JP6664574B1 - Image processing system and image processing method - Google Patents

Abstract

The image processing system (1) includes an image dividing unit (12), an image extracting unit (13), and a facility image specifying unit (15). The image dividing unit (12) divides the image of the structure including the image of the equipment attached to the structure into a plurality of images having a size smaller than the image showing the entire equipment. The image extracting unit (13) extracts a plurality of images showing a part of the equipment from the plurality of images divided by the image dividing unit (12). The equipment image specifying unit (15) connects two or more images, which are located at positions adjacent to each other, before being divided by the image dividing unit (12) among the plurality of images extracted by the image extracting unit (13). , A connected image including two or more connected images is specified as the facility image.

Description

  The present invention relates to an image processing system and an image processing method for specifying an image of a facility from an image of a structure to which the facility is attached.

  2. Description of the Related Art Conventionally, equipment such as a lighting device or a signboard attached to a structure such as a tunnel or a bridge is regularly inspected. In the inspection of the equipment, work is performed to check whether fasteners for attaching the equipment to the structure have rust or looseness, or whether the equipment itself has any problems such as cracks. If such an operation is carried out by visually confirming, for example, all the equipment attached to the structure by all the operators, it takes much time and effort.

  Instead of performing the inspection work visually, there is a method of identifying an image of the facility from an image captured by the imaging device and confirming the identified image. As a technique for specifying an image, Patent Literature 1 discloses a technique for comparing an image obtained by capturing an image of a surrounding area with an imaging camera with a teaching facility image to identify an image of the facility from an image captured by the imaging camera. Have been.

JP-A-2002-19606

  However, in the technology described in Patent Literature 1, the size of the image to be handled is large because the image captured by the imaging camera is compared with the teaching facility image, and the technology is used in a process of specifying the facility image from the image captured by the imaging camera. The amount of memory to be used is large.

  The present invention has been made in view of the above, and an object of the present invention is to provide an image processing system capable of reducing the amount of memory used for processing for specifying an image of a facility from an image of a structure to which the facility is attached. Aim.

  In order to solve the above-described problems and achieve the object, an image processing system according to the present invention includes an image dividing unit, an image extracting unit, and a facility image specifying unit. The image division unit divides an image of a structure including an image of equipment attached to the structure into a plurality of images having a smaller size than an image showing the entire equipment. The image extracting unit extracts a plurality of images showing a part of the facility from the plurality of images divided by the image dividing unit. The equipment image specifying unit connects two or more images at positions adjacent to each other before being divided by the image dividing unit among the plurality of images extracted by the image extracting unit, and combines the two or more images. The connected image including the specified image is specified as the equipment image.

  ADVANTAGE OF THE INVENTION According to this invention, it is effective in the ability to reduce the amount of memory used for the process which specifies the image of a facility from the image of the structure to which the facility was attached.

FIG. 1 is a diagram for explaining an image processing system according to a first embodiment of the present invention. The figure which shows an example of the acquisition method of the structure image by the traveling type measuring device concerning Embodiment 1. The figure which shows an example of the structure image measured by the traveling type measuring device concerning Embodiment 1. FIG. 1 is a diagram illustrating a configuration example of an image processing system according to a first embodiment; FIG. 6 is a diagram for explaining an example of an image dividing process by the image dividing unit according to the first embodiment. FIG. 7 is a view for explaining an example of an image extraction process by the image extraction unit according to the first embodiment. FIG. 7 is a diagram for explaining an example of a learning process performed by a first learning model generation unit according to the first embodiment. FIG. 6 is a diagram for explaining an example of a facility image specifying process performed by the facility image specifying unit according to the first embodiment. The figure which shows the other example of the equipment image specification processing by the equipment image specification unit according to the first embodiment. The figure which shows the other example of the equipment image specification processing by the equipment image specification unit according to the first embodiment. FIG. 6 is a diagram for explaining an example of specific region image processing by a specific region extraction unit according to the first embodiment. FIG. 8 is a diagram for explaining an example of an abnormality determination process performed by the abnormality determination unit according to the first embodiment. 5 is a flowchart illustrating an example of a processing procedure performed by the image processing system according to the first embodiment; 5 is a flowchart illustrating an example of an image extraction process performed by the image extraction unit according to the first embodiment; 5 is a flowchart illustrating an example of a facility image specifying process performed by the facility image specifying unit according to the first embodiment; 5 is a flowchart illustrating an example of each of the specific area image processing by the specific area extraction unit and the abnormality determination processing by the abnormality determination unit according to the first embodiment; FIG. 1 is a diagram illustrating an example of a hardware configuration of an image processing system according to a first embodiment. FIG. 4 is a diagram for explaining an image processing system according to a second embodiment of the present invention. The figure which shows an example of the acquisition method of the structure image by the traveling type measuring device concerning Embodiment 2. The figure which shows an example of the structure image measured by the traveling type measuring device concerning Embodiment 2. FIG. 2 is a diagram illustrating a configuration example of an image processing system according to a second embodiment; FIG. 9 is a diagram for explaining a relationship between a look-up diagram and a look-down diagram according to the second embodiment. 11 is a flowchart illustrating an example of a partial procedure in a facility image specifying process performed by the facility image specifying unit according to the second embodiment.

  Hereinafter, an image processing system and an image processing method according to an embodiment of the present invention will be described in detail with reference to the drawings. The present invention is not limited by the embodiment.

Embodiment 1 FIG.
FIG. 1 is a diagram for explaining the image processing system according to the first embodiment of the present invention. The image processing system 1 illustrated in FIG. 1 specifies a facility image that is an image of a facility from an image of a structure to which the facility is attached. In the following, a description will be given assuming that the structure imaged by the traveling measurement device 2 is the tunnel 3 and the equipment 4 attached to the tunnel 3 is a lighting device. The structure imaged by the traveling type measurement device 2 is not limited to the tunnel 3 but may be a bridge or a building. The equipment 4 is not limited to lighting equipment, but may be a blower, a signboard, or the like.

  FIG. 2 is a diagram illustrating an example of a method of acquiring a structure image by the traveling measurement device according to the first embodiment. As shown in FIG. 2, the traveling measurement device 2 has an imaging unit 51 mounted thereon. The traveling measuring device 2 repeatedly captures an image of the periphery of the traveling measuring device 2 by the imaging unit 51 while traveling in the tunnel 3, and generates a structure image that is an image of the inner wall 3 a of the tunnel 3 to which the equipment 4 is attached. I do.

  The imaging unit 51 is, for example, a line camera, and has a plurality of pixels arranged in a direction orthogonal to or intersecting with the traveling direction of the traveling measurement device 2. The traveling measurement device 2 generates a structure image based on information on pixels repeatedly output from the line camera. Note that the imaging unit 51 may be an area camera in which a plurality of pixels are arranged in a matrix.

  FIG. 3 is a diagram illustrating an example of a structure image measured by the traveling measurement device according to the first embodiment. The structure image 5 shown in FIG. 3 is a developed image of the tunnel 3 on the assumption that a part of the inner wall 3a of the tunnel 3 is developed on a two-dimensional plane. In FIG. 3, the tunnel axis direction is the X-axis direction, and the tunnel circumferential direction is the Y-axis direction. The tunnel axis direction is a direction in which the tunnel 3 extends. Further, the tunnel circumferential direction is a direction along a line indicating the inner wall 3a when the tunnel 3 is cut along a plane orthogonal to the tunnel axis direction.

  The traveling type measuring device 2 has a laser scanner device, and measures the three-dimensional shape of the inner wall 3a of the tunnel 3 by the laser scanner device. The traveling type measuring device 2 detects the three-dimensional position of each pixel constituting the structure image 5 from the data obtained by the laser scanner device. The traveling measurement device 2 can generate a developed image of the tunnel 3 based on the three-dimensional position of each pixel constituting the structure image 5. The traveling type measurement device 2 generates the structure image 5 so that the intervals between the pixels forming the structure image 5 are equal to a preset interval. That is, the traveling type measurement device 2 generates the structure image 5 so that the actual size of the tunnel 3 is reduced to a preset scale.

The structural image 5 shown in FIG. 3 is an image of the inner wall 3a of the tunnel 3 to which the equipment 4 is attached, and is an image from the entrance to the exit of the tunnel 3. Building image 5 is generated by connecting a plurality of region images 6 _{through 65,} which are sequentially output from the imaging unit 51. Area image _{6 through 65,} the different areas of the tunnel axis direction, respectively. The structure image 5 shown in FIG. 3, includes an image of a plurality of facilities ₄₁ to _7. Hereinafter, the case shown each of the plurality of equipment ₄₁ to ₇ without individually distinguished, listed and equipment 4, indicating each of the plurality of area images 6 _{through 65} without individually distinguished area Described as Image 6.

  FIG. 4 is a diagram illustrating a configuration example of the image processing system according to the first embodiment. As shown in FIG. 4, the image processing system 1 according to the first embodiment includes an acquisition unit 10, an image information storage unit 11, an image division unit 12, an image extraction unit 13, and a first learning model generation unit 14 And an equipment image specifying unit 15 and an input unit 16. Further, the image processing system 1 includes a specific area extraction unit 17, an equipment information storage unit 18, an abnormality determination unit 19, a second learning model generation unit 20, an equipment abnormality information storage unit 21, a display processing unit 22, , A display unit 23.

The acquisition unit 10 acquires structure image information, which is information on the structure image 5, from the traveling measurement device 2 via a communication network (not shown), and stores the acquired structure image information in the image information storage unit 11. Let it. Building image information stored in the image information storage unit 11 may be constructed from information of a plurality of region images 6 _{through 65} of the state of not being spliced together. In this case, information of each area image 6 includes information of an identification number or information of an imaging position so that two adjacent area images 6 along the tunnel axis direction can be specified.

For example, running type measuring device 2 allocates one by one information of a plurality of identification numbers consecutive in the order of the area image _{6 1,} 6 _2, 6 _3, 6 4, _{6 5} shown in FIG. A plurality of identification numbers for example _ID 1 _consecutive, ID _2, ID _3, ID 4, if it is ID _5, the area image _{6 1} assigned identification number "ID _1", the area image _{6 2} identification number assigned "ID _2", the area image _{6 3} are assigned identification number "ID _3". Also, the area image _{6 4} assigned identification number "ID _4", the area image _{6 5} is assigned an identification number "ID _5".

  In addition, the traveling type measuring device 2 has a position detecting unit (not shown) that detects a traveling position of the traveling type measuring device 2, and the traveling type measuring device when each region image 6 is captured by the position detecting unit. 2 is detected as the imaging position of the area image 6. The traveling type measurement device 2 can also generate structure image information by associating the information on the detected imaging position of the region image 6 with the information on the region image 6 for each region image 6. In this case, the traveling type measuring device 2 generates trajectory information indicating the traveling trajectory of the traveling type measuring device 2 based on the traveling position of the traveling type measuring device 2 repeatedly detected by the position detection unit, and generates the generated trajectory information. Is included in the structure image information.

  The image division unit 12 reads the structure image information from the image information storage unit 11 and, based on the read structure image information, converts the structure image 5 into a smaller size than the entire equipment image which is an image showing the entire equipment 4. Image division processing for dividing the image into a plurality of images. FIG. 5 is a diagram for explaining an example of an image dividing process performed by the image dividing unit according to the first embodiment. FIG. 5 shows only a part of the structure image 5.

  As illustrated in FIG. 5, the image dividing unit 12 divides the structure image 5 into a plurality of divided images 7 so that the size of the divided image 7 which is an image obtained by dividing the structure image 5 becomes a specified size. The specified size is smaller than the size of the entire equipment image. Since the specified size is smaller than the size of the entire equipment image, the entire equipment image is present over a plurality of divided images 7. As described above, since the structure image 5 is generated to have a preset scale with respect to the actual size of the tunnel 3, the size of the entire equipment image is generated by the traveling measurement device 2. It is obtained from the scale of the tunnel 3 for the whole equipment image.

  The image division unit 12 determines the size of the divided image 7 based on the size of the structure image 5 and the size of the entire facility image, and sets the determined size to a specified size. When the structure image information includes information of a plurality of region images 6, the image dividing unit 12 divides the region image 6 into a plurality of parts so that the size of the divided image 7 which is an image obtained by dividing the region image 6 becomes a specified size. The image is divided into images 7. In this case, the image dividing unit 12 determines the size of the divided image 7 based on the size of the area image 6 and the size of the entire facility image, and sets the determined size to the specified size. Note that the image division unit 12 can use information input to the input unit 16 as information of a specified size.

  The image extracting unit 13 illustrated in FIG. 4 extracts a plurality of images showing a part of the facility 4 from the plurality of divided images 7 divided by the image dividing unit 12 as partial images of the facility 4. The image extracting unit 13 extracts an image showing a part of the facility 4 from the plurality of divided images 7 using a learning model generated by machine learning. Hereinafter, an image showing a part of the equipment 4 extracted by the image extraction unit 13 may be referred to as an equipment partial image.

  FIG. 6 is a diagram for explaining an example of an image extracting process performed by the image extracting unit according to the first embodiment. As shown in FIG. 6, the image extracting unit 13 has a first learning model, and uses the first learning model to select one of the equipments 4 from the plurality of divided images 7 divided by the image dividing unit 12. A plurality of facility partial images 8 specified as images indicating a part are extracted.

  The first learning model is a calculation model generated by machine learning using an image showing a part of the facility 4. Information input to the first learning model is the divided image 7, and information output from the first learning model is information indicating whether or not the image is a part of the facility 4. The first learning model is, for example, a convolutional neural network, but may be a calculation model generated by a learning algorithm such as linear regression or logistic regression.

  The first learning model is generated by the first learning model generation unit 14 shown in FIG. The first learning model generation unit 14 generates a first learning model by machine learning using learning data. The learning data is an image showing a part of the facility 4 and an image other than an image showing a part of the facility 4. FIG. 7 is a diagram for explaining an example of a learning process performed by the first learning model generation unit according to the first embodiment. As illustrated in FIG. 7, the first learning model generation unit 14 performs a learning process using an image indicating a part of the facility 4 as a correct image and an image other than the image indicating a part of the facility 4 as an incorrect image. Generate a first learning model.

  The image extracting unit 13 inputs the divided image 7 to the first learning model, and extracts the equipment partial image 8 based on information output from the first learning model. For example, when information indicating that the image is a part of the equipment 4 is output from the first learning model, the image extracting unit 13 converts the divided image 7 input to the first learning model into the equipment partial image 8. Extract as When information indicating that the image is not an image indicating a part of the equipment 4 is output from the first learning model, the image extracting unit 13 uses the divided image 7 input to the first learning model as the equipment partial image 8. Do not extract.

  Note that the image extraction unit 13 may be configured to extract the equipment partial image 8 by pattern matching or the like using an image showing a part of the equipment 4 as a reference image instead of the first learning model. For example, the image extracting unit 13 has an image indicating a part of the facility 4 as a reference image, and when the degree of coincidence between the image included in the divided image 7 and the reference image is equal to or greater than a preset value, The image 7 can be extracted as the equipment partial image 8.

  The equipment image specifying unit 15 connects the two or more equipment partial images 8 whose positions before being divided by the image division unit 12 are adjacent to each other among the plurality of equipment partial images 8 extracted by the image extraction unit 13. Then, a connected image including two or more connected equipment partial images 8 is specified as an image showing the entire equipment 4. Hereinafter, an image showing the entire equipment 4 specified by the equipment image specifying unit 15 may be referred to as an equipment image.

  FIG. 8 is a diagram illustrating an example of a facility image specifying process performed by the facility image specifying unit according to the first embodiment. FIG. 9 is a diagram illustrating another example of the facility image specifying process performed by the facility image specifying unit according to the first embodiment.

In the example shown in FIG. 8, equipment partial image _{8 1-8 12} are extracted by the image extracting unit 13. Hereinafter, indicating each facility portion image 8 ₁ to 8 _k without individually distinguished, referred to as equipment partial images 8. As shown in FIG. 8, each facility portion image 8 _{1-8 12,} the position before division by the image division unit 12 is in at least one and adjacent to each other positioned of the equipment partial images 8 _{1-8 12,} facility image specifying unit 15, connects the equipment partial image _{8 1-8 12.}

Facility image specifying unit 15, as shown in FIG. 8, by connecting the equipment partial image 8 _{1-8 12} As facilities partial image 8 _{1-8 12} becomes each before division by the image division unit 12 positions generates one consolidated image 9 including the equipment partial image _{8 1-8 12.}

The facility image specifying unit 15 determines whether or not the size of the connected image 9 is within a preset range, and when determining that the size of the connected image 9 is within the preset range, 9 is specified as a facility image. For example, in FIG. 8, when the length Sx of the connected image 9 in the X-axis direction satisfies the following equation (1), and the length Sy of the connected image 9 in the Y-axis satisfies the following equation (2), The connected image 9 is specified as a facility image. “Αmin” and “αmax” are parameters for specifying the range of the X axis, and “βmin” and “βmax” are parameters for specifying the range of the Y axis.
αmin <Sx <αmax (1)
βmin <Sy <βmax (2)

  When the structure image 5 is composed of a plurality of region images 6 and the structure image 5 is composed of a plurality of region images 6, it is assumed that the plurality of region images 6 are connected in the tunnel axis direction. Concatenate. For example, the plurality of region images 6 include a first region image and a second region image that are continuous along the tunnel axis direction, and one end of the first region image and one end of the second region image are connected to the tunnel axis. It is assumed that they are in a positional relationship facing each other in the directions. When there is a facility partial image 8 at one end of the first region image, the facility image specifying unit 15 determines that the facility partial image 8 that is opposite to the facility partial image 8 at one end of the first region image in the tunnel axis direction is the second. Is determined at one end of the region image. If the equipment image specifying unit 15 determines that the equipment partial image 8 is at one end of the second area image, the equipment image specifying unit 15 replaces the equipment partial image 8 at one end of the second area image with the equipment at one end of the first area image. Connect to the partial image 8. When the structure image information includes the information on the identification number described above, the facility image specifying unit 15 determines the positional relationship between the plurality of region images 6 based on the information on the identification number. In addition, when the structure image information includes the above-described imaging position information and trajectory information, the facility image specifying unit 15 performs a plurality of operations based on the imaging positions of the traveling measurement device 2 in the traveling trajectory of the traveling measurement device 2. The positional relationship of the region image 6 is determined.

In the example shown in FIG. 9, equipment partial image _{8 13, 8 14} are extracted by the image extracting unit 13. As shown in FIG. 9, equipment partial image _{8 13, 8 14,} because in the position located before the division by the image division unit 12 are adjacent to each other, facility image specifying unit 15, equipment partial image _{8 13, 8 14} Concatenate. In the linked image 9 shown in FIG. 9, the length Sx in the X-axis direction is smaller than the minimum value αmin, and the length Sy in the Y-axis direction is smaller than the minimum value βmin. Therefore, the facility image specifying unit 15 does not specify the linked image 9 illustrated in FIG. 9 as the facility image.

  As described above, the facility image specifying unit 15 specifies the connected image 9 whose size is within the preset range as the facility image. For this reason, the facility image specifying unit 15 may incorrectly specify an image other than the image of the facility 4 as the facility image as compared to the case where the connected image 9 is specified as the facility image regardless of the size of the connected image 9. Can be reduced.

  Further, the facility image specifying unit 15 is configured such that, of the plurality of divided images 7 divided by the image dividing unit 12, the position before division by the image dividing unit 12 is adjacent to at least one of the plurality of facility partial images 8. A plurality of divided images 7 at positions are extracted. The facility image specifying unit 15 connects the extracted plurality of divided images 7 and the plurality of facility partial images 8 so as to have a positional relationship before the division by the image dividing unit 12 to generate a connected image 9. For example, when there is a size enlargement setting, the facility image specifying unit 15 generates the connected image 9 using the divided image 7 in which the position before the division by the image dividing unit 12 is adjacent to the facility partial image 8. The facility image specifying unit 15 turns on the size enlargement setting flag when the operation on the input unit 16 is an operation for performing the size enlargement setting. The facility image specifying unit 15 determines that there is a size enlargement setting when the size enlargement setting flag is on.

FIG. 10 is a diagram illustrating another example of the facility image specifying process performed by the facility image specifying unit according to the first embodiment. In the example shown in FIG. 10, the equipment parts by the image extracting unit 13 images _{8, 83, 5-8 8,} 8 _{10, 8 11} are extracted. Facility image specifying unit 15, to at least any one adjacent position of the image dividing unit 12 facilities partial image ₈₂ positions of a plurality of pre-divided by _{8 3, 8 5-8 8,} 8 _{10, 8 11} extracting a certain plurality of divided images _{7 1-7 5,} 7 _{8, 7 9,} 7 _{12, 7 13,} 7 _{16, 7 17,} 7 20 _{to 7 24.}

The facility image specifying unit 15, a plurality of equipment partial images _{82, 83, 5-8 8,} 8 _{10, 8 11} and a plurality of divided images _{7 1-7 5,} 7 _8, 7 _{9, 7 12} , _{7 13,} 7 _{16, 7 17,} 7 20 _{to 7} and ₂₄ are connected so that the positional relationship before the division by the image division unit 12 generates a combined image 9.

  In order to reduce the possibility that the image extraction unit 13 erroneously determines the divided image 7 that is not an image showing a part of the facility 4 as the facility partial image 8, the image used as the learning data of the first learning model includes 4 may not include an image in which the proportion of a part of the image is small. In this case, it may be difficult for the image extraction unit 13 to extract, as the equipment partial image 8, the divided image 7 in which the proportion of the partial image of the equipment 4 is small. As described above, the facility image specifying unit 15 uses the divided image 7 adjacent to the facility partial image 8 in addition to the facility partial image 8 to generate the connected image 9. Therefore, even when there is a divided image 7 in which the ratio of a part of the equipment 4 in the image extraction unit 13 is small, the equipment image can be specified with high accuracy.

  As described above, since the image processing system 1 specifies the equipment image using the divided image 7 having a smaller size than the image of the equipment 4, the size of the image handled when specifying the equipment image is small. Therefore, the image processing system 1 can reduce the amount of memory used for processing for specifying the facility image, as compared with the case where the structure image 5 is not divided.

  The specific area extracting unit 17 illustrated in FIG. 4 extracts an image of a specific area in the connected image 9 specified as the facility image. The specific area is, for example, an area including an image of a determination target component that is a component to be subjected to abnormality determination, and is set from a design drawing of the equipment 4 or the like. The part to be determined is, for example, a fastener such as a bolt or a screw for attaching the facility 4 to the inner wall 3a of the tunnel 3, or a part constituting the facility 4.

  The equipment information storage unit 18 stores design drawing information, which is information of a design drawing of the equipment 4, and the design drawing information includes information indicating an area of a part to be determined. The specific area extraction unit 17 determines the area of the determination target component based on the design drawing information stored in the equipment information storage unit 18. The specific area extracting unit 17 determines an area including the area of the determination target component as the above-described specific area based on the determined area of the determination target component. Note that the specific area extraction unit 17 can also determine a specific area based on information on the specific area input to the input unit 16.

FIG. 11 is a diagram for explaining an example of specific region image processing performed by the specific region extraction unit according to the first embodiment. In the example illustrated in FIG. 11, the specific area extraction unit 17 outputs the specific area images 31 ₁ , 31 ₂ , 31 ₃ , and 31 that are images of the _four specific areas 30 ₁ , 30 ₂ , 30 ₃ , and 304 in the connected image 9. ₄ is extracted. Hereinafter, the case shown each of the specific area _{30 1,} 30 _2, 30 3, 30 ₄ to not separately distinguished, may be referred to as a specific region 30. Moreover, indicating each particular area image _{31 1,} 31 _2, 31 3, 31 ₄ to not separately distinguished, may be referred to as the specific area image 31.

  The abnormality determining unit 19 illustrated in FIG. 4 determines the abnormality of the facility 4 from the specific area image 31 extracted by the specific area extracting unit 17. The abnormality of the equipment 4 is, for example, an abnormality in the state of attachment of the equipment 4 to the inner wall 3a of the tunnel 3, or an abnormality such as a crack in the equipment 4. The abnormality determination unit 19 determines, for example, an abnormality of the determination target component configuring the equipment 4 from the specific area image 31 extracted by the specific area extraction unit 17 using a learning model generated by machine learning. When the determination target component is a fastener, the abnormality of the determination target component is, for example, looseness of the fastener, rust of the fastener, loss of the fastener, lack of the fastener, or crack of a component constituting the facility 4.

  The abnormality determination unit 19 has information of the second learning model, and determines abnormality of the determination target component from the image extracted by the specific area extraction unit 17 using the second learning model. The second learning model is a calculation model generated by machine learning using an image of a determination target component having an abnormality. The information input to the second learning model is the specific area image 31 extracted by the specific area extracting unit 17, and the information output from the second learning model indicates whether the determination target component is abnormal. Information. The second learning model is, for example, a convolutional neural network, but may be a calculation model generated by a learning algorithm such as linear regression or logistic regression.

  The second learning model is generated by the second learning model generation unit 20 shown in FIG. The second learning model generation unit 20 generates a second learning model by machine learning using learning data. The learning data is, for example, an image of a determination target component having no abnormality and an image of a determination target component having an abnormality. The second learning model generation unit 20 generates a second learning model by a learning process in which an image of the determination target component having no abnormality is set as the correct image and an image of the determination target component having abnormality is set as the incorrect image.

  The abnormality determination unit 19 inputs the specific area image 31 extracted by the specific area extraction unit 17 to the second learning model, and determines abnormality of the determination target component based on information output from the second learning model. Specifically, when the information indicating that the determination target component is abnormal is output from the second learning model, the abnormality determination unit 19 determines that the determination target component is abnormal. When information indicating that the determination target component is not abnormal is output from the second learning model, the abnormality determination unit 19 determines that the determination target component is not abnormal.

FIG. 12 is a diagram for explaining an example of the abnormality determination process performed by the abnormality determination unit according to the first embodiment. In the example shown in FIG. 12, the specific area extracting section 17 the specific area image ₃₁ 1 extracted _by 31 _2, 31 3, 31 ₄ are inputted to the second learning model. Then, abnormality determination unit 19, specific area image 31 _2, 31 _3, 31 3 determination target component corresponding to ₄ are normal, one determination target component corresponding to a specific area image 31 ₁ is abnormal Has been determined.

Thus, the image processing system 1 is connected to the image 9, design specific region ₃₀ set in advance in such figures _1, 30 _2, 30 3, 30 the specific area image ₃₁ 1 included in the _{4, 31} 2, 31 _3, 31 ₄ identifies, determines an abnormality of the equipment 4 using the specific area image _{31 1,} 31 _2, 31 3, 31 _4. Therefore, the image processing system 1 can reduce the time required for the process of determining the abnormality of the facility 4 as compared with the case where the abnormality of the facility 4 is determined using the connected image 9 as it is. Further, since the image processing system 1 performs the process of determining the abnormality of the facility 4 using the second learning model, the accuracy of the abnormality determination for the facility 4 can be improved.

  The abnormality determination unit 19 stores equipment abnormality information indicating information of the determination target component determined to be abnormal in the equipment abnormality information storage unit 21 illustrated in FIG. The display processing unit 22 illustrated in FIG. 4 reads out the equipment abnormality information from the equipment abnormality information storage unit 21 when a specific operation is performed on the input unit 16, and determines that there is an abnormality based on the read equipment abnormality information. The information of the determined component to be determined is displayed on the display unit 23.

  FIG. 13 is a flowchart illustrating an example of a processing procedure performed by the image processing system according to the first embodiment. The process illustrated in FIG. 13 is started, for example, when the structure image 5 is acquired by the image processing system 1 or when a specific operation is performed on the input unit 16.

  As shown in FIG. 13, the image dividing unit 12 of the image processing system 1 divides the structure image 5 into a plurality of divided images 7 (Step S10). Next, the image extraction unit 13 of the image processing system 1 performs an image extraction process (Step S11). Such an image extraction process is a process of steps S20 to S24 shown in FIG. 14 and will be described later.

  Next, the facility image specifying unit 15 of the image processing system 1 performs a facility image specifying process (Step S12). Such equipment image specifying processing is processing of steps S30 to S39 shown in FIG. 15 and will be described later. Next, the abnormality determination unit 19 of the image processing system 1 performs the specific area image processing and the abnormality determination processing (Step S13). The specific area image processing and the abnormality determination processing are processing of steps S40 to S45 shown in FIG. 16 and will be described later. When ending the processing of step S13, the image processing system 1 ends the processing shown in FIG.

  FIG. 14 is a flowchart illustrating an example of an image extracting process performed by the image extracting unit according to the first embodiment. As illustrated in FIG. 14, the image extracting unit 13 selects a divided image 7 that has not been processed by the image extracting unit 13 from among the plurality of divided images 7 generated by the image dividing unit 12 (Step S20). The divided image 7 selected in S20 is input to the first learning model (Step S21). The image extracting unit 13 determines whether or not the divided image 7 selected in Step S20 is the facility partial image 8 based on the output of the first learning model (Step S22).

  When determining that the divided image 7 selected in Step S20 is the equipment partial image 8 (Step S22: Yes), the image extracting unit 13 extracts the divided image 7 selected in Step S20 as the equipment partial image 8 (Step S20). S23). When the process of step S23 is completed, or when it is determined that the divided image 7 is not the facility partial image 8 (step S22: No), the image extracting unit 13 generates the plurality of divided images 7 generated by the image dividing unit 12. It is determined whether there is an unselected divided image 7 in step S20 (step S24).

  When determining that there is an unselected divided image 7 (step S24: Yes), the image extracting unit 13 shifts the processing to step S20. When determining that there is no unselected divided image 7 (step S24: No), the image extracting unit 13 ends the processing illustrated in FIG.

  FIG. 15 is a flowchart illustrating an example of a facility image specifying process performed by the facility image specifying unit according to the first embodiment. As shown in FIG. 15, the equipment image specifying unit 15 selects the unprocessed equipment partial image 8 from the plurality of equipment partial images 8 extracted by the image extracting unit 13 (Step S30). . The equipment image specifying unit 15 determines whether there is an equipment partial image 8 or a connected image 9 adjacent to the equipment partial image 8 selected in step S30 (step S31).

  If it is determined that there is an adjacent equipment part image 8 or connected image 9 (step S31: Yes), the equipment image specifying unit 15 replaces the equipment part image 8 selected in step S30 with the adjacent equipment part image 8 or connected image 9. (Step S32).

  When the processing of step S32 is completed, or when it is determined that there is no adjacent equipment partial image 8 or connected image 9 (step S31: No), the equipment image specifying unit 15 performs step S30 of the plurality of equipment partial images 8. It is determined whether or not there is an unselected equipment partial image 8 (step S33). When determining that there is an unselected facility partial image 8 (step S33: Yes), the facility image specifying unit 15 shifts the processing to step S30. When it is determined that there is no unselected facility partial image 8 (step S33: No), the facility image specifying unit 15 determines whether or not there is the connected image 9 generated in step S32 (step S34).

  When determining that there is the connected image 9 (step S34: Yes), the facility image specifying unit 15 determines whether or not there is a size enlargement setting (step S35). When determining that there is a size enlargement setting (step S35: Yes), the facility image specifying unit 15 combines the divided image 7 adjacent to the connected image 9 with the connected image 9 to change the connected image 9 (step S36). .

  When the processing of step S36 is completed, or when it is determined that there is no size enlargement setting (step S35: No), the facility image specifying unit 15 determines whether or not the size of the connected image 9 is within a preset range. A determination is made (step S37). When determining that the size of the connected image 9 is within the preset range (step S37: Yes), the facility image specifying unit 15 specifies the connected image 9 whose range is within the preset range as a facility image (step S37: Yes). Step S38).

  When the processing of step S38 is completed, or when the size of the connected image 9 is determined to be out of the preset range (step S37: No), the equipment image specifying unit 15 does not perform the processing by the equipment image specifying unit 15. It is determined whether or not there is a connected image 9 for processing (step S39). When determining that there is an unprocessed connected image 9 (step S39: Yes), the facility image specifying unit 15 shifts the processing to step S37. When determining that there is no unprocessed connected image 9 (Step S39: No) or when determining that there is no connected image 9 (Step S34: No), the facility image specifying unit 15 ends the processing illustrated in FIG. I do.

  FIG. 16 is a flowchart illustrating an example of each of the specific region image processing by the specific region extraction unit and the abnormality determination process by the abnormality determination unit according to the first embodiment. As illustrated in FIG. 16, the specific area extraction unit 17 selects the unprocessed connected image 9 in the abnormality determination unit 19 among the connected images 9 specified as the equipment image by the equipment image specifying unit 15 (Step S40). The specific area extraction unit 17 extracts the specific area image 31 from the connected image 9 selected in step S40 (step S41), and inputs the extracted specific area image 31 to the second learning model (step S42).

  The abnormality determination unit 19 determines whether or not the determination target component has an abnormality based on the output of the second learning model (Step S43). When it is determined that the determination target component has an abnormality (step S43: Yes), the abnormality determination unit 19 stores the equipment abnormality information indicating information of the determination target component determined to be abnormal in the equipment abnormality information storage unit 21. (Step S44). When the process of step S44 is completed or when it is determined that there is no abnormality in the component to be determined (step S43: No), the abnormality determining unit 19 determines the connected image 9 specified as the equipment image by the equipment image specifying unit 15. It is determined whether there is any unselected connected image 9 in step S40 (step S45).

  When determining that there is an unselected connected image 9 (step S45: Yes), the abnormality determination unit 19 shifts the processing to step S40. When determining that there is no unselected linked image 9 (step S45: No), the abnormality determination unit 19 ends the processing illustrated in FIG.

  FIG. 17 is a diagram illustrating an example of a hardware configuration of the image processing system according to the first embodiment. As illustrated in FIG. 17, the image processing system 1 includes a computer including a processor 101, a memory 102, a communication device 103, an input / output circuit 104, and a display device 105.

  The processor 101, the memory 102, the communication device 103, the input / output circuit 104, and the display device 105 can transmit and receive data to and from each other via the bus 106, for example. The image information storage unit 11, the equipment information storage unit 18, and the equipment abnormality information storage unit 21 are realized by the memory 102. The input unit 16 is realized by the input / output circuit 104. The display unit 23 is realized by the display device 105. The processor 101 reads out and executes the program stored in the memory 102 to obtain the acquisition unit 10, the image division unit 12, the image extraction unit 13, the first learning model generation unit 14, the facility image identification unit 15, and the specific region extraction. The function of the unit 17, the abnormality determination unit 19, the second learning model generation unit 20, and the display processing unit 22 is executed. The processor 101 is, for example, an example of a processing circuit, and includes one or more of a CPU (Central Processing Unit), a DSP (Digital Signal Processor), and a system LSI (Large Scale Integration).

  The memory 102 includes at least one of a RAM (Random Access Memory), a ROM (Read Only Memory), a flash memory, an EPROM (Erasable Programmable Read Only Memory), and an EEPROM (registered trademark) (Electrically Erasable Programmable Read Only Memory). Including. Further, the memory 102 includes a recording medium on which a computer-readable program is recorded. Such a recording medium includes at least one of a nonvolatile or volatile semiconductor memory, a magnetic disk, a flexible memory, an optical disk, a compact disk, and a DVD (Digital Versatile Disc). The image processing system 1 may include an integrated circuit such as an ASIC (Application Specific Integrated Circuit) and an FPGA (Field Programmable Gate Array).

  The image processing system 1 may be configured by a client device, may be configured by a server device, or may be configured by a client device and a server device. When the image processing system 1 includes two or more devices, each of the two or more devices has, for example, a hardware configuration illustrated in FIG. Communication between two or more devices is performed via the communication device 103. Further, the image processing system 1 may be configured by two or more server devices. For example, the image processing system 1 may include a processing server and a data server. In this case, the processing server includes, for example, the acquisition unit 10, the image division unit 12, the image extraction unit 13, the first learning model generation unit 14, the equipment image identification unit 15, the specific region extraction unit 17, the abnormality determination unit 19, the second It has a learning model generator 20 and a display processor 22. Further, the data server includes an image information storage unit 11, a first learning model generation unit 14, an equipment information storage unit 18, and an equipment abnormality information storage unit 21.

  As described above, the image processing system 1 according to the first embodiment includes the image dividing unit 12, the image extracting unit 13, and the facility image specifying unit 15. The image dividing unit 12 divides an image of a structure including an image of the facility 4 attached to the structure into a plurality of divided images 7 having a smaller size than an image showing the entire facility 4. The image extracting unit 13 extracts a plurality of facility partial images 8 showing a part of the facility 4 from the plurality of divided images 7 divided by the image dividing unit 12. The equipment image specifying unit 15 connects the two or more equipment partial images 8 whose positions before being divided by the image division unit 12 are adjacent to each other among the plurality of equipment partial images 8 extracted by the image extraction unit 13. The connected image 9 including the two or more connected equipment partial images 8 is specified as the image of the equipment 4. Since the image processing system 1 specifies the equipment image using the divided image 7 having a smaller size than the image showing the entire equipment 4, the image processing system 1 can specify the equipment image as compared with the case where the structure image 5 is not divided. The amount of memory used for processing can be reduced.

  The image extracting unit 13 has a first learning model generated by machine learning using an image indicating a part of the facility 4, and includes a first learning model among the plurality of divided images 7 divided by the image dividing unit 12. A plurality of facility partial images 8 are extracted using one learning model. Thereby, the image processing system 1 can accurately specify the facility image.

  Further, the facility image specifying unit 15 determines whether or not the size of the connected image 9 is within a preset range, and when determining that the size of the connected image 9 is within the preset range, The connected image 9 is specified as a facility image. Thereby, the image processing system 1 can accurately specify the facility image.

  In addition, the facility image specifying unit 15 determines that at least one of the facility partial images 8 whose positions before the division by the image dividing unit 12 are two or more among the plurality of divided images 7 divided by the image dividing unit 12. A plurality of divided images at adjacent positions and two or more equipment partial images are connected to generate a connected image. Thereby, the image processing system 1 can accurately specify the facility image.

  Further, the image processing system 1 extracts a specific area image 31 that is an image of the specific area 30 in the connected image 9, and a facility partial image from the specific area image 31 extracted by the specific area extraction section 17. And an abnormality judging unit 19 for judging the abnormality of No. 8. Thereby, the image processing system 1 can shorten the time of the abnormality determination process as compared with the case where the abnormality of the determination target component is determined using the connected image 9 as it is.

  Further, the abnormality determining unit 19 has a second learning model generated by machine learning using an image of the determination target component in a state where the determination target component is abnormal. The second learning model is an example of a learning model for abnormality determination. The abnormality determining unit 19 determines an abnormality of the facility 4 based on a result obtained by inputting the image extracted by the specific area extracting unit 17 to the second learning model. Accordingly, the image processing system 1 can increase the accuracy of the abnormality determination for the determination target component.

Embodiment 2 FIG.
The image processing system according to the second embodiment obtains an image of the entire inner wall 3a of the tunnel 3 including the facility 4 from the traveling measurement device as a structure image from the traveling measurement device, and positions the connected image 9 in the structure image. Is different from the image processing system 1 according to the first embodiment in that processing for specifying a facility image is performed based on In the following, components having the same functions as those of the first embodiment are denoted by the same reference numerals, and description thereof will be omitted. The differences from the image processing system 1 and the traveling type measurement device 2 of the first embodiment will be mainly described. explain.

  FIG. 18 is a diagram for explaining the image processing system according to the second embodiment of the present invention. The image processing system 1A illustrated in FIG. 18 specifies an equipment image that is an image of the equipment 4 attached to the tunnel 3 from an image of the tunnel 3 generated by the traveling measurement device 2A, and uses the specified equipment image to specify the equipment 4 To detect abnormalities.

  FIG. 19 is a diagram illustrating an example of a method of acquiring a structure image by the traveling measurement device according to the second embodiment. As shown in FIG. 19, the traveling type measurement device 2A includes imaging units 51A and 51B. The traveling type measuring device 2A travels in the tunnel 3, which is a structure, and repeatedly captures an image of the periphery of the traveling type measuring device 2A while changing the direction of the imaging units 51A and 51B to generate a structure image. The structure image generated by the traveling measurement device 2A is an image covering the entire inner wall 3a of the tunnel 3.

  FIG. 20 is a diagram illustrating an example of a structure image measured by the traveling measurement device according to the second embodiment. In FIG. 20, the tunnel axis direction is the X axis direction, and the tunnel circumferential direction is the Y axis direction. The tunnel axis direction is a direction in which the tunnel 3 extends.

The structure image 5A shown in FIG. 20 is an image of the entire inner wall 3a of the tunnel 3, and is a developed image of the tunnel 3 on the assumption that the entire inner wall 3a of the tunnel 3 is developed on a two-dimensional plane. Traveling-type measuring device 2A, a plurality of regions to generate an area image 6A a plurality of region images 6A ₁ ~6A ₅ sequentially output from the imaging unit 51A by joining the tunnel axis, are sequentially output from the imaging unit 51B image _6B 1 _{~6B 5} by connecting the tunnel axis to generate an area image 6B. The traveling type measurement device 2A generates the structure image 5A by joining the region image 6A and the region image 6B in the tunnel circumferential direction. The area image 6A includes images of a plurality of facilities _{41 to 7,} the area image 6B includes an image of a plurality of equipment _{4 8-4 14.} Incidentally, the structure image 5A, similar to the structure image 5 may include a plurality of region images _{6A 1 ~6A 5, 6B 1 ~6B} 5 of status information that has not been spliced together.

  FIG. 21 is a diagram illustrating a configuration example of the image processing system according to the second embodiment. As shown in FIG. 21, the image processing system 1A according to the second embodiment includes a facility image specifying unit 15A instead of the facility image specifying unit 15. The equipment image specifying unit 15A performs at least one of the rotation processing and the inversion processing of the connected image 9 based on the position of the connected image 9 in the structure image 5A, and converts the connected image 9 that has performed such processing into equipment. Specify as an image.

  For example, the facility image specifying unit 15A rotates the connected image 9 obtained by connecting the plurality of divided images 7 extracted from the region image 6A shown in FIG. The image 9 is specified as a facility image. In addition, the facility image specifying unit 15A specifies the connected image 9 obtained by connecting the plurality of divided images 7 extracted from the area image 6B illustrated in FIG.

  The type of the structure image 5A shown in FIG. 20 is a look-up view, which is a developed image obtained by developing an image of the inner wall 3a of the tunnel 3 when the inner wall 3a of the tunnel 3 is viewed from the inside of the tunnel 3; The device 2A can also generate a plan view. The look-down view is a developed image obtained by developing an image of the inner wall 3a of the tunnel 3 when the inner wall 3a of the tunnel 3 is viewed from the outside of the tunnel. Hereinafter, the structure image of the plan view is referred to as a structure image 5A '.

  Here, the plan view and the plan view will be described with reference to the drawings. FIG. 22 is a diagram for explaining a relationship between a look-up view and a look-down view according to the second embodiment. In the example shown in FIG. 22, two facilities 4 attached to the tunnel 3 are represented by the characters “2” and “5” for the sake of simplicity. In the example shown in FIG. 22, the right end of the entrance of the tunnel 3 is "a1", the left end of the entrance of the tunnel 3 is "b1", the right end of the exit of the tunnel 3 is "a2", and the exit of the tunnel 3 is The left end is “b2”. Note that the left-right direction is the direction when the tunnel 3 is viewed from just before the entrance of the tunnel 3.

  By developing the image of the inner wall 3a of the tunnel 3 with reference to the left ends b1 and b2 of the tunnel 3, a top view of the tunnel 3 can be obtained. In this look-up view, the character “2” is rotated 180 degrees. Therefore, the equipment image specifying unit 15A rotates the connected image 9 obtained by connecting the plurality of divided images 7 extracted from the area image 6A of the structure image 5A by 180 degrees, and converts the connected image 9 rotated by 180 degrees into the equipment image. To be specified. That is, when the position of the connected image 9 in the structure image 5A is included in the region image 6A, the equipment image specifying unit 15A specifies the connected image 9 rotated by 180 degrees as the equipment image.

  Further, by developing the image of the inner wall 3a of the tunnel 3 with reference to the right ends a1 and a2 of the tunnel 3, a look down view of the tunnel 3 can be obtained. In the look-down view, the area image 6A 'is an image obtained by converting the area image 6A, and the area image 6B' is an image obtained by converting the area image 6B. In such a look-down view, the character “2” is horizontally inverted, and the character “5” is vertically inverted.

  Therefore, the equipment image specifying unit 15A inverts the connected image 9 obtained by connecting the plurality of divided images 7 extracted from the area image 6A ′ of the structure image 5A ′, and converts the connected image 9 that has been inverted left and right into the equipment image. To be specified. That is, when the position of the connected image 9 in the structure image 5A 'is included in the region image 6A', the equipment image specifying unit 15A specifies the horizontally-inverted connected image 9 as the equipment image.

  Further, the facility image specifying unit 15A vertically inverts the connected image 9 obtained by connecting the plurality of divided images 7 extracted from the area image 6B ′ of the structure image 5A ′, and converts the vertically inverted connected image 9 into the facility image. To be specified. That is, when the position of the connected image 9 in the structure image 5A 'is included in the area image 6B', the equipment image specifying unit 15A specifies the connected image 9 inverted upside down as the equipment image.

  As described above, the facility image specifying unit 15A performs a process of rotating the connected image 9 or a process of inverting the connected image 9 based on the position of the connected image 9 in the structure image and the type of the structure image. Thereby, the equipment image specifying unit 15A can appropriately specify the equipment image, and can accurately determine the abnormality of the equipment 4 from the equipment image specified by the equipment image specifying unit 15A.

  Note that the image processing system 1A is a structure image 5A that is a look-down view from a device (not shown) that converts the structure image 5A into a look-down view instead of acquiring the structure image 5A ′ from the traveling type measurement device 2A. 'Can also be obtained.

  FIG. 23 is a flowchart illustrating an example of a partial procedure in a facility image specifying process performed by the facility image specifying unit according to the second embodiment. The process illustrated in FIG. 23 is a process performed between step S34 and step S35 illustrated in FIG.

  As shown in FIG. 23, the facility image specifying unit 15A of the image processing system 1A determines whether or not the structure image is a look-up view (Step S50). When determining that the structure image is a look-up view (Step S50: Yes), the facility image specifying unit 15A determines whether the position of the connected image 9 in the structure image 5A is a specific position (Step S50). S51). In step S51, when the connected image 9 is an image included in the region image 6A in the structure image 5A, the facility image specifying unit 15A determines that the position of the connected image 9 is a specific position.

  When determining that the position of the connected image 9 is the specific position (step S51: Yes), the equipment image specifying unit 15A rotates the connected image 9 by 180 degrees and specifies the connected image 9 rotated by 180 degrees as the equipment image. (Step S52). If it is determined that the structure image is not a look-up view (Step S50: No), the equipment image specifying unit 15A determines whether the position of the connected image 9 in the structure image 5A 'is a specific position (Step S50). Step S53). In step S53, if the position of the connected image 9 in the structure image 5A 'is an image included in the region image 6B', the facility image specifying unit 15A determines that the position of the connected image 9 is the specific position.

  When determining that the position of the connected image 9 is the specific position (Step S53: Yes), the equipment image specifying unit 15A turns the connected image 9 upside down and specifies the connected image 9 that has been turned upside down as the equipment image ( Step S54). When determining that the position of the connected image 9 is not the specific position (step S53: No), the facility image specifying unit 15A reverses the connected image 9 from side to side, and specifies the connected image 9 that has been inverted from side to side as the facility image. (Step S55).

  The facility image specifying unit 15A ends the processing of step S52, determines that the position of the connected image 9 is not the specific position (step S51: No), ends the processing of step S54, or steps S55. When the processing of is completed, the processing illustrated in FIG. 23 ends.

  The hardware configuration of the image processing system 1A shown in FIG. 21 is the same as the hardware configuration of the image processing system 1 shown in FIG. The processor 101 can execute the function of the facility image specifying unit 15A by reading and executing the program stored in the memory 102.

  As described above, the facility image specifying unit 15A of the image processing system 1A according to the second embodiment performs at least one of the rotation processing and the inversion processing of the connected image 9 based on the position of the connected image 9 in the structural images 5A and 5A '. The connected image 9 including one process is identified as the facility image. Thereby, the abnormality determination unit 19 can accurately determine the abnormality of the equipment 4 from the equipment image specified by the equipment image specifying unit 15A.

  The configurations described in the above embodiments are merely examples of the contents of the present invention, and can be combined with other known technologies, and can be combined with other known technologies without departing from the gist of the present invention. Parts can be omitted or changed.

1,1A image processing system, 2, 2A running type measuring device, 3 tunnels, 3a inner _wall, 4,4 _{1-4 14} facilities, 5, 5A, 5A 'structure _image, 6,6 ₁ to 6 5, 6A, _{6A 1 ~6A 5, 6B, 6B} 1 ~6B 5 area _image, 7,7 _{1-7 5, 7 8,} 7 _{9, 7 12, 7 13,} 7 _{16, 7 17,} 7 20 _{to 7 24} divided images, 8,8 _{1-8 14} facilities partial image 9 connected image, 10 obtaining unit, 11 image information storage unit, 12 image dividing unit, 13 image extraction unit, 14 first learning model generation unit, 15, 15A facility image identification unit , 16 input unit, 17 specific area extraction unit, 18 equipment information storage unit, 19 abnormality determination unit, 20 second learning model generation unit, 21 equipment abnormality information storage unit, 22 display processing unit, 23 display unit, 30, 30 ₁ , _{30 2,} 30 3, 30 ₄ specific region, 31 _{1, 31 2,} 31 3, 31 ₄ specific area image, 51, 51A, 51B imaging unit.

Claims (10)

An image dividing unit that divides the image of the structure including the image of the equipment attached to the structure into a plurality of images of a smaller size than an image showing the entire equipment,
An image extraction unit that extracts a plurality of images showing a part of the facility from among the plurality of images divided by the image division unit,
Concatenating two or more images of the plurality of images extracted by the image extracting unit at positions adjacent to each other before being divided by the image dividing unit, and including the two or more coupled images An equipment image specifying unit that specifies an image as an image of the equipment. An image division unit that divides an image including an image of equipment into a plurality of images having a smaller size than an image showing the entire equipment,
An image extraction unit that extracts a plurality of images showing a part of the facility from among the plurality of images divided by the image division unit,
Concatenating two or more images of the plurality of images extracted by the image extracting unit at positions adjacent to each other before being divided by the image dividing unit, and including the two or more coupled images Equipment image specifying unit for specifying an image as the image of the equipment.
An image processing system, characterized in that: The image of the structure is
It is a developed image of the tunnel,
The process of specifying the image of the facility by the facility image specifying unit includes at least one of a rotation process and an inversion process of the connected image based on a position of the connected image in the developed image of the tunnel, Identify the connected image that has been subjected to the two processes as the image of the facility
The image processing system according to claim 1, wherein: The image extraction unit,
Having a learning model generated by machine learning using an image showing a part of the equipment, a part of the equipment using the learning model from among the plurality of images divided by the image dividing unit. The image processing system according to any one of claims 1 to 3 , wherein a plurality of images shown are extracted. The equipment image identification unit,
It is determined whether or not the size of the linked image is within a preset range, and when it is determined that the size of the linked image is within the preset range, the linked image is displayed as an image of the facility. The image processing system according to any one of claims 1 to 4, wherein: The equipment image identification unit,
Among the plurality of images divided by the image dividing unit, the plurality of images and the two images whose positions before being divided by the image dividing unit are located at positions adjacent to at least one of the two or more images. The image processing system according to any one of claims 1 to 5 , wherein the image is connected to the image to generate the connected image. A specific region extraction unit that extracts an image of a specific region in the connected image,
The image processing system according to any one of claims 1 to 6, characterized in that it comprises an abnormality determination unit determining abnormality of the equipment from the image extracted by the specified area extracting portion. The abnormality determination unit includes:
A learning model for abnormality determination generated by machine learning using an image of the component in a state where the component of the facility is abnormal, and an image extracted by the specific area extracting unit is used for learning for the abnormality determination. The image processing system according to claim 7 , wherein the abnormality of the facility is determined based on a result obtained by inputting to the model. An image processing method performed by a computer,
An image dividing step of dividing the image of the structure including the image of the equipment attached to the structure into a plurality of images of a smaller size than an image showing the entire equipment,
Image extraction step of extracting a plurality of images showing a part of the equipment from among the plurality of images divided by the image division step,
Concatenating two or more images, of the plurality of images extracted in the image extraction step, whose positions before division by the image division step are adjacent to each other, and including the coupled two or more images Equipment image identification step of identifying an image as an image of the equipment,
An image processing method comprising: An image processing method performed by a computer,
  An image division step of dividing an image including an image of a facility into a plurality of images having a smaller size than an image showing the entire facility,
Image extraction step of extracting a plurality of images showing a part of the equipment from among the plurality of images divided by the image division step,
Concatenating two or more images, of the plurality of images extracted in the image extraction step, whose positions before division by the image division step are adjacent to each other, and including the coupled two or more images Equipment image identification step of identifying an image as an image of the equipment,
including
An image processing method comprising:

Images