Method and apparatus for determining roadway centerline network

By employing GPS and imaging to determine roadway centerlines, the method constructs accurate and cost-effective centerline networks, addressing the challenge of dynamic lane changes for autonomous driving.

JP7579993B2Active Publication Date: 2024-11-0842DOT INC
View PDF 6 Cites 0 Cited by

Patent Information

Application Number
JP2023572547
Authority / Receiving Office
JP · JP
Patent Type
Patents
Current Assignee / Owner
Priority Date
2021-11-09
Filing Date
2022-05-26
Publication Date
2024-11-08
Estimated Expiration
2042-05-26

AI Technical Summary

Technical Problem

Existing technologies face challenges in accurately generating roadway centerline networks for road maps, particularly in dynamic driving environments where vehicles frequently change lanes, requiring efficient and cost-effective methods to ensure safe autonomous driving.

Method used

A method and apparatus using vehicle GPS and onboard imaging to determine roadway centerlines by matching travel trajectories with road maps, generating road characteristic information, and estimating centerlines based on reliability, thereby constructing a centerline network.

Benefits of technology

This approach provides an accurate, cost-effective, and efficient means to generate roadway centerline networks without the need for expensive equipment, leveraging vehicle trajectory data to reflect actual road conditions and ensure precise map topology.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 0007579993000001
    Figure 0007579993000001
  • Figure 0007579993000002
    Figure 0007579993000002
  • Figure 0007579993000003
    Figure 0007579993000003
Patent Text Reader

Abstract

The present disclosure relates to a method and an apparatus for determining a roadway centerline network. The method according to an embodiment of the present disclosure includes the steps of acquiring a vehicle's travel trajectory using a GPS mounted on the vehicle, matching the travel trajectory with a road map, generating road feature information taking the travel trajectory into consideration based on an image captured by a photographing device mounted on the vehicle, determining the positions of section nodes that divide the roads of the road map into a plurality of sections based on the road feature information, and determining a lane centerline of the travel lane of the vehicle from among a plurality of lanes included in the section based on the travel trajectory and estimating the lane centerlines of the remaining lanes to determine the lane centerline arrangement for each section. The method may include a step of determining a final longitudinal position of the section node based on the reliability of the section node for each of the driving trajectories that have passed through the same road in an overlapping manner; a step of determining a section network connection relationship between the section, a previous section, and a next section based on the roadway centerline arrangement for each section; a step of determining a geometric structure of the roadway centerline arrangement for each section based on the reliability of the section links that connect the section nodes to each other; and a step of generating a roadway centerline network based on the section network connection relationship and the geometric structure of the roadway centerlines in the section.
Need to check novelty before this filing date? Find Prior Art

Description

[Technical field]

[0001] The present invention relates to a method and apparatus for determining a roadway centerline network. [Background technology]

[0002] A vehicle traveling on a road can travel on any one of a plurality of roadways included in the road. A vehicle can frequently change roadways while traveling, and situations in which the number of roadways on a road changes also frequently occur.

[0003] The convergence of information and communication technology and the vehicle industry has led to the rapid development of smart vehicles. As vehicles become smarter, they have evolved from simple mechanical devices to smart cars, and autonomous driving has been attracting attention as a core technology of smart cars. Autonomous driving is a technology in which a vehicle can reach its destination by itself without the driver having to operate the steering wheel, accelerator pedal, brakes, etc. As various additional functions related to autonomous driving continue to be developed, there is a demand for research into methods to provide passengers with a safe autonomous driving experience by using various data to recognize and judge the driving environment and control the vehicle.

[0004] Recently, there has been a related research need to accurately generate a network of roadway centerlines for maps of roads along which vehicles travel.

[0005] The above-mentioned background art is technical information possessed by the inventor for the purpose of deriving the present invention or acquired in the process of deriving the present invention, and is not necessarily publicly known art that was disclosed to the general public prior to the filing of the present application. Summary of the Invention [Problem to be solved by the invention]

[0006] The present invention provides a method and apparatus for determining a roadway centerline network. The problem to be solved by the present invention is not limited to the problem described above, and other problems and advantages of the present invention that are not described will be understood from the following description and will be more clearly understood by the embodiments of the present invention. It will be understood that the problems and advantages to be solved by the present invention can be realized by the means and combinations thereof shown in the claims. [Means for solving the problem]

[0007] As a technical means for solving the above-mentioned technical problem, a first aspect of the present disclosure is a method for determining a lane's centerline network, comprising the steps of: acquiring a vehicle's travel trajectory using a GPS mounted on the vehicle; matching the travel trajectory with a road map; generating road feature information taking into account the travel trajectory based on an image captured by a photographing device mounted on the vehicle; determining positions of section nodes that divide a road on the road map into a plurality of sections based on the road feature information; and determining a lane centerline arrangement for each section by determining a lane centerline of the travel lane of the vehicle from among a plurality of lanes included in the section based on the travel trajectory and estimating the lane centerlines of the remaining lanes. determining a final longitudinal position of the section node based on a reliability of the section node for each of the driving paths that have passed through the same road in an overlapping manner; determining a section network connection relationship between the section, a previous section, and a next section based on the section-by-section roadway centerline arrangement; determining a geometric structure of the section-by-section roadway centerline arrangement based on the reliability of section links that connect the section nodes to each other; and generating a roadway centerline network based on the section network connection relationship and the geometric structure of the roadway centerlines in the section.

[0008] A second aspect of the present disclosure is an apparatus for determining a roadway centerline network, the apparatus including a memory having at least one program stored therein, and a processor for performing calculations by executing the at least one program, the processor acquiring a travel trajectory of a vehicle using a GPS mounted on the vehicle, matching the travel trajectory with a road map, generating road characteristic information taking into account the travel trajectory based on an image captured by an image capture device mounted on the vehicle, determining positions of section nodes that divide a road on the road map into a plurality of sections based on the road characteristic information, determining a roadway centerline of the traveled roadway of the vehicle from among a plurality of lanes included in the section based on the travel trajectory, and determining the roadway centerlines of the remaining lanes. the device determines a roadway centerline arrangement for each section by estimating a line; determines a final longitudinal position of the section node based on the reliability of the section node for each driving trajectory that has passed the same road repeatedly; determines a section network connection relationship between the section, a previous section, and a next section based on the roadway centerline arrangement for each section; determines a geometric structure of the roadway centerline arrangement for each section based on the reliability of the section links that connect the section nodes to each other; and generates a roadway centerline network based on the section network connection relationship and the geometric structure of the roadway centerlines within the section.

[0009] A third aspect of the present disclosure can provide a computer-readable recording medium having recorded thereon a program for causing a computer to execute the method according to the first aspect.

[0010] In addition, other methods and systems for implementing the present invention, and computer-readable recording media having computer programs for executing the methods can also be provided.

[0011] Further aspects, features, and advantages will become apparent from the accompanying drawings, the claims, and the following detailed description of the invention. Effect of the Invention

[0012] According to the above-mentioned problem-solving means of the present disclosure, since only vehicle trajectory and road characteristic information is used rather than directly using images, it is lighter and faster to produce than LiDAR or image-based roadway centerline detection methods.

[0013] In addition, the map production cost is low, no expensive equipment is required, no large number of manpower is required, a small number of types of input information are required, and the topological information of the map is accurate.

[0014] Furthermore, since the vehicle travel path is used, the actual road conditions can be accurately reflected. [Brief description of the drawings]

[0015] [Figure 1] 1A and 1B are diagrams for explaining an example of a travel path of a vehicle in motion and an example of images acquired by the vehicle in motion according to an embodiment; [Figure 2a] 11 is an exemplary diagram illustrating a method for determining a lane number change point and an intersection section as road feature information according to an embodiment; FIG. [Figure 2b] 11 is an exemplary diagram illustrating a method for determining a lane number change point and an intersection section as road feature information according to an embodiment; FIG. [Diagram 3] 1 is an exemplary diagram illustrating a method for determining a U-turn section as road feature information according to an embodiment; [Figure 4] 1 is an exemplary diagram illustrating a method for determining a junction / branch section as road feature information according to an embodiment; [Diagram 5] 1 is an exemplary diagram illustrating a method for determining positions of section nodes that divide roads in a road map into a plurality of sections based on road feature information according to an embodiment; [Figure 6a]FIG. 13 is an exemplary diagram illustrating a method for determining a roadway layout for each section according to an embodiment. [Figure 6b] FIG. 13 is an exemplary diagram illustrating a method for determining a roadway layout for each section according to an embodiment. [Figure 6c] FIG. 13 is an exemplary diagram illustrating a method for determining a roadway layout for each section according to an embodiment. [Figure 7a] FIG. 1 is an exemplary diagram for explaining a method for correcting a roadway centerline network within a section according to one embodiment. [Figure 7b] FIG. 1 is an exemplary diagram for explaining a method for correcting a roadway centerline network within a section according to one embodiment. [Figure 7c] FIG. 1 is an exemplary diagram for explaining a method for correcting a roadway centerline network within a section according to one embodiment. [Figure 7d] FIG. 1 is an exemplary diagram for explaining a method for correcting a roadway centerline network within a section according to one embodiment. [Figure 8a] 11 is an example diagram illustrating a method for grouping section nodes according to an embodiment; FIG. [Figure 8b] 11 is an example diagram illustrating a method for grouping section nodes according to an embodiment; FIG. [Figure 9] 11 is an exemplary diagram illustrating a method for determining a final vertical position of a section node in a node group according to an embodiment; [Figure 10] 11 is an exemplary diagram illustrating a method for determining a section network connection relationship according to an embodiment. FIG. [Figure 11a] FIG. 2 is an exemplary diagram for explaining a method for determining a geometric structure of a roadway layout by section according to an embodiment. [Figure 11b] FIG. 2 is an exemplary diagram for explaining a method for determining a geometric structure of a roadway layout by section according to an embodiment. [Figure 12] FIG. 2 is a diagram illustrating an example of a roadway centerline network according to one embodiment. [Figure 13]1 is a flowchart of a method for determining a roadway centerline network according to one embodiment. [Figure 14] FIG. 2 is a block diagram of a roadway centerline network determiner according to one embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0016] The present disclosure relates to a method and an apparatus for determining a roadway centerline network. The method according to an embodiment of the present disclosure includes the steps of acquiring a vehicle's travel trajectory using a GPS mounted on the vehicle, matching the travel trajectory with a road map, generating road feature information taking the travel trajectory into consideration based on an image captured by a photographing device mounted on the vehicle, determining the positions of section nodes that divide the roads of the road map into a plurality of sections based on the road feature information, and determining a lane centerline of the travel lane of the vehicle from among a plurality of lanes included in the section based on the travel trajectory and estimating the lane centerlines of the remaining lanes to determine the lane centerline arrangement for each section. The method may include a step of determining a final longitudinal position of the section node based on the reliability of the section node for each of the driving trajectories that have passed through the same road in an overlapping manner; a step of determining a section network connection relationship between the section, a previous section, and a next section based on the roadway centerline arrangement for each section; a step of determining a geometric structure of the roadway centerline arrangement for each section based on the reliability of the section links that connect the section nodes to each other; and a step of generating a roadway centerline network based on the section network connection relationship and the geometric structure of the roadway centerlines in the section.

[0017] The advantages and features of the present invention, as well as the methods for achieving them, will become apparent from the embodiments described in detail with the accompanying drawings. However, the present invention is not limited to the embodiments presented below, and can be realized in various different forms, and should be understood to include all modifications, equivalents, and alternatives within the spirit and technical scope of the present invention. The embodiments presented below are provided to complete the disclosure of the present invention and to allow those skilled in the art to fully understand the scope of the invention. In describing the present invention, if a detailed description of related publicly known technology is deemed to obscure the gist of the present invention, the detailed description will be omitted.

[0018] The terms used in this application are merely used to describe certain embodiments and are not intended to limit the present invention. A singular expression includes a plural expression unless the context clearly indicates otherwise. In this application, the terms "include" and "have" are used to specify the presence of features, numbers, steps, operations, components, parts, or combinations thereof described in the specification, and are not to be understood as precluding the presence or additional possibility of one or more other features, numbers, steps, operations, components, parts, or combinations thereof.

[0019] Some embodiments of the present disclosure may be illustrated in terms of functional block configurations and various processing steps. Some or all of such functional blocks may be implemented in any number of hardware and / or software configurations for performing specific functions. For example, the functional blocks of the present disclosure may be implemented by one or more microprocessors or by circuit configurations for a given function. Also, for example, the functional blocks of the present disclosure may be implemented in various programming or scripting languages. The functional blocks may be implemented by algorithms executed by one or more processors. Furthermore, the present disclosure may employ conventional techniques for electronic configuration, signal processing, and / or data processing, etc. Terms such as "mechanism," "element," "means," and "configuration" may be used broadly and are not limited to mechanical and physical configurations.

[0020] It should be noted that the connecting lines or connecting members between components shown in the drawings are merely exemplary of functional and / or physical connections or circuit connections, and that in an actual device, connections between components may be represented by various alternative or additional functional connections, physical connections or circuit connections.

[0021] Hereinafter, the term "vehicle" may refer to any type of transportation means having a locomotive and used to move people or goods, such as a car, a bus, a motorcycle, a scooter, or a truck.

[0022] Hereinafter, "roadway" may mean that portion of a roadway that is divided by lanes so that vehicles may travel single-file along a defined portion of the road. "Roadway centerline" may mean an imaginary line that runs through the center of the "roadway."

[0023] The "roadway centerline network determination device" may be mounted on the vehicle 110. Alternatively, the "roadway centerline network determination device" is located outside the vehicle 110 and can exchange data by forming a communication network with other devices (such as a GPS receiver and a camera) located inside the vehicle 110. The "roadway centerline network determination device" can be realized by a computer device or multiple computer devices that communicate via a network to provide instructions, codes, files, contents, services, and the like. For the sake of convenience in the following explanation, it is assumed that the "roadway centerline network determination device" is mounted on the vehicle 110.

[0024] The present disclosure will now be described in detail with reference to the accompanying drawings.

[0025] FIG. 1 is a diagram for explaining an example of a travel path of a vehicle in motion and images captured by the vehicle in motion according to an embodiment.

[0026] 1, a traveling vehicle 110 is equipped with a GPS receiver, and the GPS receiver can receive GPS signals from artificial satellites. The GPS receiver installed in the vehicle 110 can obtain GPS position information including information on the latitude and hardness of the vehicle 110 from the GPS signal. In addition, the roadway centerline network determination device installed in the vehicle 110 can generate a traveling trajectory 120 of the vehicle 110 by connecting the GPS position information.

[0027] The travel path 120 of the vehicle 110 may be matched with the road map 100. The roadway centerline network determination device can match the travel path 120 of the vehicle 110 with the road map 100 by matching the position information stored in the road map 100 with the position information of the travel path 120.

[0028] In addition, a photographing device such as a camera may be mounted on the vehicle 110 while it is moving. The photographing device can photograph the surroundings of the vehicle 110. Referring to Fig. 1, an image 130 photographed while the vehicle 110 is moving is shown. In Fig. 1, only an image 130 photographed by a photographing device mounted on the front side of the vehicle 110 is shown, but a photographing device that photographs the side, rear, surround view, etc. of the vehicle 110 may be additionally mounted on the vehicle 110.

[0029] The image capture device can send captured images 130 to a roadway centerline network determiner.

[0030] The roadway centerline network determination device can generate road feature information taking into account the travel path 120 based on the images 130 captured by the image capture device. This will be described later with reference to FIG.

[0031] 2a and 2b are exemplary views illustrating a method for determining lane number change points and intersection sections as road feature information according to an embodiment.

[0032] In one embodiment, the road feature information may include at least one of a lane number change point, an intersection section, a U-turn section, and a junction / branch section.

[0033] 2a, the roadway centerline network determination device can determine a point where the number of roadways changes while the vehicle is traveling by calculating the number of roadways on the left and right sides at a predetermined time interval based on the roadway on which the vehicle is currently traveling. For example, when a point occurs where the rightmost roadway merges with the adjacent left roadway while the vehicle is traveling on the same roadway, the roadway centerline network determination device can determine the merging point as a point where road feature information changes.

[0034] Referring to Fig. 2b, the roadway centerline network determination device can determine an intersection section. The roadway centerline network determination device can analyze an object in an image captured by a photographing device mounted on a vehicle, and if the object is identified as a traffic light, a pedestrian crossing, or a stop line, can determine that the point where the image was captured corresponds to the intersection section. The roadway centerline network determination device can determine the point where the intersection section starts or ends as the point where the road feature information changes.

[0035] FIG. 3 is an exemplary diagram illustrating a method for determining a U-turn section as road feature information according to an embodiment.

[0036] The roadway centerline network determination device can determine a U-turn section based on the curvature value of the vehicle's travel trajectory.

[0037] Specifically, referring to Fig. 3, the roadway centerline network determination device can calculate curvature values ​​at multiple points on the vehicle's travel trajectory. The roadway centerline network determination device can select a section in which the calculated curvature value is equal to or greater than a threshold and the rotation direction is the same as that of the candidate section. Furthermore, the roadway centerline network determination device can determine that the candidate section is a U-turn section when the angle change amount of the candidate section is similar to a preset U-turn trajectory.

[0038] The roadway centerline network determination device can determine a point where a U-turn section starts or ends as a point where the road characteristic information is changed.

[0039] FIG. 4 is an exemplary diagram illustrating a method for determining a junction / branch section as road feature information according to an embodiment.

[0040] The roadway centerline network determination device can determine a U-turn section based on the curvature value of the vehicle's travel trajectory.

[0041] Specifically, referring to Fig. 4, the roadway centerline network determination device can calculate curvature values ​​at multiple points on the vehicle's travel trajectory. The roadway centerline network determination device can select a section in which the calculated curvature value is equal to or greater than a threshold and the rotation direction is the same as the candidate section. Furthermore, the roadway centerline network determination device can determine that the candidate section is a junction / branch section when the angle change amount of the candidate section corresponds to a left or right turn and an object in an image captured by a photographing device mounted on the vehicle is identified as a pedestrian crossing.

[0042] The roadway centerline network determination device can determine the point where the junction / junction section starts or ends as the point where the road feature information changes.

[0043] FIG. 5 is an exemplary diagram illustrating a method for determining positions of section nodes for dividing roads in a road map into a plurality of sections based on road feature information according to an embodiment.

[0044] When it is detected that the road feature information of the road on which the vehicle 510 is traveling has changed, the roadway centerline network determination device can divide the road into sections based on the detected point.

[0045] 5, it is shown that road information has changed at a first point 521 and a second point 522 while a vehicle 510 is traveling along a travel trajectory 500. Specifically, a change in the roadway of the vehicle 510 occurs at the first point 521, and a change in the number of lanes of the road occurs at the second point 522, so that the roadway centerline network determination device can detect that the road information has changed at the first point 521 and the second point 522.

[0046] The roadway centerline network determining device may determine the first point 521 and the second point 522, whose road feature information has been changed, as section nodes, and divide the section 520 based on the determined section nodes. Meanwhile, a line connecting the first point 521 and the second point 522, which are nodes of the section 520, is also called a section link. That is, the section 520 may include section nodes and section links connecting the section nodes.

[0047] In one embodiment, the roadway centerline network determiner can determine the reliability of the section node, which can affect the determination of the longitudinal position of the section node in FIG.

[0048] The reliability of a section node may be determined by the reliability and accuracy weights of the road feature information.

[0049] The reliability of the road feature information may change each time the road feature information is generated. For example, the reliability of the road feature information may be determined by factors that affect the detection accuracy of the road feature information (resolution, distance to an object, surrounding brightness, etc.).

[0050] The weight of the accuracy may be determined taking into consideration the roadway on which the vehicle is traveling. For example, the weight of the accuracy may be determined to be highest for the roadway on which the vehicle is traveling, and the weight of the accuracy may be determined to be lower for roadways located farther from the roadway on which the vehicle is traveling. In addition, when the roadway on which the vehicle is traveling is changed or the vehicle is turning, the weight of the accuracy may be determined to be lower.

[0051] In one embodiment, the roadway centerline network determiner can determine the reliability of the section links, which can affect the determination of the final number of roadways and road types such as intersections when merging the section links in FIG.

[0052] The reliability of the section link can be determined by the reliability of the road feature information and the weight of the section link.

[0053] The reliability of the road feature information may change each time the road feature information is generated. For example, the reliability of the road feature information may be determined by factors that affect the detection accuracy of the road feature information (resolution, distance to an object, surrounding brightness, etc.).

[0054] The weight of a section link can be adjusted to be lower as the detection rate of the number of roadways becomes lower due to changes in roadways, etc.

[0055] 6a to 6c are exemplary views illustrating a method for determining a roadway layout for each section according to an embodiment.

[0056] The roadway centerline network determination device can determine the roadway centerline of the roadway that the vehicle 610 has passed on a section-by-section basis. For example, if the vehicle 610 continues to travel on two roadways, the roadway centerline network determination device can determine the roadway centerlines of the two roadways.

[0057] In addition, when a change of roadway occurs for vehicle 610, the roadway centerline network determination device can determine the roadway centerline of the changed roadway based on the current driving trajectory, and determine the roadway centerline of the roadway before the change by linearly estimating the past driving trajectory.

[0058] 6a and 6b, it is shown that a vehicle 610 changes lanes to lane 1 while traveling on lane 2. In this case, the lane centerline network determination device can determine the lane centerline of lane 1 based on the current travel path, and determine the lane centerline of lane 2 by linearly estimating the past travel path.

[0059] In addition, in the case of the roadway centerline of a roadway that is not traveled, the roadway centerline network determination device can determine the roadway layout by section by estimating the roadway centerline of the roadway that is not traveled by laterally replicating the roadway centerline of the traveled roadway.

[0060] Referring to FIG. 6c, when a vehicle 610 makes a lane change from lane 2 to lane 1, the lane centerline network determination device can estimate the lane centerlines of lane 3 and 4, which are not traveled on by laterally replicating the lane centerlines of lane 1 and lane 2.

[0061] Through the above process, the roadway centerline network determining device can determine the roadway centerline arrangement in the corresponding section.

[0062] 7a to 7d are exemplary diagrams illustrating a method for correcting a roadway centerline network within a section according to an embodiment.

[0063] When the predetermined road characteristic information is generated, the roadway centerline network determination device can correct the roadway centerline network in the section based on a preset criterion. The predetermined road characteristic information may include an intersection section, a U-turn section, etc. That is, since the roadway centerline is not displayed in the intersection section and the U-turn section, the roadway is unclear, and therefore it is not possible to confirm whether the roadway will be changed or not, so it is necessary to correct the roadway centerline network in the section based on a preset criterion.

[0064] In one embodiment, when the road feature information is an intersection section or a U-turn section, the roadway centerline network determination device can determine (or correct) the roadway centerline network within the section by applying the intersection traffic rules or U-turn traffic rules regardless of the vehicle's driving trajectory.

[0065] Referring to FIG. 7a, in an example where a vehicle turns right at an intersection, even if the vehicle actually enters from lane 3 and exits lane 1, the lane centerline network determination device can determine the lane centerline network in the section as if the vehicle entered from lane 4 and exited lane 4.

[0066] Referring to FIG. 7b, in an example where a vehicle turns left at an intersection, even if the vehicle actually enters from lane 1 and exits into lane 3, the lane centerline network determination device can determine the lane centerline network in the section as if the vehicle entered from lane 1 and exited into lane 1.

[0067] Referring to FIG. 7c, in an example where a vehicle goes straight through an intersection, the roadway centerline network within the section and the roadway that entered and exited can be determined using the most linearized connection method.

[0068] Referring to FIG. 7d, in an example where a vehicle makes a U-turn, even if the vehicle actually enters from a 4-way and exits onto a 3-way, the roadway centerline network determination device can determine the roadway centerline network in the section as if the vehicle entered from a 4-way and exited onto a 3-way.

[0069] 8a and 8b are exemplary diagrams illustrating a method of grouping section nodes according to an embodiment.

[0070] 8a-8b, the travel trajectories of three vehicles passing through different lanes of the same road are shown. Specifically, the trajectory A is the trajectory of vehicle A traveling on lane 1, the trajectory B is the trajectory of vehicle B traveling on lane 2, and the trajectory C is the trajectory of vehicle C traveling on lane 5.

[0071] In one embodiment, the roadway centerline network determination device can extract, as a node list, section nodes generated from each of the driving trajectories estimated to have traveled the same road based on a predetermined criterion, which may include, but is not limited to, map matching information of the road, shape characteristics such as the direction and distance of the road, and relational similarity.

[0072] Meanwhile, the roadway centerline network determination device can extract a section link list for a trajectory that is estimated to have passed through the same road based on the node list, and the section link list can be a target for subsequent merging of section links and roadway centerlines.

[0073] By tracking the section links, the roadway centerline network determination device can designate the section nodes in the node list located within a predetermined distance as a node group. Referring to Fig. 8a, the roadway centerline network determination device can designate two section nodes near an intersection entry stop line located within a predetermined distance as a node group.

[0074] A specific section node may be matched with road feature information corresponding to the section to which the specific section node belongs. The feature information of the section node may include, but is not limited to, a change in the number of roadways, an intersection section, a U-turn section, a road junction / branch section, and the like.

[0075] The roadway centerline network determination device can designate, as a node group, section nodes in the node list that are located within a predetermined distance and have the same road feature information. Referring to Fig. 8a, the roadway centerline network determination device can designate, as a node group, two section nodes near an intersection entry stop line that are located within a predetermined distance and have the same road feature information as an intersection section.

[0076] On the other hand, if no matching section node is found in the trajectory, the roadway centerline network determination device can insert a section node into the section link that has a similar direction and is located at the shortest distance, and separate the roadway centerlines. Referring to Fig. 8b, since there is no node in the two section links that matches the section node indicating the road junction section, the roadway centerline network determination device can insert a section node indicating the road junction section into the two section links, and separate the roadway centerlines.

[0077] In one embodiment, the roadway centerline network determiner can remove at least a portion of the section nodes in the node group. In particular, the roadway centerline network determiner can remove mismatched section nodes due to trajectory position errors, misdetection of road features, etc.

[0078] For example, the roadway centerline network determination device can remove, from among the section nodes in a node group, section nodes whose front / rear positional relationships differ based on the intersection section included in the road feature information.

[0079] Furthermore, when a specific section node belongs to multiple node groups, the roadway centerline network determination device can designate a node group that has a high similarity in road feature information and is closer to the specific section node as the node group of the specific section node. In other words, the specific section node can be removed from node groups that are not designated.

[0080] FIG. 9 is an example diagram illustrating a method for determining a final vertical position of a section node in a node group according to an embodiment.

[0081] Referring to FIG. 9, it is assumed that the first section node 510 and the second section node 520 are nodes that belong to the same node group.

[0082] In Figures 8a to 8d, only the section nodes of the roadway on which the vehicle traveled are shown, whereas in Figure 9, the roadway centerline of the roadway on which the vehicle traveled and the roadway centerlines of the remaining roadways other than the roadway on which the vehicle traveled are shown, and the nodes of each roadway centerline are shown.

[0083] The roadway centerline network determination device can determine the final longitudinal position of the representative section node 530 that merges the section nodes 510, 520 in the node group, using the node reliability of each of the multiple section nodes 510, 520 included in the node group as weights. Although the representative section node 530 is shown as multiple nodes in Fig. 9, the representative section node 530 may be shown as a single node because information regarding the longitudinal position on the road is important.

[0084] The reliability of a section node may be determined by the reliability and accuracy weights of the road feature information.

[0085] The reliability of the road feature information may change each time the road feature information is generated. For example, the reliability of the road feature information may be determined by factors that affect the detection accuracy of the road feature information (resolution, distance to an object, surrounding brightness, etc.).

[0086] The weight of the accuracy may be determined taking into consideration the roadway on which the vehicle is traveling. For example, the weight of the accuracy may be determined to be highest for the roadway on which the vehicle is traveling, and the weight of the accuracy may be determined to be lower for roadways located farther from the roadway on which the vehicle is traveling. In addition, when the roadway on which the vehicle is traveling is changed or the vehicle is turning, the weight of the accuracy may be determined to be lower.

[0087] The roadway centerline network determination device can correct and match the longitudinal positions of the roadway centerlines of the sections to be merged, based on the final longitudinal position of the representative section node.

[0088] In addition, the roadway centerline network determination device can correct the final longitudinal position of the representative section node so that the length of the front / rear section of the representative section node is equal to or greater than a predetermined length.

[0089] Furthermore, the roadway centerline network determination device can determine road feature information of the representative section node based on the reliability of the section nodes included in the node group and the road feature information matched with the nodes. For example, if, among 10 section nodes included in a node group, the road feature information of 9 section nodes is an intersection section and the road feature information of one section node is a pocket section, the roadway centerline network determination device can determine that the road feature information of the representative section node is an intersection section.

[0090] FIG. 10 is an example diagram illustrating a method for determining a section network connection relationship according to an embodiment.

[0091] In one embodiment, the roadway centerline network determination device may determine a section network connection relationship between a reference section and a previous section and a next section based on the roadway centerline arrangement for each section.

[0092] Specifically, the roadway centerline network determination device can select an anchor section having the highest reliability from among a plurality of sections. For example, the roadway centerline network determination device can designate links connected to a representative section node as a link group. Also, the roadway centerline network determination device can select a section corresponding to a link group having the highest reliability from among a plurality of link groups as an anchor section based on a predetermined criterion. The predetermined criterion may include, for example, whether the numbers of lanes in the section link groups match, whether the numbers of lanes in the front / rear sections match, the maximum number of lanes, etc.

[0093] Referring to FIG. 10, the first section link group 610 has the fewest number of roadway centerlines, and the numbers of roadways are consistent, so the section corresponding to the first section link group 610 can be the anchor section.

[0094] The roadway centerline network determiner can link previous and subsequent sections based on the anchor section.

[0095] Specifically, the roadway centerline network determination device can assign roadway numbers to the front and rear sections based on the roadway number of the anchor section. For example, in FIG. 10, the roadway numbers 1, 2, 3, and 4 can be changed to -1, 0, 1, and 2 to correspond to the roadway numbers of the anchor section.

[0096] In addition, the roadway centerline network determination device can calculate the probability (probability of roadway existence) for each roadway for each section, and the probability can decrease as the distance from the roadway increases. For example, in the case of a section generated by driving on roadway 1 of a three-lane road, the probability that a roadway exists is 100% for roadway 1, 75% for roadway 2, and 50% for roadway 3, and the probability that a roadway does not exist is -25% for roadway 4, and -75% for roadway 0. The roadway centerline network determination device can obtain the final number of roadways by further considering the reliability of the section links described above in FIG. 5 and removing roadways whose sum of probabilities is lower than 0%. For example, in FIG. 10, since the number of roadways in the anchor section is two, it can be determined that the final number of roadways in the next section 620 connected to the anchor section is also two.

[0097] In one embodiment, the roadway centerline network determination device repeatedly determines the final roadway number for the connected front / rear section link groups, and if there is no connected section link group, it can repeatedly merge the roadway number of the section link group with the next highest reliability. Also, the roadway centerline network determination device can rapidly and accurately complete the roadway structure by traveling on both ends of the roadway by differentially applying the influence closer to the traveling roadway.

[0098] 11a and 11b are exemplary diagrams illustrating a method for determining a geometric structure of a roadway layout for each section according to an embodiment.

[0099] In one embodiment, the lane centerline network determination device can adjust the lateral position of the lane centerline in the section by determining a higher linear weight for the lane centerline closer to the vehicle's travel lane, and can determine the geometric structure of the lane centerline in the section according to the adjusted lateral position.

[0100] Referring to FIG. 11a, the geometry of the roadway centerline arrangement can be determined by combining based on the linear weights of the roadway centerlines of the sections.

[0101] The lane centerline network determination device can reflect both the reliability of the lane centerline, the linear weight of which decreases as the lane centerline is farther away from the vehicle's traveling lane, and the linear accuracy of the lane centerline of the section, which decreases as linear distortion occurs. In other words, the closer to the traveling lane, the more the linear influence of the lane centerline is applied, so that it is possible to quickly generate an asymmetrical lane and ensure linear accuracy.

[0102] In addition, the roadway centerline network determination device can determine the geometric structure of the roadway centerline within a section by removing steps that occur at the connection portions between sections.

[0103] Referring to Fig. 11b, the roadway centerline network determination device can generate the final roadway centerline geometric structure by removing the lateral step between the front and rear roadway centerlines that occurs near the intersection. For example, if a vehicle travels straight, turns left, and turns right once at an intersection and travels on the same general road three times, a step occurs because the combination of trajectories is different between the intersection and the general road, but the step can be removed by smoothly interpolating using the method described above.

[0104] FIG. 12 is a diagram illustrating an example of a roadway centerline network according to an embodiment.

[0105] The roadway centerline network determination device can generate a roadway centerline network based on the section network connection relationships described above in Figs. 1 to 11 and the geometric structure of the roadway centerlines within the sections.

[0106] Referring to FIG. 12, roadway centerline links are shown as black lines, section nodes as dots, and sections as boxes.

[0107] Meanwhile, the number of times each section is driven may be further considered in addition to the various evaluation criteria used in the process of generating the roadway centerline network.

[0108] Specifically, when using the node reliability of each of a plurality of section nodes included in a node group as a weight, the number of times each section is driven may be additionally considered in the weight. Also, the greater the number of times each section is driven, the greater the influence on the vertical position of the section node. Also, the number of times each section is driven may be additionally considered in correcting the vertical positions of the section and the roadway centerline. For example, when a section branch point is encountered, the vertical positions of all the section links of the branching roads may be corrected in the same manner. Also, the number of times each section is driven may be additionally considered in determining the road feature information of the representative section node. Also, the number of times each section is driven may be applied as a weight to the possibility that a roadway exists or does not exist. Also, when the connection relationships of the sections to be merged are different, the number of times each section is driven may be added as a weight in selecting the connection relationship. Also, the number of times each section is driven may be added to the linear weight of the roadway centerline.

[0109] FIG. 13 is a flow chart of a method for determining a roadway centerline network according to one embodiment.

[0110] The method for determining a roadway centerline network shown in Figure 13 relates to the embodiment described in the above figure, so even if the content is omitted below, the content described in the above figure can also be applied to the method of Figure 13.

[0111] Referring to FIG. 13, in step 1310, the processor may obtain the vehicle's travel trajectory using a GPS installed in the vehicle.

[0112] In step 1320, the processor may match the driving trajectory with a road map.

[0113] In step 1330, the processor can generate road feature information taking into account the travel path based on images captured by an image capture device mounted on the vehicle.

[0114] The road characteristic information may include at least one of a lane number change point, an intersection section, a U-turn section, and a junction / branch section.

[0115] The processor can calculate curvature values ​​at multiple points on the vehicle's driving trajectory, and can select as a candidate section a section where the calculated curvature value is equal to or greater than a threshold and where the rotation direction is the same. If the angle change amount of the candidate section is similar to a predetermined U-turn trajectory, the processor can determine that the candidate section is a U-turn section.

[0116] The processor can also calculate curvature values ​​at multiple points on the vehicle's driving trajectory, and can select as a candidate section a section where the calculated curvature value is equal to or greater than a threshold and where the rotation direction is the same; if the angle change amount of the candidate section corresponds to a left or right turn, and an object in an image captured by a photographing device mounted on the vehicle is identified as a pedestrian crossing, the processor can determine that the candidate section is a junction / branch section.

[0117] In step 1340, the processor may determine, based on the road feature information, the locations of section nodes that divide the roads of the road map into sections.

[0118] A section may include section nodes and section links that connect the section nodes to each other.

[0119] When a change in road feature information is detected, the processor may determine the detected point as a section node, and divide the section based on the determined section node.

[0120] The processor may determine the reliability of the section node. The reliability of the section node may be determined by the reliability of the road feature information and an accuracy weight considering the traveling roadway. The accuracy weight for the traveling roadway of the vehicle may be determined to be the highest, and the accuracy weight may be determined to be lower for roadways located farther from the traveling roadway. When the traveling roadway of the vehicle is changed or the vehicle is turning, the accuracy weight may be determined to be lower.

[0121] The processor can determine the reliability of the section link. The reliability of the section link can be determined by the reliability of the road feature information and the weight of the section link. The lower the detection rate of the number of roadways, the lower the weight of the accuracy of the link can be determined.

[0122] In step 1350, the processor can determine the lane centerline of the vehicle's travel lane from among the multiple lanes included in the section based on the travel trajectory, and estimate the lane centerlines of the remaining lanes, thereby determining the lane centerline arrangement for each section.

[0123] When the road feature information is an intersection section or a U-turn section, the processor can determine the layout of the roadway centerline within the section by applying the intersection traffic rules or U-turn traffic rules regardless of the vehicle's travel trajectory.

[0124] In step 1360, the processor may determine a final longitudinal position of the section node based on the reliability of the section node for each of the driving trajectories that have overlappingly passed the same road.

[0125] The processor may extract, as a node list, section nodes generated from each of the travel trajectories estimated to have traveled on the same road based on a predetermined criterion. A predetermined section node may be matched with road feature information corresponding to a section to which the predetermined section node belongs.

[0126] The processor can designate section nodes in the node list that are located within a predetermined distance as a node group by following the section links.

[0127] The processor can designate, as a node group, section nodes in the node list that are located within a predetermined distance and have the same road feature information.

[0128] If there is no section node with the same road feature information within a predetermined distance, the processor can insert the specified section node into the section link that has a similar direction and is at the shortest distance to separate the roadway centerline.

[0129] The processor can remove, from among the section nodes in the node group, section nodes whose front / rear positional relationships differ with respect to the intersection section included in the road feature information.

[0130] When a specific section node belongs to multiple node groups, the processor can designate a node group that has a high similarity in road feature information to the specific section node and is closer in distance as the node group for the specific section node.

[0131] In step 1370, the processor may determine section network connection relationships between the section and the previous and next sections based on the roadway centerline arrangement by section.

[0132] The processor can determine a final vertical position of a representative section node obtained by merging the section nodes in the node group, using the node reliability of each of the multiple section nodes included in the node group as a weight.

[0133] The processor can correct the final vertical position of the section node in the node group so that the length of the front / back section of the representative section node is equal to or greater than a predetermined length.

[0134] The processor can determine the road feature information of the representative section node based on the reliability of the section nodes included in the node group and the road feature information matched with the section nodes.

[0135] The processor can designate links connected to a representative section node as a link group, select a section corresponding to the link group with the highest reliability based on a predetermined criterion from among a plurality of link groups as an anchor section, and determine a section network connection relationship between previous and subsequent sections based on the selected anchor section.

[0136] The processor can determine the reliability of the link group by determining that the closer a roadway is to the roadway on which the vehicle is traveling, the higher the possibility of the roadway existing.

[0137] In step 1380, the processor may determine the geometry of the section-by-section roadway centerline arrangement based on the confidence of the section links connecting the section nodes to each other.

[0138] The processor can adjust the lateral position of the roadway centerline within the section by determining a higher linear weight for roadway centerlines that are closer to the vehicle's traveling roadway, and determine the geometric structure of the roadway centerline within the section according to the adjusted lateral position.

[0139] The processor can determine the roadway geometry within the sections by removing bumps that occur at the junctions between sections.

[0140] In step 1390, the processor may generate a roadway centerline network based on the section network connectivity relationships and the geometry of the roadway centerlines within the sections.

[0141] FIG. 14 is a block diagram illustrating an apparatus for determining a roadway centerline network according to one embodiment.

[0142] Referring to Fig. 14, a roadway centerline network determination device 1400 may include a communication unit 1410, a processor 1420, and a DB 1430. Only components related to the embodiment are shown in the roadway centerline network determination device 1400 in Fig. 14. Therefore, a person having ordinary skill in the art would understand that the roadway centerline network determination device 1400 may further include other general-purpose components in addition to the components shown in Fig. 14.

[0143] The communication unit 1410 may include one or more components that enable wired / wireless communication with an external server or device. For example, the communication unit 1410 may include at least one of a short-range communication unit (not shown), a mobile communication unit (not shown), and a broadcast receiving unit (not shown).

[0144] The DB 1430 is hardware that stores various data processed in the roadway centerline network determination device 1400, and may store programs for processing and controlling the processor 1420. The DB 1430 may store payment information, user information, and the like.

[0145] DB1430 may include dynamic random access memory (DRAM), random access memory (RAM), such as static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), CD-ROM, Blu-ray or other optical disk storage, hard disk drive (HDD), solid state drive (SSD), or flash memory.

[0146] The processor 1420 controls the overall operation of the roadway centerline network determining apparatus 1400. For example, the processor 1420 may generally control an input unit (not shown), a display (not shown), a communication unit 1410, a DB 1430, etc. by executing a program stored in a DB 1430. The processor 1420 may generally control the operation of the roadway centerline network determining apparatus 1400 by executing a program stored in a DB 1430.

[0147] The processor 1420 may control at least a portion of the operation of the roadway centerline network determiner 1400 described above in FIGS.

[0148] The processor 1120 may be implemented using at least one of ASICs (application specific integrated circuits), DSPs (digital signal processors), DSPDs (digital signal processing devices), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, micro-controllers, microprocessors, and other electrical units for performing functions.

[0149] In one embodiment, the roadway centerline network determining device 1400 may be a mobile electronic device. For example, the traffic information providing device 800 can be realized by a smartphone, a tablet PC, a PC, a smart TV, a PDA (personal digital assistant), a laptop, a media player, a navigation, a device with a camera, and other mobile electronic devices. In addition, the roadway centerline network determining device 1400 can be realized by a wearable device such as a watch, glasses, a headband, or a ring that has a communication function and a data processing function.

[0150] In other embodiments, the roadway centerline network determiner 1400 may be an electronic device that is integrated into a vehicle, for example, the roadway centerline network determiner 1400 may be an electronic device that is inserted into the vehicle after the manufacturing process by tuning.

[0151] In yet another embodiment, the roadway centerline network determination device 1400 may be a server located outside the vehicle. The server may be realized by a computer device or multiple computer devices that communicate over a network to provide instructions, codes, files, content, services, etc. The server may receive data required to determine the vehicle's travel route from a device mounted on the vehicle, and determine the vehicle's travel route based on the received data.

[0152] The embodiments according to the present invention may be realized in the form of a computer program executable by various components on a computer, and such a computer program may be recorded on a computer readable medium, including magnetic media such as hard disks, floppy disks, and magnetic tapes, optical media such as CD-ROMs and DVDs, magneto-optical media such as floptical disks, and hardware devices specially configured to store and execute program instructions, such as ROMs, RAMs, flash memories, and the like.

[0153] On the other hand, the computer program may be one specially designed and constructed for the present invention, or it may be one that is well known and available to those skilled in the art of computer software. Examples of computer programs include not only machine code, such as that produced by a compiler, but also high-level language code that is executed by a computer using an interpreter or the like.

[0154] According to one embodiment, the methods according to various embodiments of the present disclosure can be provided in a computer program product. The computer program product can be traded between sellers and buyers as a commodity. The computer program product can be distributed in the form of a machine-readable storage medium (e.g., a compact disc read only memory (CD-ROM)) or can be distributed in the form of an application store (e.g., the Play Store). TM ) or directly between two user devices. In the case of online distribution, at least a part of the computer program product may be at least temporarily stored or temporarily generated on a machine-readable storage medium, such as a memory of a manufacturer's server, an application store's server, or an intermediary server.

[0155] Unless there is an explicit order description or a contrary description regarding the steps constituting the method according to the present invention, the steps can be performed in any suitable order. The present invention is not necessarily limited to the order of the steps described above. The use of all examples or exemplary terms (such as, for example, etc.) in the present invention is merely for the purpose of explaining the present invention in detail, and the scope of the present invention is not limited by the examples or exemplary terms unless limited by the claims. In addition, those skilled in the art will understand that various modifications, combinations and changes can be made within the scope of the claims or their equivalents according to design conditions and factors.

[0156] Therefore, the concept of the present invention should not be limited to the above-described embodiments, and all scopes equivalent to or modified equivalently to the scope of the attached claims, as well as the scope of the present invention, fall within the scope of the concept of the present invention.

Claims

1. 1. A method for determining a lane's centerline network, comprising: acquiring a travel trajectory of the vehicle using a GPS mounted on the vehicle; Matching a road map with the driving trajectory; generating road feature information taking into account the travel path based on an image captured by an image capture device mounted on the vehicle; determining, based on the road feature information, positions of section nodes that divide the roads of the road map into a plurality of sections; determining a lane centerline of the lane on which the vehicle is traveling among a plurality of lanes included in the section based on the traveling trajectory, and estimating the lane centerlines of the remaining lanes, thereby determining a lane centerline arrangement for each section; determining a final longitudinal position of the section node based on the reliability of the section node for each of the travel trajectories that have passed through the same road in an overlapping manner; determining a section network connection relationship between the section, a previous section, and a next section based on the roadway centerline arrangement for each section; determining a geometric structure of a roadway centerline arrangement for each section based on the reliability of section links connecting the section nodes to each other; generating a roadway centerline network based on the section network connectivity relationships and the geometry of the roadway centerlines within the sections.

2. The section includes section nodes and section links connecting the section nodes to each other, The method comprises: The method further includes extracting, as a node list, section nodes generated from each of the travel trajectories estimated to have traveled on the same road based on a predetermined criterion; The method according to claim 1 , wherein a predetermined section node is matched with road feature information corresponding to a section to which the predetermined section node belongs.

3. The method comprises: The method of claim 2 , further comprising the step of designating, as a node group, section nodes in the node list that are located within a predetermined distance by following the section links.

4. The step of designating as a node group includes: The method of claim 3 , further comprising the step of designating, as a node group, section nodes in the node list that are located within the predetermined distance and have the same road feature information.

5. The step of designating as a node group includes:

5. The method of claim 4, further comprising the step of, if there is no section node with the same road feature information within the predetermined distance, inserting the predetermined section node into a section link with a similar direction and the shortest distance, and separating the roadway centerline.

6. The method comprises: The method according to claim 3 , further comprising the step of removing, from the section nodes in the node group, section nodes having a different front / rear positional relationship with respect to an intersection section included in the road feature information.

7. The method comprises: The method according to claim 3, further comprising the step of, when a specified section node belongs to a plurality of node groups, designating a node group having a higher similarity and a closer distance to the specified section node as the node group of the specified section node.

8. The method comprises: The method of claim 3, further comprising a step of determining a final vertical position of a representative section node obtained by merging section nodes in the node group using the node confidences of each of the section nodes included in the node group as weights.

9. The method comprises: The method of claim 8, further comprising the step of correcting the final vertical position of a section node in the node group so that the length of the front / back section of the representative section node is equal to or greater than a predetermined length.

10. The method comprises: The method according to claim 8, further comprising a step of determining road feature information of the representative section node based on the reliability of the section nodes included in the node group and road feature information matched with the section nodes.

11. Designating the links connected to the representative section node as a link group; selecting, as an anchor section, a section corresponding to a link group having the highest reliability based on a predetermined criterion from among a plurality of link groups; The method of claim 8, further comprising: determining a section network connection relationship between the previous section and the subsequent section based on the selected anchor section.

12. The method comprises: The method according to claim 11 , further comprising a step of determining a reliability of the link group by determining that the closer a roadway is to a roadway on which the vehicle is traveling, the higher the possibility of the roadway being present.

13. 1. An apparatus for determining a roadway centerline network, comprising: a memory having at least one program stored therein; a processor for performing operations by executing the at least one program; The processor, Acquire the vehicle's travel trajectory using a GPS mounted on the vehicle; Matching a road map with the driving trajectory; generating road feature information taking into account the travel path based on images captured by an imaging device mounted on the vehicle; determining positions of section nodes that divide the roads of the road map into a plurality of sections based on the road feature information; Based on the travel trajectory, a roadway centerline of the traveled roadway of the vehicle is determined from among a plurality of roadways (lanes) included in the section, and roadway centerlines of the remaining roadways are estimated to determine a roadway centerline arrangement for each section; determining a final vertical position of the section node based on the reliability of the section node for each of the travel trajectories that have passed through the same road in duplicate; determining a section network connection relationship between the section, a previous section, and a next section based on the roadway centerline arrangement for each section; determining a geometric structure of a roadway centerline arrangement for each section based on the reliability of the section links connecting the section nodes to each other; The apparatus generates a roadway centerline network based on the section network connectivity relationships and the geometric structure of the roadway centerlines within the sections.

14. A computer-readable recording medium having recorded thereon a program for executing the method according to claim 1 on a computer.

Citation Information

Patent Citations

  • Map information generator

    JP1994273186A

  • Road data generation method

    JP2004246554A

  • Present location information management device of vehicle

    JP2006189325A

  • Car navigation device and map information

    JP2007248235A

  • Method for generating road surface marked map

    JP2009223817A