JP7512083B2 - Tunnel face imaging system and method - Google Patents

Description

The present invention relates to a face imaging system and a face imaging method.

AI (artificial intelligence) is being used to evaluate the ground conditions in mountain tunnel construction (see, for example, Patent Document 1). To perform the image classification algorithm (deep learning) used in AI with high accuracy, a large amount of image data of consistent quality taken under uniform conditions is required.

JP 2019-023392 A

However, many of the face images acquired on-site to date have inconsistent orientation, size, and resolution, making them difficult to use as training data for AI learning, making it difficult to collect training data efficiently.
In particular, when the camera automatically corrects for lighting conditions, the appearance (color) of the face can be significantly different in the image, even if the ground is the same. When using such face photos for AI training, it is necessary to edit the contrast and resolution using image editing software, which takes a lot of work time.
Also, it is difficult to reproduce the actual color of the face during editing.

The present invention has been made in consideration of the above circumstances, and its purpose is to provide a tunnel face imaging system and a tunnel face imaging method that can reduce the variation in quality of images collected as learning data for AI that evaluates the tunnel face.

In order to solve the above-mentioned problems, one aspect of the present invention is a tunnel face imaging device having an imaging unit capable of imaging a tunnel face and a display unit that displays a guide image of the cross-sectional shape of the tunnel on a live view screen that displays the image captured by the imaging unit ; a first lighting device that is provided in the upper part of the tunnel at a position a first distance away from the tunnel face and illuminates the tunnel face; a second lighting device that is provided on the first end side of the tunnel in the horizontal direction and a second distance away from the tunnel face that is shorter than the first distance and that illuminates the tunnel face from a direction different from the direction in which the first lighting device irradiates illumination light as an auxiliary to the first lighting device; and a third lighting device that is provided on the second end side of the tunnel opposite the first end side in the horizontal direction and a second distance away from the tunnel face and that illuminates the tunnel face from a direction different from the direction in which the first lighting device irradiates illumination light as an auxiliary to the first lighting device .

Moreover, one aspect of the present invention is a face imaging method comprising the steps of: arranging a first lighting device at a position in an upper part of the tunnel a first distance away from the face; arranging a second lighting device as an auxiliary to the first lighting device at a position on the first end side of the tunnel in the horizontal direction and a second distance away from the face that is shorter than the first distance; and arranging a third lighting device as an auxiliary to the first lighting device at a position on the second end side opposite the first end side in the horizontal direction of the tunnel and the second distance away from the face, the third lighting device as an auxiliary to the first lighting device, illuminating the face from a direction different from the direction in which the first lighting device irradiates illumination light; and adjusting the attitude of a face imaging device so that a guide image of the cross-sectional shape of the tunnel matches the contour shape of the face on a live view screen on which the face is imaged, and writing data of the image captured of the face to a memory unit when an image capture command is input.

As described above, this invention can reduce the variability in the quality of images collected as learning data for the AI that evaluates the face.

1 is a schematic block diagram showing the configuration of a face imaging system 1 according to an embodiment of the present invention. FIG. 2 is a diagram for explaining the installation positions of lighting devices installed in a tunnel 10. FIG. 2 is a functional block diagram illustrating functions of the imaging device 20. FIG. 4 is a diagram showing an example of a display screen 400 displayed on a display unit 202. FIG. 13 is a diagram showing an example of a setting screen for setting imaging conditions. 1 is a flowchart illustrating an imaging method for imaging a face using the face imaging system 1.

Hereinafter, a face imaging system according to an embodiment of the present invention will be described with reference to the drawings.
Fig. 1 is a schematic block diagram showing the configuration of a tunnel face imaging system 1 according to an embodiment of the present invention, and Fig. 2 is a diagram explaining the installation positions of lighting devices installed in a tunnel 10. This tunnel face imaging system 1 is used in the tunnel 10.
A face 11 is located on the opposite side of the tunnel 10 from the portal in the direction along the tunnel axis.
Facing the face 11, there is a first side portion 12 on the side surface in a first horizontal direction, and a second side portion 13 on the side surface in the horizontal direction opposite the first direction.

The imaging device 20 captures an image of the working face 11 and stores the captured image data. The imaging device 20 is also provided with a liquid crystal display device, which can display a live view screen when capturing an image of the working face 11. The imaging device 20 is held at a position a certain distance away from the working face 11 during shooting, and writes the captured image into a storage area when the shutter button is pressed.
The imaging device 20 may be a digital camera, or may be a smartphone or tablet terminal that installs and executes an application program for implementing the functions of the imaging device 20. It is preferable that the imaging device 20 has waterproof and dustproof functions and is capable of capturing images at a high resolution (for example, about 12 million pixels or more).

The lighting device 21 is installed at a position in the upper part of the tunnel 10 (e.g., the top end) a first distance L1 away from the tunnel face, and illuminates the tunnel face 11. The first distance L1 is about 10 m (meters) to about 30 m. Here, the lighting device 21 is installed at a position where the first distance L1 is 10 m, and an image of the tunnel face 11 is taken. Thereafter, as the excavation of the tunnel 10 progresses and the distance from the tunnel face 11 to the lighting device 21 becomes from distance L11 (about 10 m) to distance L12 (about 30 m), the lighting device 21 is moved from the tunnel face 11 to a position of the first distance L1 (10 m).

The lighting device 22 is provided in the vicinity of the first side surface portion 12, on the first side surface portion side (first side surface portion 12) in the horizontal direction of the tunnel 10, and at a second distance, which is shorter than the first distance, from the tunnel face 11 to illuminate the tunnel face 11. The direction in which the lighting device 22 irradiates the illumination light may be toward the tunnel face 11, but may also be toward the second side surface portion side (second side surface portion 13).
The lighting device 23 is provided at a second distance from the tunnel face 11 on the second end (second side surface portion 13) side, which is opposite to the first end side in the horizontal direction of the tunnel 10, and illuminates the tunnel face 11. The direction in which the lighting device 23 irradiates the illumination light may be toward the tunnel face 11, but may also be toward the first side surface portion (first side surface portion 12).

These lighting devices 22 and 23 are provided as auxiliary devices for the lighting device 21. For example, the lighting device 21 is used as a main lighting device, and lighting light is irradiated from a direction different from the direction of the lighting light irradiated from this lighting device 21 to the face 11. As a result, even if there is a crack or the like in the face 11, the shadow may be strong depending on the unevenness in the mirror surface of the face 11 and the shape, width, and depth of the crack with only the lighting from the lighting device 21, so by projecting light from a direction that cancels this shadow, it is possible to weaken the shadow caused by the lighting light from the lighting device 21 and achieve a balance in which the lighting light is irradiated to the entire face 11.
Furthermore, by using an auxiliary lighting device in addition to the main lighting device, the mirror surface of the face 11 can be imaged in a more natural state.
In this way, when taking a photograph of the tunnel face, by using these lighting devices 21, 22, and 23, the illuminance of the tunnel face 11 can be ensured, thereby making it possible to ensure the quality of the photograph of the tunnel face 11.

The lighting devices 22 and 23 are installed at a position 5 to 7 m away from the tunnel face 11 and at a height H of about 1.5 m from the floor of the tunnel 10. The lighting devices 22 and 23 are installed only when photographing the tunnel face 11, and may be temporarily removed during periods when photography is not being performed.

For example, the lighting device 21 is a lightweight, high-brightness LED lamp (manufactured by Japan Magnet Co., Ltd., JCT-400A-L/P, 400W, 64,000lm), and the lighting devices 22 and 23 are each a lightweight, high-brightness LED lamp (manufactured by Japan Magnet Co., Ltd., JCT-200A-L/P, 200W, 32,000lm).

The power supply device 24 supplies power to the lighting devices 22 and 23. The lighting devices 22 and 23 can emit illumination light by being driven using the power supplied from the power supply device 24. Note that the lighting device 21 may receive power from the power supply device 24, or may receive power from a separate power supply path.

FIG. 3 is a functional block diagram illustrating the functions of the imaging device 20. As shown in FIG.
The imaging device 20 includes an imaging unit 201 , a display unit 202 , an input unit 203 , and a storage unit 204 .
The imaging unit 201 is capable of imaging the working face.
The display unit 202 displays a guide image of the cross-sectional shape of the tunnel on a live view screen that displays the image captured by the imaging unit 201 .
The input unit 203 accepts operational input from the person in charge of photography.
The storage unit 204 stores the captured image.
The storage unit 204 is configured by a storage medium, for example, a hard disk drive (HDD), a flash memory, an electrically erasable programmable read only memory (EEPROM), a random access read/write memory (RAM), a read only memory (ROM), or any combination of these storage media. For example, a non-volatile memory can be used for the storage unit 204.

4 is a diagram showing an example of a display screen 400 displayed on the display unit 202. In this figure, a smartphone is used as the imaging device 20, and a case is shown in which the smartphone is held by the person in charge of photography so that the longitudinal direction of the display screen is horizontal.
This display screen 400 includes a captured image display area 401 and an imaging condition setting area 402. The captured image display area 401 displays a live view screen. The live view screen is illustrated for a case where the angle of view is such that the entire face 11, which is the imaging target, and the top end and second side face 13 from the first side face 12 side of the support 410 of the face 11 are contained within the imaging area. The live view screen is a screen that sets the imaging device 20 to imaging mode and displays an image received by a light receiving element via a lens as an imaging screen.
Furthermore, on the live view screen, a guide image 420 is displayed so as to be superimposed on the captured image showing the state in which the imaging target is being imaged.
The guide image 420 includes a curved region 421 that curves according to the shape of the upper half, and a horizontal region 422 that is linear corresponding to the horizontal plane. The shape of the guide image 420 is set based on the contour shape of the standard cross section of the tunnel 10. The display mode of the guide image 420 may be, for example, any of a solid line, a dashed line, a hatching pattern, etc., and may be displayed in a color different from the face 11 and the shoring 410. This makes it easy to understand that the guide image 420 is different from the face 11 and the shoring 410 on the live view screen.

The photographer sets the imaging device 20 to imaging mode and adjusts the orientation and zoom level of the imaging device 20 so that the shape of the curved area 421 of the guide image 420 displayed on the live view screen matches the end of the face 11 side of the face support, and the shape of the horizontal area 422 matches the boundary between the floor and the face 11. Then, by touching the shooting button 430, the imaging device 20 captures the captured image and writes the data to the memory unit 204. Here, the captured image is an image based on the light received by the imaging element (i.e., images of the face 11, shoring 410, floor, etc.), and the guide image 420 is only displayed on the live view screen and does not remain in the captured image. This allows an image to be obtained in which the contour shape of the face 11 generally matches the shape of the guide image 420, so that even if the face 11 is imaged each time the excavation of the face 11 progresses, or even if the face 11 is imaged by a different photographer, an image of the face can be obtained in which the contour shape of the face 11 has a constant size in the image. As a result, the face 11 is captured generally from the front, the elevation and depression angles are generally constant, and the size of the image of the face 11 in the image capture area is constant, with little variation between images.

Furthermore, a setting button is arranged in the imaging condition setting area 402 on the display screen 400. The imaging person in charge can specify imaging conditions by touching this setting button.
FIG. 5 is a diagram showing an example of a setting screen when setting the imaging conditions. This setting screen is switched by pressing the setting button in the imaging condition setting area 402, or is displayed as a pop-up screen. In the setting screen, the ISO sensitivity and shutter speed can be specified according to the operation input of the imaging person. Here, the arrangement, direction, and brightness of the lighting device 21, the lighting device 22, and the lighting device 23 are specified, so that sufficient illuminance can be secured for imaging the face 11, and the roughness and sensitivity of the image can be made constant and uniform, and the face 11 can be imaged. Here, the ISO sensitivity and shutter speed that can image the face 11 in a preferable state are determined and set from the setting screen. Then, after this setting is performed, it is possible to photograph the face 11 under similar conditions such as lighting and angle of view, so that the ISO sensitivity and shutter speed can be basically photographed so as to have approximately the same quality without changing the conditions that have been set once. In addition, since the ISO sensitivity and shutter speed are changed manually, the ISO sensitivity and shutter speed are not automatically changed unintentionally.

Note that here, the live view screen (Figure 4) and the setting screen (Figure 5) may be displayed on separate screens, or both may be displayed on a single screen. Also, either the ISO sensitivity or the shutter speed may be manually changeable, with the setting value for the other being determined in advance.

FIG. 6 is a flowchart illustrating an imaging method for imaging a working face using the working face imaging system 1.
When the excavation of the tunnel face 11 is completed (step S101), the imaging operator confirms that the lighting device 21 is at the first distance L1 from the tunnel face 11 (step S102). If the lighting device 21 is not at the first distance, the lighting device 21 is repositioned so that the lighting device 21 is at the first distance L1.
Next, the person in charge of photography sets up the lighting devices 22 and 23 on the left and right sides, respectively, at a position a second distance L2 from the face 11 (step S103), and confirms that the lighting is sufficient to eliminate shadows from the face overexcavation portion.
Next, the photographer sets the imaging device 20 to imaging mode, and adjusts the orientation of the imaging device 20 (the attitude of the imaging device 20) and the degree of zoom so that the shape of the guide image 420 on the live view screen matches the end of the face support on the face 11 side and the boundary between the floor surface and the face 11 (step S104). After making these adjustments, the photographer touches the imaging button to capture an image (step S105).
When the shooting is completed, the person in charge of shooting removes the lighting devices 22 and 23 (step S106).

According to the embodiment described above, it is possible to realize an imaging device 20 that can easily obtain face images of uniform quality (color, brightness, etc.) by keeping the distance from the face and size constant from the time the face is photographed, and further, by installing an application program that realizes the functions of this imaging device 20 on a smartphone, it is possible to realize the imaging device 20 even on a smartphone.
In mountain tunnel construction, due to the nature of the work, it is necessary to minimize the time that the face is occupied. However, according to the above-described embodiment, the average time for photographing at a mountain tunnel construction site is about a few minutes (for example, 1 minute), and the impact on the construction cycle can be kept to a negligible range.

In this way, captured images with little variation in quality can be obtained, and by using the captured images obtained in this way as training data, it is possible to reduce the variation in quality of images collected as learning data.

The imaging device 20 in the above-described embodiment may be realized by a computer. In this case, a program for realizing this function may be recorded on a computer-readable recording medium, and the program recorded on the recording medium may be read into a computer system and executed to realize the function. The term "computer system" as used herein includes hardware such as an OS and peripheral devices. The term "computer-readable recording medium" refers to portable media such as flexible disks, optical magnetic disks, ROMs, and CD-ROMs, and storage devices such as hard disks built into a computer system. The term "computer-readable recording medium" may also include a medium that dynamically holds a program for a short period of time, such as a communication line when a program is transmitted via a network such as the Internet or a communication line such as a telephone line, and a medium that holds a program for a certain period of time, such as a volatile memory inside a computer system that is a server or client in such a case. The program may be a program for realizing part of the above-described function, or may be a program that can realize the above-described function in combination with a program already recorded in the computer system, or may be a program that is realized using a programmable logic device such as an FPGA (Field Programmable Gate Array).

The above describes an embodiment of the present invention in detail with reference to the drawings, but the specific configuration is not limited to this embodiment and includes designs that do not deviate from the gist of the present invention.

1...face imaging system, 10...tunnel, 11...face, 12...first side portion, 13...second side portion, 20...imaging device, 21, 22, 23...lighting device, 24...power supply device, 201...imaging section, 202...display section, 203...input section, 204...storage section, 400...display screen, 401...image display area, 402...imaging condition setting area, 410...support, 420...guide image, 421...curved area, 422...horizontal area, 430...imaging button

Claims (4)

An imaging unit capable of imaging the working face;
a display unit that displays a guide image of a cross-sectional shape of a tunnel on a live view screen that displays an image captured by the imaging unit;
A face imaging device having
a first lighting device that is provided in an upper portion of the tunnel at a position a first distance away from the tunnel face and that illuminates the tunnel face;
a second lighting device that is provided at a position on a first end side in the horizontal direction of the tunnel and a second distance away from the tunnel face, the second distance being shorter than the first distance, and that illuminates the tunnel face from a direction different from the direction in which the first lighting device irradiates illumination light as an auxiliary to the first lighting device;
a third lighting device that is provided at a second end side, which is opposite to the first end side in the horizontal direction of the tunnel, and is located at a position separated by the second distance from the tunnel face, and that illuminates the tunnel face from a direction different from the direction in which the first lighting device irradiates illumination light, as an auxiliary to the first lighting device;
A face imaging system having the same . The guide image is
A curved region that curves according to the shape of the upper half;
The face imaging system according to claim 1 , further comprising a horizontal region that is linear and corresponds to a horizontal plane. The display unit is
3. The face imaging system according to claim 1, further comprising: a setting button for setting at least one of an ISO sensitivity and a shutter speed, the setting button being displayed together with a guide image. a first lighting device for illuminating the tunnel face is disposed at a position in an upper portion of the tunnel that is a first distance away from the tunnel face;
a second lighting device is disposed at a position on a first end side of the tunnel in the horizontal direction and a second distance away from the tunnel face, the second distance being shorter than the first distance, as an auxiliary to the first lighting device, the second lighting device illuminating the tunnel face from a direction different from the direction in which the first lighting device irradiates the illumination light ;
a third lighting device is disposed at a position on a second end side of the tunnel, which is opposite to the first end side in the horizontal direction of the tunnel, and separated from the face by the second distance, as an auxiliary to the first lighting device, for illuminating the face from a direction different from the direction in which the first lighting device irradiates illumination light;
A face imaging method in which the attitude of the face imaging device is adjusted so that a guide image of the cross-sectional shape of the tunnel matches the contour shape of the face on a live view screen capturing the face, and when an instruction to capture an image is input, data of the captured image of the face is written to a memory unit.

Images