Method and apparatus for determining a target road model

Abstract

This application discloses a method and apparatus for determining a target road model. The method includes: extracting a target road surface model associated with a target road element model from a road surface model to be fitted; projecting the target road surface model and the target road element model onto a target plane; determining the set of intersection points and the set of intersection segments of the target road surface model and the target road element model in the target plane, and determining a set of target constraint segments and a set of target interpolation points based on the set of intersection points, the set of intersection segments, and a pre-determined first constraint segment, wherein the set of target constraint segments is used to determine the edges of the triangular mesh corresponding to the target road model, and the set of target interpolation points is used to determine the vertices of the triangular mesh corresponding to the target road model; and determining the target road model based on the set of target constraint segments and the set of target interpolation points.

Description

Technical Field

[0001] This application relates to the field of three-dimensional road model construction technology, and more specifically, to a method and apparatus for determining a target road model. Background Technology

[0002] High-precision 3D maps are an indispensable foundational support for intelligent transportation fields such as vehicle-road cooperation, autonomous driving, smart ports, and smart parking. Compared to traditional high-precision maps, 3D high-precision maps can provide users with a clearer 3D scene reconstruction in complex intersections, tunnels, and elevated areas. One of the core issues in 3D high-precision maps is elevation accuracy. Addressing errors such as elevation overlap, stretching, and wrinkling among numerous road features is a crucial aspect of 3D high-precision map production. This is addressed through various methods, including fixed-grid interpolation algorithms and feature-based boundary interpolation algorithms. While fixed-grid interpolation algorithms perform well on ordinary urban roads and elevated highways due to relatively small and gentle elevation fluctuations, they suffer from significant elevation variations on elevated ramps, tunnel ramps, and mountain highways, resulting in overlapping issues after interpolation and a sharp increase in the amount of road feature data. Most feature-based boundary interpolation algorithms are used in fixed elevation scenarios, where the elevation values ​​are fixed in most areas, and only the elevations at elevated ramps and tunnels change. Moreover, the elevation changes are relatively gradual, so the amount of data does not change significantly after interpolation. However, the application scenarios are limited.

[0003] There is currently no effective solution to the above problems. Summary of the Invention

[0004] This application provides a method and apparatus for determining a target road model, which at least solves the technical problem that the application scope of road models constructed using fixed interpolation is limited.

[0005] According to one aspect of the embodiments of this application, a method for determining a target road model is provided, comprising: extracting a target road surface model associated with a target road element model from a road surface model to be fitted; projecting the target road surface model and the target road element model onto a target plane; determining a set of intersection points and a set of intersection segments of the target road surface model and the target road element model in the target plane, and determining a set of target constraint segments and a set of target interpolation points based on the set of intersection points, the set of intersection segments, and a pre-determined set of first constraint segments, wherein the set of target constraint segments is used to determine the edges of the triangular mesh corresponding to the target road model, and the set of target interpolation points is used to determine the vertices of the triangular mesh corresponding to the target road model; and determining the target road model according to the set of target constraint segments and the set of target interpolation points.

[0006] Optionally, determining the target constraint segment set based on the intersection point set, the intersection segment set, and a predetermined first constraint segment set includes: extracting three edges from each triangular mesh in the target road surface model and the road element model to obtain the first constraint segment set; truncating the first constraint segment in the first constraint segment set using the intersection point set and the intersection segment set to obtain an initial constraint segment set; removing initial constraint segments from the initial constraint segment set that do not meet the first preset condition to obtain a second constraint segment set; and merging the intersection segment set and the second constraint segment set to obtain the target constraint segment set.

[0007] Optionally, using the intersection point set and the intersection segment set to truncate the constraint segments in the first constraint segment set to obtain an initial constraint segment set includes: determining a target intersection point on each constraint segment in the first constraint segment set, wherein the target intersection point belongs to the intersection point set; truncating each first constraint segment in the first constraint segment set into multiple first truncated constraint segments according to the position of the target intersection point; determining the endpoints of intersection segments on each first constraint segment, wherein the intersection segments belong to the intersection segment set; truncating the multiple first constraint segments according to the intersection segment endpoints to obtain multiple second truncated segments; determining the first truncated constraint segments and the second truncated segments as initial constraint segments; and forming the initial constraint segment set from the multiple initial constraint segments.

[0008] Optionally, the step of removing initial constraint segments from the initial constraint segment set that do not meet the first preset condition to obtain a second constraint segment set includes: if the initial constraint segments in the initial constraint segment set belong to the target road surface model, determining the initial constraint segments not in the first region as initial constraint segments that do not meet the first preset condition, where the first region represents the range covered by the target road surface model; if the initial constraint segments in the initial constraint segment set belong to the target road surface model, determining the initial constraint segments whose two endpoints are both in the second region as initial constraint segments that do not meet the first preset condition, where the second region represents the range covered by the target road surface model; and removing all initial constraint segments from the initial constraint segment set that do not meet the first preset condition to obtain a second constraint segment set.

[0009] Optionally, the first region can be determined by: determining the number of triangular meshes associated with the edges of the triangular meshes in the target road feature model; determining the edges in the target road feature model with a number of one associated triangular meshes as target edges; connecting the endpoints of all target edges in sequence to form a target polygon; and determining the region defined by the target polygon as the first region.

[0010] Optionally, determining the target interpolation point set based on the intersection point set, the intersection segment set, and the predetermined first constraint segment includes: if the initial constraint segment in the initial constraint segment set belongs to the target road surface model and only one endpoint of the initial constraint segment in the initial constraint segment set is on the boundary of the first region, determining the endpoint of the initial constraint segment on the boundary of the first region as the target endpoint; determining the endpoint set composed of the target endpoints as the constraint point set; merging the intersection point set and the constraint point set to obtain the initial interpolation point set; and removing duplicates from the interpolation points in the initial interpolation point set to obtain the target interpolation point set.

[0011] Optionally, the interpolation points in the initial interpolation point set are deduplicated to obtain the target interpolation point set, including: determining interpolation points in the initial interpolation point set whose spacing is less than a preset distance threshold as the same group; determining the average coordinate of all interpolation points in the same group as the position of the target interpolation point, and replacing all interpolation points in the same group with the target interpolation point; and forming the target interpolation point set by combining all target interpolation points.

[0012] Optionally, determining the target road model based on the target constraint segment set and the target interpolation point set includes: determining the constraint segments in the target constraint segment set that coincide with the boundary of the first region as the boundary constraint segments of the target road model; determining the constraint segments in the target constraint segment set that do not coincide with the boundary of the first region as the internal constraint segments of the target road model; determining the boundary of the target road model using the boundary constraint segments; determining the internal constraint segments as the edges of the triangular mesh corresponding to the target road model; and determining the interpolation points in the target interpolation point set as the vertices of the triangular mesh corresponding to the target road model.

[0013] Optionally, extracting the target road surface model associated with the target road element model from the road surface model to be fitted includes: constructing a first directional bounding box corresponding to the road surface model to be fitted and a second directional bounding box corresponding to the target road element model; determining the first directional bounding box as the first root node and the second directional bounding box as the second root node; decomposing the first directional bounding box and the second directional bounding box sequentially according to a preset separation axis until the directional bounding boxes of the leaf nodes corresponding to the first root node and the second root node contain only one triangular mesh, thus obtaining a first directional bounding box tree and a second directional bounding box tree; traversing all nodes of the first directional bounding box tree and the second directional bounding box tree to determine the triangular mesh pairs that intersect with the second directional bounding box tree in the first directional bounding box tree; and determining the target road surface model associated with the target road element model in the road surface model to be fitted based on the intersecting triangular mesh pairs.

[0014] Optionally, determining the set of intersection points and the set of intersection segments of the target pavement model and the target road element model in the target plane includes: determining the initial set of intersection points and the initial set of intersection segments of the target pavement model and the target road element model in the target plane; determining the first elevation value of the initial intersection point in the target pavement model and the second elevation value of the initial intersection point in the target road element model; removing triangular meshes in the target pavement model and the target road element model whose difference between the first elevation value and the second elevation value is greater than a preset threshold; merging the triangular meshes in the target pavement model and the target road element model after the removal process, and determining the set of intersection points and the set of intersection segments based on the merged target pavement model and the target road element model.

[0015] Optionally, determining the set of intersection points and the set of intersection segments based on the merged target pavement model and the target road element model includes: determining the target triangle mesh pairs that intersect between the merged target pavement model and the target road element model; determining the intersection points and intersection segments of all target triangle mesh pairs in the target plane; performing deduplication processing on the intersection points and intersection segments of all target triangle mesh pairs to obtain target intersection points and target intersection segments; forming the set of intersection points from all target intersection points and forming the set of intersection segments from all target intersection segments.

[0016] According to another aspect of the embodiments of this application, a target road model determination apparatus is also provided, comprising: an extraction module for extracting a target road surface model associated with a target road feature model from a road surface model to be fitted; a projection module for projecting the target road surface model and the target road feature model onto a target plane; a first determination module for determining a set of intersection points and a set of intersection segments of the target road surface model and the target road feature model in the target plane, and determining a set of target constraint segments and a set of target interpolation points based on the set of intersection points, the set of intersection segments, and a pre-determined first constraint segment, wherein the set of target constraint segments is used to determine the edges of the triangular mesh corresponding to the target road model, and the set of target interpolation points is used to determine the vertices of the triangular mesh corresponding to the target road model; and a second determination module for determining the target road model according to the set of target constraint segments and the set of target interpolation points.

[0017] According to another aspect of the embodiments of this application, a non-volatile storage medium is also provided, wherein a program is stored in the non-volatile storage medium, and the program controls the device where the non-volatile storage medium is located to execute the above-mentioned method for determining the target road model when it runs.

[0018] According to another aspect of the embodiments of this application, a computer device is also provided, including: a memory and a processor, the processor being configured to run a program stored in the memory, wherein the program executes the above-described method for determining the target road model during runtime.

[0019] In this embodiment, a target pavement model associated with the target road element model is extracted from the pavement model to be fitted; the target pavement model and the target road element model are projected onto a target plane; the set of intersection points and the set of intersection segments of the target pavement model and the target road element model in the target plane are determined, and a set of target constraint segments and a set of target interpolation points are determined based on the set of intersection points, the set of intersection segments, and a pre-determined first constraint segment. The set of target constraint segments is used to determine the edges of the triangular mesh corresponding to the target road model, and the set of target interpolation points is used to determine the vertices of the triangular mesh corresponding to the target road model; the target constraint segment set and the target interpolation point set are used to determine the... The method of defining a target road model involves extracting a target road surface model associated with the target road element model from the road surface model to be fitted, and determining the set of intersection points and the set of intersection segments of the target road surface model and the target road element model in the target plane. Then, based on the set of intersection points, the set of intersection segments, and the pre-determined first constraint segments, the set of target constraint segments and the set of target interpolation points are determined. This achieves the goal of determining the interpolation points and constraint segments of the road model based on the spatial relationship between the target road surface model and the target road element model, thereby achieving the technical effect of accurately determining the interpolation points and constraint segments of the road model and solving the technical problem of the limited applicability of road models constructed by fixed interpolation. Attached Figure Description

[0020] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0021] Figure 1 This is a hardware structure block diagram of a computer terminal (or mobile device) for a method of determining a target road model according to an embodiment of this application;

[0022] Figure 2 This is a flowchart illustrating a method for determining a target road model according to this application;

[0023] Figure 3 This is a schematic diagram of an optional first constraint line segment truncation method according to an embodiment of this application;

[0024] Figure 4 This is a schematic diagram of an optional method for determining the region where an initial constraint line segment is located, according to an embodiment of this application.

[0025] Figure 5 This is a schematic diagram of another optional method for determining the region where the initial constraint line segment is located according to an embodiment of this application;

[0026] Figure 6 This is a schematic diagram of an optional interpolation point deduplication process according to an embodiment of this application;

[0027] Figure 7 This is a schematic diagram of an optional model coverage area determination method according to an embodiment of this application;

[0028] Figure 8 This is a schematic diagram of an optional boundary constraint line segment according to an embodiment of this application;

[0029] Figure 9 This is a schematic diagram of an optional method for finding the intersection points and intersection segments of coplanar triangles according to an embodiment of this application;

[0030] Figure 10 This is a schematic diagram of an optional target road model determination device according to an embodiment of this application. Detailed Implementation

[0031] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0032] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0033] In related technologies, to address errors such as significant elevation overlap, stretching, and wrinkling between features and roads, interpolation algorithms based on fixed grids and feature-based boundary interpolation algorithms are employed. Fixed grid-based interpolation algorithms perform well on ordinary urban roads and elevated roads due to relatively small and gradual elevation fluctuations. However, on elevated ramps, tunnel ramps, and mountain highways, significant elevation fluctuations result in overlapping issues after interpolation, and also lead to a sharp increase in the amount of road feature data. Feature-based boundary interpolation algorithms are mostly used in fixed-elevation scenarios, where elevation values ​​are fixed in most areas, with variations only at elevated ramps and tunnels, and these variations are relatively gradual, resulting in minimal changes in the amount of data after interpolation. Therefore, they have a limited applicability. To address this problem, this application provides a method embodiment for determining a target road model. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0034] The methods and embodiments provided in this application can be executed on mobile terminals, computer terminals, or similar computing devices. Figure 1 A hardware block diagram of a computer terminal (or mobile device) for implementing a method for determining a target road model is shown. Figure 1 As shown, the computer terminal 10 (or mobile device 10) may include one or more processors 102 (shown as 102a, 102b, ..., 102n in the figure) (processor 102 may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.), a memory 104 for storing data, and a transmission module 106 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of a BUS bus), a network interface, a power supply, and / or a camera. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the aforementioned electronic device. For example, computer terminal 10 may also include... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0035] It should be noted that the aforementioned one or more processors 102 and / or other data processing circuits are generally referred to herein as "data processing circuits". These data processing circuits may be embodied, in whole or in part, in software, hardware, firmware, or any other combination thereof. Furthermore, the data processing circuits may be a single, independent processing module, or may be integrated, in whole or in part, into any other element within the computer terminal 10 (or mobile device). As involved in the embodiments of this application, the data processing circuits serve as a processor control mechanism (e.g., selection of a variable resistor termination path connected to an interface).

[0036] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the method for determining the target road model in this embodiment. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, thereby realizing the aforementioned method for determining the target road model. The memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the computer terminal 10 via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0037] The transmission device 106 is used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by the communication provider of the computer terminal 10. In one example, the transmission device 106 includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission device 106 may be a Radio Frequency (RF) module, used for wireless communication with the Internet.

[0038] The display can be, for example, a touchscreen liquid crystal display (LCD) that allows the user to interact with the user interface of the computer terminal 10 (or mobile device).

[0039] Under the above operating environment, embodiments of this application provide a method for determining a target road model, such as... Figure 2 As shown, the method includes the following steps:

[0040] Step S202: Extract the target road surface model associated with the target road element model from the road surface model to be fitted;

[0041] Step S204: Project the target pavement model and the target road element model onto the target plane;

[0042] Step S206: Determine the set of intersection points and the set of intersection segments of the target pavement model and the target road element model in the target plane, and determine the set of target constraint segments and the set of target interpolation points based on the set of intersection points, the set of intersection segments and the pre-determined first constraint segments. The set of target constraint segments is used to determine the edges of the triangular mesh corresponding to the target road model, and the set of target interpolation points is used to determine the vertices of the triangular mesh corresponding to the target road model.

[0043] Step S208: Determine the target road model based on the target constraint line segment set and the target interpolation point set.

[0044] Through the above steps, it is possible to extract the target road surface model associated with the target road element model from the road surface model to be fitted, and determine the set of intersection points and the set of intersection segments of the target road surface model and the target road element model in the target plane. Then, based on the set of intersection points, the set of intersection segments, and the pre-determined first constraint segments, the set of target constraint segments and the set of target interpolation points are determined. This achieves the goal of determining the interpolation points and constraint segments of the road model based on the spatial relationship between the target road surface model and the target road element model, thereby achieving the technical effect of accurately determining the interpolation points and constraint segments of the road model and solving the technical problem of the limited applicability of using fixed interpolation to construct road models.

[0045] It should be noted that the target road element model includes, but is not limited to: ground printing, zebra crossings, pedestrian crossings and green belts, etc., and the road surface model includes, but is not limited to: the road surface model. Both the target road element model and the target road surface model are composed of multiple triangular meshes.

[0046] In step S202, the road surface model within the coverage area of ​​the target road element model is determined by the spatial relationship between the projection areas of the road surface model to be fitted and the target road element model on the target plane.

[0047] Then, by judging the elevation difference between the road element model and the road surface model, the multi-Z value area model at the elevated or tunnel location can be quickly eliminated, and the associated road model can be extracted, greatly reducing the cost of manual classification.

[0048] In steps S204 to S208, the intersection points and intersection segments of the extracted road model and road element model in the target plane are calculated, the spatial relationship between the intersection segments and the road element model is determined, and some intersection segments that do not conform to the rules are eliminated to obtain a set of intersection points and intersection segments. Each side of the triangle of the target pavement model and road element model is used as a constraint segment, and geometric breaks are performed based on the intersection points and intersection lines. The spatial positional relationship with the road element model and road model is determined, and intersection segments that do not conform to the rules are eliminated. The intersection point set and the first constraint segment set are merged. Duplicate segments and duplicate intersection points are removed based on the threshold to obtain a target constraint segment set and a target interpolation point set. Finally, based on the constraint Deluay triangulation algorithm (a triangulation algorithm), the road element model and pavement model are triangulated and reconstructed in combination with the target interpolation point set and the target constraint segment set to output the target road model.

[0049] Steps S202 to S208 are described below through specific embodiments.

[0050] In one alternative approach, determining the target constraint segment set based on the intersection point set, the intersection segment set, and a pre-determined first constraint segment set is accomplished through the following steps: extracting three edges from each triangular mesh in the target pavement model and the target road element model to obtain the first constraint segment set; truncating the constraint segments in the first constraint segment set using the intersection point set and the intersection segment set to obtain the initial constraint segment set; removing initial constraint segments from the initial constraint segment set that do not meet the first preset condition to obtain the second constraint segment set; and merging the intersection segment set and the second constraint segment set to obtain the target constraint segment set.

[0051] It should be noted that the three edges of each triangular mesh in the target pavement model and the target road element model are determined as the constraint segments in the first constraint segment set. After merging the intersection segment set and the second constraint segment set, in some embodiments of this application, it is also necessary to perform deduplication processing on the merged segment set to remove duplicate segments, thereby obtaining the target constraint segment set.

[0052] In one alternative approach, a target intersection point is determined on each constraint segment in a first set of constraint segments, wherein the target intersection point belongs to a set of intersection points; each first constraint segment in the first set of constraint segments is truncated into multiple first truncated constraint segments according to the position of the target intersection point; the endpoints of intersection segments on each first constraint segment are determined, wherein the intersection segments belong to a set of intersection segments; the multiple first constraint segments are truncated according to the endpoints of the intersection segments to obtain multiple second truncated segments; the first truncated constraint segments and the second truncated segments are determined as initial constraint segments, and the multiple initial constraint segments are combined to form the initial constraint segment set.

[0053] It should be noted that the constraint segments in the first set of constraint segments are determined as the first constraint segments.

[0054] Specifically, the intersection points in the intersection point set that exist on each of the first constraint line segments are determined as the target intersection points, such as... Figure 3 As shown in 3a, P0, P1, and P2 are three target intersection points on the first constraint line segment R. The first constraint line segment R is cut off sequentially according to the positions of P0, P1, and P2, as follows. Figure 3 As shown in 3b, four truncated constraint segments R1, R2, R3, and R4 are obtained. In some embodiments of this application, the first constraint segment set is truncated using the intersection segment set. It can be determined first whether the endpoints of the intersection segments in the intersection segment set are on the first constraint segment. If only one endpoint of the intersection segment S is on the first constraint segment R, then... Figure 3 As shown in 3c, by truncation at the endpoints, two truncated constraint line segments are obtained, as follows: Figure 3 As shown in 3d, R5 and R6 are used to determine the truncated constraint segments R1, R2, R3, R4, R5 and R6 as the initial constraint segments, forming the initial constraint segment set.

[0055] In another alternative approach, the intersection segment S has two endpoints on the first constraint segment R, such as... Figure 3 As shown in 3e, four truncation constraint segments are obtained by cutting according to the positions of the two endpoints.

[0056] Optionally, removing initial constraint segments from the initial constraint segment set that do not meet the first preset condition to obtain a second constraint segment set includes: if the initial constraint segments in the initial constraint segment set belong to the target road surface model, determining the initial constraint segments not in the first region as initial constraint segments that do not meet the first preset condition, where the first region is used to represent the range covered by the target road surface model; if the initial constraint segments in the initial constraint segment set belong to the target road surface model, determining the initial constraint segments with both endpoints in the second region as initial constraint segments that do not meet the first preset condition, where the second region is used to represent the range covered by the target road surface model; and removing all initial constraint segments from the initial constraint segment set that do not meet the first preset condition to obtain the second constraint segment set.

[0057] Specifically, if the initial constraint line segments in the initial constraint line segment set belong to the target road surface model, the spatial relationship between the initial constraint line segments and the first region is determined, such as... Figure 4 As shown in 4a, 4b, and 4c, if both endpoints of the initial constraint line segment Rs are on the boundary of the first region or inside the first region, then the initial constraint line segment Rs is determined to be within the first region, as follows: Figure 4 As shown in 4d, if neither of the two endpoints of the initial constraint line segment Rs is on the boundary of the first region or inside the first region, then it is determined that the initial constraint line segment Rs is not within the first region.

[0058] If the initial constraint line segments in the initial constraint line segment set belong to the target road element model, determine the spatial relationship between the initial constraint line segments and the second region, such as... Figure 5 As shown in 5a, 5b, and 5c, if both endpoints of the initial constraint line segment RFs are on the boundary of the second region or inside the second region, then the initial constraint line segment RFs is determined to be within the second region, as follows: Figure 5 As shown in 5d, the initial constraint line segment RFs has only one endpoint on the boundary of the second region, as... Figure 5 In Figure 5 As shown in f, neither of the two endpoints of the initial constraint line segment RFs is within the second region.

[0059] Optionally, determining the target interpolation point set based on the intersection point set, the intersection segment set, and the pre-determined first constraint segment includes: if the initial constraint segment in the initial constraint segment set belongs to the target road surface model and only one endpoint of the initial constraint segment in the initial constraint segment set is on the boundary of the first region, determining the endpoint on the boundary of the first region as the target endpoint; determining the endpoint set composed of the target endpoints as the constraint point set; merging the intersection point set and the constraint point set to obtain the initial interpolation point set; and removing duplicates from the interpolation points in the initial interpolation point set to obtain the target interpolation point set.

[0060] Specifically, such as Figure 4 As shown in 4f, if the initial constraint line segment Rs has only one endpoint on the boundary of the first region, then the endpoint of the initial constraint line segment Rs on the boundary of the first region is determined as the target endpoint.

[0061] In one optional approach, deduplication of interpolation points in the initial interpolation point set is performed to obtain a target interpolation point set, including: identifying interpolation points in the initial interpolation point set whose spacing is less than a preset distance threshold as the same group; determining the average coordinate of all interpolation points in the same group as the position of the target interpolation point, and replacing all interpolation points in the same group with the target interpolation point; and forming a target interpolation point set from all the target interpolation points.

[0062] In practical application scenarios, such as Figure 6 As shown, interpolation points in the initial interpolation point set whose spacing is less than a preset distance threshold are identified as the same group, thus obtaining the rightmost target interpolation point set.

[0063] Understandably, the method for deduplicating interpolation points is similar to the method for deduplicating constrained line segments.

[0064] Taking the set of line segments obtained by merging the set of intersecting line segments and the set of constrained line segments as an example, the method for deduplicating constrained line segments is as follows:

[0065] The set of line segments obtained by merging the set of intersecting line segments and the set of second constrained line segments is the set of line segments to be deduplicated.

[0066] In the set of line segments to be deduplicated, line segments whose spacing between line segments is less than a preset line segment distance threshold are identified as the same group; the average coordinate of all line segments in the same group is determined as the position of the target constraint line segment, and all line segments in the same group are replaced with the target constraint line segment; all target constraint line segments are combined into a target constraint line segment set.

[0067] In one alternative approach, the first region can be determined by: determining the number of triangular meshes associated with the edges of the triangular meshes in the target road feature model; identifying all edges in the target road feature model with a number of one associated triangular mesh as target edges; sequentially connecting the endpoints of all target edges to form a target polygon; and defining the region bounded by the target polygon as the first region.

[0068] Specifically, the edge-triangle topological relationships of the target road element model are first calculated as follows: Figure 7As shown in 7a, edge e0 is associated with two triangles t0 and t1, while edge e1 is associated with exactly one triangle t2. Whether an edge is a boundary is determined by the number of triangles it is associated with. If it is associated with only one triangle, then it is a boundary. This process is repeated for all triangle edges, ultimately resulting in the following... Figure 7 The set of all triangle sides in triangle 7b is obtained by connecting the first and last coordinates of the sides. Figure 7 The polygon shown in 7c represents the area covered by the target road feature model. The method for determining the area covered by the target road surface model is similar to that described above, and will not be repeated here.

[0069] In some embodiments of this application, determining the target road model based on the target constraint segment set and the target interpolation point set includes: determining the constraint segments in the target constraint segment set that coincide with the boundary of the first region as the boundary constraint segments of the target road model; determining the constraint segments in the target constraint segment set that do not coincide with the boundary of the first region as the internal constraint segments of the target road model; determining the boundary of the target road model using the boundary constraint segments; determining the internal constraint segments as the edges of the triangular mesh corresponding to the target road model; and determining the interpolation points in the target interpolation point set as the vertices of the triangular mesh corresponding to the target road model.

[0070] Specifically, such as Figure 8 As shown, Figure 8 In the diagram, b1 to b15 are boundary constraint segments, and the others are internal constraint segments.

[0071] In practical applications, the target road model is obtained by retriangulation based on the target constraint line segment set and the target interpolation point set.

[0072] In one optional approach, extracting the target road surface model associated with the target road element model from the road surface model to be fitted includes: constructing a first directional bounding box corresponding to the road surface model to be fitted and a second directional bounding box corresponding to the target road element model; determining the first directional bounding box as the first root node and the second directional bounding box as the second root node; sequentially decomposing the first directional bounding box and the second directional bounding box according to a preset separation axis until the directional bounding box of the leaf node corresponding to the first root node and the second root node contains only one triangular mesh, thus obtaining a first directional bounding box tree and a second directional bounding box tree; traversing all nodes of the first directional bounding box tree and the second directional bounding box tree to determine the triangular mesh pairs that intersect with the second directional bounding box tree in the first directional bounding box tree; and determining the target road surface model associated with the target road element model in the road surface model to be fitted based on the intersecting triangular mesh pairs.

[0073] It is understandable that the number of grids for road surfaces and road features is very large, and conventional indexing methods in related technologies are slow. By adopting the above method, based on a collision detection algorithm, indexing efficiency can be improved.

[0074] It should be noted that the preset separation axis can be set according to actual needs, such as the center point of the longest axis.

[0075] Optionally, the specific steps for determining the set of intersection points and the set of intersection segments of the target pavement model and the target road element model in the target plane are as follows: determining the initial set of intersection points and the initial set of intersection segments of the target pavement model and the target road element model in the target plane; determining the first elevation value of the initial intersection point in the target pavement model and the second elevation value of the initial intersection point in the target road element model; removing triangular meshes in the target pavement model and the target road element model whose difference between the first elevation value and the second elevation value is greater than a preset threshold; merging the triangular meshes in the target pavement model and the target road element model after the removal process, and determining the set of intersection points and the set of intersection segments based on the merged target pavement model and the target road element model.

[0076] It should be noted that the elevation value can be determined as follows: with the intersection point coordinates as (x, y), and the coordinates of the three vertices of the triangular mesh as V0(x0, y0, z0), V1(x1, y1, z1), and V2(x2, y2, z2), then the elevation value h = (1 - uv) * z o +u*z1+v*z2, where,

[0077]

[0078]

[0079] Given u∈[0,1] and v∈[0,1], determine the value of h to be valid and determine the difference between the first elevation value and the second elevation value.

[0080] In some embodiments of this application, the set of intersection points and the set of intersection segments are determined based on the merged target road surface model and the target road element model. This can be achieved by: determining the target triangle mesh pairs that intersect between the merged target road surface model and the target road element model; determining the intersection points and intersection segments of all target triangle mesh pairs in the target plane; performing deduplication on the intersection points and intersection segments of all target triangle mesh pairs to obtain target intersection points and target intersection segments; and forming the set of intersection points from all target intersection points and the set of intersection segments from all target intersection segments.

[0081] It should be noted that the method for determining the intersecting target triangle mesh pairs between the target pavement model and the target road element model after merging is similar to the method for extracting the target pavement model associated with the target road element model from the pavement model to be fitted. Both methods use a collision detection algorithm for extraction, which will not be elaborated here.

[0082] The method for determining the intersection points and intersection segments of all target triangle mesh pairs in the target plane is to first project the intersecting target triangle mesh pairs between the merged target pavement model and the target road element model onto the target plane, and then determine the intersection points and intersection segments using a coplanar triangle intersection algorithm, such as... Figure 9 As shown, Figure 9 The diagram illustrates six types of intersection problems involving coplanar triangles, where M represents the number of line segments and N represents the number of intersection points. After determining the intersection points and line segments, deduplication can be performed to improve the accuracy of finding duplicates. The deduplication method is similar to... Figure 6 The deduplication method for the interpolation points shown is similar and will not be repeated here.

[0083] This application provides a device for determining a target road model, such as... Figure 10 As shown, it includes: an extraction module 90, used to extract a target road surface model associated with a target road element model from a road surface model to be fitted; a projection module 92, used to project the target road surface model and the target road element model onto a target plane; a first determination module 94, used to determine the set of intersection points and the set of intersection lines of the target road surface model and the target road element model in the target plane, and to determine the set of target constraint lines and the set of target interpolation points based on the set of intersection points, the set of intersection lines, and a pre-determined first constraint line segment, wherein the set of target constraint lines is used to determine the edges of the triangular mesh corresponding to the target road model, and the set of target interpolation points is used to determine the vertices of the triangular mesh corresponding to the target road model; and a second determination module 96, used to determine the target road model according to the set of target constraint lines and the set of target interpolation points.

[0084] The first determining module 94 includes: an extraction submodule, a truncation submodule, a removal submodule, a target submodule, and a region determining submodule. The extraction submodule is used to extract the three edges of each triangular mesh in the target pavement model and road element model to obtain a first set of constraint line segments; truncate the constraint line segments in the first set of constraint line segments using the intersection point set and the intersection line segment set to obtain an initial set of constraint line segments; remove the initial constraint line segments in the initial set of constraint line segments that do not meet the first preset condition to obtain a second set of constraint line segments; and merge the intersection line segment set and the second set of constraint line segments to obtain a target set of constraint line segments.

[0085] The truncation submodule is used to determine the target intersection point on each constraint segment in the first constraint segment set, where the target intersection point belongs to the intersection point set; to truncate each first constraint segment in the first constraint segment set into multiple first truncated constraint segments according to the position of the target intersection point; to determine the endpoint of the intersection segment on each first constraint segment, where the intersection segment belongs to the intersection segment set; to truncate multiple second truncated constraint segments according to the endpoint of the intersection segment, to determine the first truncated constraint segments and the second truncated constraint segments as initial constraint segments, and to form an initial constraint segment set from the multiple initial constraint segments.

[0086] The elimination submodule is used to determine initial constraint segments that are not in the first region as initial constraint segments that do not meet the first preset condition, when the initial constraint segments in the initial constraint segment set belong to the target road surface model. The first region is used to represent the range covered by the target road element model. When the initial constraint segments in the initial constraint segment set belong to the target road element model, the initial constraint segments whose two endpoints are both in the second region are determined as initial constraint segments that do not meet the first preset condition, when the second region is used to represent the range covered by the target road surface model. All initial constraint segments that do not meet the first preset condition are eliminated from the initial constraint segment set to obtain the second constraint segment set.

[0087] The target submodule is used to determine the endpoint of the initial constraint line segment on the first region boundary as the first endpoint when the initial constraint line segment in the initial constraint line segment set belongs to the target road surface model and only one endpoint of the initial constraint line segment in the initial constraint line segment set is on the first region boundary; determine the endpoints of all second constraint line segments in the second constraint line segment set as the second endpoints; determine the endpoint set composed of the first endpoint and the second endpoint as the constraint point set; merge the intersection point set and the constraint point set to obtain the initial interpolation point set; and remove duplicates from the interpolation points in the initial interpolation point set to obtain the target interpolation point set.

[0088] The region determination submodule is used to determine the number of triangular meshes associated with the edges of the triangular meshes in the target road feature model; determine the edges in the target road feature model with a number of one associated triangular meshes as target edges; connect the endpoints of all target edges in sequence to form a target polygon; and determine the region defined by the target polygon as the first region.

[0089] The target submodule includes: a deduplication unit, which is used to determine interpolation points in the initial interpolation point set whose spacing is less than a preset distance threshold as the same group; determine the average coordinate of all interpolation points in the same group as the position of the target interpolation point, and replace all interpolation points in the same group with the target interpolation point; and form a target interpolation point set by combining all target interpolation points.

[0090] The second determining module 96 includes a determining submodule, which is used to determine the constraint line segments in the target constraint line segment set that coincide with the boundary of the first region as the boundary constraint line segments of the target road model; determine the constraint line segments in the target constraint line segment set that do not coincide with the boundary of the first region as the internal constraint line segments of the target road model; determine the boundary of the target road model using the boundary constraint line segments; determine the internal constraint line segments as the edges of the triangular mesh corresponding to the target road model; and determine the interpolation points in the target interpolation point set as the vertices of the triangular mesh corresponding to the target road model.

[0091] Extraction module 90 includes: extraction submodule and intersection submodule; extraction submodule is used to construct a first direction bounding box corresponding to the road surface model to be fitted and a second direction bounding box corresponding to the target road element model; the first direction bounding box is determined as the first root node and the second direction bounding box is determined as the second node; the first direction bounding box and the second direction bounding box are decomposed sequentially according to a preset separation axis until the direction bounding box of the leaf node corresponding to the first root node and the second root node contains only one triangular mesh, thus obtaining the first direction bounding box tree and the second direction bounding box tree; all nodes of the first direction bounding box tree and the second direction bounding box tree are traversed to determine the triangular mesh pairs that intersect with the second direction bounding box tree in the first direction bounding box tree; and the target road surface model associated with the target road element model in the road surface model to be fitted is determined based on the intersecting triangular mesh pairs.

[0092] The intersection point submodule is used to determine the initial intersection point set and the initial intersection segment set of the target pavement model and the target road element model in the target plane; determine the first elevation value of the initial intersection point in the target pavement model and the second elevation value of the initial intersection point in the target road element model; remove triangular meshes in the target pavement model and the target road element model whose difference between the first elevation value and the second elevation value is greater than a preset threshold; merge the triangular meshes in the target pavement model and the target road element model after the removal process, and determine the intersection point set and the intersection segment set based on the merged target pavement model and the target road element model.

[0093] The intersection point submodule includes: a determination unit, which is used to determine the target triangular mesh pairs that intersect between the target pavement model and the target road element model after merging; determine the intersection points and intersection segments of all target triangular mesh pairs in the target plane; perform deduplication processing on the intersection points and intersection segments of all target triangular mesh pairs to obtain target intersection points and target intersection segments; and form the intersection point set and the intersection segment set by forming all target intersection points and all target intersection segments.

[0094] According to another aspect of the embodiments of this application, a non-volatile storage medium is also provided, wherein a program is stored in the non-volatile storage medium, and the program controls the device where the non-volatile storage medium is located to execute the above-mentioned method for determining the target road model when it runs.

[0095] According to another aspect of the embodiments of this application, a computer device is also provided, including: a memory and a processor, the processor being configured to run a program stored in the memory, wherein the program executes the above-described method for determining the target road model during runtime.

[0096] It should be noted that each module in the above-mentioned target road model determination device can be a program module (e.g., a set of program instructions to implement a certain function) or a hardware module. For the latter, it can be expressed in the following forms, but is not limited to them: each of the above modules is expressed as a processor, or the functions of each of the above modules are implemented by a processor.

[0097] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0098] In the above embodiments of this application, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0099] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual couplings, direct couplings, or communication connections may be through some interfaces; indirect couplings or communication connections between units or modules may be electrical or other forms.

[0100] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0101] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0102] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to related technologies, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard drive, magnetic disk, or optical disk.

[0103] The above are merely preferred embodiments of this application. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A method of determining a target road model, characterized by, include: Extract the target road surface model associated with the target road element model from the road surface model to be fitted; Project the target road surface model and the target road element model onto the target plane; The set of intersection points and the set of intersection lines of the target road surface model and the target road element model in the target plane are determined. Based on the set of intersection points, the set of intersection lines, and a pre-determined set of first constraint lines, the set of target constraint lines and the set of target interpolation points are determined. The set of target constraint lines is used to determine the edges of the triangular mesh corresponding to the target road model, and the set of target interpolation points is used to determine the vertices of the triangular mesh corresponding to the target road model. The target road model is determined based on the target constraint line segment set and the target interpolation point set; The step of determining the target constraint segment set based on the intersection point set, the intersection segment set, and a pre-determined first constraint segment set includes: extracting three edges from each triangular mesh in the target road surface model and the road element model to obtain the first constraint segment set; truncating the first constraint segment in the first constraint segment set using the intersection point set and the intersection segment set to obtain an initial constraint segment set; removing initial constraint segments from the initial constraint segment set that do not meet the first preset condition to obtain a second constraint segment set; and merging the intersection segment set and the second constraint segment set to obtain the target constraint segment set. The step of removing initial constraint segments from the initial constraint segment set that do not meet the first preset condition to obtain a second constraint segment set includes: when the initial constraint segments in the initial constraint segment set belong to the target road surface model, determining initial constraint segments not in a first region as initial constraint segments that do not meet the first preset condition, where the first region represents the area covered by the target road surface model; when the initial constraint segments in the initial constraint segment set belong to the target road surface model, determining initial constraint segments with both endpoints in a second region as initial constraint segments that do not meet the first preset condition, where the second region represents the area covered by the target road surface model; and removing all initial constraint segments from the initial constraint segment set that do not meet the first preset condition to obtain a second constraint segment set. Determining the target interpolation point set based on the intersection point set, the intersection segment set, and the pre-determined first constraint segment includes: determining the endpoint of the initial constraint segment on the first region boundary as the target endpoint when the initial constraint segment in the initial constraint segment set belongs to the target road surface model and only one endpoint of the initial constraint segment in the initial constraint segment set is on the boundary of the first region; determining the endpoint set composed of the target endpoints as the constraint point set; merging the intersection point set and the constraint point set to obtain the initial interpolation point set; and removing duplicates from the interpolation points in the initial interpolation point set to obtain the target interpolation point set.

2. The method of claim 1, wherein, By truncating the constraint segments in the first constraint segment set using the intersection point set and the intersection segment set, an initial constraint segment set is obtained, including: Determine the target intersection point on each first constraint line segment in the first constraint line segment set, wherein the target intersection point belongs to the intersection point set; Each first constraint line segment in the first constraint line segment set is cut into multiple first truncated constraint line segments according to the position of the target intersection point; Determine the endpoints of the intersecting segments present on each of the first constraint segments, wherein the intersecting segments belong to the set of intersecting segments; The multiple first constraint segments are cut off according to the endpoints of the intersection segments to obtain multiple second cut-off segments. The first cut-off constraint segments and the second cut-off segments are determined as initial constraint segments, and the multiple initial constraint segments are combined into the initial constraint segment set.

3. The method of claim 1, wherein, The first region is determined by the following methods: Determine the number of edge-associated triangle meshes in the triangle mesh of the target road feature model; The edges in the target road feature model where the number of associated triangular meshes is one are identified as target edges. Connect the first and last endpoints of all target edges sequentially to form the target polygon; The area defined by the target polygon is determined as the first area.

4. The method according to claim 1, characterized in that, The interpolation points in the initial interpolation point set are deduplicated to obtain the target interpolation point set, which includes: Interpolation points in the initial interpolation point set whose spacing is less than a preset distance threshold are identified as the same group; The average coordinates of all interpolation points in the same group are used to determine the location of the target interpolation point, and the target interpolation point replaces all interpolation points in the same group. All target interpolation points are combined into the target interpolation point set.

5. The method according to claim 1, characterized in that, The target road model is determined based on the target constraint line segment set and the target interpolation point set, including: The constraint line segments in the target constraint line segment set that coincide with the boundary of the first region are determined as the boundary constraint line segments of the target road model; The constraint line segments in the target constraint line segment set that do not coincide with the boundary of the first region are determined as the internal constraint line segments of the target road model; The boundary of the target road model is determined using the boundary constraint line segments; The internal constraint line segments are defined as the edges of the triangular mesh corresponding to the target road model, and the interpolation points in the target interpolation point set are defined as the vertices of the triangular mesh corresponding to the target road model.

6. The method according to claim 1, characterized in that, Extracting the target road surface model associated with the target road feature model from the road surface model to be fitted includes: Construct a first bounding box corresponding to the road surface model to be fitted and a second bounding box corresponding to the target road element model; The first directional bounding box is determined as the first root node, and the second directional bounding box is determined as the second root node; The first directional bounding box and the second directional bounding box are decomposed sequentially according to the preset separation axis until the directional bounding box of the leaf node corresponding to the first root node and the second root node contains only one triangular mesh, thus obtaining the first directional bounding box tree and the second directional bounding box tree. Traverse all nodes of the first direction bounding box tree and the second direction bounding box tree to determine the triangular mesh pairs that intersect with the second direction bounding box tree in the first direction bounding box tree; Based on the intersecting triangular mesh pairs, the target road surface model associated with the target road element model is determined in the road surface model to be fitted.

7. The method according to claim 1, characterized in that, Determining the set of intersection points and the set of intersection segments of the target pavement model and the target road element model in the target plane includes: Determine the initial set of intersection points and the initial set of intersection segments of the target pavement model and the target road element model in the target plane; The first elevation value of the initial intersection point in the target pavement model and the second elevation value of the initial intersection point in the target road element model are determined respectively. Triangular meshes in the target pavement model and the target road element model where the difference between the first elevation value and the second elevation value is greater than a preset threshold are removed; The triangular meshes in the target road surface model and the target road element model that have undergone the removal process are merged, and the set of intersection points and the set of intersection segments are determined based on the merged target road surface model and the target road element model.

8. The method according to claim 7, characterized in that, Based on the merged target pavement model and target road element model, the set of intersection points and the set of intersection segments are determined, including: Identify the target triangular mesh pairs that intersect between the target pavement model and the target road element model after the merging is completed; Determine the intersection points and line segments of all target triangle mesh pairs in the target plane; The intersection points and intersection segments of all the target triangle mesh pairs are deduplicated to obtain the target intersection points and target intersection segments; All target intersection points are grouped into the intersection point set, and all target intersection line segments are grouped into the intersection line segment set.

9. A device for determining a target road model, characterized in that, include: The extraction module is used to extract the target road surface model associated with the target road feature model from the road surface model to be fitted; The projection module is used to project the target road surface model and the target road element model onto the target plane; The first determining module is used to determine the set of intersection points and the set of intersection segments of the target road surface model and the target road element model in the target plane, and to determine the set of target constraint segments and the set of target interpolation points based on the set of intersection points, the set of intersection segments and the pre-determined first constraint segments. The set of target constraint segments is used to determine the edges of the triangular mesh corresponding to the target road model, and the set of target interpolation points is used to determine the vertices of the triangular mesh corresponding to the target road model. The second determining module is used to determine the target road model based on the target constraint line segment set and the target interpolation point set; The first determining module is further configured to determine the target constraint segment set based on the intersection point set, the intersection segment set, and a pre-determined first constraint segment set, including: extracting three edges of each triangular mesh in the target road surface model and the road element model to obtain the first constraint segment set; truncating the first constraint segment in the first constraint segment set using the intersection point set and the intersection segment set to obtain an initial constraint segment set; removing initial constraint segments in the initial constraint segment set that do not meet the first preset condition to obtain a second constraint segment set; and merging the intersection segment set and the second constraint segment set to obtain the target constraint segment set. The step of removing initial constraint segments from the initial constraint segment set that do not meet the first preset condition to obtain a second constraint segment set includes: when the initial constraint segments in the initial constraint segment set belong to the target road surface model, determining initial constraint segments not in a first region as initial constraint segments that do not meet the first preset condition, where the first region represents the area covered by the target road surface model; when the initial constraint segments in the initial constraint segment set belong to the target road surface model, determining initial constraint segments with both endpoints in a second region as initial constraint segments that do not meet the first preset condition, where the second region represents the area covered by the target road surface model; and removing all initial constraint segments from the initial constraint segment set that do not meet the first preset condition to obtain a second constraint segment set. Determining the target interpolation point set based on the intersection point set, the intersection segment set, and the pre-determined first constraint segment includes: determining the endpoint of the initial constraint segment on the first region boundary as the target endpoint when the initial constraint segment in the initial constraint segment set belongs to the target road surface model and only one endpoint of the initial constraint segment in the initial constraint segment set is on the boundary of the first region; determining the endpoint set composed of the target endpoints as the constraint point set; merging the intersection point set and the constraint point set to obtain the initial interpolation point set; and removing duplicates from the interpolation points in the initial interpolation point set to obtain the target interpolation point set.

10. A non-volatile storage medium, characterized in that, The non-volatile storage medium stores a program, wherein when the program is executed, it controls the device where the non-volatile storage medium is located to execute the target road model method according to any one of claims 1 to 8.

11. A computer device, characterized in that, include: A memory and a processor, the processor being configured to run a program stored in the memory, wherein the program, when executed, performs the target road model method according to any one of claims 1 to 8.

Images