Configuration Method and Device for Lane Surface Relationship, Storage Medium, Electronic Device

Abstract

The present invention provides a method and apparatus for configuring lane surface relationships, a storage medium, and an electronic device, belonging to the field of map data. Among them, the method includes: reading lane initial data, direction semantic data, and stop line semantic data from map data; constructing a vector lane surface set using the lane initial data and the direction semantic data; screening out a first lane surface set of two-way traffic roads from the vector lane surface set; aligning the first lane surface set based on the stop line semantic data to obtain a second lane surface set; configuring the connection relationship between the lane surfaces in the second lane surface set and adjacent lane surfaces. Through the embodiments of the present invention, the technical problem that the attribute data of lane surfaces in the related art is incomplete is solved, and the business value of lane surfaces in high-precision maps is improved.

Description

Technical Field

[0001] The present invention relates to the field of map data, and in particular, to a method and device for configuring a lane-plane relationship, a storage medium, and an electronic device. Background Art

[0002] In the related art, high-precision maps are indispensable in the development process of autonomous driving technology, and positioning and planning need to be carried out with the help of high-precision maps. The construction of lane lines and lane topology connectivity is an important part of high-precision map production.

[0003] In the related art, the construction of lane topology mainly depends on the road scene, resulting in a strong dependence on the quality and integrity of the road scene, with great limitations and incomplete attribute data of the lane plane.

[0004] In view of the above problems in the related art, no efficient and accurate solution has been found yet. Summary of the Invention

[0005] The present invention provides a method and device for configuring a lane-plane relationship, a storage medium, and an electronic device to solve the technical problems in the related art.

[0006] According to an embodiment of the present invention, a method for configuring a lane-plane relationship is provided, including: reading lane initial data, direction semantic data, and stop line semantic data from map data; constructing a vector lane-plane set by using the lane initial data and the direction semantic data; screening out a first lane-plane set of two-way traffic roads from the vector lane-plane set; aligning the first lane-plane set based on the stop line semantic data to obtain a second lane-plane set; and configuring the connection relationship between the lane planes in the second lane-plane set and adjacent lane planes.

[0007] Further, constructing a vector lane-plane set by using the lane initial data and the direction semantic data includes: constructing a plurality of lane polygons by using the same-direction lane boundary lines in the lane initial data; for each lane polygon, determining the traffic direction of the lane polygon according to the direction semantic data; updating the vector point order of the lane polygon based on the traffic direction, and configuring the traffic direction attribute of the lane polygon to obtain a vector lane-plane set.

[0008] Further, screening out the first lane surface set of two-way traffic roads from the vector lane surface set includes: traversing each vector lane surface in the vector lane surface set, and performing the following steps for each vector lane surface: determining whether the vector lane surface is a one-way traffic lane or a two-way traffic lane; if the vector lane surface is a one-way traffic lane, filtering the vector lane surface in the vector lane surface set, and if the vector lane surface is a two-way traffic lane, configuring the front and rear relationship attributes of the vector lane surface in the vector lane surface set; after the traversal of the vector lane surface set is completed, obtaining the first lane surface set.

[0009] Further, aligning the first lane surface set based on the stop line semantic data to obtain a second lane surface set includes: generating a stop line set based on the stop line semantic data; traversing each stop line in the stop line set and each first lane surface in the first lane surface set, and determining whether the left and right sides of the first lane surface intersect with the stop line; if the left and right sides of the first lane surface intersect with the stop line, cropping the first lane surface based on the stop line; if the left and right sides of the first lane surface do not intersect with the stop line, extending the first lane surface to align with the stop line, thereby obtaining the second lane surface set.

[0010] Further, after aligning the first lane surface set based on the stop line semantic data to obtain the second lane surface set, the method further includes: swapping the left and right side relationships of each second lane surface in the second lane surface set, and constructing a virtual lane surface set; configuring the control attributes of each lane surface in the second lane surface set, where the control attributes distinguish the virtual lane surface and the real lane surface corresponding to the same lane surface identifier.

[0011] Further, configuring the connection relationship between the lane surfaces in the second lane surface set and the adjacent lane surfaces includes: for each target lane surface in the second lane surface set, obtaining the lane boundary of the target lane surface, where the lane boundary includes the upper boundary and the lower boundary; searching for the adjacent lane surfaces of the lane boundary within a specified preset range based on the traffic direction of the target lane surface, obtaining an adjacent lane surface set, where the adjacent lane surface set includes: the successor lane surface adjacent to the upper boundary, and the pre-order lane surface adjacent to the lower boundary; screening out the connection lane surface set that meets the preset boundary relationship in the adjacent lane surface set, and configuring the connection relationship between the target lane surface and the adjacent lane surfaces according to the connection lane surface set.

[0012] Further, screening a set of consecutive lane surfaces that meet the preset boundary relationship from the set of adjacent lane surfaces, and configuring the connection relationship between the target lane surface and the adjacent lane surfaces according to the set of consecutive lane surfaces includes: traversing the set of adjacent lane surfaces and performing the following steps until the last adjacent lane surface: locating the first side edge of the target lane surface and the second side edge of the current adjacent lane surface, where the first side edge and the second side edge are adjacent edges to each other; calculating the elevation difference between the midpoint of the first side edge and the midpoint of the second side edge; determining whether the elevation difference is greater than a specified threshold; if the elevation difference is less than the specified threshold; calculating the first distance between the upper boundary of the target lane surface and the lower boundary of the current adjacent lane surface, calculating the second distance between the lower boundary of the target lane surface and the lower boundary of the current adjacent lane surface, calculating the third distance between the upper boundary of the target lane surface and the upper boundary of the current adjacent lane surface, and calculating the fourth distance between the lower boundary of the target lane surface and the upper boundary of the current adjacent lane surface; determining whether the first distance is greater than the second distance and whether the third distance is greater than the fourth distance; if the first distance is less than or equal to the second distance and the third distance is less than or equal to the fourth distance, calculating the similarity between the target lane surface and the current adjacent lane surface; if the similarity is greater than a preset threshold, constructing a connection line using the midpoint of the first side edge and the midpoint of the second side edge; selecting consecutive lane surfaces that do not intersect with the connection line from the set of adjacent lane surfaces; after the traversal of the set of adjacent lane surfaces is completed, configuring the connection relationship between the target lane surface and the adjacent lane surfaces according to the set of consecutive lane surfaces of the target lane surface.

[0013] Further, configuring the connection relationship between the target lane surface and the adjacent lane surfaces according to the set of consecutive lane surfaces of the target lane surface includes: counting the number of consecutive lane surfaces of the target lane surface from the set of consecutive lane surfaces; if the number of consecutive lane surfaces is 0, configuring the relationship between the target lane surface and the consecutive lane surface as no relationship; if the number of consecutive lane surfaces is 1, obtaining the two adjacent edges of the target lane surface and the consecutive lane surface, and if the length difference between the two adjacent edges is within the specified threshold range, configuring the relationship between the target lane surface and the consecutive lane surface as 1:1, and if the length difference between the two adjacent edges is not within the specified threshold range, configuring the relationship between the target lane surface and the consecutive lane surface as M:n; if the number of consecutive lane surfaces is 2, respectively locating the first consecutive lane surface and the second consecutive lane surface and the first adjacent edge and the second adjacent edge of the target lane surface, and calculating the first projection distance ratio and the second projection distance ratio of the first adjacent edge and the second adjacent edge to the target lane surface respectively; if both the first projection distance ratio and the second projection distance ratio are less than 50%, configuring the relationship between the target lane surface and the consecutive lane surface as 1:1.2; if the number of consecutive lane surfaces is greater than 2, configuring the relationship between the target lane surface and the consecutive lane surface as M:n.

[0014] According to another embodiment of the present invention, a configuration device for lane surface relationships is provided, including: a reading module for reading lane initial data, direction semantic data, and stop line semantic data from map data; a construction module for constructing a vector lane surface set using the lane initial data and the direction semantic data; a screening module for screening out a first lane surface set of two-way traffic roads from the vector lane surface set; an alignment module for aligning the first lane surface set based on the stop line semantic data to obtain a second lane surface set; a first configuration module for configuring the connection relationship between the lane surfaces in the second lane surface set and adjacent lane surfaces.

[0015] Further, the construction module includes: a construction unit for constructing a plurality of lane polygons using the same-direction lane boundary lines in the lane initial data; a determination unit for determining the traffic direction of each lane polygon according to the direction semantic data for each lane polygon; a configuration unit for updating the vector point order of the lane polygon based on the traffic direction and configuring the traffic direction attribute of the lane polygon to obtain a vector lane surface set.

[0016] Further, the screening module includes: a traversal unit for traversing each vector lane surface in the vector lane surface set and performing the following steps for each vector lane surface: determining whether the vector lane surface is a one-way traffic lane or a two-way traffic lane; if the vector lane surface is a one-way traffic lane, filtering the vector lane surface in the vector lane surface set, and if the vector lane surface is a two-way traffic lane, configuring the front-back relationship attribute of the vector lane surface in the vector lane surface set; a processing unit for obtaining a first lane surface set after the traversal of the vector lane surface set is completed.

[0017] Further, the alignment module includes: a generation unit for generating a stop line set based on the stop line semantic data; a judgment unit for traversing each stop line in the stop line set and each first lane surface in the first lane surface set to determine whether the left and right sides of the first lane surface intersect with the stop line; an alignment unit for, if the left and right sides of the first lane surface intersect with the stop line, cropping the first lane surface based on the stop line; if the left and right sides of the first lane surface do not intersect with the stop line, extending the first lane surface to align with the stop line to obtain a second lane surface set.

[0018] Further, the method further includes: a swapping module, configured to, after the alignment module aligns the first lane surface set based on the stop line semantic data to obtain a second lane surface set, swap the left and right side relationships of each second lane surface in the second lane surface set, and construct a virtual lane surface set; a second configuration module, configured to configure the control attributes of each lane surface in the second lane surface set, where the control attributes distinguish the virtual lane surface and the real lane surface corresponding to the same lane surface identifier.

[0019] Further, the first configuration module includes: an obtaining unit, configured to obtain, for each target lane surface in the second lane surface set, the lane boundaries of the target lane surface, where the lane boundaries include an upper boundary and a lower boundary; a searching unit, configured to search, within a specified preset range based on the traffic direction of the target lane surface, for adjacent lane surfaces of the lane boundaries to obtain an adjacent lane surface set, where the adjacent lane surface set includes: a successor lane surface adjacent to the upper boundary and a preceding lane surface adjacent to the lower boundary; a configuration unit, configured to screen, from the adjacent lane surface set, a set of consecutive lane surfaces that meet the preset boundary relationship, and configure the consecutive relationship between the target lane surface and the adjacent lane surfaces according to the set of consecutive lane surfaces.

[0020] Further, the configuration unit includes: a traversing subunit, configured to perform the following steps on the adjacent lane surface set until the last adjacent lane surface: locate a first side edge of the target lane surface and a second side edge of the current adjacent lane surface, where the first side edge and the second side edge are adjacent to each other; calculate the elevation difference between the midpoint of the first side edge and the midpoint of the second side edge; determine whether the elevation difference is greater than a specified threshold; if the elevation difference is less than the specified threshold; calculate a first distance between the upper boundary of the target lane surface and the lower boundary of the current adjacent lane surface, calculate a second distance between the lower boundary of the target lane surface and the lower boundary of the current adjacent lane surface, calculate a third distance between the upper boundary of the target lane surface and the upper boundary of the current adjacent lane surface, and calculate a fourth distance between the lower boundary of the target lane surface and the upper boundary of the current adjacent lane surface; determine whether the first distance is greater than the second distance and whether the third distance is greater than the fourth distance; if the first distance is less than or equal to the second distance and the third distance is less than or equal to the fourth distance, calculate the similarity between the target lane surface and the current adjacent lane surface; if the similarity is greater than a preset threshold, construct a connection line using the midpoint of the first side edge and the midpoint of the second side edge; select, from the adjacent lane surface set, consecutive lane surfaces that do not intersect the connection line; a configuration subunit, configured to, after the traversing of the adjacent lane surface set is completed, configure the consecutive relationship between the target lane surface and the adjacent lane surfaces according to the set of consecutive lane surfaces of the target lane surface.

[0021] Further, the configuration subunit is further configured to: count the number of successive lane surfaces of the target lane surface from the set of successive lane surfaces; if the number of successive lane surfaces is 0, configure the relationship between the target lane surface and the successive lane surface as no relationship; if the number of successive lane surfaces is 1, obtain two adjacent edges of the target lane surface and the successive lane surface, and if the length difference between the two adjacent edges is within a specified threshold range, configure the relationship between the target lane surface and the successive lane surface as 1:1, if the length difference between the two adjacent edges is not within the specified threshold range, configure the relationship between the target lane surface and the successive lane surface as M:n; if the number of successive lane surfaces is 2, respectively locate the first adjacent edge and the second adjacent edge of the first successive lane surface and the second successive lane surface with respect to the target lane surface, and calculate the first projection distance ratio and the second projection distance ratio of the first adjacent edge and the second adjacent edge to the target lane surface respectively; if both the first projection distance ratio and the second projection distance ratio are less than 50%, configure the relationship between the target lane surface and the successive lane surface as 1:1.2; if the number of successive lane surfaces is greater than 2, configure the relationship between the target lane surface and the successive lane surface as M:n.

[0022] According to another aspect of the embodiments of the present application, there is also provided a storage medium, which includes a stored program, and the program executes the above steps when running.

[0023] According to another aspect of the embodiments of the present application, there is also provided an electronic device, including a processor, a communication interface, a memory, and a communication bus. Among them, the processor, the communication interface, and the memory complete communication with each other through the communication bus; wherein: the memory is used for storing a computer program; the processor is used for executing the steps in the above method by running the program stored on the memory.

[0024] The embodiments of the present application also provide a computer program product containing instructions, which, when running on a computer, causes the computer to execute the steps in the above method.

[0025] Through the embodiments of the present invention, lane initial data, direction semantic data, and stop line semantic data are read from map data. A vector lane surface set is constructed using the lane initial data and the direction semantic data. The first lane surface set of two-way traffic roads is filtered out from the vector lane surface set. The first lane surface set is aligned based on the stop line semantic data to obtain the second lane surface set. The connection relationship between the lane surfaces in the second lane surface set and adjacent lane surfaces is configured. For the lane surface data constructed by the lane edges, the lane edges and the lane-level trajectory data are used for vector point optimization. By using the stop line type semantic data to perform alignment processing on the lane surfaces, the missing lane surfaces can be optimized. By configuring the connection relationship between the lane surfaces and adjacent lane surfaces, the connection relationship between the lane surfaces in the driving direction of the road is successfully constructed, and more accurate lane centerlines can be generated and more accurate road topology relationships can be constructed, solving the technical problem of incomplete attribute data of lane surfaces in the related art and improving the business value of lane surfaces in the high-precision map. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The schematic embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0027] Figure 1 is a block diagram of the hardware structure of a computer according to an embodiment of the present invention;

[0028] Figure 2 is a flowchart of a method for configuring a lane surface relationship according to an embodiment of the present invention;

[0029] Figure 3 is a schematic diagram of the midpoint of the adjacent edges of two surfaces in an embodiment of the invention;

[0030] Figure 4 is a mapping schematic diagram of the proportion and relationship pattern in an embodiment of the present invention;

[0031] Figure 5 is a schematic diagram of the construction process of a lane surface relationship described in the present invention;

[0032] Figure 6 is a block diagram of the structure of a device for configuring a lane surface relationship according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0033] To enable those skilled in the art to better understand the solution of this application, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of this application. Obviously, the described embodiments are only a part of the embodiments of this application, rather than all the embodiments. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the scope of protection of this application. It should be noted that, without conflict, the embodiments in this application and the features in the embodiments may be combined with each other.

[0034] It should be noted that the terms "first", "second", etc. in the specification, claims and drawings of this application are used to distinguish similar objects, and do not necessarily have to be used to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of this application described here can be implemented in an order other than those illustrated or described here. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, product or device that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0035] Embodiment 1

[0036] The method embodiment provided by the first embodiment of this application can be executed on a computer, a server, or a similar processing device. Taking running on a computer as an example, Figure 1 is a hardware structure block diagram of a computer according to an embodiment of the present invention. As Figure 1 shown, the computer may include one or more ( Figure 1 only one is shown in the figure) processors 102 (the processors 102 may include, but are not limited to, processing devices such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data. Optionally, the above computer may further include a transmission device 106 for communication functions and an input / output device 108. Those of ordinary skill in the art can understand that Figure 1 the structure shown is only schematic and does not limit the structure of the above computer. For example, the computer may further include more or fewer components than Figure 1 shown in the figure, or have a different configuration from Figure 1 shown in the figure.

[0037] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to a configuration method of a lane surface relationship in an embodiment of the present invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, the above-mentioned method is implemented. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memories, or other non-volatile solid-state memories. In some instances, the memory 104 may further include a memory remotely disposed relative to the processor 102, and these remote memories can be connected to the computer through a network. Examples of the above-mentioned network include but are not limited to the Internet, intranet, local area network, mobile communication network, and combinations thereof.

[0038] The transmission device 106 is used to receive or send data via a network. Specific examples of the above-mentioned network may include a wireless network provided by a communication provider of the computer. In one instance, the transmission device 106 includes a network adapter (abbreviated as NIC), which can be connected to other network devices through a base station and thus can communicate with the Internet. In one instance, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0039] In this embodiment, a configuration method of a lane surface relationship is provided. Figure 2 It is a flowchart of a configuration method of a lane surface relationship according to an embodiment of the present invention, as Figure 2 shown, and the process includes the following steps:

[0040] Step S202, read lane initial data, direction semantic data, and stop line semantic data from the map data;

[0041] Step S204, construct a vector lane surface set by using the lane initial data and the direction semantic data;

[0042] Step S206, screen out a first lane surface set of two-way traffic roads from the vector lane surface set;

[0043] Step S208, align the first lane surface set based on the stop line semantic data to obtain a second lane surface set;

[0044] Optionally, after aligning the first lane surface set based on the stop line semantic data to obtain a second lane surface set, the method further includes: swapping the left and right side relationships of each second lane surface in the second lane surface set and constructing a virtual lane surface set; configuring the control attributes of each lane surface in the second lane surface set, where the control attributes distinguish between the virtual lane surface and the real lane surface corresponding to the same lane surface identifier. Optionally, it is also possible to update and assign the relationship attributes of the associated two-way lane surfaces and delete the two-way lane surfaces from the set.

[0045] Step S210: Configure the connection relationship between the lane surfaces in the second lane surface set and the adjacent lane surfaces.

[0046] In this embodiment, when configuring the connection relationship between the lane surfaces in the second lane surface set and the adjacent lane surfaces, it is also possible to delete the lane surfaces within the intersection and save the lane surface relationships.

[0047] During the process of deleting the lane surfaces within the intersection, filter the semantic data of the stop line and crosswalk types and record their coordinate point data , for the point set perform DBSCAN (Density-Based Spatial Clustering of Applications with Noise) density clustering analysis to obtain the intersection surface clustering set, and use the circumscribed rectangle range surface of each clustering set as the intersection surface and record it. Traverse the intersection surface and delete the lane surfaces contained within the intersection surface.

[0048] For the remaining set, store it in a file according to the specified requirements for subsequent analysis and use by business modules.

[0049] Through the above steps, read the lane initial data, direction semantic data, and stop line semantic data from the map data, construct a vector lane surface set using the lane initial data and direction semantic data, filter out the first lane surface set of two-way traffic roads from the vector lane surface set, align the first lane surface set based on the stop line semantic data to obtain a second lane surface set, configure the connection relationship between the lane surfaces in the second lane surface set and the adjacent lane surfaces, optimize the vector points through the lane surface data constructed by the lane sidelines and the lane surface edge combined with the lane-level trajectory data, optimize the missing lane surfaces by aligning the lane surfaces using the stop line type semantic data, successfully construct the connection relationship between the lane surfaces in the road traffic direction by configuring the connection relationship between the lane surfaces and the adjacent lane surfaces, can generate a more accurate lane centerline and construct a more accurate road topology relationship, solve the technical problem of incomplete attribute data of lane surfaces in the related art, and improve the business value of lane surfaces in the high-precision map.

[0050] In an implementation manner of this embodiment, constructing a vector lane surface set by using lane initial data and direction semantic data includes: constructing a plurality of lane polygons by using the same-direction lane boundary lines in the lane initial data; for each lane polygon, determining the traffic direction of the lane polygon according to the direction semantic data; updating the vector point order of the lane polygon based on the traffic direction, and configuring the traffic direction attribute of the lane polygon to obtain a vector lane surface set.

[0051] In this implementation manner, lane surface data First, a polygon is constructed from the same-direction lane boundary lines. Based on lane-level trajectory data and semantic data with a direction (such as arrows) as the basis for the road traffic direction, the vector point order of the lane polygon is optimized, and the lane traffic direction attribute is assigned.

[0052] In some examples, screening out the first lane surface set of two-way traffic roads from the vector lane surface set includes: traversing each vector lane surface in the vector lane surface set, and performing the following steps for each vector lane surface: determining whether the vector lane surface is a one-way traffic lane or a two-way traffic lane; if the vector lane surface is a one-way traffic lane, filtering the vector lane surface in the vector lane surface set, and if the vector lane surface is a two-way traffic lane, configuring the front-back relationship attribute of the vector lane surface in the vector lane surface set; after the traversal of the vector lane surface set is completed, obtaining the first lane surface set.

[0053] By traversing the vector lane surface set, filtering the items with a one-way lane direction attribute, combining the traffic direction to judge the left-right relationship of the lane surface edges and initializing and assigning attributes (process variables during operation, combining the traffic direction, judging whether the left and right of the lane surface are correct, correcting and storing the up-down-left-right edge attributes for subsequent analysis), and separately recording the lane surfaces that meet the conditions for two-way traffic. At the same time, initialize and assign the front-back relationship attributes (process variables during program operation, prev:[], next:[]).

[0054] Optionally, aligning the first lane surface set based on the stop line semantic data to obtain a second lane surface set includes: generating a stop line set based on the stop line semantic data; traversing each stop line in the stop line set and each first lane surface in the first lane surface set, and judging whether the left and right edges of the first lane surface intersect with the stop line; if the left and right edges of the first lane surface intersect with the stop line, cropping the first lane surface based on the stop line; if the left and right edges of the first lane surface do not intersect with the stop line, extending the first lane surface until it is aligned with the stop line to obtain the second lane surface set.

[0055] Load the stop line semantic data, convert the stop line surface into a line and associate the attributes. The stop line is surface data. Obtain the center line of the two long sides as the line data, and associate the converted line data with the attributes of the stop line surface data. Traverse the stop line set , for the stop line perform threshold buffering to constructa surface, and at the same time obtain the intersecting lane surfaces based on the first lane surface set and traverse and analyze the intersecting surface set. Exclude and filter the intersections of the left and right sides of the intersecting surface with the stop line surface. For the first lane surfaces that do not intersect, extend the left and right sides of the lane based on the stop line, and update the relevant attributes of the lane surface.

[0056] In this embodiment, after aligning the first lane surface set based on the stop line semantic data to obtain the second lane surface set, it further includes: swapping the left and right side relationships of each second lane surface in the second lane surface set, and constructing a virtual lane surface set; configuring the control attributes of each lane surface in the second lane surface set, where the control attributes distinguish the virtual lane surface and the real lane surface corresponding to the same lane surface identifier.

[0057] For the lane surfaces with two-way traffic, reverse the lane side vector points, swap the corresponding left and right side relationships, etc. At the same time, add virtual lane control attributes and add items to the lane surface set where the control attribute is a custom control attribute for distinguishing the virtual lane surface from the ordinary lane surface, and at the same time record the unique identifier id of the original lane surface for subsequent analysis.

[0058] In an implementation manner of this embodiment, configuring the connection relationship between the lane surfaces in the second lane surface set includes:

[0059] S11, for each target lane surface in the second lane surface set, obtain the lane boundary of the target lane surface, where the lane boundary includes the upper boundary and the lower boundary;

[0060] S12, based on the traffic direction of the target lane surface, find the adjacent lane surfaces of the lane boundary within a specified preset range to obtain an adjacent lane surface set, where the adjacent lane surface set includes: the successor lane surface adjacent to the upper boundary and the preceding lane surface adjacent to the lower boundary;

[0061] S13, screen the continuous lane surface set that meets the preset boundary relationship in the adjacent lane surface set, and configure the connection relationship between the target lane surface and the adjacent lane surface according to the continuous lane surface set.

[0062] Traverse the lane surface set (the second lane surface set), and obtain the upper, lower, left, and right sides of , , ) Intersecting successor lane surfaces within the forward exploration threshold range , Intersecting preceding lane surfaces within the backward exploration threshold range ; Obtain the list of flag id sets of the preceding and successor lane surfaces (excluding the currently analyzed lane surface), traverse the id set list respectively, and filter and obtain the items that meet the surface relationship for the preceding and successor lane surfaces through the method to obtain the items that meet the surface relationship , (successive lane surface set), and finally update the current analyzed lane surface and the preceding and successor lane surface Ids to the pres and nexts attribute fields of

[0063] In one example, filter the successive lane surface set that meets the preset boundary relationship in the adjacent lane surface set, and configure the successive relationship between the target lane surface and the adjacent lane surface according to the successive lane surface set, including: traversing the adjacent lane surface set and performing the following steps until the last adjacent lane surface: locate the first side of the target lane surface and the second side of the current adjacent lane surface, where the first side and the second side are adjacent to each other; calculate the elevation difference between the midpoint of the first side and the midpoint of the second side; determine whether the elevation difference is greater than the specified threshold; if the elevation difference is less than the specified threshold; calculate the first distance between the upper boundary of the target lane surface and the lower boundary of the current adjacent lane surface, calculate the second distance between the lower boundary of the target lane surface and the lower boundary of the current adjacent lane surface, calculate the third distance between the upper boundary of the target lane surface and the upper boundary of the current adjacent lane surface, and calculate the fourth distance between the lower boundary of the target lane surface and the upper boundary of the current adjacent lane surface; determine whether the first distance is greater than the second distance and whether the third distance is greater than the fourth distance; if the first distance is less than or equal to the second distance and the third distance is less than or equal to the fourth distance, calculate the similarity between the target lane surface and the current adjacent lane surface; if the similarity is greater than the preset threshold, construct a connection line using the midpoint of the first side and the midpoint of the second side; select the successive lane surfaces that do not intersect with the connection line in the adjacent lane surface set; after the traversal of the adjacent lane surface set is completed, configure the successive relationship between the target lane surface and the adjacent lane surface according to the successive lane surface set of the target lane surface.

[0064] In one example, this embodiment uses the method for screening, including:

[0065] Take the target lane surface as the lane surface to be analyzed , and the current adjacent lane surface as example, traverse the set of lane surfaces to be analyzed , each surface has four sides: up, down, left, and right. Respectively obtain the midpoints of the two adjacent sides of the adjacent bounding box , If the elevation difference between two points is greater than the specified threshold, skip it; Figure 3 It is a schematic diagram of the midpoint of the adjacent edges of two surfaces in the invention embodiment.

[0066] Based on the road traffic direction as the reference, combined with the relative relationship between the previous and subsequent lane surfaces, when the following conditions are not met: the distance of the previous ( ) > ( the distance ), the subsequent ( the distance) > ( the distance), then skip it;

[0067] Judge the similarity degree of the adjacent two sides (project through the endpoints and compare the proportion) < 50%, skip it; pass , Construct a connection line, and skip the other surfaces in the connection line intersection set;

[0068] Meet the above conditions and record the corresponding connection relationship.

[0069] In an implementation scenario based on the above example, configuring the connection relationship between the target lane surface and the adjacent lane surface according to the set of subsequent lane surfaces of the target lane surface includes: counting the number of subsequent lane surfaces of the target lane surface from the set of subsequent lane surfaces; if the number of subsequent lane surfaces is 0, configure the relationship between the target lane surface and the subsequent lane surface as no relationship; if the number of subsequent lane surfaces is 1, obtain the two adjacent edges of the target lane surface and the subsequent lane surface, if the length difference between the two adjacent edges is within the specified threshold range, configure the relationship between the target lane surface and the subsequent lane surface as 1:1, if the length difference between the two adjacent edges is not within the specified threshold range, configure the relationship between the target lane surface and the subsequent lane surface as M:n; if the number of subsequent lane surfaces is 2, respectively locate the first adjacent edge and the second adjacent edge of the first subsequent lane surface and the second subsequent lane surface with respect to the target lane surface, and calculate the first projection distance proportion and the second projection distance proportion of the first adjacent edge and the second adjacent edge to the target lane surface respectively; if both the first projection distance proportion and the second projection distance proportion are less than 50%, configure the relationship between the target lane surface and the subsequent lane surface as 1:1.2; if the number of subsequent lane surfaces is greater than 2, configure the relationship between the target lane surface and the subsequent lane surface as M:n.

[0070] Traverse the lane surface set, obtain the previous pres and subsequent nexts sets, and respectively analyze through the method to obtain the corresponding relationship type and update the attributes of the analysis object; where In the (border, collection, direction) method, the parameter border is the analysis object (target lane surface), collection is the set of predecessors and successors, and direction is the relative relationship (pre, next); the processing flow is as follows:

[0071] Count the number of sets in the predecessor set or successor set in collection;

[0072] When the number of collection is 0, it means there is no relationship;

[0073] When the number of collection is 1, obtain the adjacent edges of the current surface border and the collection analysis surface. If the length difference between the two edges is within the specified threshold range, it is 1:1, otherwise it is M:n; when the number of collection is 2, respectively obtain the edges adjacent to the two analysis objects in the collection for the current surface border, and judge the ratio of the projected distance lengths between the two. When the ratio of the two sides meets <50%, assign a 1:1.2 relationship;

[0074] Other values (greater than 2) are defaulted to M:n.

[0075] Figure 4 It is a mapping schematic diagram of the ratio and relationship mode of the embodiments of the present invention. E is the target lane surface, E is aligned with F, and the length difference between the two edges is within the specified threshold range, and the relationship configuration is 1:1; A or B is the target lane surface, and the relationships between A and C, and B and C are both 1:1; C is the target lane surface, and the relationships between C and A, B are 1:1.2; I or K is the target lane surface, I or K is not aligned with H, and the relationship is M:n.

[0076] The solution of this embodiment introduces lane surface data constructed by lane sidelines. The lane surface edges are combined with lane-level trajectory data for vector point optimization; the lane surface is aligned using stop line type semantic data to optimize the missing lane surface. Customize the relative relationship between lane surfaces based on the traffic direction, which is the core premise for generating the lane centerline; extract the intersection surface by clustering the stop line and crosswalk semantics in combination with the DBSCAN method, and filter and delete the lane surfaces included inside, which solves problems such as abnormal generation of virtual lane lines due to the existence of lane surfaces inside the subsequent intersection.

[0077] Figure 5 It is a schematic diagram of the construction process of a lane surface relationship according to the present invention. The following steps are included in this process schematic diagram: align the lane surface with the stop line, initially establish the lane surface relationship, identify the lane surface relationship, delete the lane surface inside the intersection, etc., and specifically include:

[0078] Step 1: Introduce semantic data of map learning objects, lane-level trajectory data, and lane surface data with optimized vector point sequences on the lane sides.

[0079] Step 2: Initialize the configuration of the lane surface, correct the left-right relationship attributes of the lane surface edges in combination with the traffic direction. Separate and record the lane surfaces that meet the conditions for two-way traffic to provide a data source for subsequent construction of virtual lane surfaces. Initialize and assign the front-back relationship attributes.

[0080] Step 3: Align the lane surface based on the stop line, extend or crop and align the eligible lane surfaces based on the stop line.

[0081] Step 4: Construct virtual lane surfaces, reverse the vector points of the lane edges for two-way traffic lane surfaces, exchange the corresponding left-right edge relationships, etc. At the same time, add new virtual lane control attributes and add items to the lane surface set. in;

[0082] Step 5: Initially construct the lane surface relationships, search for relationships within a specified threshold range for the predecessors and successors of the lane surface in combination with the traffic direction, and record and save the eligible relationships to the corresponding attributes.

[0083] Step 6: Identify lane surface relationships, combine the traffic direction, the number of results in the initial construction set of lane surface relationships, and the proportion of the width of adjacent edges to perform custom relationship analysis and determination for output (relationship patterns (no relationship; 1:1; 1:1.2; M:n)).

[0084] Step 7: Merge virtual surfaces, update and assign relationship attributes for two-way lane surfaces, and delete the two-way lane surfaces.

[0085] Step 8: Delete the lane surfaces within the intersection. Combine the semantic data of stop lines and crosswalks, perform clustering analysis by DBSCAN density to obtain the intersection surface; delete the lane surfaces within the intersection surface.

[0086] Step 9: Save the lane surface relationships, store the lane surface relationship set in the format of a physical file for easy reading and analysis by subsequent step modules.

[0087] The embodiments of the present disclosure provide a method for constructing lane surface relationships. By using semantic object data in the form of points, lines, and surfaces, high-precision map data such as lane-level trajectory lines and lane surface frames, and combining the traffic direction to establish custom relationship attributes for the surface frames, the construction of custom relationships provides a reasonable and effective basis for generating lane centerlines and constructing topological relationships to a certain extent in the case of missing semantic data and uncertain scenarios.

[0088] Through the description of the above embodiments, those skilled in the art can clearly understand that the method according to the above embodiments can be implemented by means of software plus a necessary general hardware platform. Of course, it can also be implemented by hardware, but in many cases the former is a better implementation manner. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art can be embodied in the form of a software product. The computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes several instructions for causing a terminal device (which may be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in various embodiments of the present invention.

[0089] Embodiment 2

[0090] In this embodiment, a configuration device and system for lane surface relationships are also provided. The device is used to implement the above embodiments and preferred implementation manners, and those that have been described will not be repeated. As used hereinafter, the term "module" can be a combination of software and / or hardware that can achieve a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware is also possible and contemplated.

[0091] Figure 6 is a structural block diagram of a configuration device for lane surface relationships according to an embodiment of the present invention. As Figure 6 shown, the device includes:

[0092] A reading module 60, configured to read lane initial data, direction semantic data, and stop line semantic data from map data;

[0093] A building module 62, configured to build a vector lane surface set by using the lane initial data and the direction semantic data;

[0094] A screening module 64, configured to screen out a first lane surface set of two-way traffic roads from the vector lane surface set;

[0095] An alignment module 66, configured to align the first lane surface set based on the stop line semantic data to obtain a second lane surface set;

[0096] A first configuration module 68, configured to configure the connection relationship between the lane surfaces in the second lane surface set and adjacent lane surfaces.

[0097] Optionally, the building block includes: a building unit configured to build a plurality of lane polygons by using the same-direction lane boundary lines in the initial number of lanes; a determining unit configured to determine, for each lane polygon, the traffic direction of the lane polygon according to the direction semantic data; and a configuring unit configured to update the vector point order of the lane polygon based on the traffic direction and configure the traffic direction attribute of the lane polygon to obtain a set of vector lane surfaces.

[0098] Optionally, the screening module includes: a traversing unit configured to traverse each vector lane surface in the set of vector lane surfaces and perform the following steps for each vector lane surface: determine whether the vector lane surface is a one-way traffic lane or a two-way traffic lane; if the vector lane surface is a one-way traffic lane, filter the vector lane surface in the set of vector lane surfaces, and if the vector lane surface is a two-way traffic lane, configure the front-back relationship attribute of the vector lane surface in the set of vector lane surfaces; and a processing unit configured to obtain a first lane surface set after the traversal of the set of vector lane surfaces is completed.

[0099] Optionally, the alignment module includes: a generating unit configured to generate a set of stop lines based on the stop line semantic data; a determining unit configured to traverse each stop line in the set of stop lines and each first lane surface in the first lane surface set and determine whether the left and right sides of the first lane surface intersect with the stop line; and an aligning unit configured to, if the left and right sides of the first lane surface intersect with the stop line, crop the first lane surface based on the stop line; and if the left and right sides of the first lane surface do not intersect with the stop line, extend the first lane surface until it is aligned with the stop line to obtain a second lane surface set.

[0100] Optionally, the method further includes: a swapping module configured to, after the alignment module aligns the first lane surface set based on the stop line semantic data to obtain a second lane surface set, swap the left-right side relationship of each second lane surface in the second lane surface set and build a set of virtual lane surfaces; and a second configuring module configured to configure the control attribute of each lane surface in the second lane surface set, where the control attribute differentiates the virtual lane surface and the real lane surface corresponding to the same lane surface identifier.

[0101] Optionally, the first configuration module includes: an obtaining unit, configured to obtain, for each target lane surface in the second lane surface set, the lane boundaries of the target lane surface, where the lane boundaries include an upper boundary and a lower boundary; a searching unit, configured to search for adjacent lane surfaces of the lane boundaries within a specified preset range based on the traffic direction of the target lane surface, to obtain an adjacent lane surface set, where the adjacent lane surface set includes: a successor lane surface adjacent to the upper boundary, and a preceding lane surface adjacent to the lower boundary; a configuration unit, configured to screen a set of consecutive lane surfaces that meet a preset boundary relationship from the adjacent lane surface set, and configure the consecutive relationship between the target lane surface and the adjacent lane surfaces according to the set of consecutive lane surfaces.

[0102] Optionally, the configuration unit includes: a traversing subunit, configured to perform the following steps on the adjacent lane surface set until the last adjacent lane surface: locate a first side edge of the target lane surface and a second side edge of the current adjacent lane surface, where the first side edge and the second side edge are adjacent to each other; calculate the elevation difference between the midpoint of the first side edge and the midpoint of the second side edge; determine whether the elevation difference is greater than a specified threshold; if the elevation difference is less than the specified threshold; calculate a first distance between the upper boundary of the target lane surface and the lower boundary of the current adjacent lane surface, calculate a second distance between the lower boundary of the target lane surface and the lower boundary of the current adjacent lane surface, calculate a third distance between the upper boundary of the target lane surface and the upper boundary of the current adjacent lane surface, and calculate a fourth distance between the lower boundary of the target lane surface and the upper boundary of the current adjacent lane surface; determine whether the first distance is greater than the second distance, and whether the third distance is greater than the fourth distance; if the first distance is less than or equal to the second distance, and the third distance is less than or equal to the fourth distance, calculate the similarity between the target lane surface and the current adjacent lane surface; if the similarity is greater than a preset threshold, construct a connection line using the midpoint of the first side edge and the midpoint of the second side edge; select, from the adjacent lane surface set, consecutive lane surfaces that do not intersect with the connection line; a configuration subunit, configured to, after the traversal of the adjacent lane surface set is completed, configure the consecutive relationship between the target lane surface and the adjacent lane surfaces according to the set of consecutive lane surfaces of the target lane surface.

[0103] Optionally, the configuration subunit is further configured to: count the number of consecutive lane surfaces of the target lane surface from the set of consecutive lane surfaces; if the number of consecutive lane surfaces is 0, configure the relationship between the target lane surface and the consecutive lane surface as no relationship; if the number of consecutive lane surfaces is 1, obtain two adjacent edges of the target lane surface and the consecutive lane surface, and if the length difference between the two adjacent edges is within a specified threshold range, configure the relationship between the target lane surface and the consecutive lane surface as 1:1, and if the length difference between the two adjacent edges is not within the specified threshold range, configure the relationship between the target lane surface and the consecutive lane surface as M:n; if the number of consecutive lane surfaces is 2, respectively locate the first adjacent edge and the second adjacent edge of the first consecutive lane surface and the second consecutive lane surface with respect to the target lane surface, and calculate the first projection distance ratio and the second projection distance ratio of the first adjacent edge and the second adjacent edge to the target lane surface respectively; if both the first projection distance ratio and the second projection distance ratio are less than 50%, configure the relationship between the target lane surface and the consecutive lane surface as 1:1.2; if the number of consecutive lane surfaces is greater than 2, configure the relationship between the target lane surface and the consecutive lane surface as M:n.

[0104] It should be noted that the above-mentioned modules can be implemented by software or hardware. For the latter, it can be implemented in the following ways, but not limited to: the above-mentioned modules are all located in the same processor; or, the above-mentioned modules are respectively located in different processors in any combination form.

[0105] Embodiment 3

[0106] The embodiment of the present invention further provides a storage medium, in which a computer program is stored, and the computer program is configured to execute the steps in any one of the above method embodiments when running.

[0107] Optionally, in this embodiment, the above storage medium can be configured to store a computer program for executing the following steps:

[0108] S1, read lane initial data, direction semantic data, and stop line semantic data from map data;

[0109] S2, construct a vector lane surface set by using the lane initial data and the direction semantic data;

[0110] S3, screen out a first lane surface set of two-way traffic roads from the vector lane surface set;

[0111] S4, align the first lane surface set based on the stop line semantic data to obtain a second lane surface set;

[0112] S5, configure the connection relationship between the lane surfaces in the second lane surface set and the adjacent lane surfaces.

[0113] Optionally, in this embodiment, the above storage medium may include but is not limited to: various media such as USB flash drives, read-only memories (ROM), random access memories (RAM), mobile hard disks, magnetic disks, or optical discs that can store computer programs.

[0114] An embodiment of the present invention also provides an electronic device, including a memory and a processor. A computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0115] Optionally, the above electronic device may further include a transmission device and input / output devices. Among them, the transmission device is connected to the above processor, and the input / output devices are connected to the above processor.

[0116] Optionally, in this embodiment, the above processor may be configured to execute the following steps through a computer program:

[0117] S1, read lane initial data, direction semantic data, and stop line semantic data from map data;

[0118] S2, construct a vector lane surface set using the lane initial data and the direction semantic data;

[0119] S3, screen out the first lane surface set of two-way traffic roads from the vector lane surface set;

[0120] S4, align the first lane surface set based on the stop line semantic data to obtain a second lane surface set;

[0121] S5, configure the connection relationship between the lane surfaces in the second lane surface set and the adjacent lane surfaces.

[0122] Optionally, specific examples in this embodiment may refer to the examples described in the above embodiments and optional implementation manners, and will not be elaborated herein.

[0123] The serial numbers of the above embodiments of the present application are only for description and do not represent the advantages or disadvantages of the embodiments.

[0124] In the above embodiments of the present application, the descriptions of each embodiment have their own focuses. For parts not detailed in a certain embodiment, reference may be made to the relevant descriptions of other embodiments.

[0125] In several embodiments provided by this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of units or modules can be in electrical or other forms.

[0126] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0127] In addition, in each embodiment of this application, the functional units can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units.

[0128] If the above-mentioned integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in each embodiment of this application. And the aforementioned storage medium includes: USB flash drives, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), mobile hard disks, magnetic disks, or optical discs and other various media that can store program codes.

[0129] The above is only the preferred embodiment of this application. It should be noted that for those of ordinary skill in the art, without departing from the principle of this application, several improvements and refinements can still be made, and these improvements and refinements should also be regarded as the protection scope of this application.

Claims

1. A method for configuring lane surface relationships, characterized in that, Including: Reading lane initial data, direction semantic data, and stop line semantic data from map data; Constructing a vector lane surface set by using the lane initial data and the direction semantic data; Filtering out a first lane surface set of two-way traffic roads from the vector lane surface set; Aligning the first lane surface set based on the stop line semantic data to obtain a second lane surface set; Configuring the connection relationship between the lane surfaces in the second lane surface set and adjacent lane surfaces; Wherein, configuring the connection relationship between the lane surfaces in the second lane surface set and adjacent lane surfaces includes: for each target lane surface in the second lane surface set, obtaining the lane boundary of the target lane surface, wherein the lane boundary includes an upper boundary and a lower boundary; searching for adjacent lane surfaces of the lane boundary within a specified preset range based on the traffic direction of the target lane surface to obtain an adjacent lane surface set, wherein the adjacent lane surface set includes: a successor lane surface adjacent to the upper boundary and a preceding lane surface adjacent to the lower boundary; filtering out a connection lane surface set that meets the preset boundary relationship from the adjacent lane surface set, and configuring the connection relationship between the target lane surface and the adjacent lane surface according to the connection lane surface set; wherein, filtering out a connection lane surface set that meets the preset boundary relationship from the adjacent lane surface set, and configuring the connection relationship between the target lane surface and the adjacent lane surface according to the connection lane surface set includes: traversing and executing the following steps on the adjacent lane surface set until the last adjacent lane surface: positioning the first side edge of the target lane surface and the second side edge of the current adjacent lane surface, wherein the first side edge and the second side edge are adjacent edges to each other; calculating the elevation difference between the midpoint of the first side edge and the midpoint of the second side edge; determining whether the elevation difference is greater than a specified threshold; if the elevation difference is less than the specified threshold; calculating the first distance between the upper boundary of the target lane surface and the lower boundary of the current adjacent lane surface, calculating the second distance between the lower boundary of the target lane surface and the lower boundary of the current adjacent lane surface, calculating the third distance between the upper boundary of the target lane surface and the upper boundary of the current adjacent lane surface, and calculating the fourth distance between the lower boundary of the target lane surface and the upper boundary of the current adjacent lane surface; determining whether the first distance is greater than the second distance and whether the third distance is greater than the fourth distance; if the first distance is less than or equal to the second distance and the third distance is less than or equal to the fourth distance, calculating the similarity between the target lane surface and the current adjacent lane surface; if the similarity is greater than a preset threshold, constructing a connection line by using the midpoint of the first side edge and the midpoint of the second side edge; selecting a connection lane surface that does not intersect with the connection line from the adjacent lane surface set; after the traversal of the adjacent lane surface set is completed, configuring the connection relationship between the target lane surface and the adjacent lane surface according to the connection lane surface set of the target lane surface.

2. The method according to claim 1, wherein Constructing a vector lane surface set by using the lane initial data and the direction semantic data includes: Constructing a plurality of lane polygons by using the same-direction lane side lines in the lane initial data; For each lane polygon, determine the driving direction of the lane polygon according to the direction semantic data; Based on the driving direction, update the vector point order of the lane polygon and configure the driving direction attribute of the lane polygon to obtain a set of vector lane surfaces.

3. The method according to claim 1, wherein Filtering out the first lane surface set of two-way roads from the set of vector lane surfaces includes: Traverse each vector lane surface in the set of vector lane surfaces, and perform the following steps for each vector lane surface: determine whether the vector lane surface is a one-way lane or a two-way lane; if the vector lane surface is a one-way lane, filter the vector lane surface in the set of vector lane surfaces, if the vector lane surface is a two-way lane, configure the front-back relationship attribute of the vector lane surface in the set of vector lane surfaces; After the traversal of the set of vector lane surfaces is completed, obtain the first lane surface set.

4. The method according to claim 1, wherein Aligning the first lane surface set based on the stop line semantic data to obtain a second lane surface set includes: Generating a set of stop lines based on the stop line semantic data; Traverse each stop line in the set of stop lines and each first lane surface in the first lane surface set, and determine whether the left and right sides of the first lane surface intersect with the stop line; If the left and right sides of the first lane surface intersect with the stop line, clip the first lane surface based on the stop line; if the left and right sides of the first lane surface do not intersect with the stop line, extend the first lane surface to align with the stop line to obtain the second lane surface set.

5. The method according to claim 1, wherein Configuring the connection relationship between the target lane surface and adjacent lane surfaces according to the set of successive lane surfaces of the target lane surface includes: Count the number of successive lane surfaces of the target lane surface from the set of successive lane surfaces; If the number of successive lane surfaces is 0, configure the relationship between the target lane surface and the successive lane surface as no relationship; if the number of successive lane surfaces is 1, obtain the two adjacent edges of the target lane surface and the successive lane surface, if the length difference between the two adjacent edges is within the specified threshold range, configure the relationship between the target lane surface and the successive lane surface as 1:1, if the length difference between the two adjacent edges is not within the specified threshold range, configure the relationship between the target lane surface and the successive lane surface as M:n; if the number of successive lane surfaces is 2, respectively locate the first adjacent edge and the second adjacent edge of the first successive lane surface and the second successive lane surface with respect to the target lane surface, and calculate the first projection distance ratio and the second projection distance ratio of the first adjacent edge and the second adjacent edge to the target lane surface respectively; if both the first projection distance ratio and the second projection distance ratio are less than 50%, configure the relationship between the target lane surface and the successive lane surface as 1:1.2; if the number of successive lane surfaces is greater than 2, configure the relationship between the target lane surface and the successive lane surface as M:n.

6. An apparatus for configuring lane surface relationships, characterized in that, Including: A reading module for reading lane initial data, direction semantic data, and stop line semantic data from map data; A construction module for constructing a set of vector lane surfaces using the lane initial data and the direction semantic data; A screening module, configured to screen out a first lane surface set of two-way traffic roads from the vector lane surface set; An alignment module, configured to align the first lane surface set based on the stop line semantic data to obtain a second lane surface set; A first configuration module, configured to configure the connection relationship between the lane surfaces in the second lane surface set and adjacent lane surfaces; Wherein, the first configuration module includes: an obtaining unit, configured to, for each target lane surface in the second lane surface set, obtain the lane boundary of the target lane surface, where the lane boundary includes an upper boundary and a lower boundary; a searching unit, configured to search for adjacent lane surfaces of the lane boundary within a specified preset range based on the traffic direction of the target lane surface to obtain an adjacent lane surface set, where the adjacent lane surface set includes: a successor lane surface adjacent to the upper boundary, and a preceding lane surface adjacent to the lower boundary; a configuration unit, configured to screen out a set of connection lane surfaces that meet a preset boundary relationship from the adjacent lane surface set, and configure the connection relationship between the target lane surface and adjacent lane surfaces according to the set of connection lane surfaces; wherein, the configuration unit includes: a traversing subunit, configured to perform the following steps on the adjacent lane surface set until the last adjacent lane surface: locate a first side edge of the target lane surface and a second side edge of the current adjacent lane surface, where the first side edge and the second side edge are adjacent edges to each other; calculate the elevation difference between the midpoint of the first side edge and the midpoint of the second side edge; determine whether the elevation difference is greater than a specified threshold; if the elevation difference is less than the specified threshold; calculate a first distance between the upper boundary of the target lane surface and the lower boundary of the current adjacent lane surface, calculate a second distance between the lower boundary of the target lane surface and the lower boundary of the current adjacent lane surface, calculate a third distance between the upper boundary of the target lane surface and the upper boundary of the current adjacent lane surface, and calculate a fourth distance between the lower boundary of the target lane surface and the upper boundary of the current adjacent lane surface; determine whether the first distance is greater than the second distance, and whether the third distance is greater than the fourth distance; if the first distance is less than or equal to the second distance, and the third distance is less than or equal to the fourth distance, calculate the similarity between the target lane surface and the current adjacent lane surface; if the similarity is greater than a preset threshold, construct a connection line using the midpoint of the first side edge and the midpoint of the second side edge; select connection lane surfaces that do not intersect with the connection line from the adjacent lane surface set; a configuration subunit, configured to, after the traversal of the adjacent lane surface set is completed, configure the connection relationship between the target lane surface and adjacent lane surfaces according to the set of connection lane surfaces of the target lane surface.

7. A storage medium, characterized in that, A computer program is stored in the storage medium, wherein the computer program is set to execute the method described in any one of claims 1 to 5 when running.

8. An electronic device, comprising a memory and a processor, characterized in that, A computer program is stored in the memory, and the processor is set to run the computer program to execute the method described in any one of claims 1 to 5.

Images