Map data processing method, server and storage medium

Abstract

The present application discloses a map data processing method. The processing method includes: obtaining three-dimensional road data from a first map, wherein the three-dimensional road data does not include arrow data for each lane and inductive type data for each lane; obtaining two-dimensional road data from a second map; fusing the three-dimensional road data and the two-dimensional road data to obtain a lane candidate set; determining the position data of lane arrows in the lane candidate set corresponding to the lanes based on the three-dimensional road data; and producing lane arrows based on the position data and the inductive type data of the two-dimensional road data. After obtaining the three-dimensional road data from the first map and the two-dimensional road data from the second map, the three-dimensional road data and the two-dimensional road data are fused to obtain a lane candidate set, wherein the three-dimensional road data does not include arrow data for each lane and inductive type data for each lane. By obtaining a lane arrow solution prepared by fusing the three-dimensional road data and the two-dimensional road data, the solution is easier to produce and less costly.

Description

Technical Field

[0001] The present application relates to the technical field of map data processing, and more specifically, to a map data processing method, a server, and a non-volatile computer-readable storage medium. Background Art

[0002] Currently, solutions for processing high-precision map data, such as producing lane line data by clustering point cloud data, require high-precision acquisition equipment to perceive the road environment and high-computing-power hardware to support complex perception algorithms, resulting in high production costs. Summary of the Invention

[0003] The present application provides a map data processing method, a server and a non-volatile computer-readable storage medium.

[0004] This application provides a map data processing method, including:

[0005] Acquiring three-dimensional road data of the first map, wherein the three-dimensional road data does not include arrow data of each lane and guidance type data of each lane;

[0006] obtaining two-dimensional road data of a second map;

[0007] fusing the three-dimensional road data and the two-dimensional road data to obtain a lane candidate set;

[0008] Determining, based on the three-dimensional road data, position data of a lane arrow corresponding to a lane in the lane candidate set;

[0009] The lane arrow is created based on the position data and the induction type data of the two-dimensional road data.

[0010] In this way, after obtaining 3D road data from the first map and 2D road data from the second map, the 3D and 2D road data are fused to generate a lane candidate set. Next, the position data of lane arrows corresponding to lanes in the lane candidate set is determined based on the 3D road data. Finally, lane arrows are generated based on this position data and the guidance type data from the 2D road data. The 3D road data does not include the arrow data or guidance type data for each lane. By fusing the 3D and 2D road data to generate a lane arrow solution, the solution is easier and more cost-effective to create.

[0011] Determining the position data of the lane arrow corresponding to the lane in the lane candidate set according to the three-dimensional road data includes:

[0012] performing clustering processing on the road candidate set to which the lane candidate set belongs to obtain a clustering result;

[0013] Connecting lanes in series according to the clustering result to obtain a connection path;

[0014] The position data of the lane arrow corresponding to the connection path is determined according to the three-dimensional road data.

[0015] In this way, the road candidate set to which the lane candidate set belongs is clustered to obtain a clustering result, and then the lanes are connected in series according to the clustering result to obtain a connection path. Finally, the position data of the lane arrows corresponding to the connection path is determined according to the three-dimensional road data, so that the lane arrows prepared in the end are longitudinally aligned within the single lane.

[0016] The clustering process of the road candidate set to which the lane candidate set belongs to obtain a clustering result includes:

[0017] The road candidate set to which the lane candidate set belongs is clustered according to the road-level topological relationship and a preset algorithm to obtain the clustering result.

[0018] In this way, by clustering the road candidate set to which the lane candidate set belongs according to the road-level topological relationship and the preset algorithm, the clustering result is obtained. The actual road connection relationship can be constructed without pre-setting the relevant threshold parameters, reducing the uncertainty caused by the preset relevant thresholds and thus affecting the constructed road connection relationship.

[0019] The lanes are connected in series according to the clustering results to obtain a connection path, including:

[0020] The lanes are connected in series within the clustering cluster of the clustering result according to the lane-level topological relationship to obtain the connection path.

[0021] In this way, the lanes can be connected in series within the clustering clusters of the clustering results according to the lane-level topological relationship to obtain a connection path.

[0022] Determining the position data of the lane arrow corresponding to the connection path according to the three-dimensional road data includes:

[0023] The position data of the lane arrow corresponding to the connection path is determined according to the lane center line of the three-dimensional road data and preset specifications.

[0024] In this way, the position data of the lane arrow corresponding to the connection path can be determined based on the lane centerline of the three-dimensional road data and the preset specifications.

[0025] The determining, based on the lane centerline of the three-dimensional road data and preset specifications, the position data of the lane arrow corresponding to the connection path includes:

[0026] grouping the connection paths according to road numbers of the three-dimensional road data;

[0027] Position data of the lane arrow corresponding to each of the connection paths in the group is determined according to the lane centerline of the three-dimensional road data and preset specifications.

[0028] In this way, by grouping the connecting paths according to the road numbers of the three-dimensional road data, the lane arrows between lanes can be horizontally aligned. Then, the position data of the lane arrows corresponding to each connecting path in the group can be determined according to the lane center lines and preset specifications of the three-dimensional road data. In this way, the position data of the lane arrows can be obtained, which can achieve both longitudinal alignment within the lane and equidistant horizontal alignment of multiple lanes.

[0029] The determining, based on the lane centerline of the three-dimensional road data and preset specifications, the position data of the lane arrow corresponding to each of the connection paths within the group includes:

[0030] determining the longest connection path in the group;

[0031] Determining position data corresponding to the lane arrow on the longest connecting path based on the lane centerline of the three-dimensional road data and preset specifications;

[0032] The remaining connection paths in the group are aligned with the longest connection path to determine the position data of the lane arrows corresponding to the remaining connection paths in the group according to the lane centerline of the three-dimensional road data and preset specifications.

[0033] In this way, the longest connecting path in the group is determined, and after the position data of the lane arrow corresponding to the longest connecting path is determined according to the lane centerline of the three-dimensional road data and the preset specifications, the remaining connecting paths in the group are aligned with the longest connecting path to determine the position data of the lane arrow corresponding to the remaining connecting paths in the group according to the lane centerline of the three-dimensional road data and the preset specifications, thereby achieving lane arrow alignment at the curve.

[0034] The fusing the three-dimensional road data and the two-dimensional road data to obtain a lane candidate set includes:

[0035] extracting the induction type data, lane direction data, and lane number data of the two-dimensional road data and the lane direction data and lane number data of the three-dimensional road data according to the road matching relationship between the first map and the second map;

[0036] The three-dimensional road data and the two-dimensional road data are matched according to the extracted lane direction data and lane number data to obtain a lane candidate set including the induction type data.

[0037] In this way, according to the road matching relationship between the first map and the second map, the induction type data, lane direction data and lane number data of the two-dimensional road data and the lane direction data and lane number data of the three-dimensional road data are extracted, and then the three-dimensional road data and the two-dimensional road data are matched according to the extracted lane direction data and lane number data, so that a lane candidate set including the induction type data can be obtained.

[0038] The step of producing the lane arrow according to the position data and the inductive type data of the two-dimensional road data includes:

[0039] Matching the position data with the induction type data to obtain valid data;

[0040] The lane arrow is produced according to the valid data.

[0041] In this way, after valid data is obtained by matching the position data and the induction type data, lane arrows can be made based on the valid data.

[0042] The present application also provides a server, comprising a memory and a processor, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the above-mentioned processing method is implemented.

[0043] The present application also provides a non-volatile computer-readable storage medium for a computer program, characterized in that when the computer program is executed by one or more processors, the above-mentioned processing method is implemented.

[0044] The map data processing method, server, and non-volatile computer-readable storage medium of this application obtain three-dimensional road data from a first map and two-dimensional road data from a second map, then fuse the three-dimensional and two-dimensional road data to obtain a lane candidate set. Next, the position data of lane arrows corresponding to lanes in the lane candidate set are determined based on the three-dimensional road data. Finally, lane arrows are generated based on the position data and the inductive type data from the two-dimensional road data. The three-dimensional road data does not include arrow data or inductive type data for each lane. By fusing the three-dimensional and two-dimensional road data to create a lane arrow solution, the solution is easier and less costly to create.

[0045] Additional aspects and advantages of the embodiments of the present application will be given in part in the description below, and in part will become obvious from the description below, or will be learned through practice of the embodiments of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the description of the embodiments in conjunction with the following drawings, in which:

[0047] Figure 1 It is a flowchart of the processing method of this application;

[0048] Figure 2 It is a scenario diagram of the processing method of this application;

[0049] Figure 3 It is a flowchart of the processing method of this application;

[0050] Figure 4 It is a flowchart of the processing method of this application;

[0051] Figure 5 It is a flowchart of the processing method of this application;

[0052] Figure 6 It is a flowchart of the processing method of this application;

[0053] Figure 7 It is a flowchart of the processing method of this application;

[0054] Figure 8 It is a flowchart of the processing method of this application;

[0055] Figure 9 It is a flowchart of the processing method of this application;

[0056] Figure 10 It is a flowchart of the processing method of this application;

[0057] Figure 11 This is a schematic diagram of the connection status of the non-volatile computer-readable storage medium and the processor of the present application. DETAILED DESCRIPTION

[0058] The embodiments of the present application are described in detail below. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals represent the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the embodiments of the present application, and should not be understood as limiting the embodiments of the present application.

[0059] See also Figure 1 The map data processing method of the present application comprises the following steps:

[0060] 01: Acquire three-dimensional road data of the first map, wherein the three-dimensional road data does not include arrow data of each lane and guidance type data of each lane;

[0061] 02: Obtain the two-dimensional road data of the second map;

[0062] 03: Fuse 3D road data and 2D road data to obtain lane candidate sets;

[0063] 04: Determine the position data of the lane arrow corresponding to the lane in the lane candidate set based on the 3D road data;

[0064] 05: Create lane arrows based on the induction type data of the position data and the two-dimensional road data.

[0065] The present application also provides a server comprising a memory and a processor. The memory stores a computer program, and the processor is configured to obtain three-dimensional road data of a first map, wherein the three-dimensional road data does not include arrow data for each lane and inductive type data for each lane; obtain two-dimensional road data of a second map; fuse the three-dimensional road data with the two-dimensional road data to obtain a lane candidate set; determine, based on the three-dimensional road data, position data of lane arrows corresponding to lanes in the lane candidate set; and generate lane arrows based on the position data and the inductive type data of the two-dimensional road data.

[0066] Specifically, the first map refers to a high-precision map, and the three-dimensional road data is data that can represent the road network in the high-precision map. For example, the three-dimensional road data includes data on roads, lanes within the roads, and lane centerlines within the lanes. It also includes lane-level three-dimensional spatial information, such as the grouping and topological relationships between roads, lanes, and lane centerlines. A road includes multiple lanes. However, the three-dimensional road data does not include data on arrows for each lane or the guidance type for each lane. The guidance type of a lane can inform the driver of the direction of travel in a particular lane, such as whether a certain section of a lane indicates a left turn, a right turn, or straight ahead.

[0067] The second map refers to a standard precision map, and the two-dimensional road data refers to data that can represent relevant information in the standard precision map, such as lane inductive data, but the two-dimensional road data does not have spatial information data.

[0068] See also Figure 2First, obtain the three-dimensional road data in the high-precision map and the two-dimensional road data in the standard-precision map, match the obtained two-dimensional road data with the three-dimensional road data, and then extract the induction type data, lane direction data and lane number data from the two-dimensional road data in the matched data, and extract the lane direction data and lane number data of the three-dimensional road data at the same time. Then, lane matching is performed on the three-dimensional road data and the two-dimensional road data based on the extracted lane direction data and lane number data, and the data of the three-dimensional lane set is obtained from the lane-matched data, which is also the lane candidate set. At the same time, the lane-matched data includes the induction type data from the two-dimensional road data, so the lane candidate set including the induction type data can be obtained. Next, the specific position data of the lane arrow in the lane candidate set is determined based on the lane centerline data in the lane candidate set. Finally, the lane arrow is prepared based on the induction type data and the position data. At this time, the lane arrow is in a point shape. As shown Figure 2 The lane arrow data rendering shown in the figure shows that the position of the airplane-shaped user interface element in the figure is the identification position of the lane arrow, the direction of the airplane is the direction of road traffic, and the number next to the airplane indicates the type of arrow.

[0069] In subsequent specific application scenarios, the shape of a complete lane arrow surface can be prepared based on the preset arrow attributes, and the lane arrow can be used on a high-precision map. The preset arrow attributes can be set in advance by the developer, and the values ​​corresponding to the preset arrow attributes can also be obtained from two-dimensional road data or three-dimensional road data. The preset arrow attributes include the number corresponding to each arrow data, the type of arrow, the inclination angle of the road surface where the arrow is located, the shape of the arrow data, and the direction angle of the arrow, etc. The direction angle of the arrow refers to the angle between the direction of the arrow object and the north direction. For example, the specific shape of the lane arrow is determined according to the arrow type, the direction of the lane arrow is determined according to the value of the arrow's direction angle, the pitch angle of the lane arrow is determined by the value of the inclination angle of the ground where the arrow is located, etc., thereby preparing the shape of a complete lane arrow surface.

[0070] Understandably, after acquiring three-dimensional road data from high-precision maps and two-dimensional road data from standard-precision maps at low cost, this application utilizes the fact that three-dimensional road data lacks inductive type data and two-dimensional road data lacks spatial data, and then matches and fuses the three-dimensional road data with the two-dimensional road data to obtain data that can express both inductive type and spatial information. Furthermore, the application combines relevant algorithms to deduce the reasonable position of the arrow on the lane and the type of arrow corresponding to the inductive type, thereby preparing lane arrows. Compared to lane arrows obtained through the support of vehicle hardware equipment and high-threshold perception algorithms, this application does not require all the data from high-precision maps, but only requires basic road network data, which is easier to produce and less costly.

[0071] At the same time, if only high-precision map data is used to create lane arrows, the position and type of lane arrows can only be determined by the lane-level topological relationship at the intersection. It is also necessary to obtain data other than the high-precision map data that can express the attributes of the intersection.

[0072] In this way, after obtaining 3D road data from the first map and 2D road data from the second map, the 3D and 2D road data are fused to generate a lane candidate set. Next, the position data of lane arrows corresponding to lanes in the lane candidate set is determined based on the 3D road data. Finally, lane arrows are generated based on this position data and the guidance type data from the 2D road data. The 3D road data does not include the arrow data or guidance type data for each lane. By fusing the 3D and 2D road data to generate a lane arrow solution, the solution is easier and more cost-effective to create.

[0073] See also Figure 3 , step 04 includes:

[0074] 040: Clustering the road candidate set to which the lane candidate set belongs to obtain a clustering result;

[0075] 041: Based on the clustering results, the lanes are connected in series to obtain the connection path;

[0076] 042: Determine the position data of the lane arrow corresponding to the connection path based on the three-dimensional road data.

[0077] The processor is used to cluster the road candidate set to which the lane candidate set belongs to obtain a clustering result, to connect the lanes in series according to the clustering result to obtain a connection path, and to determine the position data corresponding to the lane arrow on the connection path according to the three-dimensional road data.

[0078] Specifically, the road candidate set refers to a set of three-dimensional roads to which the three-dimensional lanes of the lane candidate set belong.

[0079] A clustering algorithm is used to cluster the 3D road collection, generating multiple connected 3D road regions. Next, within each connected 3D road region, the lanes within that region are connected in series to generate connected lanes. In other words, the connected lanes are referred to as connected paths. Finally, the corresponding position data of the lane arrows within the connected lanes is determined based on the 3D road data.

[0080] It is understandable that since the lane arrows are located on the lanes and their positions are determined by the relevant information on the lanes, after the lanes are connected in series to obtain a connected path, the lane arrows can be aligned longitudinally within a single lane.

[0081] In this way, the road candidate set to which the lane candidate set belongs is clustered to obtain the clustering result, and then the lanes are connected in series based on the clustering result to obtain the connection path. Finally, the position data of the lane arrows corresponding to the connection path is determined based on the three-dimensional road data, so that the finally prepared lane arrows are longitudinally aligned within the single lane.

[0082] See also Figure 4 , step 040 includes:

[0083] 0401: Cluster the road candidate set to which the lane candidate set belongs according to the road-level topological relationship and a preset algorithm to obtain a clustering result.

[0084] The processor is used to cluster the road candidate set to which the lane candidate set belongs according to the road-level topological relationship and a preset algorithm to obtain a clustering result.

[0085] Specifically, the road-level topological relationship can be obtained from three-dimensional data or two-dimensional data. The road-level topological relationship refers to the connection relationship between a constructed road and its preceding and following roads based on the connection information of the road.

[0086] The preset algorithm refers to a density clustering algorithm. It's understandable that typical clustering algorithms require pre-setting thresholds for correlation coefficients and categories. However, poor threshold settings can lead to over- or under-classification, affecting clustering results. This application uses a density clustering algorithm to identify connected areas of three-dimensional roads. Therefore, it's possible to construct realistic road connectivity without setting relevant threshold parameters.

[0087] The pseudo code for constructing real road connection relationships based on road-level topological relationships and density clustering algorithms can be shown as follows:

[0088]

[0089] The input includes a map mapping table TopoMap, the key is the road number (group number), the value is a list of other road numbers related to the road, and the output is in the form of a list structure, the elements of which are lists of road numbers clustered into one category.

[0090] In this way, by clustering the road candidate set to which the lane candidate set belongs according to the road-level topological relationship and the preset algorithm to obtain the clustering result, the actual road connection relationship can be constructed without pre-setting the relevant threshold parameters, reducing the uncertainty caused by the preset relevant thresholds and thus affecting the constructed road connection relationship.

[0091] See also Figure 5 , step 041 includes:

[0092] 0410: Based on the lane-level topological relationship, the lanes are connected in series within the clustering clusters of the clustering results to obtain connection paths.

[0093] The processor is used to connect the lanes in series within the clustering clusters of the clustering results according to the lane-level topological relationship to obtain a connection path.

[0094] Specifically, the lane-level topological relationship can be derived from 3D road data. The lane-level topological relationship refers to

[0095] The connection relationship between lanes and their predecessor and successor lanes is constructed based on the lane's direction of travel. Within each connected 3D road area, that is, within each clustering result, the lanes within the 3D road area are connected in series according to the lane-level topological relationship to obtain connected lanes. In other words, the connection path refers to the connected lanes.

[0096] In this way, the lanes can be connected in series within the clustering clusters of the clustering results according to the lane-level topological relationship to obtain a connection path.

[0097] See also Figure 6 , step 042 includes:

[0098] 0420: Determine the position data of the lane arrow corresponding to the connection path based on the lane centerline of the three-dimensional road data and preset specifications.

[0099] The processor is used to determine the position data of the lane arrow corresponding to the connection path according to the lane center line of the three-dimensional road data and preset specifications.

[0100] Specifically, lane centerline data is derived from 3D road data. Besides the arrow type, other arrow attribute information can be extracted from the lane centerline. This includes information such as the arrow's location, the road surface's inclination angle, the arrow's shape, and its direction. Preset specifications refer to arrow specifications set by the developer. For example, all arrow types can be 3 meters long, with 30 meters between adjacent arrows.

[0101] After the lanes are connected in series to form a connecting path, the three-dimensional point data of the lane centerline is extracted on the connecting path. Then, all types of arrows are made according to the specifications of a length of 3 meters and a spacing of 30 meters between adjacent arrows, thereby determining the specific position of the lane arrows on the lane and obtaining the data of the specific position of the lane arrows on the lane.

[0102] In this way, the position data of the lane arrow corresponding to the connection path can be determined based on the lane centerline of the three-dimensional road data and the preset specifications.

[0103] See also Figure 7 , step 0420 includes:

[0104] 04200: Group the connected paths according to the road numbers of the 3D road data;

[0105] 04201: Determine the position data of the lane arrow corresponding to each connection path within the group based on the lane centerline of the three-dimensional road data and preset specifications.

[0106] The processor is used to group the connection paths according to the road numbers of the three-dimensional road data, and to determine the position data of the lane arrow corresponding to each connection path in the group according to the lane center line of the three-dimensional road data and preset specifications.

[0107] Specifically, the road candidate set to which the lane candidate set obtained by fusing the three-dimensional road data and the two-dimensional road data belongs includes a road number, that is, the road number can be extracted from the acquired three-dimensional road data.

[0108] After connecting lanes to form connecting paths, you can group paths with the same first and last road numbers based on the first and last road numbers, thereby generating multiple groups of connecting paths. For example, there are four connecting paths: group1 lane 1 -> group2 lane 1 -> group3 lane 1, group4 lane 1 -> group5 lane 1 -> group6 lane 1, group1 lane 2 -> group2 lane 2 -> group3 lane 2, and group4 lane 2 -> group5 lane 2 -> group6 lane 2. Group1, group2, group3, group4, group5, and group6 are road numbers. The first and last road numbers for the two connecting paths in lane 1 are group1 and group1, and group4 and group6, respectively. Similarly, the first and last road numbers for the two connecting paths in lane 2 are group1 and group1, and group4 and group6, respectively. Group the connecting paths with the same first and last numbers into one group, that is, group1 lane 1 -> group2 lane 1 -> group3 lane 1 and group1 lane 2 -> group2 lane 2 -> group3 lane 2 into one group, and group4 lane 1 -> group5 lane 1 -> group6 lane 1 and group4 lane 2 -> group5 lane 2 -> group6 lane 2 into one group.

[0109] As can be understood, after the lanes are connected in series, the lane arrows on the lanes can be aligned longitudinally within a single lane. Subsequently, the resulting connected paths are grouped together according to the same first and last number, which allows for lateral alignment of the lane arrows between lanes, i.e., equidistant alignment of multiple lanes. Finally, the position data for the lane arrows corresponding to each connected path within the group is determined based on the lane centerline and preset specifications. This allows for the generation of lane arrow position data that achieves both longitudinal alignment within a single lane and equidistant alignment across multiple lanes.

[0110] In this way, by grouping the connecting paths according to the road numbers of the three-dimensional road data, the lane arrows between lanes can be horizontally aligned. Then, the position data of the lane arrows corresponding to each connecting path in the group can be determined according to the lane center lines and preset specifications of the three-dimensional road data. In this way, the position data of the lane arrows can be obtained, which can achieve both longitudinal alignment within the lane and equidistant horizontal alignment of multiple lanes.

[0111] See also Figure 8 , step 04201 includes:

[0112] 042010: Determine the longest connection path in the group;

[0113] 042011: Determine the position data of lane arrows on the longest connecting path based on the lane centerline of the 3D road data and preset specifications;

[0114] 042012: Align the remaining connection paths in the group with the longest connection path to determine the position data of the lane arrows corresponding to the remaining connection paths in the group based on the lane centerline of the three-dimensional road data and preset specifications.

[0115] The processor is used to determine the longest connecting path in the group, and to determine the position data of the lane arrow corresponding to the longest connecting path based on the lane centerline of the three-dimensional road data and preset specifications, and to align the remaining connecting paths in the group with the longest connecting path to determine the position data of the lane arrow corresponding to the remaining connecting paths in the group based on the lane centerline of the three-dimensional road data and preset specifications.

[0116] Specifically, after dividing multiple connecting paths according to the same first and last road numbers, the longest connecting path in each group can also be determined. After the position data of the lane arrow corresponding to the longest connecting path is determined based on the lane centerline of the three-dimensional road data and preset specifications, the remaining connecting paths in the group are aligned with the longest connecting path. Then, the position data of the lane arrow corresponding to the remaining connecting paths is determined based on the lane centerline of the three-dimensional road data and preset specifications. There are various ways to align the remaining connecting paths in the group with the longest connecting path, such as using auxiliary lines. For example, group1 lane 1 -> group2 lane 1 -> group3 lane 1 and group1 lane 2 -> group2 lane 2 -> group3 lane 2 are a group, where lane 1 has the longest connecting path. After the position data of the lane arrow corresponding to lane 1 is determined based on the lane centerline of the three-dimensional road data and preset specifications, auxiliary lines are used to align lanes 1 and 2. Then, the position data of the lane arrow corresponding to lane 2 is determined based on the lane centerline of the three-dimensional road data and preset specifications.

[0117] It can be understood that after the lanes are connected in series, the lane arrows on the lanes can be aligned longitudinally within the single lane. Then, the resulting connected paths with the same first and last numbers are grouped together to achieve horizontal alignment of the lane arrows between lanes. The longest connected path in the group is then determined, and after the position data of the lane arrows on the longest connected path is generated, the remaining connected paths are aligned with the longest connected path, and the position data of the lane arrows on the remaining connected paths is generated, thereby achieving lane arrow alignment on curves.

[0118] In this way, the longest connecting path in the group is determined, and after the position data of the lane arrow corresponding to the longest connecting path is determined according to the lane centerline of the three-dimensional road data and the preset specifications, the remaining connecting paths in the group are aligned with the longest connecting path to determine the position data of the lane arrow corresponding to the remaining connecting paths in the group according to the lane centerline of the three-dimensional road data and the preset specifications, thereby achieving lane arrow alignment at the curve.

[0119] See also Figure 9 , step 03 includes:

[0120] 030: extracting the induction type data, lane direction data, and lane number data of the two-dimensional road data and the lane direction data and lane number data of the three-dimensional road data according to the road matching relationship between the first map and the second map;

[0121] 031: Match the three-dimensional road data and the two-dimensional road data according to the extracted lane direction data and lane number data to obtain a lane candidate set including induction type data.

[0122] The processor is configured to extract, based on a road matching relationship between the first map and the second map, the inductive type data, lane direction data, and lane number data from the two-dimensional road data and the lane direction data and lane number data from the three-dimensional road data. Furthermore, the processor is configured to match the three-dimensional road data with the two-dimensional road data based on the extracted lane direction data and lane number data to obtain a lane candidate set including the inductive type data.

[0123] Specifically, the data required to create lane arrows includes location data, such as the arrow's position, its azimuth, the inclination angle of the road surface where the arrow is located, and the shape of the arrow data, to determine the location of the lane arrow. Furthermore, lane arrow creation also requires guidance type data, which identifies the arrow's type, such as left turn, right turn, U-turn, left turn plus U-turn, and straight ahead. Therefore, after fusing 2D and 3D road data, in addition to extracting lane information data, the guidance type data corresponding to each lane can also be extracted to determine the type of arrow in the lane.

[0124] The method for obtaining a lane candidate set containing inductive type data includes first utilizing the road matching relationship between a high-precision map and a standard-precision map, specifically the matching relationship between the two-dimensional road data and the three-dimensional road data. Then, the inductive type data, lane direction data, and lane number data are extracted from the two-dimensional road data, while the lane direction data and lane number data are simultaneously extracted from the three-dimensional road data. Secondly, lane matching is performed on the three-dimensional road data and the two-dimensional road data based on the extracted lane direction data and lane number data, ultimately obtaining a lane candidate set containing inductive type data. This method for obtaining a lane candidate set containing inductive type data can be used when a certain segment of a three-dimensional road is associated with a certain two-dimensional road, or when a certain segment of a three-dimensional road is associated with multiple two-dimensional roads.

[0125] In this way, according to the road matching relationship between the first map and the second map, the induction type data, lane direction data and lane number data of the two-dimensional road data and the lane direction data and lane number data of the three-dimensional road data are extracted, and then the three-dimensional road data and the two-dimensional road data are matched according to the extracted lane direction data and lane number data, so that a lane candidate set including the induction type data can be obtained.

[0126] See also Figure 10 , step 05 includes:

[0127] 050: Valid data is obtained by matching the position data and the induction type data;

[0128] 051: Create lane arrows based on valid data.

[0129] The processor is used to match the position data and the induction type data to obtain valid data, and to make lane arrows according to the valid data.

[0130] Specifically, the inductive type data obtained using the road matching relationship is further matched with the determined lane arrow position data to obtain valid data. For example, the inductive type data for a certain section of a lane in the lane candidate set indicates that the turn type for that section is T. The lane containing this inductive type data is matched with the lane arrow position data to obtain valid data that matches the position data with that lane section. This valid data can be used to determine that the lane arrow at that location can be assigned an arrow type corresponding to turn type T, such as a left turn. This means that the lane arrow at that location can be assigned a left turn arrow type.

[0131] In this way, after valid data is obtained by matching the position data and the induction type data, lane arrows can be made based on the valid data.

[0132] See also Figure 11 The present application further provides a non-volatile computer-readable storage medium 100 containing a computer program 101. When the computer program 101 is executed by one or more processors 200, the one or more processors 200 execute the interaction method of any of the above embodiments.

[0133] In the description of this specification, the reference terms "certain embodiments", "in an example", "exemplarily", etc. mean that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, technical users in this field may combine and combine different embodiments or examples described in this specification and features of different embodiments or examples without contradiction.

[0134] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code that includes one or more executable instructions for implementing the steps of a specific logical function or process, and the scope of the preferred embodiments of the present application includes additional implementations in which functions may be performed out of the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by technical users in the technical field to which the embodiments of the present application belong.

[0135] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations on the present application. Ordinary technical users in the field can change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A map data processing method, characterized in that: include: Acquiring three-dimensional road data of the first map, wherein the three-dimensional road data does not include arrow data of each lane and guidance type data of each lane; Acquiring two-dimensional road data of a second map; fusing the three-dimensional road data and the two-dimensional road data to obtain a lane candidate set; Determining, based on the three-dimensional road data, position data of a lane arrow corresponding to a lane in the lane candidate set, including: clustering a road candidate set to which the lane candidate set belongs to obtain a clustering result; concatenating the lanes according to the clustering result to obtain a connection path; and determining, based on the three-dimensional road data, position data of the lane arrow corresponding to the connection path; The lane arrow is created based on the position data and the induction type data of the two-dimensional road data.

2. The processing method according to claim 1, characterized in that The clustering process of the road candidate set to which the lane candidate set belongs to obtain a clustering result includes: The road candidate set to which the lane candidate set belongs is clustered according to the road-level topological relationship and a preset algorithm to obtain the clustering result.

3. The processing method according to claim 2, characterized in that The connecting path obtained by connecting the lanes in series according to the clustering result includes: The lanes are connected in series within the clustering cluster of the clustering result according to the lane-level topological relationship to obtain the connection path.

4. The processing method according to claim 2, characterized in that Determining the position data of the lane arrow corresponding to the connection path according to the three-dimensional road data includes: The position data of the lane arrow corresponding to the connection path is determined according to the lane center line of the three-dimensional road data and preset specifications.

5. The processing method according to claim 4, characterized in that: The determining, based on the lane centerline of the three-dimensional road data and preset specifications, the position data of the lane arrow corresponding to the connection path includes: grouping the connection paths according to road numbers of the three-dimensional road data; Position data of the lane arrow corresponding to each of the connection paths in the group is determined according to the lane centerline of the three-dimensional road data and preset specifications.

6. The processing method according to claim 5, characterized in that: The determining, based on the lane centerline of the three-dimensional road data and preset specifications, the position data of the lane arrow corresponding to each of the connection paths within the group includes: determining the longest connection path in the group; Determining position data corresponding to the lane arrow on the longest connecting path based on the lane centerline of the three-dimensional road data and preset specifications; The remaining connection paths in the group are aligned with the longest connection path to determine the position data of the lane arrows corresponding to the remaining connection paths in the group according to the lane centerline of the three-dimensional road data and preset specifications.

7. The processing method according to claim 1, characterized in that The fusing the three-dimensional road data and the two-dimensional road data to obtain a lane candidate set includes: extracting the induction type data, lane direction data, and lane number data of the two-dimensional road data and the lane direction data and lane number data of the three-dimensional road data according to the road matching relationship between the first map and the second map; The three-dimensional road data and the two-dimensional road data are matched according to the extracted lane direction data and lane number data to obtain a lane candidate set including the induction type data.

8. The processing method according to claim 7, characterized in that: The step of producing the lane arrow according to the position data and the inductive type data of the two-dimensional road data includes: Matching the position data with the induction type data to obtain valid data; The lane arrow is produced according to the valid data.

9. A server, characterized in that: The invention comprises a memory and a processor, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the processing method according to any one of claims 1 to 8 is implemented.

10. A non-volatile computer-readable storage medium for a computer program, characterized in that: When the computer program is executed by one or more processors, the processing method according to any one of claims 1 to 8 is implemented.

Images