Road surface information acquisition method, road surface information acquisition device, and road surface information acquisition program

Abstract

To provide a road surface information acquisition method.SOLUTION: The first vehicle onboard machine 5 mounted on the measuring vehicle 5 has a LiDAR23B. The first onboard machine 5 receives a reflected wave of a laser transmitted to a road surface and reflected by the road surface, and recognizes an end of a division line formed on the road surface based on the intensity of the reflected wave. The first onboard vehicle 5 transmits road surface information including the recognized end of the lane marking to the server device 3 via the network N. The server device 3 adds, to the information on the lane marking included in the map information based on the road surface information, the end portion information indicating the end portion of the lane marking and the continuous information indicating that the section is continuously present. The second in-vehicle device mounted in the vehicle 6 acquires the information on the lane marking from the server device 3, compares the end portion of the lane marking recognized by the LiDAR41B with the information indicating the end portion of the lane marking acquired from the server device 3, and estimates the current position.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to a road surface information acquisition method, a road surface information acquisition device, and a road surface information acquisition program. [Background technology]

[0002] In an autonomous vehicle, it is necessary to estimate the current position with high accuracy by matching the positions of features measured by a sensor such as LiDAR (Light Detection and Ranging) with the positions of features in map information for autonomous driving. Patent Document 1 describes an example of a method for estimating the current position using the positions of features as landmarks detected using LiDAR and the features in map information.

[0003] Furthermore, Patent Document 2 describes a method of detecting white lines using LiDAR and detecting with high accuracy the relative lateral position of the white lines with respect to the vehicle or the direction in which the vehicle is facing with respect to the white lines. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Publication No. 2017-72422 [Patent Document 2] Japanese Patent Application Laid-Open No. 2017-215199 Summary of the Invention [Problem to be solved by the invention]

[0005] As described above, when detecting lane markings such as white lines using a sensor such as LiDAR and estimating the current position of a vehicle, it is necessary to detect lane markings such as white lines with high accuracy.

[0006] The present invention aims to address such problems, and provides a road surface information acquisition method that improves the accuracy of detecting (recognizing) lane markings, for example. [Means for solving the problem]

[0007] The road surface information acquisition method described in claim 1, which was made to solve the above-mentioned problems, is a road surface information acquisition method in which electromagnetic waves transmitted to a road surface are received as reflected waves reflected by the road surface, and the ends of marking lines formed on the road surface are recognized based on the intensity of the reflected waves, characterized in that the electromagnetic waves are transmitted from a sensor arranged on a mobile body, and the ends of the marking lines are recognized based on changes in the intensity of the reflected waves along the longitudinal direction of the marking lines.

[0008] The road surface information acquisition method described in claim 5 is a road surface information acquisition method in which electromagnetic waves transmitted to a road surface are received as reflected waves reflected by the road surface, and the ends of marking lines formed on the road surface are recognized based on the intensity of the reflected waves, characterized in that the electromagnetic waves are transmitted from a sensor arranged on a mobile body, and the ends of the marking lines are recognized based on the intensity distribution of the reflected waves within a reflection area scanned along the longitudinal direction of the marking line.

[0009] The road surface information acquisition device described in claim 8 comprises a transmitting unit capable of transmitting electromagnetic waves to a road surface, a receiving unit capable of receiving reflected waves of the transmitted electromagnetic waves reflected by the road surface, and a recognition unit that recognizes the end of a marking line formed on the road surface based on the intensity of the reflected waves, wherein the recognition unit recognizes the end of the marking line based on a change in the intensity of the reflected waves along the longitudinal direction of the marking line, or the intensity distribution of the reflected waves within a reflection area scanned along the longitudinal direction of the marking line.

[0010] The road surface information acquisition program described in claim 9 is characterized in that it causes a computer to function as a recognition unit that recognizes the ends of demarcation lines formed on the road surface based on the change in intensity of the reflected waves along the longitudinal direction of the demarcation line, or the intensity distribution of the reflected waves within a reflection area scanned along the longitudinal direction of the demarcation line, among the reflected waves received when electromagnetic waves transmitted to the road surface are reflected by the road surface.

[0011] A recording medium according to a tenth aspect of the present invention is characterized in that the road surface information acquisition program according to the ninth aspect of the present invention is recorded on the recording medium.

[0012] Furthermore, one example of the problem with the above-described conventional technology is that it is not possible to estimate the position of a vehicle (moving object) in the direction of movement using white lines (demarcation lines). Another invention of the present application aims to address such a problem. That is, an object of the other invention of the present application is to provide, for example, a map information creation method and a current position estimation method that improve the accuracy of estimating the position of a moving object in the direction of movement.

[0013] Another invention of the present application is a method for creating lane marking information, which is characterized by adding to information indicating lane markings formed on the road surface at least one of end information indicating the ends of the lane markings and continuity information indicating that the lane marks exist continuously.

[0014] In addition, another invention of the present application is a method for creating lane marking information, which is characterized by adding to information indicating lane markings formed on the road surface at least one of end information indicating the end of the lane marking, and non-end information indicating information that is included in the lane marking but is not the end.

[0015] In addition, the lane marking data structure of another invention of the present application is a data structure of lane marking data indicating lane markings formed on the road surface, and is characterized in that the lane marking data can be assigned end information indicating the end of the lane marking line and continuity information indicating that the lane marks exist continuously.

[0016] In addition, the lane marking data structure of another invention of the present application is a data structure of lane marking data indicating lane markings formed on the road surface, and is characterized in that the lane marking data can be assigned end information indicating the end of the lane marking line and non-end information indicating a part of the lane marking line that is not the end.

[0017] In addition, a memory device of another invention of the present application is a memory device that stores demarcation line information indicating demarcation lines formed on a road surface, and is characterized in that the demarcation line information includes end information indicating the end of the demarcation line and non-end information indicating a part that is included in the demarcation line but is not the end.

[0018] In addition, a current position estimation method of another invention of the present application is a current position estimation method that estimates the current position of a mobile body based on information regarding lane markings, and is characterized by including an acquisition process of acquiring end information indicating the end of the lane markings from an external device, and an estimation process of estimating the current position of the mobile body based on information indicating the end of the lane markings on the road surface recognized by a sensor arranged on the mobile body and the acquired end information.

[0019] In addition, another invention of the present application is characterized in that the lane marking information creation device is equipped with an assignment unit that assigns to information indicating lane markings formed on the road surface at least one of end information indicating the end of the lane marking, and continuity information indicating that the lane markings exist continuously.

[0020] In addition, another invention of the present application is a lane marking information creation program characterized by causing a computer to function as an assignment unit that assigns to information indicating lane marking lines formed on the road surface at least one of end information indicating the end of the lane marking line and continuity information indicating that the lane marks exist continuously.

[0021] A recording medium according to another aspect of the present invention is characterized in that the lane marking information creation program is recorded thereon.

[0022] In addition, another invention of the present application provides a method for creating demarcation line information, which is characterized in that each piece of point information indicating a demarcation line is assigned a latitude and longitude on the demarcation line, and is also assigned at least one of end information indicating the end of the demarcation line and non-end information indicating that the piece is included in the demarcation line but is not the end.

[0023] In addition, a current position estimation method of another invention of the present application is a current position estimation method for estimating the current position of a mobile body, and is characterized by including the steps of: acquiring multiple pieces of end information of dividing lines each having latitude and longitude assigned thereto and included in surrounding map information; acquiring multiple pieces of information indicating the ends of dividing lines on the road surface using a sensor disposed on the mobile body; and estimating the current position based on the positional relationship between the acquired end information and the positional relationship between the information indicating the ends of dividing lines on the road surface.

[0024] In addition, another invention of the present application is a demarcation line information creation device that is characterized by having an assignment unit that assigns latitude and longitude on the demarcation line to each of the point information of information indicating a demarcation line that is composed of multiple point information, and assigns at least one of end information indicating the end of the demarcation line and non-end information indicating that the information is included in the demarcation line but is not the end.

[0025] In addition, another invention of the present application is a demarcation line information creation program that causes a computer to function as an assignment unit that assigns latitude and longitude on the demarcation line to each of the point information in information indicating a demarcation line that is composed of multiple point information, and assigns at least one of end information indicating the end of the demarcation line and non-end information indicating that the information is included in the demarcation line but is not the end.

[0026] In addition, a current position estimation device of another invention of the present application is a current position estimation device that estimates the current position of a mobile body, and is characterized by including: an acquisition unit that acquires multiple pieces of end information of demarcation lines that are assigned latitude and longitude contained in surrounding map information; a sensor that is disposed on the mobile body and acquires multiple pieces of information indicating the ends of demarcation lines on the road surface; and an estimation unit that estimates the current position based on the positional relationship between the acquired end information and the positional relationship between the information indicating the ends of the demarcation lines on the road surface.

[0027] Further, a recording medium according to another aspect of the present invention is characterized in that the above-mentioned lane marking information creation program is recorded on the recording medium.

[0028] A current position estimation program according to another aspect of the present invention is characterized in that the current position estimation method is executed by a computer.

[0029] In addition, a road surface information acquisition device of another invention of the present application is a road surface information acquisition device that acquires information about the road surface, and is characterized by having a shape recognition unit that recognizes dividing lines on the road surface, an end recognition unit that recognizes both ends of the recognized dividing lines, and an interpolation unit that interpolates a series of points between the both ends. [Brief explanation of the drawings]

[0030] [Figure 1] 1 is a block diagram showing an embodiment of a driving assistance system that implements a road surface information acquisition method, a map information creation method, and a current position estimation method of the present invention. [Figure 2] FIG. 2 is a functional configuration diagram of a first vehicle-mounted device shown in FIG. [Figure 3] FIG. 2 is a functional configuration diagram of the server device shown in FIG. [Figure 4] FIG. 10 is an explanatory diagram for explaining map information before the end portions of the lane lines are recorded. [Figure 5] FIG. 10 is an explanatory diagram for explaining map information after the end of a lane marking has been recorded. [Figure 6] FIG. 2 is a functional configuration diagram of a second vehicle-mounted device shown in FIG. [Figure 7] 4 is a flowchart showing the procedure of a road surface information acquisition process executed by the first vehicle-mounted device shown in FIG. [Figure 8] 10 is a graph showing the reflection intensity when a laser is irradiated onto a demarcation line when there is no fading at the end. [Figure 9] 10 is a graph showing the reflection intensity when a laser is irradiated onto a demarcation line having a faint edge. [Figure 10] 10 is a graph showing the intensity distribution of a reflected wave when a laser is irradiated onto a demarcation line with no fading at the end. [Figure 11] 10 is a graph showing the intensity distribution of a reflected wave when a laser is irradiated onto a demarcation line having a faint edge. [Figure 12]10 is a flowchart showing a driving assistance process performed by the second vehicle-mounted device shown in FIG. [Figure 13] FIG. 10 is an explanatory diagram for explaining map information in which the end portions of lane dividing lines are recorded in another embodiment. [Figure 14] FIG. 10 is a functional configuration diagram of a first vehicle-mounted device according to another embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0031] A method for creating lane marking information according to one embodiment of the present invention is characterized in that it adds, to information indicating lane markings formed on a road surface, at least one of end information indicating the end of the lane markings and continuity information indicating that the lane marks are continuous. This allows the end of the lane markings to be used as landmarks for estimating the current position, thereby improving the accuracy of estimating the position of the moving object in the direction of movement.

[0032] In addition, a method for creating lane marking information according to one embodiment of the present invention is characterized in that it adds, to information indicating lane markings formed on a road surface, at least one of edge information indicating the edge of the lane marking, and non-edge information indicating a part of the lane marking that is included in the lane marking but is not the edge. This allows the edge of the lane marking to be used as a landmark for estimating the current position, thereby improving the accuracy of estimating the position of the moving object in the direction of movement.

[0033] The information indicating the demarcation line may include point information indicating latitude and longitude on the demarcation line, and at least one of the edge information and non-edge information may be added to the point information. This makes it possible to easily add the edge information and non-edge information.

[0034] Furthermore, the non-edge information may be provided so that information indicating a portion of the lane marking line that is free from defects and information indicating a portion of the lane marking line that is defective can be distinguished from each other. This makes it possible to avoid using defective portions of the lane marking line as landmarks, thereby further improving the accuracy of position estimation in the direction of movement of the moving object.

[0035] In addition, a lane marking data structure according to one embodiment of the present invention is a data structure for lane marking data indicating lane markings formed on a road surface, and is characterized in that the lane marking data can be provided with end information indicating the end of the lane markings and continuity information indicating that the lane markings exist consecutively. This allows the end of the lane markings to be used as landmarks for estimating the current position, thereby improving the accuracy of estimating the position of the moving object in the direction of movement.

[0036] In addition, a lane marking data structure according to one embodiment of the present invention is a data structure for lane marking data indicating lane markings formed on a road surface, and is characterized in that the lane marking data can be assigned edge information indicating the edge of the lane marking, and non-edge information indicating a part of the lane marking that is included in the lane marking but is not the edge. This allows the edge of the lane marking to be used as a landmark for estimating the current position, thereby improving the accuracy of estimating the position of the moving object in the direction of movement.

[0037] In addition, a storage device according to one embodiment of the present invention is a storage device that stores lane marking information indicating lane markings formed on a road surface, and the lane marking information includes end information indicating end portions of the lane markings and non-end information indicating portions that are included in the lane markings but are not the end portions. This allows the end portions of the lane markings to be used as landmarks for estimating the current position, thereby improving the accuracy of estimating the position of the moving object in the direction of movement.

[0038] Furthermore, a current position estimation method according to one embodiment of the present invention is a current position estimation method for estimating the current position of a mobile object based on information about lane markings, and is characterized by including: an acquisition step of acquiring edge information indicating the edge of the lane markings from an external device; and an estimation step of estimating the current position of the mobile object based on information indicating the edge of the lane markings on the road surface recognized by a sensor disposed on the mobile object and the acquired edge information. This makes it possible to improve the accuracy of position estimation in the direction of movement of the mobile object.

[0039] In addition, the lane marking information creation device according to one embodiment of the present invention is characterized by including an assigning unit that assigns, to information indicating lane markings formed on a road surface, at least one of end information indicating the end of the lane markings and continuity information indicating that the lane marks exist consecutively. This allows the end of the lane markings to be used as landmarks for estimating the current position, thereby improving the accuracy of estimating the position of the moving object in the direction of movement.

[0040] The method for creating lane marking information described above may also be implemented as a lane marking information creation program that is executed by a computer. Since the program is executed by a computer in this manner, dedicated hardware or the like is not required, and the method can be installed and run on a general-purpose information processing device.

[0041] The information processing program may be stored on a computer-readable recording medium, which allows the program to be distributed as a standalone program rather than being incorporated into a device, and allows for easy version upgrades. [Example]

[0042] A driving assistance system that implements the road surface information acquisition method, lane marking information creation method, and current position estimation method of the present invention will be described below with reference to FIGS.

[0043] The driving assistance system 1 includes a first vehicle-mounted device 2 as a road surface information acquisition device, a server device 3 as an external device and a lane marking information creation device, and a second vehicle-mounted device 4. The first vehicle-mounted device 2 is a device that acquires road surface information and transmits it to the server device 3, and is mounted, for example, on a measurement vehicle 5 as a mobile body that travels on roads for the purpose of creating map information. The server device 3 acquires the road surface information from the first vehicle-mounted device 2 and creates map information. The server device 3 is capable of communicating with the first vehicle-mounted device 2 via a network N such as the Internet, and acquires the road surface information from the first vehicle-mounted device 2 using the network N. Note that the acquisition of road surface information by the server device 3 is not limited to the above-described form. For example, an operator or the like may manually transfer the road surface information from the first vehicle-mounted device 2 to the server device 3 without using the network N. In the following explanation, the exchange of information between the first vehicle-mounted unit 2 and the second vehicle-mounted unit 4 and the server device 3 will be described as being sent and received via the network N, but as mentioned above, this is not limited to this form, and the exchange of information may also be done manually by an operator.

[0044] The second vehicle-mounted device 4 is capable of communicating with the server device 3 via the network N. The second vehicle-mounted device 4 is a device that receives map information from the server device 3 and provides driving assistance, and is mounted, for example, on a vehicle 6 serving as a moving body receiving driving assistance. In this embodiment, the first and second vehicle-mounted devices 2 and 4 mounted on the measurement vehicle 5 and the vehicle 6 are described as examples of terminals capable of communicating with the server device 3, but they may also be portable terminals that can be placed on moving bodies, such as smartphones. Note that the reception of map information by the second vehicle-mounted device 4 is not limited to the above-described form; for example, an operator or the like may manually transfer map information from the server device 3 to the second vehicle-mounted device 4 without using the network N.

[0045] 2 shows the functional configuration of the first vehicle-mounted device 2. The first vehicle-mounted device 2 includes a control unit 21, an input / output unit 22, and a sensor unit .

[0046] The control unit 21 functions as a processor such as a CPU (Central Processing Unit) of the first vehicle-mounted device 2, and is responsible for overall control of the first vehicle-mounted device 2. The control unit 21 recognizes the ends of dividing lines such as white lines and yellow lines formed on the road surface using a LiDAR 23B described later, and transmits this as road surface information to the server device 3. The control unit 21 may also obtain surrounding information other than road surface information and transmit it to the server device 3.

[0047] The input / output unit 22 functions as a network interface of the first vehicle-mounted device 2 and transmits road surface information.

[0048] The sensor unit 23 includes a GPS (Global Positioning System) receiver 23A, a transmitter, a LiDAR 23B as a receiver, and the like. In this embodiment, the sensor unit 23 includes the LiDAR 23B as an example of a sensor capable of transmitting electromagnetic waves. The GPS receiver 23A detects current position information of the measurement vehicle 5. As is well known, the GPS receiver 23A periodically receives radio waves emitted from a plurality of GPS satellites, obtains current position information and time, and outputs the information to the control unit 21.

[0049] The LiDAR 23B outputs a pulsed laser while changing the output direction in a predetermined detection area, receives reflected waves of the laser, and generates point cloud information. The LiDAR 23B outputs multiple pulses of laser within the detection area and generates point cloud information based on the reflected waves of the multiple pulses of laser. Each piece of information constituting the point cloud information indicates the laser output direction, the distance to the object that reflected the laser, and the intensity of the reflected waves. In this embodiment, the LiDAR 23B irradiates the laser toward the road surface, and the road surface is the detection area. Therefore, the point cloud information is information indicating the distance to the road surface as the object. Note that the LiDAR 23B may also emit a laser toward a location other than the road surface to acquire surrounding information other than road surface information.

[0050] The server device 3 is installed in an office or the like that provides map information.

[0051] 3 shows the functional configuration of the server device 3. The server device 3 includes a storage unit 31 as a storage device, a control unit 32, and an input / output unit 33.

[0052] The storage unit 31 functions as a storage device such as a hard disk of the server device 3, and stores map information. In this embodiment, it is assumed that the map information already includes information about the lane markings. The information about the lane markings will be explained using FIG. 4. In the example shown in FIG. 4, point information P1, ..., P 14 In addition, the point information P1, ...P 14 Each of these is assigned location information (latitude and longitude).

[0053] The control unit 32 controls the entire server device 3 by using a processor such as a CPU of the server device 3. Based on road surface information such as the end of a lane marking transmitted from the first vehicle-mounted device 2, the control unit 32 generates point information P1, ..., P2, as shown in FIG. 14 Among these, those recognized as end points (shown as white circles in the figure) are assigned end information indicating the end of the lane line. By assigning the above-mentioned end information to the information about the lane line included in the map information in this way, the second vehicle-mounted device 4 that has received the map information can recognize the end of the lane line from the information about the lane line.

[0054] The input / output unit 33 functions as a network interface of the server device 3 , receives road surface information from the first vehicle-mounted device 2 , and transmits map information to the second vehicle-mounted device 4 .

[0055] 6 shows the functional configuration of the second vehicle-mounted device 4. The second vehicle-mounted device 4 includes a sensor unit 41, a control unit 42, and an input / output unit 43.

[0056] The sensor unit 41 includes a GPS receiver 41A, a LiDAR 41B, etc. The GPS receiver 41A is a device having the same functions as the GPS receiver 23A of the first vehicle-mounted device 2 described above, and the LiDAR 41B is a device having the same functions as the LiDAR 23B of the first vehicle-mounted device 2 described above, so detailed explanations thereof will be omitted here.

[0057] The control unit 42 is a processor such as a CPU of the second in-vehicle device 4, and is responsible for overall control of the second in-vehicle device 4. The control unit 42 performs driving assistance (such as controlling the steering wheel, accelerator, brake, etc., and presenting driving-related information) using information obtained from the sensor unit 41 and map information obtained from the server device 3. For simplicity of explanation, the following description will be given assuming that autonomous driving control is performed as driving assistance. The control unit 42 needs to estimate the current position of the vehicle in order to perform autonomous driving control. In this embodiment, the control unit 42 estimates the current position based on information indicating the end of a lane marking recognized using the LiDAR 41B and lane marking end information included in the map information obtained from the server device 3.

[0058] The input / output unit 43 functions as a network interface of the second vehicle-mounted device 4 and receives map information.

[0059] Next, the operation of the driving assistance system 1 in this embodiment will be described. First, the road surface information acquisition process executed by the control unit 21 of the first vehicle-mounted device 2 (hereinafter simply referred to as the first vehicle-mounted device 2) will be described below with reference to Fig. 7. The first vehicle-mounted device 2 uses the flowchart shown in Fig. 7 as a computer program, which becomes a road surface information acquisition program that causes a computer to execute a road surface information acquisition method.

[0060] The first vehicle-mounted device 2 executes a road surface information acquisition process while traveling. In the road surface information acquisition process, the first vehicle-mounted device 2 controls the LiDAR 23B to acquire point cloud information related to the road surface on which the vehicle is traveling (step S1). Next, the first vehicle-mounted device 2 extracts lane line segments based on the point cloud information. Specifically, an orthoimage of the point cloud is generated based on the acquired point cloud information. Then, image processing is performed on the orthoimage to detect, for example, line segments (straight lines). The detected line segments (straight lines) are then grouped to extract lane line segments that form the outline of a single lane line (step S2). Note that KS in FIG. 8 is an example of a lane line segment. Next, as shown in FIGS. 8 and 9, the first vehicle-mounted device 2 recognizes the ends and non-ends of lane lines formed on the road surface on which the vehicle is traveling from the extracted lane line segments (step S3). Next, the first vehicle-mounted device 2 interpolates the sequence of points between the recognized end and non-end points (i.e., interpolates the sequence of points into the continuous portion between the end points) (step S4), and then returns to step S1.

[0061] Details of step S3 will be explained using Figures 8 and 9. Figure 8 shows a case where there is no defect such as fading in the lane markings, while Figure 9 shows a case where there is a defect such as fading in the lane markings. One example of step S3 is a method of recognizing the end and non-end portions of a lane marking based on changes in the intensity of reflected waves (hereinafter referred to as "reflection intensity") along the longitudinal direction of each of multiple lines L1 to L4 along the lane markings, as shown in Figures 8 and 9. Note that non-end portions are locations on the lane markings where defects such as fading make it impossible to accurately detect the end portion. In other words, non-end portions are locations where the reflection intensity of the lane markings changes along the longitudinal direction, but the change is recognized as being due to a defect such as fading, rather than the end portion of the lane marking. Note that defects other than fading can also include thinning, dirt, and overlapping lines.

[0062] The laser reflectivity is high on road surfaces with markings, and low on road surfaces without markings. Therefore, the LiDAR 23B receives reflected waves with higher intensity from road surfaces with markings than from road surfaces without markings. Therefore, the first vehicle-mounted device 2 estimates the positions of the markings from the laser reflection intensity (i.e., the intensity of the reflected waves received by the LiDAR 23B) and sets lines L1 to L4 along the longitudinal direction of the markings.

[0063] 8, at the ends of the lane markings that are free of defects such as fading, the reflection intensity changes suddenly on each of the lines L1 to L4 along the longitudinal direction of the lane markings. Therefore, at the ends of the lane markings that are free of defects such as fading, there is little variability when the LiDAR 41B mounted on the vehicle 6 detects the ends of the lane markings, and they can be used as landmarks.

[0064] On the other hand, as shown in Fig. 9, at the end of a faded lane marking, the reflection intensity changes gradually along all or part of lines L1 to L4 along the longitudinal direction of the lane marking. For this reason, the detection position of the end of a faded lane marking is likely to vary when the LiDAR 41B mounted on the vehicle 6 detects the end of the lane marking, making it unsuitable to use the end of the faded lane marking as a landmark for estimating the self-position in the traveling direction of the vehicle 6 (the longitudinal direction of the lane marking).

[0065] Therefore, in this embodiment, the first vehicle-mounted device 2 recognizes the position on the lines L1 to L4 where the change in reflection intensity is abrupt as the end T1 of the demarcation line, and recognizes the position on the lines L1 to L4 where the change in reflection intensity is gradual as the non-end T2 of the demarcation line. Also, in FIG. 9, the blurring occurs uniformly in the left-right direction. However, in actuality, the blurring may not occur uniformly in the left-right direction, and may occur only on the upper side, lower side, or center of the demarcation line. Therefore, in this embodiment, if the change in reflection intensity is abrupt on all of the lines L1 to L4, the first vehicle-mounted device 2 recognizes the position where the change in reflection intensity is abrupt as the end T1 of the demarcation line, and if the change in reflection intensity on even one of the lines is gradual, the first vehicle-mounted device 2 recognizes the position where the change in reflection intensity is a non-end T2 of the demarcation line.

[0066] Specifically, the first vehicle-mounted device 2 recognizes the end T1 of a lane marking when the reflection intensity on all lines L1 to L4 changes from a high state due to reflection on the lane marking to a low state due to reflection on the road surface other than the lane marking, and the rate of change on all lines L1 to L4 is equal to or greater than a first threshold.Furthermore, the first vehicle-mounted device 2 recognizes the end T1 of a lane marking when the reflection intensity on all lines L1 to L4 changes from a low state due to reflection on the road surface other than the lane marking to a high state due to reflection on the lane marking, and the rate of change on all lines L1 to L4 is equal to or greater than a first threshold.

[0067] Furthermore, if the reflection intensity on all of the lines L1 to L4 changes from a high state due to reflection on the marking lines to a low state due to reflection on the road surface other than the marking lines, and the rate of change for at least one of the lines L1 to L4 is less than a first threshold, the first vehicle-mounted device 2 recognizes the line as a non-end T2 of the marking line.If the reflection intensity on at least one of the lines L1 to L4 changes from a low state due to reflection on the road surface other than the marking lines to a high state due to reflection on the marking line, and the rate of change is less than the first threshold, the first vehicle-mounted device 2 recognizes the line as a non-end T2 of the marking line.

[0068] Furthermore, the first vehicle-mounted device 2 associates the recognized end portion T1 or non-end portion T2 with an end portion T1 or non-end portion T2 on the same demarcation line (or the same continuous line in the case of a broken line). More specifically, if the reflectance between two adjacent end portions T1, two non-end portions T2, or between an end portion T1 and a non-end portion T2 along the longitudinal direction is high, the first vehicle-mounted device 2 associates and stores the two adjacent end portions T1, two non-end portions T2, or adjacent end portions T1 and a non-end portion T2 as being on the same demarcation line.

[0069] Another example of step S3 is a method of recognizing the ends of the lane markings based on the intensity distribution of the reflected waves reflected from reflection areas A1 to A4 scanned along the longitudinal direction of the lane markings, as shown in Figures 10 and 11. The first vehicle-mounted device 2 estimates the positions of the lane markings from the reflection intensity of the laser, and sets reflection areas A1 to A4 along the longitudinal direction of the lane markings.

[0070] As shown in Figure 10, the intensity distribution around the end of a marking line that is free of defects such as fading exhibits a rapid change in reflection intensity while maintaining a small variance. In other words, in the example shown in Figure 10, the intensity distribution in reflective area A1, which is formed at the end of the marking line, exhibits a small variance and a high reflection intensity. Reflection areas A2, A3, and A4, which are adjacent to this reflective area A1, A2, A3, and A3, respectively, are reflected by a road surface on which no marking lines are formed. Therefore, the intensity distribution in reflective areas A2 to A3 exhibits a rapid decrease in reflection intensity compared to reflective area A1 while maintaining a small variance.

[0071] On the other hand, as shown in Figure 11, the intensity distribution around the end of a marking line that has a defect such as fading has a large variance, and the reflection intensity gradually changes. That is, in the example shown in Figure 11, the intensity distribution in reflective area A1 formed on the marking line has a small variance and a large reflection intensity. Reflective area A2 adjacent to reflective area A1 and reflective area A3 adjacent to reflective area A2 are formed in parts of the marking line where defects such as fading have occurred. Therefore, the intensity distribution in reflective areas A2 and A3 has a large variance, and the reflection intensity is lower than that of reflective area A1. Furthermore, reflective area A4 adjacent to reflective area A3 is reflected on a road surface where no markings are formed, so its intensity distribution has a small variance and the reflection intensity is lower than that of reflective areas A2 and A3.

[0072] Therefore, in this embodiment, the first vehicle-mounted unit 2 recognizes the position where the reflection intensity changes while the variance of the intensity distribution of the reflective areas A1 to A4 remains small as the end T1 of the demarcation line, and recognizes the position where the reflection intensity changes without the variance of the intensity distribution of the reflective areas A1 to A4 remaining small as the non-end T2 of the demarcation line.

[0073] Specifically, the first vehicle-mounted device 2 recognizes as the end T1 of the lane marking the position where the intensity of the reflective area changes from a high state where the intensity is reflected on the lane marking while the variance of the intensity distribution of the reflective area remains below the second threshold value to a low state where the intensity is reflected on a road surface other than the lane marking. The first vehicle-mounted device 2 also recognizes as the end T1 of the lane marking the position where the intensity of the reflective area changes from a low state where the intensity is reflected on a road surface other than the lane marking while the variance of the intensity distribution of the reflective area remains below the second threshold value to a high state where the intensity is reflected on the lane marking.

[0074] The first vehicle-mounted device 2 also recognizes as a non-end T2 of the lane marking a position where the variance of the intensity distribution of the reflective area becomes equal to or greater than a second threshold and the intensity of the reflective area changes from a high state where the intensity is reflected on the lane marking to a low state where the intensity is reflected on the road surface other than the lane marking.The first vehicle-mounted device 2 also recognizes as a non-end T2 of the lane marking a position where the variance of the intensity distribution of the reflective area becomes equal to or greater than a second threshold and the intensity of the reflective area changes from a low state where the intensity is reflected on the road surface other than the lane marking to a high state where the intensity is reflected on the lane marking.

[0075] At a predetermined timing, the first vehicle-mounted device 2 transmits road surface information to the server device 3, including the positions of the end T1 and non-end T2 of the dividing line, and information about the end T1 or non-end T2 on the same dividing line associated with the recognized end T1 or T2.

[0076] Next, the lane marking information creation process performed by the control unit 32 of the server device 3 (hereinafter simply referred to as the server device 3) will be described with reference to Figures 5 and 6. The server device 3 makes the lane marking information creation process a computer program, which becomes a road surface information acquisition program that causes a computer to execute the lane marking information creation method.

[0077] When the server device 3 receives road surface information including the positions of the ends and non-ends of the lane markings, the server device 3 assigns either end information indicating the end of the lane marking, or non-end information (with a defect) or non-end information (without a defect) indicating that the lane marking is included in the lane marking but is not an end, to the information about the lane markings shown in Fig. 4. In more detail, as shown in Fig. 5, the server device 3 assigns the points P1 to P2 stored as information about the lane markings to the information about the lane markings. 14If there is a point corresponding to the end or non-end position of the received lane marking, the point is assigned end information or non-end information (defective). In the example shown in Figure 5, points P1, P8, and P 13 end information is assigned to point P1, and non-end information (with defect) is assigned to point P2 indicated by diagonal lines. Note that instead of assigning either end information indicating an end of a demarcation line, or non-end information (with defect) or non-end information (without defect) indicating that a point is included in the demarcation line but is not an end, as described above, continuity information indicating that the demarcations exist consecutively may be assigned to the corresponding point information. In other words, continuity information may be assigned to point information that is not considered to be an end (non-end information (with defect) and non-end information (without defect)), and continuity information may not be assigned to point information that is considered to be an end.

[0078] The server device 3 also stores points P1 to P2 stored as information about the lane markings. 14 If there is no point corresponding to the end or non-end position of the received lane marking, the point corresponding to the end or non-end position of the lane marking is added to the information about the lane marking, and edge information or non-edge information (defective) is further assigned to that point. In the example shown in Figure 5, point P 15 , P 16 , P 18 The point P is given non-edge information (with defects) indicated by diagonal lines. 17 is added.

[0079] In addition, the server device 3 assigns non-edge information (no defect) to points between edge and non-edge points on the same lane line. In the example shown in FIG. 5, points P2 to P6, P9, and P 11 , P 14 Non-edge information (no defect) is added to

[0080] Next, the driving assistance process performed by the second vehicle-mounted device 4 will be described with reference to the flowchart in Fig. 12. The server device 3 executes this driving assistance process to implement a current position estimation method. First, the second vehicle-mounted device 4 acquires point cloud information from the LiDAR 41B (step S10). Next, the second vehicle-mounted device 4 performs object detection from the point cloud information and detects the ends of the lane markings based on the point cloud information from the LiDAR 41B (step S11).

[0081] Specifically, the second vehicle-mounted device 4 detects objects and recognizes their type (building, pedestrian, other vehicle, etc.) by performing so-called object recognition processing based on the point cloud information. This allows the second vehicle-mounted device 4 to recognize the type of object around the vehicle and the distance to that object. In addition, the second vehicle-mounted device 4 detects the ends of lane markings and recognizes the distance to those ends using the same determination method as the first vehicle-mounted device 2.

[0082] Next, the second vehicle-mounted device 4 communicates with the server device 3 to obtain map information about the area surrounding the current location detected by a signal from the GPS receiver 41A (step S12). Thereafter, the second vehicle-mounted device 4 estimates its current location using the recognized objects and the ends of the lane markings as landmarks (step S13). That is, in step S13, the second vehicle-mounted device 4 estimates its current location based on the positional relationship between the positional information of the features included in the map information and the position of the object recognized in step S10. The second vehicle-mounted device 4 also estimates its current location by comparing the positional relationship between the information about the lane markings included in the map information and the position of the ends of the lane markings recognized in step S11.

[0083] Thereafter, the second vehicle-mounted device 4 performs driving assistance based on the estimated current position (step S14), and the process returns to step S10 again.

[0084] According to the above-described embodiment, a laser beam is transmitted to a road surface, and a wave reflected by the road surface is received. The reflected wave is then reflected and the end of the lane marking formed on the road surface is recognized based on the intensity of the reflected wave. This allows the end of the lane marking to be recognized with high accuracy. Furthermore, the recognized end of the lane marking can be used as a landmark to estimate the current position, thereby improving the accuracy of estimating the position of the vehicle 6 in the direction of travel.

[0085] Furthermore, according to the above-described embodiment, a laser is transmitted from the LiDAR 23B arranged on the measurement vehicle 5. In this way, by installing the LiDAR 23B on the measurement vehicle 5, it is possible to easily recognize the ends of lane markings over a wide range.

[0086] Furthermore, according to the above-described embodiment, the ends of the demarcation lines are recognized based on changes in reflection intensity on the lines L1 to L4 along the longitudinal direction of the demarcation lines, thereby improving the recognition accuracy of the ends of the demarcation lines.

[0087] Furthermore, according to the above-described embodiment, the ends of the lane markings are recognized based on the change in reflection intensity along the longitudinal direction of the lines L1 to L4 that are aligned perpendicular to the longitudinal direction, thereby further improving the recognition accuracy of the ends of the lane markings.

[0088] Furthermore, according to the above-described embodiment, the intensity of the reflected waves changes along the longitudinal direction on all lines L1 to L4, and the positions where the rate of change is equal to or greater than the first threshold are recognized as the ends of the demarcation lines. This prevents the positions where the ends cannot be accurately recognized due to defects such as blurring from being recognized as the ends of the demarcation lines.

[0089] Furthermore, according to the above-described embodiment, the intensity of the reflected waves changes along the longitudinal direction on all lines L1 to L4, and positions where the rate of change is less than the first threshold are recognized as non-ends, not ends, of the marking lines. This makes it possible to recognize as non-ends of marking lines points where defects such as blurring make it difficult to accurately recognize ends.

[0090] Furthermore, according to the above-described embodiment, the ends of the lane markings are recognized based on the intensity distribution of the reflected waves from the reflection areas A1 to A4 scanned along the longitudinal direction of the lane markings, thereby improving the recognition accuracy of the ends of the lane markings.

[0091] Furthermore, according to the above-described embodiment, the position where the intensity of the reflected wave changes while the variance of the intensity distribution of the reflected wave remains below the second threshold is recognized as the end of the marking line, thereby preventing a location where the end cannot be accurately recognized due to defects such as blurring from being recognized as the end of the marking line.

[0092] Furthermore, according to the above-described embodiment, the position where the variance of the intensity distribution of the reflected wave becomes equal to or greater than the second threshold and the intensity of the reflected wave changes is recognized as a non-end of the marking line. This makes it possible to recognize as a non-end of the marking line a location where an end cannot be accurately recognized due to defects such as blurring.

[0093] In the above-described embodiment, the information about the lane markings included in the map information is provided with at least one of end information indicating the end of the lane markings and continuity information indicating that the lane marks are continuous. This allows the end of the lane markings to be used as landmarks for estimating the current position, thereby improving the accuracy of estimating the position of the vehicle 6 in the direction of travel.

[0094] In the above-described embodiment, the information about the lane markings included in the map information is provided with end information indicating the end of the lane marking, and non-end information indicating a part of the lane marking that is included in the lane marking but is not the end. This allows the end of the lane marking to be used as a landmark for estimating the current position, thereby improving the accuracy of estimating the position of the vehicle 6 in the direction of travel.

[0095] In the above-described embodiment, the information about the latitude and longitude of the latitude line included in the map information is point information indicating the latitude and longitude of the latitude line, and edge information and non-edge information are added to the point information. This makes it possible to easily add edge information and non-edge information.

[0096] In the above-described embodiment, the non-edge information is provided in a distinguishable manner, i.e., non-edge information (no defect) indicating a portion of the lane marking that is free of defects, and non-edge information (defect) indicating a portion of the lane marking that is defective. This makes it possible to avoid using defective portions of the lane marking as landmarks, thereby further improving the accuracy of estimating the position of the vehicle 6 in the direction of travel.

[0097] In the above-described embodiment, the second in-vehicle device 4 acquires edge information indicating the edge of the lane marking from the server device 3, which is an external device, and estimates the current position of the vehicle 6 based on the acquired edge information and information indicating the edge of the lane marking on the road surface recognized by the LiDAR 41B installed in the vehicle 6. This improves the accuracy of position estimation in the direction of movement of the vehicle 6.

[0098] In the above-described embodiment, end information and non-end information are added to points constituting information about lane markings already stored in the storage unit 31 of the server device 3, but the present invention is not limited to this. The server device 3 may also create new information about lane markings based on road surface information received from the first vehicle-mounted device 2. In this case, when the server device 3 receives road surface information including the positions of end and non-end points of lane markings, for example, it creates information about lane markings as shown in FIG. 13.

[0099] The server device 3 also receives the point P 20 , P 27 , P 30 , P 31 , P 34 , P 37 The server device 3 also assigns edge information to the point P 26 , P33 Next, the server device 3 assigns non-edge information (defective) to points P corresponding to edges and non-edges on the same lane line. 20 -P 26 Between, point P 27 -P 30 Between, point P 31 -Point P 33 Between, point P 34 -Point P 37 Points P are arranged at equal intervals along the lot line between 21 ~P 25 , point P 28 ~P 29 , point P 32 , point P 35 ~P 36 and the point P 21 ~P 25 , point P 28 ~P 29 , point P 32 , point P 35 ~P 36 Add non-edge information (no defect) to the

[0100] The server device 3 receives the point P indicating the position of the end from the first vehicle-mounted device 2. 20 , P 27 , P 30 , P 31 , P 34 , P 37 It is also possible to add continuity information indicating that the sections are continuous (in other words, information indicating that the section is not an end) to points other than the above.

[0101] In the example shown in FIG. 13, the server device 3 adds the point P 28 ~P 29 , point P 32 , point P 35 ~P 36 and the point P 28 ~P 29 , point P 32 , point P 35 ~P 36 However, this is not limited to this.

[0102] In addition, in this embodiment, the first on-vehicle device 2 is mounted on the measurement vehicle 5 dedicated to measurement, and the second on-vehicle device 4 is mounted on the vehicle 6 receiving driving assistance, but this is not limited to this. The second on-vehicle device 4 mounted on the vehicle 6 receiving driving assistance may have the functions of both the first on-vehicle device 2 and the second on-vehicle device 4.

[0103] In the above-described embodiment, the first vehicle-mounted device 2 recognizes the edge and non-edge portions, but this is not limiting. The first vehicle-mounted device 2 may transmit only the point cloud information to the server device 3, and the server device 3 may recognize the edge and non-edge portions.

[0104] In the above-described embodiment, the non-edge information can be distinguished between non-edge information (with defects) and non-edge information (without defects), but this is not limited to this. It is also possible to assign non-edge information to points on the demarcation line other than those corresponding to the edges, so that it is not necessary to distinguish between defective and non-defective parts.

[0105] In the above-described embodiment, an edge portion having defects such as fading is recognized as a non-edge portion, but this is not limited to this. An edge portion may be recognized as an edge portion even if it has defects such as fading.

[0106] In the above-described embodiment, the server device 3 assigns edge information and non-edge information to the information about the lane markings. However, this is not limiting. For example, an operator at a map manufacturer may manually assign edge information and non-edge information based on road surface information transmitted from the first vehicle-mounted device 2. In the above-described embodiment, map information including information about lane markings is stored and held in the server device 3 (storage unit 31). However, the first vehicle-mounted device 2 and the second vehicle-mounted device 4 may also store and hold at least a portion of the map information by appropriately communicating with the server device 3. The process of assigning edge information and non-edge information described above may be performed on the measurement vehicle side (first vehicle-mounted device 2). That is, the process of recognizing the edges and non-edges of lane markings (step S3 in FIG. 7) and the process of generating map information, including the process of assigning edge information or non-edge information, may be performed by the server device 3 or on the measurement vehicle side (first vehicle-mounted device 2).

[0107] In the above-described embodiment, the sensor unit 23 mounted on the first in-vehicle device 2 includes, as an example, a LiDAR 23B. Alternatively, or in addition, the sensor unit 23 mounted on the first in-vehicle device 2 may include a photographing unit 23C that photographs the road surface on which the measurement vehicle 5 travels, as shown in FIG. 14 . In this case, the control unit 21 of the first in-vehicle device 2 acquires an image of the road surface photographed by the photographing unit 23C from the photographing unit 23C, and recognizes the ends of the lane markings formed on the road surface based on brightness information, etc., of the acquired image. The photographing unit 23C is configured, for example, by a stereo camera that can detect the distance to an object to be photographed.

[0108] Specifically, when executing the road surface information acquisition process illustrated in FIG. 7, the first vehicle-mounted device 2 (control unit 21) acquires an image of the road surface captured by the image capture unit 23C from the image capture unit 23C, instead of or in addition to "acquiring point cloud information" in step S1. Then, as in step S3, the first vehicle-mounted device 2 (control unit 21) recognizes the end and non-end portions of the lane markings formed on the road surface during travel from the acquired image (step S3), and then returns to step S1. More specifically, in step S3, the first vehicle-mounted device (control unit 21) converts the acquired captured image into an orthoimage and recognizes the end and non-end portions of the lane markings (white lines) using brightness information, etc., of the orthoimage. As another example, the image capture unit 23C may be configured with a monocular camera, and an image of the road surface captured by the monocular camera may be acquired and associated with the point cloud information acquired from the LiDAR 23B. In this case, it is possible to recognize the edges and non-edges of the dividing line (white line) on the point cloud information acquired from the LiDAR 23B (in other words, as 3D information) using brightness information in the captured image.

[0109] Here, the brightness of the road surface in the captured image is high in the areas where markings are formed, and low in the areas where markings are not formed. Also, at the end of the marking line without defects such as fading, as shown in Figure 8, the brightness intensity changes suddenly along each of the lines L1 to L4 along the longitudinal direction of the marking line in the captured image. Also, at the end of the marking line with fading, as shown in Figure 9, the reflection intensity changes gradually along each of the lines L1 to L4 along the longitudinal direction of the marking line in the captured image.

[0110] Therefore, the first vehicle-mounted device 2 (controller 21) sets lines L1 to L4 along the longitudinal direction of the lane markings on the captured image, and based on the results of detecting and recognizing changes in brightness along these lines, can recognize the ends and non-ends of the lane markings (white lines) in the same way as in the above-described embodiment. In other words, the "brightness information" of the lane markings in the captured image of this modified example can be treated as equivalent to the "reflection intensity" of the lane markings in the above-described embodiment. In this case, the "reflection intensity" in Figures 8 to 11 can be appropriately interpreted as "brightness" in the captured image.

[0111] Furthermore, the sensor unit 41 mounted on the second in-vehicle device 4 includes the LiDAR 41B as an example, but instead of or in addition to this, the sensor unit 41 mounted on the second in-vehicle device 4 may include an image capturing unit 41C that captures an image of the road surface on which the vehicle 6 is traveling, as in the first in-vehicle device 2. That is, the second in-vehicle device 4 may recognize the end of the lane marking from the captured image using the above-mentioned method, and may execute the driving assistance processing described in FIG.

[0112] The present invention is not limited to the above-described embodiment, and can be implemented in various modifications without departing from the gist of the present invention. [Explanation of symbols]

[0113] 2 First onboard device (road surface information acquisition device) 3 Server device (external device, lane marking information creation device) 5. Measurement vehicle (mobile) 6. Vehicles (moving objects) 23B LiDAR (sensor, transmitter, receiver) 31 Storage unit (storage device) 41B LiDAR (sensor) L1~L4 lines A1~A4 Reflective Area

Claims

[Claim 1] Electromagnetic waves transmitted to a road surface are reflected by the road surface and received. A road surface information acquisition method for recognizing an end of a marking line formed on the road surface based on the intensity of the reflected wave, The electromagnetic waves are transmitted from a sensor disposed on a moving object, A road surface information acquisition method characterized by recognizing the end of a lane marking based on changes in the intensity of the reflected wave along the longitudinal direction of the lane marking.

Images