Virtual lane line generation method and device, electronic equipment and storage medium

Abstract

The invention relates to the technical field of data processing, in particular to a virtual lane line generation method and device, electronic equipment and a storage medium, and the method comprises the steps: firstly obtaining two virtual side lines generated for a transition road section, the end point coordinates of each single lane line end point, connected with the transition road section, on the first road section and the second road section are obtained; after the two virtual side lines are equally proportionally segmented to obtain M segmentation point connecting lines and corresponding segmentation point coordinates, smoothing of a lane line of at least one virtual lane edge and consistency of a lane line direction and a corresponding segment direction are taken as constraint conditions, and starting and ending coordinates of the at least one virtual lane edge and the segmentation point coordinates are combined to obtain a segmentation point coordinate of the at least one virtual lane edge; and calculating the coordinates of the intersection points, and drawing a virtual lane line corresponding to the virtual lane edge according to the coordinates of the intersection points. Therefore, the virtual lane line can be generated from the virtual lane edge corresponding to the single lane on the whole, and the generation efficiency and the generation quality of the virtual lane line are greatly improved.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and in particular to a method, apparatus, electronic device and storage medium for generating virtual lane lines. Background Technology

[0002] In vehicle navigation scenarios, lane lines provide key information about road layout; lane lines include: physical lane lines generated for lanes with physical lane edge lines in the actual scene, and virtual lane lines generated for lanes that do not usually have corresponding physical lane edge lines in the actual scene.

[0003] Currently, due to the simple road layout involved, when generating virtual lane lines for the transition section connecting two single-lane road segments, the virtual lane lines used to connect the sides of the two single lanes can be generated based on the obtained center lane line and width information of the transition section.

[0004] However, the above-mentioned methods for generating virtual lane lines can only generate virtual lane lines between single-vehicle road segments, and therefore cannot effectively handle complex road layouts. When generating virtual lane lines for transitional road segments connecting multiple vehicle road segments, it is necessary to split multiple lanes into single lanes for processing. This makes the generation efficiency of virtual lane lines very low, and it is impossible to generate virtual lane lines that meet the needs of road transitions as a whole. It is difficult to guarantee the overall presentation effect and accuracy of each virtual lane line, thus greatly affecting the vehicle navigation effect. Summary of the Invention

[0005] This application provides a method, apparatus, electronic device, and storage medium for generating virtual lane lines, in order to improve the generation quality and efficiency of virtual lane lines.

[0006] Firstly, a method for generating virtual lane lines is proposed, including:

[0007] Obtain two virtual side lines generated for the transition section between the first road segment and the second road segment, as well as the endpoint coordinates of the endpoints of each single lane line connecting the first road segment and the second road segment to the transition section; at least one of the first road segment and the second road segment contains multiple single lanes;

[0008] The first endpoint connection line and the second endpoint connection line are respectively used as the dividing point connection lines at the edge. The two virtual side lines are divided into M equal proportions to obtain M dividing point connection lines and corresponding dividing point coordinates. The first endpoint connection line and the second endpoint connection line are obtained based on the endpoints of each single lane line on the first road segment and the endpoints of each single lane line on the second road segment, respectively. M is a positive integer greater than 2.

[0009] Based on the lane division of the first and second road segments, and combined with the endpoint coordinates of each single lane line endpoint, determine the start and end coordinates of the edge of at least one virtual lane planned in the transition segment.

[0010] Using the smoothing of the lane lines of the at least one virtual lane edge and the consistency of the lane line direction with the corresponding road segment direction as constraints, and combining the start and end coordinates of the at least one virtual lane edge and the coordinates of each dividing point, the intersection coordinates of the at least one virtual lane edge on the M dividing point connecting lines are determined respectively, and the virtual lane lines corresponding to each of the at least one virtual lane edge are drawn according to the coordinates of each intersection point.

[0011] Secondly, a virtual lane line generation device is proposed, comprising:

[0012] The acquisition unit is used to acquire two virtual side lines generated for the transition section between the first road segment and the second road segment, as well as the endpoint coordinates of the endpoints of each single lane line connecting the first road segment and the second road segment to the transition section; at least one of the first road segment and the second road segment contains multiple single lanes.

[0013] The segmentation unit is used to divide the two virtual side lines into M equal segments, using the first endpoint connection line and the second endpoint connection line as the segmentation point connection lines at the edges, to obtain M segmentation point connection lines and corresponding segmentation point coordinates; the first endpoint connection line and the second endpoint connection line are obtained based on the endpoints of each single lane line on the first road segment and the endpoints of each single lane line on the second road segment, respectively, where M is a positive integer greater than 2;

[0014] The determining unit is used to determine the start and end coordinates of at least one virtual lane edge planned in the transition section based on the lane division of the first road segment and the second road segment, combined with the endpoint coordinates of each single lane line endpoint.

[0015] The drawing unit is used to smooth the lane lines of the at least one virtual lane edge and use the lane line direction being consistent with the corresponding road segment direction as constraints. Combining the start and end coordinates of the at least one virtual lane edge and the coordinates of each dividing point, it determines the intersection coordinates of the at least one virtual lane edge on the M dividing point connecting lines, and draws the virtual lane lines corresponding to each of the at least one virtual lane edge according to the coordinates of each intersection point.

[0016] Optionally, when determining the intersection coordinates of the at least one virtual lane edge on the M dividing point connecting lines by combining the start and end coordinates of the at least one virtual lane edge and the coordinates of each dividing point, the drawing unit is used to:

[0017] For each dividing point connecting line, perform the following operations: construct intersection points with each dividing point connecting line for each virtual lane edge planned in the transition section, in the form of a proportional coefficient of the straight-line distance from the reference point on the dividing point connecting line to the total length of the dividing point connecting line; the reference point is a dividing point indicated by the corresponding dividing point coordinates.

[0018] Using a convex optimization approach, the proportional coefficient of the intersection point of the at least one virtual lane edge on the M dividing point connection line is determined when the constraint conditions are met. Based on each proportional coefficient, combined with the start and end coordinates of the at least one virtual lane edge and the coordinates of each dividing point, the coordinates of each intersection point are obtained.

[0019] Optionally, when determining the intersection coordinates of the at least one virtual lane edge on the M dividing point connecting lines by combining the start and end coordinates of the at least one virtual lane edge and the coordinates of each dividing point, the drawing unit is used to:

[0020] For each virtual lane edge planned in the transition section, construct the intersection point with the M dividing points connecting the lines;

[0021] Using a convex optimization approach, by combining the start and end coordinates of the edge of the at least one virtual lane with the coordinates of each dividing point, the coordinates of the intersection points of the edges of the at least one virtual lane on the M dividing point connecting lines are determined when the constraints are satisfied.

[0022] Optionally, when the constraint conditions of smoothing the lane lines at the edge of the at least one virtual lane and ensuring that the lane line direction is consistent with the direction of the corresponding road segment are used, the drawing unit is used to:

[0023] In the intersections of the lines connecting the M dividing points constructed for each virtual lane edge, the total intersection distance between adjacent intersections is minimized, and the included angle between the intersections of every three adjacent intersections is constrained to approach a flat angle, so as to make the constructed lane lines smooth.

[0024] In the intersection of the lines connecting the edges of each virtual lane with the M dividing points, the direction of the intersection vectors at both ends of the virtual lane edge is constrained to be the same as the direction between the corresponding target road segments; the target road segments are either the first road segment or the second road segment.

[0025] Optionally, when constraining the intersections of the lines connecting the M dividing points to the edges of each virtual lane to minimize the total intersection distance between adjacent intersections and constraining the included angle between every three adjacent intersections to approach a straight angle, the drawing unit is used to:

[0026] For each virtual lane edge, perform the following operations: determine the intersection points of the virtual lane edge with every three adjacent dividing point connecting lines in the M dividing point connecting lines, and for each of the three obtained intersection points, obtain the corresponding sum vector by establishing an intersection vector pointing from the middle intersection point to the two side intersection points; and determine the intersection points with every two adjacent dividing point connecting lines in the M dividing point connecting lines, and for each of the two obtained intersection points, determine the corresponding intersection distance.

[0027] Establish the first constraint to minimize the total magnitude of each sum vector and the cumulative distance between each intersection point.

[0028] Optionally, when constraining the direction of the intersection vector at both ends of the virtual lane edge to be the same as the direction between the corresponding target road segments in the intersection points of the lines connecting the edges of each virtual lane and the M dividing points, the drawing unit is used to:

[0029] For each virtual lane edge, perform the following operations: determine the intersection of the two dividing point connecting lines at each edge of the M dividing point connecting lines constructed for a corresponding virtual lane edge, and construct two edge direction vectors corresponding to the virtual lane edge based on the two intersection points at each edge, and determine the inner product results between the two edge direction vectors and the vertical vector on the corresponding target road segment respectively;

[0030] Establish a second constraint to minimize the cumulative value of each inner product result.

[0031] Optionally, the first road segment and the second road segment include the same total number of single lanes, which is equal to two; after determining the start and end coordinates of the edge of at least one virtual lane planned in the transition road segment, and before determining the intersection coordinates of the at least one virtual lane edge on the M dividing point connecting lines, the drawing unit is further configured to:

[0032] For the M dividing point connecting lines, perform the following operations respectively: determine the intersection point of the virtual lane edge construction with the dividing point connecting line, and each dividing point determined by the dividing point connecting line as the lane positioning point, and obtain the distance difference result based on the positioning point distance between every two adjacent lane positioning points;

[0033] A third constraint is established to minimize the cumulative value of the distance difference results.

[0034] Optionally, the first road segment and the second road segment include the same total number of single lanes and more than two; after determining the start and end coordinates of the edge of at least one virtual lane planned in the transition road segment, and before determining the intersection coordinates of the at least one virtual lane edge on the M dividing point connecting lines, the drawing unit is further configured to:

[0035] For the M dividing point connecting lines, perform the following operations respectively: for each of the multiple virtual lane edges, construct each intersection point with a dividing point connecting line, and determine the intersection distance between each two adjacent intersection points;

[0036] A fourth constraint is established to minimize the cumulative value of the distance results at each intersection point.

[0037] Optionally, when dividing the two virtual side lines into M equal segments to obtain M connecting lines of the dividing points and the corresponding coordinates of the dividing points, the dividing unit is used for:

[0038] Obtain the preset M segmentation ratio values, and the length of each of the two virtual side lines;

[0039] Obtain the initial division points selected on the two virtual side lines respectively, wherein the two initial division points are located on the first endpoint connection line or the second endpoint connection line;

[0040] For each of the preset M segmentation ratio values, the following operations are performed: based on a segmentation ratio value and the lengths of the two virtual side lines, combined with the initial segmentation point, the segmentation point corresponding to the segmentation ratio value is located on the two virtual side lines, and the two segmentation points are connected to obtain the corresponding segmentation point connection line, and the coordinates of the segmentation point corresponding to the segmentation point connection line are determined.

[0041] Optionally, when locating the segmentation point corresponding to the segmentation ratio value on the two virtual side lines based on a segmentation ratio value and the respective side line lengths of the two virtual side lines, combined with the initial segmentation point, the segmentation unit is used for:

[0042] For the two virtual side lines, perform the following operations respectively:

[0043] Based on a segmentation ratio value and the edge length of a virtual side line, the segmentation length of the segmentation ratio value on the virtual side line is determined, and the distance from the corresponding initial segmentation point along the virtual side line is determined as the segmentation point of the segmentation length.

[0044] Optionally, after drawing the corresponding virtual lane lines based on the coordinates of each intersection point, the device further includes a sending unit, which is used to:

[0045] Receive a data acquisition request sent by the target object for a target path, wherein the target path includes the transition segment;

[0046] The virtual lane lines drawn for the transition section, along with other map data associated with the target path, will be sent to the target object.

[0047] Thirdly, an electronic device is proposed, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-described method when executing the computer program.

[0048] Fourthly, a computer-readable storage medium is proposed, on which a computer program is stored, which, when executed by a processor, implements the above-described method.

[0049] Fifthly, a computer program product is proposed, comprising a computer program that, when executed by a processor, implements the above-described method.

[0050] The beneficial effects of this application are as follows:

[0051] This application proposes a method, apparatus, electronic device, and storage medium for generating virtual lane lines. First, two virtual side lines are generated for a transition section between a first road segment and a second road segment, along with the endpoint coordinates of each single-lane line endpoint connecting the first and second road segments to the transition section. At least one of the first and second road segments contains multiple single lanes. Then, the first endpoint connection line and the second endpoint connection line are used as edge segmentation point connection lines, and the two virtual side lines are proportionally divided M times to obtain M segmentation point connection lines and their corresponding segmentation point coordinates. The first endpoint connection line and the second endpoint connection line are obtained based on the endpoints of each single-lane line on the first road segment and the endpoints of each single-lane line on the second road segment, respectively. Because M proportional divisions are performed, when connecting each segmentation point connection line, it can adapt to the length and curvature differences between the two virtual side lines, determining suitable segmentation points. Moreover, since the segmentation points are known points on the two virtual side lines, the coordinates of each segmentation point are known, providing a processing basis for subsequently determining the coordinate positions used to locate the virtual lane lines.

[0052] Next, based on the lane division of the first and second road segments and the endpoint coordinates of each single lane line, the start and end coordinates of at least one virtual lane edge planned in the transition segment are determined. Then, the smoothing of the lane line of at least one virtual lane edge and the consistency of the lane line direction with the corresponding road segment direction are used as constraints. Based on the start and end coordinates of at least one virtual lane edge and the coordinates of each dividing point, the intersection coordinates of at least one virtual lane edge on the M dividing point connection lines are determined. Based on the coordinates of each intersection point, the corresponding virtual lane line is drawn.

[0053] In this way, by using the M connecting lines of dividing points constructed between the two virtual side lines in the transition section, the area to be drawn virtual lane lines can be filled, transforming the problem of locating virtual lane lines into the problem of determining appropriate intersection points on each connecting line of dividing points. On the other hand, since the coordinates of the points on the two virtual side lines and the endpoints of the single lane lines are known, the coordinates of the intersection points can be effectively determined by using the constructed connecting lines of dividing points in combination with the preset constraints, thus achieving effective positioning of the virtual lane lines. In addition, since the preset constraints constrain the smoothness and direction of the lane lines, in scenarios where there are multiple single lanes on a road segment in at least one direction, virtual lane lines are generated from the edges of the virtual lanes between the single lanes in the transition section connecting the first and second road segments. This greatly improves the generation efficiency and quality of virtual lane lines. Moreover, it can generate virtual lane lines that meet the needs of road transitions as a whole, ensuring the overall presentation effect and accuracy of each virtual lane line. Attached Figure Description

[0054] Figure 1 This is a schematic diagram illustrating possible application scenarios in the embodiments of this application;

[0055] Figure 2 This is a schematic diagram illustrating the generation process of a virtual lane line in an embodiment of this application;

[0056] Figure 3 This is a schematic diagram illustrating a possible relationship between road segments in the same direction in an embodiment of this application;

[0057] Figure 4 This is a schematic diagram illustrating another feasible relationship between road segments in the same direction in the embodiments of this application;

[0058] Figure 5 This is a schematic diagram illustrating another possible relationship between road segments in the same direction in the embodiments of this application;

[0059] Figure 6 This is a schematic diagram illustrating another possible relationship between road segments in the same direction in the embodiments of this application;

[0060] Figure 7 This is a schematic diagram illustrating a possible relationship between road segments under different directional conditions in the embodiments of this application;

[0061] Figure 8 This is a schematic diagram illustrating another feasible relationship between road segments under different directional conditions in the embodiments of this application;

[0062] Figure 9 This is a schematic diagram illustrating another possible relationship between road segments under different directional conditions in the embodiments of this application;

[0063] Figure 10 This is a schematic diagram illustrating another possible relationship between road segments under different directional conditions in the embodiments of this application;

[0064] Figure 11 This is a schematic diagram illustrating the process of obtaining the M dividing point connection lines in an embodiment of this application;

[0065] Figure 12 This is a schematic diagram illustrating the planning effect of the virtual lane edge under the same direction in the implementation of this application;

[0066] Figure 13 This is a schematic diagram illustrating another planning effect of the virtual lane edge in the same direction scenario during the implementation of this application;

[0067] Figure 14 This is a schematic diagram illustrating another planning effect of the virtual lane edge in the same direction scenario during the implementation of this application;

[0068] Figure 15 This is a schematic diagram illustrating the planning effect of virtual lane edges under different directional conditions in the embodiments of this application;

[0069] Figure 16 This is a schematic diagram illustrating another planning effect of the virtual lane edge under different directional conditions in the embodiments of this application;

[0070] Figure 17 This is a schematic diagram illustrating another planning effect of the virtual lane edge under different directional conditions in the embodiments of this application;

[0071] Figure 18 This is a schematic diagram illustrating the process of determining the edge direction vector in an embodiment of this application;

[0072] Figure 19 This is a schematic diagram illustrating another virtual lane line generation process in an embodiment of this application;

[0073] Figure 20 This is a schematic diagram of the intersection point representation constructed in the embodiments of this application;

[0074] Figure 21 This is a schematic diagram illustrating the process of generating virtual lane lines at an intersection in an embodiment of this application;

[0075] Figure 22 This is a schematic diagram illustrating the process of generating virtual lane lines in an embodiment of this application;

[0076] Figure 23 This is a schematic diagram of the logical structure of the virtual lane line generation device in the embodiments of this application;

[0077] Figure 24 This is a schematic diagram of the hardware structure of an electronic device using an embodiment of this application;

[0078] Figure 25 This is a schematic diagram of the hardware structure of another electronic device using an embodiment of this application. Detailed Implementation

[0079] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of this application will be clearly and completely described below with reference to the accompanying drawings of the embodiments of this application. Obviously, the described embodiments are only some embodiments of the technical solutions of this application, and not all embodiments. Based on the embodiments recorded in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the technical solutions of this application.

[0080] The terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention described herein can be implemented in sequences other than those illustrated or described herein.

[0081] In this application embodiment, the terms "module" or "unit" refer to a computer program or part of a computer program that has a predetermined function and works with other related parts to achieve a predetermined goal, and can be implemented wholly or partially using software, hardware (such as processing circuitry or memory), or a combination thereof. Similarly, a processor (or multiple processors or memory) can be used to implement one or more modules or units. Furthermore, each module or unit can be part of an overall module or unit that includes the functionality of that module or unit.

[0082] The following explanations of some terms used in the embodiments of this application are provided to facilitate understanding by those skilled in the art.

[0083] A transition section refers to a road segment that connects a discontinuous first road segment and a second road segment. Alternatively, it can be understood as an intermediate road segment between two discontinuous road segments, where the directions of the first and second road segments can be the same or different. For example, a transition section is the intermediate road segment between the first and second road segments at an intersection. Taking the processing of map data generated based on real-world rail transit conditions as an example, in the real world, a transition section might correspond to a road segment at an intersection that connects two road segments without any physical lane lines marked; or, a transition section might correspond to a road segment at an intersection that connects two road segments but only has physical lane lines marked on both sides of the overall structure; or, a transition section might correspond to a road segment at an intersection that connects two road segments and has physical lane lines marked.

[0084] Virtual lane lines: In this embodiment of the application, virtual lane lines refer to lane lines drawn for the edges of virtual lanes planned in the transition section, wherein the total number of generated virtual lane lines is consistent with the number of planned virtual lane edges.

[0085] Virtual bike lane: refers to a bike lane in a transition section used to connect the bike lanes on the first section and the bike lanes on the second section; moreover, considering that in real rail transit scenarios, the bike lanes included in the transition section are usually not marked, the bike lanes in the transition section are called virtual bike lanes.

[0086] Virtual lane edge: refers to the lane edge that is planned and defined in the transition section to connect a single lane from the first section and the second section.

[0087] Virtual side lines: Specifically, there are two side lines. They refer to the side lines constructed in the transition section to connect the first and second road segments, without considering the single lanes within the road segment and taking the first and second road segments as a whole.

[0088] Single lane: refers to a lane that allows a single vehicle to travel in one direction.

[0089] Single lane endpoint: refers to the endpoint on the edge of a single lane; in this embodiment of the application, for the single lane endpoint on the first road segment, it refers to the edge endpoint of each single lane on the first road segment at the position where it connects with the transition road segment; similarly, for the single lane endpoint on the second road segment, it refers to the edge endpoint of each single lane on the second road segment at the position where it connects with the transition road segment.

[0090] First endpoint connection line: refers to the connection line used to connect the endpoints of each single lane line on the first road segment to the transition road segment.

[0091] Second endpoint connection line: refers to the connection line used to connect the endpoints of each single lane line on the second road segment and the transition road segment.

[0092] Dividing point connection line: refers to the connection line obtained by connecting two determined dividing points on two virtual side lines based on a dividing ratio value.

[0093] Data compilation: Raw map data is usually provided in the form of text files, such as geojson. Data compilation involves processing and refining the raw map data to generate more compact and easier-to-use binary files, which are then provided to upper-level applications (such as navigation, positioning, guidance, rendering, etc.). Therefore, data compilation is a crucial link between these processes.

[0094] The design concept of the embodiments of this application is briefly introduced below:

[0095] Under current technology, when drawing virtual lane lines, only the transition section between two single-vehicle road segments can be drawn to draw virtual lane lines that connect the edges of single lanes on the two single-vehicle road segments.

[0096] When drawing virtual lane lines, it is necessary to first obtain the center lane line corresponding to the transition section, and then extract the center position point on the center lane line to reflect the outline of the center lane line. At the same time, based on the actual side lane lines of the two single-vehicle road segments, the width information of the transition section connecting the two single-vehicle road segments is determined. Then, based on the determined center position point and the width information of the transition section, the side position point used to reflect the outline of the virtual side in the transition section is determined, and the corresponding virtual lane line is obtained based on the side position point. The virtual side is used to connect the edges of the single lanes on the two single-vehicle road segments.

[0097] However, the above-mentioned methods for generating virtual lane lines can only generate virtual lane lines between single lanes. Therefore, when generating virtual lane lines for transitional road sections connecting multiple lanes, it is necessary to split the multiple lanes into single lanes for processing. This makes the generation efficiency of virtual lane lines very low, and it is impossible to generate virtual lane lines that meet the needs of road transitions as a whole. It is difficult to guarantee the overall presentation effect and accuracy of each virtual lane line, which greatly affects the vehicle navigation effect.

[0098] In view of this, this application proposes a method, apparatus, electronic device, and storage medium for generating virtual lane lines. First, two virtual side lines generated for the transition section between a first road segment and a second road segment are obtained, along with the endpoint coordinates of each single-lane line endpoint connecting the first and second road segments to the transition section. At least one of the first and second road segments contains multiple single lanes. Then, the first endpoint connection line and the second endpoint connection line are used as dividing point connection lines at the edges, and the two virtual side lines are divided M times proportionally to obtain M dividing point connection lines and their corresponding dividing point coordinates. The first endpoint connection line and the second endpoint connection line are obtained based on the endpoints of each single-lane line on the first road segment and the endpoints of each single-lane line on the second road segment, respectively. Thus, because M times proportional division is performed, when connecting each dividing point connection line, it can adapt to the length and curvature differences of the two virtual side lines, determining suitable dividing points. Moreover, since the dividing points are points on the two known virtual side lines, the dividing point coordinates of each dividing point are known, providing a processing basis for subsequently determining the coordinate positions used to locate the virtual lane lines.

[0099] Next, based on the lane division of the first and second road segments and the endpoint coordinates of each single lane line, the start and end coordinates of at least one virtual lane edge planned in the transition segment are determined. Then, the smoothing of the lane line of at least one virtual lane edge and the consistency of the lane line direction with the corresponding road segment direction are used as constraints. Based on the start and end coordinates of at least one virtual lane edge and the coordinates of each dividing point, the intersection coordinates of at least one virtual lane edge on the M dividing point connecting lines are determined. Based on the coordinates of each intersection point, the virtual lane lines corresponding to each virtual lane edge are drawn.

[0100] In this way, by using the M connecting lines of dividing points constructed between the two virtual side lines in the transition section, the area to be drawn for the virtual lane lines can be filled, transforming the problem of locating the virtual lane lines into determining the appropriate intersection points on each connecting line of dividing points. On the other hand, since the coordinates of the points on the two virtual side lines and the endpoints of the single lane lines are known, the coordinates of the intersection points can be effectively determined by using the constructed connecting lines of dividing points in combination with the preset constraints, thus achieving effective positioning of the virtual lane lines. In addition, since the preset constraints constrain the smoothness and direction of the lane lines, in scenarios where there are multiple single lanes on a road segment in at least one direction, virtual lane lines are generated from the edges of the virtual lanes between the single lanes in the transition section connecting the first and second road segments. This greatly improves the generation efficiency and quality of virtual lane lines. Moreover, it can generate virtual lane lines that meet the needs of road transitions as a whole, ensuring the overall presentation effect and accuracy of each virtual lane line. This enables effective navigation guidance for vehicle travel in the transition section in specific business scenarios.

[0101] The preferred embodiments of this application are described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit this application. Furthermore, the embodiments and features in the embodiments of this application can be combined with each other without conflict.

[0102] See Figure 1 The diagram shown illustrates a possible application scenario in an embodiment of this application. This application scenario diagram includes a client device 110 and a processing device 120.

[0103] In feasible embodiments of this application, the processing device 120 can generate map data according to actual processing needs and corresponding to the rail transit environment of a specified area in the real world. Moreover, in the process of generating map data or updating and adjusting map data, the virtual lane line generation method claimed in this application can be adopted to generate corresponding virtual lane lines for each transition section. Considering that the total number of single lanes in the two sections connected by the transition section may be different, the total number of virtual lane lines generated for a transition section is at least one.

[0104] Furthermore, in response to a data acquisition request sent by the target object on the client device 110 for a target path, the processing device 120 can send map data associated with the target road segment to the client device 110, so that the client device 110 can provide vehicle driving navigation for the target object based on the obtained map data; or, in response to a data acquisition request triggered by the target object on the client device 110 for a target area, the processing device can send map data associated with the target area to the client device 110, so that the client device 110 can view the map data associated with the target area offline.

[0105] The request triggered by the target object can be initiated from any of the following applications: mini-program application, client application, and web application. This application does not impose any specific restrictions on this.

[0106] Client devices 110 include, but are not limited to, mobile phones, tablets, laptops, e-book readers, smart voice interaction devices, smart home appliances, vehicle terminals, aircraft, etc.

[0107] The processing device 120 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms.

[0108] In this embodiment, the client device 110 and the processing device 120 can communicate via a wired network or a wireless network. The following description focuses solely on the generation process of the virtual lane lines from the perspective of the processing device 120.

[0109] The following section provides an illustrative explanation of the virtual lane line generation process, considering potential application scenarios:

[0110] Application Scenario 1: In lane-level navigation scenarios, virtual lane lines are generated for intersections in real-world rail transit.

[0111] It should be noted that lane-level navigation is a technology that provides lane-level navigation information. Compared with traditional road-level navigation, lane-level navigation can provide more detailed location information, helping drivers to know their location more accurately and how to get to their destination. Moreover, lane-level navigation can achieve the following functions: providing precise turning instructions at complex intersections or ramps, helping drivers avoid entering prohibited lanes or missing exits, dynamically adjusting the best driving route according to real-time traffic conditions, and integrating with Advanced Driver Assistance Systems (ADAS) to help vehicles automatically change lanes and perform other operations.

[0112] In the processing corresponding to application scenario one, the processing device acquires map data of the corresponding real-world rail transit and determines the transition section to which the virtual lane line is generated in the map data. Depending on the actual processing needs, the virtual side line generated in the map data corresponding to the transition section can be added after acquiring the pre-built map data, or it can be carried in the pre-built map data. This application does not impose any specific restrictions on this.

[0113] Subsequently, the processing device can use the virtual lane line generation method claimed in this application to generate virtual lane lines for transitional road sections in the map data.

[0114] Furthermore, based on the reorganized map data, lane-level navigation path planning and vehicle trajectory simulation can be performed according to actual processing needs.

[0115] Application Scenario 2: In high-precision maps for autonomous driving, virtual lane lines are generated for intersections in real-world rail transit.

[0116] It's important to note that high-precision maps for autonomous driving are specifically designed for self-driving vehicles. Their accuracy is typically at the centimeter level, far exceeding that of traditional navigation maps. These high-precision maps contain a wealth of detailed information, such as lane boundaries, traffic signs, traffic light locations, and static obstacles, enabling autonomous vehicles to make accurate decisions.

[0117] In the processing of application scenario two, the processing device acquires a high-precision map of autonomous driving drawn from the real-world rail transit, and determines the transition section to which the virtual lane line is generated in the acquired map data. Depending on the actual processing needs, the virtual side line generated in the map data corresponding to the transition section can be added after acquiring the pre-built map data, or it can be carried in the pre-built map data.

[0118] Subsequently, the processing device can use the virtual lane line generation method claimed in this application to generate virtual lane lines for transitional road sections in the map data.

[0119] Furthermore, based on the reorganized map data, autonomous driving path planning algorithms and vehicle trajectory simulations can be developed according to actual processing needs.

[0120] In addition, it should be understood that the specific implementation of this application involves the generation process of virtual lane lines. When the embodiments described in this application are applied to specific products or technologies, the collection, use and processing of related data need to comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0121] The following description, with reference to the accompanying diagram, explains the process of generating virtual lane lines from the perspective of the processing device:

[0122] See Figure 2 As shown, this is a schematic diagram of the generation process of a virtual lane line in an embodiment of this application. The following is a detailed explanation in conjunction with the attached diagram. Figure 2 Taking the direct planning of the intersection coordinates determined for the virtual lane line as an example, the process of generating the virtual lane line is explained:

[0123] Step 201: The processing device acquires two virtual side lines generated for the transition section between the first road segment and the second road segment, as well as the endpoint coordinates of the endpoints of each single lane line connecting the first road segment and the transition section; at least one of the first road segment and the second road segment contains multiple single lanes.

[0124] In this embodiment of the application, when determining the road segment where virtual lane lines need to be drawn, the processing device determines the transition segment between the first road segment and the second road segment, and obtains two virtual side lines generated for the transition segment, wherein the first road segment and the second road segment refer to a road segment in one direction.

[0125] The two virtual sidelines acquired by the processing device can be generated by itself or pre-generated by other devices; this application does not impose any specific restrictions on this. Moreover, the coordinates of any point on the two virtual sidelines can be considered as known.

[0126] Among some feasible methods for generating two virtual side lines, the following operations can be performed for each set of side lines corresponding to the first and second road segments: determine the two single-lane lines corresponding to each set of side lines, determine the endpoints of the single-lane lines at the junction of the two single-lane lines and the transition road segment, and obtain the corresponding virtual side lines based on the endpoints of the two single-lane lines using Bézier curves or other feasible curve forms.

[0127] In other feasible implementations, given the known center lane line of the transition section, a center position point reflecting the outline of the center lane line can be extracted from the center lane line. Simultaneously, the width information of the transition section is determined based on the side lines of the first and second road segments as a whole. Furthermore, by leveraging the similarity between the virtual side of the transition section and the center lane line of the transition section—that is, the similarity between the outline of the virtual side of the transition section and the outline of the center lane line of the transition section—side position points reflecting the virtual side of the transition section are determined based on the center position point and the width of the transition section. The corresponding virtual side line can be obtained based on the side position points, wherein the virtual side is used to connect the sides of the first and second road segments in the transition section.

[0128] It should be noted that, in the embodiments of this application, the first road segment and the second road segment may have the same or different road segment directions, and this application does not impose specific restrictions on this; moreover, at least one of the first road segment and the second road segment contains multiple single lanes, and the total number of single lanes included in the first road segment and the second road segment may be the same or different; if the total number of single lanes included in the first road segment and the second road segment is different, the total number of single lanes in the first road segment may be greater than the total number of single lanes in the second road segment, or the total number of single lanes in the first road segment may be less than the total number of single lanes in the second road segment, and this application does not impose specific restrictions on this; in addition, for the first road segment and the second road segment, the side line of a single road segment as a whole can be understood as the lane line of a single lane at the upper edge of the road segment.

[0129] The following, with reference to the attached diagram, explains the possible relationships between the road segments (i.e., the first segment, the second segment, and the transition segment) when the first and second road segments have the same direction:

[0130] In some feasible embodiments of this application, where the total number of single lanes included in the first road segment and the second road segment is the same, see [reference]. Figure 3 As shown, this is a schematic diagram illustrating a possible relationship between road segments in the same direction in an embodiment of this application. The first road segment and the second road segment include the same total number of single lanes, and the road segments of the first and second road segments have the same direction. Every two adjacent single lanes share the same lane markings; according to the appendix... Figure 3 As shown in the diagram, the first and second road segments each include three single lanes. The driving direction of each single lane in a road segment is the same. The first and second road segments are not continuous. The endpoint coordinates of each single lane in the first and second road segments are known information. In addition, the transition road segment connects the first and second road segments.

[0131] In other feasible embodiments of this application, where the total number of single lanes included in the first road segment and the second road segment is the same, see [reference needed]. Figure 4As shown, this is a schematic diagram illustrating another feasible relationship between road segments in the same direction in an embodiment of this application. The first road segment and the second road segment include the same total number of single lanes, and the road segments of the first and second road segments are in the same direction. Each pair of adjacent single lanes does not share the same lane markings; according to the appendix... Figure 4 As shown in the diagram, the first and second road segments each include three single lanes, and the driving direction of each single lane in the first and second road segments is the same. The first and second road segments are not continuous, and the endpoint coordinates of each single lane line endpoint in the first and second road segments are known information. In addition, the transition road segment connects the first and second road segments.

[0132] In some feasible embodiments of this application, where the number of single lanes included in the first road segment and the second road segment are different, see [reference]. Figure 5 As shown, this is a schematic diagram illustrating another feasible relationship between road segments in the same direction in an embodiment of this application. The first road segment and the second road segment include different total numbers of single lanes, and the road segments of the first and second road segments have the same direction. Every two adjacent single lanes share the same lane markings; according to the appendix... Figure 5 As shown in the diagram, the first section includes three single lanes, the second section includes one single lane, and the driving direction of each single lane in the first and second sections is the same. The first and second sections are not continuous, and the endpoint coordinates of each single lane in the first and second sections are known information. In addition, the transition section connects the first and second sections.

[0133] In some further feasible embodiments of this application, where the number of single lanes included in the first road segment and the second road segment are different, see [reference needed]. Figure 6 As shown, this is a schematic diagram illustrating another feasible relationship between road segments in the same direction in an embodiment of this application. The first road segment and the second road segment include different total numbers of single lanes, and the road segments of the first and second road segments have the same direction. Every two adjacent single lanes do not share the same lane markings; according to the appendix... Figure 6 As shown in the diagram, the first section includes three single lanes, the second section includes one single lane, and the driving direction of each single lane in the first and second sections is the same. The first and second sections are not continuous, and the endpoint coordinates of each single lane in the first and second sections are known information. In addition, the transition section connects the first and second sections.

[0134] The following, with reference to the attached diagram, explains the possible relationships between the road segments (i.e., the first segment, the second segment, and the transition segment) when the road directions of the first and second segments are different:

[0135] In some feasible embodiments of this application, where the number of single lanes included in the first road segment and the second road segment is the same, see [reference]. Figure 7 As shown, this is a schematic diagram illustrating a possible relationship between road segments under different directional conditions in an embodiment of this application. Taking the perpendicular direction of the first and second road segments as an example, the first and second road segments include the same total number of single lanes, and every two adjacent single lanes share the same lane markings; according to the appendix... Figure 7 As shown in the diagram, the first and second road segments each include three single lanes, and the driving direction of each single lane in the first road segment is the same as that of each single lane in the second road segment; the first and second road segments are not continuous, and the endpoint coordinates of each single lane line endpoint in the first and second road segments are known information; in addition, the transition road segment connects the first and second road segments.

[0136] In other feasible embodiments of this application, where the number of single lanes included in the first road segment and the second road segment is the same, see [reference needed]. Figure 8 As shown, this is a schematic diagram illustrating another feasible relationship between road segments in the same direction in an embodiment of this application. Taking the perpendicular direction of the first and second road segments as an example, the first and second road segments include the same total number of single lanes, and no two adjacent single lanes share the same lane markings; according to the appendix... Figure 8 As shown in the diagram, the first and second road segments each include three single lanes, and the driving direction of each single lane in the first road segment is the same as that of each single lane in the second road segment; the first and second road segments are not continuous, and the endpoint coordinates of each single lane line endpoint in the first and second road segments are known information; in addition, the transition road segment connects the first and second road segments.

[0137] In some feasible embodiments of this application, where the number of single lanes included in the first road segment and the second road segment are different, see [reference]. Figure 9 As shown, this is a schematic diagram illustrating another feasible relationship between road segments under different directional conditions in this application embodiment. Taking the perpendicular direction of the first road segment and the second road segment as an example, the first road segment and the second road segment include different total numbers of single lanes, and every two adjacent single lanes share the same lane markings; according to the appendix... Figure 9 As shown in the diagram, the first road segment includes three single lanes, and the second road segment includes one single lane. The driving directions of all single lanes in the first road segment are the same, and the driving directions of all single lanes in the second road segment are the same. The first road segment and the second road segment are not continuous, and the endpoint coordinates of the endpoints of each single lane in the first road segment and the second road segment are known information. In addition, the transition road segment connects the first road segment and the second road segment.

[0138] In some further feasible embodiments of this application, where the number of single lanes included in the first road segment and the second road segment are different, see [reference needed]. Figure 10As shown, this is a schematic diagram illustrating another feasible relationship between road segments under different directional conditions in an embodiment of this application. Taking the perpendicular direction of the first road segment and the second road segment as an example, the first road segment and the second road segment include different total numbers of single lanes, and no two adjacent single lanes share the same lane markings; according to the appendix... Figure 10 As shown in the diagram, the first road segment includes three single lanes, and the second road segment includes one single lane. The driving directions of all single lanes in the first road segment are the same, and the driving directions of all single lanes in the second road segment are the same. The first road segment and the second road segment are not continuous, and the endpoint coordinates of the endpoints of each single lane in the first road segment and the second road segment are known information. In addition, the transition road segment connects the first road segment and the second road segment.

[0139] It should be understood that, in the implementation of this application, the appendix Figure 3-10 In the illustration, adjacent lanes may share lane lines, or they may not share lane lines. Moreover, when lane line smoothness and lane line direction are used as constraints in the future, whether lane lines are shared or not does not affect the generation principle of virtual lane lines. The following explanation will only take the case of lane lines being shared between lanes as an example. In addition, for the case where adjacent lanes do not share lane lines, it is not necessary to establish constraint relationships for the uniform distribution of lane lines in the future.

[0140] Step 202: The processing device uses the first endpoint connection line and the second endpoint connection line as the dividing point connection lines at the edge, and performs M equal-proportional divisions on the two virtual side lines to obtain M dividing point connection lines and the corresponding dividing point coordinates.

[0141] The first endpoint connection line and the second endpoint connection line are obtained based on the endpoints of each single lane line on the first road segment and the endpoints of each single lane line on the second road segment, respectively; M is a positive integer greater than 2.

[0142] When obtaining M dividing point connection lines, it is necessary to first determine M dividing ratio values, and then, for each dividing ratio value, obtain the corresponding dividing point connection line by connecting the dividing points determined on the two virtual side lines. The value of M is set according to the actual processing needs, and this application does not impose specific restrictions on it. It should be understood that the larger the value of M, the better the effect of drawing virtual lane lines in the future, and the more helpful it is to ensure the smoothness of virtual lane lines, but it will increase the difficulty of determining the coordinates of each intersection point to a certain extent.

[0143] Specifically, the processing device first obtains M preset segmentation ratio values ​​and the edge lengths of the two virtual side lines; then it obtains the initial segmentation points selected on the two virtual side lines, wherein the two initial segmentation points are located on the first endpoint connection line or the second endpoint connection line; then, for the M preset segmentation ratio values, it performs the following operations respectively: based on a segmentation ratio value and the edge lengths of the two virtual side lines, combined with the initial segmentation points, it locates a segmentation point corresponding to a segmentation ratio value on the two virtual side lines, connects the two segmentation points to obtain the corresponding segmentation point connection line, and determines the coordinates of the segmentation point corresponding to the segmentation point connection line.

[0144] It should be noted that since the first and second road segments may have the same or different road directions, the virtual side lines may be straight lines or curves. When the virtual side lines are curves, after determining the corresponding representation of the curve, the length of the curve can be calculated by means of integration, so that the length of each virtual side line can be determined. In particular, when the corresponding representation of the curve is uncertain, the length of the curve can be approximated by discretization methods, etc., which will not be specifically described in this application.

[0145] Furthermore, for the preset M segmentation ratio values, since the connecting lines of the segmentation points need to cover the connecting lines of the first endpoint and the second endpoint, the M segmentation ratio values ​​must include segmentation ratio values ​​with a value of 0 and segmentation ratio values ​​with a value of 1. Moreover, the M segmentation ratio values ​​can be selected uniformly, or selected according to a preset value selection rule, or specified by the relevant processing object. This application does not impose specific restrictions on this. Uniform selection means that the difference between any two adjacent segmentation ratio values ​​is the same. The preset value selection rule can constrain the value difference between adjacent segmentation ratio values, so that the specific value of the segmentation ratio can be determined based on the value difference. The relevant processing object can be the developer who instructs the map data generation.

[0146] When determining the initial points for segmentation, depending on the actual processing needs, the two intersections of the first endpoint connecting line and the two virtual side lines, i.e., the two endpoints of the outermost single lane lines on the first endpoint connecting line, can be selected as the two initial points for segmentation; or, the two intersections of the second endpoint connecting line and the two virtual side lines, i.e., the two endpoints of the outermost single lane lines on the second endpoint connecting line, can be selected as the two initial points for segmentation.

[0147] Taking the determination of two dividing points on two corresponding virtual sidelines corresponding to a dividing ratio as an example, the processing device can perform the following operations on the two virtual sidelines respectively: based on a dividing ratio and the edge length of a virtual sideline, determine the dividing length of a dividing ratio on a virtual sideline, and along a virtual sideline, determine the dividing point at a distance from the corresponding initial dividing point as the dividing length.

[0148] In determining the segmentation point along a virtual sideline, where the distance from the initial segmentation point is the segmentation length, and the virtual sideline is a curve, some feasible implementations, when the representation of the virtual sideline (i.e., the parametric curve of the virtual sideline) is known, can first establish an arc length formula to represent the arc length from the initial segmentation point to any point on the virtual sideline, and then determine the position of the segmentation point by solving the arc length formula. This application will not elaborate on this. In other feasible implementations, when the representation of the virtual sideline is unknown, the curve can first be discretized into a series of points, and then the Euclidean distance between each pair of adjacent points can be calculated. After that, the Euclidean distances of each adjacent point are accumulated starting from the initial segmentation point until the accumulated distance is close to a set value, and then the currently accumulated point is taken as a segmentation point. In still other feasible implementations, other methods that can determine the segmentation point can be used for processing, and this application will not specifically limit them.

[0149] It should be noted that in the embodiments of this application, the endpoint coordinates of each single lane line endpoint on the first road segment and the second road segment, as well as the two virtual side lines, are all represented in the same coordinate system. In addition, since the coordinates of each point on the two virtual side lines are known, the coordinates of the corresponding dividing point can be specifically determined after the dividing point is determined. Moreover, when generating virtual lane lines, the drawing is also completed in this coordinate system.

[0150] It should be understood that, in the embodiments of this application, proportional segmentation based on a proportional segmentation value means that, assuming a point is selected on a virtual sideline (assumed to be virtual sideline 1), the ratio of the distance from this point to the initial segmentation point on virtual sideline 1 (i.e., the curve distance calculated along virtual sideline 1) to the length of the edge of virtual sideline 1 is r. Then, a corresponding point is selected on another virtual sideline (assumed to be virtual sideline 2), such that the ratio of the distance from this point to the initial segmentation point on virtual sideline 2 (the curve distance calculated along virtual sideline 2) to the length of the edge of virtual sideline 2 is also r. Then, corresponding to the segmentation ratio value r, segmentation points can be determined on virtual sideline 1 and virtual sideline 2 respectively. After that, connecting the two determined segmentation points, a segmentation point connection line can be obtained.

[0151] In this way, for each segmentation ratio value, the proportion of the distance from the initial segmentation point to the length of the side line can be determined on the two virtual side lines, which are the segmentation points of the corresponding segmentation ratio value, so that proportional segmentation can be achieved along the virtual side lines.

[0152] Similarly, the processing device can obtain M dividing point connection lines for two virtual side lines based on M dividing ratio values, where the first endpoint connection line and the second endpoint connection line are dividing point connection lines at the two edges.

[0153] For example, see Figure 11 As shown, this is a schematic diagram of the process of obtaining M dividing point connection lines in an embodiment of this application. Taking the first road segment and the second road segment as having different road segment directions, and each of the first road segment and the second road segment containing the same number of single lanes as an example, assuming that the initial dividing point is determined on the second endpoint connection line, then as follows... Figure 11 As shown, initial segmentation point 1 is an initial segmentation point on one virtual side line, and initial segmentation point 2 is an initial segmentation point on another virtual side line. Then, the second endpoint connection line is the segmentation point connection line corresponding to the segmentation ratio value of 0, and the first endpoint connection line is the segmentation point connection line corresponding to the segmentation ratio value of 1. Furthermore, for each segmentation ratio value, segmentation points can be determined on the two virtual side lines respectively, and the corresponding segmentation point connection line can be obtained by connecting the two determined segmentation points.

[0154] In this way, based on the preset M segmentation ratio values, the two virtual side lines can be divided proportionally. Moreover, since each segmentation point is determined along the virtual side line, it can be evenly divided according to the curvature of the virtual side line. This allows the area between the two virtual side lines to be evenly filled by connecting the M segmentation points with known position information, providing a processing basis for determining the coordinates of each intersection point on the edge of the virtual lane.

[0155] Step 203: The processing device determines the start and end coordinates of at least one virtual lane edge planned in the transition section based on the lane division of the first and second road segments and the endpoint coordinates of each single lane line endpoint.

[0156] In this embodiment of the application, before drawing virtual lane lines in the transition section, it is necessary to first plan the virtual lane lines in the transition section. That is, plan the start and end coordinates of at least one virtual lane edge in the transition section. The start and end coordinates are used to define the coordinates of the two endpoints on the two virtual lane edges.

[0157] When the processing device determines the start and end coordinates of at least one virtual lane edge planned in the transition section, in some feasible embodiments, it can determine the total number of planned virtual lane edges and the start and end coordinates of each virtual lane edge according to the instructions of the relevant processing object; in other feasible embodiments, the processing device can automatically plan the total number of virtual lane edges and the start and end coordinates of each virtual lane edge when facing different transition sections according to the pre-set processing logic. The virtual lane edges are used to connect the single lanes that can be connected in the first section and the second section. For any virtual lane edge, the start and end coordinates of the virtual lane edge refer to the endpoints of the single lane lines of the first section and the second section that are connected.

[0158] It should be understood that in the embodiments of this application, the first road segment and the second road segment may have the same total number of single lanes, or they may have different total number of single lanes; moreover, in specific scenarios, the designated first road segment and the second road segment have a fixed driving direction (i.e., road segment direction), so the driving direction in the transition section is also fixed. In the technical solution claimed in this application, there is no specific restriction on the road segment direction of the first road segment and the second road segment; moreover, regardless of the total number of single lanes included in the first road segment and the second road segment, the number and approximate shape of the virtual lane edges can be planned, thereby providing a processing basis for drawing virtual lane lines for the corresponding virtual lane edges in the future.

[0159] Furthermore, since this application does not limit the total number of single lanes contained in the first and second road segments respectively, when the total number of single lanes in one road segment is 1 and the total number of single lanes in another road segment is 2, the corresponding total number of virtual lane edges is 1; when the total number of single lanes in one road segment is 1 and the total number of single lanes in another road segment is more than two, the corresponding total number of virtual lane edges is multiple; and when the total number of single lanes in both road segments is multiple, the corresponding total number of virtual lane edges is multiple. It is evident that the processing device determines at least one total number of virtual lane edges for the transition road segment.

[0160] For example, see Figure 12 As shown, this is a schematic diagram of the planning effect of virtual lane edges under the same direction in the implementation of this application. Assuming that the first and second road segments have the same direction, and that travel from the second road segment to the first road segment, adjacent lanes share the same lane markings in the map data. The first road segment includes a total of 3 lanes, and the second road segment includes a total of 1 lane. Therefore, based on the planning instructions from the rail transit department, the planning can be done as follows: Figure 12The diagram illustrates the edges of four virtual lanes. The start and end coordinates of each virtual lane edge are the endpoints of the single lane lines on the first and second road segments it connects to. This allows, in specific map navigation scenarios, the appropriate single lane to be selected for vehicles traveling from the second road segment to the first road segment based on the vehicle congestion situation in different single lanes of the first road segment.

[0161] For example, see Figure 13 As shown, this is a schematic diagram of another planning effect for the virtual lane edge under the same direction in the implementation of this application. Assuming the first and second road segments have the same direction, and the journey from the second road segment to the first road segment involves adjacent lanes sharing the same lane markings in the map data, and the first road segment has a total of 3 lanes while the second road segment includes 2 lanes; then, combined with the planning instructions from the rail transit department, the planning can be done as follows: Figure 13 The diagram shows the edges of three virtual lanes. The start and end coordinates of each virtual lane edge are the endpoints of the single lane lines on the first and second road segments it connects to.

[0162] For example, see Figure 14 As shown, this is a schematic diagram illustrating another planning effect of virtual lane edges in the same-direction scenario in this application. Assuming the first and second road segments have the same direction, and travel from the second segment to the first segment, adjacent lanes share the same lane lines in the map data. The first segment has a total of 3 lanes, and the second segment also includes 3 lanes. Therefore, given the same total number of lanes in both segments, the total number of virtual lane lines is: total number of lanes - 1. Based on the planning instructions from the rail transit department, a plan can be developed as follows: Figure 14 The diagram shows the edges of two virtual lanes. The start and end coordinates of each virtual lane edge are the endpoints of the single lane lines on the first and second road segments they connect.

[0163] For example, see Figure 15 As shown, this is a schematic diagram of the planning effect of virtual lane edges under different directional conditions in an embodiment of this application. Assuming the first and second road segments have different directions, and the journey from the second segment to the first segment involves adjacent lanes sharing the same lane lines in the map data, the first segment has a total of 3 lanes, and the second segment includes a total of 1 lane. Therefore, the following can be planned: Figure 15 The diagram illustrates the edges of four virtual lanes. The start and end coordinates of each virtual lane edge are the endpoints of the single lane lines on the first and second road segments it connects to. This allows, in specific map navigation scenarios, the appropriate single lane to be selected for vehicles traveling from the second road segment to the first road segment based on the vehicle congestion situation in different single lanes of the first road segment.

[0164] For example, see Figure 16As shown, this is a schematic diagram illustrating another planning effect of the virtual lane edge under different directional conditions in this application embodiment. Assuming the first and second road segments have different directions, and the journey from the second road segment to the first road segment involves adjacent lanes sharing the same lane markings in the map data, the first road segment has a total of 3 lanes, and the second road segment includes a total of 2 lanes; then, combined with the planning instructions from the rail transit department, the planning can be done as follows... Figure 16 The diagram shows the edges of three virtual lanes. The start and end coordinates of each virtual lane edge are the endpoints of the single lane lines on the first and second road segments it connects to.

[0165] For example, see Figure 17 As shown, this is a schematic diagram illustrating another planning effect of the virtual lane edge under different directional conditions in this application embodiment. Assuming the first and second road segments have different directions, and the journey from the second road segment to the first road segment involves adjacent lanes sharing the same lane lines in the map data, and the first road segment has a total of 3 lanes, while the second road segment also includes 3 lanes; then, in conjunction with the planning instructions from the rail transit department, the planning can be done as follows: Figure 17 The diagram shows the edges of two virtual lanes. The start and end coordinates of each virtual lane edge are the endpoints of the single lane lines on the first and second road segments they connect.

[0166] It should be noted that, in the embodiments of this application, the appendix... Figure 12-17 The proposed virtual lane edge planning effect is illustrated using only a few possible transitional road segment connections as examples. This demonstrates the planned virtual lane edge, allowing us to determine the total number of single lanes in each of the first and second road segments based on their lane divisions. This, in turn, enables us to determine the total number of virtual lane edges and the start and end coordinates of the virtual lane edges needed to connect single lanes in different road segments.

[0167] Step 204: The processing device uses the smoothing of the lane line of at least one virtual lane edge and the consistency of the lane line direction with the corresponding road segment direction as constraints. Combining the start and end coordinates of at least one virtual lane edge and the coordinates of each dividing point, it determines the intersection coordinates of at least one virtual lane edge on the M dividing point connection lines. Based on the coordinates of each intersection point, it draws the virtual lane line corresponding to each of the at least one virtual lane edge.

[0168] In some feasible implementations of this application, the processing device can use the smoothness of the lane line at the edge of a single virtual lane and the consistency of the lane line direction with the corresponding road segment direction as constraints to independently constrain the edge of a single lane line, thereby determining the intersection coordinates of the intersection point with the M dividing point connection lines for each virtual lane line edge.

[0169] Specifically, the processing device can constrain the total intersection distance between adjacent intersections in the intersections of the virtual lane edge and the M dividing point connecting lines, and constrain the included angle of every three adjacent intersections to approach a straight angle, so as to make the constructed lane lines smooth; in the intersections of the virtual lane edge and the M dividing point connecting lines, the device can constrain the direction of the intersection vector at both ends of the virtual lane edge to be the same as the direction between the corresponding target road segment; the target road segment is the first road segment or the second road segment.

[0170] The processing device, by constraining the angle between the intersections of every three adjacent intersections to ensure the smoothness of the constructed lane lines, can perform the following operations for each virtual lane edge: determine the intersections of the virtual lane edge with every three adjacent dividing point connecting lines among the M dividing point connecting lines, and for each of the three obtained intersections, obtain the corresponding sum vector by establishing an intersection vector pointing from the middle intersection point to the two side intersection points; determine the intersections with every two adjacent dividing point connecting lines among the M dividing point connecting lines, and determine the corresponding intersection distance for each of the two obtained intersections; and establish a first constraint condition to minimize the total magnitude of each sum vector and the cumulative value of each intersection distance.

[0171] Specifically, to achieve the smoothest possible lane lines, the processing device can constrain the sum of the squares of the distances between any two adjacent intersections defined for the virtual lane edge to be as small as possible, and the included angle between any three adjacent intersections to be as close to 180 degrees as possible. Adjacent intersections refer to the intersections between the constructed lines connecting adjacent dividing points. When constraining the intersection angle, a vector pointing from the middle intersection to the two outer intersections can be determined from among the three adjacent intersections. The sum of these two vectors is then obtained, and by minimizing the magnitude of the sum vector, the 180-degree intersection angle constraint is achieved.

[0172] Suppose we want to generate N virtual lane lines corresponding to the edges of N virtual lanes, and there are M dividing point connecting lines. Then the shape of these N virtual lane lines can be expressed as a matrix of size N×M, where each column of the matrix represents a virtual lane line and each row of the matrix represents a proportionally cut line.

[0173] Suppose that for any virtual lane edge j, the intersection points between any two adjacent lines connecting the virtual lane edge j to the M dividing points are denoted as follows: The value of i ranges from 1 to M-1.

[0174] Therefore, the following formula is used to constrain the intersection distance between every two adjacent intersection points and minimize the cumulative value of the intersection distances:

[0175]

[0176] in, The square of the intersection distance between any two adjacent intersection points is used to represent the total number of virtual lane edges and the total number of connecting lines of the dividing points. V1 is the cumulative value of the square of the intersection distance. By constraining V1, the cumulative value of the intersection distance can be constrained.

[0177] Furthermore, assuming any virtual lane edge j, each of its three adjacent intersection points is denoted as... The following formula can be used to constrain the included angle of any three adjacent intersection points to be as close to 180 degrees as possible. Assume: From... point to The vector is from point to The vector is and The sum vector between them is represented as When the angle between the intersection points is 180 degrees If the length of is as close to 0 as possible, then the following relationship can be established:

[0178]

[0179]

[0180] Where V2 refers to the sum of the squares of the magnitudes of each sum vector, and by constraining V2, the total magnitude of each sum vector can be constrained; N is the total number of virtual lane edges, and M is the total number of connecting lines of the dividing points.

[0181] Furthermore, the first constraint condition can be established by minimizing k1*V1+k2*V2, thereby minimizing the cumulative value of the total magnitude of each sum vector and the distance between each intersection point.

[0182] In this way, for the intersection of each constructed virtual lane edge and the N dividing point connecting lines, by constraining the intersection distance between every two adjacent intersections and the intersection angle between every three adjacent intersections, the lane line smoothing constraint can be achieved.

[0183] When the direction at both ends of a single virtual lane edge is consistent with the direction of the corresponding target road segment, the processing device can perform the following operations for each virtual lane edge: determine the intersection points of the two dividing point connecting lines at each edge of the M dividing point connecting lines constructed for a corresponding virtual lane edge, and construct two edge direction vectors corresponding to the virtual lane edge based on the two intersection points at each edge, and determine the inner product results between the two edge direction vectors and the vertical vector on the corresponding target road segment. Further, a second constraint condition is established to minimize the cumulative value of each inner product result.

[0184] It should be noted that in the embodiments of this application, the direction vector and vertical vector of the first road segment, as well as the direction vector and vertical vector of the second road segment, are known data. The direction vector refers to the vector corresponding to the direction of the road segment, and the direction vector and vertical vector of the same road segment are perpendicular to each other.

[0185] For example, see Figure 18 As shown, this is a schematic diagram of the process of determining the edge direction vector in an embodiment of this application. It is assumed that the first and second road segments each contain a total of 3 single lanes, and the total number of determined dividing point connecting lines is M; according to the appendix... Figure 18 As illustrated, assuming two virtual lane edges can be constructed, namely virtual lane edges 1 and 2, then when defining the edge direction for virtual lane edge 2, the connecting lines between the two dividing points at one edge are: dividing point connecting lines 1 and 2, and the connecting lines between the two dividing points at the other edge are: dividing point connecting lines M-1 and M. Furthermore, when determining the edge direction vector, the edge direction vector at one edge is obtained based on the intersections of dividing point connecting lines 1 and 2 with virtual lane edge 2, and the corresponding target road segment is the first road segment. Similarly, the edge direction vector at the other edge is obtained based on the intersections of dividing point connecting lines M-1 and M with virtual lane edge 2, and the corresponding target road segment is the second road segment.

[0186] In establishing constraints, assume that for any virtual lane edge j, the edge direction vector at one edge is... The edge vector at the other edge is Therefore, the edge direction of the virtual lane can be constrained using the following formula:

[0187]

[0188] in, Let J be the coordinates of the intersection point of line 2 connecting the dividing points at the edge and the virtual lane edge j; Let J be the coordinates of the intersection point of line 1 connecting the dividing points at the edge and the virtual lane edge j; Let M-1 be the coordinate of the intersection point of the dividing line M-1 at the edge and the virtual lane edge j; Let M be the coordinates of the intersection point of the dividing line M at the edge and the virtual lane edge j; It is the vertical vector of the target road segment corresponding to the dividing point connecting line 1 and 2; V1 is the vertical vector of the target road segment corresponding to the dividing point connecting line M-1 and M; V3 is the cumulative value of each inner product result, where the inner product result specifically refers to the square of the inner product. Additionally, it should be clarified that... and These are the endpoint coordinates of the two single-lane line endpoints determined by the virtual lane edge j, so the specific coordinates are known.

[0189] Based on this, the second constraint can be established by minimizing the value of V3.

[0190] In this way, by constraining the inner product between the edge direction vector of the virtual lane edge and the vertical vector of the corresponding target road segment, it is possible to ensure that the edge direction of the virtual lane edge is consistent with the road segment direction of the corresponding target road segment.

[0191] Based on this, by establishing constraints from the perspectives of lane line smoothness and lane line direction, constraints can be established starting from the edge of a single virtual lane, ensuring the generation effect of a single virtual lane line.

[0192] In some feasible embodiments of this application, lane line smoothness and lane line direction being consistent with the direction of the corresponding target road segment can be used as constraints. In this case, constraints can be established by minimizing the value of k1*V1+k2*V2+k3*V3. The values ​​of coefficients k1, k2, and k3 are set according to the actual processing needs. The larger the value of the coefficient, the more important the corresponding target is. For example, k1 is 10, k2 is 100, and k3 is 100.

[0193] Based on this, when determining the coordinates of the intersection point of at least one virtual lane edge on the connecting lines of M dividing points, the following formula can be used to solve the problem:

[0194]

[0195] in, The value of j is a fixed value determined based on known coordinates. The value of j ranges from 1 to N and is used to identify the edge of each virtual lane; i is used to indicate the connecting line of the dividing point.

[0196] Based on this, after constructing the intersection points with the M dividing point connection lines for each virtual lane edge planned in the transition section, the processing device can use convex optimization to combine the start and end coordinates of at least one virtual lane edge and the coordinates of each dividing point to determine the intersection point coordinates of the intersection points of at least one virtual lane edge with the M dividing point connection lines when the constraints are met.

[0197] Specifically, when solving the problem, the processing equipment can use open-source convex optimization libraries such as OperatorSplitting Quadratic Program (OSQP) or Interior Point Optimizer (IPOPT) to determine the coordinates of the intersection points of the lines connecting each split point to the edge of each constructed virtual lane.

[0198] It should be noted that the processing device transforms the solution of the intersection point coordinates into a convex optimization problem, so that the obtained local optimal solution is also the global optimal solution. Therefore, the solution results are the same each time, which can guarantee the stability of the results. At the same time, since convex optimization is supported by very mature mathematical theory, the solution speed is fast.

[0199] In this way, by using convex optimization to perform the calculation, the coordinates of each intersection point that meets the constraints can be effectively obtained, and the stability and accuracy of the results can be guaranteed.

[0200] In other feasible implementations of this application, when the total number of lanes in the first and second road segments is the same, in addition to constraining lane line smoothness and lane line direction to be consistent with the road segment direction of the corresponding target road segment, the uniform distribution of lane lines can be further constrained. Based on this, when the total number of lanes is different, there are the following two possible constraint situations:

[0201] Constraint 1: The total number of single lanes on the first and second road segments is the same and equal to two.

[0202] In the scenario indicated by constraint condition one, since both the first and second road segments include two single lanes, the total number of virtual lane edges is 1. Therefore, when constraining the uniformity of lane lines, the constraint can be set at the intersection point determined on the connection line of each dividing point, and the distance between the intersection point and the two dividing points on the connection line of that dividing point should be as small as possible.

[0203] Specifically, the processing device can perform the following operations for each of the M dividing point connection lines: the intersection point of the virtual lane edge construction with the dividing point connection line, and each dividing point determined by the dividing point connection line, are determined as lane positioning points, and the distance difference is obtained based on the positioning point distance between every two adjacent lane positioning points; then, a third constraint condition is established to minimize the cumulative value of each distance difference.

[0204] Specifically, the distance difference result can be the difference of the squares of the distances between the two positioning points.

[0205] Correspondingly, the constraint relationship corresponding to the third constraint condition can be represented by the following formula:

[0206]

[0207] Wherein, V4 is the constraint target obtained when the lane lines are uniformly distributed; Let i be the coordinates of a dividing point on the line connecting the dividing points. Let i be the coordinates of another dividing point on the line connecting the dividing points; and in this embodiment, the coordinates of each dividing point are known. The intersection of the line connecting the split point i, constructed for the edge of a virtual lane.

[0208] In this way, when planning virtual lane edges between road segments containing two single lanes, the uniform distribution of lane edges can be used as a constraint condition to establish constraint relationships.

[0209] Therefore, when obtaining the coordinates of each intersection point, the relevant constraint formula can be adjusted as follows:

[0210]

[0211] in, as well as For fixed values ​​determined based on known coordinates, j is used to identify the edges of each virtual lane; i is used to indicate the connecting lines of the dividing points.

[0212] Constraint Scenario 2: The total number of single lanes on the first and second road segments is the same and greater than two.

[0213] In the scenario indicated by constraint case two, since both the first and second road segments include more than two single lanes, the total number of virtual lane edges is at least two; therefore, when constraining the uniformity of lane lines, the distance between each intersection point determined on the connecting line of each dividing point can be constrained to be as small as possible.

[0214] Specifically, after the processing device determines the start and end coordinates of at least one virtual lane edge planned in the transition section, before determining the intersection coordinates of at least one virtual lane edge on the M dividing point connecting lines, it can also perform the following operations for the M dividing point connecting lines: for each of the multiple virtual lane edges, construct the intersection points with a dividing point connecting line, and determine the intersection distance between each pair of adjacent intersection points; then, establish a fourth constraint condition to minimize the cumulative value of the intersection distance results; wherein, the intersection distance result can be expressed as the square of the distance between intersection points.

[0215] Correspondingly, the constraint relationship indicated by the fourth constraint condition can be represented by the following formula:

[0216]

[0217] Where V5 is the constraint target obtained when the lane lines are uniformly distributed; j is used to identify the virtual lane edge; and i is used to indicate the connecting line of the dividing point. The x-coordinate of the intersection point of the virtual lane edge j and the line connecting the dividing point i; The x-coordinate of the intersection point of the virtual lane edge j+1 and the line connecting the dividing point i; The ordinate of the intersection point of the virtual lane edge j and the line connecting the dividing point i is represented; This represents the ordinate of the intersection point of the virtual lane edge j+1 and the line connecting the dividing point i.

[0218] In this way, when planning virtual lane edges between road segments containing more than two single lanes, the uniform distribution of lane edges can be used as a constraint condition to establish constraint relationships.

[0219] Therefore, when obtaining the coordinates of each intersection point, the relevant constraint formula can be adjusted as follows:

[0220]

[0221] in, For fixed values ​​determined based on known coordinates, j is used to identify the edges of each virtual lane; i is used to indicate the connecting lines of the dividing points.

[0222] It should be noted that in the embodiments of this application, k1, k2, k3, k4, and k5 are weight coefficients determined for different constraint objectives. The larger the coefficient, the more important the corresponding constraint objective is. The specific values ​​can be set according to the actual processing needs, such as k1=10, k2=100, k3=100, k4=1, and k5=1. That is, in the process of establishing constraints, priority is given to ensuring tangency in the front and rear directions and smooth lane lines.

[0223] Furthermore, for each virtual lane edge, the processing device obtains the intersection coordinates of the corresponding intersection points, locates each intersection point in a unified coordinate system, and obtains the corresponding virtual lane line for at least one virtual lane edge based on each intersection point. This application does not specifically limit the method of obtaining the virtual lane line based on each intersection point. Given the coordinates of each intersection point, this application can use various feasible fitting methods to fit the curve or straight line representation corresponding to each virtual lane line, thereby drawing the corresponding virtual lane line.

[0224] For example, feasible fitting methods include: least squares fitting, polynomial fitting, Bézier curve fitting, etc.

[0225] See Figure 19 As shown, this is a schematic diagram of another virtual lane line generation process in an embodiment of this application. The following is a detailed explanation in conjunction with the attached diagram. Figure 19Taking the determination of intersection coordinates for virtual lane lines as an example, the process of generating virtual lane lines is explained by first directly determining the relative position of the intersection point on the dividing line, and then indirectly determining the intersection coordinates based on the relative position:

[0226] Step 1901: The processing device acquires two virtual side lines generated for the transition section between the first road segment and the second road segment, as well as the endpoint coordinates of the endpoints of each single lane line connecting the first road segment and the transition section; at least one of the first road segment and the second road segment contains multiple single lanes.

[0227] Step 1902: The processing device uses the first endpoint connection line and the second endpoint connection line as the dividing point connection lines at the edge, and performs M equal-proportional divisions on the two virtual side lines to obtain M dividing point connection lines and the corresponding dividing point coordinates.

[0228] The first endpoint connection line and the second endpoint connection line are obtained based on the endpoints of each single lane line on the first road segment and the endpoints of each single lane line on the second road segment, respectively.

[0229] Step 1903: The processing device determines the start and end coordinates of at least one virtual lane edge planned in the transition section based on the lane division of the first and second road segments and the endpoint coordinates of each single lane line endpoint.

[0230] In this embodiment of the application, the processing procedures involved in steps 1901-1903 are the same as those proposed in steps 201-203, so they will not be described in detail here.

[0231] Step 1904: The processing device uses the smoothing of the lane line at least one virtual lane edge and the consistency of the lane line direction with the corresponding road segment direction as constraints, and performs the following operations for each dividing point connection line: constructs the intersection point with a dividing point connection line for each virtual lane edge planned in the transition segment in the form of a proportional coefficient of the straight-line distance from the reference point on the dividing point connection line to the total length of the dividing point connection line; the reference point is a dividing point indicated by the corresponding dividing point coordinates.

[0232] When the processing device executes step 1904, the constraints it needs to consider have the same constraint logic as those involved in step 204. However, when specifically representing the intersection coordinates of the constructed intersection points, the relative position of the intersection points on the corresponding dividing point connecting lines can be represented by corresponding scaling factors. This allows the coordinates of each intersection point to be indirectly determined simply by determining the scaling factor corresponding to each intersection point when determining the intersection points between the virtual lane edge and the dividing point connecting lines. Based on this, each intersection point determined for a virtual lane edge can be uniquely represented by an ordered array of values ​​located in the interval [0,1].

[0233] Furthermore, depending on the actual processing needs, the dividing point on the left side of the dividing point connecting line can be selected as the reference point; or, the dividing point on the right side of the dividing point connecting line can be selected as the corresponding reference point. This application does not impose specific restrictions on this. The following description only uses the dividing point on the left side of the dividing point connecting line as the reference point for illustrative purposes.

[0234] For example, see Figure 20 As shown, it is a schematic diagram of the intersection point representation constructed in the embodiments of this application, according to the appendix. Figure 20 As shown in the diagram, the leftmost dividing point on the line connecting the M dividing points (i.e., the point on the leftmost virtual side line) has a scale factor of 0, while the rightmost dividing point on the line connecting the M dividing points (i.e., the point on the rightmost virtual side line) has a scale factor of 1. Therefore... and The value of is 0. and The value of is 1. and The value of is determined based on the distance to the corresponding point. The distance to the corresponding dividing point is determined by the ratio of the distance to the total length of line 1 connecting the dividing points; similarly, and The value of is determined based on the distance to the corresponding point. The distance to the corresponding dividing point is determined by the ratio of the distance to the total length of the line connecting the dividing points M.

[0235] Therefore, to implement the constraint logic illustrated in step 204—namely, smooth lane lines and lane line directions consistent with the direction of the corresponding target road segment—the constraint relationship can be established as shown in the following formula:

[0236] Suppose that for the edge of the j-th virtual lane, the scaling factors corresponding to the intersections of its lines with the lines connecting its two adjacent dividing points (or its two adjacent intersections) are respectively... The coordinates of the corresponding intersection point are Therefore, the following relationship exists:

[0237]

[0238] in, Let i be the coordinates of the leftmost dividing point (i.e., the reference point) on the line connecting the dividing points; Let i be the coordinates of the rightmost dividing point on the line connecting the dividing points; Let i+1 be the coordinates of the leftmost dividing point (i.e., the reference point) on the dividing point connecting line i+1; Let i+1 be the coordinates of the rightmost dividing point on the line connecting the dividing points.

[0239] from arrive The square of the distance is expressed as:

[0240]

[0241] Since the coordinates of the dividing points on the M dividing point connecting lines are known, we can let... To simplify the known information, we have:

[0242]

[0243] Therefore, when constraining the intersection distance between any two adjacent intersection points and minimizing the cumulative value of the intersection distances, the following formula can be used:

[0244]

[0245] in, The square of the intersection distance between any two adjacent intersection points is used to represent the total number of virtual lane edges and the total number of connecting lines of the dividing points. V1 is the cumulative value of the square of the intersection distance. By constraining V1, the cumulative value of the intersection distance can be constrained.

[0246] In addition, in order to achieve smooth lane lines, besides requiring the length to be as small as possible, it is also desirable that the included angle between any three adjacent intersection points is as close to 180 degrees as possible.

[0247] Based on this, for the j-th (j=1,…,N) virtual lane edge, assume that the scaling factors corresponding to its three adjacent intersection points on the line connecting the three cutting points are as follows: The coordinates of the corresponding points are respectively The following relationship exists:

[0248]

[0249] from point to The vector is from point to The vector is Then we have:

[0250]

[0251] Since the coordinates of the dividing points on the M dividing point connecting lines are known, we can let: To simplify the known information, we have:

[0252]

[0253] Similarly, we have:

[0254]

[0255] After simplifying the known information, we have:

[0256]

[0257] In this embodiment of the application, in order to achieve and To make the included angle as close to 180 degrees as possible, we can require that the vectors... sum vector The sum of them is The module length should be as close to 0 as possible.

[0258] Therefore:

[0259]

[0260] make: Then we have:

[0261]

[0262] In order to make The length should ideally be 0, that is, we hope... To minimize it, we introduce the following objective function:

[0263]

[0264] Based on this, by constraining V 1' and V 2' The value of can establish the first constraint condition to minimize the cumulative value of the total magnitude of each sum vector and the distance between each intersection point.

[0265] In this embodiment of the application, when the directions at both ends of a single virtual lane edge are consistent with the direction of the corresponding target road segment, the processing device can perform the following operations for each virtual lane edge: determine the intersection points of the two dividing point connecting lines at each edge of the M dividing point connecting lines constructed for a virtual lane edge, and construct two edge direction vectors corresponding to the virtual lane edge based on the two intersection points at each edge, and determine the inner product results between the two edge direction vectors and the vertical vector on the corresponding target road segment. Further, a second constraint condition is established to minimize the cumulative value of each inner product result.

[0266] Specifically, suppose that for the j-th (j=1,…,N) virtual lane line, the ratio of its intersection with the line connecting two adjacent dividing points is respectively The coordinates of the corresponding point are Then from point to The vector is It can be represented as:

[0267]

[0268] For a virtual lane edge j, suppose the vertical vector of the target road segment at one of its edges is... The vertical vector of the target road segment at another edge is

[0269] To ensure that the directions of the constructed virtual lane lines are as tangent as possible at the connection points, it is desirable that the vector at one edge of the virtual lane is... and They should be as perpendicular as possible, meaning the square of their inner product should be as small as possible; similarly, we want the vector at the other edge of the virtual lane line to be... and If they are as perpendicular as possible, that is, if the square of their inner product is as small as possible, then the second constraint can be achieved using the following objective function:

[0270]

[0271] Based on this, when only lane line smoothness and lane line direction being consistent with the corresponding target road segment direction are used as constraints, k1*V can be minimized. 1′ +k2*V 2' +k3*V 3′ The values ​​of k1, k2, and k3 are used to establish constraints. The values ​​of the coefficients k1, k2, and k3 are set according to the actual processing needs. The larger the value of the coefficient, the more important the corresponding target is. For example, k1 is 10, k2 is 100, and k3 is 100.

[0272] In other feasible implementations of this application, when the total number of single lanes in the first road segment and the second road segment is the same, in addition to constraining the smoothness of the lane lines and the consistency of the lane line direction with the road segment direction of the corresponding target road segment, the uniform distribution of lane lines can be further constrained. Based on this, when the total number of single lanes is the same and equal to two, the processing device can use the constraint method corresponding to constraint case one in step 204 to process and obtain the constraint target for constraining the uniform distribution of lane lines. When the total number of single lanes in the first road segment and the second road segment is the same and greater than two, the uniform distribution of lane lines can be constrained using the following formula:

[0273] For the i-th (i = 1, ..., M) dividing point connecting line, assume that the scaling factor corresponding to the intersection point with the edges of two adjacent virtual lanes is... Then we can introduce the following objective function to represent the fourth constraint:

[0274]

[0275] This allows us to minimize the sum of the squares of any adjacent coordinates on the same proportional cutting line in order to achieve the goal of making the width of the virtual lane as uniform as possible.

[0276] Overall, in the embodiments of this application, when constraints are established based on the first constraint, the second constraint, and the third constraint, the constraint relationship is illustrated by the following formula:

[0277]

[0278]

[0279] To ensure that the virtual lane lines do not intersect each other, it is necessary to guarantee and It is strictly increasing, which means that a constraint equation is introduced:

[0280]

[0281] For the road portion entering the intersection, the scaling factors of each virtual lane edge at each intersection point on the first dividing line can be considered constants. Let these scaling factors be:

[0282]

[0283] For the road portion leaving the intersection, the scaling factors of each virtual lane edge at each intersection point on the last dividing line can be considered constants. Let these scaling factors be:

[0284]

[0285] Furthermore, in order to ensure that the final virtual lane lines connect with the corresponding lane lines on the preceding and following roads, it is necessary to constrain the connection relationship between the virtual lane edges and the single lane lines, and to introduce constraint equations:

[0286]

[0287] and

[0288]

[0289] Since the scaling factor at each dividing point on the left virtual side line is 0, the constraint equation is as follows:

[0290]

[0291] Similarly, the scaling factor of each dividing point on the right virtual side line is 1, therefore the constraint equation is:

[0292]

[0293] In this embodiment of the application, when constraints are established based on the first constraint, the second constraint, and the fourth constraint, the following constraint relationships exist:

[0294]

[0295]

[0296] st

[0297]

[0298] Step 1905: The processing device uses convex optimization to determine the proportional coefficient of the intersection point of at least one virtual lane edge with the M dividing point connection line when the constraint conditions are met. Based on each proportional coefficient, combined with the start and end coordinates of at least one virtual lane edge and the coordinates of each dividing point, the coordinates of each intersection point are obtained.

[0299] Specifically, the processing equipment, based on the actual processing needs and establishing constraint relationships according to the first and second constraints; or the first, second, and third constraints; or the first, second, and fourth constraints, can use convex optimization to solve for the proportional coefficients corresponding to each intersection point between the virtual lane edge and the M dividing point connection lines.

[0300] Then, based on the conversion formula between the proportional coefficient and the coordinates of the intersection point, the coordinates of the intersection point are determined.

[0301] For the edge of the j-th (j=1,…,N) virtual lane, assume that the scaling factor of its previous intersection point is... The corresponding coordinates in the orthogonal coordinate system are The following conversion relationships exist:

[0302] Suppose the starting point of a line connecting certain dividing points is... The destination is If i = 1, ..., M, then the length of the line connecting these dividing points is:

[0303]

[0304] Unit vector from the starting point to the ending point for:

[0305]

[0306] This leads to a transformation relationship from the scaling factor to the coordinates of the intersection point:

[0307]

[0308] In this way, the coordinates of the intersection point can be determined based on the proportional coefficient corresponding to the intersection point on the line connecting the dividing points, combined with the coordinate relationship on the line connecting the dividing points.

[0309] Step 1906: The processing device draws at least one virtual lane line corresponding to each virtual lane edge based on the coordinates of each intersection point.

[0310] For each virtual lane edge, the processing device obtains the intersection coordinates of the corresponding intersection points, locates each intersection point in a uniformly constructed coordinate system, and obtains the corresponding virtual lane line for at least one virtual lane edge based on each intersection point. This application does not specifically limit the method of obtaining the virtual lane line based on each intersection point. Given the coordinates of each intersection point, this application can use various feasible fitting methods to fit the curve or straight line representation of each virtual lane line, thereby drawing the corresponding virtual lane line.

[0311] For example, feasible fitting methods include: least squares fitting, polynomial fitting, Bézier curve fitting, etc.

[0312] Furthermore, in adopting Figure 2 or Figure 19 After the virtual lane lines are generated, the processing device can receive data acquisition requests sent by the target object for the target path, which includes transition sections. Then, the virtual lane lines drawn for the transition sections, as well as other map data associated with the target path, are sent to the target object.

[0313] Specifically, if the map data requested by the target object includes transitional road sections, the processing device can integrate and compile the virtual lane lines generated for the transitional road sections with the map data on other road sections in the target path before sending it to the target object.

[0314] In this way, based on the actual map data acquisition needs, the map data provided to the target object can include newly generated virtual lane lines for transition sections. This allows the target object to better present the map content on the target path with the help of the obtained map data, and to provide better navigation services in navigation scenarios.

[0315] The following description, in conjunction with the attached diagram, illustrates the process of generating virtual lane lines, using the example of generating virtual lane lines for the transition section at an intersection. The first and second sections connected by the transition section each include three single lanes.

[0316] See Figure 21As shown, this is a schematic diagram of the process of generating virtual lane lines at an intersection in an embodiment of this application. The following is a detailed explanation in conjunction with the attached diagram. Figure 21 The relevant generation process is explained below:

[0317] Step 2101: The processing device acquires the two roads entering and leaving the intersection.

[0318] Among them, the two roads correspond to the two road segments in the above-mentioned processing process.

[0319] Step 2102: The processing device obtains the virtual side line on the left and the virtual side line on the right at the intersection connecting the two roads.

[0320] Step 2103: The processing device uses M division ratio values ​​to divide the two virtual side lines proportionally, resulting in M ​​dividing point connection lines.

[0321] Step 2104: The processing device calculates the optimal position of each constructed virtual lane edge on the M dividing point connection line.

[0322] Specifically, the processing device establishes constraints and, given some known information, ultimately optimizes to obtain the optimal position of the intersection of the edges of each virtual lane on the connecting lines of the M dividing points, while satisfying the constraints.

[0323] Step 2105: The processing device generates virtual lane lines according to the optimal positions determined for each virtual lane edge.

[0324] Step 2106: The processing device forms virtual lanes based on adjacent virtual lane lines.

[0325] Specifically, by creating virtual lanes, it is possible to rationally plan drivable lanes in navigation scenarios.

[0326] See Figure 22 As shown, it is a schematic diagram of the process of generating virtual lane lines in an embodiment of this application. Figure 22 As shown, in the process of generating virtual lane lines, the first road segment and the second road segment, as well as the corresponding transition road segment connecting the first road segment and the second road segment, are first determined, and the virtual side line on the left and the virtual side line on the right are obtained. Then, M segmentation ratio values ​​are obtained, and the two virtual side lines are divided proportionally according to the M segmentation ratio values ​​to obtain M dividing point connection lines. Then, the intersection points of the virtual lane edge and the M dividing point connection lines are constructed, and the optimal position of each intersection point is obtained by establishing constraints and given conditions. Further, based on the determined optimal positions of each intersection point, the corresponding virtual lane lines are connected to obtain the virtual lane lines. Then, based on the virtual side lines and virtual lane lines generated for the transition road segment, virtual lanes 1-3 can be divided from the transition road segment.

[0327] Thus, by using the virtual lane line generation method proposed in this application, several virtual lane lines between two roads entering and exiting intersections can be generated simultaneously. Moreover, by incorporating the constraints of smooth, uniform, non-intersecting lane lines and tangent to the directions of entering and exiting intersections into the objective function and constraint equations, virtual lane lines can be automatically and quickly generated in various map data generation scenarios, improving the robustness of virtual lane line generation and adapting to complex scenarios, thereby improving the overall generation effect of virtual lane lines and greatly reducing the computational resources consumed in the virtual lane line generation process. Furthermore, the generated virtual lane lines can meet the following requirements as a whole: (1) as smooth as possible; (2) if there are multiple virtual lanes, the width of these virtual lanes should be as uniform as possible; (3) the virtual lane lines should be as consistent as possible with the directions of entering and exiting intersections; (4) if there are multiple virtual lanes, these lane lines should not intersect, provided that the total number of single lanes included in the first and second road segments is the same; (5) the virtual lane lines should connect the corresponding lane lines of the preceding and following roads (i.e., the first and second road segments).

[0328] Furthermore, in the virtual lane line generation logic proposed in this application, the intersection of a virtual lane edge and the connecting lines of each dividing point is first assumed. Then, by constraining and limiting the position of each intersection point, the optimal intersection point coordinates are finally determined. Based on this, a virtual lane line can be formed according to the intersection points determined on each connecting line of the dividing point.

[0329] Based on the same inventive concept, see [reference] Figure 23 As shown, this is a schematic diagram of the logical structure of the virtual lane line generation device in this embodiment of the application. The virtual lane line generation device 2300 includes an acquisition unit 2301, a segmentation unit 2302, a determination unit 2303, and a drawing unit 2304.

[0330] The acquisition unit 2301 is used to acquire two virtual side lines generated for the transition section between the first road segment and the second road segment, as well as the endpoint coordinates of the endpoints of each single lane line connecting the first road segment and the transition section; at least one of the first road segment and the second road segment contains multiple single lanes.

[0331] The segmentation unit 2302 is used to divide the two virtual side lines into M equal segments by using the first endpoint connection line and the second endpoint connection line as the segmentation point connection lines at the edge, respectively, to obtain M segmentation point connection lines and the corresponding segmentation point coordinates; the first endpoint connection line and the second endpoint connection line are obtained based on the endpoints of each single lane line on the first road segment and the endpoints of each single lane line on the second road segment, respectively, where M is a positive integer greater than 2;

[0332] The determining unit 2303 is used to determine the start and end coordinates of at least one virtual lane edge planned in the transition section based on the lane division of the first road segment and the second road segment, combined with the endpoint coordinates of each single lane line endpoint.

[0333] The drawing unit 2304 is used to smooth the lane lines of at least one virtual lane edge and use the lane line direction being consistent with the corresponding road segment direction as constraints. Combining the start and end coordinates of at least one virtual lane edge and the coordinates of each dividing point, it determines the intersection coordinates of at least one virtual lane edge on the M dividing point connection lines, and draws the virtual lane lines corresponding to each virtual lane edge based on the coordinates of each intersection point.

[0334] Optionally, by combining the start and end coordinates of at least one virtual lane edge and the coordinates of each dividing point, at least one virtual lane edge is determined. When the coordinates of the intersection point on the connecting lines of the M dividing points are determined, the drawing unit 2304 is used for:

[0335] For each dividing point connecting line, perform the following operations: construct the intersection point with a dividing point connecting line for each virtual lane edge planned in the transition section, in the form of a proportional coefficient of the straight-line distance from the reference point on a dividing point connecting line to the total length of the dividing point connecting line; the reference point is a dividing point indicated by the corresponding dividing point coordinates.

[0336] Using convex optimization, the proportional coefficient of the intersection point of at least one virtual lane edge with the M dividing point connection line is determined when the constraint conditions are met. Based on each proportional coefficient, combined with the start and end coordinates of at least one virtual lane edge and the coordinates of each dividing point, the coordinates of each intersection point are obtained.

[0337] Optionally, by combining the start and end coordinates of at least one virtual lane edge and the coordinates of each dividing point, at least one virtual lane edge is determined. When the coordinates of the intersection point on the connecting lines of the M dividing points are determined, the drawing unit 2304 is used for:

[0338] For each virtual lane edge planned in the transition section, construct the intersection point with the M dividing point connection lines;

[0339] By employing a convex optimization approach, and combining the start and end coordinates of at least one virtual lane edge with the coordinates of each segmentation point, the coordinates of the intersection points of at least one virtual lane edge on the M segmentation point connection lines are determined to satisfy the constraints.

[0340] Optionally, when the constraints are smoothing of the lane line at least one virtual lane edge and the lane line direction being consistent with the corresponding road segment direction, the drawing unit 2304 is used for:

[0341] In the intersection of the lines connecting the edges of each virtual lane with the M dividing points, the total intersection distance between adjacent intersections is minimized, and the included angle between the intersections of every three adjacent intersections is constrained to approach a flat angle, so as to make the constructed lane lines smooth.

[0342] For each virtual lane edge, the intersection points with the M dividing points are constructed, and the direction of the intersection vectors at both ends of the virtual lane edge is constrained to be the same as the direction between the corresponding target road segments; the target road segments are the first road segment or the second road segment.

[0343] Optionally, among the intersections of the lines connecting the edges of each virtual lane to the M dividing points, the drawing unit 2304 is used to minimize the total intersection distance between adjacent intersections and to ensure that the included angle between every three adjacent intersections approaches a straight angle.

[0344] For each virtual lane edge, perform the following operations: determine the intersection points of the virtual lane edge with every three adjacent dividing point connecting lines in the M dividing point connecting lines, and for each of the three obtained intersection points, obtain the corresponding sum vector by establishing an intersection vector pointing from the middle intersection point to the two side intersection points; and determine the intersection points with every two adjacent dividing point connecting lines in the M dividing point connecting lines, and for each of the two obtained intersection points, determine the corresponding intersection distance;

[0345] Establish the first constraint to minimize the total magnitude of each sum vector and the cumulative distance between each intersection point.

[0346] Optionally, in the intersection points of the lines connecting the edges of each virtual lane and the M dividing points, the direction of the intersection vectors at both ends of the virtual lane edge is constrained to be the same as the direction between the corresponding target road segments. The drawing unit 2304 is then used for:

[0347] For each virtual lane edge, perform the following operations: determine the intersection of the two dividing point lines at each edge of the M dividing point lines constructed for a corresponding virtual lane edge, and construct two edge direction vectors corresponding to the virtual lane edge based on the two intersection points at each edge, and determine the inner product results between the two edge direction vectors and the vertical vector on the corresponding target road segment respectively.

[0348] Establish a second constraint to minimize the cumulative value of each inner product result.

[0349] Optionally, the first and second road segments include the same total number of single lanes, which is equal to two; after determining the start and end coordinates of at least one virtual lane edge planned in the transition segment, and before determining the intersection coordinates of at least one virtual lane edge on the M dividing point connection lines, the drawing unit 2304 is also used for:

[0350] For M dividing point connecting lines, perform the following operations respectively: determine the intersection point of the virtual lane edge construction with a dividing point connecting line, and each dividing point determined by the dividing point connecting line as the lane positioning point, and obtain the distance difference result for the positioning point distance between every two adjacent lane positioning points;

[0351] A third constraint is established to minimize the cumulative value of the distance difference results.

[0352] Optionally, the first and second road segments include the same total number of single lanes and more than two; after determining the start and end coordinates of at least one virtual lane edge planned in the transition segment, and before determining the intersection coordinates of at least one virtual lane edge on the M dividing point connection lines, the drawing unit 2304 is also used for:

[0353] For each of the M dividing point connecting lines, perform the following operations: For each of the multiple virtual lane edges, construct the intersection points with a dividing point connecting line, and determine the intersection distance between each pair of adjacent intersection points;

[0354] A fourth constraint is established to minimize the cumulative value of the distance results at each intersection point.

[0355] Optionally, when dividing the two virtual side lines into M equal segments to obtain M connecting lines of the dividing points and the corresponding coordinates of the dividing points, the dividing unit 2302 is used for:

[0356] Obtain the preset M segmentation ratio values, and the length of each of the two virtual side lines;

[0357] Obtain the initial division points selected on the two virtual side lines respectively, wherein the two initial division points are located on the first endpoint connection line or the second endpoint connection line;

[0358] For each of the preset M segmentation ratio values, perform the following operations: Based on a segmentation ratio value and the lengths of the two virtual side lines, and combined with the initial segmentation point, locate the segmentation point corresponding to the segmentation ratio value on each of the two virtual side lines, connect the two segmentation points to obtain the corresponding segmentation point connection line, and determine the coordinates of the segmentation point corresponding to the segmentation point connection line.

[0359] Optionally, when locating a segmentation point corresponding to the segmentation ratio on each of the two virtual side lines based on a segmentation ratio value and the lengths of the respective side lines, combined with the initial segmentation point, the segmentation unit 2302 is used to:

[0360] For the two virtual sidelines, perform the following operations respectively:

[0361] Based on a segmentation ratio and the length of a virtual side line, determine the segmentation length of the segmentation ratio on a virtual side line, and along a virtual side line, determine the segmentation point at the distance from the corresponding initial segmentation point as the segmentation length.

[0362] Optionally, after drawing the corresponding virtual lane lines based on the coordinates of each intersection point, the device further includes a sending unit, which is used for:

[0363] Receive data acquisition requests sent by the target object for the target path, wherein the target path includes transitional road segments;

[0364] The virtual lane lines drawn for the transition section, along with other map data associated with the target path, will be sent to the target object.

[0365] For ease of description, the above sections are divided into modules (or units) according to their functions and described separately. Of course, in implementing this application, the functions of each module (or unit) can be implemented in one or more software or hardware components.

[0366] Having introduced the virtual lane line generation method and apparatus according to exemplary embodiments of this application, we will now introduce an electronic device according to another exemplary embodiment of this application.

[0367] Those skilled in the art will understand that various aspects of this application can be implemented as a system, method, or program product. Therefore, various aspects of this application can be specifically implemented in the following forms: a completely hardware implementation, a completely software implementation (including firmware, microcode, etc.), or a combination of hardware and software implementations, collectively referred to herein as a "circuit," "module," or "system."

[0368] Based on the same inventive concept as the above-described method embodiments, this application also provides an electronic device. See reference... Figure 24 As shown, it is a schematic diagram of the hardware composition structure of an electronic device applying an embodiment of this application. In one embodiment, the electronic device may be... Figure 1 The processing device 120 is shown. In this embodiment, the electronic device can be structured as follows: Figure 24 As shown, it includes a memory 2401, a communication module 2403, and one or more processors 2402.

[0369] The memory 2401 is used to store computer programs executed by the processor 2402. The memory 2401 may mainly include a program storage area and a data storage area. The program storage area may store the operating system and programs required to run instant messaging functions, etc.; the data storage area may store various instant messaging information and operation instruction sets, etc.

[0370] Memory 2401 may be volatile memory, such as random-access memory (RAM); memory 2401 may also be non-volatile memory, such as read-only memory, flash memory, hard disk drive (HDD), or solid-state drive (SSD); or memory 2401 may be any other medium capable of carrying or storing a desired computer program having the form of instructions or data structures and accessible by a computer, but is not limited thereto. Memory 2401 may be a combination of the above-described memories.

[0371] Processor 2402 may include one or more central processing units (CPUs) or digital processing units, etc. Processor 2402 is used to implement the above-described method for generating virtual lane lines when it calls the computer program stored in memory 2401.

[0372] The communication module 2403 is used to communicate with client devices and servers.

[0373] This application embodiment does not limit the specific connection medium between the memory 2401, communication module 2403, and processor 2402. This application embodiment... Figure 24 The memory 2401 and the processor 2402 are connected via a bus 2404, and the bus 2404 is in Figure 24 The diagram uses thick lines to describe the connections between other components; these are for illustrative purposes only and should not be considered limiting. The 2404 bus can be divided into address bus, data bus, control bus, etc. For ease of description, Figure 24 It is described using only a thick line, but does not indicate that there is only one bus or one type of bus.

[0374] The memory 2401 stores a computer storage medium containing computer-executable instructions for implementing the virtual lane line generation method of this application embodiment. The processor 2402 is used to execute the aforementioned virtual lane line generation method, such as... Figure 2 As shown.

[0375] In another embodiment, the electronic device may also be other electronic devices, see [reference]. Figure 25 As shown, it is a schematic diagram of the hardware composition structure of another electronic device applying the embodiments of this application. The electronic device may specifically be... Figure 1 The client device 110 is shown. In this embodiment, the electronic device can be structured as follows: Figure 25 As shown, it includes components such as: communication component 2510, memory 2520, display unit 2530, camera 2540, sensor 2550, audio circuit 2560, Bluetooth module 2570, processor 2580, etc.

[0376] The communication component 2510 is used to communicate with the server. In some embodiments, it may include a Circuit-Wireless Fidelity (WiFi) module, which is a short-range wireless transmission technology. Electronic devices can use the WiFi module to help users send and receive information.

[0377] The memory 2520 can be used to store software programs and data. The processor 2580 executes various functions of the client device 110 and performs data processing by running the software programs or data stored in the memory 2520. In this application, the memory 2520 can store the operating system and various application programs, and can also store computer programs related to the virtual lane line generation method of the embodiments of this application.

[0378] The display unit 2530 can also be used to display information input by the user or information provided to the user, as well as various menus of the client device 110, in a graphical user interface (GUI). Specifically, the display unit 2530 may include a display screen 2532 disposed on the front of the client device 110. The display unit 2530 can be used to display pages, etc.

[0379] The display unit 2530 can also be used to receive input digital or character information and generate signal inputs related to user settings and function control of the client device 110. Specifically, the display unit 2530 may include a touch screen 2531 disposed on the front of the client device 110, which can collect touch operations of the user on or near it.

[0380] The touchscreen 2531 can be placed over the display screen 2532, or the touchscreen 2531 and the display screen 2532 can be integrated to realize the input and output functions of the client device 110. After integration, it can be referred to as a touch display screen. In this application, the display unit 2530 can display the application program and the corresponding operation steps.

[0381] Camera 2540 can be used to capture still images, which users can then post comments on via an application. An object is projected onto a photosensitive element through a lens, generating an optical image. This photosensitive element can be a charge-coupled device (CCD) or a complementary metal-oxide-semiconductor (CMOS) phototransistor. The photosensitive element converts the light signal into an electrical signal, which is then transmitted to processor 2580 to be converted into a digital image signal.

[0382] The client device may also include at least one sensor 2550, such as an accelerometer 2551, a proximity sensor 2552, a fingerprint sensor 2553, and a temperature sensor 2554. The client device may also be configured with other sensors such as a gyroscope, barometer, hygrometer, thermometer, infrared sensor, light sensor, and motion sensor.

[0383] Audio circuitry 2560, speaker 2561, and microphone 2562 provide an audio interface between the user and client device 110. Audio circuitry 2560 converts received audio data into electrical signals and transmits them to speaker 2561, where speaker 2561 converts them into sound signals for output. Conversely, microphone 2562 converts collected sound signals into electrical signals, which are then received by audio circuitry 2560, converted back into audio data, and output to communication component 2510 for transmission to, for example, another client device 110, or to memory 2520 for further processing.

[0384] The Bluetooth module 2570 is used to exchange information with other Bluetooth devices that have Bluetooth modules via the Bluetooth protocol.

[0385] The processor 2580 is the control center of the client device, connecting various parts of the terminal via various interfaces and lines. It executes software programs stored in the memory 2520 and calls data stored in the memory 2520 to perform various functions and process data for the client device. In some embodiments, the processor 2580 may include at least one processing unit; the processor 2580 may also integrate an application processor and a baseband processor. In this application, the processor 2580 can run an operating system, applications, user interface display and touch response, and methods related to the generation of virtual lane lines in the embodiments of this application. Furthermore, the processor 2580 is coupled to the display unit 2530.

[0386] In some possible implementations, various aspects of the virtual lane line generation method provided in this application can also be implemented as a program product, which includes a computer program. When the program product is run on an electronic device, the computer program causes the electronic device to perform the steps in the virtual lane line generation method according to the various exemplary embodiments of this application described above. For example, the electronic device can perform actions such as... Figure 2 The steps are shown in the figure.

[0387] The program product may employ any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of readable storage media include: electrical connections having one or more wires, portable disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0388] The program product of the embodiments of this application may employ a portable compact disc read-only memory (CD-ROM) and include a computer program, and may run on an electronic device. However, the program product of this application is not limited thereto. In this document, the readable storage medium may be any tangible medium that contains or stores a program that may be used by or in conjunction with a command execution system, apparatus, or device.

[0389] A readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying a readable computer program. This propagated data signal may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable signal medium may also be any readable medium other than a readable storage medium, capable of sending, propagating, or transmitting a program for use by or in conjunction with a command execution system, apparatus, or device.

[0390] Computer programs contained on readable media may be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination thereof.

[0391] Computer programs for performing the operations of this application can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java and C++, and conventional procedural programming languages ​​such as C or similar languages. The computer program can execute entirely on the user's electronic device, partially on the user's electronic device, as a standalone software package, partially on the user's electronic device and partially on a remote electronic device, or entirely on a remote electronic device or server. In cases involving remote electronic devices, the remote electronic device can be connected to the user's electronic device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external electronic device (e.g., via the Internet using an Internet service provider).

[0392] It should be noted that although several units or sub-units of the device have been mentioned in the detailed description above, this division is merely exemplary and not mandatory. In fact, according to embodiments of this application, the features and functions of two or more units described above can be embodied in one unit. Conversely, the features and functions of one unit described above can be further divided and embodied by multiple units.

[0393] Furthermore, although the operations of the method of this application are described in a specific order in the accompanying drawings, this does not require or imply that these operations must be performed in that specific order, or that all the operations shown must be performed to achieve the desired result. Additionally or alternatively, certain steps may be omitted, multiple steps may be combined into one step, and / or one step may be broken down into multiple steps.

[0394] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing a computer-usable computer program.

[0395] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, produce a machine for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0396] Although preferred embodiments of this application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of this application.

[0397] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. A method for generating virtual lane lines, characterized in that, include: Obtain two virtual side lines generated for the transition section between the first road segment and the second road segment, as well as the endpoint coordinates of the endpoints of each single lane line connecting the first road segment and the second road segment to the transition section; at least one of the first road segment and the second road segment contains multiple single lanes; The first endpoint connection line and the second endpoint connection line are respectively used as the dividing point connection lines at the edge. The two virtual side lines are divided into M equal proportions to obtain M dividing point connection lines and corresponding dividing point coordinates. The first endpoint connection line and the second endpoint connection line are obtained based on the endpoints of each single lane line on the first road segment and the endpoints of each single lane line on the second road segment, respectively. M is a positive integer greater than 2. Based on the lane division of the first and second road segments, and combined with the endpoint coordinates of each single lane line endpoint, determine the start and end coordinates of the edge of at least one virtual lane planned in the transition segment. Using the smoothing of the lane lines of the at least one virtual lane edge and the consistency of the lane line direction with the corresponding road segment direction as constraints, and combining the start and end coordinates of the at least one virtual lane edge and the coordinates of each dividing point, the intersection coordinates of the at least one virtual lane edge on the M dividing point connecting lines are determined respectively, and the virtual lane lines corresponding to each of the at least one virtual lane edge are drawn according to the coordinates of each intersection point.

2. The method as described in claim 1, characterized in that, The step of determining the intersection coordinates of the at least one virtual lane edge on the M connecting lines of the dividing points by combining the start and end coordinates of the at least one virtual lane edge and the coordinates of each dividing point includes: For each dividing point connecting line, perform the following operations: construct intersection points with each dividing point connecting line for each virtual lane edge planned in the transition section, in the form of a proportional coefficient of the straight-line distance from the reference point on the dividing point connecting line to the total length of the dividing point connecting line; the reference point is a dividing point indicated by the corresponding dividing point coordinates. Using a convex optimization approach, the proportional coefficient of the intersection point of the at least one virtual lane edge on the M dividing point connection line is determined when the constraint conditions are met. Based on each proportional coefficient, combined with the start and end coordinates of the at least one virtual lane edge and the coordinates of each dividing point, the coordinates of each intersection point are obtained.

3. The method as described in claim 1, characterized in that, The step of determining the intersection coordinates of the at least one virtual lane edge on the M connecting lines of the dividing points by combining the start and end coordinates of the at least one virtual lane edge and the coordinates of each dividing point includes: For each virtual lane edge planned in the transition section, construct the intersection point with the M dividing points connecting the lines; Using a convex optimization approach, by combining the start and end coordinates of the edge of the at least one virtual lane with the coordinates of each dividing point, the coordinates of the intersection points of the edges of the at least one virtual lane on the M dividing point connecting lines are determined when the constraints are satisfied.

4. The method as described in claim 1, characterized in that, The constraint conditions include smoothing the lane lines at the edge of the at least one virtual lane and ensuring that the lane line direction is consistent with the direction of the corresponding road segment. In the intersections of the lines connecting the M dividing points constructed for each virtual lane edge, the total intersection distance between adjacent intersections is minimized, and the included angle between the intersections of every three adjacent intersections is constrained to approach a flat angle, so as to make the constructed lane lines smooth. In the intersection of the lines connecting the edges of each virtual lane with the M dividing points, the direction of the intersection vectors at both ends of the virtual lane edge is constrained to be the same as the direction between the corresponding target road segments; the target road segments are either the first road segment or the second road segment.

5. The method as described in claim 4, characterized in that, The constraint, which involves constructing lines connecting the edges of each virtual lane to the M dividing points, minimizes the total intersection distance between adjacent intersections and ensures that the included angle between every three adjacent intersections approaches a straight angle, includes: For each virtual lane edge, perform the following operations: determine the intersection points of the virtual lane edge with every three adjacent dividing point connecting lines in the M dividing point connecting lines, and for each of the three obtained intersection points, obtain the corresponding sum vector by establishing an intersection vector pointing from the middle intersection point to the two side intersection points; and determine the intersection points with every two adjacent dividing point connecting lines in the M dividing point connecting lines, and for each of the two obtained intersection points, determine the corresponding intersection distance. Establish the first constraint to minimize the total magnitude of each sum vector and the cumulative distance between each intersection point.

6. The method as described in claim 4, characterized in that, The step of constraining the direction of the intersection vector at both ends of the virtual lane edge, among the intersection points of the lines connecting the M dividing points constructed for each virtual lane edge, to be the same as the direction between the corresponding target road segments includes: For each virtual lane edge, perform the following operations: determine the intersection of the two dividing point connecting lines at each edge of the M dividing point connecting lines constructed for a corresponding virtual lane edge, and construct two edge direction vectors corresponding to the virtual lane edge based on the two intersection points at each edge, and determine the inner product results between the two edge direction vectors and the vertical vector on the corresponding target road segment respectively; Establish a second constraint to minimize the cumulative value of each inner product result.

7. The method according to any one of claims 1-6, characterized in that, The first road segment and the second road segment include the same total number of single lanes, which is equal to two; after determining the start and end coordinates of the edge of at least one virtual lane planned in the transition road segment, and before determining the intersection coordinates of the at least one virtual lane edge on the M dividing point connecting lines, the method further includes: For the M dividing point connecting lines, perform the following operations respectively: determine the intersection point of the virtual lane edge construction with the dividing point connecting line, and each dividing point determined by the dividing point connecting line as the lane positioning point, and obtain the distance difference result based on the positioning point distance between every two adjacent lane positioning points; A third constraint is established to minimize the cumulative value of the distance difference results.

8. The method according to any one of claims 1-6, characterized in that, The first road segment and the second road segment include the same total number of single lanes, which is greater than two; after determining the start and end coordinates of the edge of at least one virtual lane planned in the transition road segment, and before determining the intersection coordinates of the at least one virtual lane edge on the M dividing point connecting lines, the method further includes: For the M dividing point connecting lines, perform the following operations respectively: for each of the multiple virtual lane edges, construct each intersection point with a dividing point connecting line, and determine the intersection distance between each two adjacent intersection points; A fourth constraint is established to minimize the cumulative value of the distance results at each intersection point.

9. The method according to any one of claims 1-6, characterized in that, The step of dividing the two virtual side lines into M equal segments to obtain M connecting lines of the dividing points and the corresponding coordinates of the dividing points includes: Obtain the preset M segmentation ratio values, and the length of each of the two virtual side lines; Obtain the initial division points selected on the two virtual side lines respectively, wherein the two initial division points are located on the first endpoint connection line or the second endpoint connection line; For each of the preset M segmentation ratio values, the following operations are performed: based on a segmentation ratio value and the lengths of the two virtual side lines, combined with the initial segmentation point, the segmentation point corresponding to the segmentation ratio value is located on the two virtual side lines, and the two segmentation points are connected to obtain the corresponding segmentation point connection line, and the coordinates of the segmentation point corresponding to the segmentation point connection line are determined.

10. The method as described in claim 9, characterized in that, The step of locating the segmentation point corresponding to the segmentation ratio value on the two virtual side lines based on a segmentation ratio value and the lengths of the respective side lines, combined with the initial segmentation point, includes: For the two virtual side lines, perform the following operations respectively: Based on a segmentation ratio value and the edge length of a virtual side line, the segmentation length of the segmentation ratio value on the virtual side line is determined, and the distance from the corresponding initial segmentation point along the virtual side line is determined as the segmentation point of the segmentation length.

11. The method according to any one of claims 1-6, characterized in that, After drawing the corresponding virtual lane lines based on the coordinates of each intersection point, the method further includes: Receive a data acquisition request sent by the target object for a target path, wherein the target path includes the transition segment; The virtual lane lines drawn for the transition section, along with other map data associated with the target path, will be sent to the target object.

12. A device for generating virtual lane lines, characterized in that, include: The acquisition unit is used to acquire two virtual side lines generated for the transition section between the first road segment and the second road segment, as well as the endpoint coordinates of the endpoints of each single lane line connecting the first road segment and the second road segment to the transition section; at least one of the first road segment and the second road segment contains multiple single lanes. The segmentation unit is used to divide the two virtual side lines into M equal segments, using the first endpoint connection line and the second endpoint connection line as the segmentation point connection lines at the edges, to obtain M segmentation point connection lines and corresponding segmentation point coordinates; the first endpoint connection line and the second endpoint connection line are obtained based on the endpoints of each single lane line on the first road segment and the endpoints of each single lane line on the second road segment, respectively, where M is a positive integer greater than 2; The determining unit is used to determine the start and end coordinates of at least one virtual lane edge planned in the transition section based on the lane division of the first road segment and the second road segment, combined with the endpoint coordinates of each single lane line endpoint. The drawing unit is used to smooth the lane lines of the at least one virtual lane edge and use the lane line direction being consistent with the corresponding road segment direction as constraints. Combining the start and end coordinates of the at least one virtual lane edge and the coordinates of each dividing point, it determines the intersection coordinates of the at least one virtual lane edge on the M dividing point connecting lines, and draws the virtual lane lines corresponding to each of the at least one virtual lane edge according to the coordinates of each intersection point.

13. The apparatus as claimed in claim 12, characterized in that, When determining the intersection coordinates of the at least one virtual lane edge and the coordinates of each dividing point by combining the start and end coordinates of the at least one virtual lane edge, the drawing unit is used to: For each virtual lane edge planned in the transition section, construct the intersection point with the M dividing points connecting the lines; Using a convex optimization approach, by combining the start and end coordinates of the edge of the at least one virtual lane with the coordinates of each dividing point, the coordinates of the intersection points of the edges of the at least one virtual lane on the M dividing point connecting lines are determined when the constraints are satisfied.

14. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method as described in any one of claims 1-11.

15. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, it implements the method as described in any one of claims 1-11.

16. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1-11.

Images