WO2022157939A1 - Deterioration evaluation device, deterioration evaluation method, and program - Google Patents

Abstract

A deterioration evaluation device (20) according to this disclosure comprises a facility area detection unit (211) for detecting a facility area from an acquired image, a deterioration area detection unit (212) for detecting a deterioration area from the image, a pixel resolution estimation unit (213) for estimating the pixel resolution of at least a portion of the image on the basis of the detected facility area, and a deterioration size estimation unit (214) for estimating the size of the deterioration area on the basis of the pixel resolution.

Description

Deterioration evaluation device, deterioration evaluation method and program

The present disclosure relates to a deterioration evaluation device, a deterioration evaluation method, and a program.

There is a method for detecting deterioration that occurs on the surface of structures using image processing. In recent years, segmentation methods have been used in deep learning. As a technique for quantitatively evaluating the deteriorated area, a technique for quantitatively evaluating the deteriorated area from the scale by embedding the crack scale in the image (see Non-Patent Document 1), and keeping the distance to the photographing object constant. A technique is known in which an image is acquired using imaging equipment having a mechanism for maintaining the image, and a degraded region is quantitatively evaluated from the pixel resolution (see Non-Patent Document 2).

　Conventional techniques for quantitative evaluation of degraded areas required some ingenuity in the captured images. Therefore, it is difficult to quantitatively evaluate the degraded region using an image processing algorithm such as a segmentation method for images captured without satisfying certain imaging conditions, and there is room for improvement.

An object of the present disclosure, which has been made in view of such circumstances, is to provide a deterioration evaluation device, a deterioration evaluation method, and a program capable of evaluating the actual size value of a deteriorated region without being limited to certain shooting conditions.

In order to solve the above-described problems, the deterioration evaluation apparatus according to the present disclosure includes an equipment area detection unit that detects an equipment area from an acquired image, a deteriorated area detection unit that detects a deteriorated area from the image, and the detected equipment A pixel resolution estimating unit that estimates pixel resolution of at least part of the image based on the area, and a degradation size estimating unit that estimates the size of the degraded area based on the pixel resolution.

Further, a deterioration evaluation method according to the present disclosure is a deterioration evaluation method for evaluating deterioration by a deterioration evaluation device, and includes a step of detecting an equipment area from an acquired image, a step of detecting a deteriorated area from the image, and a step of detecting estimating a pixel resolution of at least a portion of the image based on the facility area obtained; and estimating a size of the degraded area based on the pixel resolution.

Also, the program according to the present disclosure causes a computer to function as the deterioration evaluation device according to the present disclosure.

According to the present disclosure, it is possible to evaluate the actual size value of the deteriorated region without being limited to certain shooting conditions.

1 is a diagram for explaining a deterioration evaluation system according to an embodiment of the present disclosure; FIG. It is a figure which simplifies and shows a tunnel. 1 is a block diagram showing the configuration of a deterioration evaluation device according to an embodiment of the present disclosure; FIG. It is a figure which shows an example of the image which the deterioration evaluation apparatus acquired. It is a figure which shows an example of the image which the deterioration evaluation apparatus acquired. 4 is a block diagram showing the configuration of a pixel resolution estimation unit according to an embodiment of the present disclosure; FIG. FIG. 10 is a diagram showing an example of an image when it is determined that the number of objects N is N=1; FIG. 10 is a diagram showing another example of an image when the number of objects N is determined to be N=1; FIG. 10 is a diagram showing another example of an image when the number of objects N is determined to be N=1; FIG. 4 is a diagram for explaining a pixel resolution map; FIG. FIG. 10 is a diagram showing an example of an image when it is determined that the number of objects N is N=2; FIG. 10 is a diagram showing another example of an image when the number of objects N is determined to be N=2; FIG. 10 is a diagram showing another example of an image when the number of objects N is determined to be N=2; FIG. 10 is a diagram showing an example of an image when it is determined that the number of objects N is N≧3; FIG. 10 is a diagram showing another example of an image when it is determined that the number of objects N is N≧3; 4 is a block diagram showing the configuration of a degradation magnitude estimator according to an embodiment of the present disclosure; FIG. FIG. 4 is a diagram for explaining an example of coordinates of a deteriorated area; FIG. FIG. 4 is a diagram for explaining a state in which coordinates of a degraded area are plotted on a pixel resolution map; FIG. 3 is a diagram showing the operation of a deterioration assessment system according to an embodiment of the present disclosure; FIG. FIG. 3 is a diagram showing the operation of a deterioration assessment system according to an embodiment of the present disclosure; FIG. It is a figure which shows operation|movement of the control part of the deterioration evaluation apparatus which concerns on one Embodiment of this indication. It is a figure which shows operation|movement of the control part of the deterioration evaluation apparatus which concerns on one Embodiment of this indication. FIG. 11 is a diagram for explaining an equipment area correction unit according to Modification 1; FIG. 11 is a diagram for explaining an equipment area correction unit according to Modification 1; FIG. 11 is a diagram for explaining an equipment area correction unit according to Modification 1; FIG. 11 is a diagram for explaining an equipment area correction unit according to Modification 1; FIG. 11 is a diagram for explaining an equipment area correction unit according to Modification 1; FIG. 11 is a diagram showing an example of an image acquired by a deterioration evaluation device according to modification 2; FIG. 11 is a diagram for explaining a pixel resolution map according to modification 2;

Hereinafter, embodiments of the present disclosure will be described with reference to the drawings as appropriate. In each drawing, the same reference numerals are given to the same or corresponding parts. In the description of this embodiment, the description of the same or corresponding parts will be omitted or simplified as appropriate. The embodiments described below are examples of the configuration of the present disclosure, and the present disclosure is not limited to the following embodiments.

<Configuration of deterioration evaluation system>
An example of the configuration of a deterioration evaluation system 1 according to this embodiment will be described with reference to FIG.

The deterioration evaluation system 1 is a system that quantitatively evaluates the deterioration occurring in the structure body using the known information of the equipment from the photographed images of the structure. In the deterioration evaluation system 1, an image processing algorithm is used to detect a deteriorated area and known facilities from a photographed image. The known dimensions for the detected equipment are then compared to the number of pixels on the image to estimate the pixel resolution at each location. Then, the actual size value of the degraded area is calculated based on the estimated pixel resolution. This makes it possible to estimate the actual size of the degraded area without being limited to certain shooting conditions.

A structure refers to a tunnel in this embodiment. A tunnel is an underground tunnel for laying telecommunication cables. Structures include, but are not limited to, for example, tunnels for laying gas pipes or power lines, or manholes. The equipment, in this embodiment, is hard metal that is part of the hardware equipment. Deterioration to be detected includes damage, stains, etc. occurring in the tunnel main body in the photographed image. The deterioration may be damage, dirt, etc. occurring in the equipment.

Figure 2 is a simplified diagram of a tunnel. The height in the Z-axis direction from the top to the bottom of the tunnel and the width in the X-axis direction are, for example, about 3 meters. The tunnel may have a rectangular cross-sectional shape as well as a circular cross-sectional shape as shown in FIG. Workers enter the tunnel and perform work such as laying, connecting, maintaining, repairing, and removing communication cables. In the tunnel, hardware equipment for housing communication cables, lighting, ventilation equipment, drainage equipment, etc. are installed. The hardware equipment includes a flat steel metal piece fixed to the wall surface of the cable tunnel, and a receiving metal piece attached to the metal metal piece to support the communication cable. In this embodiment, the hard metal has a width of about 8 cm, but is not limited to this. The steel bars extend in the Z-axis direction in FIG. 2 and are installed at regular intervals in the Y-axis direction, which is the depth direction of the cable tunnel. The Z-axis direction in FIG. 2 indicates the longitudinal direction of the metal rod, and the Y-axis direction indicates the lateral direction of the metal rod.

Referring to FIG. 1 again, the deterioration evaluation system 1 includes an imaging device 10, a deterioration evaluation device 20, and a server device 30. The photographing device 10, the deterioration evaluation device 20, and the server device 30 are connected by wire or wirelessly so as to be able to communicate with each other. A communication method for transmitting and receiving information between devices is not particularly limited.

The photographing device 10 is a device that has a function of photographing the inside of the tunnel, and is, for example, a smartphone, a tablet terminal, a notebook PC (personal computer), an unmanned flying object, or the like. The photographing device 10 transmits data of the photographed image to the deterioration evaluation device 20 . At least part of the equipment in the tunnel is reflected in the captured image. The number of imaging devices 10 is not limited to one, and may be plural. The imaging device 10 may be integrated with the deterioration evaluation device 20 .

The deterioration evaluation device 20 is any electronic device such as a smartphone or tablet terminal. The deterioration evaluation device 20 may be a general-purpose computer, a dedicated computer, or a PC (Personal Computer). The deterioration evaluation device 20 may be used by workers who perform inspections in tunnels. The deterioration evaluation device 20 receives the data of the captured image from the imaging device 10 . Although the details will be described later, the deterioration evaluation device 20 detects the facility area and the deteriorated area based on the received photographed image, estimates the pixel resolution, and estimates the size of the deteriorated area. The deterioration evaluation device 20 transmits information indicating the estimated actual size of the deteriorated region to the server device 30 via the network.

The server device 30 may be installed in a facility such as a data center. The server device 30 receives information indicating the actual size of the deteriorated area of the equipment from the deterioration evaluation device 20 via the network. The server device 30 stores information indicating the actual dimension value of the degraded area in the storage unit of the server device 30 .

<Deterioration detector>
An example of the configuration of the deterioration evaluation device 20 according to this embodiment will be described with reference to FIGS. 3 to 13B.

As shown in FIG. 3, the deterioration evaluation device 20 includes a control unit 21, a storage unit 22, a communication unit 23, an input unit 24, and an output unit 25. The control unit 21 includes an equipment area detection unit 211 , a deterioration area detection unit 212 , a pixel resolution estimation unit 213 and a deterioration magnitude estimation unit 214 .

The storage unit 22 includes one or more memories, and may include, for example, semiconductor memory, magnetic memory, optical memory, and the like. Each memory included in the storage unit 22 may function as, for example, a main memory device, an auxiliary memory device, or a cache memory. Each memory does not necessarily have to be provided inside the deterioration evaluation device 20 , and may be provided outside the deterioration evaluation device 20 . The storage unit 22 stores information used for the operation of the deterioration evaluation device 20 and information obtained by the operation of the deterioration evaluation device 20 . The storage unit 22 includes, for example, information indicating the actual width of the reinforcing metal, information indicating the installation interval of the reinforcing metal, information on the created pixel resolution map, information on the actual size of the deteriorated region estimated by the control unit 21, and the like. can be stored.

The communication unit 23 includes at least one communication interface. The communication interface is, for example, a LAN interface. The communication unit 23 receives information used for the operation of the deterioration evaluation device 20 and transmits information obtained by the operation of the deterioration evaluation device 20 . The communication unit 23 receives the data of the photographed image from the photographing device 10 . The communication unit 23 transmits information on the estimated actual size of the deteriorated region to the server device 30 .

The input unit 24 includes at least one input interface. The input interface is, for example, a physical key, a capacitive key, a pointing device, a touch screen integrated with the display, or a microphone. The input unit 24 receives an operation of inputting information used for operation of the deterioration evaluation device 20 . The input unit 24 may be connected to the deterioration evaluation device 20 as an external input device instead of being provided in the deterioration evaluation device 20 . Any connection method may be used. For example, the operator can input image data, such as an inspection image, captured in the cable tunnel to the deterioration evaluation device 20 by performing a predetermined operation using the input unit 24 .

The output unit 25 includes at least one output interface. The output interface is, for example, a display or speaker. The display is, for example, an LCD (liquid crystal display) or an organic EL (electro luminescence) display. The output unit 25 outputs information obtained by the operation of the deterioration evaluation device 20 . The output unit 25 may be connected to the deterioration evaluation device 20 as an external output device instead of being provided in the deterioration evaluation device 20 . Any connection method may be used. For example, the output unit 25 may notify the operator of information on the estimated actual size of the deteriorated region by image or sound.

The control unit 21 includes at least one processor, at least one dedicated circuit, or a combination thereof. The processor is a general-purpose processor such as a CPU (central processing unit) or a GPU (graphics processing unit), or a dedicated processor specialized for specific processing. A dedicated circuit is, for example, an FPGA (field-programmable gate array) or an ASIC (application specific integrated circuit). The control unit 21 executes processing related to the operation of the deterioration evaluation device 20 while controlling each unit of the deterioration evaluation device 20 . The control unit 21 obtains an image obtained inside the communication tunnel, estimates the pixel resolution of the image based on the equipment area detected from the image using an image processing method such as segmentation deep learning, and It has the function of quantitatively evaluating the region detection results.

The equipment area detection unit 211 detects a metal object as an equipment area from the acquired image, and outputs it to the pixel resolution estimation unit 213 . Objects to be detected as equipment areas are not limited to solid metal objects, and may be set freely. Detection is performed by an image processing technique such as segmentation deep learning.

The degraded area detection unit 212 detects a degraded area that occurs in the main body of the cable tunnel from the acquired image, and outputs it to the degradation magnitude estimation unit 214 . The detection may be based on the same image processing method as that used by the facility area detection unit 211 .

FIG. 4A shows an example of an acquired image. FIG. 4B is a diagram showing the equipment area detected by the equipment area detection unit 211 and the degraded area detected by the degraded area detection unit 212. As shown in FIG. The equipment area detector 211 and the deteriorated area detector 212 may be integrated so that the equipment area and the deteriorated area can be detected simultaneously. If the equipment area is not detected from the acquired image, the equipment area detection unit 211 may notify the photographing device 10 to that effect via the output unit 25 and prompt photographing again.

The equipment area detected by the equipment area detection unit 211 and the deterioration area detected by the deterioration area detection unit 212 may be displayed to the worker using the deterioration evaluation device 20 via the output unit 25 . In this case, the operator can operate the input unit 24 to manually set the range between the facility area and the deterioration area.

The pixel resolution estimation unit 213 estimates the pixel resolution of at least a part of the image based on the equipment area detected by the equipment area detection unit 211 . Specifically, the pixel resolution, which is the actual size value of the length per pixel of the image, is estimated for each pixel from the width of the reinforcing metal or the installation interval, and a pixel resolution map is created for the entire image to determine the degree of deterioration. output to the height estimation unit 214 . One pixel means one pixel.

As shown in FIG. 5, the pixel resolution estimation unit 213 includes an object number extraction unit 2131, an object number determination unit 2132, an object width extraction unit 2133a and an object width extraction unit 2133b, a thinning unit 2134, and an installation interval extraction unit. 2135, an actual size comparison unit 2136a, an actual size comparison unit 2136b, an actual size comparison unit 2136c, a pixel resolution map creation unit 2137a, a pixel resolution map creation unit 2137b, and a pixel resolution map creation unit 2137c.

The number-of-objects extraction unit 2131 divides the detected hard metal objects into objects one by one from the detection result of the equipment area by the equipment area detection unit 211, and extracts the number of hard metal objects detected as the equipment area. For example, the number-of-objects extracting unit 2131 extracts that the number of objects (number of hardened metal objects) N of hard metal objects is 2 from the detection result of the facility area shown in FIG. 4B. The number-of-objects extraction unit 2131 outputs the extracted result to the number-of-objects determination unit 2132 .

The number-of-objects determination unit 2132 determines whether N=1, N=2, or N≧3 for the number N of metal objects extracted by the number-of-objects extraction unit 2131 . As shown in FIG. 5, when the number of metal objects N=1, the processing is sequentially executed by an object width extraction unit 2133a, an actual size comparison unit 2136a, and a pixel resolution map creation unit 2137a. When the number of metal parts N=2, the thinning unit 2134, the installation interval extraction unit 2135, the actual size comparison unit 2136b, and the pixel resolution map generation unit 2137b sequentially perform processing. When the number of metal objects N≧3, the processing is sequentially executed by the object width extraction unit 2133b, the actual size comparison unit 2136c, and the pixel resolution map generation unit 2137c.

A case where the object number determination unit 2132 determines that the number of metal objects N=1 will be described below.

The object width extraction unit 2133a measures the number of pixels corresponding to the width of the hard metal and outputs it to the actual size comparison unit 2136a. FIG. 6 shows an example of an image when the number-of-objects determination unit 2132 determines that the number of metal objects is N=1. FIG. 6 shows a single hard metal area and a background area detected as an equipment area. The object width extraction unit 2133a measures the number of pixels corresponding to the width of the metal object indicated by the arrow symbol in FIG. The vertical position of the width of the object to be measured may be set freely. For example, as shown in FIG. 6, the number of pixels corresponding to the width at a plurality of positions of the hard metal may be measured. By measuring the number of pixels for the width of a plurality of positions, it is possible to improve the accuracy of the pixel resolution map described later.

7A and 7B are diagrams showing other examples of acquired images. FIG. 7A is an image taken looking up at the metal object, and FIG. 7B is an image taken looking down at the metal object. The upper part of the hard metal in FIG. 7A and the lower part of the hard metal in FIG. 7B are displayed smaller due to perspective. In this way, when the width of the metal object changes on the image according to the perspective method, the object width extracting unit 2133a measures the number of pixels for the width at a plurality of positions. For example, the object width extraction unit 2133a may measure the number of pixels for widths at the top, center, and bottom positions of the metal object in the vertical direction.

The actual size comparison unit 2136a calculates the pixel resolution for each pixel and outputs it to the pixel resolution map creation unit 2137a. Specifically, the actual size comparison unit 2136a compares the number of pixels corresponding to the width of the metal object in the image measured by the object width extraction unit 2133a with the actual size value of the width of the metal object. The pixel resolution is obtained by (1).

In formula (1), R is the pixel resolution for each pixel, and the unit is mm/pixel. B is the actual value of the width of the metal bar, and the unit is mm. C is the number of pixels (ie, the number of pixels) corresponding to the width of the hard metal. In this manner, the actual size comparison unit 2136a divides the actual size value B of the width of the metal by the measured number of pixels C to estimate the pixel resolution R. The actual size comparison unit 2136a refers to the storage unit 22, reads out the pre-stored actual size value of the width of the metal rod, and calculates the pixel resolution R as the B value. The actual size comparison unit 2136a may calculate the pixel resolution R using the actual size value of the width of the metal rod input via the input unit 24 as the value of B.

The pixel resolution map creation unit 2137a creates a pixel resolution map A indicating the pixel resolution of each pixel of the entire image by linearly approximating the relationship between the pixel resolution calculated by the actual size comparison unit 2136a and the coordinates of the image. . The pixel resolution map creation unit 2137 a outputs the created pixel resolution map A to the deterioration magnitude estimation unit 214 . The coordinates are coordinates in the vertical direction of the image, that is, in the longitudinal direction of the steel metal. Any type of approximation method may be used, for example, a method such as the least squares method may be used. As shown in FIG. 7A, in an image taken as if looking up at the metal object from the lower part of the tunnel, the pixel resolution value of the upper part of the image corresponding to the upper part of the tunnel becomes large. In addition, as shown in FIG. 7B , in an image taken from the upper part of the tunnel to look down on the steel metal, the pixel resolution value of the lower part of the image corresponding to the lower part of the tunnel becomes large. In this way, in the case of an image in which only one metal object is detected, the image is often distorted in the vertical direction. It is possible to improve the accuracy of This allows the distortion correction to be reproduced on the pixel resolution map. The pixel resolution map may be created by linear approximation in the longitudinal direction of the metal rod, or by using an approximation method that considers angles and the like.

FIG. 8 is a diagram for explaining the pixel resolution map A created by the pixel resolution map creation unit 2137a when only one metal object is detected. The scale on the right side of the figure expresses the pixel resolution value in the image by shading. In FIG. 8, the hard metal is photographed from below the tunnel. It can be seen that the pixel resolution value increases in the direction indicated by the arrow symbol in the image.

A case where the object number determination unit 2132 determines that the number of metal objects N=2 will be described below.

The thinning unit 2134 displays a thin line along the longitudinal direction of the detected hard metal at the center of the width of the hard metal, and thins the width of the hard metal with a line. FIG. 9 shows an example of an image when the number-of-objects determination unit 2132 determines that the number of metal objects is N=2. FIG. 9 shows two hard metal areas and a background area detected as the facility area. The thinning unit 2134 displays thin lines as indicated by dotted lines in FIG. 9, and linearly represents the width of each of the two reinforcing metals. The thinning unit 2134 outputs the thinning result to the installation interval extracting unit 2135 .

The installation interval extraction unit 2135 measures the number of pixels corresponding to the interval distance of the fine lines displayed by the thinning unit 2134, and outputs it to the actual size comparison unit 2136b. The installation interval extraction unit 2135 measures the number of pixels corresponding to the interval distance between the thin lines indicated by the arrow symbols in FIG. The vertical position of the distance between objects to be measured may be set freely. For example, as shown in FIG. 9, the number of pixels corresponding to the spacing distance at a plurality of positions on the metal rod may be measured. By measuring the number of pixels for the interval distances at a plurality of positions, the accuracy of the pixel resolution map, which will be described later, can be improved.

10A and 10B are diagrams showing other examples of acquired images. FIG. 10A is an image taken looking up at the metal object, and FIG. 10B is an image taken looking down at the metal object. The upper portion of the spacing distance between the reinforcing metals in FIG. 10A and the lower portion of the spacing distance between the reinforcing metals in FIG. 10B are displayed smaller in perspective. In this way, when the interval distance between the metal fittings on the image changes according to the perspective method, the installation interval extraction unit 2135 measures the number of pixels for the interval distance at a plurality of positions. For example, the installation interval extraction unit 2135 may measure the number of pixels for the interval distances at the uppermost position, the center position, and the lowermost position of the fine wire of the metal wire.

The actual size comparison unit 2136b calculates the pixel resolution R for each pixel and outputs it to the pixel resolution map creation unit 2137b. Specifically, the actual size comparison unit 2136b compares the number of pixels corresponding to the interval distance between the fine lines of the reinforcing metal in the image measured by the installation interval extraction unit 2135, and the actual size value of the interval distance. 2) Obtain the pixel resolution.

In Equation (2), R is the pixel resolution for each pixel, and the unit is mm/pixel. L is the actual size of the distance between the metal bars, and the unit is mm. C is the number of pixels (that is, the number of pixels) corresponding to the distance between the metal bars. In this manner, the actual size comparison unit 2136b divides the actual size value L of the interval distance between the metal parts by the measured number of pixels C to estimate the pixel resolution R. The actual size comparison unit 2136b refers to the storage unit 22, reads out the pre-stored actual size value of the distance between the reinforcing metals, and calculates the pixel resolution R as the value of L. The actual size comparison unit 2136b may calculate the pixel resolution R using the actual size value of the interval distance between the reinforcing metals input via the input unit 24 as the value of L.

The pixel resolution map creation unit 2137b creates a pixel resolution map B indicating the pixel resolution of each pixel of the entire image by linearly approximating the relationship between the pixel resolution calculated by the actual size comparison unit 2136b and the coordinates of the image. . The pixel resolution map creation unit 2137 b outputs the created pixel resolution map B to the deterioration magnitude estimation unit 214 . The details of the pixel resolution map creation unit 2137b are the same as those of the pixel resolution map creation unit 2137a, so description thereof will be omitted.

In addition, when the actual size value of the installation interval of the reinforcing metal of the cable tunnel is unknown, the pixel resolution may be calculated from the width of the reinforcing metal in the same manner as when the number of objects determination unit 2132 determines that N = 1. . Alternatively, the overall pixel resolution of the image may be calculated based on the number of pixels and the actual size values measured for both the width of the hard metal and the distance between the fine lines of the hard metal. This makes it possible to create a pixel resolution map with higher accuracy.

A case where the number-of-objects determination unit 2132 determines that the number of metal objects N≧3 will be described below.

The object width extraction unit 2133b measures the number of pixels corresponding to the width of the hard metal and outputs it to the actual size comparison unit 2136c. 11A and 11B show examples of images when the number-of-objects determination unit 2132 determines that the number of metal objects N≧3. The images of FIGS. 11A and 11B show three hard metal areas and a background area detected as the equipment area. The image was taken toward the back of the tunnel, the right side of the image is the front side of the tunnel, and the left side is the back side. As indicated by the arrow symbol, the hard metal object as the facility area detected toward the far side is displayed smaller due to the perspective method. Other details of the object width extraction unit 2133b are the same as those of the object width extraction unit 2133a, and thus description thereof is omitted.

The object width extraction unit 2133b may measure the number of pixels in each width for all detected equipment areas. Alternatively, the object width extracting unit 2133b may identify a plurality of metal objects in descending order of the ratio of the size of the facility area in the image, and measure the number of pixels for the width of only the identified metal objects. As a result, it is possible to omit the process of measuring the number of pixels corresponding to the width of a metal object having an extremely small proportion of the size of the equipment area in the image, that is, the metal object existing on the far side of the cable tunnel. Alternatively, the object width extracting unit 2133b may also measure the number of pixels corresponding to the width of the metal object existing on the far side of the cable tunnel when a deteriorated region is detected on the far side of the image. As a result, the accuracy of the pixel resolution map created by the pixel resolution map creation unit 2137c is increased compared to the case of measuring the width only for the specified hard metal, and the actual size value of the deteriorated region on the far side of the image is estimated with high accuracy. can. In this way, the object width extraction unit 2133b can freely determine which of the detected facility areas the number of pixels of the width is to be measured.

Similar to the above-described case where the number of objects determining unit 2132 determines that the number of metal objects N=2, the thinning unit 2134 and the installation interval extracting unit 2135 are added to the object width extracting unit 2133b or the object width extracting unit 2133b. may be provided instead. As a result, for example, even if the actual width of some of the steel bars is unknown, the thinning unit 2134 and the installation interval extraction unit 2135 can flexibly measure the number of pixels of the gap distance. FIG. 11B is a diagram illustrating a case where the number of pixels of the interval distance is measured by the thinning unit 2134 and the installation interval extraction unit 2135 instead of the object width extraction unit 2133b. In FIG. 11B, the thinning unit 2134 represents the widths of three or more steel bars in a line shape, and the installation interval extraction unit 2135 measures the number of pixels corresponding to the interval distance of each line. As with the object width extraction unit 2133b described above, the thinning unit 2134 and the installation interval extraction unit 2135 freely determine the number of pixels of which interval distance among the plurality of interval distances between the plurality of hard metal objects to be measured. can.

The actual size comparison unit 2136c calculates the pixel resolution for each pixel and outputs it to the pixel resolution map creation unit 2137c. The details of the actual size comparison section 2136c are the same as those of the actual size comparison section 2136a or the actual size comparison section 2136b, so description thereof will be omitted.

The pixel resolution map creation unit 2137c creates a pixel resolution map indicating the pixel resolution of each pixel of the entire image by linearly approximating the relationship between the pixel resolution calculated by the actual size comparison unit 2136c and the coordinates of the image. The pixel resolution map creation unit 2137 c outputs the created pixel resolution map C to the deterioration magnitude estimation unit 214 . The coordinates are in the horizontal direction of the image, that is, in the lateral direction of the metal. Any type of approximation method may be used, for example, a method such as the least squares method may be used. As shown in FIGS. 11A and 11B, in images in which a plurality of metal objects are photographed from the front side to the back of the tunnel, the pixel resolution value of the left side of the image corresponding to the back side of the tunnel is large. As a result, the pixel resolution value of the right side of the image corresponding to the front side of the tunnel becomes smaller. When the left side of the image corresponds to the front side of the tunnel and the right side of the image corresponds to the back side of the tunnel, the pixel resolution value of the right side of the image increases, and the pixels of the left side of the image The resolution value becomes smaller. In this way, in the case of an image in which three or more metal objects are detected, the image is often distorted in the horizontal direction. It is possible to improve the precision of the value. This allows the distortion correction to be reproduced on the pixel resolution map.

The deterioration magnitude estimation unit 214 estimates the actual size value of the deteriorated area detected by the deteriorated area detection unit 212 based on the pixel resolution map created by the pixel resolution estimation unit 213 . This allows the degradation magnitude estimator 214 to evaluate the degradation region. As shown in FIG. 12 , the deterioration magnitude estimation unit 214 includes a deterioration area coordinate acquisition unit 2141 , a deterioration area length estimation unit 2142 and a deterioration area area estimation unit 2143 .

The degraded area coordinate acquisition unit 2141 acquires the coordinates in the image of the area detected as the degraded area. According to the acquired coordinate values, the degraded area coordinate acquisition unit 2141 determines which of the degraded area length estimation unit 2142 and the degraded area area estimation unit 2143 performs the next process. 2142 and the deteriorated region area estimation unit 2143, the acquired coordinates are output. For example, when the photographed deterioration in the tunnel is linear deterioration such as a crack whose shape is not uniformly determined, the deterioration area coordinate acquisition unit 2141 determines the deterioration area length estimation unit 2142 from the acquired coordinate values. decides what to do next. Then, the acquired coordinates are output to the deteriorated region length estimating section 2142 . For example, when the deterioration in the photographed tunnel is deterioration such as a hole-shaped defect having a certain area, the deteriorated area coordinate acquisition unit 2141 determines that the deteriorated area area estimation unit 2143 performs next processing from the acquired coordinate values. decide to do Then, the acquired coordinates are output to the deteriorated area area estimation unit 2143 .

Which of the deteriorated area length estimating unit 2142 and the deteriorated area area estimating unit 2143 should perform the next process may be determined according to preset deterioration area recording items or inspection items.

The degraded area length estimation unit 2142 calculates the length of the degraded area from the coordinates indicating the degraded area, and stores the result in the storage unit 22 . Here, an example of calculating the maximum length of the degraded region will be described, but the length to be calculated may be set freely. FIG. 13A shows an example of coordinates on the image of the acquired deteriorated region. Referring to FIG. 13A, cracks as degraded areas are indicated by dotted lines. The degraded region length estimating unit 2142 calculates, of the coordinates of the degraded region, the point A having the maximum value on the vertical axis (Y axis), the point B having the maximum value on the horizontal axis (X axis), and the point B having the maximum value on the vertical axis (Y The point C with the minimum value on the X-axis and the point D with the minimum value on the horizontal axis (X-axis) are extracted. Degraded region length estimation section 2142 creates a quadrangle formed by straight lines connecting point A to point D, and the straight line connecting point A and point C among the diagonal lines of the quadrangle has maximum length L′. It is determined that it is max. The degraded region length estimator 2142 may extract points forming an arbitrary polygon according to the shape of the degraded region. The degraded region length estimation unit 2142 may determine any side or diagonal line of the polygon as the maximum length.

The degraded region length estimation unit 2142 next plots the coordinates of point A and point C on the pixel resolution map. FIG. 13B is a diagram for explaining a state where points A and C forming the maximum length obtained in FIG. 13A are plotted on the pixel resolution map. The degraded area length estimator 2142 obtains the distance between the plotted points, that is, the actual size value of the maximum length of the degraded area from the pixel resolution value indicated by the pixel resolution map. On the pixel resolution map of FIG. 13B, the degraded region length estimator 2142 forms a right-angled triangle whose oblique side is the straight line connecting the plotted points A and C. FIG. The degraded region length estimation unit 2142 calculates the pixel resolution of pixels corresponding to a straight line extending downward along the vertical axis from point A and a straight line extending leftward from point C along the horizontal axis, which form a right angle. Measure and determine the actual size of each straight line.

In FIG. 13B, the pixel resolution value of the pixel corresponding to the straight line extending downward from point A is 1.1+1.1+1.1+1.1+1.1=5.5 mm/pixel, and the actual size of the straight line is 5.5 mm. It can be seen that it is. Also, the pixel resolution value of the pixels corresponding to the straight line extending leftward from the point C is 1.1+1.1+1.2=3.4 mm/pixel, and the actual size of the straight line is 3.4 mm. . Then, the degraded region length estimation unit 2142 obtains the length of the hypotenuse by the Pythagorean theorem. Specifically, the deteriorated region length estimation unit 2142 sums 30.25 mm, which is the value obtained by squaring 5.5 mm, and 11.56 mm, which is the value obtained by squaring 3.4 mm, to calculate a value of 41.81 mm. . Then, the square root of the value of 41.81 mm is obtained, and the value of 6.5 mm is calculated by rounding off to the second decimal place. Thus, it is determined that the actual length of the oblique side L'max is 6.5 mm.

When the degraded region whose length is to be estimated is parallel to the vertical axis or the horizontal axis on the pixel resolution map, the degraded region length estimation unit 2142 calculates the pixel resolution corresponding to the straight line between the coordinates indicating the degraded region. may be simply summed up to calculate the actual size of the straight line.

The deteriorated area area estimation unit 2143 obtains the area of the deteriorated area and stores the result in the storage unit 22 . Specifically, the deteriorated area area estimation unit 2143 plots the acquired coordinate values of the deteriorated area on the pixel resolution map. The degraded area area estimation unit 2143 identifies the pixel resolution value of each pixel corresponding to the degraded area based on the plotted coordinates. Next, the deteriorated area area estimation unit 2143 squares each of the specified pixel resolution values to obtain the actual size value of the area per pixel. The deteriorated area area estimator 2143 adds the obtained actual size values of the area per pixel, and calculates the total value as the actual size value of the area of the entire deteriorated region.

<Program>
The degradation assessment device 20 may be a computer capable of executing program instructions. The computer stores a program describing the processing details for realizing each function of the deterioration evaluation apparatus 20 in the memory of the computer, and the processor of the computer reads and executes the program. A part of these processing contents may be realized by hardware. Here, the computer may be a general purpose computer, a special purpose computer, a workstation, a PC, an electronic notepad, or the like. Program instructions may be program code, code segments, etc. for performing the required tasks. The processor may be a CPU, GPU, DSP (Digital Signal Processor), or the like.

In addition, this program may be recorded on a computer-readable recording medium. By using such a recording medium, it is possible to install the program in the computer. Here, the recording medium on which the program is recorded may be a non-transitory recording medium. The non-transitory recording medium is not particularly limited, but may be, for example, a recording medium such as a CD-ROM or a DVD-ROM. This program can also be provided by download over a network.

<Operation of deterioration evaluation system 1>
13A, 13B, 14A, 14B, 15A, and 15B, the operation of the deterioration evaluation system 1 including the deterioration evaluation device 20 according to this embodiment will be described. Among the operations of the deterioration evaluation system 1, the operation of the deterioration evaluation device 20 corresponds to the deterioration evaluation method according to this embodiment.

In step S1, the photographing device 10 photographs the deteriorated part inside the tunnel and the facilities inside the tunnel. The photographing device 10 transmits photographed image data to the deterioration evaluation device 20 .

In step S<b>2 , the communication unit 23 of the deterioration evaluation device 20 receives image data from the imaging device 10 . The control unit 21 of the deterioration evaluation device 20 acquires the received image.

In step S3, the facility area detection unit 211 of the deterioration evaluation device 20 detects the facility area from the acquired image. In this example, hard metal is detected as an equipment area. Here, when the equipment area detection unit 211 determines that the equipment is not captured in the image, the equipment area detection unit 211 may notify the photographing device 10 to that effect. The equipment area detection unit 211 outputs the detection result to the pixel resolution estimation unit 213 .

In step S4, the degraded area detection unit 212 of the degradation evaluation device 20 detects degraded areas from the acquired image. Degraded area detection section 212 outputs the detection result to degradation magnitude estimation section 214 .

Note that the order of steps S3 and S4 may be changed, and the processes of steps S3 and S4 may be performed simultaneously.

In step S5, the pixel resolution estimation unit 213 of the deterioration evaluation device 20 estimates the pixel resolution of at least part of the image based on the detected facility area. 15A and 15B show a specific processing flow of pixel resolution estimation in step S5 of FIG. 14A.

First, in step S6, the number-of-objects extraction unit 2131 extracts the number of solid metal objects detected as the facility area. The number-of-objects extraction unit 2131 outputs the extracted result to the number-of-objects determination unit 2132 .

In step S7, the number-of-objects determination unit 2132 determines whether the number N of the extracted metal objects is N=1, N=2, or N≧3. If the number of metal objects N=1, the object width extraction unit 2133a performs processing in step S8, followed by the actual size comparison unit 2136a and the pixel resolution map generation unit 2137a. If the number of metal parts N=2, the thinning unit 2134 performs processing in step S11, followed by the installation interval extraction unit 2135, the actual size comparison unit 2136b, and the pixel resolution map creation unit 2137b. be done. If the number of metal objects N≧3, the object width extraction unit 2133b performs processing in step S15, followed by the actual size comparison unit 2136c and the pixel resolution map creation unit 2137c.

First, the case where it is determined that the number of hard metals N=1 in step S7 will be described. In step S8, the object width extracting unit 2133a measures the number of pixels corresponding to the width of the metal object. The position of the width of the object to be measured may be freely set, and the number of pixels corresponding to the width at a plurality of positions of the hard metal may be measured. For example, the object width extraction unit 2133a may measure the number of pixels for widths at the top, center, and bottom positions of the metal object in the vertical direction. The object width extraction unit 2133a outputs the measurement result to the actual size comparison unit 2136a.

In step S9 of FIG. 15B, the actual size comparison unit 2136a calculates the pixel resolution for each pixel. Specifically, the actual size comparison unit 2136a compares the number of pixels corresponding to the width of the metal rod in the image measured in step S8 with the actual size value of the metal rod pre-stored in the storage unit 22. Then, the pixel resolution is obtained from the above equation (1). The actual size comparison unit 2136a outputs the calculated result to the pixel resolution map generation unit 2137a.

In step S10, the pixel resolution map creation unit 2137a generates a pixel resolution map A representing the pixel resolution of each pixel of the entire image by linearly approximating the relationship between the pixel resolution calculated by the actual size comparison unit 2136a and the coordinates of the image. to create The pixel resolution map is created by linear approximation in the longitudinal direction of the metal. The pixel resolution map creation unit 2137 a outputs the created pixel resolution map A to the deterioration magnitude estimation unit 214 .

Next, the case where it is determined in step S7 that the number of metal fittings N=2 will be described. In step S11, the thinning unit 2134 displays a thin line along the longitudinal direction of the detected hard metal at the center of the width of the hard metal, and performs thinning processing to linearly represent the width of the hard metal. The thinning unit 2134 outputs the thinning result to the installation interval extracting unit 2135 .

In step S12 of FIG. 15B, the installation interval extraction unit 2135 measures the number of pixels corresponding to the interval distance of the fine lines displayed by the thinning unit 2134, and outputs it to the actual size comparison unit 2136b. The vertical position of the interval distance to be measured may be freely set, and the number of pixels corresponding to the interval distance at a plurality of positions of the thin line may be measured.

In step S13, the actual size comparison unit 2136b calculates the pixel resolution for each pixel and outputs it to the pixel resolution map creation unit 2137b. Specifically, the actual size comparison unit 2136b compares the number of pixels corresponding to the distance between the thin lines represented by the steel metal in the image measured in step S12 and the steel metal pre-stored in the storage unit 22. is compared with the actual size value of the interval distance, and the pixel resolution is obtained by the above equation (2).

In step S14, the pixel resolution map creation unit 2137b performs linear approximation of the relationship between the pixel resolution calculated by the actual size comparison unit 2136b and the coordinates of the image, thereby generating a pixel resolution map B indicating the pixel resolution of each pixel of the entire image. to create The pixel resolution map creation unit 2137 b outputs the created pixel resolution map B to the deterioration magnitude estimation unit 214 .

Next, a case where it is determined in step S7 that the number of metal fittings N≧3 will be described. In step S15, the object width extraction unit 2133b measures the number of pixels corresponding to the width of the metal object. The object width extraction unit 2133b may measure the number of pixels in each width of all the detected metal objects. Alternatively, the object width extracting unit 2133b may identify a plurality of metal objects in descending order of the ratio of the size of the facility area in the image, and measure the number of pixels for the width of only the identified metal objects. The object width extraction unit 2133b outputs the measurement result to the actual size comparison unit 2136c.

At step S16 in FIG. 15B, the actual size comparison unit 2136c calculates the pixel resolution for each pixel. The details of the processing of step S16 are the same as those of step S9 or step S13, and thus the description thereof is omitted. The actual size comparison unit 2136c outputs the calculated result to the pixel resolution map creation unit 2137c.

In step S17, the pixel resolution map creation unit 2137c linearly approximates the relationship between the pixel resolution calculated by the actual size comparison unit 2136c and the coordinates of the image, thereby generating a pixel resolution map indicating the pixel resolution of each pixel of the entire image. create C. The pixel resolution map is created by linear approximation in the transverse direction of the metal. The pixel resolution map creation unit 2137 c outputs the created pixel resolution map C to the deterioration magnitude estimation unit 214 .

After performing the above-described processing, the pixel resolution estimation unit 213 finishes estimating the pixel resolution.

Referring to FIG. 14A again, in step S18, the deteriorated area coordinate acquisition unit 2141 of the deterioration magnitude estimation unit 214 acquires the coordinates in the image of the area detected as the deteriorated area.

In step S19 in FIG. 14B , the deteriorated area coordinate acquisition unit 2141 determines which of the deteriorated area length estimation unit 2142 and the deteriorated area area estimation unit 2143 performs the next process according to the acquired coordinate values. , the degraded region length estimator 2142 and the degraded region area estimator 2143 . Degraded region coordinate acquisition section 2141 determines that degraded region length estimation section 2142 performs next processing when the degradation region is linear degradation, and outputs the acquired coordinates to degradation region length estimation section 2142. do. In this case, the process proceeds to step S20. Degraded area coordinate acquisition section 2141 determines that degraded area area estimation section 2143 performs next processing when the degraded area has a shape having an area, and outputs the acquired coordinates to degraded area area estimation section 2143 . In this case, the process proceeds to step S21.

First, the case where it is determined in step S19 that the degraded region length estimation unit 2142 will perform the next process and the process proceeds to step S20 will be described. In step S20, the degraded region length estimator 2142 calculates the length of the degraded region from the coordinates indicating the degraded region. The degraded region length estimation unit 2142 stores the calculated result in the storage unit 22 . Although an example of calculating the maximum length of the degraded region will be described here, the length to be calculated may be set freely.

Specifically, the degraded region length estimator 2142 extracts points that form an arbitrary polygon according to the shape of the degraded region, and determines one of the diagonals of the polygon as the maximum length. do. For example, referring to FIG. 13A, cracks are indicated by dashed lines as degraded regions. The degraded region length estimating unit 2142 calculates, of the coordinates of the degraded region, the point A having the maximum value on the vertical axis (Y axis), the point B having the maximum value on the horizontal axis (X axis), and the point B having the maximum value on the vertical axis (Y The point C with the minimum value on the X-axis and the point D with the minimum value on the horizontal axis (X-axis) are extracted. The degraded region length estimating unit 2142 creates a quadrangle formed by straight lines connecting points A to D, and the straight line connecting points A and C among the diagonals of the quadrangle has the maximum length L′. It is determined that it is max.

Next, the degraded area length estimation unit 2142 plots the coordinates of the point forming the maximum length on any one of the pixel resolution maps AC. Then, the degraded area length estimator 2142 obtains the distance between the plotted points, that is, the actual size value of the maximum length of the degraded area from the pixel resolution value indicated by the pixel resolution map. For example, FIG. 13B shows points A and C forming the maximum length plotted on a pixel resolution map. The degraded area length estimator 2142 obtains the distance of the plotted coordinate values, ie, the actual size value of the maximum length of the degraded area, from the pixel resolution value indicated by the pixel resolution map. On the pixel resolution map of FIG. 13B, the degraded region length estimator 2142 forms a right-angled triangle whose oblique side is the straight line connecting the plotted points A and C. FIG. The degraded region length estimation unit 2142 calculates the pixel resolution of pixels corresponding to a straight line extending downward along the vertical axis from point A and a straight line extending leftward from point C along the horizontal axis, which form a right angle. Measure and determine the actual size of each straight line. From FIG. 13B, the deteriorated region length estimator 2142 totals the pixel resolution values of the pixels corresponding to the straight line extending from the point A, and calculates that the actual size value of the straight line is 5.5 mm. Also, the pixel resolution values of the pixels corresponding to the straight line extending from the point C are totaled to calculate that the actual size value of the straight line is 3.4 mm. Then, the deteriorated region length estimation unit 2142 calculates that the actual size value of the oblique side connecting the points A and C is 6.5 mm by the Pythagorean theorem.

Next, a case where it is determined in step S19 that the degraded area area estimation unit 2143 will perform the next process and the process proceeds to step S21 will be described. In step S21, the degraded area area estimation unit 2143 calculates the area of the degraded area. The deteriorated area area estimation unit 2143 stores the calculated result in the storage unit 22 .

Specifically, the degraded area area estimation unit 2143 plots the acquired coordinate values of the degraded area on one of the pixel resolution maps AC. The degraded area area estimation unit 2143 identifies the pixel resolution value of each pixel corresponding to the degraded area based on the plotted coordinates. Next, the deteriorated area area estimation unit 2143 squares each of the specified pixel resolution values to obtain the actual size value of the area per pixel. The deteriorated area area estimator 2143 adds the obtained actual size values of the area per pixel, and calculates the total value as the actual size value of the area of the entire deteriorated region.

As shown in steps S18 to S21, the deterioration magnitude estimation unit 214 estimates the actual size value of the deteriorated area detected by the deteriorated area detection unit 212 based on the pixel resolution map created by the pixel resolution estimation unit 213.

In step S<b>22 , the control unit 21 of the deterioration evaluation device 20 reads information indicating the estimated actual size of the deteriorated region from the storage unit 22 and transmits the information to the server device 30 via the communication unit 23 .

In step S23, the server device 30 receives the information indicating the actual size of the deteriorated area and stores it in the storage section of the server device 30.

As described above, the deterioration evaluation apparatus 20 according to this embodiment includes the equipment area detection unit 211 that detects the equipment area from the acquired image, the deterioration area detection unit 212 that detects the deterioration area from the image, and the detected equipment area and a deterioration size estimation unit 214 for estimating the size of the deteriorated region based on the pixel resolution.

According to this embodiment, by estimating the pixel resolution from the detected equipment area and using the pixel resolution, the actual size value of the deteriorated area can be estimated. Therefore, it is possible to provide a deterioration evaluation device and a deterioration evaluation method capable of evaluating the actual size value of a deteriorated region without being limited to certain photographing conditions.

As described above, in the degradation evaluation apparatus 20 according to this embodiment, the pixel resolution estimation unit 213 creates a pixel resolution map of the entire image by approximating the relationship between the coordinates of the image and the pixel resolution. A creation unit 2137 is further provided. A degradation size estimation unit 214 estimates the size of the degradation region based on the pixel resolution indicated by the pixel resolution map.

According to this embodiment, the pixel resolution map of the entire image can be grasped in a unified manner. By superimposing the coordinates of the degraded region on the pixel resolution map, the actual size of the degraded region can be easily estimated. Therefore, it is possible to provide a deterioration evaluation device and a deterioration evaluation method capable of evaluating the actual size value of a deteriorated region without being limited to certain photographing conditions.

As described above, in the deterioration evaluation apparatus 20 according to the present embodiment, the pixel resolution estimation unit 213 includes the object number extraction unit 2131 that extracts the number of facilities indicated by the facility area, and the number of extracted facilities. It further includes an actual size comparison unit 2136 for estimating the pixel resolution by comparing the number of pixels indicating the facility area and the actual size value.

According to this embodiment, a method of estimating pixel resolution is selected according to the number of facilities. This makes it possible to estimate the pixel resolution of an image with higher accuracy. Therefore, it is possible to provide a deterioration evaluation device and a deterioration evaluation method capable of evaluating the actual size value of a deteriorated region without being limited to certain photographing conditions.

As described above, in the deterioration evaluation apparatus 20 according to the present embodiment, when the number of facilities extracted by the object number extraction section 2131 is 1 or 3 or more, the pixel resolution estimation unit 213 selects pixels corresponding to the width of the facility. It further comprises an object width extractor 2133 that measures the number. The actual size comparison unit 2136 divides the actual size value of the width of the facility by the number of pixels measured to estimate the pixel resolution.

According to this embodiment, when the number of facilities is 1 or 3 or more, the pixel resolution can be accurately estimated based on the number of pixels corresponding to the width of the facility and the known actual width of the facility. The image in which only one metal object was detected was an image taken relatively close to the tunnel wall, and the deteriorated area was often reflected near the metal object. By estimating the pixel resolution for the corresponding number of pixels and the actual size value, the actual size value of the degraded region can be accurately estimated. On the other hand, images in which three or more metal objects are detected are often images shot from the front to the back of the cable tunnel. highly sexual. By estimating the pixel resolution with respect to the number of pixels corresponding to the width of a plurality of metal bars and the actual size value, the actual size value of such a deteriorated region can also be accurately estimated. Therefore, it is possible to provide a deterioration evaluation apparatus and a deterioration evaluation method capable of evaluating the actual size value of a deteriorated region without being limited to certain photographing conditions.

As described above, in the deterioration evaluation apparatus 20 according to the present embodiment, when the number of facilities extracted by the object number extraction section 2131 is two, the pixel resolution estimation unit 213 performs thinning to express the width of the facilities linearly. 2134, and an installation interval extraction unit 2135 for measuring the number of pixels corresponding to the interval distance between fine lines. The actual size comparison unit 2136 divides the actual size value of the gap distance by the measured number of pixels to estimate the pixel resolution.

According to this embodiment, when the number of facilities is 2, the facilities are represented by thin lines, and the accuracy The pixel resolution can be estimated well. Based on the actual size of the separation distance between the metal objects and the number of pixels measured, the overall pixel resolution of the image can be made closer to the actual size value, even if the two steel objects are not close to the center of the image. can be reproduced in the near future. Therefore, it is possible to provide a deterioration evaluation apparatus and a deterioration evaluation method capable of evaluating the actual size value of a deteriorated region without being limited to certain photographing conditions.

Although the present disclosure has been described based on the drawings and embodiments, it should be noted that a person skilled in the art can easily make various modifications and modifications based on the present disclosure. Therefore, it should be noted that these variations and modifications are included within the scope of this disclosure.

(Modification 1)
As a modified example of the present disclosure, the control unit 21 of the deterioration evaluation device 20 may further include an equipment area correction unit 215 . The facility area correction unit 215 performs at least one of a process of deleting an overdetected area from the facility area and a process of interpolating a segmented area in the facility area.

An over-detected area is an area where the equipment area detection unit 211 has detected an area other than the equipment area as the equipment area. For example, when a background area in an image is detected as an equipment area, the detected area is called an overdetected area.

First, the process of detecting an area over-detected by the equipment area detection unit 211 and deleting the area by the equipment area correction unit 215 will be described. In FIG. 16A, the overdetected regions are indicated by arrow symbols. Detection of over-detected regions may be performed by any image analysis technique. For example, the equipment area correction unit 215 binarizes the result detected by the equipment area detection unit 211 based on the density of the pixels, refers to pixels in an arbitrary peripheral range of 4 or 8 neighborhoods of the target pixel, and obtains the same value , the pixels with the same value are taken as one connected pixel. The facility area correction unit 215 deletes connected pixels whose sizes are equal to or smaller than the threshold. The threshold in this case may be set arbitrarily. After deleting the overdetected area, the facility area correction unit 215 generates a corrected facility area by correcting the facility area. FIG. 16B shows the corrected equipment area with the over-detected area removed in FIG. 16A.

Next, the process of interpolating the divided area in the equipment area detected by the equipment area detection unit 211 by the equipment area correction unit 215 will be described. Here, division of the facility area occurs due to the presence of an object between the imaging device 10 and the facility. In FIG. 17A, an arrow symbol indicates a segmented facility area due to the presence of a cable or a bracket for supporting the cable on the front face of the steel. Detection of the segmented regions may be performed by any image analysis method. The facility region correction unit 215 interpolates the segmented regions by, for example, a morphological conversion method. Also, although the type of morphological transformation is not limited, it is effective and desirable to perform a closing process in which an erosion process is performed after an expansion process. After interpolating the divided area, the facility area correction unit 215 generates a corrected facility area by correcting the facility area. FIG. 17B shows the corrected equipment area with the fragmented area detected in FIG. 17A interpolated.

As shown in FIG. 18, the equipment area correction unit 215 can perform processing after the equipment area detection unit 211 performs processing. As a result, the number-of-objects extraction unit 2131 included in the pixel resolution estimation unit 213 can extract the number of facilities indicated by the corrected facility area generated by the facility area correction unit 215 .

The equipment area correction unit 215 may be able to detect divided areas in the degraded areas detected not only by the equipment area detection unit 211 but also by the degraded area detection unit 212 and interpolate the areas. In this case, the equipment area correction unit 215 can execute processing after the processing of the deteriorated area detection unit 212 .

As described above, the deterioration evaluation apparatus 20 according to Modification 1 performs at least one of the process of deleting the overdetected area from the equipment area and the process of interpolating the divided area in the equipment area. further includes an equipment area correction unit 215 that generates a corrected equipment area by correcting The object number extraction unit 2131 extracts the number of facilities indicated by the corrected facility area.

According to this modified example, it is possible to accurately grasp the number of facilities in an image by deleting overdetected areas or interpolating divided areas. Therefore, the pixel resolution can be estimated more accurately, and the actual size value of the degraded area can be estimated. Therefore, it is possible to provide a deterioration evaluation device and a deterioration evaluation method capable of evaluating the actual size value of a deteriorated region without being limited to certain photographing conditions.

(Modification 2)
As a modification of the present disclosure, the pixel resolution map created by the pixel resolution map creation unit 2137a, the pixel resolution map creation unit 2137b, or the pixel resolution map creation unit 2137c may have two-dimensional angles.

Depending on the shooting angle of the image, it is conceivable that the pixel resolution of the entire image changes in both the horizontal and vertical directions of the image. For example, in the example shown in FIG. 19, the image is angled and three metal objects are detected. In this case, as indicated by arrow symbols, the object width extraction unit 2133b, the thinning unit 2134, and the installation interval extraction unit 2135 measure the pixels corresponding to the width and the installation interval of the reinforcing metal. The dimension comparison unit 2136c estimates the pixel resolution in both the longitudinal direction and the lateral direction of the metal rod. Then, the pixel resolution map creation unit 2137b and the pixel resolution map creation unit 2137c create a pixel resolution map D that changes two-dimensionally.

FIG. 20 is a diagram for explaining the pixel resolution map D created based on the image shown in FIG. The scale on the right side of the figure expresses the pixel resolution value in the image by shading. Looking at FIG. 20, it can be seen that the pixel resolution value increases along the direction indicated by the two arrow symbols in the image, that is, from the upper right to the lower left of the image. Thus, in the pixel resolution map D, the pixel resolution values change two-dimensionally with angles.

According to this modified example, it is possible to estimate the pixel resolution in consideration of the imaging angle of the image and create a pixel resolution map. Therefore, it is possible to provide a deterioration evaluation apparatus and a deterioration evaluation method capable of evaluating the actual size value of a deteriorated region without being limited to certain photographing conditions.

1 deterioration evaluation system 10 photographing device 20 deterioration evaluation device 30 server device 21 control unit 22 storage unit 23 communication unit 24 input unit 25 output unit 211 facility area detection unit 212 deterioration area detection unit 213 pixel resolution estimation unit 2131 object number extraction unit 2132 Object number determination unit 2133a, 2133b Object width extraction unit 2134 Object thinning unit 2135 Installation interval extraction unit 2136a, 2136b, 2136c Actual size comparison unit 2137a, 2137b, 2137c Pixel resolution map creation unit 214 Degradation magnitude estimation unit 2141 Degraded area coordinates Acquisition unit 2142 Degraded area length estimation unit 2143 Degraded area area estimation unit 215 Facility area correction unit

Claims (8)

1. an equipment area detection unit that detects an equipment area from the acquired image;
   a degraded area detection unit that detects a degraded area from the image;
   a pixel resolution estimation unit that estimates the pixel resolution of at least part of the image based on the detected facility area;
   a deterioration size estimation unit that estimates the size of the deteriorated region based on the pixel resolution;
   A deterioration evaluation device.
2. The pixel resolution estimator,
   a pixel resolution map creation unit that creates a pixel resolution map of the entire image by approximating the relationship between the coordinates of the image and the pixel resolution;
   2. The deterioration evaluation apparatus according to claim 1, wherein said deterioration size estimating section estimates the size of said deteriorated region based on said pixel resolution indicated by said pixel resolution map.
3. The pixel resolution estimator,
   an object number extraction unit that extracts the number of facilities indicated by the facility area;
   an actual size comparison unit for estimating the pixel resolution by comparing the number of pixels indicating the facility area and the actual size value according to the extracted number of the facilities;
   The deterioration evaluation device according to claim 1 or 2, further comprising:
4. The pixel resolution estimator,
   further comprising an object width extraction unit that measures the number of pixels corresponding to the width of the facility when the number of facilities extracted by the object number extraction unit is 1 or 3 or more,
   4. The deterioration evaluation apparatus according to claim 3, wherein said actual size comparison unit divides the actual size value of the width of said facility by said measured number of pixels to estimate said pixel resolution.
5. The pixel resolution estimator,
   when the number of facilities extracted by the number-of-objects extraction unit is two, a thinning unit representing the width of the facility in a line;
   an installation interval extraction unit that measures the number of pixels corresponding to the interval distance between the fine lines;
   4. The deterioration evaluation apparatus according to claim 3, wherein said actual size comparison unit divides the actual size value of said gap distance by said measured number of pixels to estimate said pixel resolution.
6. A facility area correction unit that generates a corrected facility area by correcting the facility area by at least one of a process of deleting an overdetected area from the facility area and a process of interpolating a segmented area in the facility area. further comprising
   The deterioration evaluation device according to any one of claims 3 to 5, wherein the number-of-objects extraction unit extracts the number of facilities indicated by the repair facility area.
7. A deterioration evaluation method for evaluating deterioration by a deterioration evaluation device,
   a step of detecting an equipment area from the acquired image;
   detecting degraded regions from the image;
   estimating a pixel resolution of at least a portion of the image based on the detected equipment area;
   estimating the size of the degraded region based on the pixel resolution;
   Deterioration evaluation method, including
8. A program for causing a computer to function as the deterioration evaluation device according to any one of claims 1 to 6.

Images