A road network data processing method, device and electronic equipment

Abstract

The application discloses a road network data processing method, obtains a bounding box corresponding to road network data, the bounding box can surround the road network structure corresponding to the road network data, and the bounding box has a starting point and an ending point corresponding to the road network structure. A set of intersections is extracted from the road network data, and the set of intersections includes the center points of the intersections. The starting point is taken as a target point, a first intersection with a center point and the target point meeting a preset condition is searched from the set of intersections, and the first intersection with a line connecting the center point and the target point not intersecting any road lane line is taken as a candidate intersection. If there is a first candidate intersection with a line connecting the center point and the ending point not intersecting any road lane line in the candidate intersection, the road network structure is divided based on the starting point, the ending point and the line connecting the center points corresponding to the first candidate intersection. Through the technical scheme provided by the application, the road network structure can be automatically divided, and the division effect is improved.

Description

Technical Field

[0001] This application relates to the field of map data technology, specifically to a road network data processing method, apparatus, and electronic device. Background Technology

[0002] High-precision maps are commonly used in autonomous driving. They contain rich map elements, such as road shapes, road markings, traffic signs, and obstacle information, with very high precision, typically at the decimeter level. The creation of high-precision maps requires optimizing a large amount of road network data. To facilitate parallel multitasking, the road network data is usually segmented, allowing for separate processing of each area and improving efficiency.

[0003] Currently, road network data is mainly segmented manually, which is not only time-consuming but also has high labor costs. Summary of the Invention

[0004] In view of this, this application provides a road network data processing method, apparatus and electronic device to achieve automatic segmentation of road network data, improve segmentation efficiency and reduce costs.

[0005] To solve the above problems, the technical solution provided in this application is as follows:

[0006] In a first aspect of this application, a road network data processing method is provided, the method comprising:

[0007] Obtain road network data and the bounding box corresponding to the road network data. The bounding box is used to enclose the road network structure corresponding to the road network data. The bounding box has a starting point and an ending point that divide the road network structure.

[0008] Extract a set of intersections from the road network data, the set of intersections including the center point of each intersection;

[0009] Using the starting point as the target point, perform the following target operation:

[0010] Find the first intersection in the set of intersections whose distance between the center point and the target point meets a preset condition;

[0011] The first intersection where the line connecting the center point and the target point does not intersect with any lane line of any road segment is determined as a candidate intersection, wherein the lane line of the road segment refers to the lane line outside the intersection area;

[0012] In response to the existence of a first candidate intersection where the line connecting the center point and the end point does not intersect any lane line of any road segment, the road network structure is segmented based on the line connecting the starting point, the end point, and the center point corresponding to the first candidate intersection.

[0013] In a second aspect of this application, a road network data processing apparatus is provided, the apparatus comprising:

[0014] The acquisition unit is used to acquire road network data and the bounding box corresponding to the road network data. The bounding box is used to enclose the road network structure corresponding to the road network data. The bounding box has a starting point and an ending point that divide the road network structure.

[0015] An extraction unit is used to extract a set of intersections from the road network data, the set of intersections including the center point of each intersection;

[0016] The processing unit is configured to perform the following target operations after setting the starting point as the target point: find a first intersection in the intersection set whose distance between the center point and the target point meets a preset condition; determine a first intersection whose line connecting the center point and the target point does not intersect any lane line of a road segment as a candidate intersection, wherein the lane line of a road segment refers to the lane line outside the intersection area; in response to the existence of a first candidate intersection whose line connecting the center point and the ending point does not intersect any lane line of a road segment, segment the road network structure based on the line connecting the starting point, the ending point, and the center point corresponding to the first candidate intersection.

[0017] In a third aspect of this application, an electronic device is provided, comprising:

[0018] One or more processors;

[0019] Storage device, on which one or more programs are stored,

[0020] When the one or more programs are executed by the one or more processors, the one or more processors implement the road network data processing method as described in the first aspect.

[0021] In a fourth aspect of this application, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the road network data processing method as described in the first aspect.

[0022] In a fifth aspect of this application, a computer program product is provided that, when the computer program product is run on a computer, causes the computer to implement the road network data processing method described in the first aspect.

[0023] Therefore, this application has the following beneficial effects:

[0024] This application provides a road network data processing method. For the road network data to be processed, a bounding box corresponding to the road network data is obtained. This bounding box encloses the road network structure corresponding to the road network data, and has a starting point and an ending point corresponding to the segmentation of the road network structure. A set of intersections is extracted from the road network data, including the center point of each intersection. For the starting point, this starting point is used as the target point. A first intersection is found in the intersection set whose distance between the center point and the target point meets a preset condition. For any first intersection, if the line connecting the center point and the target point of the first intersection does not intersect any lane line of any road segment, the first intersection is considered a candidate intersection. If there is a first candidate intersection whose line connecting the center point and the ending point does not intersect any lane line of any road segment, the road network structure is segmented based on the line connecting the starting point, the ending point, and the corresponding center point of the first candidate intersection. The technical solution provided by this application can automatically segment the road network structure, improving the segmentation effect. Furthermore, by extracting intersections and segmenting them at the junctions of intersections and road segments, the integrity of the intersections and road segments of the segmented sub-road network is ensured, reducing the workload of subsequent splicing. Attached Figure Description

[0025] Figure 1 A flowchart of a road network data processing method provided in this application embodiment;

[0026] Figure 2 A schematic diagram of an intersection extraction provided in this application embodiment;

[0027] Figure 3a This is a schematic diagram of an application scenario provided by an embodiment of this application;

[0028] Figure 3b This is a schematic diagram illustrating another application scenario provided by an embodiment of this application;

[0029] Figure 4a A schematic diagram of road network structure segmentation provided in this application embodiment;

[0030] Figure 4b A schematic diagram of lane marking at an intersection provided in this application embodiment;

[0031] Figure 5 A schematic diagram of a road network data processing framework provided in an embodiment of this application;

[0032] Figure 6 This is a schematic diagram of a road network data processing device provided in an embodiment of this application. Detailed Implementation

[0033] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, the embodiments of this application will be further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0034] To facilitate understanding and explanation of the technical solutions provided in the embodiments of this application, the background technology of this application will be described first.

[0035] To improve the efficiency of high-precision map production, large-scale road network data will be segmented to enable multi-task parallel processing. Currently, segmentation is mainly done manually using bounding boxes or dividing lines. This method is not only time-consuming and costly, but it also sometimes cuts off lane lines within the same road segment, affecting lane line integrity. Because lane lines are cut off, during the subsequent high-precision map construction, to ensure that the lane lines for the same road segment in the high-precision map provided to users are complete, the cut lane lines need to be stitched together, increasing the workload of stitching.

[0036] Based on this, this application provides a road network data processing method. For the road network data to be processed, the bounding box corresponding to the road network data is obtained. Starting from the starting point of the bounding box, several intersections within a certain distance from the starting point are selected from the intersection set. Then, candidate intersections are selected from these intersections whose line connecting the center point and the starting point does not intersect any lane line of any road segment. If a specific candidate intersection exists whose line connecting the center point and the end point does not intersect any lane line of any road segment, the road network structure is segmented based on the line connecting the starting point, the end point, and the center point of this specific candidate intersection. If the specific candidate intersection does not exist, the search continues sequentially from the center point of the candidate intersection until the specific candidate intersection is found, completing the segmentation of the road network structure. The method provided in this application can automate the segmentation of large amounts of road network data, improving segmentation efficiency. Furthermore, compared to manual segmentation, the intersections and road segments of the sub-road network segmented by this scheme are relatively complete, facilitating subsequent splicing and improving the processing efficiency of road network data.

[0037] The following explains the definitions of the technical terms in this application. Unless otherwise specified, the definitions of the technical terms in this application shall prevail.

[0038] An axis-aligned bounding box (AABB) consists of a max coordinate and a min coordinate. In a 2D scene, an AABB has the following characteristics: it is represented as a quadrilateral, meaning it encloses an object; each side of the quadrilateral is perpendicular to one of the coordinate axes. In a 3D scene, an AABB has the following characteristics: it is represented as a hexahedron; each side of the hexahedron is parallel to a coordinate plane.

[0039] Road network data includes geometric information about roads and lane lines, such as road coordinates, lane line type, and direction.

[0040] An intersection is a junction of different roads, including level crossings, T-junctions, and roundabouts.

[0041] A road section is the area of ​​a road other than intersections.

[0042] Lane markings at intersections refer to lane markings within the intersection area; lane markings on road sections refer to lane markings outside the intersection area.

[0043] A road network is a network structure composed of multiple roads.

[0044] Breadth-First Search (BFS), also known as the breadth-first algorithm, employs a carpet-like, layer-by-layer search strategy: starting from the starting point, it searches sequentially from the nearest to the farthest point until the target point is found.

[0045] Greedy algorithms do not consider the overall optimal solution, but only a locally optimal solution in some sense. The sum of these locally optimal solutions constitutes the overall optimal solution, or a near-optimal solution, for the problem. A locally optimal solution refers to the best choice made under the current state.

[0046] To facilitate understanding of the technical solution of this application, the following description will be provided in conjunction with the accompanying drawings.

[0047] See Figure 1 The figure is a flowchart of a road network data processing method provided in an embodiment of this application, as shown below. Figure 1 As shown, the method includes:

[0048] S101: Obtain road network data and the bounding box corresponding to the road network data.

[0049] The bounding box is used to enclose the road network structure corresponding to the road network data. This bounding box contains start and end points that divide the road network structure. These start and end points are used to subsequently find candidate intersections that meet the criteria. The bounding box can be an AABB bounding box, a convex-concave bounding box, etc.

[0050] In this embodiment, the starting and ending points of the bounding box can be determined manually or automatically according to preset rules. The preset rules can be: the line connecting the starting and ending points divides the bounding box into two regions, and the area difference between these two regions is within a preset range. This preset range can be set according to the actual application, for example, [-0.5, 0.5]. In other words, the line connecting the starting and ending points divides the bounding box into two regions with equal or approximately equal areas. The starting point can be randomly determined, and after determining the starting point, the corresponding ending point is determined according to the above rules. Of course, the starting and ending points can also be determined manually using the above rules.

[0051] S102: Extract the intersection set based on the road network data. This intersection set includes the center point of each intersection.

[0052] In this embodiment, after acquiring road network data, intersections can be extracted from the road network data using a segmentation algorithm. Specifically, the location coordinates of the intersections are extracted, such as the boundary coordinates of the intersections, and the coordinates of the center points of the intersections are determined based on the location coordinates of the intersections. After completing the intersection extraction, the coordinates of the center points of each intersection are stored to obtain a set of intersections.

[0053] The segmentation algorithm can employ a deep learning-based segmentation algorithm based on a bird's-eye view (top view) of lane lines. This segmentation algorithm can include methods such as instance segmentation and panoramic segmentation. For example... Figure 2 The image shown is an intersection rendering extracted using a deep learning segmentation algorithm based on a bird's-eye view (top view) of the lane lines.

[0054] Instance segmentation detects and distinguishes different object instances in an image by assigning a different identifier or mask to each object. The goal of instance segmentation is to segment each object instance independently, thereby enabling the identification and tracking of each object in the image. Panoptic segmentation is a comprehensive method combining semantic segmentation and instance segmentation, assigning a semantic label and a unique instance identifier to each pixel in the image. The goal of panoptic segmentation is to simultaneously provide semantic understanding of objects and background in the image, as well as the localization and segmentation of object instances. Semantic segmentation is a technique that assigns a specific category label to each pixel in an image, classifying regions in the image into different categories, such as roads, sky, and grass. The goal of semantic segmentation is to categorize each pixel in the image into its corresponding category.

[0055] After extracting the intersection, lane lines can be distinguished. Lane lines within the intersection area are marked as intersection lane lines, and lane lines outside the intersection area are marked as road segment lane lines. It should be noted that during the marking process, if a lane line crosses an intersection or road segment—that is, if the lane line is not broken at the intersection turning point, such as a left-turn lane line including a left-turn waiting line or a straight-ahead lane line including a straight-ahead waiting line—this type of lane line needs to be broken. The broken lane line belongs to either the intersection area or the road segment area. Specifically, the breaking process can include: determining the intersection point of the lane line with the intersection boundary, and breaking the lane line at the intersection point, thus dividing it into multiple lane lines.

[0056] Using the starting point as the target point, perform the following target operation:

[0057] S103: Find the first intersection in the intersection set whose distance between the center point and the target point meets the preset conditions.

[0058] S104: The first intersection where the line connecting the center point and the target point does not intersect with any lane line of any road segment is identified as a candidate intersection.

[0059] After determining the set of intersections and the target point, starting from the target point, find the first intersection in the set whose center point is within a preset distance from the target point. The preset condition can be that the distance is less than a preset distance threshold.

[0060] After identifying the first intersection, for any given first intersection, determine whether the line connecting the center point and the starting point of the first intersection intersects with the lane lines of the road segment. If they do not intersect, then the first intersection is taken as a candidate intersection, thus obtaining a set of candidate intersections.

[0061] S105: In response to a first candidate intersection where the line connecting the center point and the end point does not intersect any lane line of any road segment, the road network structure is segmented based on the line connecting the start point, the end point, and the corresponding center point of the first candidate intersection.

[0062] In this embodiment, if there is a first candidate intersection in the candidate intersection set whose line connecting the center point and the end point does not intersect with any lane line of any road segment, the line connecting the starting point, the end point, and the center point of the first candidate intersection is used as a dividing line to divide the road network structure.

[0063] Specifically, if a first candidate intersection exists in the candidate intersection set, before segmenting the road network structure based on the line connecting the starting point, ending point, and the center point corresponding to the first candidate intersection, a target candidate intersection is selected from multiple first candidate intersections. Then, the road network structure is segmented based on the line connecting the starting point, ending point, and the center point of the target candidate intersection. When selecting the target candidate intersection, a first candidate intersection can be randomly selected, or a target candidate intersection can be determined from multiple first candidate intersections according to a preset search strategy.

[0064] The preset search strategy can be to search for the candidate intersection closest to the end point from multiple first candidate intersections, or to search for the candidate intersection with the highest score of the first line connecting the center point and the target point from multiple first candidate intersections.

[0065] Specifically, if the search strategy is to search for the candidate intersection closest to the termination point from multiple first candidate intersections, then the distance from each first candidate intersection to the termination point is calculated, and the first candidate intersection with the shortest distance is taken as the target candidate intersection.

[0066] If the search strategy is to search for the candidate intersection with the highest score of the first line connecting the center point to the target point from multiple first candidate intersections, then the target candidate intersection is determined from multiple first candidate intersections according to the preset search strategy, including: obtaining the score of the first line connecting the center point and the target point of each first candidate intersection; and taking the first candidate intersection corresponding to the first line with the highest score as the target candidate intersection.

[0067] The score for the first connection line is related to the length of the first connection line and / or the angle between the first connection line, the line connecting the target point, and the endpoint. Specifically, the score for the first connection line between the center point of each first candidate intersection and the target point is obtained, including:

[0068] One implementation is to obtain the first length of the first connection and determine the score of the first connection based on the first length of the first connection. The score of the first connection is positively correlated with the length of the first connection.

[0069] In this embodiment, the longer the connection, the higher the score. The reason for choosing the first candidate intersection corresponding to a longer connection is that a longer connection is closer to the connection between the target point and the endpoint, thus reducing the need for segmentation operations. For example, Figure 3a As shown, the bounding box includes a starting point S and an ending point P. After passing through S104, two first candidate intersections are determined, with center points A and B respectively. If the length of SA is greater than the length of SB, then SA scores higher than SB.

[0070] Another approach is to obtain the angle between the first connecting line and the line connecting the target point and the end point, and determine the score of the first connecting line based on the angle. The score of the first connecting line is negatively correlated with the angle.

[0071] In this embodiment, the smaller the angle, the higher the score. The reason for choosing the first candidate intersection corresponding to the connection with the smallest angle is that the smaller the angle, the closer the connection is to the line between the start and end points, thus reducing the need for segmentation operations. For example, Figure 3a As shown, if angle ASP is less than angle BSP, then SA's score is higher than SB's.

[0072] Another implementation involves obtaining the length of the first connecting line and the angle between the first connecting line and the line connecting the target point and the end point. A weighted sum is then calculated based on the length of the first connecting line and the angle. The score of the first connecting line is determined based on the sum, which is positively correlated with the sum. A larger sum results in a higher score. The angle has a negative weight.

[0073] For example, Figure 3a As shown, weights α and β are assigned to length and angle, respectively, where α + β = 1. Therefore, the weighted sum of the SA line is a1 = α * SA + β * angle ASP, and the weighted sum of the SB line is a2 = α * SB + β * angle BSP. If a1 is greater than a2, then the score of SA is higher than that of SB.

[0074] Another implementation method is to obtain the first length of the first connecting line and the second length of the second connecting line between the center point and the end point of the first candidate intersection; and determine the score of the first connecting line based on the first length and the second length.

[0075] In this embodiment, length is positively correlated with score; that is, the longer the line, the higher the score. The reason for choosing the first candidate intersection corresponding to a longer connection is that a longer connection is closer to the line between the target point and the endpoint, thus reducing the need for segmentation operations. For example, Figure 3a As shown, the score of the candidate intersection corresponding to center point A is determined based on the length of AS+AP, and the score of the candidate intersection corresponding to center point B is determined based on the length of BS+BP. If the length of AS+AP is greater than that of BS+BP, then AS+AP has a higher score.

[0076] Another approach is to obtain the first included angle between the first connecting line, the target point, and the third connecting line, as well as the second included angle between the second and third connecting lines; and to determine the score of the first connecting line based on the first and second included angles.

[0077] In this embodiment, the smaller the angle, the higher the score. The reason for choosing the first candidate intersection corresponding to the connection with the smaller angle is that the smaller the angle, the closer the connection is to the connection between the target point and the end point, thereby reducing the number of segmentation operations.

[0078] For example, Figure 3a As shown, the score of the candidate intersection corresponding to center point A is determined based on angle ASP+APS, and the score of the candidate intersection corresponding to center point B is determined based on angle BSP+BPS. If angle ASP+APS is less than angle BSP+BPS, then angle ASP+APS has a higher score.

[0079] Another implementation involves obtaining the sum of the lengths of the first and second lengths, as well as the sum of the angles of the first and second included angles; then, a weighted sum of the length sum and the angle sum is performed, and the score of the first connection is determined based on the weighted result. The weighted result is positively correlated with the score; that is, the larger the weighted result, the higher the score.

[0080] For example, Figure 3a As shown, weights α and β are assigned to length and angle, respectively. The score for line SA is b1 = α*(AS+AP) + β*angle(ASP+APS), and the score for line SB is b2 = α*(BS+BP) + β*angle(BSP+BPS). If b1 is greater than b2, then the score for SA is higher than that for SB.

[0081] As can be seen, the technical solution provided in this application can automatically segment the road network structure, improving the segmentation effect. Moreover, by extracting intersections and segmenting at the junctions of intersections and road segments, the integrity of intersections and road segments in the segmented sub-road network is ensured. When merging the sub-road networks, there is no need to consider splicing data between road segments and intersections, reducing the workload of subsequent splicing and improving the processing efficiency of road network data.

[0082] If the first candidate intersection is not found among all the candidate intersections selected by S104, the center point of the candidate intersection is taken as the target point, and the operations of S103-S104 are continued until the first candidate intersection is found. After the first candidate intersection is found, the road network structure is segmented based on the lines connecting the starting point, ending point, target point, and the corresponding center point of the first candidate intersection.

[0083] When there is only one candidate intersection, its center point is used as the target point. When there are multiple candidate intersections, one can be randomly selected and its center point used as the target point, or a second candidate intersection can be selected from among the multiple candidate intersections according to a preset search strategy and its center point used as the target point. The preset search strategy is used to indicate the candidate intersection with the highest score of the fourth line connecting its center point and the target point (the target point determined in the previous loop), or to indicate the candidate intersection closest to the termination point.

[0084] It should be noted that, regarding how to select a second candidate intersection from multiple candidate intersections according to a preset search strategy, please refer to the above description of selecting a target candidate intersection from multiple first candidate intersections according to a preset search strategy, which will not be repeated here in this embodiment.

[0085] Specifically, when selecting the second candidate intersection based on the score of the fourth connecting line, the score of the fourth connecting line between the center point and the target point of each candidate intersection is obtained; the candidate intersection corresponding to the fourth connecting line with the highest score is selected as the second candidate intersection. The score of the fourth connecting line is related to the length of the fourth connecting line and / or the angle between the fourth connecting line, the line connecting the target point and the endpoint. The score of the fourth connecting line is obtained by:

[0086] Obtain the third length of the fourth connection, and determine the score of the fourth connection based on the third length. The score of the fourth connection is positively correlated with the third length. Alternatively,

[0087] Obtain the angle between the fourth connecting line and the line connecting the target point and the end point. Determine the score of the fourth connecting line based on the angle; the score of the fourth connecting line is negatively correlated with the angle. Alternatively,

[0088] Obtain the third length of the fourth connecting line and the angle between the fourth connecting line and the line connecting the target point and the end point. Perform a weighted sum based on the third length and the angle, and determine the score of the fourth connecting line based on the sum. The score of the fourth connecting line is positively correlated with the sum. Alternatively...

[0089] Obtain the third length of the fourth connecting line and the fourth length of the fifth connecting line between the center point and the end point of the candidate intersection; determine the score of the fourth connecting line based on the third and fourth lengths. Alternatively,

[0090] Obtain the third included angle between the fourth connecting line, the sixth connecting line between the target point and the end point, and the fourth included angle between the fifth and sixth connecting lines; determine the score for the fourth connecting line based on the third and fourth included angles. Alternatively,

[0091] Obtain the sum of the lengths of the third and fourth lengths and the sum of the angles of the third and fourth included angles; perform a weighted summation of the sum of lengths and the sum of included angles, and determine the score of the first connection based on the weighted result.

[0092] Furthermore, if no candidate intersection is identified through S104, a second intersection is selected from the intersection set, and the center point of the second intersection is taken as the target point. For this target point, the operations of S103-S105 are repeated until the first candidate intersection is found. Here, the second intersection refers to the intersection in the intersection set whose center point has not been selected as the target point.

[0093] It should be noted that when calculating the score of the line connecting the center point of the candidate intersection and the target point in each iteration, the target point changes, and the score of the line is calculated based on the target point determined in the previous iteration.

[0094] For example, Figure 3b As shown, during the first search, candidate intersection center point A is found. However, the line connecting center point A and end point P intersects the road segment lane lines. Therefore, center point A is taken as the target point, and operations S103-S105 are executed again to find candidate intersection center point C. When calculating the score of the connection, if length is used, the length of CA is considered; if angle is used, angles CAP and CPA are considered, regardless of the starting point S. When it is determined that the line connecting center point C and end point P does not intersect the road segment lane lines, the line connecting the starting point S, the center points A and C of the multiple candidate intersections, and the end point P is taken as a tangent line, and this division is used to divide the road network structure. When it is determined that the line connecting center point C and end point P intersects the road segment lane lines, center point C is taken as the target point again, and operations S103-S105 are executed again.

[0095] After multiple searches, a first candidate intersection is found. The road network structure is then segmented using lines connecting the starting point, multiple target points along the route, the center point of the first candidate intersection, and the ending point. For example, Figure 4a As shown, the line connecting the starting point, the target point A along the route, the center point C of the first candidate intersection, and the ending point is used as the dividing line to divide the road network structure.

[0096] In this embodiment, when dividing the road network structure using dividing lines, a first sub-road network and a second sub-road network are obtained. To avoid the problem of large subsequent splicing workload caused by the lane lines corresponding to intersections passed by the dividing lines (such as first candidate intersections, target candidate intersections, or candidate intersections where the center point is used as the target point) being divided into two different sub-road networks, the intersection faces corresponding to the intersections passed by the dividing lines are assigned to the same sub-road network. Here, an intersection face refers to the polygonal face that constitutes an intersection, which may include intersection lane lines and intersection areas.

[0097] For example, Figure 4b As shown, the lines connecting the starting point, center point A, center point C, and the ending point divide the road network structure into two sub-road networks (gray sub-network and white sub-road network). Since the above lines cross intersection a corresponding to center point A and intersection c corresponding to center point C, the intersection faces of intersection a and intersection c are both included in the gray sub-road network structure.

[0098] For ease of understanding, please refer to the detailed processing procedure of this application. Figure 5 The framework diagram shown

[0099] S501: Extract the intersection set based on the road network data, and use the starting point on the bounding box as the target point.

[0100] For a detailed description of the implementation of S501, please refer to the relevant description of S102 above. This embodiment will not repeat it here.

[0101] S502: Starting from the target point, find the first intersection in the intersection set whose distance from the center point to the target point meets the preset conditions.

[0102] S503: The first intersection where the line connecting the center point and the target point does not intersect with any lane line of any road segment is identified as a candidate intersection, thereby obtaining a set of candidate intersections.

[0103] S504, determine whether the candidate intersection set is empty. If the candidate intersection set is empty, proceed to step S510. If the candidate intersection set is not empty, proceed to step S505.

[0104] S505: Determine whether there exists a first candidate intersection in the candidate intersection set whose line connecting the center point and the end point does not intersect with any lane line of any road segment. If it exists, proceed to step S506; if it does not exist, proceed to S508.

[0105] S506: If there are multiple first candidate intersections, search for a target candidate intersection from among the multiple first candidate intersections according to the preset search strategy;

[0106] S507: Use the line connecting the starting point, the center point of the target candidate intersection, and the ending point as the dividing line to divide the road network structure.

[0107] S508: According to the preset search strategy, select a second candidate intersection from the candidate intersection set, take the center point of the second candidate intersection as the target point, and execute S502.

[0108] S509: Select a second intersection from the intersection set, use the center point of the second intersection as the target point, and execute step S502.

[0109] Specifically, regarding how to determine the target candidate intersection from multiple first candidate intersections according to the search strategy, and how to select the second candidate intersection from the candidate intersection set according to the search strategy, please refer to [the relevant documentation / reference]. Figure 1 The relevant descriptions of the methods shown will not be repeated here in this embodiment.

[0110] Based on the above method, this application also provides a road network data processing device, which will be described below with reference to the accompanying drawings.

[0111] See Figure 6 This figure is a structural diagram of a road network data processing device provided in an embodiment of this application, as shown below. Figure 6 As shown, the processing device 600 is capable of achieving the above-mentioned... Figure 1 The method includes: an acquisition unit 601, an extraction unit 602, and a processing unit 603.

[0112] The acquisition unit 601 is used to acquire road network data and the bounding box corresponding to the road network data. The bounding box is used to enclose the road network structure corresponding to the road network data. The bounding box has a starting point and an ending point that divide the road network structure.

[0113] Extraction unit 602 is used to extract a set of intersections from the road network data, the set of intersections including the center point of each intersection;

[0114] Processing unit 603 is configured to perform the following target operations after setting the starting point as the target point: find a first intersection in the intersection set whose distance between the center point and the target point meets a preset condition; determine a first intersection whose line connecting the center point and the target point does not intersect any lane line of a road segment as a candidate intersection, wherein the lane line of a road segment refers to the lane line outside the intersection area; in response to the existence of a first candidate intersection whose line connecting the center point and the ending point does not intersect any lane line of a road segment, segment the road network structure based on the line connecting the starting point, the ending point, and the center point corresponding to the first candidate intersection.

[0115] In some implementations, if there are multiple first candidate intersections, the processing unit 603 is specifically used to determine a target candidate intersection from the multiple first candidate intersections according to a preset search strategy. The preset search strategy is used to indicate that the candidate intersection with the highest score of the first line connecting the center point and the target point is searched from the multiple first candidate intersections, or to indicate that the candidate intersection closest to the end point is searched from the multiple first candidate intersections. The road network structure is segmented based on the line connecting the starting point, the end point, and the center point corresponding to the target candidate intersection.

[0116] In some implementations, if the preset search strategy searches for the candidate intersection closest to the termination point from the plurality of first candidate intersections, the processing unit 603 is specifically used to obtain the distance from the center point of each first candidate intersection to the termination point; and to take the first candidate intersection with the shortest distance as the target candidate intersection.

[0117] In some implementations, if the preset search strategy is used to indicate searching for the candidate intersection with the highest score of the first connection between the center point and the target point from the plurality of first candidate intersections, the processing unit 603 is specifically used to obtain the score of the first connection between the center point and the target point of each first candidate intersection, wherein the score of the first connection is related to the length of the first connection and / or the angle between the first connection, the line connecting the target point and the termination point; and the first candidate intersection corresponding to the first connection with the highest score is taken as the target candidate intersection.

[0118] In some embodiments, the processing unit 603 is specifically configured to: obtain a first length of the first connecting line; determine a score for the first connecting line based on the first length, wherein the score of the first connecting line is positively correlated with the first length; or, obtain the angle between the first connecting line and the line connecting the target point and the termination point; determine a score for the first connecting line based on the angle, wherein the score of the first connecting line is negatively correlated with the angle; or, obtain a first length of the first connecting line and the angle between the first connecting line and the line connecting the target point and the termination point; perform a weighted summation based on the first length and the angle; determine a score for the first connecting line based on the summation result, wherein the score of the first connecting line is positively correlated with the summation result.

[0119] In some embodiments, the processing unit 603 is specifically configured to: obtain a first length of the first connecting line and a second length of the second connecting line between the center point of the first candidate intersection and the termination point; determine a score for the first connecting line based on the first length and the second length; or, obtain a first included angle between the first connecting line, the third connecting line between the target point and the termination point, and a second included angle between the second connecting line and the third connecting line; determine a score for the first connecting line based on the first included angle and the second included angle; or, obtain the sum of the first length and the second length and the sum of the included angles; perform a weighted summation of the sum of the lengths and the sum of the included angles, and determine a score for the first connecting line based on the weighted result.

[0120] In some embodiments, the processing unit 603 is further configured to, in response to the absence of a first candidate intersection among the candidate intersections, take the center point of the candidate intersection as the target point and continue to perform the target operation until the first candidate intersection appears; and to segment the road network structure based on the line connecting the starting point, the ending point, the target point and the corresponding center point of the first candidate intersection.

[0121] In some implementations, the processing unit 603 is specifically used to determine a second candidate intersection from the candidate intersections according to a preset search strategy. The preset search strategy is used to instruct to search for the candidate intersection with the highest score of the fourth line connecting the center point and the target point from the candidate intersections, or to instruct to search for the candidate intersection closest to the termination point from the candidate intersections; and to take the center point of the second candidate intersection as the target point.

[0122] In some embodiments, the processing unit 603 is further configured to select a second intersection from the intersection set, use the center point of the second intersection as the target point, and perform the target operation on the target point. The second intersection refers to an intersection in the intersection set whose center point has not been selected as a target point.

[0123] In some embodiments, the processing unit 603 is further configured to divide the intersection surfaces corresponding to the intersections traversed by the connecting line into the same sub-road network, wherein the connecting line refers to the connecting line that divides the road network structure into different sub-road networks.

[0124] It should be noted that the specific implementation of each unit in this embodiment can be found in the relevant descriptions in the above method embodiments. The division of units in this application embodiment is illustrative and only represents a logical functional division; in actual implementation, there may be other division methods. The functional units in this application embodiment can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. For example, in the above embodiments, the processing unit and the sending unit can be the same unit or different units. The integrated unit can be implemented in hardware or as a software functional unit.

[0125] Based on the road network data processing method provided in the above-described method embodiments, this application also provides an electronic device, including: one or more processors; and a storage device storing one or more programs thereon, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the road network data processing method described in any of the above embodiments.

[0126] The electronic device provided in this application embodiment and the road network data processing method provided in the above embodiments belong to the same inventive concept. Technical details not described in detail in this embodiment can be found in the above embodiments, and this embodiment has the same beneficial effects as the above embodiments.

[0127] Based on the message processing method provided in the above embodiments, this application provides a computer-readable medium storing a computer program thereon, wherein the program, when executed by a processor, implements the road network output processing method as described in any of the above embodiments.

[0128] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.

[0129] The aforementioned computer-readable medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to perform the aforementioned road network data processing method.

[0130] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0131] The units described in the embodiments of this application can be implemented in software or hardware. The names of the units / modules do not necessarily limit the specific unit itself.

[0132] In the context of this application, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. Machine-readable media can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0133] It should be noted that the various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the systems or apparatus disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the descriptions are relatively simple, and relevant parts can be referred to the method section.

[0134] It should be understood that in this application, "at least one (item)" means one or more, and "more than" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0135] It should also be noted that, in this document, relational terms such as "first" and "second" are used only 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 one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0136] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented directly by hardware, a software module executed by a processor, or a combination of both. The software module can be located in random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.

[0137] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A road network data processing method, characterized in that, The method includes: Obtain road network data and the bounding box corresponding to the road network data. The bounding box is used to enclose the road network structure corresponding to the road network data. The bounding box has a starting point and an ending point that divide the road network structure. Extract the intersection set from the road network data, the intersection set including the center point of each intersection; Using the starting point as the target point, perform the following target operation: Find the first intersection in the set of intersections whose distance from the center point to the target point meets a preset condition, where the preset condition means that the distance is less than a preset distance threshold; The first intersection where the line connecting the center point and the target point does not intersect with any lane line of a road segment is determined as a candidate intersection, wherein the lane line of the road segment refers to the lane line outside the intersection area; In response to the existence of a first candidate intersection where the line connecting the center point and the end point does not intersect any lane line of any road segment, the road network structure is segmented based on the line connecting the starting point, the end point, and the center point corresponding to the first candidate intersection.

2. The method according to claim 1, characterized in that, If multiple first candidate intersections exist, the segmentation of the road network structure based on the lines connecting the starting point, the ending point, and the center point corresponding to the first candidate intersection includes: According to a preset search strategy, a target candidate intersection is determined from the plurality of first candidate intersections. The preset search strategy is used to indicate that the candidate intersection with the highest score of the first line connecting the center point and the target point is searched from the plurality of first candidate intersections, or to indicate that the candidate intersection closest to the termination point is searched from the plurality of first candidate intersections. The road network structure is segmented based on the lines connecting the starting point, the ending point, and the center point corresponding to the target candidate intersection.

3. The method according to claim 2, characterized in that, If the preset search strategy searches for the candidate intersection closest to the termination point from the plurality of first candidate intersections, the step of determining the target candidate intersection from the plurality of first candidate intersections according to the preset search strategy includes: Obtain the distance from the center point of each first candidate intersection to the termination point; The first candidate intersection with the shortest distance is selected as the target candidate intersection.

4. The method according to claim 2, characterized in that, If the preset search strategy is used to indicate that the candidate intersection with the highest score of the first line connecting the center point and the target point is searched from the plurality of first candidate intersections, the step of determining the target candidate intersection from the plurality of first candidate intersections according to the preset search strategy includes: Obtain a score for the first line connecting the center point of each first candidate intersection to the target point. The score of the first line is related to the length of the first line and / or the angle between the first line, the line connecting the target point and the termination point. The first candidate intersection corresponding to the first connection with the highest score is selected as the target candidate intersection.

5. The method according to claim 4, characterized in that, The step of obtaining the score for the first line connecting the center point of each first candidate intersection to the target point includes: Obtain the first length of the first connecting line, determine the score of the first connecting line based on the first length, and the score of the first connecting line is positively correlated with the first length; or... Obtain the angle between the first connecting line and the line connecting the target point and the termination point; determine the score of the first connecting line based on the angle; the score of the first connecting line is negatively correlated with the angle; or... Obtain the first length of the first connecting line and the angle between the first connecting line and the line connecting the target point and the termination point. Perform a weighted summation based on the first length and the angle. Determine the score of the first connecting line based on the summation result. The score of the first connecting line is positively correlated with the summation result.

6. The method according to claim 4, characterized in that, The scoring of obtaining the first line connecting the center point of each first candidate intersection to the target point includes: Obtain the first length of the first connecting line and the second length of the second connecting line between the center point of the first candidate intersection and the termination point; determine the score of the first connecting line based on the first length and the second length; or... Obtain the first included angle between the first connecting line, the third connecting line between the target point and the termination point, and the second included angle between the second connecting line and the third connecting line; determine the score of the first connecting line based on the first included angle and the second included angle; or... Obtain the sum of the lengths of the first length and the second length, and the sum of the angles of the first angle and the second angle; perform a weighted summation of the sum of the lengths and the sum of the angles, and determine the score of the first connection based on the weighted result.

7. The method according to claim 1, characterized in that, The method further includes: In response to the absence of a first candidate intersection among the candidate intersections, the center point of the candidate intersection is taken as the target point, and the target operation is continued until the first candidate intersection appears; The road network structure is segmented based on the lines connecting the starting point, the ending point, the target point, and the center point corresponding to the first candidate intersection.

8. The method according to claim 7, characterized in that, The step of using the center point of the candidate intersection as the target point includes: A second candidate intersection is determined from the candidate intersections according to a preset search strategy. The preset search strategy is used to indicate that the candidate intersection with the highest score of the fourth line connecting the center point and the target point is searched from the candidate intersections, or to indicate that the candidate intersection closest to the termination point is searched from the candidate intersections. The center point of the second candidate intersection is taken as the target point.

9. The method according to any one of claims 1-8, characterized in that, The method further includes: The intersections through which the connecting lines pass are divided into the same sub-road network. The connecting lines refer to the lines that divide the road network structure into different sub-road networks.

10. A road network data processing device, characterized in that, The device includes: The acquisition unit is used to acquire road network data and the bounding box corresponding to the road network data. The bounding box is used to enclose the road network structure corresponding to the road network data. The bounding box has a starting point and an ending point that divide the road network structure. An extraction unit is used to extract a set of intersections from the road network data, the set of intersections including the center point of each intersection; The processing unit is configured to perform the following target operations after setting the starting point as the target point: finding a first intersection in the intersection set whose distance between the center point and the target point meets a preset condition, wherein the preset condition is that the distance is less than a preset distance threshold; determining a first intersection whose line connecting the center point and the target point does not intersect any lane line of a road segment as a candidate intersection, wherein the lane line of a road segment refers to the lane line outside the intersection area; and, in response to the existence of a first candidate intersection whose line connecting the center point and the end point does not intersect any lane line of a road segment, segmenting the road network structure based on the line connecting the starting point, the end point, and the center point corresponding to the first candidate intersection.

11. An electronic device, characterized in that, include: One or more processors; Storage device, on which one or more programs are stored, When the one or more programs are executed by the one or more processors, the one or more processors implement the road network data processing method as described in any one of claims 1-9.

12. A computer-readable storage medium, characterized in that, It stores a computer program, which, when executed by a processor, implements the road network data processing method as described in any one of claims 1-9.

Images