WO2019235004A1

WO2019235004A1 - Calibration device and electronic mirror system

Info

Publication number: WO2019235004A1
Application number: PCT/JP2019/008266
Authority: WO
Inventors: 彩乃宮下; 清水　直樹
Original assignee: クラリオン株式会社
Priority date: 2018-06-07
Filing date: 2019-03-04
Publication date: 2019-12-12
Also published as: JP7226930B2; JP2019213108A

Abstract

In order for a calibration device to precisely determine, from an image of a camera installed in a vehicle, the real space positional relation of the vehicle to another vehicle captured by the camera, a camera ECU (30) is provided with: a road state detection unit (31) for detecting the state of a curb on a road (400) on which the vehicle (200) is traveling on the basis of multiple images (P1) of the road (400) captured at different points in time chronologically by the camera (10) installed in the vehicle (200); a storage unit (32) for storing, in the form of a table consisting of a calibration grid (40), correspondence relations between the positions of a subsequent vehicle (400) in the images (P1) and positions along the road (400) in real space in a reference state in which the road (400) is assumed to be straight and level; and a correction unit (33) for correcting the grid (40) stored in the storage unit (32) on the basis of the state of the curb on the road (400) detected by the road state detection unit (31).

Description

Calibration apparatus and electronic mirror system

The present invention relates to a calibration device and an electronic mirror system.

When the vehicle driver changes lanes, the driver looks at the side mirrors provided facing both sides of the vehicle and visually confirms the image of the rear area reflected by the side mirror.

In recent years, instead of a side mirror, a so-called electronic mirror system has been developed that includes a camera facing rearward and a monitor installed in a vehicle interior that displays an image of a rear area captured by the camera ( For example, see Patent Document 1). According to the electronic mirror system, the aerodynamic resistance of the vehicle can be reduced by replacing the camera with a physical size smaller than that of the side mirror.

Japanese Patent Laid-Open No. 2018-6936

According to the electronic mirror system, it is possible to detect the following vehicle existing in the rear area based on the image captured by the camera. However, if the driving road is curved, the exact position of the following vehicle along the road (the driving lane and the distance from the vehicle) is detected based on the position of the following vehicle in the image. Difficult to do.

The present invention has been made in view of the above circumstances, and based on an image of a camera provided in the own vehicle, the positional relationship between the other vehicle reflected in the image of the camera and the own vehicle in real space is accurately obtained. It is an object of the present invention to provide a calibration device and an electronic mirror system that can be used.

The first aspect of the present invention is the state of the curve of the road based on a plurality of images respectively taken by cameras mounted on the host vehicle at a plurality of time points different in time series on the road on which the host vehicle is traveling. Correspondence between a position on the image and a position along the road in the real space of a portion shown in the image in a reference state on the assumption that the road is a straight line A calibration apparatus comprising: a storage unit that stores a relationship; and a correction unit that corrects the correspondence stored in the storage unit based on the state of the road curve detected by the road state detection unit It is.

According to a second aspect of the present invention, a camera that is mounted on a host vehicle and is provided at a site where a reflector is to be provided, and that captures an image of the outside of the host vehicle, and an image captured by the camera, is the reflector. An image display device provided in the passenger compartment of the host vehicle that displays a horizontally inverted image as reflected and viewed, and a calibration device according to the present invention, wherein the image display device is a calibration device. It is an electronic mirror system which performs display which emphasizes the approaching other vehicle by the signal output from the notification output unit of the apparatus.

According to the calibration device and the electronic mirror system according to the present invention, based on the image of the camera provided in the own vehicle, the positional relationship between the other vehicle reflected in the image of the camera and the own vehicle in the real space is accurately determined. Can be sought.

1 is a block diagram showing an electronic mirror system 1 that is an example of an electronic mirror system according to the present invention, including a camera ECU (Electronic Control Unit) 30 that is an example of a calibration device according to the present invention. FIG. A vehicle (hereinafter referred to as a host vehicle) equipped with the electronic mirror system shown in FIG. 1 is traveling in the left lane of a horizontal road that is not curved, for example, three lanes on one side. It is the figure represented typically. It is an example of the image which expressed the image which the camera shown in FIG. 2 image | photographed horizontally reversed. It is a schematic diagram which shows the grating | lattice for calibration which the memory | storage part has memorize | stored. It is a schematic diagram which shows an example when the grating | lattice for calibration was image | photographed with the camera and it superimposed on the image reversed horizontally. It is the figure which represented typically the state which the own vehicle is drive | working the left lane of the horizontal road which curves gently in the right direction of 3 lanes on one side from the viewpoint from the top. It is an example of the image which expressed the image which the camera shown in FIG. 6 image | photographed horizontally reversed. FIG. 7 is a diagram illustrating a state in which a grid corrected to follow the road curve illustrated in FIGS. 6 and 7 is superimposed on the image illustrated in FIG. 6. From the perspective of the vehicle from above, for example, when your vehicle is driving in a right-hand lane that diverges from a two-lane highway on one side to a left-hand lane. It is the figure represented typically. FIG. 10 is an example of an image obtained by inverting the image captured by the camera illustrated in FIG. It is a figure which shows the state which superimposed the grating | lattice correct | amended so that it might follow the curve of the road shown to FIG. 9, 10 on the image shown in FIG. It is a schematic representation of how the end point has moved from the initial position in the image as the vehicle is running.

Hereinafter, specific embodiments of the electronic mirror system according to the present invention will be described with reference to the drawings.

<Configuration of electronic mirror system>
FIG. 1 is a block diagram showing an electronic mirror system 1 which is an example of an electronic mirror system according to the present invention, including a camera ECU (Electronic Control Unit) 30 which is an example of a calibration apparatus according to the present invention. FIG. A vehicle 200 equipped with the electronic mirror system 1 shown below (hereinafter referred to as the own vehicle 200) is traveling from the upper side in a state in which the vehicle is traveling on the left lane L1 of a horizontal road 400 that is not curved, for example, three lanes on one side. FIG. 3 schematically shows a viewpoint, and FIG. 3 is an example of an image P1 that is obtained by horizontally inverting the image taken by the camera 10 shown in FIG.

The electronic mirror system 1 shown in FIG. 1 includes a camera 10, an in-vehicle network (CAN: Controller Area Network) 20, a camera ECU 30, and a monitor 90.

The camera 10 is provided as an alternative to the left and right side mirrors at positions on both sides where the left and right side mirrors of the host vehicle 200 should be respectively attached. That is, one camera 10 is provided on each of the left and right, and each camera 10 captures a rear region on the side where the host vehicle 200 is mainly installed. Specifically, as shown in FIG. 2, the camera 10 provided on the right side of the traveling direction indicated by the arrow of the host vehicle 200 is installed toward the rear of the right side of the host vehicle 200, and Shoot the area. Although not shown, the camera 10 provided on the left side of the traveling direction indicated by the arrow of the host vehicle 200 is installed toward the rear left side of the host vehicle 200, and the left rear region is defined. Take a picture.

Then, when the image taken by the right camera 10 shown in FIG. 2 is reversed left and right, for example, an image P1 shown in FIG. 3 is obtained. If the right side mirror is installed in the host vehicle 200, the driver of the host vehicle 200 visually recognizes the right rear image reflected by the side mirror, but the image reflected by the side mirror is Left and right are reversed with respect to the image incident on the mirror.

For a driver who is accustomed to the reflected image reflected in the side mirror, when the image captured by the camera 10 is displayed on the monitor 90 as it is, the image familiar to the side mirror is an inverted image. , You may feel uncomfortable or confused.

Therefore, the camera ECU 30 performs a process of horizontally reversing the image captured by the camera 10 to display the horizontally reversed image P1 on the monitor 90 as shown in FIG.

The in-vehicle network 20 is a line that shares various types of information (vehicle speed, steering angle, gear position, etc.) of the host vehicle 200.

<Configuration of camera ECU>
The camera ECU 30 includes a road state detection unit 31, a storage unit 32, a correction unit 33, an object recognition unit 34, a travel lane detection unit 35, a distance calculation unit 36, and a notification output unit 37. .

The road state detection unit 31 detects the curve state of the road 400 on which the host vehicle 200 is traveling. Specifically, the state of the curve is detected based on a plurality of left and right reversed images P1 captured by the camera 10 at a plurality of time points different in time series on the road 400 on which the host vehicle 200 is traveling. In this embodiment, the end points 411 of the white line 410 that separates the lanes L1 and L2 (see FIG. 2) of the road 400 in a plurality of images P1 captured by the camera 10 at a plurality of time points that are different in time series and reversed left and right. For example, the degree of the curve of the road 400 is detected based on a time-series change in the position of the upper left corner point).

Note that the road state detection unit 31 may detect a curve state based on a change in time-series position of a photographed object other than the end point 411 of the white line 410.

FIG. 4 is a schematic diagram showing the calibration grid 40 stored in the storage unit 32. FIG. 5 shows an example when the calibration grid 40 is captured by the camera 10 and superimposed on the horizontally inverted image P1. It is a schematic diagram shown.

The storage unit 32 stores a calibration grid 40 shown in FIG. This lattice 40 is the position and real space on the image P1 of each part on the road surface of the road 400 shown in the image P1 in a reference state assuming that the road 400 on which the vehicle 200 is traveling is a straight line. It is an example of the table (map) showing the correspondence with the position along the road 400 in FIG.

That is, when this grid 40 is superimposed on the image P1 captured by the camera 10, for example, as shown in FIG. 5, by associating the position of each part on the road surface of the road 400 in the image P1 with the position in the grid 40, The position of each part (the position in the coordinate space on the image) on the road surface of the road 400 is associated with the position in the real space (the position in the coordinate space of the real space).

4 is set based on so-called camera parameters such as an angle of view and a focal length of the camera 10, an attachment position to the host vehicle 200, and an orientation. The lines M1, M2, M3, M4, M5, M6, and M7 extending in the lateral direction of the grid 40 are equidistant intervals in the front-rear direction of the host vehicle 200 in the real space (for example, 10 [m] intervals in the real space) ) And the lines N1, N2, N3, N4, N5, and N6 extending in the vertical direction are equidistant intervals in the vehicle width direction of the host vehicle 200 in the real space (for example, 1 [m] intervals in the real space) It corresponds to. That is, the lattice 40 corresponds to a rectangular area in the front-rear direction 60 [m] and the vehicle width direction 5 [m] of the host vehicle 200 in the real space.

The correction unit 33 corrects the lattice 40 stored in the storage unit 32 based on the curve state of the road 400 detected by the road state detection unit 31. Specifically, for example, when the road state detection unit 31 detects that the road 400 is in a straight line that is not curved, the correction unit 33 uses the lattice 40 in the reference state stored in the storage unit 32. Without being corrected, as shown in FIG. 5, it is directly superimposed on the image P1.

On the other hand, for example, when the road 400 detected by the road condition detection unit 31 is curved, the correction unit 33 corrects the lattice 40 in the reference state so as to follow the detected curve of the road 400. I do.

Here, FIG. 6 schematically illustrates a state in which the host vehicle 200 is traveling on the left lane L1 of a horizontal road that is gently curved in the right direction of, for example, three lanes on one side, from the viewpoint from above. FIGS. 7 and 7 are examples of an image P1 obtained by reversing the image P0 captured by the camera 10 shown in FIG. 6, and FIG. 8 is corrected so as to follow the curve of the road 400 shown in FIGS. FIG. 7 is a diagram showing a state in which a grid 40 ′ is superimposed on the image P1 shown in FIG. 6.

Further, FIG. 9 shows that the own vehicle 200 exits a side road lane L1 branched from the two-lane highway on the left side, for example, and curves to the right of the side lane L1. FIG. 10 is a diagram schematically illustrating the state of the camera 10 from above, FIG. 10 is an example of an image P1 obtained by horizontally inverting the image P0 captured by the camera 10 illustrated in FIG. 9, and FIG. FIG. 10 is a diagram showing a state in which a lattice 40 ′ corrected to follow the curve of the road 400 shown is superimposed on the image P <b> 1 shown in FIG. 9.

For example, when the road state detection unit 31 detects that the road 400 is gently curved in the right direction as shown in FIGS. 6 and 7, the correction unit 33 sets the grid 40 to be superimposed on the image P1 in FIG. Then, it is transformed into a lattice 40 ′ along the detected curve of the road 400 and superimposed on the image P 1 of FIG. 6 as shown in FIG. Thereby, it is possible to specify the positional relationship between each part on the road surface of the road 400 and the target object in contact with the road surface with the host vehicle 200 along the curve of the road 400 in the real space.

Similarly, when the road state detection unit 31 detects that the road 400 is branched to the left as shown in FIGS. 9 and 10 and then curved in the right direction, the correction unit 33 displays the image P1 in FIG. The grid 40 to be superimposed is transformed into a grid 40 ′ along the detected curve of the road 400 and superimposed on the image P 1 of FIG. 9 as shown in FIG. Thereby, the positional relationship between each part on the road surface of the road 400 and the vehicle 200 along the curve of the road 400 in the real space can be specified.

As shown in FIGS. 3, 7, 10, etc., the object recognizing unit 34 follows

vehicles

301, 302,... (Hereinafter referred to as succeeding vehicles 301) running behind the host vehicle 200 in the image P <b> 1. To detect. The object recognizing unit 34 stores in advance a pattern such as a contour shape or a pattern mainly on the front surface of a vehicle including a motorcycle or the like in the storage unit 32, and the stored pattern is subjected to pattern matching or the like with respect to the image P1. The subsequent vehicle 301 is detected. In addition, the object recognition unit 34 detects the position of the subsequent vehicle 301 or the like in the image P1 by detecting the position of the detected subsequent vehicle 301 or the like on the road surface.

The traveling lane detection unit 35 creates a road 400 in the real space based on the grid 40 obtained by correcting the position of the succeeding vehicle 301 or the like recognized by the object recognition unit 34 on the image P1 by the correction unit 33. The position along the road 400 in the real space is specified by converting to the position along the road, and the lane in which the succeeding vehicle 301 or the like is traveling in the real space is specified.

That is, for example, as shown in FIG. 3, in a straight line where the road 400 is not curved, the lattice 40 remains the lattice 40 in the reference state, and the lattice 40 in the reference state is superimposed on FIG. Accordingly, the lane is specified in the real space of each succeeding vehicle 301 or the like.

In this case, as shown in FIG. 5, the traveling lane detector 35, the following vehicle 301 travels in the same lane L <b> 1 as the own vehicle 200, and the following vehicle 302 is adjacent to the right of the traveling lane L <b> 1 of the own vehicle 200 ( It is determined that the vehicle travels in the adjacent lane (L2) and the following vehicle 303 is traveling in the lane (adjacent lane) L3 adjacent to the right of the adjacent lane L2.

Further, in the case shown in FIG. 8, since the lattice 40 in the reference state is deformed from the lattice 40 ′, the traveling lane detection unit 35 follows each of the following vehicles 301 according to the state where the deformed lattice 40 ′ is superimposed. Identify the lane in real space such as.

In this case, as shown in FIG. 8, the traveling lane detection unit 35 causes the subsequent vehicle 302 to travel in the lane (adjacent lane) L2 adjacent to the right of the traveling lane L1 of the host vehicle 200, and the

subsequent vehicles

303, 304, 305. Specifies that the vehicle is traveling in a lane (adjacent lane) L3 adjacent to the right of the adjacent lane L2.

Similarly, in the case shown in FIG. 11, since the lattice 40 in the reference state is deformed from the lattice 40 ′, the traveling lane detector 35 detects each succeeding vehicle according to the state in which the deformed lattice 40 ′ is superimposed. A lane is specified in a real space such as 301.

In this case, the traveling lane detector 35 specifies that the following

vehicles

301 and 306 are traveling in the same lane L1 as the host vehicle 200, as shown in FIG.

The distance calculation unit 36 obtains the distance along the curve of the road 400 between the position of the own vehicle 200 and the position of the succeeding vehicle 301 in the real space based on the grid 40 obtained by the correction by the correction unit 33. .

The notification output unit 37 includes a lane L2 adjacent to the lane L1 in which the vehicle 200 is traveling, and the distance calculation unit in which the lane in which the subsequent vehicle 301 detected by the travel lane detection unit 35 is traveling. When the distance calculated by 36 is shortened in time series, that is, when a subsequent vehicle traveling in the adjacent lane L2 is approaching the host vehicle 200, a signal for notifying the approach of the subsequent vehicle is monitored. Output to 90.

The monitor 90 visually displays an image P1 obtained by horizontally inverting the image P0 taken by the camera 10 by the camera ECU 30. At this time, when the camera ECU 30 outputs a signal that informs the adjacent lane L2 of the following vehicle having a higher traveling speed than the own vehicle 200 so as to approach the own vehicle 200, the monitor 90 displays, for example, FIG. As shown in FIG. 3, a vehicle detection frame 350 surrounding the detected subsequent vehicle 302 is superimposed on the image P1.

<Action>
Next, the operation of the electronic mirror system 1 of the present embodiment will be described. The camera 10 installed on the right side of the host vehicle 200 captures a right rear area of the host vehicle 200 at a predetermined cycle, and the captured image is input to the camera ECU 30. The camera ECU 30 converts each image periodically input from the camera 10 into a left-right inverted image P1.

The road state detection unit 31 detects the state of the curve of the road 400 on which the host vehicle 200 is traveling based on a plurality of images P1 that are periodically input to the camera ECU 30 and reversed left and right. The detection of the state of the curve is based on each image P1 taken at different timings in time series when the end point 411 of the specific white line 410 shown in FIG. 2 moves backward as the host vehicle 200 travels. It is determined by the position transition above.

FIG. 12 schematically shows how the end point 411 moves from the initial position R1 to the position R2 ′, the position R3 ′, the position R4 ′, and the position R5 ′ in the image P1 as the host vehicle 200 travels. It is a thing. The road condition detection unit 31 detects the positions R1, R2 ′, R3 ′, R4 ′, R5 ′ of the end points 411 that move with time on the image P1, for example, as the positions of the XY orthogonal coordinates in FIG.

In FIG. 12, the position R1, the position R2, the position R3, the position R4, and the position R5 are vehicle speeds (CAN20 at that time) of the host vehicle 200 with a steering angle of 0 [degree] in a reference state where the road 400 is not curved. Represents the position where the end point 411 is predicted to move. The predicted positions R1, R2, R3, R4, and R5 are based on a steering angle of 0 [degree] using the vehicle speed of the host vehicle 200 input from the in-vehicle network 20. The predicted positions R1, R2, R3, R4, and R5 in this reference state are aligned on a straight line.

However, the positions R1, R2 ′, R3 ′, R4 ′, and R5 ′ detected by the road condition detection unit 31 are not aligned, and the position R2 ′ is shifted from the position R2 in the X-axis direction and the Y-axis direction, respectively. The subsequent positions R3 ′, R4 ′, and R5 ′ are also shifted in the X-axis direction and the Y-axis direction from the corresponding positions R3, R4, and R5, respectively. This positional deviation in the X-axis direction and the Y-axis direction indicates that the direction of the host vehicle 200 is changing in time series, that is, the road 400 on which the host vehicle 200 is traveling is curved. Yes.

The correction unit 33 corrects the calibration grid 40 based on the curve state of the road 400 detected by the road state detection unit 31.

More specifically, a deviation amount ΔR2x in which the position R2 ′ detected by the road state detection unit 31 is displaced in the X-axis direction from the predicted position R2 in the reference state (beside the X-axis in FIG. 12). The following description is the same.) And the amount of displacement ΔR2y displaced in the Y-axis direction (described beside the Y-axis in FIG. 12; the same applies hereinafter), and the position R3 ′ from the predicted position R3 in the reference state The deviations ΔR3x and ΔR3y and R4 ′ which are displaced in the X-axis direction and the Y-axis direction are shifted from the predicted position R4 in the reference state in the X-axis direction. The amount ΔR4x and the amount of displacement ΔR4y, R5 ′ that is displaced in the Y-axis direction are displaced in the Y-axis direction from the amount of displacement ΔR5x that is displaced in the X-axis direction from the predicted position R5 in the reference state. Based on the deviation amount ΔR5y, the lattice 40 shown in FIG. 2 is deformed. Let

At this time, the movement destination positions other than the positions R2, R3, R4, and R5 in the lattice 40 are the movement destination positions R2 ′, R3 ′, and R4 ′ of these positions R2, R3, R4, and R5. , R5 ′ can be calculated as representative points, whereby the lattice 40 can be deformed along the curved road 400.

Thereby, based on the image P1 of the camera 10 provided in the own vehicle 200, the positional relationship of the subsequent vehicle shown in the image P1 of the camera 10 with the own vehicle 200 along the curve of the road 400 in the real space. Can be obtained accurately.

Note that the amount of movement of the position in the grid 40 due to the curve of the road 400 is small in the immediate rear of the host vehicle 200 and increases as the distance from the host vehicle 200 increases. Therefore, the correction amount for deformation of the grid 40 is calculated. The calculation may be performed only for a partial region P2 behind the host vehicle 200 shown in FIG. Thereby, the calculation amount for correction | amendment can be reduced and calculation load can be suppressed. For the camera ECU 30 mounted on a moving body such as a vehicle with limited resources, suppression of calculation load is one of the important issues.

On the other hand, the target recognition unit 34 detects the following vehicle from the image P1. The traveling lane detector 35 identifies the lane in which the subsequent vehicle is traveling based on the corrected grid 40 '.

Similarly, the distance calculation unit 36 obtains the distance along the curve of the road 400 from the own vehicle 200 to the following vehicle detected in the image P1 based on the corrected grid 40 ′.

Thus, the camera ECU 30 identifies the detected lane in which each subsequent vehicle travels and the distance along the curve of the road 400 from the own vehicle 200 to each subsequent vehicle. And the alerting | reporting output part 37 while driving the lane L2 adjacent to the lane L1 where the own vehicle 200 drive | works among the detected subsequent vehicles, and the following vehicle and the own vehicle which drive the adjacent lane L2, When the distance along the curve of the road 400 is reduced in time series, that is, the notification output unit 37 detects a succeeding vehicle traveling in the adjacent lane L2 approaching the host vehicle 200, the monitor 90 A notification signal is output.

As shown in FIG. 8, the monitor 90 displays a vehicle detection frame 350 that surrounds the succeeding vehicle 302 as shown in FIG. It is displayed superimposed on the image P1.

Thereby, it is possible to alert the driver of the own vehicle 200 looking at the monitor 90 not to change the lane to the adjacent lane L2.

On the other hand, among the detected succeeding vehicles, the notification output unit 37 follows the following vehicle that travels in the lane L1 in which the host vehicle 200 travels and the succeeding vehicle that travels in the adjacent lane L3. Even if the vehicle approaches the vehicle 200, no notification signal is output. Similarly, even if the following vehicle travels in the adjacent lane L2, the notification output unit 37 does not output a notification signal even when the subsequent vehicle is not approaching the host vehicle 200.

Since there is no notification signal output from the notification output unit 37, the monitor 90 displays the image P1 without adding a vehicle detection frame 350 that alerts the driver to any subsequent vehicle.

As a result, it is possible to prevent the driver of the own vehicle 200 looking at the monitor 90 from performing unnecessary alerts not to change the lane to the adjacent lane L2. The frequent occurrence of unnecessary notifications can be prevented or suppressed.

As described above, according to the camera ECU 30 and the electronic mirror system 1 of the present embodiment, based on the image P1 of the camera 10 provided in the host vehicle 200, the following vehicle 301 or the like shown in the image P1 of the camera 10, The positional relationship with the own vehicle 200 along the road 400 in the real space can be accurately obtained.

In addition, although this embodiment demonstrated only the positional relationship of the own vehicle 200 and the following vehicle mainly on the right rear of the own vehicle 200 image | photographed with the camera 10 provided in the right side of the own vehicle 200, the own vehicle The positional relationship between the own vehicle 200 and the following vehicle, mainly the rear left side of the own vehicle 200, taken by the camera 10 provided on the left side of the own vehicle 200 is similarly implemented.

Moreover, although this embodiment demonstrated only the positional relationship of the following vehicle and the own vehicle 200 which exist behind the own vehicle 200, the calibration apparatus and electronic mirror system which concern on this invention are not only a subsequent vehicle. The positional relationship between the preceding vehicle existing ahead of the host vehicle 200 and the host vehicle 200 can be similarly applied. In this case, the camera which faces the front of the own vehicle is applied.

In the embodiment described above, the grid 40 is deformed in accordance with the degree of bending of the road 400, and the position of the succeeding vehicle in the image P1 is obtained by the lane and the distance along the lane represented by the deformed grid 40 ′. However, the image P1 is converted into an image of another coordinate system specified by the horizontal lines M1, M2,... And the vertical lines N1, N2,. The position (lane, distance from own vehicle 200, etc.) of the following vehicle may be specified on the image of another coordinate system obtained as described above.

Cross-reference of related applications

This application claims priority based on Japanese Patent Application No. 2018-109139 filed with the Japan Patent Office on June 7, 2018, the entire disclosure of which is fully incorporated herein by reference.

Claims

A road state detection unit that detects the state of the curve of the road based on a plurality of images respectively taken by cameras mounted on the own vehicle at a plurality of time points different in time series on the road on which the own vehicle is traveling. When,
A storage unit that stores a correspondence relationship between a position on the image and a position along the road in a real space of a portion in the image in a reference state on the assumption that the road is a straight line;
A calibration device comprising: a correction unit that corrects the correspondence stored in the storage unit based on a state of a curve of the road detected by the road state detection unit.
The road state detection unit detects the state of a curve of the road based on the position of an end point of a line that divides the lane in the plurality of images respectively taken at a plurality of time points different in time series. The calibration apparatus according to 1.
An object recognition unit for detecting other vehicles in the image;
Based on the correspondence obtained by correcting by the correction unit, the position of the other vehicle recognized by the target recognition unit along the road in the real space is specified, and the vehicle in the real space The calibration device according to claim 1, further comprising a distance calculation unit that calculates a distance along the road between the host vehicle and the other vehicle.
An object recognition unit for detecting other vehicles in the image;
Based on the correspondence obtained by correcting by the correction unit, the position of the other vehicle recognized by the target recognition unit along the road in the real space is specified, and the vehicle in the real space The calibration device according to any one of claims 1 to 3, further comprising a travel lane detection unit that identifies a lane in which another vehicle is traveling.
A traveling lane detector that identifies the lane in which the other vehicle is traveling in the real space based on the correspondence obtained by the correction performed by the correcting unit;
The lane in which the other vehicle is detected detected by the travel lane detector is a lane adjacent to the lane in which the host vehicle is traveling, and the distance calculated by the distance calculator is time-series. The calibration device according to claim 3, further comprising: a notification output unit that outputs a signal that notifies the approach of the other vehicle when the vehicle is shorter.
A camera that is mounted on the vehicle and is provided at a site where a reflector should be provided;
An image display device provided in a cabin of the host vehicle, which displays an image obtained by reversing the image captured by the camera as viewed from the reflecting mirror;
A calibration device according to claim 5,
The said image display apparatus is an electronic mirror system which performs the display which emphasizes the said other vehicle which approaches by the signal output from the said alerting | reporting output part.