersection provided for embodiments of this application. Figure 6 ;

[0078] Figure 18 A schematic diagram of a first type of intersection provided for embodiments of this application. Figure 7 ;

[0079] Figure 19 A schematic diagram of a first type of intersection provided for embodiments of this application. Figure 8 ;

[0080] Figure 20 An example of an intersection surface generated based on the original, high-precision data of the road centerline at the intersection, provided in this application embodiment;

[0081] Figure 21 This is a schematic diagram of the structure of a data processing device provided in an embodiment of this application;

[0082] Figure 22 This is a schematic diagram of another data processing apparatus provided in an embodiment of this application;

[0083] Figure 23 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0084] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0085] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0086] Figure 1 Here is a schematic diagram of an intersection, combined with... Figure 1 The following is a description of the technical terms used in this application:

[0087] Stop line: A stop line located at a road intersection for vehicles waiting for a traffic signal to proceed.

[0088] Separation of lanes: There are physical barriers between the two directions of the road (such as stone blocks, fences, green belts, solid yellow lines on the ground, etc.).

[0089] Connecting lines: also known as intersection bend connecting lines, are connecting lines between adjacent roads leading to an intersection.

[0090] Intersection surface: The area where traffic flows from all directions cross outside the stop line at a road intersection.

[0091] Lane-level navigation is a technology that presents lanes and their connections to users and provides navigation based on lane accuracy. Lane navigation services based on this technology need to display lane-level navigation information to users, such as drivable lanes and navigation actions. Therefore, it is necessary to create a lane-level model of the base map upon which lane-level navigation relies.

[0092] Due to the limited production cost and update frequency of high-precision map data, some intersection surface rendering data are currently generated based on the standard-precision map data of the intersection, so that the intersection model built based on the intersection surface rendering data is as consistent as possible with the reality.

[0093] The refined raw dataset mentioned here refers to the refined raw dataset of the intersection obtained by vectorizing the roads involved in the intersection based on refined map data. This refined raw dataset includes the refined raw data of all roads involved in the intersection. The refined raw data may include: road topology, road type, road width, and the position of each point on the road centerline, etc.

[0094] In some embodiments, road topology, road type, and road width can also be referred to as the road's attribute information. The refined raw dataset of the intersection can also be referred to as the refined raw dataset based on the road centerline. It should be noted that the road centerline referred to here is a line located at the center of the road, that is, the line is equidistant from the left and right edges of the road.

[0095] The topological relationships of a road are used to characterize other roads that connect to it. For example, the topological relationships of a road can be represented by the connections between points located at the road endpoints and other points.

[0096] Road types are categorized as follows: virtual roads within intersections, roads with separate upper and lower lanes, roads without separate upper and lower lanes, main roads with separate upper and lower lanes (referred to as main roads), main roads without separate upper and lower lanes, auxiliary roads (referred to as auxiliary roads), U-turn roads, roads for early left turns, and roads within intersections. Among these, virtual roads within intersections refer to roads that are virtually created within an intersection, used to represent the approximate location of the intersection.

[0097] The following example illustrates the roads involved in an intersection. Figure 2 This is a schematic diagram of an intersection after road vectorization. Taking an intersection consisting of two roads, one of which includes a main road and two auxiliary roads, where the main road has separate upper and lower lanes, and the other road does not, as an example, the road centerlines of each road are obtained by vectorizing the roads based on high-resolution map data, as shown below. Figure 2 As shown.

[0098] It should be noted that during road vectorization, this applies to roads where the top and bottom lines are separated (e.g., Figure 2 For a main road running longitudinally, it is generally treated as the center line of two roads. If it is a road that is not separated by upper and lower lines (e.g.) Figure 2 Central and horizontal roads Figure 2 The longitudinal auxiliary roads and virtual roads inside intersections are processed into the center line of a single road.

[0099] in addition, Figure 2 This is merely an illustrative example and does not exhaustively list all types of roads that an intersection may include.

[0100] Currently, the main methods for generating intersection surface rendering data for this intersection using the standard and refined original dataset are as follows:

[0101] First, the road surfaces of the roads connecting to the intersection are generated using the standard and refined original dataset of the intersection. Then, the intersection of the road surfaces of the multiple roads connecting to the intersection is obtained by using polygon intersection calculation, and this intersection is used as the intersection surface to obtain the rendering data of the intersection surface. The surrounding roads mentioned here refer to roads distributed around the intersection and connected to the intersection.

[0102] However, some intersections may connect to surrounding roads of varying widths, shapes, or numbers, resulting in some adjacent roads (e.g., parallel or nearly parallel roads) not intersecting. This can lead to gaps in the intersection face obtained using polygon intersection methods, preventing it from connecting with all surrounding roads. In other words, intersection faces obtained using polygon intersection methods are prone to gaps, resulting in lower accuracy and causing discrepancies between the rendered intersection model and the actual intersection.

[0103] In view of this, this application provides a data processing method, apparatus, and storage medium that can obtain the standard raw data of the surrounding roads connected to the target intersection based on the standard raw dataset of the target intersection. After constructing the edges of each surrounding road, it can generate connecting lines between adjacent edges of the surrounding roads. Thus, by sequentially connecting the connecting lines of the edges of each surrounding road to generate the intersection surface of the target intersection, the intersection surface can be a complete polygonal region without any gaps.

[0104] Therefore, the method provided in this application embodiment can be applied to the acquisition of intersection surface rendering data for any intersection. That is, regardless of whether the width, shape, or number of surrounding roads connected to the intersection are consistent, the method of this application embodiment can be used to construct a complete intersection surface without any gaps, thus improving the accuracy of intersection surface construction and consequently improving the accuracy of the obtained intersection surface rendering data, and expanding the applicable intersection scenarios of the method.

[0105] The execution subject of the method in this application embodiment can be any electronic device with data processing capabilities, or it can be a data processing platform. It should be noted that the data processing platform can be deployed separately on an electronic device in any environment (e.g., deployed separately on an edge server in an edge environment), or it can be deployed entirely in a cloud environment, or it can be distributed and deployed in different environments.

[0106] For example, a data processing platform can be logically divided into multiple parts, each with different functions. These parts can be deployed in any two or three of the following environments: electronic devices (located on the user side), edge environments, and cloud environments. An edge environment is defined as a collection of edge electronic devices located close to the electronic devices, including edge servers and edge stations with computing power. The various parts of the data processing platform deployed in different environments or devices work together to achieve the platform's functions.

[0107] It should be understood that this application does not restrict the specific deployment environment of which parts of the data processing platform are deployed. In actual application, the deployment can be adapted according to the computing power of electronic devices, the resource availability of edge and cloud environments, or specific application requirements.

[0108] The methods of this application will be described in detail below with reference to specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments.

[0109] Figure 3 This is a flowchart illustrating a data processing method provided in an embodiment of this application. Figure 3 As shown, the method includes:

[0110] S101. Obtain the standard and refined raw data of the surrounding roads of the target intersection from the standard and refined raw dataset of the target intersection; wherein, the surrounding roads include roads entering and / or exiting the intersection. That is, the surrounding roads may only include roads entering the intersection, or only include roads exiting the intersection, or include both roads entering and exiting the intersection.

[0111] The target intersection can be any intersection in the base map that will be used to generate intersection surface rendering data from the original dataset.

[0112] It should be noted that the target intersection's original, high-precision dataset mentioned here can be obtained by vectorizing the roads involved in the target intersection based on high-precision map data. For details, please refer to the preceding content. That is, the target intersection's original, high-precision dataset can include: the original, high-precision data of the roads involved in the target intersection, where the original, high-precision data of the roads includes: road topology, road type, road width, and the position of each point on the road centerline, etc.

[0113] From the target intersection's standard and fine raw dataset, obtain the standard and fine raw data of the surrounding roads of the target intersection. The purpose of this step is to delineate the surrounding roads connected to the target intersection.

[0114] This application does not limit the method of obtaining the standardized raw data of the surrounding roads of the target intersection from the standardized raw dataset of the target intersection. One possible implementation is to classify roads that are neither internal virtual roads nor internal roads of the intersection as surrounding roads based on the type of each road in the standardized raw dataset of the target intersection.

[0115] Another possible approach is to first define the virtual roads within the intersection based on the topological relationships and road types of each road in the original dataset, and then, based on the topological relationships of the virtual roads within the intersection, obtain the roads that connect to the virtual roads within the intersection as surrounding roads.

[0116] S102. Generate the edge lines of the surrounding roads based on the road width and center line in the original data of the surrounding roads.

[0117] For example, based on the position of each point on the centerline of the surrounding roads and the width of those surrounding roads, the left and right lines of the surrounding roads are generated. Both the left and right lines are parallel to the centerline and equidistant from it. The distance between the left and right lines represents the width of the surrounding roads.

[0118] At this point, the surface formed between the left and right edges of the surrounding roads is the road surface of the surrounding roads. Therefore, in some embodiments, this step can also be referred to as generating the road surface of the surrounding roads based on the road width and road centerline in the original data of the surrounding roads.

[0119] S103. Construct connecting lines for the edges of adjacent surrounding roads.

[0120] A connecting line is a curved connecting line between adjacent edges of two roads.

[0121] One possible implementation is to connect two adjacent sidelines with a line, and then apply an arc to the connecting line based on the positional relationship between the two adjacent sidelines to obtain the connecting line between the adjacent sidelines.

[0122] Alternatively, different construction methods can be chosen based on the parallelism between two adjacent edges to construct their connecting lines. Parallelism is used to determine whether two edges are parallel or approximately parallel.

[0123] When two sidelines are parallel or nearly parallel, meaning they do not intersect, their connecting line can be constructed by considering their positional relationship. For example, if the two sidelines are facing each other, a spline can be used to connect them, serving as the connecting line. The spline mentioned here can be, for example, a quadratic, cubic, or quartic spline. As another example, if the two sidelines are parallel or nearly parallel in the same direction, their connecting line can be constructed by considering the virtual road within the intersection connecting them.

[0124] When the parallelism between two adjacent sidelines indicates that the two sidelines intersect, for example, a line with a preset arc can be used to connect the two sidelines as a connecting line.

[0125] This application does not limit the implementation method of obtaining the adjacency relationship of the edges of surrounding roads. For example, the adjacency relationship of surrounding roads in actual space can be obtained, and the edges of adjacent surrounding roads can be obtained based on the adjacency relationship. Another example is obtaining the adjacency relationship of the edges of surrounding roads input by the user.

[0126] S104. Generate intersection surface data for the target intersection based at least on the connecting lines of the edges of the surrounding roads.

[0127] For example, the endpoints of adjacent connecting lines can be connected according to the adjacency relationship of surrounding roads in actual space to form a polygon, and the endpoints of the surrounding roads can be moved back to the intersection of the polygon. At this time, the polygonal area is the intersection face of the target intersection.

[0128] This application does not limit the storage method after generating the intersection surface data of the target intersection; the specific method can be determined according to actual needs. For example, the position of each point on the intersection surface, as well as the connection relationship between the intersection surface and the surrounding roads, can be added to the map base map as intersection surface data. That is, the intersection surface rendering data includes: the position of each point on the intersection surface, and the connection relationship between the intersection surface and the surrounding roads. Subsequently, clients with this map base map installed can construct a model of the target intersection using the intersection surface rendering data of the target intersection, so as to clearly and accurately present the intersection information to the user during map display or during lane-level navigation. Taking lane-level navigation as an example, for instance, the connection relationship of roads, auxiliary information, and turning actions at the intersection can be displayed.

[0129] The data processing method provided in this application can obtain the standard raw data of the surrounding roads connected to the target intersection based on the standard raw dataset of the target intersection. After constructing the edges of each surrounding road, it can generate connecting lines between adjacent edges of the surrounding roads. Thus, by sequentially connecting the connecting lines of the edges of each surrounding road to generate the intersection surface of the target intersection, the intersection surface can be a complete polygonal region without gaps. Therefore, the method provided in this application can be applied to obtaining intersection surface rendering data for any intersection. That is, regardless of whether the width, shape, or number of surrounding roads connected to the intersection is consistent, the method of this application can be used to construct a complete intersection surface without gaps, improving the accuracy of intersection surface construction and thus improving the accuracy of the obtained intersection surface rendering data, expanding the applicable intersection scenarios of the method.

[0130] The following example illustrates how to obtain the standardized raw data of the surrounding roads of the target intersection from the standardized raw dataset of the target intersection:

[0131] Figure 4 This is a flowchart illustrating a process for obtaining precise raw data of surrounding roads at a target intersection, as provided in an embodiment of this application. Figure 4 As shown, step S101 above may include, for example:

[0132] S201. Based on the topological relationships and road types of each road in the refined original dataset, obtain a refined original data subset from the refined original dataset; the refined original data subset includes the topological relationships of virtual roads within intersections. For example, the refined original data subset may include the mapping relationship between the identifiers of virtual roads within intersections and the topological relationships of virtual roads within intersections.

[0133] In a possible implementation, by marking the types of each road in the refined original dataset, selecting a road whose type is an internal virtual road of an intersection as a reference, and searching for roads connected to it that are also internal virtual roads of the intersection based on the topological relationship of the reference internal virtual road of the intersection. Then, taking the found internal virtual road of the intersection as a new reference, searching for roads connected to it that are also internal virtual roads of the intersection based on the topological relationship of this new reference internal virtual road of the intersection, and so on, until all internal virtual roads of the intersection are obtained.

[0134] Figure 5 Schematic diagram of the first intersection provided in the embodiments of the present application Figure 1 , as Figure 5 shown, for example, it is assumed that initially the internal virtual road A in the target intersection is taken as the reference. Based on the topological relationship of internal virtual road A, internal virtual road B and internal virtual road C connected to internal virtual road A are found. Then, taking internal virtual road B as the reference, based on the topological relationship of internal virtual road B, internal virtual road D and internal virtual road E connected to internal virtual road B are found; meanwhile, taking internal virtual road C as the reference, based on the topological relationship of internal virtual road C, internal virtual road D and internal virtual road F connected to internal virtual road C are found. And so on, until all internal virtual roads of the intersection that are of the internal virtual road type of the intersection are obtained.

[0135] In this example, all internal virtual roads of the intersection in the target intersection, namely A, B, C, D, E, F, G, H, I, J, form a #-shaped region. The present application does not limit the shape formed by all internal virtual roads of the intersection that are of the internal virtual road type, which specifically depends on the actual situation of the intersection, for example, it may be a hollow square shape, a square shape, a # shape, etc.

[0136] Optionally, in some embodiments, before the above step S201, the method may further comprise: acquiring the refined original dataset of the target intersection.

[0137] One possible implementation involves acquiring high-resolution map data and vectorizing the roads involved in the target intersection based on the high-resolution map data to obtain the original high-resolution dataset of the target intersection. Alternatively, the original high-resolution dataset of the target intersection can be obtained by vectorizing the roads involved in the target intersection based on high-resolution map data from other devices or platforms. Alternatively, the original high-resolution dataset of the target intersection can be obtained from a connected storage medium or database, pre-vectorized based on high-resolution map data. This application does not limit the implementation method of obtaining the original high-resolution dataset of the target intersection by vectorizing the roads involved in the target intersection based on high-resolution map data; specific implementation methods can be found in existing methods.

[0138] S202. Based on the subset of the standardized and refined original data, obtain the standardized and refined original data of the surrounding roads of the target intersection from the standardized and refined original dataset.

[0139] One possible implementation is to obtain the standard raw data of surrounding roads connected to the M virtual roads within each intersection from the standard raw dataset, based on the topological relationship of the virtual roads within each intersection, and use this data as the standard raw data of the surrounding roads of the target intersection. For details on how to obtain surrounding roads based on topological relationships, please refer to section S201 on how to find other virtual roads within intersections based on topological relationships; the implementation method is similar and will not be elaborated further.

[0140] Another possible implementation is to use a subset of the standardized and refined original data to treat all roads in the standardized and refined original data, except for the virtual roads inside the intersection, as the surrounding roads of the target intersection, so as to obtain the standardized and refined original data of the surrounding roads of the target intersection.

[0141] In some embodiments, before obtaining the refined raw data of the surrounding roads of the target intersection from the refined raw dataset, it can be determined whether there exists a group of roads of type "separated upper and lower lanes" in the refined raw dataset, excluding the virtual roads inside the intersection. That is, a group of roads with the same identifier (or the same name), opposite directions, and all of type "separated upper and lower lanes". If such a group exists, the refined raw data of the group of roads of type "separated upper and lower lanes" is merged into the refined raw data of a single road in the refined raw dataset. This refined raw data includes: the position of each point on the centerline of the road when the "group of roads of type "separated upper and lower lanes" is considered as a single road, as well as the road's width, topological relationship, and type.

[0142] Then, based on the subset of the refined raw data, the refined raw data of the surrounding roads of the target intersection is obtained from the refined raw dataset. Still using... Figure 5Taking the intersection shown as an example, Figure 6 A schematic diagram of a first type of intersection provided for embodiments of this application. Figure 2 ,like Figure 6 As shown, with Figure 6 Taking a vertical road as an example, where the upper and lower lines are separate, after merging, the middle line becomes the center line of the merged road.

[0143] In this way, a group of roads that were previously separated by upper and lower boundaries can be merged into a single road, making it easier to treat them as a single road when connecting to intersections. This ensures that when generating road surfaces based on the refined original data of this road, each road in the previously separated group has the same width, improving both the parallelism and aesthetics of the two roads.

[0144] The following explains how to construct the connecting lines of adjacent surrounding roads:

[0145] Figure 7 This is a schematic diagram illustrating a process for constructing a connection line between the edges of adjacent surrounding roads, as provided in an embodiment of this application. Figure 7 As shown, step S103 above may include, for example, the following steps:

[0146] S301. Sort the surrounding roads based on the endpoints of the road centerlines; where the endpoints of the road centerlines are the endpoints of the surrounding roads that connect to the intersections.

[0147] Implementation method 1:

[0148] For example, based on the orientation or angle of the centerline of the surrounding roads in space (the angle mentioned here can be, for example, taking any point on the virtual road inside a certain intersection of the target intersection as the vertex of the angle, obtaining the angle formed by the endpoint of the centerline of the surrounding roads and the vertex, and the ray formed by "the ray starting from the vertex and heading towards the preset orientation"), the surrounding roads can be sorted in order of increasing angle or in order of decreasing angle.

[0149] Implementation method 2:

[0150] As mentioned above Figure 6 Taking the intersection shown as an example, Figure 8 A schematic diagram of a first type of intersection provided for embodiments of this application. Figure 3 ,like Figure 8 As shown, firstly, based on the endpoints of the center lines of the surrounding roads (i.e. Figure 8 The points marked with + in the middle are used to obtain a convex polygon with the endpoint of the road centerline as its vertex. Figure 8(Not shown in the image). For instructions on how to construct the convex polygon based on multiple endpoints, please refer to existing technologies; this application does not limit this method. Furthermore, this application does not limit the shape of the convex polygon; it can be determined based on the number and distribution of roads surrounding the target intersection.

[0151] Then, starting from the intersection of the centerline of any surrounding road and the convex polygon, the sorting order of the endpoints of the centerlines of the surrounding roads on the convex polygon can be obtained according to a preset rotation direction. The preset rotation direction mentioned here can be, for example, a counterclockwise rotation direction or a clockwise rotation direction.

[0152] Alternatively, the boundary of the convex polygon can be moved outward from the intersection so that the centerline of the surrounding roads intersects with the convex polygon. That is, while keeping the convex polygon's center point position unchanged, it can be enlarged to extend its boundary, resulting in a convex polygon with its boundary moved outward from the intersection (i.e.,...). Figure 8 (polygons in the text).

[0153] Starting from the intersection point of the centerline of any surrounding road and the convex polygon formed by moving the boundary outwards from the intersection, the intersection points are sorted according to a preset rotation direction. That is, the sorting order of the intersection points of the surrounding roads' centerlines on the convex polygon formed by moving the boundary outwards from the intersection is obtained, and this sorting order is used as the sorting order of the surrounding roads. For example, the distance between the intersection point of the surrounding roads' centerlines and the starting point along the preset rotation direction can be calculated, and the intersection points of the surrounding roads' centerlines and the convex polygon formed by moving the boundary outwards from the intersection can be sorted in ascending order of distance. This sorting order is then used as the sorting order of the surrounding roads.

[0154] Continue to refer to Figure 8 Assume there are four surrounding roads at the target intersection: surrounding road 0, surrounding road 1, surrounding road 2, and surrounding road 3. The intersection of surrounding road 0 and the convex polygon formed by moving the boundary outwards from the intersection is marked as intersection point 0; the intersection of surrounding road 1 and the convex polygon formed by moving the boundary outwards from the intersection is marked as intersection point 1; the intersection of surrounding road 2 and the convex polygon formed by moving the boundary outwards from the intersection is marked as intersection point 2; and the intersection of surrounding road 3 and the convex polygon formed by moving the boundary outwards from the intersection is marked as intersection point 3.

[0155] Taking intersection point 1 as the starting point and the preset rotation direction as counterclockwise as an example, in this implementation, the distance 2 between intersection point 2 and intersection point 1 along the counterclockwise direction can be calculated, the distance 3 between intersection point 3 and intersection point 1 along the counterclockwise rotation direction can be calculated, and the distance 0 between intersection point 0 and intersection point 1 along the counterclockwise rotation direction can be calculated. For details on how to calculate the distances, please refer to existing technologies.

[0156] As shown in the diagram, distance 0 > distance 3 > distance 2. Therefore, the sorting order obtained in this example is intersection 1, intersection 2, intersection 3, intersection 0.

[0157] It should be understood that this application does not limit which intersection point is used as the starting point. For example, the minimum intersection point can be used as the starting point according to the convex hull algorithm, or other rules can be used to select the intersection point as the starting point, etc. The specific settings can be made according to actual needs.

[0158] The order in which the intersection points of the centerlines of the surrounding roads obtained through the above method and the convex polygons after shifting the boundaries outwards from the intersections can be used as the order of the surrounding roads. Continue referring to... Figure 8 For example, the surrounding roads are sorted in the following order according to the preset rotation direction: surrounding road 1, surrounding road 2, surrounding road 3, surrounding road 0.

[0159] One possible implementation is to store the original, calibrated data of the surrounding roads of the target intersection in a subset manner. After sorting according to the aforementioned sorting order, the order of the original, calibrated data of the surrounding roads of the target intersection in the subset is adjusted so that the arrangement order of the calibrated data of the surrounding roads in the subset represents the sorting order of the surrounding roads of the target intersection according to a preset rotation direction.

[0160] Still with Figure 8 For example, suppose the original data of the surrounding roads in the initially obtained subset are sorted as follows: original data of surrounding road 1, original data of surrounding road 3, original data of surrounding road 2, and original data of surrounding road 0.

[0161] After obtaining the surrounding roads in the preset rotation direction as Surrounding Road 1, Surrounding Road 2, Surrounding Road 3, and Surrounding Road 0 through the above method, the original data of the surrounding roads in the adjusted subset are sorted as follows: original data of Surrounding Road 1, original data of Surrounding Road 2, original data of Surrounding Road 3, and original data of Surrounding Road 0.

[0162] Another possible implementation is to use an array to store the identifiers of the surrounding roads of the target intersection in the sorting order obtained above, so that the sorting order of the surrounding roads of the target intersection according to the preset rotation direction can be represented by the arrangement order of the identifiers of the surrounding roads in the array.

[0163] S302. Sort the surrounding roads and obtain the adjacency relationship of the edges of the surrounding roads.

[0164] That is, in the sorting, the adjacent surrounding roads have an adjacency relationship, and whether it is the left or right side line depends on the preset rotation direction.

[0165] As mentioned above Figure 6 Taking the intersection shown as an example, Figure 9 A schematic diagram of a first type of intersection provided for embodiments of this application. Figure 4 .like Figure 9 As shown in the example, based on the width of the surrounding road 0 and the position of each point on the centerline of the surrounding road 0, a result like this can be generated. Figure 9 The road surface of surrounding road 0 is shown; based on the width of surrounding road 1 and the position of each point on the centerline of surrounding road 1, a model like this can be generated. Figure 9 The road surface of the surrounding road 1 shown can be generated based on the width of the surrounding road 2 and the position of each point on the centerline of the surrounding road 2, as shown below. Figure 9 The road surface of the surrounding road 2 shown can be generated based on the width of the surrounding road 4 and the position of each point on the centerline of the surrounding road 4, as shown. Figure 9 The road surface of the surrounding road 4 is shown.

[0166] This means that the road surface of each surrounding road includes a center line, a left side line, and a right side line. The left and right side lines are parallel to the road center line, equidistant from it, and their endpoints are aligned with the endpoint of the road center line. The distance between the left and right side lines is the width of that surrounding road.

[0167] In this example, following the order of the four surrounding roads: surrounding road 1, surrounding road 2, surrounding road 3, and surrounding road 0, the adjacency relationship of the edges of these four surrounding roads is as follows: the right edge of surrounding road 1 is adjacent to the left edge of surrounding road 2, the right edge of surrounding road 2 is adjacent to the left edge of surrounding road 3, the right edge of surrounding road 3 is adjacent to the left edge of surrounding road 0, and the right edge of surrounding road 0 is adjacent to the left edge of surrounding road 1.

[0168] It should be noted that the above steps S301-S302 can be performed at any time after obtaining the standard raw data of the surrounding roads of the target intersection. For example, it can be performed before or after generating the edge lines of the surrounding roads.

[0169] S303. Based on the parallelism of the edges of adjacent surrounding roads, construct connecting lines for the edges of adjacent surrounding roads.

[0170] One possible implementation method, Figure 10 This is a schematic diagram illustrating another process for constructing a connection line between the edges of adjacent surrounding roads, provided as an embodiment of this application. Figure 10 As shown, step S303 may include, for example:

[0171] S3031. For any two adjacent perimeter roads, determine whether the parallelism between the two adjacent perimeter roads is less than or equal to a preset threshold.

[0172] For example, the angle between the edges of two adjacent surrounding roads (referred to as adjacent edges) can be obtained, and then the parallelism of the adjacent edges can be obtained based on the angle. Existing technologies can be consulted for methods to obtain the parallelism of two lines, and no limitations are imposed thereon. This parallelism is used to determine whether adjacent edges are parallel; the parallelism referred to here can mean absolute parallelism or approximate parallelism.

[0173] When the parallelism of the adjacent edge lines is greater than a preset threshold, it indicates that the adjacent edge lines are not approximately parallel, and can be processed in the manner of generating connecting lines as if they were not approximately parallel. That is, step S3033 is executed.

[0174] When the parallelism of adjacent edges is less than or equal to a preset threshold, it indicates that the adjacent edges are approximately parallel, and can then be processed by generating connecting lines in an approximately parallel manner. That is, step S3032 is executed.

[0175] S3032. Generate a connecting line between the two adjacent surrounding roads based on the direction of the edge lines and the endpoints of the edge lines.

[0176] Based on the directions and endpoints of the edges of two adjacent surrounding roads, the angle formed by their edges can be determined. If this angle is obtuse, meaning the adjacent edges form an angle close to 180°, then, in this scenario, a spline can be used to connect the edges of the two adjacent surrounding roads, based on their directions and endpoints, serving as the connecting line. The spline mentioned here can be, for example, a quadratic, cubic, or quartic spline. This method ensures tangential continuity of the roads to which the adjacent edges belong. Figure 11 A schematic diagram of a second type of intersection provided in an embodiment of this application, as shown below. Figure 11 As shown, Figure 11 The diagram shows the connection line between adjacent sides using cubic splines.

[0177] If the angle is acute, meaning adjacent edges form an angle close to 0°, it indicates that there is an internal road at the intersection, and the edge of the adjacent surrounding road intersects with the internal road. Therefore, a connecting line can be constructed between the edge of the internal road and the edge of the surrounding road based on the internal road and the edge of the adjacent surrounding road. The internal road referred to here is a road belonging to the target intersection, but whose endpoint does not connect to the target intersection. For details on how to construct the connecting line between the edge of the internal road and the edge of the surrounding road, please refer to the following description.

[0178] S3033. Extend the edges of the two adjacent surrounding roads to obtain the intersection of the edges of the two adjacent surrounding roads, and generate the connecting line of the edges of the two adjacent surrounding roads based on the intersection and the endpoints of the edges.

[0179] For example, the direction of two adjacent edges is determined by their intersection point. Then, based on the endpoints and directions of these two adjacent edges, splines are used to generate the connecting line between the edges of these two adjacent surrounding roads. The splines mentioned here can be, for example, cubic splines, quartic splines, etc.

[0180] Continue with Figure 9 For example, as shown, Figure 12 A schematic diagram of a first type of intersection provided for embodiments of this application. Figure 5 , combined Figure 9 and Figure 12 In this example, based on the following relationships—the right edge of surrounding road 1 being adjacent to the left edge of surrounding road 2, the right edge of surrounding road 2 being adjacent to the left edge of surrounding road 3, the right edge of surrounding road 3 being adjacent to the left edge of surrounding road 0, and the right edge of surrounding road 0 being adjacent to the left edge of surrounding road 1—the resulting connecting lines for each adjacent edge are as follows: Figure 14 As shown. It should be noted that... Figure 12 The surrounding roads and their boundary lines are not clearly marked. Please refer to [link / reference needed] for details. Figure 9 The marker in.

[0181] Repeat step S303 above until all the connecting lines between two adjacent edges are obtained.

[0182] As mentioned above, in some embodiments, the target intersection also includes internal roads, which are roads that belong to the target intersection but whose endpoints are not connected to the target intersection.

[0183] In this scenario, the standard raw data of the roads inside the target intersection can also be obtained from the standard raw dataset of the target intersection, and the edge lines of the roads inside the intersection can be generated based on the road width and road centerline in the standard raw data of the roads inside the intersection.

[0184] For example, based on the type of each road in the target intersection's refined raw dataset, refined raw data of type "intersection internal roads" can be obtained. For details on how to generate the edge lines of internal roads, please refer to the aforementioned description of how to generate the edge lines of surrounding roads.

[0185] In this scenario, in addition to constructing connecting lines between the edges of the surrounding roads of the target intersection, it is also possible to construct connecting lines between the edges of the roads inside the intersection and the edges of the surrounding roads; the surrounding roads referred to here are those adjacent to the roads inside the intersection. Accordingly, the intersection surface data of the target intersection can be generated based on the connecting lines of the edges of the surrounding roads and the connecting lines between the edges of the surrounding roads and the edges of the roads inside the intersection. That is, according to the adjacency relationship between the surrounding roads and the roads inside the intersection in actual space, the endpoints of adjacent connecting lines are connected to form a polygon, and the endpoints of the surrounding roads and the endpoints of the roads inside the intersection are moved back to the intersection of this polygon. At this point, the polygonal region is the intersection surface of the target intersection.

[0186] The following explains how to construct the connecting line between the edge line of the internal road of an intersection and the edge line of the surrounding roads:

[0187] Figure 13 This is a schematic diagram illustrating a process for constructing a connection line between the edge line of an internal road at an intersection and the edge lines of surrounding roads, provided as an embodiment of this application. Figure 13 As shown, the method includes:

[0188] S401. Determine the two intersection points of the edge lines of the two adjacent surrounding roads and the target edge line.

[0189] The target edge line is the edge line of the endpoint closest to the surrounding road.

[0190] For example, extend the edges of the two adjacent surrounding roads to obtain two intersection points between the edges of the two adjacent surrounding roads and the target edge.

[0191] S402. Determine whether the order of the intersection points is consistent with the order of the two adjacent surrounding roads.

[0192] The order of the intersection points is the sorting order of the intersection points on the target edge line obtained by the preset rotation direction.

[0193] If they match, proceed to step S403; if they do not match, i.e., the order of the intersection points is the opposite of the order of the two adjacent surrounding roads, proceed to step S404.

[0194] S403. Based on the intersection point and the endpoints of the two adjacent surrounding roads, generate a connection line between the two adjacent surrounding roads and the road edge inside the intersection.

[0195] For example, the directions of the two adjacent perimeter roads and the target perimeter road are determined by the intersection of the two adjacent perimeter roads and the target perimeter road. Then, based on the endpoints and directions of the two adjacent perimeter roads and the endpoints and directions of the target perimeter road, splines are used to generate the connecting line of the two adjacent perimeter roads.

[0196] Figure 14 A schematic diagram of a third type of intersection provided in the embodiments of this application. Figure 1 , Figure 15 A schematic diagram of a third type of intersection provided in the embodiments of this application. Figure 2 , combined Figure 14 and Figure 15 As shown, the order of the intersection points of the edges of the two adjacent surrounding roads and the target edge is consistent with the order of the two adjacent surrounding roads.

[0197] Assuming the internal roads of the intersection are as follows Figure 14 As shown, the three boundary lines formed by the adjacent boundary lines of the surrounding roads and the boundary lines of the road targets inside the intersection are as follows: Figure 15 As shown, the connecting line between the edge lines of the two adjacent surrounding roads and the edge lines of the roads inside the intersection is as follows. Figure 14 and Figure 15 As shown. In this way, the connection line between the edge lines of the two adjacent surrounding roads and the edge lines of the roads inside the intersection can be smoothly constructed.

[0198] S404. Obtain the intersection point of the two adjacent perimeter roads, and generate the connecting line of the two adjacent perimeter roads based on the intersection point and the endpoints of the perimeter roads.

[0199] For example, the direction of the two adjacent perimeter lines is determined by the intersection point formed by the edge lines of the two adjacent perimeter roads. Then, based on the endpoints and directions of the two adjacent perimeter lines, splines are used to generate the connecting line of the edge lines of the two adjacent perimeter roads.

[0200] Figure 16 This is a schematic diagram of a fourth type of intersection provided in an embodiment of this application. Figure 16 As shown, taking two adjacent surrounding roads, surrounding road A and surrounding road B, as an example, and assuming a counter-clockwise rotation direction, the order of surrounding roads A and B in this implementation is: surrounding road A first, then surrounding road B. However, the order of the intersection points of surrounding road A and the target edge line, and the order of the intersection points of surrounding road B and the target edge line, is: the intersection points of surrounding road B first, then the intersection points of surrounding road A. These are exactly the reverse orders.

[0201] In this scenario, the directions of surrounding roads A and B are determined by their intersection. Then, based on the endpoints and directions of surrounding roads A and B, spline lines are used to generate the connecting lines of the edges of these two adjacent surrounding roads, as shown below. Figure 16 As shown.

[0202] By using the above method, when there are internal roads at the target intersection, a connection line between the edge line of the internal road and the edge line of the surrounding roads adjacent to the internal road can be generated, which improves the accuracy of intersection surface construction, thereby improving the accuracy of the obtained intersection surface rendering data and expanding the applicable intersection scenarios of this method.

[0203] Optionally, in some embodiments, after constructing the connecting lines of the edges of the surrounding roads, the following operations may also be performed:

[0204] If both sides of the surrounding road are connected by connecting lines, that is, for a surrounding road with connecting lines for the left and right sides, it can be determined whether the deviation between the endpoints of the connecting lines for the left and right sides is greater than or equal to a preset deviation. In other words, whether the deviation between the endpoints of the connecting lines for the two sides is greater than or equal to a preset deviation.

[0205] If the deviation between the endpoints of the connecting lines of the two side lines is greater than or equal to the preset deviation, then the endpoint of the connecting line of one side line is used as a reference to adjust the endpoint of the connecting line of the other side line. For example, the farthest endpoint of the connecting lines of two intersection bends is used as the reference position of the endpoint of the surrounding road, and the endpoint of the connecting line of the other intersection bend is adjusted so that the deviation between the endpoints of the adjusted connecting lines of the left and right intersection bends is less than the preset deviation.

[0206] Continue with Figure 9 Taking the surrounding road 1 as an example, Figure 17 A schematic diagram of a first type of intersection provided for embodiments of this application. Figure 6 , combined Figure 9 and Figure 17 It can be seen that the widths of surrounding roads 0 and 2 are different, which causes a deviation between the endpoints of the connecting lines of the left and right sides of the surrounding road 1 that connects to surrounding roads 0 and 2.

[0207] Assuming the deviation is greater than or equal to the preset deviation, and the farthest endpoint of the connection lines of the left and right sides of surrounding road 1 is the endpoint of the right side connection line, the endpoint of the right side connection line can be used as a reference to adjust the position of the endpoint of the left side connection line. This achieves the purpose of adjusting the left side connection line so that the deviation between the endpoints of the adjusted left and right side connection lines is less than the preset deviation. For example, Figure 17 The connecting line of the left side shown by the dashed line is the connecting line of the left side after adjusting the endpoints.

[0208] This method ensures that when surrounding roads connect to an intersection, their ends are neat, or rather, straight lines, rather than diagonal lines. Generally, most surrounding roads connecting to an intersection have straight ends. Therefore, by focusing on the regularity of the connecting lines, this approach ensures that the final intersection surface matches the actual situation of the intersection as closely as possible, preventing the appearance of fragmented shapes at the intersection's boundaries.

[0209] If the deviation between the endpoints of the connecting line of the two side lines is less than the preset deviation, it means that when the surrounding road enters the intersection, the end face of the surrounding road is roughly neat and no processing is required.

[0210] As mentioned earlier, after constructing the connecting lines of the surrounding roads' edges, the endpoints of the connecting lines of adjacent intersection bends can be connected according to the adjacency relationship of the surrounding roads in actual space to form a polygon. Then, the endpoints of the surrounding roads are moved back to the intersection of this polygon. At this point, the polygonal area is the intersection face of the target intersection.

[0211] by Figure 14 For example, as shown, Figure 18 A schematic diagram of a first type of intersection provided for embodiments of this application. Figure 7 ,like Figure 18 As shown, assuming the connecting lines of the surrounding roads after adjusting the endpoints of the connecting lines are as follows: Figure 18 As shown, based on the adjacency relationship of the four roads, the endpoints of adjacent connecting lines are connected to form a polygon as shown. Figure 18 As shown.

[0212] Figure 19 A schematic diagram of a first type of intersection provided for embodiments of this application. Figure 8 ,like Figure 19 As shown, after obtaining Figure 18 After drawing the polygon shown, the endpoints of the surrounding roads are retracted to the intersection of the polygon to make the road surfaces of the surrounding roads align with the intersection surface. At this point, the intersection surface of the target intersection is as follows: Figure 19 As shown.

[0213] Figure 20 This application provides an embodiment of a rendering of an intersection surface generated based on the refined raw data of the road centerline at the intersection. For more complex integrated intersections, the intersection surface region obtained after modeling the intersection surface rendering data obtained through the method provided in this application is as follows: Figure 20 As shown.

[0214] pass Figure 20As can be seen from the example, compared with the existing technology that directly uses polygon intersection to generate intersection surfaces, the data processing method provided in this application focuses more on the regularity of the connecting lines, so that the boundary of the intersection surface will not have trivial points, nor will there be gaps in the intersection surface.

[0215] Furthermore, existing technologies that use polygon intersection to generate intersection surfaces cannot handle cases where adjacent roads are parallel or nearly parallel. This application, however, addresses intersections with diverse connecting roads by generating connecting lines using different methods based on the parallelism between adjacent edges. Therefore, the method provided in this application is applicable to acquiring intersection surface rendering data for any intersection in a map base map. That is, regardless of whether the width, shape, or number of surrounding roads connected to the intersection is consistent, the method of this application can be used to construct a complete intersection surface without gaps, improving the accuracy of intersection surface construction and thus the accuracy of the obtained intersection surface rendering data, expanding the applicable intersection scenarios of this method.

[0216] Furthermore, this application addresses intersections with diverse road connections by generating intersection bend connection lines in different ways based on the parallelism between adjacent edges. This can be seen as breaking down a complex problem into smaller problems for various scenarios. Thus, even if unsolvable issues arise with adjacent roads, a solution can be added for that specific scenario, facilitating algorithm expansion and enabling subsequent extensions to various data sets.

[0217] This application also provides a data processing method, which includes the following steps:

[0218] First, obtain the standard and refined raw data of the surrounding roads of the target intersection from the standard and refined raw dataset of the target intersection. The surrounding roads include roads that enter and / or exit the intersection.

[0219] Secondly, based on the endpoints of the road centerlines in the original data of the surrounding roads, a convex polygon with the endpoints of the road centerlines as vertices is obtained;

[0220] Finally, the convex polygon is used to obtain the sorting order of the surrounding roads. For example, the boundary of the convex polygon is moved outward from the intersection so that the center line of the surrounding roads intersects with the convex polygon; starting from any intersection point, the intersection points are sorted according to a preset rotation direction; the sorting of the intersection points is used as the sorting order of the surrounding roads.

[0221] This application does not limit the processing content after obtaining the sorting order of the surrounding roads as described above; the specific processing depends on the user's actual needs. Through the above sorting method, the sorting order of the surrounding roads at an intersection can be accurately determined, thus providing accurate data support for subsequent data processing of the surrounding roads and ensuring the accuracy of subsequent processing.

[0222] Regarding the implementation of the embodiments of this application, please refer to the above embodiment on how to sort the surrounding roads in the embodiment of generating the intersection surface data of the target intersection from the standard and refined original dataset of the target intersection, which will not be repeated here.

[0223] Figure 21 This is a schematic diagram of the structure of a data processing device provided in an embodiment of this application. Figure 21 As shown, the data processing device includes: an acquisition module 501, a first processing module 502, a construction module 503, and a second processing module 504. Among them,

[0224] The acquisition module 501 is used to acquire the standard and refined raw data of the surrounding roads of the target intersection from the standard and refined raw dataset of the target intersection, wherein the surrounding roads include roads that enter and / or exit the intersection;

[0225] The first processing module 502 is used to generate the edge lines of the surrounding roads based on the road width and road centerline in the standard original data of the surrounding roads.

[0226] Construction module 503 is used to construct the connection line of the edge lines of the adjacent surrounding roads;

[0227] The second processing module 504 is used to generate intersection surface data of the target intersection based at least on the connection lines of the edge lines of the surrounding roads.

[0228] One possible implementation is that the construction module 503 is specifically used to: sort the surrounding roads based on the endpoints of the road centerlines of the surrounding roads, wherein the endpoints are the endpoints connected to the intersection; obtain the adjacency relationship of the edges of the surrounding roads according to the sorting of the surrounding roads; and construct the connecting line of the edges of adjacent surrounding roads according to the parallelism of the edges of adjacent surrounding roads.

[0229] For example, the construction module 503 is specifically used to obtain a convex polygon with the endpoint of the road centerline as the vertex based on the endpoint of the road centerline, and to obtain the sorting order of the surrounding roads using the convex polygon.

[0230] For example, the construction module 503 is specifically used to move the boundary of the convex polygon outward from the intersection so that the center line of the surrounding road intersects with the convex polygon; starting from any intersection point, sort the intersection points according to a preset rotation direction; and use the sorting of the intersection points as the sorting of the surrounding roads.

[0231] In one possible implementation, the construction module 503 is specifically used to determine whether the parallelism of the edges of any two adjacent surrounding roads is less than or equal to a preset threshold; if the parallelism of the edges of the two adjacent surrounding roads is greater than the preset threshold, then the edges of the two adjacent surrounding roads are extended to obtain the intersection point of the edges of the two adjacent surrounding roads, and a connecting line of the edges of the two adjacent surrounding roads is generated based on the intersection point and the endpoints of the edges; if the parallelism of the edges of the two adjacent surrounding roads is less than or equal to the preset threshold, then a connecting line of the edges of the two adjacent surrounding roads is generated based on the direction of the edges of the two adjacent surrounding roads and the endpoints of the edges.

[0232] In one possible implementation, the target intersection further includes internal roads: the acquisition module 501 is further configured to acquire the standardized raw data of the internal roads of the target intersection from the standardized raw dataset of the target intersection; the first processing module 502 is further configured to generate the edge lines of the internal roads based on the road width and road centerline in the standardized raw data of the internal roads; the construction module 503 is further configured to construct the connecting lines between the edge lines of the internal roads and the edge lines of the surrounding roads; the second processing module 504 is specifically configured to generate the intersection surface data of the target intersection based on the connecting lines of the edge lines of the surrounding roads and the connecting lines between the edge lines of the surrounding roads and the edge lines of the internal roads.

[0233] In one possible implementation, the construction module 503 is specifically used to determine two intersection points between the edges of the two adjacent surrounding roads and the target edge, where the target edge is the edge closest to the endpoint of the surrounding road; if the order of the intersection points is consistent with the order of the two adjacent surrounding roads, then based on the intersection points and the endpoints of the edges of the two adjacent surrounding roads, a connecting line is generated between the edges of the two adjacent surrounding roads and the edge of the road inside the intersection; if the order of the intersection points is reversed compared to the order of the two adjacent surrounding roads, then the intersection points of the edges of the two adjacent surrounding roads are obtained, and based on the intersection points and the endpoints of the edges, a connecting line is generated between the edges of the two adjacent surrounding roads.

[0234] In one possible implementation, the construction module 503 is further configured to, after constructing the connecting lines of the adjacent perimeter roads, if both perimeter roads have connecting lines and the deviation between the endpoints of the connecting lines of the two perimeter roads is greater than or equal to a preset deviation, adjust the endpoint of the connecting line of one perimeter road as a reference.

[0235] The data processing apparatus provided in this application embodiment can perform the action of generating intersection surface data of the target intersection based on the standard and refined original dataset of the target intersection in the above method embodiment, that is... Figures 3 to 20 The content shown is implemented in a similar way and has similar technical effects, so it will not be described again here.

[0236] Figure 22 This is a schematic diagram of another data processing apparatus provided in an embodiment of this application. Figure 22 As shown, the data processing device includes: an acquisition module 601, a first processing module 602, and a second processing module 603. Among them,

[0237] The acquisition module 601 is used to acquire the standard and refined raw data of the surrounding roads of the target intersection from the standard and refined raw dataset of the target intersection, wherein the surrounding roads include roads that enter and / or exit the intersection;

[0238] The first processing module 602 is used to obtain a convex polygon with the endpoint of the road centerline as the vertex based on the endpoint of the road centerline in the original data of the surrounding roads.

[0239] The second processing module 603 is used to obtain the sorting order of the surrounding roads using the convex polygon. In one possible implementation, the second processing module 603 is specifically used to move the boundary of the convex polygon outwards from the intersection so that the center lines of the surrounding roads intersect with the convex polygon; starting from any intersection point, sort the intersection points according to a preset rotation direction; and use the sorted intersection points as the sorting order of the surrounding roads.

[0240] The data processing apparatus provided in this application embodiment can perform the action of obtaining the sorting order of the surrounding roads from the standard and refined original dataset of the target intersection in the above method embodiment. Its implementation principle and technical effect are similar, and will not be described again here.

[0241] Figure 23 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 23 As shown, the electronic device 700 may include at least one processor 701 and a memory 702.

[0242] Memory 702 is used to store programs. Specifically, the program may include program code, which includes computer operation instructions. Memory 702 may include high-speed RAM, and may also include non-volatile memory, such as at least one disk storage device.

[0243] The processor 701 is used to execute computer execution instructions stored in the memory 702 to implement the data processing method described in the foregoing method embodiments. The processor 701 may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application.

[0244] Optionally, the electronic device may also include a communication interface 703 for communicating with the outside world.

[0245] In practical implementation, if the communication interface 703, memory 702, and processor 701 are implemented independently, they can be interconnected via a bus to complete communication. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc., but this does not imply that there is only one bus or one type of bus.

[0246] Optionally, in a specific implementation, if the communication interface 703, memory 702, and processor 701 are integrated on a single chip, then the communication interface 703, memory 702, and processor 701 can communicate through an internal interface.

[0247] This application also provides a computer-readable storage medium, which may include various media capable of storing program code, such as a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk. Specifically, the computer-readable storage medium stores program instructions, which are used in the methods described in the above embodiments.

[0248] This application also provides a program product including executable instructions stored in a readable storage medium. At least one processor of an electronic device can read the executable instructions from the readable storage medium, and the at least one processor executes the executable instructions to cause the electronic device to perform the data processing methods provided in the various embodiments described above.

[0249] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application.

Claims

1. A data processing method, characterized in that, The method includes: From the target intersection's standard and refined raw dataset, obtain the standard and refined raw data of the surrounding roads of the target intersection, including roads leading into and / or exiting the target intersection; Based on the road width and road centerline in the standard original data of the surrounding roads, generate the edge lines of the surrounding roads; Based on the centerline endpoints of the surrounding roads, a convex polygon with the centerline endpoints of the roads as vertices is obtained, where the endpoints are the endpoints connected to the target intersection. The sorting order of the surrounding roads is obtained using the convex shape; Based on the order of the surrounding roads, obtain the adjacency relationship of the edges of the surrounding roads; For any two adjacent perimeter roads, determine whether the parallelism between the two adjacent perimeter roads is less than or equal to a preset threshold. If the parallelism of the edges of two adjacent surrounding roads is greater than the preset threshold, then the edges of the two adjacent surrounding roads are extended to obtain the intersection of the edges of the two adjacent surrounding roads, and a connecting line of the edges of the two adjacent surrounding roads is generated based on the intersection and the endpoints of the edges. If the parallelism of the edges of the two adjacent surrounding roads is less than or equal to the preset threshold, then a connecting line of the edges of the two adjacent surrounding roads is generated according to the direction of the edges and the endpoints of the edges. The intersection surface data of the target intersection is generated based at least on the connecting lines of the edges of the surrounding roads.

2. The method according to claim 1, characterized in that, The step of using the convex polygon to obtain the sorting order of the surrounding roads specifically includes: Move the boundary of the convex polygon outward from the intersection so that the center line of the surrounding road intersects with the convex polygon; Starting from any intersection point, sort the intersection points according to a preset rotation direction; The order of the intersection points is used as the order of the surrounding roads.

3. The method according to claim 1 or 2, characterized in that, in, If the target intersection also includes roads within the intersection, then the method further includes: From the standard and refined raw dataset of the target intersection, obtain the standard and refined raw data of the roads inside the target intersection; Based on the road width and road centerline in the original data of the roads inside the intersection, generate the edge lines of the roads inside the intersection; Construct a connecting line between the edge line of the internal road at the intersection and the edge line of the surrounding roads; The generation of intersection surface data for the target intersection, based at least on the connecting lines of the edges of the surrounding roads, specifically includes: The intersection surface data of the target intersection is generated based on the connecting lines of the edges of the surrounding roads and the connecting lines between the edges of the surrounding roads and the internal roads of the intersection.

4. The method according to claim 3, characterized in that, The construction of the connecting line between the edge line of the internal road at the intersection and the edge lines of the surrounding roads specifically includes: Determine the two intersection points of the two adjacent perimeter roads and the target perimeter, where the target perimeter is the perimeter closest to the endpoint of the perimeter road. If the order of the intersection points is consistent with the order of the two adjacent surrounding roads, then based on the intersection points and the endpoints of the edges of the two adjacent surrounding roads, a connection line is generated between the edges of the two adjacent surrounding roads and the edges of the roads inside the intersection. If the order of the intersection points is opposite to the order of the two adjacent surrounding roads, then the intersection point of the edges of the two adjacent surrounding roads is obtained, and the connecting line of the edges of the two adjacent surrounding roads is generated based on the intersection point and the endpoints of the edges.

5. The method according to claim 1 or 2, characterized in that, After constructing the connecting lines of the adjacent edges of the surrounding roads, the method further includes: If both sides of the surrounding road are connected by a connecting line, and the deviation between the endpoints of the connecting lines of the two sides is greater than or equal to a preset deviation, then the endpoint of the connecting line of one side is used as a reference to adjust the endpoint of the connecting line of the other side.

6. A data processing method, characterized in that, The method includes: From the target intersection's standard and refined raw dataset, obtain the standard and refined raw data of the surrounding roads of the target intersection, including roads leading into and / or exiting the target intersection; Based on the endpoints of the road centerlines in the original data of the surrounding roads, a convex polygon with the endpoints of the road centerlines as vertices is obtained; the endpoints are those connected to the target intersection. The sorting order of the surrounding roads is obtained using the convex shape; Based on the order of the surrounding roads, obtain the adjacency relationship of the edges of the surrounding roads; For any two adjacent perimeter roads, determine whether the parallelism between the two adjacent perimeter roads is less than or equal to a preset threshold. If the parallelism of the edges of two adjacent surrounding roads is greater than the preset threshold, then the edges of the two adjacent surrounding roads are extended to obtain the intersection of the edges of the two adjacent surrounding roads, and a connecting line of the edges of the two adjacent surrounding roads is generated based on the intersection and the endpoints of the edges. If the parallelism of the edges of two adjacent surrounding roads is less than or equal to the preset threshold, then a connecting line of the edges of the two adjacent surrounding roads is generated according to the direction of the edges and the endpoints of the edges.

7. The method according to claim 6, characterized in that, The step of obtaining the sorting order of the surrounding roads using the convex polygon includes: Move the boundary of the convex polygon outward from the intersection so that the center line of the surrounding road intersects with the convex polygon; Starting from any intersection point, sort the intersection points according to a preset rotation direction; The order of the intersection points is used as the order of the surrounding roads.

8. A data processing apparatus, characterized in that, The device includes: The acquisition module is used to acquire the standard and refined raw data of the surrounding roads of the target intersection from the standard and refined raw dataset of the target intersection. The surrounding roads include roads that enter and / or exit the target intersection. The first processing module is used to generate the edge lines of the surrounding roads based on the road width and road centerline in the standard original data of the surrounding roads; A construction module is used to obtain a convex polygon with the endpoint of the centerline of the surrounding road as its vertex, based on the endpoint of the centerline of the surrounding road. The endpoint is the endpoint connected to the target intersection. The sorting order of the surrounding roads is obtained using the convex shape; Based on the order of the surrounding roads, obtain the adjacency relationship of the edges of the surrounding roads; For any two adjacent perimeter roads, determine whether the parallelism between the two adjacent perimeter roads is less than or equal to a preset threshold. If the parallelism of the edges of two adjacent surrounding roads is greater than the preset threshold, then the edges of the two adjacent surrounding roads are extended to obtain the intersection of the edges of the two adjacent surrounding roads, and a connecting line of the edges of the two adjacent surrounding roads is generated based on the intersection and the endpoints of the edges. If the parallelism of the edges of the two adjacent surrounding roads is less than or equal to the preset threshold, then a connecting line of the edges of the two adjacent surrounding roads is generated according to the direction of the edges and the endpoints of the edges. The second processing module is used to generate intersection surface data of the target intersection based at least on the connecting lines of the edges of the surrounding roads.

9. A data processing apparatus, characterized in that, The device includes: The acquisition module is used to acquire the standard and refined raw data of the surrounding roads of the target intersection from the standard and refined raw dataset of the target intersection. The surrounding roads include roads that enter and / or exit the target intersection. The first processing module is used to obtain a convex polygon with the endpoint of the road centerline as the vertex based on the endpoint of the road centerline in the standard raw data of the surrounding roads; the endpoint is the endpoint connected to the target intersection. The second processing module is used to obtain the sorting order of the surrounding roads using the convex polygon; Based on the order of the surrounding roads, obtain the adjacency relationship of the edges of the surrounding roads; For any two adjacent perimeter roads, determine whether the parallelism between the two adjacent perimeter roads is less than or equal to a preset threshold. If the parallelism of the edges of two adjacent surrounding roads is greater than the preset threshold, then the edges of the two adjacent surrounding roads are extended to obtain the intersection of the edges of the two adjacent surrounding roads, and a connecting line of the edges of the two adjacent surrounding roads is generated based on the intersection and the endpoints of the edges. If the parallelism of the edges of two adjacent surrounding roads is less than or equal to the preset threshold, then a connecting line of the edges of the two adjacent surrounding roads is generated according to the direction of the edges and the endpoints of the edges.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1 to 7.

Images