Virtual lane construction method, device, equipment and computer-readable storage medium

Abstract

The present application discloses a method, apparatus, device and computer-readable storage medium for constructing a virtual lane; specifically, multiple center line segments of each lane can be calculated based on lane information collected by a target vehicle, and after the multiple center line segments are stored in a multidimensional data space, a first center line segment and a second center line segment adjacent to each center line segment are selected therefrom, and the center line segment is respectively connected to the first center line segment and the second center line segment to form a virtual center line of the lane, and a virtual lane is constructed based on each virtual center line; thus, the present solution can first calculate multiple center line segments corresponding to each lane based on the lane information, and query the first center line segment and the second center line segment adjacent to each center line segment, thereby constructing a virtual center line and a virtual lane; in this way, a virtual lane for guiding vehicle driving can be accurately constructed without relying on a high-precision map, thereby ensuring the safety of vehicle automatic driving and improving the driving experience of the user.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a virtual lane construction method, device, equipment and computer-readable storage medium. Background Art

[0002] With the continuous development of autonomous driving technology, virtual lane construction plays an important role in the field of autonomous driving, and how to effectively identify lanes has become one of the core technical problems that autonomous driving technology needs to solve. Related technologies can obtain the lanes on the road where the vehicle is driving by using the electronic map provided by the in-vehicle navigation software.

[0003] However, although the relevant technology can obtain lane information on the driving road through electronic maps, since electronic maps are too dependent on signal reception, in some driving scenarios where signal reception is unstable, the electronic navigation map cannot accurately construct the lanes within the driving scenario, which is not conducive to the development of autonomous driving technology, affects the safety of vehicle autonomous driving, and reduces the user's driving experience. Summary of the invention

[0004] The embodiments of the present application provide a virtual lane construction method, device, equipment and computer-readable storage medium, which can accurately establish a virtual driving lane based on lane information in the driving road, ensure the safety of vehicle autonomous driving, and thus improve the user's driving experience.

[0005] The present application provides a virtual lane construction method, including:

[0006] Collect lane information within a preset range of the target vehicle;

[0007] Calculating a plurality of center line segments of each lane according to the lane information, and storing the plurality of center line segments in a multi-dimensional data space;

[0008] Selecting a first center line segment and a second center line segment adjacent to each center line segment from the multidimensional data space;

[0009] Connecting the center line segment with the first center line segment and the second center line segment respectively to obtain a virtual center line of each lane;

[0010] A corresponding virtual lane is constructed according to each virtual center line.

[0011] Accordingly, an embodiment of the present application provides a virtual lane construction device, including:

[0012] A calculation unit, used for calculating a plurality of center line segments of each lane according to the lane information, and storing the plurality of center line segments in a multi-dimensional data space;

[0013] A selection unit, used for selecting a front center line segment and a rear center line segment adjacent to each center line segment from the multi-dimensional data space;

[0014] A connection unit, used for connecting the center line segment with the front center line segment and the rear center line segment respectively to obtain a virtual center line of each lane;

[0015] The construction unit is used to construct a corresponding virtual lane according to each virtual center line.

[0016] In some embodiments, the computing unit is further configured to:

[0017] Determining, based on the lane information, a first lane line segment and a second lane line segment constituting a lane;

[0018] Calculating a lane midpoint between the first lane segment and the second lane segment;

[0019] A center line is constructed according to the midpoint of the lane to obtain a plurality of center line segments of each lane.

[0020] In some embodiments, the selection unit is further configured to:

[0021] Querying a plurality of candidate center line segments corresponding to each center line segment within a preset distance range from the multidimensional data space;

[0022] Determine a position distribution relationship between each center line segment and the plurality of candidate center line segments;

[0023] A first center line segment and a second center line segment adjacent to each center line segment are selected according to the position distribution relationship.

[0024] In some embodiments, the selection unit is further configured to:

[0025] Get the first coordinate and the second coordinate of each end of each center line segment respectively;

[0026] The center line segments within a preset distance range between the first coordinate and the second coordinate are respectively searched from the multi-dimensional data space to obtain a plurality of candidate center line segments corresponding to each center line segment.

[0027] In some embodiments, the selection unit is further configured to:

[0028] According to the position distribution relationship, obtaining the angle value and position relationship between the center line segment and each candidate center line segment;

[0029] According to the angle value and the position relationship, a first center line segment and a second center line segment adjacent to each center line segment are selected from the plurality of candidate center line segments.

[0030] In some embodiments, the selection unit is further configured to:

[0031] Determining a planar geometric relationship between the center line segment and each candidate center line segment according to the angle value;

[0032] Determine the candidate center line segments whose plane geometric relationship is parallel as target candidate center line segments;

[0033] Based on the positional relationship, a first center line segment and a second center line segment adjacent to each center line segment are selected from the plurality of target candidate center line segments.

[0034] In some embodiments, the virtual lane construction device further includes a determining unit, configured to:

[0035] Acquire a lane direction mark from the lane information, where the lane direction mark is used to indicate the direction of traffic in the lane;

[0036] Determining, according to the traffic driving direction, a sorting relationship between each center line segment and the adjacent first center line segment and the second center line segment;

[0037] The connection unit includes:

[0038] According to the sorting relationship, the center line segment is connected with the adjacent first center line segment and the adjacent second center line segment in sequence to obtain a virtual center line of each lane.

[0039] In addition, an embodiment of the present application also provides a computer device, including a processor and a memory, the memory stores a computer program, and the processor is used to run the computer program in the memory to implement the steps in the virtual lane construction method provided in the embodiment of the present application.

[0040] In addition, an embodiment of the present application also provides a computer-readable storage medium, which stores multiple instructions, and the instructions are suitable for a processor to load to execute the steps in any virtual lane construction method provided in the embodiment of the present application.

[0041] In addition, the embodiment of the present application also provides a computer program product, which includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device performs the steps in any one of the virtual lane construction methods provided in the embodiment of the present application.

[0042] The embodiments of the present application can collect lane information within a preset range of the target vehicle; calculate multiple centerline segments of each lane according to the lane information, and store the multiple centerline segments in a multidimensional data space; select the first centerline segment and the second centerline segment adjacent to each centerline segment from the multidimensional data space; connect the centerline segment with the first centerline segment and the second centerline segment, respectively, to obtain a virtual centerline of each lane; construct a corresponding virtual lane according to each virtual centerline; thus, the present solution can first collect lane information within a preset range, and calculate multiple centerline segments corresponding to each lane, and store the centerline segments in the multidimensional data space to facilitate querying the first centerline segment and the second centerline segment adjacent to each centerline segment, thereby constructing a virtual centerline, and then constructing a virtual lane; in this way, without relying on a high-precision map, a virtual lane for guiding vehicle driving is accurately constructed, thereby ensuring the safety of vehicle automatic driving and improving the user's driving experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0044] Figure 1 is a schematic diagram of a scenario of a virtual lane construction system provided in an embodiment of the present application;

[0045] Figure 2 A schematic diagram of the steps of the virtual lane construction method provided in an embodiment of the present application;

[0046] Figure 3 is another step flow chart of the virtual lane construction method provided in an embodiment of the present application;

[0047] Figure 4 It is a structural schematic diagram of an unreasonable center line segment association relationship of a virtual lane construction method provided in an embodiment of the present application;

[0048] Figure 5 is a structural schematic diagram of a virtual lane construction device provided in an embodiment of the present application;

[0049] Figure 6 It is a schematic diagram of the structure of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0050] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0051] The embodiments of the present application provide a virtual lane construction method, device, equipment and computer-readable storage medium. The embodiments of the present application will be described from the perspective of a virtual lane construction device, which can be integrated into a computer device, which can be a terminal device, specifically a terminal device carried on a transportation vehicle, that is, a vehicle-mounted terminal; in addition, the terminal device can also be other types of devices, for example, the terminal can be a TV, a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart speaker, a smart watch, a smart wearable device and other devices; in addition, but not limited to this.

[0052] For example, see Figure 1 , is a schematic diagram of a scenario of a virtual lane construction system provided in an embodiment of the present application. The scenario includes a terminal or a server.

[0053] Specifically, the terminal can be a vehicle-mounted terminal, used to collect lane information within a preset range of the target vehicle; calculate multiple center line segments of each lane based on the lane information, and store the multiple center line segments in a multidimensional data space; select a first center line segment and a second center line segment adjacent to each center line segment from the multidimensional data space; connect the center line segment with the first center line segment and the second center line segment respectively to obtain a virtual center line of each lane; and construct a corresponding virtual lane based on each virtual center line.

[0054] It should be noted that the description order of the following embodiments is not intended to limit the preferred order of the embodiments.

[0055] In the embodiments of the present application, the description will be made from the perspective of a virtual lane construction device, and the virtual lane construction device can be integrated into a computer device such as a terminal device or a server. Figure 2 , Figure 2 A schematic flow chart of the steps of a virtual lane construction method provided in an embodiment of the present application is provided. Taking a terminal device as an example, the terminal device is a terminal mounted on a vehicle. When a processor on the terminal device executes a program corresponding to the virtual lane construction method, the specific process of the virtual lane construction method is as follows:

[0056] 101. Collect lane information within a preset range of the target vehicle.

[0057] In an embodiment of the present application, in order to construct a virtual lane on a road without relying on a high-precision map, vehicle sensors can be used to obtain lane information within a preset range of the target vehicle, thereby providing information assistance for the subsequent use of the lane information to construct a virtual lane.

[0058] Among them, the target vehicle can be a means of transportation with carrying capacity, such as a car, a two-wheeled vehicle, a three-wheeled vehicle, an electric vehicle, etc. The target vehicle is equipped with a vehicle-mounted terminal, and the vehicle-mounted terminal can control corresponding software or hardware to collect lane information.

[0059] The lane information may be traffic marking information that separates different lanes on a traffic road. The lane line information includes the distribution position, number, type, and direction of the lane lines, and may also include traffic signs on the road surface.

[0060] Specifically, when a vehicle is traveling in a traffic road area, lane line information and roadside information in the road, namely, lane information, is obtained through on-board sensors, including but not limited to lane lines for forward travel, lane lines for reverse travel, ground arrows, and lane lines of the lane being traveled. The corresponding lane is determined based on the neighborhood relationship between the above lane lines. In this way, the lane information in the road can be obtained without relying on a high-precision map.

[0061] For example, vehicle A is traveling on a straight road with three lanes in total. Based on the fact that two lanes form one lane, the road with three lanes can be divided into two lanes, and ground traffic arrows marked on the ground can also be collected. The center line segment corresponding to each lane is calculated, so that each center line segment can be identified as representing a lane, and the direction of the center line segment is the same as the corresponding lane.

[0062] In the above manner, the lane information within the preset range of the target vehicle can be obtained by using the vehicle sensor, thereby providing information assistance for the subsequent use of the lane information to construct a virtual lane.

[0063] 102. Calculate multiple center line segments of each lane according to the lane information, and store the multiple center line segments in a multi-dimensional data space.

[0064] In an embodiment of the present application, in order to ensure that the virtual lane can be constructed more conveniently and smoothly, the center line segment in each lane can be calculated based on the lane information, and multiple center line segments can be stored in a multidimensional data space, thereby providing assistance for subsequent queries on the first center line segment and the second center line segment corresponding to each center line segment, and the virtual lane can be constructed smoothly and accurately.

[0065] Among them, the center line segment can be a line segment located in the middle of the lane, and each lane can be composed of multiple center line segments arranged in sequence. In the embodiment of the present application, the center line segment can represent the corresponding lane segment information in the electronic map or traffic road map to be constructed. It can be understood that each lane can be composed of multiple center line segments connected.

[0066] The multidimensional data space may be a spatial structure database for data storage according to the arrangement and organization of data. The multidimensional data space converts graphic data, image data, statistical data and other materials into a form suitable for computer storage and processing according to a certain data structure. The data structure includes but is not limited to: grid files and their deformations, quadtrees and their deformation trees, kd trees and their deformation trees, R trees and their deformation trees. The center line segments can be stored in the multidimensional data space according to a certain arrangement order.

[0067] Specifically, after the target vehicle collects lane information within a preset range, two lane lines corresponding to each lane are obtained according to the lane line information in the lane information. Since the lane line may be a solid line or a dotted line, a corresponding center line segment is generated in the lane according to the specific lane line situation of each lane, and according to the position of each center line segment within the preset range, the center line segments of each lane are stored in the vehicle memory in a tree structure from front to back, so that the predecessor and successor relationship between the lanes can be more conveniently queried later.

[0068] Exemplarily, based on the lane lines of lane A, it is calculated that there are three center line segments in lane A, namely segment 1, segment 2 and segment 3, and then, with segment 1 as the head node, the three center line segments are stored in the multidimensional data space in the order of segment 1, segment 2, and segment 3.

[0069] In addition, each center line segment can be represented in the form of two-dimensional coordinate information, and each center line segment can be stored in a multidimensional data space in the form of coordinate information. For example, first coordinate information and second coordinate information at both ends of each center line segment are obtained, and the corresponding center line segment is stored in a multidimensional data space, such as an Rtree data storage structure, according to the first coordinate information and the second coordinate information, so that the preceding lane center line segment and the succeeding lane center line segment adjacent to each center line segment can be quickly queried from the multidimensional data space in the form of coordinates.

[0070] In some implementations, when calculating the center line segment of a lane, two lane boundary lines constituting the lane may be first determined, and multiple lane center point positions of the lane may be calculated based on the lane boundary lines, and then the center line segment may be determined based on the lane center point positions. For example, "calculating multiple center line segments of each lane based on lane information" in step 102 may include:

[0071] (102.1) determining a first lane line segment and a second lane line segment constituting a lane according to the lane information;

[0072] (102.2) calculating a lane midpoint between the first lane segment and the second lane segment;

[0073] (102.3) Construct a center line according to the midpoint of the lane to obtain multiple center line segments for each lane.

[0074] The first lane line segment may be the first lane line segment on the left side of each lane, the second lane line segment may be the first lane line segment on the right side of each lane, and the first lane line segment and the second lane line segment form a lane.

[0075] Among them, the lane midpoint can be the midpoint of the connecting line segment between the first lane segment and the second lane segment, and the lane center is located on the centerline position of the lane. It is worth noting that each lane can have multiple connecting line segments, that is, there are multiple corresponding lane midpoints.

[0076] Specifically, when the vehicle obtains lane line information and roadside information within a preset range, that is, lane information, through the on-board sensor, the lanes in each road are determined, and the adjacent lane lines in the lane line information are connected to obtain the distance straight line segment between the two adjacent lane lines. The line segment can represent the width of the lane, and then the midpoint on the distance line segment is calculated. For example, if the length of a distance line segment is 3 meters, the corresponding midpoint of the distance line segment is at a position of 1.5 meters of the line segment. This method is used to connect multiple distance line segments in the lane, and the corresponding midpoints are calculated using the above method. The center line segment of the lane is formed by connecting each midpoint in turn.

[0077] Through the above method, the center line segment in each lane can be calculated through the lane information, and multiple center line segments can be stored in a multidimensional data space, thereby providing assistance for subsequent queries of the first center line segment and the second center line segment corresponding to each center line segment, and thus the virtual lane can be smoothly and accurately constructed.

[0078] 103. Select a first center line segment and a second center line segment adjacent to each center line segment from the multidimensional data space.

[0079] In an embodiment of the present application, in order to construct a virtual lane, the first center line segment and the second center line segment adjacent to each center line segment can be selected from the multidimensional data space to obtain the topological relationship between the lanes to provide assistance for the subsequent construction of the lane.

[0080] Among them, taking any center line segment as the target center line segment as an example, the first center line segment can be the lane center line segment closest to the front of the target center line segment in the same lane, or it can be the lane center line segment closest to the front of the target center line segment in a different lane. The center line segment whose coordinates are in front of the target center line segment in the multidimensional data space, for example, the positional relationship between line segments 1, 2, and 3 is a front-to-back relationship, then line segment 1 is the first center line segment of line segment 2.

[0081] Among them, taking any center line segment as the target center line segment as an example, the second center line segment can be the lane center line segment closest to the target center line segment in the same lane, or it can be the lane center line segment closest to the target center line segment in a different lane. The center line segment whose coordinates are behind the target center line segment in the multidimensional data space, for example, the positional relationship between line segments 1, 2, and 3 is a front-to-back relationship, then line segment 3 is the second center line segment of line segment 2.

[0082] Specifically, after the center line segments of each lane are stored in a multidimensional data space in a tree structure, since in the multidimensional data space, the tree node of the center line segment may be connected to multiple predecessor center line segments, and the tree node may also be connected to multiple successor center line segments, it is necessary to accurately select the lanes that can ensure the parallelism and series connection between the lanes from the multiple predecessor center line segments, that is, to select the first center line segment and the second center line segment.

[0083] Exemplarily, A is a tree storage structure, center line segment a is the top node of the tree, followed by two child nodes, center line segment b and center line segment c, and center line segment b has two child nodes, center line segment d and center line segment e. Then center line segment a is the first center line segment of center line segment b, and center line segment d and center line segment e are the second center line segment of center segment b.

[0084] Therefore, in some implementations, multiple candidate center line segments corresponding to each center line segment within a preset distance range may be queried from the multidimensional data space, and then the first center line segment and the second center line segment adjacent to each center line segment may be selected according to the position distribution relationship between each center line segment and the multiple candidate center line segments. For example, in step 103, “selecting the first center line segment and the second center line segment adjacent to each center line segment from the multidimensional data space” may include:

[0085] (103.1) querying multiple candidate center line segments corresponding to each center line segment within a preset distance range from the multidimensional data space;

[0086] (103.2) determining a position distribution relationship between each center line segment and a plurality of candidate center line segments;

[0087] (103.3) Select the first center line segment and the second center line segment adjacent to each center line segment according to the position distribution relationship.

[0088] Among them, the position distribution relationship can be the relative position of each center line segment and the corresponding multiple candidate center line segments within a preset range, including but not limited to the coordinate position of each center line segment. The position distribution relationship is mainly to enable the center line segment to select the corresponding first center line segment and second center line segment from the candidate center line segments.

[0089] Specifically, after the center line segments of each lane are stored in a multidimensional data space in the form of a tree structure according to the positions of the center line segments in the road area, the sequential position relationship between the center line segments is identified according to the node position relationship of each center line segment in the multidimensional data space, and the center line segment at the rear end is used as the successor center line segment of the front end center line segment, and the center line segment at the front end is used as the predecessor center line segment of the rear end center line segment, that is, multiple candidate center line segments corresponding to the preset distance range of each center line segment are selected. Then, according to the position distribution relationship of each center line segment within the preset range, the predecessor center line segment and the successor center line segment that are parallel and serial with the middle center line segment are selected, that is, the first center line segment and the second center line segment adjacent to each center line segment are selected.

[0090] Therefore, in some implementations, multiple candidate center line segments corresponding to each center line segment can be queried from the multidimensional data space using the first coordinate and the second coordinate at both ends of each center line segment. For example, in step (103.1), “querying multiple candidate center line segments corresponding to each center line segment within a preset distance range from the multidimensional data space” can include:

[0091] (103.1.1) Obtain the first coordinate and the second coordinate of each end of each center line segment respectively;

[0092] (103.1.2) The center line segments within the preset distance range of the first coordinate and the second coordinate are respectively searched in the multidimensional data space to obtain multiple candidate center line segments corresponding to each center line segment.

[0093] The first coordinate may be the coordinate of the front end point of each center line segment in the multi-dimensional data space.

[0094] The second coordinate may be the coordinate of the rear endpoint of each center line segment in the multidimensional data space.

[0095] Specifically, after the center line segments of each lane are stored in the form of a tree structure in the multidimensional data space, a plane coordinate system is established within a preset range, and the coordinates of the two end points of the center line segment of each lane, that is, the first coordinate and the second coordinate, are obtained. Then, based on the first coordinate and the second coordinate, the distance position between the head node and the tail node of the center line segment of each lane is determined. The specific method can be to query the front center line segment before the head node in the multidimensional data space according to the positions of the head and tail points of the center line segment. If the distance between the head node and the front center line segment is within the preset distance range, the corresponding center line segment is determined as a candidate predecessor center line segment. Similarly, the rear center line segment after the tail node is queried in the multidimensional data space. If the distance between the tail node and the rear center line segment is within the preset distance range, the corresponding center line segment is determined as a candidate successor center line segment. It is worth noting that there may be multiple candidate predecessor centerline segments and multiple successor centerline segments for a centerline segment. The multiple candidate predecessor centerline segments and multiple candidate successor lanes are uniformly determined as candidate centerline segments of the corresponding centerline segment, thereby providing data assistance for the subsequent selection of parallel and smooth predecessor and successor centerline segments.

[0096] Therefore, in some implementations, the angle value and position relationship between the center line segment and each candidate center line segment can be obtained through the position distribution relationship, and then the first center line segment and the second center line segment adjacent to each center line segment can be selected based on the angle value and the position relationship. For example, in step (103.3), "selecting the first center line segment and the second center line segment adjacent to each center line segment based on the position distribution relationship" can include:

[0097] (103.3.1) according to the position distribution relationship, obtain the angle value and position relationship between the center line segment and each candidate center line segment;

[0098] (103.3.2) Select a first center line segment and a second center line segment adjacent to each center line segment from a plurality of candidate center line segments based on the angle value and the position relationship.

[0099] The positional relationship may be the position of the center line segments on the ground within a preset range, such as whether there are intersections between the center line segments, and whether there are intersections between the lane lines corresponding to the center line segments.

[0100] Specifically, after querying the multiple candidate center line segments corresponding to each center line segment within the preset distance range from the multidimensional data space, the angle value and position relationship between the center line segment and each candidate center line segment are obtained according to the position distribution relationship between each center line segment and the corresponding candidate center line segment. When the angle value between the candidate center line segment and the center line segment meets the preset angle threshold, the adjacent candidate center line segment located in the front area of ​​the center line segment is determined as the first center line segment, and the adjacent candidate center line segment located in the rear area of ​​the center line segment is determined as the second center line segment according to the position relationship between each center line segment and all candidate center line segments that meet the preset angle threshold. It is worth noting that if an unreasonable first center line segment or second center line segment is encountered, the association relationship between the first center line segment or the second center line segment and the center line segment needs to be deleted, such as Figure 4 As shown, since there is a shorter center line segment C between center line segment A and center line segment B, center line segment A can easily cross the line segment and use center line segment B as the second center line segment. At this time, center line segment B cannot be used as the second center line segment of center line segment A.

[0101] Therefore, in some implementations, the plane geometric relationship between the center line segment and each candidate center line segment can be determined by the plane geometric relationship corresponding to each angle value, so as to select the first center line segment and the second center line segment from the candidate center line segments according to the position relationship. For example, in step (103.3.2), "selecting the first center line segment and the second center line segment adjacent to each center line segment from the plurality of candidate center line segments according to the angle value and the position relationship" can include:

[0102] (103.3.2.1) Determine the plane geometric relationship between the center line segment and each candidate center line segment based on the angle value;

[0103] (103.3.2.2) Determine the candidate center line segments whose plane geometric relationship is parallel as the target candidate center line segments;

[0104] (103.3.2.3) Based on the positional relationship, a first center line segment and a second center line segment adjacent to each center line segment are selected from multiple target candidate center line segments.

[0105] Specifically, after obtaining the angle value and position relationship between each center line segment and the candidate center line segment, if the angle value between the center line segment and a candidate center line segment is 0°, that is, the plane geometric relationship between the two center line segments is a parallel relationship, it means that the lanes corresponding to the two center line segments are in the same road, or the relationship between the lanes where the two center line segments are located is a parallel relationship. The candidate center line segments that are in a parallel plane geometric relationship with the center line segment and are adjacent in position among the multiple candidate center line segments are determined as the first center line segment and the second center line segment.

[0106] Exemplarily, a vehicle is traveling in a certain road area, and a center line segment A in the road area has three candidate successor center line segments, namely candidate successor center line segment a, candidate successor center line segment b, and candidate successor center line segment c, wherein the angle values ​​between the center line segments of candidate successor center line segment a and candidate successor center line segment b and the center line segment of center line segment A are both 0°, that is, the plane geometric relationship is parallel sharing, and the angle values ​​between candidate successor center line segment c and the center line segment of center line segment A are both 90°, that is, the plane geometric relationship is a perpendicular relationship, which means that candidate successor center line segment a and candidate successor center line segment b are on the same driving road as center line segment A, and the second center line segment of center line segment A is center line segment a and center line segment b.

[0107] In the above manner, the topological relationship between lanes can be obtained by selecting the first center line segment and the second center line segment adjacent to each center line segment from the multidimensional data space, thereby providing assistance for subsequent lane construction.

[0108] 104. Connect the center line segment with the first center line segment and the second center line segment respectively to obtain a virtual center line of each lane.

[0109] In an embodiment of the present application, in order to accurately construct a virtual lane within a preset range and ensure the safe implementation of autonomous driving, the center line segment in the lane can be connected with the corresponding first center line segment and second center line segment to obtain the virtual center line required to construct the virtual lane, thereby more accurately constructing the virtual lane and ensuring the driving safety of the car.

[0110] The virtual center line may be a connecting line between a center line segment and the corresponding first center line segment and second center line segment, and the virtual center line may be used as a lane center line required for constructing a virtual lane.

[0111] Specifically, after determining the first center line segment and the second center line segment that have a topological relationship with the center line segment of the lane, the center line segment of each lane is connected to the corresponding first center line segment and second center line segment to obtain a virtual center line of each lane, so that the front endpoint of the center line segment is connected to the rear endpoint of the first center line segment, and the rear endpoint of the center line segment is connected to the front endpoint of the second center line segment, so that a virtual lane can be constructed through the virtual center line in the subsequent process. It is worth noting that when there are multiple first center line segments or multiple second center line segments in the center line segment, a corresponding number of virtual center lines will be connected, so that corresponding smooth connecting lines are established between different lanes.

[0112] Exemplarily, the center line segment a corresponding to lane A has two second center line segments, namely line segment b and line segment c, wherein line segment c is also a center line segment in lane A and is located behind center line segment a, and line segment b belongs to the adjacent lane B and is also behind center line segment a within a preset range. Line segment a and line segment c are connected, and line segment a and line segment b are connected, so that line segment a and line segment c are on one connecting line, and line segment a and line segment b are on another connecting line.

[0113] In some implementations, the virtual center line has a direction, and the center line segment needs to be connected with the first center line segment and the second center line segment according to the direction of the center line segment to obtain a correct virtual center line. The direction of each center line segment can be determined according to the lane direction identifier in the lane information, so as to determine the sorting relationship between the center line segment and the first center line segment and the second center line segment. For example, before "connecting the center line segment with the first center line segment and the second center line segment respectively to obtain a virtual center line of each lane" in step 104, the following may also be included:

[0114] (104.a.1) obtaining a lane direction indicator from the lane information, where the lane direction indicator is used to indicate the direction of traffic in the lane;

[0115] (104.a.1) determining, based on the direction of traffic travel, a ranking relationship between each center line segment and the adjacent first center line segment and the adjacent second center line segment;

[0116] Then step 104 includes: connecting the center line segment with the adjacent first center line segment and the adjacent second center line segment in sequence according to the sorting relationship to obtain a virtual center line of each lane.

[0117] The lane direction sign may be a traffic sign on a ground road, such as a straight arrow, a left turn arrow, or the like, which may indicate the lane travel direction.

[0118] Among them, the sorting relationship can be used to represent the sorting order between the center line segment, the first center line segment and the second center line segment. The sorting order can be specifically determined according to the driving direction of the lane. For example, according to the driving direction, the sorting order is determined by determining the chronological distribution order between the center line segment, the first center line segment and the second center line segment.

[0119] Specifically, according to the lane direction signs collected by the vehicle-mounted sensor, such as ground traffic arrows, etc., it is determined in which lane the ground traffic sign is located. If the ground traffic sign is a ground traffic arrow, the driving direction of the lane where the arrow is located is determined according to the direction of the ground traffic arrow, thereby determining the traffic driving direction of the center line segment of the lane, and using the lane as a reference lane with a clear direction. It is worth noting that there are some lanes on the road that do not have lane direction signs. The traffic driving direction of the lane on the right side of the lane with a clear traffic driving direction can be determined according to common sense of traffic roads (the driving direction of the lane on the right side of the lane driving direction is consistent with the driving direction of the lane). In this way, the driving direction of the remaining lanes can be determined. In another case, if the vehicle-mounted sensor does not detect the lane direction sign, the driving direction of the current lane can be determined according to the navigation information of the current lane, thereby determining the driving direction of other lanes. After obtaining the center line segment with a clear driving direction, the driving direction of the first center line segment and the second center line segment is determined according to the positional relationship between the center line segment and the first center line segment and the second center line segment, and then the sorting relationship between each center line segment and the adjacent first center line segment and the second center line segment is determined.

[0120] Furthermore, after obtaining the sorting relationship between each center line segment and the adjacent first center line segment and the second center line segment, the center line segment is sequentially connected with the adjacent first center line segment and the second center line segment to obtain a virtual center line of each lane.

[0121] Through the above method, the center line segment in the lane can be connected with the corresponding first center line segment and second center line segment to obtain the virtual center line required for constructing the virtual lane, so as to more accurately construct the virtual lane and ensure the driving safety of the car.

[0122] 105. Construct a corresponding virtual lane according to each virtual center line.

[0123] In an embodiment of the present application, in order to ensure the driving safety of the vehicle, the virtual center line obtained from the road can be used to accurately construct the corresponding virtual lane, and a smooth connection between different lanes can be achieved, thereby ensuring the safety of the vehicle's automatic driving and further improving the user's driving experience.

[0124] Among them, the virtual lane can be a virtual driving lane for the vehicle constructed by the vehicle-mounted terminal in the vehicle-mounted map of the target vehicle based on the virtual center line, and the virtual lane can assist the target vehicle in performing automated driving.

[0125] Specifically, after constructing the virtual center line of each lane, a virtual lane is constructed in the preset area where the target vehicle is traveling, using the virtual center line as the lane center position based on the distance between lane lines, so that the vehicle can travel safely through the virtual lane; in this way, the virtual lane can assist the target vehicle in implementing the automatic driving function.

[0126] Through the above method, the corresponding virtual lane can be accurately constructed by utilizing the virtual center line obtained from the road, and a smooth connection between different lanes can be achieved, thereby ensuring the safety of vehicle autonomous driving and improving the user's driving experience.

[0127] By implementing any one implementation or combination of implementations in the embodiments of the present application, an application scenario of the virtual lane construction process can be realized.

[0128] As can be seen from the above, the embodiments of the present application can collect lane information within a preset range of the target vehicle; calculate multiple center line segments of each lane based on the lane information, and store the multiple center line segments in a multidimensional data space; select the first center line segment and the second center line segment adjacent to each center line segment from the multidimensional data space; connect the center line segment with the first center line segment and the second center line segment respectively to obtain a virtual center line of each lane; construct a corresponding virtual lane according to each virtual center line; thus, the present solution can first collect lane information within a preset range, and calculate multiple center line segments corresponding to each lane, and store the center line segments in the multidimensional data space to facilitate the query of the first center line segment and the second center line segment adjacent to each center line segment, thereby constructing a virtual center line, and then constructing a virtual lane; in this way, without relying on a high-precision map, a virtual lane for guiding vehicle driving is accurately constructed, thereby ensuring the safety of vehicle automatic driving and improving the user's driving experience.

[0129] According to the method described in the above embodiment, the following is further described in detail with examples.

[0130] The embodiment of the present application takes the virtual lane construction device as an example to further describe the virtual lane construction method provided by the embodiment of the present application. Figure 3 This is another step flow chart of the virtual lane construction method provided in the embodiment of the present application. Figure 3 Give a description.

[0131] In the embodiment of the present application, the virtual lane construction device will be described from the perspective of the virtual lane construction device, which can be integrated into a computer device such as a vehicle-mounted terminal. When the processor on the vehicle-mounted terminal executes the program instructions corresponding to the data transmission method, the specific process of the virtual lane construction method is as follows:

[0132] 201. The vehicle-mounted terminal collects lane information within a preset range of the target vehicle.

[0133] Among them, the target vehicle can be a means of transportation with carrying capacity, such as a car, a two-wheeled vehicle, a three-wheeled vehicle, an electric vehicle, etc. The target vehicle is equipped with a vehicle-mounted terminal, and the vehicle-mounted terminal can control corresponding software or hardware to collect lane information.

[0134] The lane information may be traffic marking information that separates different lanes on a traffic road. The lane line information includes the distribution position, number, type, and direction of the lane lines, and may also include traffic signs on the road surface.

[0135] Specifically, when a vehicle is traveling in a traffic road area, the on-board terminal obtains lane line information and roadside information in the road through on-board sensors, that is, lane information, including but not limited to lane lines for forward driving, lane lines for reverse driving, ground arrows, and lane lines of the lane being driven, and determines the corresponding lane based on the neighborhood relationship between the above lane lines. In this way, the lane information in the road can be obtained without relying on high-precision maps.

[0136] For example, vehicle A is traveling on a straight road with three lanes in total. Based on the fact that two lanes form one lane, the road with three lanes can be divided into two lanes, and ground traffic arrows marked on the ground can also be collected. The center line segment corresponding to each lane is calculated, so that each center line segment can be identified as representing a lane, and the direction of the center line segment is the same as the corresponding lane.

[0137] 202. The vehicle-mounted terminal calculates multiple center line segments of each lane according to the lane information, and stores the multiple center line segments in a multi-dimensional data space.

[0138] Among them, the center line segment can be a line segment located in the middle of the lane, and each lane can be composed of multiple center line segments arranged in sequence. In the embodiment of the present application, the center line segment can represent the corresponding lane segment information in the electronic map or traffic road map to be constructed. It can be understood that each lane can be composed of multiple center line segments connected.

[0139] The multidimensional data space may be a spatial structure database for data storage according to the arrangement and organization of data. The multidimensional data space converts graphic data, image data, statistical data and other materials into a form suitable for computer storage and processing according to a certain data structure. The data structure includes but is not limited to: grid files and their deformations, quadtrees and their deformation trees, kd trees and their deformation trees, R trees and their deformation trees. The center line segments can be stored in the multidimensional data space according to a certain arrangement order.

[0140] Specifically, after the target vehicle collects lane information within a preset range, the on-board terminal obtains two lane lines corresponding to each lane according to the lane line information in the lane information. Since the lane line may be a solid line or a dotted line, a corresponding center line segment is generated in the lane according to the specific lane line situation of each lane, and according to the position of each center line segment within the preset range, the center line segments of each lane are stored in the on-board memory in a tree structure from front to back, so that the predecessor and successor relationship between the lanes can be more conveniently queried later.

[0141] Exemplarily, based on the lane lines of lane A, it is calculated that there are three center line segments in lane A, namely segment 1, segment 2 and segment 3, and then, with segment 1 as the head node, the three center line segments are stored in the multidimensional data space in the order of segment 1, segment 2, and segment 3.

[0142] In addition, each center line segment can be represented in the form of two-dimensional coordinate information, and each center line segment can be stored in a multidimensional data space in the form of coordinate information. For example, first coordinate information and second coordinate information at both ends of each center line segment are obtained, and the corresponding center line segment is stored in a multidimensional data space, such as an Rtree data storage structure, according to the first coordinate information and the second coordinate information, so that the preceding lane center line segment and the succeeding lane center line segment adjacent to each center line segment can be quickly queried from the multidimensional data space in the form of coordinates.

[0143] 203. The vehicle-mounted terminal obtains the first coordinate and the second coordinate at both ends of each center line segment, and respectively searches for center line segments within a preset distance range of the first coordinate and the second coordinate from the multidimensional data space to obtain multiple candidate center line segments corresponding to each center line segment.

[0144] The first coordinate may be the coordinate of the front end point of each center line segment in the multi-dimensional data space.

[0145] The second coordinate may be the coordinate of the rear endpoint of each center line segment in the multidimensional data space.

[0146] Specifically, after the on-board terminal stores the center line segments of each lane in the form of a tree structure in the multidimensional data space, a plane coordinate system is established within a preset range to obtain the coordinates of the two end points of the center line segment of each lane, that is, the first coordinate and the second coordinate, and then the distance position between the head node and the tail node of the center line segment of each lane is determined based on the first coordinate and the second coordinate. The specific method can be to query the front center line segment before the head node in the multidimensional data space according to the positions of the head and tail points of the center line segment. If the distance between the head node and the front center line segment is within the preset distance range, the corresponding center line segment is determined as a candidate predecessor center line segment. Similarly, the rear center line segment after the tail node is queried in the multidimensional data space. If the distance between the tail node and the rear center line segment is within the preset distance range, the corresponding center line segment is determined as a candidate successor center line segment. It is worth noting that there may be multiple candidate predecessor centerline segments and multiple successor centerline segments for a centerline segment. The multiple candidate predecessor centerline segments and multiple candidate successor lanes are uniformly determined as candidate centerline segments of the corresponding centerline segment, thereby providing data assistance for the subsequent selection of parallel and smooth predecessor and successor centerline segments.

[0147] 204. The vehicle-mounted terminal selects a first center line segment and a second center line segment adjacent to each center line segment from a plurality of candidate center line segments according to an angle value and a position relationship between the center line segment and each candidate center line segment.

[0148] Among them, taking any center line segment as the target center line segment as an example, the first center line segment can be the lane center line segment closest to the front of the target center line segment in the same lane, or it can be the lane center line segment closest to the front of the target center line segment in a different lane. The center line segment whose coordinates are in front of the target center line segment in the multidimensional data space, for example, the positional relationship between line segments 1, 2, and 3 is a front-to-back relationship, then line segment 1 is the first center line segment of line segment 2.

[0149] Among them, taking any center line segment as the target center line segment as an example, the second center line segment can be the lane center line segment closest to the target center line segment in the same lane, or it can be the lane center line segment closest to the target center line segment in a different lane. The center line segment whose coordinates are behind the target center line segment in the multidimensional data space, for example, the positional relationship between line segments 1, 2, and 3 is a front-to-back relationship, then line segment 3 is the second center line segment of line segment 2.

[0150] Specifically, after the on-board terminal queries the multiple candidate center line segments corresponding to each center line segment within the preset distance range from the multidimensional data space, the angle value and position relationship between the center line segment and each candidate center line segment are obtained according to the position distribution relationship between each center line segment and the corresponding candidate center line segment. If the angle value between the center line segment and a candidate center line segment is 0°, that is, the plane geometric relationship between the two center line segments is parallel, it means that the lanes corresponding to the two center line segments are in the same road, and the candidate center line segments in the multiple candidate center line segments that are parallel to the center line segments and adjacent in position are determined as the first center line segment and the second center line segment. It is worth noting that if an unreasonable first center line segment or second center line segment is encountered, the association relationship between the first center line segment or the second center line segment and the center line segment needs to be deleted, such as Figure 4 As shown, since there is a shorter center line segment C between center line segment A and center line segment B, center line segment A can easily cross the line segment and use center line segment B as the second center line segment. At this time, center line segment B cannot be used as the second center line segment of center line segment A.

[0151] Exemplarily, a vehicle is traveling in a certain road area, and a center line segment A in the road area has three candidate successor center line segments, namely candidate successor center line segment a, candidate successor center line segment b, and candidate successor center line segment c, wherein the angle values ​​between the center line segments of candidate successor center line segment a and candidate successor center line segment b and the center line segment of center line segment A are both 0°, that is, the plane geometric relationship is parallel sharing, and the angle values ​​between candidate successor center line segment c and the center line segment of center line segment A are both 90°, that is, the plane geometric relationship is a perpendicular relationship, which means that candidate successor center line segment a and candidate successor center line segment b are on the same driving road as center line segment A, and the second center line segment of center line segment A is center line segment a and center line segment b.

[0152] 205. The vehicle-mounted terminal determines the traffic driving direction of the lane to which the lane direction sign belongs based on the lane direction sign in the lane information.

[0153] The lane direction sign may be a traffic sign on a ground road, such as a straight arrow, a left turn arrow, or the like, which may indicate the lane travel direction.

[0154] Specifically, the vehicle terminal determines in which lane the ground traffic sign is located based on the lane direction signs collected by the vehicle sensor, such as ground traffic arrows, etc. If the ground traffic sign is a ground traffic arrow, the driving direction of the lane where the arrow is located is determined according to the direction of the ground traffic arrow, thereby determining the traffic driving direction of the center line segment of the lane, and using the lane as a reference lane with a clear direction. It is worth noting that there are some lanes on the road that do not have lane direction signs. The traffic driving direction of the lane on the right side of the lane with a clear traffic driving direction can be determined based on common sense of traffic roads (the driving direction of the lane on the right side of the lane driving direction is consistent with the driving direction of the lane). In this way, the driving direction of the remaining lanes can be determined. In another case, if the vehicle sensor does not detect the lane direction sign, the driving direction of the current lane can be determined based on the navigation information of the current lane, thereby determining the driving direction of other lanes.

[0155] 206. The vehicle-mounted terminal determines, according to the traffic driving direction, a sorting relationship between each center line segment and the adjacent first center line segment and the adjacent second center line segment.

[0156] Among them, the sorting relationship can be used to represent the sorting order between the center line segment, the first center line segment and the second center line segment. The sorting order can be specifically determined according to the driving direction of the lane. For example, according to the driving direction, the sorting order is determined by determining the chronological distribution order between the center line segment, the first center line segment and the second center line segment.

[0157] Specifically, after obtaining the center line segment with a clear driving direction, the vehicle-mounted terminal determines the driving direction of the first center line segment and the second center line segment according to the positional relationship between the center line segment and the first center line segment and the second center line segment, and determines the sorting method between the first center line segment, the center line segment and the second center line segment from front to back or from back to front according to the traffic driving direction of the first center line segment, the center line segment and the second center line segment.

[0158] 207. The vehicle-mounted terminal connects the center line segment with the adjacent first center line segment and the adjacent second center line segment in sequence according to the sorting relationship to obtain a virtual center line of each lane.

[0159] The virtual center line may be a connecting line between a center line segment and the corresponding first center line segment and second center line segment, and the virtual center line may be used as a lane center line required for constructing a virtual lane.

[0160] Specifically, after determining the first center line segment and the second center line segment that have a topological relationship with the center line segment of the lane, the on-board terminal connects the center line segment of each lane with the corresponding first center line segment and second center line segment according to the sorting relationship between the center line segment and the first center line segment and the second center line segment to obtain a virtual center line for each lane, so that the front end point of the center line segment is connected to the rear end point of the first center line segment, and the rear end point of the center line segment is connected to the front end point of the second center line segment, so that a virtual lane can be constructed subsequently through the virtual center line. It is worth noting that when there are multiple first center line segments or multiple second center line segments in the center line segment, a corresponding number of virtual center lines will be connected to establish corresponding smooth connecting lines between different lanes.

[0161] 208. The vehicle-mounted terminal constructs a corresponding virtual lane according to each virtual center line.

[0162] Among them, the virtual lane can be a virtual driving lane for the vehicle constructed by the vehicle-mounted terminal in the vehicle-mounted map of the target vehicle based on the virtual center line, and the virtual lane can assist the target vehicle in performing automated driving.

[0163] Specifically, after constructing the virtual center line of each lane, a virtual lane is constructed in the preset area where the target vehicle is traveling based on the distance between lane lines and the virtual center line is used as the lane center line, so that the vehicle can travel safely through the virtual lane; in this way, the virtual lane can be used to assist the target vehicle in implementing the automatic driving function.

[0164] By executing steps 201-208, the following scenario of the virtual lane construction process can be realized:

[0165] The vehicle terminal stores the center line segment of each lane in the RTree data structure for query. Then, the vehicle terminal uses breadth-first search (BFS) to search for initial topological information. Specifically, according to the positions of the head and tail points of the lane center line, the candidate predecessor center line segment can be queried through Rtree within a certain range of the head node, and the candidate successor center line segment can be queried through Rtree within a certain range of the tail node. The candidate center line segments are screened for angle position and boundary conflict, and the first center line segment (predecessor center line segment) and the second center line segment (successor center line segment) of the center line segment are selected from the candidate center line segments to ensure that the predecessor and successor lanes meet the requirements of parallelism and series connection. It is worth noting that unreasonable topological information needs to be deleted, such as the existence of short lanes. Figure 4The cross-lane topology information in the vehicle is disordered. The lane direction traffic arrow on the ground (and the lane on its right) and the lane where the vehicle is located (and the lane on its right) are defined as lanes with clear directions; the lanes with clear directions are used as the search starting points of breadth-first search (BFS), and the driving direction information of the first center line segment and the second center line segment in the topological network are determined. In this way, the driving direction is inferred for most lanes that cannot be bound to the lane direction traffic arrows. Each center line segment is connected with its corresponding first center line segment and second center line segment to obtain a virtual center line. It is worth noting that for a center line segment with multiple first center line segments or multiple second center line segments, multiple virtual center lines are created for smooth connection. For a center line segment with only a single first center line segment or a single second center line segment, the center line segment is smoothly extended; thereby ensuring smooth connection between center line segments. Finally, the corresponding virtual lane is constructed according to the center line of the virtual lane. In this way, the virtual lane can assist the target vehicle in implementing the automatic driving function to ensure the safety of vehicle driving.

[0166] Through the above application scenario examples, the following effects can be achieved: during vehicle driving, multiple center line segments of each lane are calculated based on the lane information collected by the vehicle sensor, and the multiple center line segments are stored in the multidimensional data space, so that the first center line segment and the second center line segment of each center line segment are selected in the multidimensional data space, and a smooth connecting line is established between the center line segment and the first center line segment and the second center line segment to construct a virtual center line, and then accurately construct a virtual lane, so that different lanes can be smoothly connected, ensuring the safety of vehicle driving.

[0167] It can be concluded that this solution can first collect lane information within a preset range, calculate multiple center line segments corresponding to each lane, and store the center line segments in a multidimensional data space to facilitate querying the first center line segment and the second center line segment adjacent to each center line segment, thereby constructing a virtual center line and then a virtual lane; in this way, without relying on high-precision maps, a virtual lane for guiding vehicle driving can be accurately constructed, thereby ensuring the safety of vehicle autonomous driving and improving the user's driving experience.

[0168] In order to better implement the above method, the embodiment of the present application further provides a virtual lane construction device, which can be integrated into a computer device, such as a vehicle-mounted terminal or other computer device.

[0169] For example, Figure 5 As shown, the virtual lane construction device may include a collection unit 301 , a calculation unit 302 , a selection unit 303 , a connection unit 304 , and a construction unit 305 .

[0170] A collection unit 301 is used to collect lane information within a preset range of a target vehicle;

[0171] A calculation unit 302, used for calculating a plurality of center line segments of each lane according to the lane information, and storing the plurality of center line segments in a multi-dimensional data space;

[0172] A selection unit 303, used for selecting a front center line segment and a rear center line segment adjacent to each center line segment from the multi-dimensional data space;

[0173] A connection unit 304, used to connect the center line segment with the front center line segment and the rear center line segment respectively to obtain a virtual center line of each lane;

[0174] The construction unit 305 is used to construct a corresponding virtual lane according to each virtual center line.

[0175] In some embodiments, the computing unit 302 is further configured to:

[0176] Determine, according to the lane information, a first lane line segment and a second lane line segment constituting the lane;

[0177] Calculate a lane midpoint between the first lane segment and the second lane segment;

[0178] The centerline is constructed according to the midpoint of the lane, and multiple centerline segments of each lane are obtained.

[0179] In some embodiments, the selection unit 303 is further configured to:

[0180] Querying multiple candidate center line segments corresponding to each center line segment within a preset distance range from the multidimensional data space;

[0181] Determine the position distribution relationship between each center line segment and multiple candidate center line segments;

[0182] The first center line segment and the second center line segment adjacent to each center line segment are selected according to the position distribution relationship.

[0183] In some embodiments, the selection unit 303 is further configured to:

[0184] Get the first coordinate and the second coordinate of each end of each center line segment respectively;

[0185] The center line segments within the preset distance range of the first coordinate and the second coordinate are respectively searched from the multidimensional data space to obtain a plurality of candidate center line segments corresponding to each center line segment.

[0186] In some embodiments, the selection unit 303 is further configured to:

[0187] According to the position distribution relationship, the angle value and position relationship between the center line segment and each candidate center line segment are obtained;

[0188] According to the angle value and the position relationship, a first center line segment and a second center line segment adjacent to each center line segment are selected from a plurality of candidate center line segments.

[0189] In some embodiments, the selection unit 303 is further configured to:

[0190] Determine the plane geometric relationship between the center line segment and each candidate center line segment according to the angle value;

[0191] Determine the candidate center line segments whose plane geometric relationship is parallel as the target candidate center line segments;

[0192] Based on the positional relationship, a first center line segment and a second center line segment adjacent to each center line segment are selected from a plurality of target candidate center line segments.

[0193] In some embodiments, the virtual lane construction device further includes a determining unit, configured to:

[0194] A lane direction mark is obtained from the lane information, where the lane direction mark is used to indicate the direction of traffic in the lane;

[0195] Determine, according to the traffic driving direction, a sorting relationship between each center line segment and an adjacent first center line segment and a second center line segment;

[0196] The connection unit 304 includes:

[0197] According to the sorting relationship, the center line segment is connected with the adjacent first center line segment and the second center line segment in sequence to obtain a virtual center line of each lane.

[0198] From the above, it can be seen that the embodiment of the present application can first collect lane information within a preset range, and calculate multiple center line segments corresponding to each lane, and store the center line segments in a multi-dimensional data space to facilitate the query of the first center line segment and the second center line segment adjacent to each center line segment, thereby constructing a virtual center line, and then constructing a virtual lane; in this way, without relying on high-precision maps, a virtual lane for guiding vehicle driving is accurately constructed, thereby ensuring the safety of vehicle autonomous driving and improving the user's driving experience.

[0199] The specific implementation of the above operations can be found in the previous embodiments, which will not be described in detail here.

[0200] The present application also provides a computer device, such as Figure 6 As shown, it shows a schematic diagram of the structure of the computer device involved in the embodiment of the present application, specifically:

[0201] The computer device may include components such as a processor 401 with one or more processing cores, a memory 402 with one or more computer-readable storage media, a power supply 403, and an input unit 404. Those skilled in the art will appreciate that Figure 6 The computer device structure shown in the figure does not constitute a limitation on the computer device, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently. Among them:

[0202] The processor 401 is the control center of the computer device. It uses various interfaces and lines to connect various parts of the entire computer device. By running or executing software programs and / or modules stored in the memory 402 and calling data stored in the memory 402, it executes various functions of the computer device and processes data, thereby monitoring the computer device as a whole. Optionally, the processor 401 may include one or more processing cores; preferably, the processor 401 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface, and application programs, and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 401.

[0203] The memory 402 can be used to store software programs and modules. The processor 401 executes various functional applications and virtual lane construction by running the software programs and modules stored in the memory 402. The memory 402 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function (such as a voice playback function, an image playback function, etc.), etc.; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 402 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage device. Accordingly, the memory 402 may also include a memory controller to provide the processor 401 with access to the memory 402.

[0204] The computer device also includes a power supply 403 for supplying power to various components. Preferably, the power supply 403 can be logically connected to the processor 401 through a power management system, so as to manage charging, discharging, and power consumption through the power management system. The power supply 403 can also include any components such as one or more DC or AC power supplies, recharging systems, power failure detection circuits, power converters or inverters, and power status indicators.

[0205] The computer device may further include an input unit 404, which may be used to receive input digital or character information and generate keyboard, mouse, joystick, optical or trackball signal input related to user settings and function control.

[0206] Although not shown, the computer device may further include a display unit, etc., which will not be described in detail herein. Specifically in this embodiment, the processor 401 in the computer device will load the executable files corresponding to the processes of one or more application programs into the memory 402 according to the following instructions, and the processor 401 will run the application programs stored in the memory 402, thereby realizing various functions, as follows:

[0207] The lane information within a preset range of the target vehicle is collected; multiple center line segments of each lane are calculated according to the lane information, and the multiple center line segments are stored in a multidimensional data space; a first center line segment and a second center line segment adjacent to each center line segment are selected from the multidimensional data space; the center line segment is connected to the first center line segment and the second center line segment respectively to obtain a virtual center line of each lane; and a corresponding virtual lane is constructed according to each virtual center line.

[0208] The specific implementation of the above operations can be found in the previous embodiments and will not be described in detail here.

[0209] From the above, it can be seen that this solution can first collect lane information within a preset range, and calculate multiple center line segments corresponding to each lane, and store the center line segments in a multidimensional data space to facilitate the query of the first center line segment and the second center line segment adjacent to each center line segment, thereby constructing a virtual center line, and then constructing a virtual lane; in this way, without relying on high-precision maps, a virtual lane for guiding vehicle driving can be accurately constructed, thereby ensuring the safety of vehicle autonomous driving and improving the user's driving experience.

[0210] A person of ordinary skill in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be completed by instructions, or by controlling related hardware through instructions. The instructions may be stored in a computer-readable storage medium and loaded and executed by a processor.

[0211] To this end, an embodiment of the present application provides a computer-readable storage medium, in which a plurality of instructions are stored, and the instructions can be loaded by a processor to execute the steps in any of the virtual lane construction methods provided in the embodiments of the present application. For example, the instructions can execute the following steps:

[0212] The lane information within a preset range of the target vehicle is collected; multiple center line segments of each lane are calculated according to the lane information, and the multiple center line segments are stored in a multidimensional data space; a first center line segment and a second center line segment adjacent to each center line segment are selected from the multidimensional data space; the center line segment is connected to the first center line segment and the second center line segment respectively to obtain a virtual center line of each lane; and a corresponding virtual lane is constructed according to each virtual center line.

[0213] The specific implementation of the above operations can be found in the previous embodiments, which will not be described in detail here.

[0214] The computer-readable storage medium may include: a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0215] The present application also provides a computer program product or a computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the virtual lane construction method provided in various optional implementations in the above embodiments.

[0216] Since the instructions stored in the computer-readable storage medium can execute the steps in any virtual lane construction method provided in the embodiments of the present application, the beneficial effects that can be achieved by any virtual lane construction method provided in the embodiments of the present application can be achieved. Please refer to the previous embodiments for details and will not be repeated here.

[0217] The above is a detailed introduction to a virtual lane construction method, device, equipment and computer-readable storage medium provided in the embodiments of the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for technical personnel in this field, according to the ideas of the present application, there will be changes in the specific implementation methods and application scopes. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A virtual lane construction method, characterized in that: include: Collect lane information within a preset range of the target vehicle; Calculate multiple center line segments of each lane according to the lane information, and store the multiple center line segments in a multi-dimensional data space in the form of a tree structure; in the multi-dimensional data space, multiple preceding center line segments are connected before the tree node of the center line segment, and multiple succeeding center line segments are connected after the tree node of the center line segment; the center line segment is represented in the form of two-dimensional coordinate information; Querying a plurality of candidate center line segments corresponding to each center line segment within a preset distance range from the multidimensional data space; Determine a position distribution relationship between each center line segment and the plurality of candidate center line segments; Determine the angle value and position relationship between the center line segment and each candidate center line segment according to the position distribution relationship; Determining a planar geometric relationship between the center line segment and each candidate center line segment according to the angle value; Determine the candidate center line segments whose plane geometric relationship is parallel as target candidate center line segments; Based on the positional relationship, selecting a first center line segment and a second center line segment adjacent to each center line segment from a plurality of target candidate center line segments; Connecting the center line segment with the first center line segment and the second center line segment respectively to obtain a virtual center line of each lane; A corresponding virtual lane is constructed according to each virtual center line.

2. The method according to claim 1, characterized in that: The calculating a plurality of center line segments of each lane according to the lane information comprises: Determining, based on the lane information, a first lane line segment and a second lane line segment constituting a lane; Calculating a lane midpoint between the first lane segment and the second lane segment; A center line is constructed according to the midpoint of the lane to obtain a plurality of center line segments of each lane.

3. The method according to claim 1, characterized in that The step of querying the multidimensional data space for a plurality of candidate center line segments corresponding to each center line segment within a preset distance range includes: Get the first coordinate and the second coordinate of each end of each center line segment respectively; The center line segments within a preset distance range between the first coordinate and the second coordinate are respectively searched from the multi-dimensional data space to obtain a plurality of candidate center line segments corresponding to each center line segment.

4. The method according to claim 1, characterized in that Before connecting the center line segment with the first center line segment and the second center line segment respectively to obtain a virtual center line of each lane, the method further includes: Acquire a lane direction mark from the lane information, where the lane direction mark is used to indicate the direction of traffic in the lane; Determining, according to the traffic driving direction, a sorting relationship between each center line segment and the adjacent first center line segment and the second center line segment; Then the step of connecting the center line segment with the first center line segment and the second center line segment respectively to obtain a virtual center line of each lane includes: According to the sorting relationship, the center line segment is connected with the adjacent first center line segment and the adjacent second center line segment in sequence to obtain a virtual center line of each lane.

5. A virtual lane construction device, characterized in that: include: A collection unit, used to collect lane information within a preset range of the target vehicle; A calculation unit, used for calculating a plurality of center line segments of each lane according to the lane information, and storing the plurality of center line segments in a multi-dimensional data space in the form of a tree structure; in the multi-dimensional data space, a plurality of preceding center line segments are connected before the tree node of the center line segment, and a plurality of succeeding center line segments are connected after the tree node of the center line segment; the center line segment is represented in the form of two-dimensional coordinate information; A selection unit, used for querying a plurality of candidate center line segments corresponding to a preset distance range of each center line segment from the multidimensional data space; determining a position distribution relationship between each center line segment and the plurality of candidate center line segments; determining an angle value and a position relationship between the center line segment and each candidate center line segment according to the position distribution relationship; determining a plane geometric relationship between the center line segment and each candidate center line segment according to the angle value; determining a candidate center line segment whose plane geometric relationship is a parallel relationship as a target candidate center line segment; and selecting a first center line segment and a second center line segment adjacent to each of the plurality of target candidate center line segments based on the position relationship; A connection unit, used for connecting the center line segment with the first center line segment and the second center line segment respectively to obtain a virtual center line of each lane; The construction unit is used to construct a corresponding virtual lane according to each virtual center line.

6. A computer device, characterized in that: The method comprises a processor and a memory, wherein the memory stores a computer program, and the processor is used to execute the computer program in the memory to implement the steps in the virtual lane construction method according to any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium is computer-readable and stores a plurality of instructions, wherein the instructions are suitable for being loaded by a processor to execute the steps in the virtual lane construction method according to any one of claims 1 to 4.

Images