Depression angle correction device, depression angle correction method, and depression angle correction program

Abstract

To obtain a depression angle correction device capable of accurately correcting a depression angle; and to obtain a depression angle correction method, and a depression angle correction program therefor.SOLUTION: A depression angle correction device comprises: an acquisition part for acquiring a runway image as an image of a runway on which a vehicle travels; an extraction part for extracting a boundary of a lane based on the runway image; an estimation part for estimating a second coordinate as a coordinate in the coordinate system of the boundary of the lane at a second time point behind the first time point, based on a first coordinate as a coordinate in a preset coordinate system, and a value measured by a sensor installed in the vehicle, according to a coordinate of the boundary of the lane extracted from the runway image photographed at a first time point; and a derivation part for deriving a depression angle correction amount based on a difference between the second coordinate and a third coordinate as the coordinate in the coordinate system, according to the coordinate of the boundary of the lane extracted from the runway image photographed at the second time point.SELECTED DRAWING: Figure 2

Description

[Technical field]

[0001] The present disclosure relates to a depression angle correction device, a depression angle correction method, and a depression angle correction program. [Background technology]

[0002] Patent Document 1 discloses an image conversion device that converts an image obtained by capturing an image of the rear of a vehicle into a bird's-eye view image. This image conversion device detects lane marks from the converted image, and calculates the correction amount for the depression angle of the camera if the detected lane marks are inclined. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2002-140696 A Summary of the Invention [Problem to be solved by the invention]

[0004] The technology described in Patent Document 1 is premised on the ability to detect lane marks on both the left and right sides, and so there are cases where the depression angle cannot always be corrected with high accuracy, for example, when lane marks on only one side are detected.

[0005] The present disclosure has been made in consideration of the above circumstances, and has an object to provide a depression angle correction device, a depression angle correction method, and a depression angle correction program that can correct the depression angle with high accuracy. [Means for solving the problem]

[0006] The depression angle correction device of the first aspect includes an acquisition unit that acquires a road image, which is an image of the road along which the vehicle travels, captured by a photographing device mounted on the vehicle; an extraction unit that extracts lane boundaries based on the road image; an estimation unit that estimates a first coordinate, which is a coordinate in a predetermined coordinate system of the lane boundary extracted from the road image captured at a first time point, and a second coordinate, which is a coordinate in the coordinate system of the lane boundary at a second time point later than the first time point, based on a measurement value by a sensor mounted on the vehicle; and a derivation unit that derives a correction amount for the depression angle based on the difference between the second coordinate and a third coordinate, which is a coordinate in the coordinate system of the lane boundary extracted from the road image captured at the second time point.

[0007] According to the depression angle correction device of the first aspect, the depression angle can be corrected with high accuracy.

[0008] The depression angle correction device of a second aspect is the depression angle correction device of the first aspect, further including a correction unit that corrects the depression angle using the correction amount.

[0009] According to the depression angle correction device of the second aspect, the depression angle can be corrected with high precision.

[0010] A depression angle correction device of a third aspect is the depression angle correction device of the first or second aspect, wherein the estimation unit derives the first coordinate and the third coordinate by using longitudinal linearity data of the road.

[0011] According to the depression angle correction device of the third aspect, the depression angle can be corrected with higher accuracy.

[0012] A fourth aspect of the depression angle correction device is the depression angle correction device of any one of the first to third aspects, wherein the preset coordinate system is a road surface fixed coordinate system, and the derivation unit derives the correction amount by setting the coordinate value of the first coordinate in the vehicle width direction as the coordinate value of the third coordinate in the vehicle width direction when the vehicle is traveling straight.

[0013] According to the depression angle correction device of the fourth aspect, the calculation cost can be reduced.

[0014] A fifth aspect of the depression angle correction method involves a computer executing a process in which a road image, which is an image of the road along which the vehicle is traveling and is captured by a photographing device mounted on a vehicle, is acquired, lane boundaries are extracted based on the road image, and a first coordinate, which is a coordinate in a predetermined coordinate system of the lane boundary extracted from the road image captured at a first time point, and a measurement value by a sensor mounted on the vehicle, is used to estimate a second coordinate, which is the coordinate in the coordinate system of the lane boundary at a second time point later than the first time point, based on the first coordinate and a measurement value by a sensor mounted on the vehicle, and a depression angle correction amount is calculated based on the difference between the second coordinate and a third coordinate, which is the coordinate in the coordinate system of the lane boundary extracted from the road image captured at the second time point.

[0015] The depression angle correction program of the sixth aspect causes a computer to execute a process of acquiring a road image, which is an image of the road along which the vehicle is traveling, captured by a photographing device mounted on a vehicle, extracting lane boundaries based on the road image, estimating a second coordinate, which is the coordinate in a predetermined coordinate system of the lane boundary at a second time point later than the first time point, based on a first coordinate, which is the coordinate in a predetermined coordinate system of the lane boundary extracted from the road image captured at a first time point, and a measurement value by a sensor mounted on the vehicle, and deriving a correction amount for the depression angle based on the difference between the second coordinate and a third coordinate, which is the coordinate in the coordinate system of the lane boundary extracted from the road image captured at the second time point. Effect of the Invention

[0016] According to the present disclosure, the depression angle can be corrected with high precision. [Brief description of the drawings]

[0017] [Figure 1] FIG. 1 is a schematic side view showing an example of a configuration of a vehicle. [Diagram 2]FIG. 2 is a block diagram showing an example of a hardware configuration of the depression angle correction device. [Diagram 3] FIG. 13 is a diagram showing an example of an image in which only one side of a white line is visible; [Figure 4] FIG. 11 is a side cross-sectional view for explaining a distance error. [Diagram 5] FIG. 13 is a plan view for explaining an error in the X-axis direction of a white line point. [Figure 6] FIG. 1 is a diagram showing an example of a white line shown in road images captured at two different times. [Figure 7] FIG. 2 is a block diagram showing an example of a functional configuration of a depression angle correction device. [Figure 8] FIG. 2 is a plan view showing an example of a first coordinate, a second coordinate, and a third coordinate. [Figure 9] FIG. 13 is a diagram for explaining the influence of an error in the depression angle. [Figure 10] 10 is a flowchart showing an example of a depression angle correction process. [Figure 11] FIG. 13 is a plan view showing an example of first coordinates, second coordinates, and third coordinates according to a modified example. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0018] Hereinafter, examples of embodiments for carrying out the technology of the present disclosure will be described in detail with reference to the drawings.

[0019] First, the configuration of a vehicle 10 according to this embodiment will be described with reference to FIG. 1. As shown in FIG. 1, the vehicle 10 includes a camera 12 as an example of a photographing device mounted on the vehicle, and a depression angle correction device 14. In the following, an embodiment will be described in which an orthogonal coordinate system fixed to the camera 12 (hereinafter, referred to as a "camera fixed coordinate system") is applied as an example of a preset coordinate system. The camera fixed coordinate system according to this embodiment is composed of three axes, with the X axis being the vehicle width direction of the vehicle 10 (in this embodiment, to the right), the Y axis being the gravity direction, and the Z axis being the traveling direction of the vehicle 10. The depression angle correction device 14 according to this embodiment is applied to an autonomous vehicle that allows switching between autonomous driving and manual driving, and a vehicle equipped with a driving support device.

[0020] Camera 12 is a monocular camera equipped with an image sensor such as a CCD (Charge Coupled Device) image sensor or a CMOS (Complementary Metal Oxide Semiconductor) image sensor. Camera 12 is installed facing forward at the rearview mirror position inside the vehicle cabin, captures an image of the road ahead of vehicle 10, and outputs an image of the road along which vehicle 10 is traveling (hereinafter referred to as a "road image") to depression angle correction device 14. Camera 12 captures the road image according to a preset frame rate. In the following, a description will be given using an orthogonal coordinate system consisting of two axes, with the vertical direction of the image being the i-axis and the horizontal direction of the image being the ix-axis, as the coordinate system of the image captured by camera 12 (hereinafter referred to as an "image coordinate system").

[0021] Next, the hardware configuration of the depression angle correction device 14 according to this embodiment will be described with reference to Fig. 2. As shown in Fig. 2, the depression angle correction device 14 includes a CPU (Central Processing Unit) 20, a ROM (Read Only Memory) 21, a RAM (Random Access Memory) 22, and an in-vehicle communication I / F (Interface) 23. The CPU 20, the ROM 21, the RAM 22, and the in-vehicle communication I / F 23 are connected to each other so as to be able to communicate with each other via a bus 27. An example of the depression angle correction device 14 is a computer such as an ECU (Electronic Control Unit).

[0022] The CPU 20 is an example of a processor, and executes various programs and controls various parts. That is, the CPU 20 reads out a program from the ROM 21 and executes the program using the RAM 22 as a working area.

[0023] The ROM 21 serving as a storage unit stores a depression angle correction program 30 and vertical line shape data 32. The vertical line shape data 32 includes, for example, position information represented by a combination of longitude and latitude, and vertical line shape data of the road at the position indicated by the position information. Examples of this vertical line shape data include the height of the road surface or the curvature of the vertical curve relative to the traveled distance.

[0024] The longitudinal line shape data 32 includes, for example, accumulated data in which altitude information measured by a high-precision positioning device when the vehicle and other vehicles have traveled in the past is stored against the travel distance of the vehicle. The longitudinal line shape data 32 may also include longitudinal line shape data in the vehicle travel direction measured by a distance measuring sensor such as LiDAR (Light Detection And Ranging), a stereo camera, or a monocular moving stereo camera. The longitudinal line shape data 32 may also include, for example, longitudinal line shape data based on design data at the time of road design.

[0025] The RAM 22 temporarily stores programs and data as a working area. The in-vehicle communication I / F 23 is an interface for connecting to the camera 12 and the sensor 16. The interface uses a communication standard based on the CAN (Controller Area Network) protocol. The sensor 16 includes various sensors mounted on the vehicle 10. The sensor 16 includes, for example, a vehicle speed sensor that measures the vehicle speed, and a yaw rate sensor that measures the yaw rate.

[0026] In this embodiment, a case will be described in which the depression angle of the camera 12 includes a steady error, that is, the depression angle error continues within a certain range for a certain period of time. This is the case, for example, when the road on which the vehicle 10 runs does not have any unevenness (e.g., a step) that would cause the vehicle 10 to sway up and down, that is, when there is no instantaneous change in the depression angle that occurs when the vehicle 10 goes over a step.

[0027] In such a case, as shown in FIG. 3, the lane boundary on only one side of the lane on which the vehicle 10 is traveling may be captured in the road image. In this embodiment, a case where a white line is used as a lane mark indicating the lane boundary will be described. In this case, the depression angle cannot be calculated by a method of calculating the depression angle from the vanishing points of the white lines on both the left and right sides. For this reason, it is considered to correct the error in the depression angle using a correction amount for the depression angle that is set in advance as a fixed value.

[0028] In this case, as shown in FIG. 4, when a white line point on the road image is reverse perspective projected onto the road surface on a side cross-sectional view, a distance error occurs due to an error in the depression angle. The distance error here means the difference between Z1 and Z2 in the example shown in FIG. 4. When this distance error occurs, an error in the X-axis direction of the white line point occurs on a plan view, as shown in FIG. 5. Thus, in order to avoid misidentifying the position of the white line, it is necessary to accurately correct the error in the depression angle.

[0029] Furthermore, when the vehicle 10 is traveling on a straight road, the change in the shape of the white line captured in the monocular camera image is relatively small between two frames of road images captured at two different times, as shown in Fig. 6. In this case, it is difficult to extract corresponding white line points between two frames of road images using a method using a moving stereo camera or model matching of the shape of the white line.

[0030] The depression angle correction device 14 of this embodiment has the function of correcting the depression angle even when the depression angle contains a steady-state error, when white lines on both sides cannot be detected from the road image but only one side is detected, and when there is relatively little change in the shape of the white line between two frames of road image taken at two different times.

[0031] Next, the functional configuration of the depression angle correction device 14 according to this embodiment will be described with reference to Fig. 7. As shown in Fig. 7, the depression angle correction device 14 includes an acquisition unit 40, an extraction unit 42, an estimation unit 44, a derivation unit 46, and a correction unit 48. The CPU 20 executes the depression angle correction program 30 to function as the acquisition unit 40, the extraction unit 42, the estimation unit 44, the derivation unit 46, and the correction unit 48.

[0032] The acquisition unit 40 acquires a road image captured by the camera 12 at a first time point (hereinafter referred to as a "first road image") via the in-vehicle communication I / F 23. The acquisition unit 40 also acquires a road image captured by the camera 12 at a second time point after the first time point (hereinafter referred to as a "second road image") via the in-vehicle communication I / F 23. The time difference between the first time point and the second time point is experimentally determined according to the frame rate of the camera 12, such as a period of five frames.

[0033] The extraction unit 42 extracts white lines based on the first road image by known processing. Similarly, the extraction unit 42 extracts white lines based on the second road image. For example, the extraction unit 42 assumes that there is a luminance difference on the image at the boundary between the road surface and the white lines, and extracts the white lines from the road image by an edge extraction filter such as a Sobel filter. Note that the extraction unit 42 may extract the white lines by a Hough transform or the like, assuming that the white lines are straight lines within a small region in the image. The extraction unit 42 may also extract the white lines by inputting the road image to a trained model obtained by deep learning.

[0034] The estimation unit 44 derives the coordinates (ixs, iys) of the white line point on the road image corresponding to the Z coordinate Zs, based on the longitudinal section linearity data 32 and the Z coordinate Zs at the first time point. The estimation unit 44 also derives the coordinates (ixe, iye) of the white line point on the road image corresponding to the Z coordinate Ze, based on the longitudinal section linearity data 32 and the Z coordinate Ze at the second time point. Zs and Ze are set in advance corresponding to the distance from the camera 12 to the white line point at the first time point and the second time point. For example, Zs is set to a coordinate value equivalent to 19 [m], and Ze is set to a coordinate value equivalent to 10 [m]. A specific example of the process of deriving these coordinate values ​​on the road image will be described below.

[0035] The horizontal alignment model of the white line is expressed by the following equation (1): X in equation (1) is the position of the white line Z [m] away in the X-axis direction, and f(Z) is a function that represents the horizontal alignment of the white line.

[0036]

number

[0037] The vertical linearity model of the white line is expressed by the following formula (2). In formula (2), Y is the road surface height of the white line Z [m] ahead, and g(Z) is a function expressing the vertical linearity of the white line. This function may be derived in advance based on the vertical linearity data 32, for example.

[0038]

number

[0039] When the road surface is flat, g(z) is expressed by the following equation (3). In equation (3), h is the height [m] of the camera 12 with respect to the road surface at Z=0, and φ is the depression angle [rad] of the camera 12 with respect to the road surface at Z=0. h is assumed to be known by measuring it in advance or by acquiring a measurement value by a vehicle height sensor. φ is a variable value.

[0040]

number

[0041] The coordinates (ix, iy) of the white line point on the image are expressed by the following equations (4) and (5). In equations (4) and (5), f is the focal length [m], and r h , r v are the horizontal pixel resolution [m / pixel] and the vertical pixel resolution [m / pixel], and ixc, iyc are the coordinates of the center of the image.

[0042]

number

[0043]

number

[0044] The estimation unit 44 derives the iy coordinate iys on the road image corresponding to the Z coordinate Zs by substituting the Z coordinate Zs into equation (5). Next, the estimation unit 44 selects a white line point whose iy coordinate is iys from among the white line points extracted from the first road image by the extraction unit 42, and sets the ix coordinate of the selected white line point to ixs. In this way, the estimation unit 44 derives the coordinates (ixs, iys) of the white line point on the road image corresponding to the Z coordinate Zs.

[0045] The estimation unit 44 also derives the iy-coordinate iye on the road image corresponding to the Z-coordinate Ze by substituting the Z-coordinate Ze into equation (5). Next, the estimation unit 44 selects a white line point whose iy-coordinate is iye from among the white line points extracted from the second road image by the extraction unit 42, and sets the ix-coordinate of the selected white line point to ixe. In this way, the estimation unit 44 derives the coordinate (ixe, iye) of the white line point on the road image corresponding to the Z-coordinate Ze.

[0046] The estimation unit 44 may assume that the road is a local plane and derive iys and iye without using the longitudinal section linearity data 32. In this case, the estimation unit 44 uses equation (3) as g(Z) in equation (5). In this case, φ is assumed to be known by measuring in advance and includes a certain amount of error.

[0047] Next, the estimation unit 44 derives the coordinates of the white line point in the camera fixed coordinate system by inverse perspective projection. Specifically, the estimation unit 44 derives an X coordinate Xs corresponding to Zs and ixs based on Zs, the derived ixs, and equation (4). (Xs, Zs) are the coordinates of the white line extracted from the first road image, and are an example of a first coordinate that is a coordinate in the camera fixed coordinate system. Furthermore, the estimation unit 44 derives an X coordinate Xe corresponding to Ze and ixe based on Ze, the derived ixe, and equation (4). (Xe, Ze) are the coordinates of the white line extracted from the second road image, and are an example of a third coordinate that is a coordinate in the camera fixed coordinate system.

[0048] The estimation unit 44 also derives a gradient αs of the tangent of the white line on the road image at the coordinates (ixs, iys) of the white line point with respect to the iy axis. The estimation unit 44 also derives a gradient αe of the tangent of the white line on the road image at the coordinates (ixe, iye) of the white line point with respect to the iy axis.

[0049] Furthermore, the estimation unit 44 estimates (Xt, Zt) as a second coordinate, which is the coordinate of the white line point in the camera fixed coordinate system at the second time point, based on (Xs, Zs) and the vehicle speed and yaw rate as examples of measured values ​​by the sensor 16. Since the vehicle 10 is traveling, the point with the coordinate (Xs, Zs) at the first time point will move relatively by the second time point in the camera fixed coordinate system. The estimation unit 44 derives this relative movement amount by an algorithm based on known knowledge of vehicle motion. In this way, the estimation unit 44 estimates the coordinate (Xt, Zt) of the white line point in the camera fixed coordinate system at the second time point.

[0050] FIG. 8 shows an example of the relationship between (Xs, Zs), (Xe, Ze), and (Xt, Zt). FIG. 8 illustrates an example in which Ze and Zt are equal, but if Ze and Zt are different, Xt may be corrected by an interpolation calculation so that Zt matches Ze. As shown in FIG. 9, when an error is included in the depression angle, the coordinates (Xt, Zt) estimated based on the white line point extracted at the first time point deviate from the white line as the error in the depression angle increases. In the example of FIG. 9, point P1 indicates the white line point extracted at the first time point, point P2 indicates a point obtained by perspectively projecting (Xt, Zt) onto the image when the error in the depression angle is relatively small, and point P3 indicates a point obtained by perspectively projecting (Xt, Zt) onto the image when the error in the depression angle is relatively large.

[0051] The derivation unit 46 derives the depression angle correction amount Δφ based on the difference between (Xt, Zt) and (Xe, Ze) in accordance with the following formula (6a): When the inclination αs can be approximately equal to the inclination αe, the derivation unit 46 may use formula (6b) instead of formula (6a).

[0052]

number

[0053]

number

[0054] The correction unit 48 corrects the depression angle using the correction amount Δφ by changing the above formula (2) to the following formula (7).

[0055]

number

[0056] As described above, by correcting the depression angle, the white lines are detected with high accuracy, and the detected white lines are used for controlling automatic driving and driving assistance devices.

[0057] Next, the operation of the depression angle correction device 14 according to this embodiment will be described with reference to Fig. 10. The depression angle correction process shown in Fig. 10 is executed, for example, when the operation mode of the vehicle 10 is set to the automatic driving mode, when an execution command is input by the driver, etc.

[0058] In step S10 of FIG. 10, the acquisition unit 40 acquires a road image at a first time point via the in-vehicle communication I / F 23. The acquisition unit 40 also acquires a road image at a second time point via the in-vehicle communication I / F 23. In step S12, the extraction unit 42 extracts white lines based on the road image at the first time point acquired in step S10, as described above. The extraction unit 42 also extracts white lines based on the road image at the second time point acquired in step S10, as described above.

[0059] In step S14, the estimation unit 44 derives the coordinates (ixs, iys) of the white line point on the road image corresponding to the Z coordinate Zs based on the longitudinal section linearity data 32 and the Z coordinate Zs at the first time point, as described above. Also, the estimation unit 44 derives the coordinates (ixe, iye) of the white line point on the road image corresponding to the Z coordinate Ze based on the longitudinal section linearity data 32 and the Z coordinate Ze at the second time point, as described above.

[0060] In step S16, the estimation unit 44 derives the X-coordinate Xs corresponding to Zs and ixs based on Zs, ixs derived in step S14, and equation (4) as described above. Also, the estimation unit 44 derives the X-coordinate Xe corresponding to Ze and ixe based on Ze, ixe derived in step S14, and equation (4) as described above. Also, the estimation unit 44 derives the gradient αs of the tangent of the white line on the road image with respect to the iy-axis at the coordinates (ixs, iys) of the white line point. Also, the estimation unit 44 derives the gradient αe of the tangent of the white line on the road image with respect to the iy-axis at the coordinates (ixe, iye) of the white line point.

[0061] In step S18, the estimation unit 44 estimates (Xt, Zt) as the second coordinate, which is the coordinate of the white line point in the camera fixed coordinate system at the second time point, based on (Xs, Zs) and the vehicle speed and yaw rate as examples of measured values ​​by the sensor 16, as described above. In step S20, the derivation unit 46 derives the depression angle correction amount Δφ according to equation (6a) based on the difference between (Xt, Zt) and (Xe, Ze) estimated in step S18. In step S22, the correction unit 48 corrects the depression angle using the correction amount Δφ by changing the above equation (2) to the above equation (7) below. When the process of step S22 ends, the depression angle correction process ends.

[0062] As described above, according to this embodiment, even when the white line on only one side can be detected, the depression angle can be corrected with high accuracy.

[0063] In the above embodiment, a case where an orthogonal coordinate system fixed to the camera 12 is applied as the preset coordinate system has been described, but the disclosed technology is not limited to this aspect. For example, an orthogonal coordinate system fixed to the road surface on which the vehicle 10 runs (hereinafter referred to as a "road surface fixed coordinate system") may be applied as the preset coordinate system. In this embodiment, an orthogonal coordinate system consisting of three axes, with the camera 12 at the first time point as the origin, the vehicle width direction of the vehicle 10 (here, the right hand direction) as the X axis, the gravity direction as the Y axis, and the traveling direction of the vehicle 10 as the Z axis, is fixed to the road surface.

[0064] In this embodiment, as in the above embodiment, the estimation unit 44 can derive (Xs, Zs) and (Xe, Ze) by using the equations (1) to (5) through reverse perspective projection. At this time, the estimation unit 44 updates the coordinates and azimuth of the camera 12 in the road surface fixed coordinate system based on the vehicle speed and yaw rate, stores them in the ROM 21, etc., and uses them for reverse perspective projection. Figure 11 shows an example of the relationship between (Xs, Zs), (Xe, Ze), and (Xt, Zt) in this embodiment. Figure 11 illustrates a case where Ze is equal to Zt and Xs is equal to Xt.

[0065] In this embodiment, the derivation unit 46 may derive the depression angle correction amount Δφ by setting Xs=Xt when the vehicle 10 is moving straight. That is, when the vehicle 10 is moving straight, the derivation unit 46 may derive the correction amount Δφ by setting the coordinate value Xs in the vehicle width direction of the first coordinate as the coordinate value Xt in the vehicle width direction of the third coordinate. In this case, the derivation unit 46 may determine whether the vehicle 10 is moving straight based on multiple frames of road images, or may determine based on map data and the current position of the vehicle 10.

[0066] In the above embodiment, the longitudinal line shape data of the road is stored in advance in the ROM 21, but the present invention is not limited to this. The CPU 20 may derive the longitudinal line shape data from positioning information obtained from a positioning device such as a GPS (Global Positioning System) device. The CPU 20 may derive the longitudinal line shape data by inputting the longitudinal line shape data to a trained model obtained by deep learning, which is a trained model that receives a road image as input and outputs longitudinal line shape data.

[0067] In the above embodiment, the functional units that execute various processes of the depression angle correction device 14 may be realized by a processor other than a CPU. Examples of the processor in this case include a PLD (Programmable Logic Device) such as an FPGA (Field-Programmable Gate Array) whose circuit configuration can be changed after manufacture, and a dedicated electric circuit such as an ASIC (Application Specific Integrated Circuit) that is a processor having a circuit configuration designed exclusively for executing specific processes. Each functional unit of the depression angle correction device 14 may be realized by one of these various processors, or may be realized by a combination of two or more processors of the same or different types (for example, a plurality of FPGAs, and a combination of a CPU and an FPGA). More specifically, the hardware structure of these various processors is an electric circuit that combines circuit elements such as semiconductor elements.

[0068] In the above embodiment, the depression angle correction program 30 is stored (installed) in advance in the ROM 21, but the present invention is not limited to this. The depression angle correction program 30 may be provided in a form recorded on a recording medium such as a CD-ROM (Compact Disc Read Only Memory), a DVD-ROM (Digital Versatile Disc Read Only Memory), or a USB (Universal Serial Bus) memory. The depression angle correction program 30 may also be downloaded from an external device via a network. [Explanation of symbols]

[0069] 10 Vehicles 12 Camera 14 Depression angle correction device 16 Sensors 20 CPU 21 ROM 22 RAM 23 In-vehicle communication I / F 27 Bus 30 Depression correction program 32 Longitudinal Alignment Data 40 Acquisition Department 42 Extraction part 44 Estimation part 46 Derivation part 48 Correction section

Claims

1. An acquisition unit that acquires a road image, which is an image of the road along which the vehicle travels, captured by a photographing device mounted on the vehicle; An extraction unit that extracts lane boundaries based on the road image; an estimation unit that estimates a second coordinate, which is a coordinate in a coordinate system of the lane boundary at a second time point after the first time point, based on a first coordinate, which is a coordinate in a preset coordinate system, and a measurement value by a sensor mounted on the vehicle, the second coordinate, which is a coordinate in the coordinate system of the lane boundary at a second time point after the first time point; A derivation unit that derives a correction amount of the depression angle based on a difference between the second coordinate and a third coordinate, which is a coordinate of the boundary of the lane extracted from the road image captured at the second time point and is a coordinate in the coordinate system; A depression correction device including:

2. A correction unit that corrects the depression angle using the correction amount. The depression correction device according to claim 1 , further comprising:

3. The estimation unit derives the first coordinate and the third coordinate by using longitudinal linearity data of the road. The depression angle correction device according to claim 1 or 2.

4. The preset coordinate system is a road surface fixed coordinate system, The derivation unit derives the correction amount by setting a coordinate value of the first coordinate in a vehicle width direction to a coordinate value of a third coordinate in a vehicle width direction when the vehicle is traveling straight. The depression angle correction device according to claim 1 or 2.

5. Acquire a road image, which is an image of the road along which the vehicle is traveling, captured by a photographing device mounted on the vehicle; Extracting lane boundaries based on the road image; a first coordinate, which is a coordinate in a preset coordinate system of the lane boundary extracted from the road image captured at a first time point, and a second coordinate, which is a coordinate in the coordinate system of the lane boundary at a second time point after the first time point, based on a measurement value by a sensor mounted on the vehicle; A correction amount of the depression angle is derived based on a difference between the second coordinate and a third coordinate, which is a coordinate of the boundary of the lane extracted from the road image captured at the second time point and is a coordinate in the coordinate system. A depression angle correction method in which processing is performed by a computer.

6. Acquire a road image, which is an image of the road along which the vehicle is traveling, captured by a photographing device mounted on the vehicle; Extracting lane boundaries based on the road image; a first coordinate, which is a coordinate in a preset coordinate system of the lane boundary extracted from the road image captured at a first time point, and a second coordinate, which is a coordinate in the coordinate system of the lane boundary at a second time point after the first time point, based on a measurement value by a sensor mounted on the vehicle; A correction amount of the depression angle is derived based on a difference between the second coordinate and a third coordinate, which is a coordinate of the boundary of the lane extracted from the road image captured at the second time point and is a coordinate in the coordinate system. A depression angle correction program for causing a computer to execute the processing.

Images