Intersection surface generation method, intersection surface generation device, computer device, and computer program
The method addresses the inaccuracy of conventional geometry algorithms by using road surface width and constraint-based calculations to generate precise intersection surfaces, improving map data accuracy and scalability for navigation and autonomous driving.
Patent Information
- Application Number
- JP2024532541
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2022-05-31
- Filing Date
- 2023-02-21
- Publication Date
- 2024-11-15
- Estimated Expiration
- 2043-02-21
AI Technical Summary
Conventional pure geometry algorithms for generating intersection surfaces in electronic maps are inaccurate due to road shape point errors and poor scalability, especially in complex scenarios, leading to inaccuracies in intersection surface calculations.
A method that generates intersection surfaces by obtaining road information, determining road surface width, and using constraints and target functions to calculate offset distances, eliminating the need for complex geometry algorithms, and ensuring accurate intersection surface generation.
This method allows for the effective and accurate generation of intersection surfaces in complex road scenarios, enhancing map data accuracy and scalability, and supporting navigation and autonomous driving applications.
Smart Images

Figure 2024542706000001_ABST
Abstract
Description
[Technical field]
[0001] This application was filed with the China Patent Office on May 31, 2022, bearing application number 2022106120660, and claims priority to a Chinese patent application entitled "Method for generating intersection surface and related apparatus", the entire contents of which are incorporated herein by reference.
[0002] FIELD OF THE DISCLOSURE The embodiments of the present application relate to the fields of maps, traffic, and the like, and in particular to the field of map data processing. [Background technology]
[0003] Currently, map applications provide maps that replicate the real world as closely as possible. The map includes a large number of road networks, and an intersection surface is an area on the map that indicates the space where an intersection is located. However, due to the complexity of road intersections, it is difficult to draw a specific intersection surface. Summary of the Invention [Problem to be solved by the invention]
[0004] In the related art, the offset distance of each road is generally set in advance, and the intersection plane of the intersection node is calculated using a pure geometry algorithm with a large amount of calculation. However, due to the existence of errors in road shape points, the influence of factors such as the mutual coupling of related geometric conditions, and the poor scalability of the pure geometry algorithm, the accurate intersection plane cannot be calculated using the traditional pure geometry algorithm, and especially for some complex road scenarios, the intersection plane generated in the electronic map by the traditional pure geometry algorithm will be more inaccurate.
[0005] The embodiments of the present application provide a method and related apparatus for generating intersection surfaces, which can effectively generate intersection surfaces of intersection nodes without relying on complex pure geometric algorithms, can generate accurate intersection surfaces, and has the advantage of strong scalability. [Means for solving the problem]
[0006] According to a first aspect, an embodiment of the present application provides a method for generating an intersection surface executed by a computing device, the method comprising: obtaining road information for a target intersection node, the road information indicating at least two roads associated with the target intersection node; determining road surface width information for each road based on the road information; Obtaining a constraint and a target function, the target function indicating a target area dimension of an intersection face of a target intersection node and including offset variables corresponding to each of the at least two roads, the offset variables indicating a distance condition between the target intersection node and a tangent of the corresponding road, the constraint indicating a limit condition of the target area dimension and including a constraint relationship between the offset variables corresponding to each of two adjacent roads among the at least two roads; determining an offset distance for the road based on road width information, constraints and a target function for the road; generating an intersection surface of the target intersection node on the map based on the road surface width information of the road and the offset distance of the road.
[0007] According to a second aspect, an embodiment of the present application provides an intersection plane generation device, the intersection plane generation device comprising: an acquisition unit for acquiring road information of a target intersection node, the road information indicating at least two roads associated with the target intersection node; a processing unit for determining road surface width information of each of the roads based on the road information; The acquisition unit further acquires a constraint condition and a target function, the target function indicating a target area dimension of an intersection face of the target intersection node, and including offset variables corresponding to each of the at least two roads, the offset variables indicating a distance condition between the target intersection node and a tangent of the corresponding road, the constraint condition indicating a limit condition of the target area dimension, and including a constraint relationship between the offset variables corresponding to each of two adjacent roads among the at least two roads; The processing unit further determines an offset distance of the road based on the road surface width information of the road, the constraints and the target function, and generates an intersection surface of the target intersection node on the map based on the road surface width information of the road and the offset distance of the road.
[0008] A third aspect of an embodiment of the present application provides a computer device, comprising a processor and a memory, the memory storing program instructions, the processor executing the program instructions in the memory to perform a method for generating an intersection surface corresponding to an embodiment of the first aspect above.
[0009] A fourth aspect of the present application provides a computer-readable storage medium having stored thereon instructions which, when executed on a computer, cause the computer to perform a method for generating an intersection surface corresponding to an embodiment of the first aspect above.
[0010] A fifth aspect of the present application provides a computer program product comprising instructions, which when executed on a computer or processor, causes the computer or processor to perform a method for generating an intersection surface corresponding to an embodiment of the first aspect above. Effect of the Invention
[0011] As can be seen from the above technical solutions, the embodiments of the present application have the following advantages: In an embodiment of the present application, the road information of the target intersection node is obtained, and road surface width information of each road associated with the target intersection node is determined based on the road information, and a constraint condition and a target function are obtained, the target function indicates the target area dimension of the intersection surface of the target intersection node, the constraint condition includes a constraint relationship between the offset variables of two adjacent roads associated with the target intersection node, and indicates the limit condition of the area dimension, and the target function includes offset variables corresponding to at least two roads associated with the target intersection node. In this way, the offset distance of each road can be calculated and obtained based on the road surface width information of the road, the constraint condition and the target function, and further, the intersection surface of the target intersection node is generated on the map based on the road surface width information of the road and the offset distance of the road. According to the above embodiment, it is not necessary to rely on a complex pure geometry algorithm, and it is only necessary to construct a constraint condition based on the constraint relationship between the offset variables of the adjacent roads, combine the road surface width information of the road to calculate the offset distance of the road, and the intersection surface of the intersection node can be effectively and accurately generated. In some complex road scenarios, the corresponding accurate offset distance can be calculated by modifying the constraints, which has strong scalability and can be widely applied to various map scenarios, thereby effectively and accurately generating intersection surfaces in various map scenarios. [Brief description of the drawings]
[0012] [Figure 1] FIG. 2 is a schematic diagram of an application scenario of the intersection surface generation method according to the present application; [Figure 2A] FIG. 2 is a schematic diagram of a single node intersection according to an embodiment of the present application; [Figure 2B] FIG. 2 is a schematic diagram of a complex node intersection according to an embodiment of the present application; [Diagram 3] 1 is a flowchart of a method for generating an intersection surface according to an embodiment of the present application. [Figure 4] FIG. 2 is a schematic diagram of a road after widening according to an embodiment of the present application. [Diagram 5]FIG. 2 is a schematic diagram of a tangent intersection of a road according to an embodiment of the present application; [Figure 6] FIG. 13 is a schematic diagram of the relationship between offset distances according to an embodiment of the present application. [Figure 7] FIG. 2 is a schematic diagram showing tangents that do not intersect with each other or intersect at the tangent end points according to an embodiment of the present application. [Figure 8] 1 is a schematic diagram of an intersection surface according to an embodiment of the present application; [Figure 9] 1 is a schematic diagram of an embodiment of an intersection plane generating device according to an embodiment of the present application; [Figure 10] 1 is a schematic diagram of a hardware structure of an intersection plane generation device according to an embodiment of the present application; DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS
[0013] Specific embodiments of the present application may involve specific products or technologies related to data such as user information, and where the embodiments of the present application are applied to such specific products or technologies, user permission or consent must be obtained, and the collection, use and processing of related data must comply with the relevant laws, regulations and standards of the relevant countries and regions.
[0014] Hereinafter, the technical solutions of the embodiments of the present application will be clearly and completely described in conjunction with the drawings of the embodiments of the present application, and the described embodiments are not all the embodiments, but only some of the embodiments of the present application. Based on the embodiments of the present application, on the premise that a person skilled in the art does not make any inventive efforts, all other embodiments obtained fall within the protection scope of the present application.
[0015] The terms "first," "second," "third," "fourth," and the like (if present) in the specification, claims, and above drawings of this application do not describe a particular order or sequential order, but are intended to distinguish between similar objects. It is to be understood that, where appropriate, the terms so used can be interchanged, whereby the embodiments of the application described herein can be, for example, performed in orders other than those illustrated or described herein. The terms "comprise," "comprising," or any other variant thereof, are intended to include a non-exclusive inclusion, e.g., a process, method, system, product, or apparatus comprising a series of steps or units is not limited to those steps or units expressly recited, but further includes those not expressly recited or inherent elements of such process, method, product, or apparatus.
[0016] An intersection plane is an area on an electronic map that indicates the space where an intersection is located. By generating an accurate intersection plane, map data of the intersection can be provided to the navigation engine, the visualization effect of the navigation interface can be enhanced, and data support can be provided for automatic driving when making decisions at intersections, or data support can be provided for objects (such as drivers) that use electronic maps to make driving decisions, preventing vehicles from driving beyond the intersection range, reducing the probability of accidents occurring at intersections, and improving driving safety.
[0017] The intersection surface generation method provided in this application relates at least to the following technologies, such as smart traffic system, cloud computing, and computer vision technology. Exemplarily, an intersection surface of a target intersection node is generated according to road network data in an electronic map. In some examples, a smart traffic system provides a driving object, such as a driver, with a smart navigation route service based on the position information, contour, etc. of the intersection surface. Or, a terminal device uses computer vision technology, etc. to more realistically and clearly display a high-precision three-dimensional image corresponding to the intersection surface on a navigation application page or a map page.
[0018] In the related art, the intersection surface is generally obtained by calculating based on the pure geometry algorithm according to the offset distance of each road that is pre-installed. However, the pure geometry algorithm has poor scalability, and due to the influence of factors such as the mutual coupling of related geometric conditions, there is a large deviation between the intersection surface generated based on the pure geometry algorithm and the actual intersection area. In addition, the generation of a suitable intersection surface for the conventional roadway level navigation on the market mainly relies on high-precision map data, but due to the limitations of some conditions, the coverage area of high-precision map data is limited, so that a suitable intersection surface cannot be generated in an area not covered by high-precision map data.
[0019] In order to solve the above technical problems, the embodiments of the present application provide a method for generating an intersection surface, which does not need to rely on a purely geometric algorithm that is poorly scalable to generate an intersection surface of an intersection node, and the intersection surface generated according to the method provided by the embodiments of the present application has mutual accuracy and scalability, is applicable to high-precision map scenarios, and can obtain the effect of approximation using high-precision map data even in areas not covered by high-precision map data.
[0020] FIG. 1 is a schematic diagram of an application scenario of the intersection surface generation method according to the present application. As shown in FIG. 1, the application scenario includes a server. Exemplarily, it may further include a terminal device, etc. The described server may be a background server of an application program, and the application program is also installed in the terminal device. The terminal device and the server perform data interaction based on the application program. The server stores road network data such as road information of an intersection node and road surface width information corresponding to each road, and further generates an intersection surface of the intersection node using the road network data. Exemplarily, the server transmits position information of the generated intersection surface to the terminal device, and the terminal device displays the intersection surface based on the position information of the intersection surface.
[0021] Here, in practical application, the terminal device may store road network data such as road information of the target intersection node, and the terminal device generates an intersection surface based on the road network data, and the embodiment of the present application does not limit the execution body of the generation of the intersection surface. Hereinafter, the embodiment of the present application will be described simply with the server as the execution body.
[0022] In addition, the application program may be a map application, a navigation application, or any application program that supports displaying a map page, such as a traffic application, etc. The terminal device may be an in-vehicle terminal (such as an in-vehicle navigation terminal and an in-vehicle computer), a smartphone, a tablet, a notebook computer, a mobile Internet device, a personal digital assistant (PDA), a desktop computer, a smart speaker, a smart watch, etc.
[0023] The server may be an independent physical server, a server cluster or a distributed system consisting of multiple physical servers, or a cloud server or server cluster that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, Content Delivery Network (CDN), big data and artificial intelligence platforms. The terminal device and the server may be directly or indirectly connected by wired or wireless communication, but are not limited thereto. Specifics may be determined based on the needs of the actual application scenario, and are not limited here.
[0024] Also, the intersection node described in FIG. 1 above is an intersection where at least two roads intersect. An intersection is a location where at least two roads merge, and is generally represented by several nodes. According to the number of nodes included, the intersection is divided into a single-node intersection and a multiple-node intersection. Based on this, the intersection node may include a single-node intersection and a multiple-node intersection. For example, FIG. 2A is a schematic diagram of a single-node intersection provided by an embodiment of the present application. As shown in FIG. 2A, in a scenario where the intersection node is a single-node intersection, four roads, namely, roads (link) 1 to link 4, merge at the same intersection (i.e., dot A in FIG. 2A). Also, for example, FIG. 2B is a schematic diagram of a multiple-node intersection provided by an embodiment of the present application. As shown in FIG. 2B, in a scenario where the intersection node is a multiple-node intersection, the multiple-node intersection is composed of four single-node intersections, and for each of the single-node intersections, four roads also merge at the same intersection, and the specific details can be understood by referring to the contents of FIG. 2A above, and are not described here in detail.
[0025] Here, for the intersection node in Figures 2A and 2B, the number of roads aggregated is 4, but this is merely a general description, and in actual applications, 2, 3, 6, or 10 roads may be aggregated, and this application does not specifically limit it. In addition, the single-node intersection in Figure 2A and the complex-node intersection in Figure 2B simply show a situation where links are perpendicular to each other, and in actual applications, there may be a situation where links are not perpendicular to each other, and this application does not specifically limit it. Hereinafter, the embodiment of this application will be described simply by taking the perpendicular links in Figures 2A and 2B as an example.
[0026] In addition, as shown in Figure 2B, a complex node intersection is actually composed of at least two single node intersections, so in the following description of the intersection surface generation method of the present application, the single node intersection in Figure 2A is simply taken as the target intersection node for detailed description. The process of generating a corresponding intersection surface for a complex node intersection can be specifically understood by referring to the process of generating an intersection surface of a single node intersection, and the embodiments of the present application will not be described in detail.
[0027] Taking the single-node intersection scenario in Figure 2A as an example, the intersection plane generation method provided in the embodiments of the present application will be introduced below in conjunction with the drawings. Figure 3 is a flowchart of the intersection plane generation method provided in the embodiments of the present application, which is executed by a computer device, such as the server or terminal device in Figure 1. As shown in Figure 3, the intersection plane generation method includes the following steps: 301: Obtain road information of a target intersection node, where the road information indicates two roads related to the target intersection node.
[0028] In this example, the target intersection node may be the single-node intersection in FIG. 2A or the multi-node intersection in FIG. 2B, and no further description is given here. Hereinafter, the target intersection node is described as the single-node intersection in FIG. 2A as an example. Corresponding road information is obtained for the target intersection node, and the number of roads merging into the target intersection node can be known based on the road information. Exemplarily, the road information indicates at least two roads, and the at least two roads are jointly connected to the target intersection node. For example, for the single-node intersection in FIG. 2A, the road information of the single-node intersection indicates four links, and the four links are jointly connected to the same target intersection node A.
[0029] 302: Determine road surface width information for each road based on the road information.
[0030] In this example, the roads mentioned in the general navigation map are shown as line segments with no width. Before generating the intersection surface of the target intersection node, the line segments with no width are widened to a road surface with a certain width. Exemplarily, road surface width information of each road is determined based on the road information, and the road surface width information reflects the specific width of the road surface of the road. The road width information described may include, but is not limited to, the width dimension of the road surface, and the present application is not specifically limited thereto.
[0031] In some examples, the corresponding road surface may be widened to different widths for roads of different levels. For example, at the city road level, the road surface of the main road is higher than that of the secondary road, and the road surface of the secondary road is higher than that of the branch road. The higher the road level, the larger the road surface width of the corresponding road. For example, the road surface width of the main road is generally larger than that of the secondary road, and the road surface width of the secondary road is larger than that of the branch road. Based on this, in step 302, the specific implementation process of determining the road surface width information of each road based on the road information is to determine the road level of each road based on the road information, and determine the road surface width information of each road based on the road level of each road.
[0032] In addition, the road surface of each road includes a left surface road surface and a right surface road surface, and correspondingly, the road surface width information of the road includes width information of the left surface road surface and width information of the right surface road surface.
[0033] For example, taking the single-node intersection of FIG. 2A as an example, FIG. 4 is a schematic diagram of a road after widening provided by an embodiment of the present application. As shown in FIG. 4, for four roads (i.e., link1 to link4) connected to the target intersection node A, each road can be widened to a road surface having a certain width. For example, for link1, the corresponding road surface width information is the road surface width information of the left side surface road surface of link1 (i.e., l w1 ), and the road surface width information of the right side surface road surface of link1 (i.e., r w1For link2, the corresponding road surface width information is also the road surface width information of the left side surface road surface of link2 (i.e., w2 ), and the road surface width information of the right side surface road surface of link2 (i.e., r w2 Similarly, the road surface width information of link3 and the road surface width information of link4 can be understood by specifically referring to the road surface width information of link1 and link2, and no detailed explanation will be given here.
[0034] Here, the roads described above may include, but are not limited to, main roads, secondary roads, and branch roads. In actual applications, roads may include expressways, roads within housing estates, etc., and the embodiments of the present application are not specifically limited. In addition, in FIG. w1 , r w1 , l w2 , r w2 Regarding the road surface width information such as the above, the values may be similar or different, and the present application does not specifically limit the values.
[0035] 303: Obtain a constraint condition and a target function, the target function indicating a target area dimension of an intersection surface of the target intersection node and including an offset variable corresponding to each of at least two roads, the offset variable indicating a distance condition between the target intersection node and a tangent of the corresponding road, the constraint condition indicating a limit condition of the target area dimension and including a constraint relationship between the offset variables corresponding to each of two adjacent roads among the at least two roads.
[0036] In this example, if the tangents corresponding to two adjacent roads intersect, it will cause an abnormality in the shape of the intersection surface of the target intersection node generated, and cannot accurately reflect the actual intersection surface. Therefore, in order to ensure that the shape of the intersection surface is not abnormal, it is necessary to ensure that the tangents corresponding to two adjacent roads do not intersect. Each road is perpendicular to the corresponding tangent, and the position of the tangent is indicated by the distance from the intersection point between the tangent and the road to the target intersection node. Here, the intersection of the tangents referred to in the embodiment of the present application should be understood as the intersection at the middle part of the tangent, and does not include the intersection at the end points of the two tangents.
[0037] In the embodiment of the present application, the distance from the intersection point between the tangent and the road to the target intersection node is called the offset distance, and whether the tangents corresponding to two adjacent roads intersect depends on the offset distance of the two roads. For example, if the offset distance of the road is too small, the corresponding tangents will intersect at the middle part of the tangent, which will cause abnormality in the shape of the intersection surface.
[0038] For example, FIG. 5 is a schematic diagram of road tangents intersecting according to an embodiment of the present application. As shown in FIG. 5, the tangent of link1 (i.e., L1) intersects with the tangent of link2 (i.e., L2), and the cause of the intersection between L1 and L2 is that the value of the offset variable of link1 (i.e., w1) and the value of the offset variable of adjacent link2 (i.e., w2) are too small. Similarly, the cause of the intersection between L2 and the tangent of link3 (i.e., L3) is that the value of w2 and the value of the offset variable of adjacent link3 (i.e., w3) are too small. The situation of the intersection between L3 and the tangent of link4 (i.e., L4) and the situation of the intersection between L4 and L1 can be understood by referring to the situation of the intersection between L1 and L2 or the intersection between L2 and L3, and will not be described here in detail.
[0039] Here, Fig. 5 only illustrates the intersection of road tangents by taking as an example that all four links intersect, and in actual application, only a situation in which two or three of the links intersect may occur, and this application does not specifically limit it. In addition, the offset variable mentioned indicates the distance situation between the target intersection node and the corresponding road tangent, for example, w1 indicates the distance situation between the target intersection node A and the tangent L1 of link1. After a specific value is assigned to the offset variable, it is called the offset distance.
[0040] Based on this, the value of w1 affects the value of adjacent w2, the value of w2 affects the value of adjacent w3, the value of w3 affects the value of adjacent w4, and the value of w4 affects the value of adjacent w1. Similarly, the value of w1 affects the value of adjacent w4, the value of w4 affects the value of adjacent w3, the value of w3 affects the value of adjacent w2, and the value of w2 affects the value of adjacent w1. Obviously, whether the four links of the target intersection node are sorted clockwise or counterclockwise, the coupling relationship between the offset variables w1, w2, w3, and w4 is cyclic, and can be specifically understood by referring to the schematic diagram of the relationship between the offset distances in FIG. 6. It is difficult to process such a coupling relationship using a pure geometric algorithm in the conventional solution. Therefore, in the embodiment of the present application, a mathematical optimization method is used to process such a coupling relationship, that is, the constraint relationship between the offset variables of each road is changed into a constraint equation of the optimization problem.
[0041] As mentioned above, the tangents of each road should satisfy the following two conditions, namely: (1) the tangents are perpendicular to the road (e.g., L1 is perpendicular to link); (2) the tangents do not cross each other or cross only at the tangent endpoints. Based on this, the constraint equation that the offset variable should satisfy is established by taking the above scenario in FIG. 4 as an example, and can be specifically understood by referring to the schematic diagram in FIG. 7 where the tangents do not cross each other or cross at the tangent endpoints.
[0042] As shown in FIG. 7, the constraint condition is constructed based on the constraint relationship between the offset variables of two adjacent roads so that the tangents L of the corresponding roads do not intersect or only intersect at their endpoints depending on the value of the offset variable w of each road.
[0043] The constraint relationship between the offset variables of two adjacent roads is established by the included angle information between the two adjacent roads. For example, the included angle information between the two adjacent roads is determined based on the road surface width information and the corresponding offset variables of the two adjacent roads, and the constraint condition is established based on the included angle information between the two adjacent roads. The mentioned included angle information indicates the intersection situation between the tangents corresponding to the two adjacent roads. The described intersection situation between the tangents can be specifically understood by referring to the contents of FIG. 5, and is not described here in detail.
[0044] The construction of the constraint condition is realized as follows: obtain an included angle between a first road and a second road, the first road and the second road being adjacent roads among at least two roads related to the target intersection node, obtain a first included angle between the first road and a boundary line on the right side of the first road, a second included angle between the second road and a boundary line on the left side of the second road, and a third included angle between a boundary line on the right side of the first road and a boundary line on the left side of the second road. Then, construct the constraint condition based on the included angle between the first road and the second road, the first included angle, the second included angle, and the third included angle.
[0045] For example, first, obtain the coordinates of the road shape points of the first road and the coordinates of the road shape points of the second road. Then, calculate and obtain the included angle between the first road and the second road based on the coordinates of the road shape points of the first road and the coordinates of the road shape points of the second road. Here, on the premise that the road form of the first road and the road form of the second road have already been fixed, the included angle between the roads calculated based on the coordinates of the road shape points of the roads is also fixed, that is, the obtained included angle between the first road and the second road is a specific value.
[0046] Also, the first included angle may be obtained by indicating the road surface width information of the right side surface road surface of the first road and the offset variable of the first road. Similarly, the second included angle may be obtained by indicating the road surface width information of the left side surface road surface of the second road and the offset variable of the second road. Here, the first included angle and the second included angle described are functions related to the offset variable w of the corresponding road.
[0047] The left side surface rough road surface and the right side surface rough road surface described herein can be understood by specifically referring to the contents described in FIG. 4 above, and no detailed explanation will be given here.
[0048] The sum of the first included angle, the second included angle and the third included angle is less than or equal to the included angle between the first road and the second road.
[0049] For example, take the schematic diagram in the upper right corner of Figure 7 as an example, link1 in Figure 7 is the first road, link2 is the second road, and link1 and link2 are adjacent to each other. Point A is the target intersection node. The intersection point between the tangent L1 and the boundary line of the right side surface road surface of link1 is P1, and the intersection point between the tangent L2 and the boundary line of the left side surface road surface of link2 is P2.
[0050] With point A as the origin, the included angle between link 1 and link 2, i.e., α 12 Calculate and obtain.
[0051] Similarly, the first included angle, i.e., α1, is obtained by calculating the angle between link1 and P1A with point A as the origin. For example, the tangent line L1 is perpendicular to link1, and the road surface width of the right side road surface of link1 is r w1 Therefore, the road surface width of the right side surface road surface of the link 1 is calculated by the arctangent function. w1 and processing the offset variable w1 of link1 to obtain:
number
[0052] The second included angle, i.e., α2, is obtained by calculating the angle between link2 and P2A. For example, the tangent L2 is perpendicular to link2, and the road surface width of the left side road surface of link2 is l w2 Similarly, the road surface width of the left side surface road surface of link2, l, is calculated by the arctangent function. w2 And processing the offset variable w2 of link2, we get:
number
[0053] To ensure that L1 and L2 do not cross, or cross only at their endpoints, the included angles α1 and α2 should satisfy the following formula:
number
[0054] In general, when a target intersection node has n (n>1) roads associated with it, n constraints can be constructed to obtain them. For example, the target intersection node A in FIG. 7 has four roads associated with it, and the following four constraints can be constructed for the target intersection node A:
number
[0055] Here, the above constraint (2) is constructed based on the included angle information between link2 and link3, α3 is the included angle between link2 and P3A, α4 is the included angle between link3 and P4A, and β2 is the included angle between P3A and P4A. The above constraint (3) is constructed based on the included angle information between link3 and link4, α5 is the included angle between link3 and P5A, α6 is the included angle between link4 and P6A, and β3 is the included angle between P5A and P6A. The above constraint (4) is constructed based on the included angle information between link4 and link1, α7 is the included angle between link4 and P7A, α8 is the included angle between link1 and P8A, and β4 is the included angle between P7A and P8A. Specifically, it can be understood by referring to the construction of the constraint between link1 and link2 in the above FIG. 7, and no detailed description is given here.
[0056] Also, assuming that the above-mentioned constraint conditions are satisfied, if it is desired that the intersection surface of the generated target intersection node is as small as possible, the target area dimension of the intersection surface of the target intersection node can be set as a target function, and the target area dimension can be restricted by the above-constructed constraint conditions. Here, the target function includes offset variables corresponding to at least two roads, and the constraint relationship between each offset variable can be understood by referring to the above-constructed constraint conditions, and is not described in detail here. In other words, the target area dimension of the intersection surface is influenced by the value of the offset variable of the road related to the target intersection node. Therefore, the representation of the target area dimension of the intersection surface of the target intersection node is determined based on the magnitude of the value of the offset variable w of the road related to the target intersection node. For example, for the target intersection node A in FIG. 7, if the sum of the squares of the offset variables w is set as the representation of the target area dimension of the intersection surface, the target area dimension of the intersection surface can be expressed as follows: V=w1 2 +w2 2 +w3 2 +w4 2 where w1, w2, w3, and w4 are the offset variables of the corresponding link1, link2, link3, and link4.
[0057] Here, the intersection area target area size is expressed as the sum of the squares of the offset variables, and in actual applications, it may be expressed in a manner such as the sum of the cubes of the offset variables, the sum of the N (N≧2) powers, or the sum of the absolute values, and the embodiments of the present application are not specifically limited thereto.
[0058] Thus, the target function for the target area dimension of the intersection surface is given as follows: min V=w1 2 +w2 2 +w3 2 +w4 2 can be constructed.
[0059] 304: Determine an offset distance for the road based on road surface width information of the road, the constraints, and the target function.
[0060] In this example, after constructing the constraint conditions and obtaining the target function through the operation of step 303, the target function is solved and calculated according to the road surface width information and the constraint conditions of the road, and the specific values of each offset variable in the target function are calculated to obtain the offset distance of each road. For example, after constructing and obtaining the constraint conditions and the target function, an optimized mathematical model corresponding to the target intersection node in FIG. 7 of the present application is constructed, namely:
number
[0061] In this way, the target function is solved based on the constraint conditions and road surface width information of the road based on a predetermined constraint optimization model such as an interior point method. For example, after obtaining road surface width information of each road (including road surface width information of the left surface road surface and road surface width information of the right surface road surface), the road surface width information of each road is processed by the predetermined constraint optimization model to obtain a specific value of the offset variable of each road, i.e., an optimal solution of the offset distance of each road.
[0062] 305: Generate an intersection surface of the target intersection node on the map based on the road surface width information of the road and the offset distance of the road.
[0063] In this example, after calculating and obtaining the offset distance of each road, an intersection surface of the target intersection node in the map is generated based on the road surface width information of each road and the corresponding offset distance. Exemplarily, a position of an intersection shape point is determined based on the road surface width information of each road and the corresponding offset distance. In this way, after obtaining the position of the intersection shape point, the intersection surface of the target intersection node can be generated based on the position of the intersection shape point. Here, the intersection shape point described indicates the area contour feature of the intersection surface, for example, the eight intersection shape points P1 to P8 in the above FIG. 7 can accurately describe the area contour of the intersection surface.
[0064] Generally, the determination of the position of each intersection shape point may be specifically realized by referring to the following method: calculate the coordinates of a first intersection shape point based on road surface width information of the right surface road surface of a first road and an offset distance of the first road, the first intersection shape point is an intersection point between a tangent of the first road and a boundary line of the right surface road surface of the first road, and the coordinates of the first intersection shape point indicate the position of the first intersection shape point; calculate the coordinates of a second intersection shape point based on road surface width information of the left surface road surface of a second road and an offset distance of the second road, the second intersection shape point is an intersection point between a tangent of the second road and a boundary line of the left surface road surface of the second road, and the coordinates of the second intersection shape point indicate the position of the second intersection shape point. Then, generate the intersection surface of the target intersection node by connecting the coordinates of the first intersection shape point and the coordinates of the second intersection shape point.
[0065] For example, take the first intersection shape point P1 and the second intersection shape point P2 in FIG. 8 as an example. The above is the road surface width information of the right side surface road surface of the link 1, that is, r w1 In step 304, the specific value of the offset variable w1 of the link1 is calculated and obtained. In this case, the coordinates of the P1 point can be calculated and obtained based on the Pythagorean theorem with the target road sign node A as the origin. Similarly, the above is the road width information of the left side surface road surface of the link2, that is, l w2In step 304, the specific value of the offset variable w2 of the link2 is calculated and obtained. In this case, the coordinates of the P2 point can be calculated and obtained by using the Pythagorean theorem in the same manner with the target road sign node A as the origin.
[0066] Based on the same principle, the coordinates of other intersection shape points (i.e., P3 to P8) can be obtained by solving, and the intersection surface can be obtained by connecting these intersection shape points with straight lines, which can be specifically understood by referring to the schematic diagram of the intersection surface in Figure 8.
[0067] In some examples, after the intersection surface is generated, the intersection surface may be displayed on a terminal device.
[0068] In the embodiment of the present application, the road information of the target intersection node is obtained, and the road surface width information of each road is determined based on the road information, and a constraint condition and a target function are obtained, the target function indicates the target area dimension of the intersection surface of the target intersection node, the constraint condition includes the constraint relationship between the offset variables of each two adjacent roads, and indicates the limit condition of the area dimension, and the target function includes at least two offset variables. In this way, the offset distance of each road can be calculated and obtained based on the road surface width information of the road, the constraint condition and the target function, and the intersection surface of the target intersection node is generated on the map based on the road surface width information of the road and the offset distance of the road. According to the above method, it is not necessary to rely on a complex pure geometry algorithm, but only by constructing the constraint condition based on the constraint relationship between the offset variables of the adjacent roads, combining the road surface width information of the road, and calculating the offset distance of the road, the intersection surface of the intersection node can be effectively and accurately generated. In some complex road scenarios, the corresponding accurate offset distance can be calculated by modifying the constraints, which has strong scalability and can be widely applied to various map scenarios, thereby effectively and accurately generating intersection surfaces in various map scenarios.
[0069] The above mainly introduces the solutions provided by the embodiments of the present application from the perspective of methods. Here, in order to realize the above functions, corresponding hardware structures and / or software modules are included for performing each function. As those skilled in the art can easily recognize, the present application may be realized in the form of hardware or a combination of hardware and computer software by combining each exemplary module and algorithm step described in the embodiments disclosed in the present application. Whether a function is implemented in the form of hardware or in the form of computer software driving the hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art may use different methods to realize the described functions for each specific application, and such realization does not go beyond the scope of the present application.
[0070] In the embodiment of the present application, based on the above example of the method, the device is divided into functional modules, for example, each functional module may be divided to correspond to each function, or two or more functions may be integrated into one processing module. The integrated modules may be realized in the form of hardware or software functional modules. Here, in the embodiment of the present application, the division of modules is schematic and is merely a division of logical functions, and when actually implemented, other division methods may exist.
[0071] The intersection plane generating device of the embodiment of the present application will be described in detail below. FIG. 9 is a schematic diagram of one embodiment of the intersection plane generating device provided by the embodiment of the present application. As shown in FIG. 9, the intersection plane generating device includes: An acquisition unit 901 for acquiring road information of a target intersection node, the road information indicating at least two roads related to the target intersection node; and a processing unit 902 for determining road surface width information for each road based on the road information.
[0072] The acquisition unit 901 further acquires a constraint condition and a target function, the target function indicating a target area dimension of the intersection surface of the target intersection node and including offset variables respectively corresponding to the at least two roads, the offset variables indicating the distance condition between the target intersection node and the tangent of the corresponding road, the constraint condition indicating a limit condition of the target area dimension and including a constraint relationship between the offset variables corresponding to each of two adjacent roads among the at least two roads.
[0073] The processing unit 902 further determines an offset distance of the road based on the road surface width information of the road, the constraints and the target function, and generates an intersection surface of the target intersection node on the map based on the road surface width information of the road and the road offset distance.
[0074] In some exemplary embodiments, the processing unit 902 determines included angle information between every two adjacent roads based on road surface width information and road offset variables of every two adjacent roads, where the included angle information indicates an intersection situation between tangents corresponding to each of the two adjacent roads, and constructs a constraint based on the included angle information between every two adjacent roads.
[0075] In some preferred examples, the road surface of each road includes a left side surface road surface and a right side surface road surface. The acquisition unit 901 further acquires an included angle between a first road and a second road, the first road and the second road being adjacent roads among the at least two roads, and acquires a first included angle between the first road and a boundary line on the right side surface road surface of the first road, a second included angle between the second road and a boundary line on the left side surface road surface of the second road, and a third included angle between a boundary line on the right side surface road surface of the first road and a boundary line on the left side surface road surface of the second road; The processing unit 902 specifically establishes a constraint condition based on the included angle between the first road and the second road, the first included angle, the second included angle and the third included angle.
[0076] In some other preferred examples, the sum of the first included angle, the second included angle, and the third included angle is less than or equal to the included angle between the first road and the second road.
[0077] In some other preferred examples, the acquisition unit 901 specifically acquires coordinates of road shape points of a first road and coordinates of road shape points of a second road, and the processing unit 902 specifically calculates an included angle between the first road and the second road according to the coordinates of the road shape points of the first road and the coordinates of the road shape points of the second road.
[0078] In some other preferred examples, the first included angle is obtained based on road surface width information of the right side surface road surface of the first road and an offset variable of the first road.
[0079] In some other preferred examples, the second included angle is obtained based on road surface width information of the left side surface road surface of the second road and an offset variable of the second road.
[0080] In some other preferred examples, the processing unit 902 specifically determines a road level of each road based on the road information, and determines road surface width information of each road based on the road level of each road.
[0081] In some other preferred examples, the processing unit 902 specifically determines positions of intersection shape points based on the road surface width information of each road and the offset distance of the road, where the intersection shape points indicate area contour features of the intersection surface, and generates an intersection surface of the target intersection node on the map based on the positions of the intersection shape points.
[0082] In some other preferred examples, the road surface width information of the road includes road surface width information of the left surface road surface of the road and road surface width information of the right surface road surface of the road. The processing unit 902 specifically calculates a coordinate of a first intersection shape point according to the road surface width information of the right surface road surface of the first road and the offset distance of the first road, the first intersection shape point is an intersection point between the tangent of the first road and the boundary line on the right surface road surface of the first road, calculates a coordinate of a second intersection shape point according to the road surface width information of the left surface road surface of the second road and the offset distance of the second road, the second intersection shape point is an intersection point between the tangent of the second road and the boundary line on the left surface road surface of the second road, the first road and the second road are adjacent roads among the at least two roads, and connects the coordinate of the first intersection shape point and the coordinate of the second intersection shape point to generate an intersection surface of the target intersection node.
[0083] In some other preferred examples, the processing unit 902 specifically determines the offset distance of the road based on a predetermined constraint optimization model and the target function when the constraint conditions and road surface width information of the road are known.
[0084] The above describes the intersection plane generating device of the embodiment of the present application from the perspective of modularized functional entities, and the following describes the computer device that executes the intersection plane generating method of the embodiment of the present application from the perspective of hardware processing. Figure 10 is a schematic diagram of the hardware structure of the computer device provided by the embodiment of the present application. The intersection plane generating device has a large difference due to different configurations or performances. The intersection plane generating device includes at least one processor 1001, a communication line 1007, a memory 1003 and at least one communication interface 1004.
[0085] The processor 1001 may be a general purpose central processing unit (CPU), a microprocessor, an application-specific integrated circuit (server IC), or one or more integrated circuits for controlling the execution of programs of the solutions of the present application.
[0086] The communication lines 1007 include paths for transmitting information between the above components.
[0087] Any transceiver-like device may be used with the communications interface 1004 to communicate with other devices or communications networks, such as Ethernet, radio access networks (RAN), wireless local area networks (WLAN), and the like.
[0088] The memory 1003 may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, a random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, and the memory may exist separately and be connected to the processor via a communication line 1007. The memory may also be integrated with the processor.
[0089] The memory 1003 stores computer-executable instructions for implementing the solutions of the present application and controls the execution by the processor 1001. The processor 1001 executes the computer-executable instructions stored in the memory 1003 to realize the intersection surface generation method provided by the above embodiments of the present application.
[0090] Preferably, the computer-executable instructions of the embodiments of the present application may also be referred to as application program code, although the embodiments of the present application are not specifically limited thereto.
[0091] In a specific implementation, for example, the computing device includes multiple processors, such as processor 1001 and processor 1002 in FIG. 10. Each of these processors may be a single-core (single-CPU) processor or a multi-core (multi-CPU) processor, where a processor is one or more devices, circuits, and / or processing cores that process data (e.g., computer program instructions).
[0092] In a specific implementation, for example, the computer device further includes an output device 1005 and an input device 1006. The output device 1005 communicates with the processor 1001 to display information in multiple ways. The input device 1006 communicates with the processor 1001 to receive input of a target object in multiple ways. For example, the input device 1006 may be a mouse, a touch panel device, a sensing device, etc.
[0093] The above-mentioned computer device may be a general-purpose device or a dedicated device. In a specific implementation, the computer device may be a server, a terminal, etc., or a device having a similar configuration to that of FIG. 10. The embodiments of the present application do not limit the type of the computer device.
[0094] Here, the processor 1001 of FIG. 10 invokes computer-executable instructions stored in the memory 1003 to cause the computing device to perform the method in the method embodiment corresponding to FIG.
[0095] Specifically, the function / implementation process of the processing unit 902 in FIG. 9 is realized by the processor 1001 in FIG. 10 invoking computer-implemented instructions stored in the memory 1003. The function / implementation process of the acquisition unit 901 in FIG. 9 is realized by the communication interface 1004 in FIG.
[0096] The above embodiments may be implemented in whole or in part in software, hardware, firmware, or any combination thereof. If implemented in software, they may be implemented in whole or in part in the form of a computer program product.
[0097] As those skilled in the art will appreciate, for the convenience and conciseness of description, the specific operation processes of the above-described systems, devices and units may be referred to the corresponding processes in the above method embodiments, and will not be described in detail here.
[0098] In some embodiments provided by the present application, it can be understood that the disclosed system, device and method may be realized in other ways. For example, the device embodiments described above are merely schematic, for example, the division of units is merely a division of logical functions, and in actual implementation, other division ways may exist, for example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not implemented. In addition, the couplings or direct couplings or communication connections between each other shown or discussed may be indirect couplings or communication connections by some interfaces, devices or units, which may be electrical, mechanical or other forms.
[0099] The units described as individual components may or may not be physically separated, and the components shown as units may or may not be physical units, i.e., they may be located in one place or distributed among multiple network units. Based on actual needs, some or all of the units can be selected to achieve the objective of the technical solution of the embodiment.
[0100] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, each unit may exist separately and physically, and two or more units may be integrated into one unit. The integrated units may be realized in the form of hardware or in the form of a software functional unit.
[0101] When the integrated unit is realized in the form of a software functional unit and sold or used as an independent product, it is stored in a computer-readable storage medium. Based on this understanding, the essence of the technical solution of the present application, or a part having a contribution to the prior art, or all or a part of the technical solution is embodied in the form of a software product, and the computer software is stored in a storage medium and includes some instructions to make a computer device (which may be a personal computer, a server, or a network device, etc.) execute all or a part of the steps of each embodiment method of the present application. The above storage medium includes various media that can store program code, such as U disk, portable hard disk, read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk.
[0102] The above embodiments may be implemented in whole or in part in software, hardware, firmware or any combination thereof, and if implemented in software, may be implemented in whole or in part in the form of a computer program product.
[0103] A computer program product includes one or more computer instructions. When the computer-executed instructions are read and executed by a computer, it generates the flow or function according to the embodiment of the present application in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another, for example, the computer instructions are transmitted from one website, computer, server, or data center to another website, computer, server, or data center in the form of a wire (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or a wireless (e.g., infrared, radio, microwave, etc.). The computer-readable storage medium is any available medium on which a computer can store, or a data storage device such as a server, data center, etc. that is integrated to include one or more available media. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a magnetic tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., an SSD), etc.
[0104] The above examples do not limit the technical solutions of the present application, but are merely for illustrative purposes. The present application has been described in detail with reference to the above examples. However, as can be understood by those skilled in the art, the technical solutions described in the above examples may still be amended or equivalent substitutions may be made to some technical features, and the essence of the corresponding technical solutions will not deviate from the spirit and scope of the technical solutions of the embodiments of the present application because of these modifications or substitutions. [Explanation of symbols]
[0105] 901 Acquired Units 902 Processing Unit 1001 Processor 1002 processor 1003 Memory 1004 Communication Interface 1005 Output equipment 1006 Input Devices 1006 Input Device 1007 Communication lines
Claims
1. 1. A method for generating an intersection surface implemented by a computing device, comprising: obtaining road information for a target intersection node, the road information indicating at least two roads associated with the target intersection node; determining road surface width information of each of the roads based on the road information; obtaining a constraint and a target function, the target function indicating a target area dimension of an intersection face of the target intersection node and including offset variables corresponding to each of the at least two roads, the offset variables indicating a distance condition between the target intersection node and a tangent of a corresponding road, the constraint indicating a limit condition of the target area dimension and including a constraint relationship between the offset variables corresponding to each of two adjacent roads of the at least two roads; determining an offset distance for the road based on road surface width information of the road, the constraints, and the target function; generating an intersection surface of the target intersection node on a map based on road surface width information of the road and an offset distance of the road.
2. The step of obtaining the constraint condition includes: determining an included angle between each two roads based on road surface width information and corresponding offset variables of each two adjacent roads, the included angle information indicating an intersection situation between tangents corresponding to each of the two adjacent roads; and developing the constraint based on included angle information between each pair of adjacent roads.
3. The road surface of each road includes a left side surface road surface and a right side surface road surface, and the step of constructing the constraint condition based on the included angle information between the two adjacent roads includes: obtaining an included angle between a first road and a second road, the first road and the second road being adjacent roads among the at least two roads; obtaining a first included angle between the first road and a boundary line on a right side surface of the first road, a second included angle between the second road and a boundary line on a left side surface of the second road, and a third included angle between the boundary line on the right side surface of the first road and a boundary line on the left side surface of the second road; and developing the constraint based on an included angle between the first road and a second road, the first included angle, the second included angle, and the third included angle.
4. 4. The method of claim 3, wherein the sum of the first included angle, the second included angle, and the third included angle is less than or equal to the included angle between the first road and the second road.
5. The step of obtaining an angle between the first road and the second road includes: obtaining coordinates of road shape points of the first road and coordinates of road shape points of the second road; 5. The method according to claim 3 or 4, further comprising: calculating an included angle between the first road and the second road based on coordinates of road shape points of the first road and coordinates of road shape points of the second road.
6. The method according to claim 3 or 4, wherein the first included angle is obtained based on road surface width information of a right side surface road surface of the first road and an offset variable of the first road.
7. The method according to claim 3 or 4, wherein the second included angle is obtained based on road surface width information of a left side surface road surface of the second road and an offset variable of the second road.
8. The step of determining road surface width information of each of the roads based on the road information includes: determining a road level of each of the roads based on the road information; The method according to any one of claims 1 to 4, further comprising: determining road surface width information of each of the roads based on a road level of each of the roads.
9. generating an intersection surface of the target intersection node on a map based on road surface width information of the road and an offset distance of the road, determining locations of intersection shape points based on road surface width information and corresponding offset distances for each of the roads, the intersection shape points indicating area contour features of the intersection surface; and generating an intersection surface of the target intersection node on the map based on the positions of the intersection shape points.
10. The road surface width information of the road includes road surface width information of a left side surface road surface of the road and road surface width information of a right side surface road surface of the road, and the step of determining a position of an intersection shape point based on the road surface width information of each of the roads and a corresponding offset distance includes: A step of calculating coordinates of a first intersection shape point based on road surface width information of a right-side surface road surface of a first road and an offset distance of the first road, the first intersection shape point being an intersection between a tangent to the first road and a boundary line on the right-side surface road surface of the first road; a step of calculating coordinates of a second intersection shape point based on road surface width information of a left surface road surface of a second road and an offset distance of the second road, the second intersection shape point being an intersection point between a tangent to the second road and a boundary line on the left surface road surface of the second road, the first road and the second road being adjacent roads among the at least two roads, generating an intersection face of the target intersection node based on the positions of the intersection shape points, 10. The method of claim 9, comprising connecting coordinates of the first intersection shape point and coordinates of the second intersection shape point to generate an intersection plane for the target intersection node.
11. The step of determining an offset distance of the road based on road surface width information of the road, the constraint condition, and the target function includes: The method according to any one of claims 1 to 4, further comprising a step of determining an offset distance for the road based on a predetermined constraint optimization model and the target function when the constraint conditions and road surface width information of the road are known.
12. An intersection surface generation device, comprising: an acquisition unit for acquiring road information of a target intersection node, the road information indicating at least two roads associated with the target intersection node; a processing unit for determining road surface width information of each of the roads based on the road information; The acquisition unit further acquires a constraint condition and a target function, the target function indicating a target area dimension of the intersection face of the target intersection node and including offset variables corresponding to each of the at least two roads, the offset variables indicating a distance condition between the target intersection node and a tangent of the corresponding road, the constraint condition indicating a limit condition of the target area dimension and including a constraint relationship between the offset variables corresponding to each of two adjacent roads among the at least two roads; The processing unit further determines an offset distance for the road based on road surface width information of the road, the constraints, and the target function; The processing unit further includes a device for generating road width information of the road and an offset distance of the road, an intersection surface of the target intersection node on a map.
13. A computing device comprising a processor and a memory, the memory having program instructions stored therein; A computing apparatus for carrying out the method according to any one of claims 1 to 11, wherein said processor executes program instructions stored in a memory.
14. A computer readable storage medium comprising instructions on said computer readable storage medium which, when executed on a computing device, cause said computing device to perform the method of any one of claims 1 to 11.
15. A computer program comprising instructions which, when executed on a computing device, cause the computing device to carry out a method according to any one of claims 1 to 11.
Citation Information
Patent Citations
Indication method of junction, its map display and recording medium
JP2001215129A
Method and device for drawing intersections, server and storage medium
JP2020160448A
