An intersection-based map road network segmentation method, device, medium and equipment

Abstract

The application discloses a kind of intersection-based map road network segmentation method, device, medium and equipment, belong to computer technical field.Mainly include searching and obtaining multiple Y-type fork nodes in the map road network of predetermined area;At the first predetermined length of each road distance connected with each Y-type fork node corresponding Y-type fork node, corresponding second predetermined length road vertical segment is generated, each road vertical segment includes first end point and tail end point sequentially distributed in clockwise direction with Y-type fork node as rotation center;The first end point of each road vertical segment is connected with the tail end point of adjacent road vertical segment, and multiple Y-type fork convex hulls containing each Y-type fork node are obtained;And, using corresponding Y-type fork convex hull constructs the map road network segmentation unit including the road section at the intersection where Y-type fork node is located.The application can improve the efficiency of making high-precision map, reduce resource consumption and reduce the difference error of merging.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to a method, apparatus, medium, equipment, and map production system for road network segmentation based on intersections. Background Technology

[0002] In many practical applications, there are situations where it is necessary to merge map data from multiple areas based on the road network information of existing maps. For example, when creating a high-precision map of a predetermined area, the map is created separately through multiple segment tasks, and then the map data from the multiple map segment tasks are merged. However, if the endpoint of a road network unit happens to be at an intersection, the presence of multiple roads at the intersection increases the difficulty of merging the corresponding map data. Summary of the Invention

[0003] To address the problems existing in the prior art, this application mainly provides a method, apparatus, medium, equipment, and map production system for road network segmentation based on intersections. By dividing road segments at intersections into indivisible units and using the indivisible units including intersections to obtain map road network segmentation units, the high-precision map segmentation process can be carried out in a single map segmentation task, thus avoiding merging at intersections during subsequent merging. This improves the production efficiency of high-precision maps, reduces resource consumption, and minimizes merging errors.

[0004] In a first aspect, embodiments of this application provide a map road network segmentation method based on intersections, comprising:

[0005] Find multiple Y-shaped branch road nodes in the map road network of a predetermined area; at a first predetermined distance from each road connected to each Y-shaped branch road node, generate a road vertical line segment of a second predetermined length, each road vertical line segment including a first endpoint and a last endpoint distributed in a clockwise direction with the Y-shaped branch road node as the rotation center; connect the first endpoint of each road vertical line segment to the last endpoint of the adjacent road vertical line segment to obtain multiple Y-shaped branch road convex hulls containing each Y-shaped branch road node; and construct a map road network segmentation unit including the road segment at the intersection where the Y-shaped branch road node is located using the corresponding Y-shaped branch road convex hulls.

[0006] Secondly, embodiments of this application provide a map road network segmentation method based on intersections, which includes:

[0007] Obtain multiple Y-shaped branch road nodes in the map road network of a predetermined area; at a first predetermined distance from the corresponding Y-shaped branch road node, extend a second predetermined length to both sides of the road along the normal direction of the road to obtain a first reference point and a second reference point corresponding to the road; construct the Y-shaped branch road convex hull corresponding to the corresponding Y-shaped branch road node using the first reference points and second reference points of all roads connected to each Y-shaped branch road node; and construct a map road network segmentation unit including the road segment at the intersection where the Y-shaped branch road node is located using the corresponding Y-shaped branch road convex hull.

[0008] Thirdly, embodiments of this application provide a map road network segmentation device based on intersections, comprising:

[0009] A Y-shaped branch road node acquisition module is used to find and acquire multiple Y-shaped branch road nodes in the map road network of a predetermined area; a road vertical line segment generation module is used to generate a road vertical line segment of a second predetermined length at a first predetermined length distance from the corresponding Y-shaped branch road node for each road connected to each Y-shaped branch road node, each road vertical line segment including a first endpoint and a last endpoint distributed in a clockwise direction with the Y-shaped branch road node as the rotation center; a Y-shaped branch road convex hull acquisition module is used to connect the first endpoint of each road vertical line segment with the last endpoint of the adjacent road vertical line segment to obtain multiple Y-shaped branch road convex hulls containing each Y-shaped branch road node; and a map road network segmentation unit construction module is used to construct a map road network segmentation unit including the road segment at the intersection where the Y-shaped branch road node is located using the corresponding Y-shaped branch road convex hulls.

[0010] Fourthly, embodiments of this application provide a map production system, which includes the aforementioned intersection-based map road network segmentation device.

[0011] Fifthly, embodiments of this application provide a computer-readable storage medium storing computer instructions that are operated to perform the intersection-based map road network segmentation method described above.

[0012] Sixthly, embodiments of this application provide a computer device including a processor and a memory, the memory storing computer instructions that are operated to execute the intersection-based map road network segmentation method in the above-described scheme.

[0013] The beneficial effects that the technical solution of this application can achieve are as follows: This application divides the road segment at the intersection into a map road network segmentation unit, and uses the non-divisible unit including the intersection to obtain the map road network segmentation unit, so that the intersection road segment can be carried out in a map segmentation task during the high-precision map segmentation and mapping process, so that merging at the intersection is avoided during subsequent merging; thereby improving the production efficiency of high-precision maps, reducing resource consumption and reducing merging errors. Attached Figure Description

[0014] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings in the following description exemplarily illustrate some embodiments of this application.

[0015] Figure 1 This is a schematic diagram of a specific implementation of a road network segmentation method based on intersections according to this application;

[0016] Figure 2 This is a schematic diagram of the convex hull of a Y-shaped branch road in a specific embodiment of a road network segmentation method based on intersections in this application;

[0017] Figure 3 This is a schematic diagram of the convex hull of an intersection in a specific embodiment of the intersection-based map road network segmentation method of this application;

[0018] Figure 4 This is a schematic diagram of a specific embodiment of a map road network segmentation device based on intersections according to this application;

[0019] The accompanying drawings have illustrated specific embodiments of this disclosure, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concepts of this disclosure to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0020] The preferred embodiments of this application will now be described in detail with reference to the accompanying drawings, so that the advantages and features of this application can be more easily understood by those skilled in the art, thereby providing a clearer and more definite definition of the scope of protection of this application.

[0021] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus that includes said element.

[0022] In many practical applications, there are situations where it is necessary to merge map data from multiple areas based on the road network information of existing maps. For example, when creating a high-precision map of a predetermined area, the map is created separately through multiple segment tasks, and then the map data from the multiple map segment tasks are merged. However, if the endpoint of a road network unit happens to be at an intersection, the presence of multiple roads at the intersection increases the difficulty of merging the corresponding map data.

[0023] This application provides a method, apparatus, medium, device, and map production system for intersection-based map road network segmentation. By dividing road segments at intersections into indivisible units and utilizing these indivisible units, map road network segmentation units are obtained. This allows the high-precision map segmentation process to perform intersection road segments within a single segmentation task, avoiding subsequent merging at intersections. This improves the efficiency of high-precision map production, reduces resource consumption, and minimizes merging errors.

[0024] The technical solutions of this application will now be described in detail with reference to specific embodiments and accompanying drawings. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments.

[0025] Figure 1 This invention illustrates a specific implementation of a map road network segmentation method based on intersections.

[0026] exist Figure 1 The specific implementation of the intersection-based map road network segmentation method of this application shown includes the following steps: Step S101: Finding and obtaining multiple Y-shaped branch road nodes in the map road network of a predetermined area; Step S102: Generating a road vertical line segment of a second predetermined length at a first predetermined distance from each road connected to each Y-shaped branch road node, wherein each road vertical line segment includes a first endpoint and a last endpoint distributed in a clockwise direction with the Y-shaped branch road node as the rotation center; Step S103: Connecting the first endpoint of each road vertical line segment to the last endpoint of the adjacent road vertical line segment to obtain multiple Y-shaped branch road convex hulls containing each Y-shaped branch road node; and Step S104: Constructing a map road network segmentation unit including the road segment at the intersection where the Y-shaped branch road node is located using the corresponding Y-shaped branch road convex hulls.

[0027] This application uses an intersection-based map road network segmentation method to divide road segments at intersections into a map road network segmentation unit, and uses indivisible units including intersections to obtain the map road network segmentation unit. This allows the intersection road segments to be constructed in a single map segmentation task during the high-precision map segmentation process, avoiding merging at intersections during subsequent merging. This improves the efficiency of high-precision map production, reduces resource consumption, and reduces merging errors.

[0028] Process S101 represents the process of finding and obtaining multiple Y-shaped branch nodes in the map road network of a predetermined area, which can facilitate the location and acquisition of intersection road segments based on branch nodes.

[0029] In one specific embodiment of this application, the road network of the predetermined area is a traditional road network in an open-source map database. The road network segmentation method of this application also includes obtaining the traditional road network of the predetermined area from the open-source map database. Obtaining the traditional road network directly from the open-source map database can improve work efficiency by utilizing existing resources.

[0030] In one specific embodiment of this application, the process of obtaining multiple Y-shaped branch road nodes in the map road network of the predetermined area includes: traversing the intermediate road nodes of each road in the map road network of the predetermined area to obtain intersecting intermediate nodes connecting other roads besides the corresponding road, and breaking the corresponding road from the intersecting intermediate nodes to obtain the preprocessed road network of the predetermined area; traversing the first and last nodes of all roads in the preprocessed road network of the predetermined area to obtain Y-shaped branch road nodes with more than 2 connected roads.

[0031] Specifically, some Y-shaped branching nodes are located at the endpoints of the roads they connect, while others are located in the middle of a connected road, serving as the middle node of that road. In the case where a Y-shaped branching node is located in the middle of a road, the road needs to be broken at that node. The resulting preprocessed road network contains all Y-shaped branching nodes located at the endpoints of the roads they connect, serving as either the first or last node of the corresponding road. Therefore, when searching for Y-shaped branching nodes, only the first and last nodes of each road are needed to obtain all Y-shaped branching nodes in the road network, avoiding the need to determine whether each road node is a Y-shaped branching node. This simplifies the algorithm, improves efficiency, and saves computational resources.

[0032] Process S102 represents the process of generating a road vertical line segment of a second predetermined length at a first predetermined distance from each road connected to each Y-shaped branch node. This process facilitates the generation of the Y-shaped branch convex hull based on the vertical line segment, and further facilitates the generation of map road network segmentation units for the road segment at the corresponding intersection.

[0033] In one specific embodiment of this application, the first predetermined length is not less than the length of all roads within the corresponding intersection, which helps to ensure that all roads within the intersection are subsequently divided into the map road network segmentation unit of the road segment at the corresponding intersection.

[0034] Preferably, the first predetermined length is 20-50m. If the value of the first predetermined length is too small, the area of ​​each Y-shaped branch convex hull obtained subsequently may be too small, resulting in no overlap between them, making it impossible to find the large intersection (crossroads, multi-way intersection) to which the Y-shaped branch convex hull belongs by merging. If it is too large, it will result in an excessively large intersection, which may merge multiple real-world crossroads into one intersection.

[0035] Preferably, the second predetermined length is set between 15 and 30 m.

[0036] Specifically, open-source map databases contain many two-way roads without physical separation, represented as two roads in opposite directions. If these two roads are not at the same intersection, visual mapping may create an incorrect map of the opposite lane, which is unacceptable. Therefore, intersection recognition must ensure that the up and down lanes of each road at the intersection are contained within an equal length. This is precisely why a second predetermined length is set: the up and down roads are parallel, and a line drawn from any point on any road can be perpendicular to both up and down roads. This ensures that the up and down roads within the defined intersection area are aligned.

[0037] Process S103 represents the process of connecting the first endpoint of each road vertical line segment to the last endpoint of the adjacent road vertical line segment to obtain multiple Y-shaped branch convex hulls containing each Y-shaped branch node, which can facilitate the construction of map road network segmentation units at the corresponding intersections using the corresponding Y-shaped branch convex hulls.

[0038] Specifically, the convex hull of a Y-shaped branch is as follows: Figure 2 As shown, a first predetermined length of road segment connected to the corresponding Y-shaped branch node is used as a connection buffer segment. Together with the Y-shaped branch node, it forms the smallest indivisible unit. This ensures that when creating high-precision maps in segments, the first predetermined length of road segment at the Y-shaped branch node is within one mapping segment task. Thus, when merging the resulting high-precision map segment task with other adjacent segment tasks, the merging always occurs on straight road segments that are less prone to errors, have higher merging efficiency, and better results.

[0039] Process S104 represents the construction of map road network segmentation units including the road segments at the intersections where the Y-shaped branch nodes are located using the corresponding Y-shaped branch convex hulls. This can ultimately obtain map road network segmentation units including the road segments at the intersections where the Y-shaped branch nodes are located. This is beneficial for the high-precision map segmentation and mapping process, allowing intersection road segments to be completed in one mapping segmentation task, thus avoiding merging at intersections during subsequent merging. This improves the production efficiency of high-precision maps, reduces resource consumption, and reduces merging errors.

[0040] Specifically, the aforementioned intersections can be Y-shaped intersections, crossroads, T-shaped intersections, or multi-way intersections, etc. Because different types of intersections, regardless of how many roads converge, always contain at least one Y-shaped fork, that is to say, a large intersection must be composed of multiple Y-shaped forks.

[0041] In a specific embodiment of this application, the process of constructing a map road network segmentation unit including the road segment at the intersection where the Y-type branch node is located using the corresponding Y-type branch convex hull further includes checking whether each Y-type branch convex hull intersects with each other Y-type branch convex hull. If they intersect, the two intersecting Y-type branch convex hulls are merged to obtain multiple intersection convex hulls that do not intersect each other, which is beneficial for obtaining the smallest indivisible unit of the intersection based on the intersection convex hull.

[0042] Specifically, the aforementioned intersection protrusions are as follows: Figure 3 As shown, larger intersections often have numerous Y-shaped branching nodes, and these nodes are very close together, which can easily cause confusion when merging high-precision map segmentation tasks. Therefore, it is necessary to group multiple closely spaced Y-shaped branching nodes within each intersection and their connected first predetermined length road segments into a single, indivisible unit. High-precision map construction at the corresponding intersection should then be performed within a single segment task. This avoids the need to merge high-precision map data at intersections when merging multiple segmentation tasks to obtain a high-precision map of the predetermined area later, thus reducing the complexity of the mapping algorithm and improving mapping efficiency.

[0043] In one specific embodiment of this application, the process of checking whether each Y-shaped branch convex hull intersects with every other Y-shaped branch convex hull in a plurality of Y-shaped branch convex hulls includes: first sorting the plurality of Y-shaped branch convex hulls according to longitude coordinates, and then sorting them according to latitude coordinates; and determining whether the minimum longitude coordinate value of the Y-shaped branch convex hull with the larger longitude coordinate in the longitude coordinate sorting among two adjacent Y-shaped branch convex hulls is greater than the maximum longitude coordinate value of the Y-shaped branch convex hull with the smaller longitude coordinate in the longitude coordinate sorting.

[0044] If the difference is not greater than the maximum value, then the minimum latitude coordinate value of the Y-shaped convex hull with the larger latitude coordinate in the corresponding two adjacent Y-shaped branch convex hulls is determined to be greater than the maximum latitude value of the Y-shaped convex hull with the smaller latitude coordinate. If the difference is not greater than the maximum latitude coordinate, then the corresponding two adjacent Y-shaped branch convex hulls are determined to be intersecting; otherwise, the corresponding two adjacent Y-shaped branch convex hulls are determined to be non-intersecting.

[0045] Otherwise, the corresponding two Y-shaped branch convex hulls are judged as non-intersecting.

[0046] This embodiment is suitable for situations where there are few Y-shaped roads, and can perform intersection recognition relatively simply and quickly.

[0047] In one specific embodiment of this application, the process of checking whether each Y-shaped branch road convex hull intersects with every other Y-shaped branch road convex hull, and merging the two intersecting Y-shaped branch road convex hulls to obtain multiple intersection convex hulls that do not intersect, includes using a spatial indexing algorithm to search for other Y-shaped branch road convex hulls within a predetermined spatial range around each Y-shaped branch road convex hull. If other Y-shaped branch road convex hulls are found, a disjoint-set data structure algorithm is used to calculate whether each Y-shaped branch road convex hull within the predetermined spatial range intersects with every other Y-shaped branch road convex hull. If they intersect, the two intersecting Y-shaped branch road convex hulls are merged. This embodiment is applicable to intersection scenarios with a large number of Y-shaped roads, and can quickly group and merge convex hulls belonging to the same intersection range, efficiently identifying the intersection range.

[0048] Specifically, by using space indexing algorithms with low time complexity, such as R-trees, and disjoint-set data structures, the efficiency of convex hull grouping and merging within each group can be greatly improved.

[0049] In a specific embodiment of this application, the process of constructing a map road network segmentation unit including the road segment at the intersection where the Y-shaped branch node is located using the corresponding Y-shaped branch convex hull further includes obtaining the smallest indivisible unit of the intersection where the corresponding Y-shaped branch node is located using the roads within the range included by each intersection convex hull. This facilitates mapping the intersections included by the smallest indivisible unit of the intersection in a high-precision map segmentation task, thereby avoiding the need to merge high-precision map data at the intersection when multiple segmentation tasks need to be merged to obtain the high-precision map of the predetermined area in the future, reducing the complexity of the mapping algorithm and improving the mapping efficiency.

[0050] Specifically, the smallest indivisible unit of the intersection obtained in this embodiment uses a first predetermined length of road segment connected to each Y-shaped branch node at the intersection as a connection buffer segment. This ensures that the Y-shaped branch nodes at the intersection and the roads within the intersection, i.e., the road segments within the line connecting the Y-shaped branch nodes at the intersection, are all within the corresponding smallest indivisible unit of the intersection. This ensures that the relevant road segments at the intersection are mapped within a high-precision map segmentation task, avoiding the merging of map segmentation task data at Y-shaped branch nodes or roads within the intersection where merging may be difficult.

[0051] In one specific embodiment of this application, the process of constructing a map road network segmentation unit including the road segment at the intersection where the Y-shaped branch node is located using the corresponding Y-shaped branch convex hull further includes obtaining multiple map road network segmentation units using the smallest indivisible unit of all intersections. This facilitates obtaining map road network segmentation units with the required length and size as needed for high-precision map segmentation tasks.

[0052] In one optional embodiment of this application, the length of multiple map road network segmentation units does not exceed the range of length values ​​predetermined based on available computer resources and corresponding task time limits, so as to maximize the saving of available computer resources and improve mapping efficiency.

[0053] Specifically, the number of concurrent mapping tasks and the size of the data processed by each concurrent task can be determined based on available computer resources, thereby saving computer resources and reducing task time as much as possible. Correspondingly, the aforementioned [specific parameters] can be determined based on the size of the data processed by each concurrent task.

[0054] Specifically, each of the above-mentioned road network segmentation units can be a road network unit with a length value not much different from 3km.

[0055] In one specific embodiment of this application, the map road network segmentation method further includes dividing the non-intersection portion of the map road network in a predetermined area according to predetermined rules to obtain multiple non-intersection minimum indivisible units whose lengths differ from the sum of the lengths of all road segments in the minimum indivisible unit of an intersection by no more than a preset length threshold. The non-intersection portion includes the rest of the map road network in the predetermined area excluding the minimum indivisible unit of an intersection.

[0056] This embodiment facilitates the subsequent merging of the smallest indivisible unit at intersections and the smallest indivisible unit at non-intersections into multiple map road network segmentation units with similar lengths. This allows for high concurrency in the map production process by utilizing multiple map road network segmentation units of uniform length, thereby achieving low resource consumption and low time consumption, thus improving the efficiency of producing high-precision maps and reducing resource consumption.

[0057] In a specific example of this application, the non-intersection portion of the map road network of the predetermined area is uniformly divided to obtain multiple other minimum indivisible units whose lengths differ from the sum of the lengths of all road segments in the minimum indivisible unit of each intersection by no more than a first preset length threshold.

[0058] This embodiment applies to areas where, apart from intersections, there are no other sensitive points in the predetermined area that would easily lead to merging difficulties when merging map data. Specifically, the aforementioned other smallest indivisible unit can be a road network unit with a length of 300m.

[0059] Specifically, dividing non-intersection areas into subdivision units that are not significantly different from the sum of the lengths of all road segments in the smallest indivisible unit of each intersection is beneficial for subsequent merging to obtain multiple map road network subdivision units with the smallest length differences.

[0060] In one specific embodiment of this application, the process of obtaining multiple map road network segmentation units using the smallest indivisible units of all intersections includes merging each smallest indivisible unit of an intersection with at least one adjacent smallest indivisible unit of a non-intersection to obtain multiple map road network segmentation units with lengths conforming to a preset length range. This allows for the merging of multiple map road network segmentation units with minimal length differences, enabling multiple mapping tasks to run concurrently with low resource consumption and low time consumption, thereby improving the efficiency of high-precision map production, reducing resource consumption, and minimizing merging errors.

[0061] In another specific embodiment of this application, a map road network segmentation method based on intersections includes,

[0062] Obtain multiple Y-shaped branch road nodes in the map road network of a predetermined area; at a first predetermined distance from the corresponding Y-shaped branch road node, extend a second predetermined length to both sides of the road along the normal direction of the road to obtain a first reference point and a second reference point corresponding to the road; construct the Y-shaped branch road convex hull corresponding to the corresponding Y-shaped branch road node using the first reference points and second reference points of all roads connected to each Y-shaped branch road node; and construct a map road network segmentation unit including the road segment at the intersection where the Y-shaped branch road node is located using the corresponding Y-shaped branch road convex hull.

[0063] This implementation divides the road segment at the intersection into a map road network segmentation unit, and uses the indivisible unit including the intersection to obtain the map road network segmentation unit. This allows the intersection road segment to be completed in a single map segmentation task during the high-precision map segmentation and mapping process, thus avoiding merging at the intersection during subsequent merging. This improves the efficiency of high-precision map production, reduces resource consumption, and reduces merging errors.

[0064] In one specific embodiment of this application, the aforementioned Y-shaped branch convex hull is as follows: Figure 2 As shown.

[0065] The specific intersections mentioned above can be Y-shaped intersections, crossroads, T-shaped intersections, or multi-way intersections, etc. Because different types of intersections, regardless of how many roads converge, they all contain at least one Y-shaped branch road. In other words, a large intersection must be composed of multiple Y-shaped branches roads.

[0066] In one specific embodiment of this application, the process of constructing a map road network segmentation unit including the road segment at the intersection where the Y-shaped branch node is located using the corresponding Y-shaped branch convex hull includes merging the Y-shaped branch convex hulls with overlapping areas to obtain an intersection convex hull; and constructing the map road network segmentation unit using the Y-shaped branch convex hull or the intersection convex hull that do not overlap with other Y-shaped branch convex hulls.

[0067] Specifically, for a Y-shaped intersection, which only includes one Y-shaped branch, the map road network segmentation unit can be constructed directly using the convex hull of this Y-shaped branch to include all road segments at the intersection containing the Y-shaped branch node within a single map road network segmentation unit; however, for some intersections, such as crossroads... Figure 2 As shown, there are multiple Y-shaped branches, so it is necessary to merge the overlapping convex hulls to obtain the intersection convex hull, and then construct the map road network segmentation unit based on the intersection convex hull.

[0068] In one specific embodiment of this application, the latitude, longitude, and elevation information of the Y-shaped intersection convex hull can be used to determine whether there is an overlapping area with other Y-shaped intersection convex hulls. Specifically, the process of checking whether each Y-shaped intersection convex hull intersects with every other Y-shaped intersection convex hull in a plurality of Y-shaped intersection convex hulls includes: first sorting the plurality of Y-shaped intersection convex hulls according to longitude coordinates, and then sorting them according to latitude coordinates; and determining whether the minimum longitude coordinate value of the Y-shaped intersection convex hull with the larger longitude coordinate in the longitude coordinate sorting among two adjacent Y-shaped intersection convex hulls is greater than the maximum longitude coordinate value of the Y-shaped intersection convex hull with the smaller longitude coordinate in the longitude coordinate sorting.

[0069] If the difference is not greater than the maximum value, then the minimum latitude coordinate value of the Y-shaped convex hull with the larger latitude coordinate in the corresponding two adjacent Y-shaped branch convex hulls is determined to be greater than the maximum latitude value of the Y-shaped convex hull with the smaller latitude coordinate. If the difference is not greater than the maximum latitude coordinate, then the corresponding two adjacent Y-shaped branch convex hulls are determined to be intersecting; otherwise, the corresponding two adjacent Y-shaped branch convex hulls are determined to be non-intersecting.

[0070] Otherwise, the corresponding two Y-shaped branch convex hulls are judged as non-intersecting.

[0071] Figure 4 This application illustrates a specific embodiment of a map road network segmentation device based on intersections.

[0072] exist Figure 4 The specific implementation of the intersection-based map road network segmentation device of this application shown includes,

[0073] Y-shaped branch road node acquisition module 401 is used to find and acquire multiple Y-shaped branch road nodes in the map road network of a predetermined area; road vertical line segment generation module 402 is used to generate a road vertical line segment of a second predetermined length at a first predetermined length distance from the corresponding Y-shaped branch road node for each road connected to each Y-shaped branch road node, each road vertical line segment including the first endpoint and the last endpoint distributed in a clockwise direction with the Y-shaped branch road node as the rotation center; Y-shaped branch road convex hull acquisition module 403 is used to connect the first endpoint of each road vertical line segment with the last endpoint of the adjacent road vertical line segment to obtain multiple Y-shaped branch road convex hulls containing each Y-shaped branch road node; and map road network segmentation unit construction module 404 is used to construct a map road network segmentation unit including the road segment at the intersection where the Y-shaped branch road node is located using the corresponding Y-shaped branch road convex hulls.

[0074] The device of this application divides the road segment at the intersection into an indivisible unit of the map road network segmentation unit, and uses the indivisible unit including the intersection to obtain the map road network segmentation unit. This allows the intersection road segment to be carried out in a single map segmentation task during the high-precision map segmentation and mapping process, so that subsequent merging avoids merging at the intersection. This improves the production efficiency of high-precision maps, reduces resource consumption, and reduces merging errors.

[0075] The Y-shaped branch node acquisition module 401 is used to find and acquire multiple Y-shaped branch nodes in the map road network of a predetermined area, which can facilitate the location and acquisition of intersection road segments based on the acquired branch nodes.

[0076] This module generates a road vertical line segment of a second predetermined length at a first predetermined distance from the corresponding Y-shaped branch node for each road connected to each Y-shaped branch node. Each road vertical line segment includes a road vertical line segment generation module 402 with the first and last endpoints distributed in a clockwise direction around the Y-shaped branch node as the rotation center. This facilitates the generation of Y-shaped branch convex hulls based on vertical line segments, and further facilitates the generation of map road network segmentation units for road segments at the corresponding intersections.

[0077] The Y-shaped branch convex hull acquisition module 403 connects the first endpoint of each road vertical line segment to the last endpoint of the adjacent road vertical line segment to obtain multiple Y-shaped branch convex hulls containing each Y-shaped branch node. This facilitates the construction of map road network segmentation units at corresponding intersections using the corresponding Y-shaped branch convex hulls. The map road network segmentation unit construction module 404 constructs map road network segmentation units including road segments at intersections containing Y-shaped branch nodes using the corresponding Y-shaped branch convex hulls. This ultimately yields map road network segmentation units including road segments at intersections containing Y-shaped branch nodes. This facilitates high-precision map segmentation and mapping processes, allowing intersection and road segments to be segmented within a single mapping task, avoiding merging at intersections during subsequent merging. This improves the efficiency of high-precision map production, reduces resource consumption, and minimizes merging errors.

[0078] The intersection-based map road network segmentation device provided in this application can be used to execute the intersection-based map road network segmentation device described in any of the above embodiments. Its implementation principle and technical effect are similar, and will not be repeated here.

[0079] In one specific embodiment of this application, the functional modules of the intersection-based map road network segmentation device of this application can be directly in hardware, in software modules executed by a processor, or in a combination of both.

[0080] Software modules may reside in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disks, removable disks, CD-ROMs, or any other form of storage medium known in this art. An exemplary storage medium is coupled to the processor, enabling the processor to read information from and write information to the storage medium.

[0081] The processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic, discrete hardware components, or any combination thereof. A general-purpose processor can be a microprocessor, but alternatively, it can be any conventional processor, controller, microcontroller, or state machine. The processor can also be implemented as a combination of computing devices, such as a combination of a DSP and a microprocessor, multiple microprocessors, one or more microprocessors incorporating a DSP core, or any other such configuration. Alternatively, the storage medium can be integrated with the processor. The processor and storage medium can reside in an ASIC. The ASIC can reside in the user terminal. Alternatively, the processor and storage medium can reside as discrete components in the user terminal.

[0082] In another specific embodiment of this application, a map production system is provided, wherein the driving system includes a map matching device, and optionally, the image sensing and display device includes a processor and a memory, which are coupled together; the map matching device is used to execute the map road network segmentation method in any of the above schemes.

[0083] In another specific embodiment of this application, a computer-readable storage medium is provided, which stores computer instructions that are operated to perform the intersection-based map road network segmentation method in any of the above schemes.

[0084] In another specific embodiment of this application, a computer device includes a processor and a memory, the memory storing computer instructions that are operated to execute the intersection-based map road network segmentation method in any of the above schemes.

[0085] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only 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 coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0086] 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 network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0087] The above are merely embodiments of this application and do not limit the scope of this patent application. Any equivalent structural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the scope of patent protection of this application.

Claims

1. A map road network partitioning method based on intersections, characterized by, include: Find and retrieve multiple Y-shaped branch road nodes in the map road network of a predetermined area; At a first predetermined distance from the corresponding Y-shaped branch node, a road vertical segment of a second predetermined length is generated for each road connected to each Y-shaped branch node. Each road vertical segment includes a head end and a tail end distributed in a clockwise direction with the Y-shaped branch node as the rotation center. Connect the first endpoint of each road vertical segment to the last endpoint of the adjacent road vertical segment to obtain multiple Y-shaped branch convex hulls containing each of the Y-shaped branch nodes; and, Constructing a map road network segmentation unit including the road segment at the intersection where the Y-shaped branch node is located using the corresponding Y-shaped branch convex hull, wherein the construction of the map road network segmentation unit including the road segment at the intersection where the Y-shaped branch node is located using the corresponding Y-shaped branch convex hull further includes: The process involves checking whether each Y-shaped branch convex hull intersects with every other Y-shaped branch convex hull. If they intersect, the two intersecting Y-shaped branch convex hulls are merged to obtain multiple intersection convex hulls that do not intersect with each other. The process of checking whether each Y-shaped branch convex hull intersects with every other Y-shaped branch convex hull includes: The multiple Y-shaped branch convex hulls are first sorted according to longitude coordinates, and then sorted according to latitude coordinates; To determine whether the minimum longitude coordinate value of the Y-shaped branch convex hull with the larger longitude coordinate ranking among two adjacent Y-shaped branch convex hulls is greater than the maximum longitude coordinate value of the Y-shaped branch convex hull with the smaller longitude coordinate ranking, we need to examine whether it is greater than the maximum longitude coordinate value of the Y-shaped branch convex hull with the smaller longitude coordinate ranking. If not greater than, then determine whether the minimum latitude coordinate value of the Y-shaped branch convex hull with the larger latitude coordinate in the corresponding two adjacent Y-shaped branch convex hulls is greater than the maximum latitude value of the Y-shaped branch convex hull with the smaller latitude coordinate. If not greater than, then determine that the corresponding two adjacent Y-shaped branch convex hulls intersect; otherwise, determine that the corresponding two adjacent Y-shaped branch convex hulls do not intersect. The smallest indivisible unit of the intersection where the corresponding Y-shaped branch node is located is obtained by utilizing the roads within the range included by the convex hull of each intersection; and, Multiple map road network segmentation units are obtained by utilizing the smallest indivisible unit of all the aforementioned intersections.

2. The intersection-based map road network partitioning method of claim 1, wherein, The process of checking whether each Y-shaped branch convex hull intersects with every other Y-shaped branch convex hull in the plurality of Y-shaped branch convex hulls, and merging the two intersecting Y-shaped branch convex hulls if they intersect, to obtain a plurality of intersection convex hulls that do not intersect with each other, includes, A spatial indexing algorithm is used to search within a predetermined spatial range around each Y-shaped branch convex hull to determine if there are other Y-shaped branch convex hulls. If other Y-shaped branch convex hulls are found, the disjoint-set data structure algorithm is used to calculate whether each Y-shaped branch convex hull in the predetermined spatial range intersects with each other Y-shaped branch convex hull. If they intersect, the two intersecting Y-shaped branch convex hulls are merged.

3. The intersection-based map road network partitioning method of claim 1, wherein, The process of merging the convex hulls of two intersecting Y-shaped branch roads to obtain multiple non-intersecting intersection convex hulls includes: Reconstruct a new convex hull from all the points that form the convex hulls of the two intersecting Y-shaped forks to obtain the intersection convex hull.

4. The intersection-based map road network partitioning method of claim 1, wherein, The process of obtaining multiple Y-shaped branch road nodes in the map road network of the predetermined area includes: Traverse the intermediate road nodes of each road in the map road network of the predetermined area to obtain the intersecting intermediate nodes that connect the corresponding road to other roads, and break the corresponding road at the intersecting intermediate nodes to obtain the preprocessed road network of the predetermined area. Traverse the first and last nodes of all roads in the preprocessed road network of the predetermined area to obtain Y-shaped branch nodes with more than 2 connected roads.

5. The intersection-based map road network segmentation method according to claim 1, characterized in that, It also includes, The non-intersection portion of the map road network in the predetermined area is divided according to predetermined rules to obtain multiple non-intersection minimum indivisible units whose lengths differ from the sum of the lengths of all road segments in each minimum indivisible unit of the intersection by no more than a preset length threshold. The non-intersection portion includes the road network of the predetermined area other than the smallest indivisible unit of the intersection.

6. The intersection-based map road network segmentation method according to claim 5, characterized in that, The process of obtaining multiple map road network segmentation units using the smallest indivisible units of all the intersections includes: Each of the intersection's smallest indivisible unit is merged with at least one adjacent non-intersection's smallest indivisible unit to obtain multiple map road network segmentation units with lengths conforming to a preset length range.

7. A method for segmenting a map road network based on intersections, characterized in that, include: Obtain multiple Y-shaped branch road nodes in the map road network of a predetermined area; At a first predetermined length from the corresponding Y-shaped branch node, each road connected to each Y-shaped branch node is extended a second predetermined length to both sides of the road along the road normal direction to obtain a first reference point and a second reference point corresponding to the road. Using the first and second reference points of all roads connected to each Y-shaped branch node, construct the Y-shaped branch convex hull corresponding to the respective Y-shaped branch node; and Constructing a map road network segmentation unit including the road segment at the intersection where the Y-shaped branch node is located using the corresponding Y-shaped branch convex hull, wherein the construction of the map road network segmentation unit including the road segment at the intersection where the Y-shaped branch node is located using the corresponding Y-shaped branch convex hull further includes: The process involves checking whether each Y-shaped branch convex hull intersects with every other Y-shaped branch convex hull. If they intersect, the two intersecting Y-shaped branch convex hulls are merged to obtain multiple intersection convex hulls that do not intersect with each other. The process of checking whether each Y-shaped branch convex hull intersects with every other Y-shaped branch convex hull includes: The multiple Y-shaped branch convex hulls are first sorted according to longitude coordinates, and then sorted according to latitude coordinates; To determine whether the minimum longitude coordinate value of the Y-shaped branch convex hull with the larger longitude coordinate ranking among two adjacent Y-shaped branch convex hulls is greater than the maximum longitude coordinate value of the Y-shaped branch convex hull with the smaller longitude coordinate ranking, we need to examine whether it is greater than the maximum longitude coordinate value of the Y-shaped branch convex hull with the smaller longitude coordinate ranking. If not greater than, then determine whether the minimum latitude coordinate value of the Y-shaped branch convex hull with the larger latitude coordinate in the corresponding two adjacent Y-shaped branch convex hulls is greater than the maximum latitude value of the Y-shaped branch convex hull with the smaller latitude coordinate. If not greater than, then determine that the corresponding two adjacent Y-shaped branch convex hulls intersect; otherwise, determine that the corresponding two adjacent Y-shaped branch convex hulls do not intersect. The smallest indivisible unit of the intersection where the corresponding Y-shaped branch node is located is obtained by utilizing the roads within the range included by the convex hull of each intersection; and, Multiple map road network segmentation units are obtained by utilizing the smallest indivisible unit of all the aforementioned intersections.

8. The intersection-based map road network segmentation method according to claim 7, characterized in that, The construction of a map road network segmentation unit, including the road segment at the intersection where the Y-shaped branch node is located, using the corresponding Y-shaped branch convex hull, further includes: The Y-shaped branch convex hulls with overlapping areas are merged to obtain a single intersection convex hull; The map road network segmentation unit is constructed using the Y-shaped branch convex hull or the intersection convex hull, which do not overlap with the Y-shaped branch convex hulls of other Y-shaped branch convex hulls.

9. The intersection-based map road network segmentation method according to claim 8, characterized in that, The latitude, longitude, and elevation information of the Y-shaped intersection convex hull are used to determine whether there is an overlapping area with other Y-shaped intersection convex hulls.

10. A map road network segmentation device based on intersections, characterized in that, include, The Y-type branch road node acquisition module is used to find and acquire multiple Y-type branch road nodes in the map road network of a predetermined area; The road vertical segment generation module is used to generate a road vertical segment of a second predetermined length at a first predetermined distance from the corresponding Y-shaped branch node for each road connected to each Y-shaped branch node. Each road vertical segment includes a first endpoint and a last endpoint that are distributed in a clockwise direction with the Y-shaped branch node as the rotation center. The Y-shaped branch convex hull acquisition module is used to connect the first endpoint of each road vertical line segment to the last endpoint of the adjacent road vertical line segment to obtain multiple Y-shaped branch convex hulls containing each Y-shaped branch node; and, A map road network segmentation unit construction module is used to construct a map road network segmentation unit including the road segment at the intersection where the Y-shaped branch road node is located using the corresponding Y-shaped branch road convex hulls. The construction of the map road network segmentation unit including the road segment at the intersection where the Y-shaped branch road node is located using the corresponding Y-shaped branch road convex hulls further includes: checking whether each Y-shaped branch road convex hull intersects with each other in the plurality of Y-shaped branch road convex hulls; if they intersect, merging the two intersecting Y-shaped branch road convex hulls to obtain a plurality of intersection convex hulls that do not intersect with each other. The process of checking whether each Y-shaped branch road convex hull intersects with each other in the plurality of Y-shaped branch road convex hulls includes: first sorting the plurality of Y-shaped branch road convex hulls according to longitude coordinates, and then sorting them according to latitude coordinates; and sorting adjacent Y-shaped branch road convex hulls... The system determines whether the minimum longitude coordinate of the Y-shaped branch convex hull with a larger longitude coordinate is greater than the maximum longitude coordinate of the Y-shaped branch convex hull with a smaller longitude coordinate. If not, it determines whether the minimum latitude coordinate of the Y-shaped branch convex hull with a larger latitude coordinate is greater than the maximum latitude coordinate of the Y-shaped branch convex hull with a smaller latitude coordinate. If not, the two adjacent Y-shaped branch convex hulls are considered intersecting; otherwise, they are considered non-intersecting. The system then uses the roads within the area included by each intersection convex hull to obtain the smallest indivisible unit of the intersection where the corresponding Y-shaped branch node is located. Finally, it uses all the smallest indivisible units of the intersection to obtain multiple map road network segmentation units.

11. A map creation system, characterized in that, The map creation system includes the intersection-based map road network segmentation device as described in claim 10.

12. A computer-readable storage medium storing computer instructions, characterized in that, When the computer instructions are executed, the computer performs the intersection-based map road network segmentation method as described in any one of claims 1-6.

13. A computer device comprising a processor and a memory, the memory storing computer instructions, characterized in that, When the computer instructions are executed by the processor, they implement the intersection-based map road network segmentation method as described in any one of claims 1-6.

Images