Image adjustment apparatus of in-vehicle camera

Abstract

To adjust an image of an in-vehicle camera without requiring complicated operation or using a large space around a vehicle.SOLUTION: A processor 152 of an ECU 150 includes: an image acquisition unit 152a which acquires a first captured image that represents the shape of the body of a vehicle 100 with an in-vehicle camera 110 mounted thereon, the first captured image being captured by the in-vehicle camera 110; a reference image acquisition unit 152b which acquires a first reference image that represents the shape of the body, the first reference image being stored in advance and serving as a criterion for adjusting the image of the in-vehicle camera 110; and an image adjustment unit 152d which adjusts the image captured by the in-vehicle camera on the basis of misalignment between the shape of the body represented by the first reference image and the shape of the body represented by the first captured image.SELECTED DRAWING: Figure 7

Description

Technical Field

[0001] The present invention relates to an image adjustment device for an in-vehicle camera.

Background Art

[0002] Conventionally, when adjusting a radar and a camera, it is known that the adjustment man-hours can be significantly reduced by arranging the target of the camera at the front end of the vehicle (see Patent Document 1).

Prior Art Document

Patent Document

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, the technology described in the above patent document is premised on a vehicle equipped with both a radar and a camera that monitor the same direction (for example, the front). Therefore, in a vehicle that does not have a radar and requires individual adjustment of a plurality of cameras that image the periphery of the vehicle, the technology of the above patent document cannot be applied.

[0005] When adjusting the camera of a vehicle without a radar, a target for adjustment photographed by the camera is used. In this case, however, there is a problem that a large space around the vehicle is required to install the target. Further, the target for adjustment needs to be accurately arranged based on the vehicle position, and a considerable amount of man-hours is required for arranging the target.

[0006] Therefore, an object of the present invention is to provide an image adjustment device for an in-vehicle camera that can adjust the image of the in-vehicle camera without using a large space around the vehicle and without involving complicated operations.

Means for Solving the Problems

[0007] The gist of the present disclosure is as follows.

[0008] (1) An image acquisition unit that acquires a first captured image captured by an in-vehicle camera, the first captured image representing the shape of the body of a vehicle on which the in-vehicle camera is mounted; A reference image acquisition unit that acquires a first reference image stored in advance and serving as a reference for adjusting the image of the in-vehicle camera, the first reference image representing the shape of the body; An image correction unit that corrects the image captured by the in-vehicle camera based on the deviation between the shape of the body represented in the first reference image and the shape of the body represented in the first captured image; An in-vehicle camera image adjustment device comprising the above.

[0009] (2) The reference image acquisition unit acquires a second reference image captured by the first in-vehicle camera that has been adjusted, the second reference image representing an object on the ground; The image acquisition unit acquires a second captured image captured by a second in-vehicle camera that has not been adjusted, the second captured image representing the object; The image adjustment unit adjusts the image captured by the second in-vehicle camera based on the deviation between the object represented in the second reference image and the object represented in the second captured image, for the in-vehicle camera image adjustment device according to (1) above.

[0010] (3) The object extends along the side surface of the vehicle; The first in-vehicle camera is a camera that images the side of the vehicle, and the second in-vehicle camera is a camera that images the front or rear of the vehicle, for the in-vehicle camera image adjustment device according to (2) above.

[0011] (4) The shape of the body of the vehicle includes the shape of a member that is attached to the body and integrated with the body for the adjustment, for the in-vehicle camera image adjustment device according to (1) or (2) above.

Effect of the Invention

[0012] According to the present invention, it is possible to adjust the image of an in-vehicle camera without using a wide space around the vehicle and without involving complicated operations.

Brief Description of the Drawings

[0013]

Figure 1

Figure 2

Figure 3A

Figure 3B

Figure 4

Figure 5

Figure 6A

Figure 6B

Figure 7

Figure 8

Figure 9A

Figure 9B

Figure 9C

Figure 9D

Figure 9E

Figure 10

Figure 11

Embodiments for Carrying Out the Invention

[0014] Hereinafter, several embodiments according to the present invention will be described with reference to the drawings. However, these descriptions are intended merely as examples of preferred embodiments of the present invention and are not intended to limit the present invention to such specific embodiments.

[0015] FIG. 1 is a schematic configuration diagram of a vehicle system 1000 according to one embodiment. The vehicle system 1000 is mounted on a vehicle such as an automobile, and includes an in-vehicle camera 110, a notification device 120, and an electronic control unit (ECU: Electronic Control Unit, hereinafter referred to as ECU) 150. Each of the in-vehicle camera 110, the notification device 120, and the ECU 150 is communicably connected via an in-vehicle network conforming to a standard such as Controller Area Network (CAN).

[0016] The in-vehicle camera 110 includes a two-dimensional detector composed of an array of photoelectric conversion elements sensitive to visible light, such as a CCD or a C-MOS, and an imaging optical system that forms an image of the area to be photographed on the two-dimensional detector. The in-vehicle camera 110 photographs the surroundings of the vehicle (for example, in front of the vehicle) and generates an image representing the environment around the vehicle. That is, the in-vehicle camera 110 captures an image representing the environment around the vehicle. The in-vehicle camera 110 performs photographing at a predetermined photographing cycle (for example, 1 / 30 second to 1 / 10 second). The in-vehicle camera 110 may be composed of a stereo camera and may be configured to acquire the distance from the parallax of the left and right images to each structure on the image. Each time the in-vehicle camera 110 generates an image, the generated image is output to the ECU 150 via the in-vehicle network.

[0017] The notification device 120 includes a display device and a speaker. The display device is composed of, for example, a liquid crystal display (LCD), is provided near the meter panel or the dashboard, and displays and outputs a notification in response to an instruction from the ECU 150. The speaker outputs a notification as sound in response to an instruction from the ECU 150.

[0018] The ECU 150 is an aspect of the image adjustment device for an in-vehicle camera according to the present disclosure. The ECU 150 includes a processor 152, a memory 154, and a communication interface 156. The processor 152 includes one or a plurality of CPUs (Central Processing Units) and peripheral circuits thereof. The processor 152 may further include other arithmetic circuits such as a logical arithmetic unit, a numerical arithmetic unit, or a graphic processing unit. The memory 154 includes, for example, a volatile semiconductor memory and a non-volatile semiconductor memory, and stores data related to the processing according to the present embodiment. The communication interface 156 includes an interface circuit for connecting the ECU 150 to the in-vehicle network.

[0019] The in-vehicle camera 110 includes a front camera 20, two side cameras 30 on the left and right, and a rear camera 40. FIG. 2 is a plan view of the vehicle 10 seen from above, showing the arrangement of the front camera 20, the two side cameras 30 on the left and right, and the rear camera 40 and their viewing angles. In FIG. 2, the viewing angle θ1 of the front camera 20 is indicated by two dashed lines 22. Also, the viewing angle θ2 of each of the left and right side cameras 30 is indicated by two dashed lines 32. Further, the viewing angle θ3 of the rear camera 40 is indicated by two dashed lines 42.

[0020] In the images captured by the front camera 20, the two side cameras 30 on the left and right, and the rear camera 40, the points on the image are coordinate-transformed to the points on the ground. Then, by synthesizing the images of each camera, an image of the vehicle 10 viewed from above is created. The image of the vehicle 10 viewed from above may be displayed on a display device.

[0021] In this embodiment, the images captured by these cameras are adjusted with respect to a reference. More specifically, first, the image of the side camera 30 is adjusted with respect to the reference. Then, based on the image of the side camera 30, the images of the front camera 20 and the rear camera 40 are adjusted respectively.

[0022] FIGS. 3A, 3B, and 4 are schematic diagrams for explaining a method of adjusting the image of the side camera 30. The side camera 30 is attached to the door mirror of the vehicle 10 that can be folded. FIGS. 3A and 3B show how the viewing angle of the side camera 30 changes when the door mirror is folded. That is, the viewing angle θ2 of the side camera 30 in the state where the door mirror is not folded is indicated by the dashed line 32 in FIG. 3A. On the other hand, the viewing angle θ2 of the side camera 30 in the state where the door mirror is folded is indicated by the dashed line 32 in FIG. 3B.

[0023] As shown in FIG. 3B, in the state where the door mirror is folded, the body of the vehicle 10 is included in the range of the viewing angle θ2 of the side camera 30. Therefore, the shape of the body is represented in the image captured by the side camera 30. Based on the shape of the body represented in the image, the deviation of the image of the side camera 30 can be adjusted.

[0024] FIG. 4 is a schematic diagram showing an example of the shape of the body that can be used as a reference when adjusting the image of the side camera 30 in the state where the door mirror 34 is folded. As shown in FIG. 3B, in the state where the door mirror 34 is folded, the shape of the body behind the door mirror 34 is included in the range of the viewing angle θ2 of the side camera 30. Therefore, in the state where the door mirror 34 is folded, the shapes such as the boundary 46 between the rear door and the front door and the edge 48 of the window of the rear door are represented in the image captured by the side camera 30. The shapes of these boundaries 46 or the window edges 48 are used as a reference when adjusting the image of the side camera 30.

[0025] A reference image in which the boundary 46 or the window edge 48 is represented in the state where the image of the side camera 30 is properly adjusted in the state where the door mirror 34 is folded is stored in the memory 154 in advance. When the position of the boundary 46 or the window edge 48 in the image captured by the side camera 30 in the state where the door mirror 34 is folded is deviated from the position of the boundary 46 or the window edge 48 of the pre-stored reference image, the image of the side camera 30 is adjusted so that the boundary 46 or the window edge 48 of the captured image coincides with the boundary 46 or the window edge 48 of the reference image. Thereby, the viewing angle, the vertical, horizontal and left - right positions, and the angle (tilt) of the image of the side camera 30 are properly adjusted with respect to the body of the vehicle 10.

[0026] As described above, when adjusting the camera of a vehicle without a radar, a target for adjustment is used. However, in order to arrange the target for adjustment, a large flat area (for example, about 10 m × 5 m) including the vehicle 10 may be required. In addition, misrecognition may occur, such as the camera recognizing something other than the target, and an additional area may be required to prevent the target from being misrecognized. When adjusting the camera at the dealership of the vehicle 10, it is difficult to secure such a large area. Furthermore, the target for adjustment needs to be accurately arranged based on the vehicle position, which also causes a problem that a considerable amount of man-hours is required for arranging the target.

[0027] According to the method for adjusting the image of the in-vehicle camera 110 according to the present embodiment as described above, since the adjustment can be performed based on the shape of the body of the vehicle 10, targets, markers, etc. that each camera shoots for adjustment are unnecessary, and a large space for adjustment is also unnecessary. As a result, the adjustment can be performed even in a narrow occupied space of only the host vehicle. In addition, it is no longer necessary to accurately arrange the target at a position measured based on the body of the host vehicle at a distant location around the vehicle, and the man-hours for adjustment can be significantly reduced.

[0028] FIG. 5, FIG. 6A, and FIG. 6B are schematic diagrams for explaining a method for adjusting the images of the front camera 20 and the rear camera 40. In this case, as shown in FIG. 5, the vehicle 10 is parked on the ground where a white line 50 is drawn. The white line 50 is previously drawn on the ground at assumed positions extending along the left and right sides of the vehicle 10. In this state, the white line 50 on the ground is photographed by the front camera 20, the side camera 30, and the rear camera 40.

[0029] As shown in FIG. 2, there is an overlapping range 36 indicated by hatching between the viewing angle of the side camera 30 indicated by the dashed line 32 and the viewing angle of the front camera 20 indicated by the dashed line 22. Similarly, there is an overlapping range 36 indicated by hatching between the viewing angle of the side camera 30 indicated by the dashed line 32 and the viewing angle of the rear camera 40 indicated by the dashed line 42. In FIG. 5, the overlapping range 36 is schematically shown as an area surrounded by a dashed-dotted line.

[0030] If the image of the front camera 20 or the rear camera 40 is displaced with respect to the image of the side camera 30, a displacement occurs in the overlapping range 36 between the position of the white line 50 represented in the image captured by the side camera 30 and the position of the white line 50 represented in the image captured by the front camera 20 or the rear camera 40.

[0031] FIG. 6A is a diagram showing a composite image 55 in which points on the images of the rear camera 40 and the side camera 30 in the overlapping range 36 at the right rear of the vehicle 10 shown in FIG. 5 are coordinate-transformed to points on the ground and then combined. In the example shown in FIG. 6A, a state where the positions of the white line 50a represented in the image generated by the rear camera 40 and the white line 50b represented in the image generated by the side camera 30 are displaced is shown.

[0032] Since the image of the side camera 30 has been adjusted by the method described above, the image of the rear camera 40 is adjusted based on the white line 50b represented in the image generated by the side camera 30. Specifically, as shown in FIG. 6B, the viewing angle, the up-down, left-right positions, and the angle (tilt) of the image of the rear camera 40 are adjusted so that the white line 50a represented in the image captured by the rear camera 40 coincides with the position of the reference white line 50b.

[0033] When adjusting the image of the front camera 20, the image of the front camera 20 is adjusted based on the white line 50b represented in the image generated by the side camera 30 in the overlapping range 36 in the same manner as the adjustment of the image of the rear camera 40.

[0034] According to the method for adjusting the images of the front camera 20 and the rear camera 40 as described above, if there is a space where two white lines 50 are drawn at an interval slightly wider than the width of the vehicle 10, the adjustment can be performed. Therefore, if there is a space slightly wider than the vehicle 10, image adjustment is possible.

[0035] FIG. 7 is a schematic diagram showing a functional block of a processor 152 of an ECU 150 for realizing the above-described processing. The processor 152 of the ECU 150 includes an image acquisition unit 152a, a reference image acquisition unit 152b, a comparison unit 152c, and an image adjustment unit 152d. Each of these units included in the processor 152 is, for example, a functional module realized by a computer program operating on the processor 152. That is, the functional block of the processor 152 is composed of the processor 152 and a program (software) for operating the same. Further, the program may be recorded in a memory 154 provided in the ECU 150 or a recording medium connected from the outside. Alternatively, each of these units included in the processor 152 may be a dedicated arithmetic circuit provided in the processor 152.

[0036] The image acquisition unit 152a of the processor 152 acquires a first captured image captured by the in-vehicle camera 110, and the first captured image represents the shape of the body of the vehicle 10 on which the in-vehicle camera 110 is mounted. Specifically, the image acquisition unit 152a acquires an image captured by the side camera 30, and the image represents the shape of the body of the vehicle 10. Note that the image acquisition unit 152a may acquire an image captured by the front camera 20 and the rear camera 40, and the image represents the shape of the body of the vehicle 10.

[0037] In addition, the image acquisition unit 152a acquires a second captured image captured by the second in-vehicle camera 110 that has not been adjusted, and in which an object on the ground is represented. Specifically, when adjusting the image of the rear camera 40, the image acquisition unit 152a acquires an image captured by the rear camera 40, in which a point on the image is coordinate-transformed to a point on the ground, and the white line 50a on the ground is represented. Note that the image acquisition unit 152a may perform the coordinate transformation process. When adjusting the image of the front camera 20, the image acquisition unit 152a may acquire an image captured by the front camera 20, in which a point on the image is coordinate-transformed to a point on the ground, and the white line on the ground is represented.

[0038] The reference image acquisition unit 152b of the processor 152 acquires a first reference image that is pre-stored and serves as a reference for adjusting the image of the in-vehicle camera 110, and in which the shape of the body of the vehicle 10 equipped with the in-vehicle camera 110 is represented. Specifically, the reference image acquisition unit 152b acquires, as a reference image for adjusting the image of the side camera 30, an image pre-stored in the memory 154 and representing the shape of the body of the vehicle 10. As described above, the reference image represents, as the shape of the body of the vehicle 10, the boundary 46 between the rear door and the front door, the edge 48 of the window of the rear door, and the like.

[0039] In addition, the reference image acquisition unit 152b acquires a second reference image captured by the first in-vehicle camera that has been adjusted, and in which an object on the ground is represented. Specifically, the reference image acquisition unit 152b acquires, as a reference image serving as a reference for adjusting the image of the front camera 20 or the rear camera 40, an image captured by the side camera 30, in which a point on the image is coordinate-transformed to a point on the ground, and the white line 50b on the ground is represented. Note that the reference image acquisition unit 152b may perform the coordinate transformation process.

[0040] The comparison unit 152c of the processor 152 compares the reference image acquired by the reference image acquisition unit 152b with the captured image captured by the in-vehicle camera 110 to be adjusted. Specifically, when adjusting the image of the side camera 30, the comparison unit 152c compares the shape of the body represented in the reference image stored in advance in the memory 154 with the shape of the body represented in the image captured by the side camera 30, and measures the deviation between the shape of the body represented in the reference image and the shape of the body represented in the captured image. Also, when adjusting the image of the rear camera 40, the comparison unit 152c compares the white line 50b represented in the reference image captured by the side camera 30 with the white line 50a represented in the image captured by the rear camera 40, and measures the deviation between the white line 50b and the white line 50a.

[0041] The image adjustment unit 152d of the processor 152 adjusts the image captured by the in-vehicle camera 110 based on the deviation between the shape of the body represented in the first reference image and the shape of the body represented in the first captured image. Specifically, when adjusting the image of the side camera 30, the image adjustment unit 152d adjusts the image of the side camera 30 so that the body shape represented in the image captured by the side camera 30 matches the body shape represented in the reference image stored in advance in the memory 154, which serves as a reference for adjusting the image of the side camera 30. The adjustment may be performed automatically or based on an instruction from an operator. At this time, for example, the body shape represented in the image captured by the side camera 30 is identified by template matching between the template image of the body shape stored in the memory 154 in advance and the image captured by the side camera 30, and the image of the side camera 30 is adjusted so that the identified body shape matches the body shape represented in the reference image.

[0042] Further, the image adjustment unit 152d adjusts the image captured by the second in-vehicle camera 110 based on the deviation between the object represented in the second reference image and the object represented in the second captured image. Specifically, when adjusting the image of the rear camera 40, the image adjustment unit 152d adjusts the image of the rear camera 40 so that the position of the white line 50a represented in the image captured by the rear camera 40 coincides with the white line 50b represented in the image captured by the side camera 30. At this time, for example, the white line 50b represented in the image captured by the side camera 30 is identified by template matching between the template image of the white line stored in the memory 154 in advance and the image captured by the side camera 30, and the white line 50a represented in the image captured by the rear camera 40 is identified by the same template matching, and the image of the rear camera 40 is adjusted so that the position of the white line 50a coincides with the white line 50b.

[0043] FIG. 8 is a flowchart showing the processing performed by the processor 152 of the ECU 150 for each predetermined control cycle. Hereinafter, the processing for adjusting the images of the side camera 30 and the rear camera 40 will be described. First, the image acquisition unit 152a acquires the image captured by the side camera 30 (step S10). Next, the reference image acquisition unit 152b acquires, as a reference image for adjusting the image of the side camera 30, a reference image representing the shape of the body of the vehicle 10 stored in the memory 154 in advance (step S11). Next, the comparison unit 152c compares the body shape represented in the reference image stored in the memory 154 in advance, which is a reference for adjusting the image of the side camera 30, with the body shape represented in the image captured by the side camera 30, and measures the deviation between the body shape represented in the reference image and the body shape represented in the captured image (step S12). Then, it is determined whether or not the measured deviation is equal to or less than a predetermined value (step S14).

[0044] When the deviation between the body shape represented in the reference image and the body shape represented in the captured image is equal to or less than a predetermined value in step S12, the image adjustment unit 152d adjusts the image captured by the side camera 30 so that the body shape represented in the image captured by the side camera 30 matches the body shape represented in the reference image stored in advance in the memory 154 (step S16). On the other hand, when the deviation exceeds the predetermined value in step S12, since the physical attachment of the side camera 30 is greatly deviated and exceeds the adjustment range by the image, the notification device 120 notifies that readjustment of the attachment position of the side camera 30 is necessary (step S17).

[0045] Next, the image acquisition unit 152a acquires the image captured by the rear camera 40 (step S18). Next, the reference image acquisition unit 152b acquires, as a reference image for adjusting the image of the rear camera 40, an image captured by the adjusted side camera 30 in which the white line 50b on the ground is represented (step S19). Next, the comparison unit 152c compares the white line 50b represented in the reference image captured by the side camera 30, which is a reference for adjusting the image of the rear camera 40, with the white line 50a represented in the image captured by the rear camera 40, and measures the deviation between the white line 50b and the white line 50a (step S20). Then, it is determined whether or not the measured deviation is equal to or less than a predetermined value (step S22).

[0046] When the deviation between the white line 50b and the white line 50a is equal to or less than a predetermined value in step S22, the image adjustment unit 152d adjusts the image of the rear camera 40 based on the image of the side camera 30 so that the white line 50a matches the white line 50b (step S24). On the other hand, when the deviation between the white line 50b and the white line 50a exceeds the predetermined value in step S22, since the physical attachment position of the rear camera 40 is greatly deviated and exceeds the adjustment range by the image, the notification device 120 notifies that readjustment of the attachment position of the rear camera 40 is necessary (step S17).

[0047] In the above description, a method of adjusting the image of the side camera 30 based on the body shape has been described. However, the images of the front camera 20 or the rear camera 40 may also be adjusted based on the body shape. As described above, when adjusting both the image of the side camera 30 and the image of the front camera 20 or the rear camera 40, after adjusting the image of the side camera 30, the image of the front camera 20 or the rear camera 40 is adjusted based on the image of the side camera 30. On the other hand, for example, when the vehicle 10 does not include the side camera 30, when individually adjusting the image of the front camera 20 or the rear camera 40 without using the image of the side camera 30, the image of the front camera 20 or the rear camera 40 is adjusted based on the body shape.

[0048] Figures 9A to 9E are diagrams showing the image 60 of the front camera 20, and are schematic diagrams showing a method of adjusting the image of the front camera 20 based on the shape of the body (bumper 70) of the vehicle 10. Figure 9A shows a case where the range of the image 60 of the front camera 20 is in an appropriate position with respect to the position of the bumper 70 represented in the image 60 of the front camera 20. Figure 9B shows a case where the range of the image 62 is shifted to the left with respect to the position of the bumper 70 represented in the image 62 of the front camera 20. Similarly, Figure 9C shows a case where the image 62 is shifted to the right with respect to the position of the bumper 70, Figure 9D shows a case where the image 62 is shifted upward with respect to the position of the bumper 70, and Figure 9E shows a case where the image 62 is shifted downward with respect to the position of the bumper 70.

[0049] The image 60 shown in Figure 9A is stored in the memory 154 in advance as a reference image. As shown in Figures 9B to 9E, when the image 62 of the front camera 20 is shifted with respect to the position of the bumper 70, the image 62 of the front camera 20 is adjusted to match the reference image 60.

[0050] Note that the front-facing direction of the front camera 20 may not be in an appropriate position. For example, when the image 62 shown in Figure 9B becomes the reference image, the image of the front camera 20 is adjusted to match the reference image shown in Figure 9B.

[0051] Figure 10 is a schematic diagram showing a method of adjusting the image of the front camera 20 by attaching the attachment 90 in front of the front camera 20 and adjusting the image of the front camera 20 with reference to the attachment 90. In the example shown in Figure 10, the front camera 20 is supported by a support member 80 integral with the body of the vehicle 10. The attachment 90 is composed of a cylindrical member, and a recess 94 for fitting with the support member 80 is provided at one end. Further, a crosshair 96 made of a filament line, thread, wire, etc. is provided at the other end of the attachment 90.

[0052] When the attachment 90 is attached in front of the front camera 20, the recess 94 fits with the support member 80, and the attachment 90 becomes integral with the body of the vehicle 10. When the image of the front camera 20 is in an appropriate position with respect to the crosshair 96, the image representing the crosshair 96 is stored in advance in the memory 154 as a reference image. When the crosshair 96 in the image captured by the front camera 20 is deviated from the crosshair 96 in the reference image, the position, angle, and angle of view of the image captured by the front camera 20 are adjusted to match the position, angle, and angle of view of the crosshair 96 in the reference image. When the image of the front camera 20 is adjusted, the attachment 90 is removed.

[0053] FIG. 11 is a schematic diagram showing a method of adjusting an image of the front camera 20 by directly fixing a crosshair 98 made of a filament line, thread, wire, etc. in front of the front camera 20 to the body and adjusting the image of the front camera 20 with reference to the crosshair 98. In the example shown in FIG. 11, grooves, steps, etc. are provided at predetermined positions on the body of the vehicle 10, and the crosshair 98 is fixed to these grooves, steps, etc. As a result, the crosshair 98 is integrated with the body of the vehicle 10. When the image of the front camera 20 is in an appropriate position with respect to the crosshair 98, the image representing the crosshair 98 is stored in advance in the memory 154 as a reference image. The image of the front camera 20 is performed in the same manner as in the example of FIG. 10 based on the reference image. When the image of the front camera 20 is adjusted, the crosshair 98 is removed from the body.

[0054] According to the methods shown in FIGS. 10 and 11, even when the shape of the body of the vehicle 10 such as a bumper is not included in the imaging range of the front camera 20, it is possible to adjust the image of the front camera 20. Note that the methods shown in FIGS. 10 and 11 can also be applied to the adjustment of the rear camera 40 and may be applied to the adjustment of the side camera 30.

[0055] As described above, according to the present embodiment, since the image of the in-vehicle camera 110 can be adjusted based on the shape of the body of the vehicle 10, targets, markers, etc. that each camera shoots for adjustment are not required, and a large space for adjustment is also not required. In addition, it is not necessary to accurately arrange the target at a position measured based on the body of the own vehicle at a location away from the vehicle around the vehicle, and the man-hours for adjustment can be significantly reduced.

Explanation of Signs

[0056] 20 Front camera 30 Side camera 40 Rear camera 110 In-vehicle camera 150 Electronic control unit (ECU) 152 Processor 152a Image acquisition unit 152b Reference Image Acquisition Unit 152d Image Adjustment Unit

Claims

1. An image acquisition unit that acquires a first captured image captured by an in-vehicle camera, the first captured image representing the shape of the body of a vehicle on which the in-vehicle camera is mounted; A reference image acquisition unit that acquires a first reference image stored in advance, which is a reference for adjusting the image of the in-vehicle camera, the first reference image representing the shape of the body; An image adjustment unit that adjusts the image captured by the in-vehicle camera based on the deviation between the shape of the body represented in the first reference image and the shape of the body represented in the first captured image; An in-vehicle camera image adjustment device comprising the above.

2. The reference image acquisition unit acquires a second reference image captured by the first in-vehicle camera after the adjustment, the second reference image representing an object on the ground; The image acquisition unit acquires a second captured image captured by the second in-vehicle camera before the adjustment, the second captured image representing the object; The image adjustment unit according to claim 1, wherein the image adjustment unit adjusts the image captured by the second in-vehicle camera based on the deviation between the object represented in the second reference image and the object represented in the second captured image.

3. The object extends along the side surface of the vehicle; The first in-vehicle camera is a camera that images the side of the vehicle, and the second in-vehicle camera is a camera that images the front or rear of the vehicle. The in-vehicle camera image adjustment device according to claim 2.

4. The shape of the body of the vehicle includes the shape of a member attached to the body and integrated with the body for the adjustment. The in-vehicle camera image adjustment device according to claim 1 or 2.

Images