Deterioration determination device, deterioration determination method, and program

The device corrects images to enhance target area extraction and deteriorated area detection, addressing inaccuracies in existing methods and enabling precise deterioration assessment.

JP7583331B2Active Publication Date: 2024-11-14NIPPON TELEGRAPH & TELEPHONE CORP
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
JP2023525331
Authority / Receiving Office
JP · JP
Patent Type
Patents
Current Assignee / Owner
Filing Date
2021-06-04
Publication Date
2024-11-14
Estimated Expiration
2041-06-04

AI Technical Summary

Technical Problem

Existing image processing methods using deep learning, such as Mask-R-CNN, struggle to accurately extract target regions from images where the inspection object extends obliquely, leading to inaccurate determination of the degree of deterioration.

Method used

A deterioration determination device and method that corrects images using geometric transformations to increase the aspect ratio of the target region, allowing for precise extraction of the target area and detection of deteriorated areas through deep learning techniques.

Benefits of technology

Enables accurate determination of the degree of deterioration by enhancing the extraction of target and deteriorated areas, facilitating timely maintenance of inspection objects.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 0007583331000001
    Figure 0007583331000001
  • Figure 0007583331000002
    Figure 0007583331000002
  • Figure 0007583331000003
    Figure 0007583331000003
Patent Text Reader

Abstract

A deterioration determination device (2) according to the present disclosure comprises: an input unit (21) which receives an input of image data indicating an image including an image of an object to be inspected; a correction unit (232) which generates a corrected image obtained by correcting the image such that the aspect ratio of the area surrounding an image of at least a part of the object to be inspected, included in the image, is increased; a target area extracting unit (252) which extracts, from the corrected image, a target area indicating an image of the object to be inspected included in the corrected image; a deteriorated area detection unit (253) which detects, from the corrected image, a deteriorated area indicating an image of a deteriorated part of the object to be inspected; and a determination unit (254) which determines the deterioration degree of the object to be inspected, on the basis of the target area and the deteriorated area.
Need to check novelty before this filing date? Find Prior Art

Description

[Technical field]

[0001] The present disclosure relates to a deterioration determination device, a deterioration determination method, and a program for determining a degree of deterioration of an inspection object. [Background technology]

[0002] It is known that an area showing an image of an inspection object (hereinafter referred to as a "target area") is extracted from an image using image processing using deep learning such as Mask-R-CNN (Convolutional Neural Network). When the image of the inspection object extends obliquely with respect to the periphery that defines the entire image, the above-mentioned image processing using deep learning may extract an area including the entire image, or the inspection object and part of the background. In other words, there has been a problem that the target area cannot be extracted with high accuracy, and as a result, the deterioration degree of the inspection object cannot be calculated with high accuracy.

[0003] Orthorectification is known as a technique for changing the orientation of an image contained in an image (Non-Patent Document 1). In orthorectification, the image of an object shown at any position in the image is corrected so that the front of the object is captured facing the imaging element. Therefore, in an orthorectified image, the position and size of the object whose image is included in the image are accurately shown. [Prior art documents] [Non-patent literature]

[0004] [Non-Patent Document 1] "What are "orthoimages" created by drone surveying? | JDRONE", [online], [searched May 21, 2021], Internet<URL:https: / / jdrone.tokyo / ortho-commentary / > Summary of the Invention [Problem to be solved by the invention]

[0005] However, in orthorectification, it is necessary to obtain multiple images with overlapping areas within an imaging range that includes the object. Therefore, in an image that does not have overlapping areas, it may not be possible to perform orthorectification so that the target area can be appropriately extracted. For this reason, there remains a problem that the deterioration level of the inspection target cannot be determined with high accuracy.

[0006] In consideration of the above circumstances, an object of the present disclosure is to provide a deterioration determination device, a deterioration determination method, and a program that can determine the degree of deterioration of an inspection object with high accuracy. [Means for solving the problem]

[0007] In order to solve the above problems, the deterioration determination device of the present disclosure comprises an input unit that accepts input of image data indicating an image including an image of an inspection object, a correction unit that generates a corrected image by correcting the image so that the aspect ratio of an area surrounding at least a portion of the image of the inspection object contained in the image is increased, a target area extraction unit that extracts from the corrected image a target area indicating the image of the inspection object contained in the corrected image, a deteriorated area detection unit that detects from the corrected image a deteriorated area indicating an image of a deteriorated portion of the inspection object, and a determination unit that determines the degree of deterioration of the inspection object based on the target area and the deteriorated area.

[0008] In addition, in order to solve the above problem, the deterioration determination method disclosed herein includes the steps of accepting input of image data indicating an image including an image of an object to be inspected, generating a corrected image by correcting the image so that the aspect ratio of an area surrounding at least a portion of the image of the object to be inspected contained in the image is increased, extracting from the corrected image a target area indicating the image of the object to be inspected contained in the corrected image, detecting from the corrected image a deteriorated area indicating an image of a deteriorated portion of the object to be inspected, and determining the degree of deterioration of the object to be inspected based on the target area and the deteriorated area.

[0009] In order to solve the above problem, a program according to the present disclosure causes a computer to function as the above-mentioned deterioration determination device. Effect of the Invention

[0010] According to the deterioration determination device, deterioration determination method, and program disclosed herein, the degree of deterioration of an inspection object can be determined with high accuracy. [Brief description of the drawings]

[0011] [Figure 1] 1 is a schematic diagram of a deterioration determination system according to an embodiment of the present disclosure. [Figure 2A] FIG. 2 is a diagram showing an example of an image represented by image data. [Figure 2B] 2B is a diagram showing an example of a corrected image generated by correcting the image shown in FIG. 2A. FIG. [Figure 2C] FIG. 2C is a diagram showing an example of a target region extracted from the corrected image shown in FIG. 2B. [Figure 3A] FIG. 13 is a diagram showing another example of a corrected image. [Figure 3B] FIG. 3B is a diagram showing an example of a target region extracted from the corrected image shown in FIG. 3A. [Figure 3C] 3B is a diagram showing an example of a degraded region detected from the image of the object shown in FIG. 3A. FIG. [Figure 4] 2 is a diagram for explaining the determination of the deterioration degree by a determining unit shown in FIG. 1. FIG. [Diagram 5] FIG. 11 is a diagram showing an example of display data. [Figure 6] 5 is a flowchart illustrating an example of an operation of the deterioration determination device according to an embodiment. [Figure 7] FIG. 2 is a hardware block diagram of the deterioration determination device. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0012] The overall configuration of this embodiment will be described with reference to Fig. 1. Fig. 1 is a schematic diagram of a deterioration determination system 100 according to this embodiment.

[0013] 1, a deterioration determination system 100 according to this embodiment includes an image capture device 1 and a deterioration determination device 2. The image capture device 1 and the deterioration determination device 2 communicate with each other via a communication network.

[0014] <Configuration of imaging device> The imaging device 1 includes an imaging unit 11 and an output unit 12. The imaging unit 11 is configured by a camera having an optical element, an imaging element, and the like. The camera may be a telephoto camera, or may be a camera such as a photographic device mounted on a UAV (unmanned aerial vehicle). The output unit 12 may be configured by an output interface for outputting information, or may be configured by a communication interface for communicating with other devices such as external devices. For the communication interface, standards such as Ethernet (registered trademark), FDDI (Fiber Distributed Data Interface), and Wi-Fi (registered trademark) may be used.

[0015] The imaging unit 11 captures an object to be inspected and generates an image including an image of the object to be inspected. The object to be inspected is an object such as equipment to be inspected, and may be a bridge, a bridge-attached member, a pipeline (bridge-attached pipeline), a pipeline-attached member, etc. The image may be an image expressed by three colors, R (Red), G (Green), and B (Blue).

[0016] The output unit 12 transmits image data indicating the image generated by the imaging unit 11 to the deterioration determination device 2 via a communication network. As described above, when the image generated by the imaging unit 11 is an image expressed by three colors, R, G, and B, the image data can be data indicating the RGB values ​​of each pixel.

[0017] <Configuration of the Deterioration Determination Device> The deterioration determination device 2 may be a terminal device such as a personal computer (PC) or a tablet, or may be a computer device integrated with the above-mentioned imaging device 1. The deterioration determination device 2 includes an input unit 21, a data storage unit 22, a processing unit 23, a correction data storage unit 24, an inspection unit 25, and an output unit 26. The input unit 21 may be configured by an input interface that accepts input of information, or may be configured by a communication interface that receives information. The data storage unit 22 and the correction data storage unit 24 are configured by memories such as a hard disk drive (HDD), a solid state drive (SSD), an electrically erasable programmable read-only memory (EEPROM), a read-only memory (ROM), and a random access memory (RAM). The processing unit 23 and the inspection unit 25 constitute a control unit (controller). The control unit may be configured by dedicated hardware such as an application specific integrated circuit (ASIC) or a field programmable gate array (FPGA), may be configured by a processor, or may be configured including both. The output unit 26 may be configured by an output interface that outputs information, or may be configured by a communication interface that transmits information.

[0018] The input unit 21 accepts input of image data showing an image generated by capturing an image of an inspection target by the imaging device 1. The input unit 21 may accept input of image data showing an image including images I1 and I2 of two pipelines, which are multiple inspection targets, as shown in Fig. 2A, for example.

[0019] The data storage unit 22 stores image data whose input is accepted by the input unit 21. The data storage unit 22 can store image data in a directory, which is a virtual data storage area provided in the data storage unit 22, for example.

[0020] The processing unit 23 processes image data. The processing unit 23 includes a reading unit 231 and a correction unit 232. The processing unit 23 may further include a functional unit that performs any data processing such as changing the image size, changing the bit size, and color space decomposition.

[0021] The reading unit 231 reads out the image data stored by the data storage unit 22. At this time, the reading unit 231 can assign an identifier to the read image data for uniquely identifying the image data. The identifier can be, for example, a number. The identifier can also be a number incremented by a predetermined value in the order in which the image data is input. The predetermined value can be 1. In particular, when the image input by the input unit 21 is a moving image composed of a plurality of still images, the reading unit 231 assigns an identifier to each piece of image data indicating the still images constituting the moving image. This makes it possible to associate the results of processing by each functional unit described later with the image data even when the input of a plurality of image data is accepted. In the following, a still image is simply referred to as an "image".

[0022] When the reading unit 231 reads out the image data stored by the data storage unit 22, the reading unit 231 may determine the format of the image data, specifically, the extension of the image data. Specifically, when each functional unit described below is configured to process image data of a predetermined format, that is, image data having a predetermined extension, the reading unit 231 determines whether the format of the image data is the predetermined format. Then, when the reading unit 231 determines that the format of the image data is not the predetermined format, it converts the format of the image data to the predetermined format. Also, when the reading unit 231 determines that the format of the image data is the predetermined format, it does not convert the format of the image data. Specifically, the reading unit 231 determines whether the extension of the image data is the predetermined extension. Then, when the reading unit 231 determines that the extension of the image data is not the predetermined extension, it converts the extension of the image data to the predetermined extension. Also, when the reading unit 231 determines that the extension of the image data is the predetermined extension, it does not convert the extension of the image data.

[0023] The correction unit 232 generates a corrected image by correcting the image so that the aspect ratio of the area surrounding at least a part of the image of the inspection object included in the image represented by the image data is increased. The predetermined area can be a bounding box. This reduces the inclusion of subjects such as the background other than the inspection object within the bounding box. This increases the accuracy of the extraction of the target area by the target area extraction unit 251, which will be described in detail later.

[0024] Specifically, the correction unit 232 generates a corrected image by geometrically transforming an image including an image of an inspection object. The geometric transformation by the correction unit 232 can be an affine transformation, a projective transformation, or the like.

[0025] For example, first, the correction unit 232 sets four points that are vertices of a rectangular area including the image of the inspection object as shown in Fig. 2A. In Fig. 2A, the coordinates of the four points are represented as P1 (x1, y1), P2 (x2, y2), P3 (x3, y3), and P4 (x4, y4), respectively.

[0026] Then, the correction unit 232 converts the angle of the direction in which the inspection object extends with respect to the predetermined direction by projective transformation using the set four points. As a result, the correction unit 232 generates a corrected image in which the image of the inspection object is corrected to an image along the sides of the bounding box. In this example, the correction unit 232 generates a corrected image by converting an area surrounded by a rectangle having vertices P1 (x1, y1), P2 (x2, y2), P3 (x3, y3), and P4 (x4, y4) shown in FIG. 2A into an area surrounded by a rectangle having vertices P1' (x1', y1'), P2' (x2', y2'), P3' (x3', y3'), and P4' (x4', y4'), respectively. In this way, the correction unit 232 generates a corrected image in which the images I1 and I2 of the pipeline, which is the inspection object shown in Fig. 2A, are corrected to the images I1' and I2' of the pipeline shown in Fig. 2B. In this example, the region (bounding box B) including the inspection object as shown in Fig. 2A is converted to the region (bounding box B') including the inspection object as shown in Fig. 2B, and thus the aspect ratio of the region including the inspection object is increased.

[0027] The correction unit 232 generates a corrected image by correcting an image by using projective transformation, but is not limited to this, and the correction unit 232 may correct an image by using affine transformation. However, when the correction unit 232 corrects an image by using affine transformation, mapping by using projective transformation cannot be performed. Therefore, by using projective transformation, the correction unit 231 can correct an image with a higher degree of freedom than when using affine transformation.

[0028] In addition, in a configuration in which the correction unit 232 generates a corrected image corrected using projective transformation, the correction unit 232 may determine whether or not it is possible to select four points that are vertices of a quadrangular area including the image of the inspection object. For example, if the inspection object extends in a direction facing the imaging surface of the imaging device 1, the target area may not form a quadrangle. In such a case, the correction unit 232 cannot select four points and does not perform the above-mentioned correction. Accordingly, the processing in each functional unit described later is not performed.

[0029] Furthermore, the correction unit 232 may assign an identifier to the corrected image data indicating the corrected image. The identifier assigned to the corrected image data may be the same as the identifier assigned to the image data before correction, or may be a different identifier that can be recognized as being related to the identifier assigned to the image data before correction.

[0030] The correction data storage unit 24 stores the correction image data indicating the corrected image generated by the correction unit 232 correcting the image. The correction data storage unit 24 stores the correction image data in a predetermined directory. The directory in which the correction data storage unit 24 stores the correction data may be the same as the directory used by the processing unit 23, or may be different.

[0031] The inspection unit 25 judges the deterioration degree of the inspection object indicated by the image included in the corrected image based on the corrected image indicated by the corrected image data. The inspection unit 25 includes a readout unit 251, an object area extraction unit 252, a deteriorated area detection unit 253, a judgment unit 254, and a display data generation unit 255.

[0032] The reading unit 251 reads out the corrected image data stored in the correction data storage unit 24. Specifically, the reading unit 251 reads out the corrected image data indicating the corrected image corrected by the correction unit 232 from a predetermined directory in the correction data storage unit 24.

[0033] The target area extraction unit 252 extracts a target area showing an image of an inspection object from the corrected image shown by the corrected image data. For example, the target area extraction unit 252 detects an image of an inspection object from the corrected image by using class-based segmentation by instance segmentation (e.g., Mask-R-CNN), which is a deep learning method. In such a configuration, the target area extraction unit 252 can detect images of a plurality of inspection objects included in the corrected image by distinguishing them from each other. In the example shown in FIG. 2B and FIG. 2C, the target area extraction unit 252 extracts target areas R1 and R2 shown in the solid-line rectangle in FIG. 2C, which are areas including images I1 and I2 of two pipes, respectively, from the image shown by the corrected image data shown in FIG. 2B.

[0034] In addition, when the inspection object is three pipelines and an attachment member that supports the three pipelines, the corrected image represented by the corrected image data includes images I1, I2, and I3 of the three pipelines and an image I4 of the attachment member, as shown in Fig. 3A. In such an example, the object region extraction unit 252 extracts an object region R, which is an area showing the images I1, I2, I3, and I4, as shown in Fig. 3B. 1A , R 2A , R 3A , and R 4A Extract.

[0035] The degraded area detection unit 253 detects a degraded area indicating an image of a degraded part in the inspection object from the corrected image indicated by the corrected image data. The degraded area detection unit 253 can detect the degraded area using deep learning techniques such as bounding box, class classification, segmentation, etc. The degraded area detection unit 253 can detect degradation for each pixel by using segmentation. For example, the degraded area detection unit 253 detects a target area R as shown in FIG. 3B. 1A , R 2A , R 3A , and R 4A From this, the degradation region R 1B , R 2B , R 3B , and R 4B Extract.

[0036] The determination unit 254 determines the degree of deterioration of the inspection object based on the target area and the deteriorated area in the corrected image indicated by the corrected image data.

[0037] First, the determination unit 254 calculates the area of ​​the target region. When multiple target regions are extracted, the determination unit 254 may calculate the area of ​​each target region individually. When calculating the area of ​​the target region, the determination unit 254 may calculate the area by counting the number of pixels that constitute the image of the inspection object.

[0038] Furthermore, the determination unit 254 calculates the area of ​​the degraded region. As described above, in a configuration in which the degraded region detection unit 253 detects, for each pixel, degradation of a portion of an object whose image is represented by that pixel using segmentation, the determination unit 254 may calculate the area of ​​the degraded region by counting the number of pixels in which degradation is detected. In this case, the determination unit 254 can efficiently calculate the area of ​​the degraded region by using the degraded pixels detected by the degraded region detection unit 253.

[0039] The determination unit 254 then determines the ratio of the area of ​​the deteriorated area to the area of ​​the target area as the deterioration degree of the inspection object. At this time, the determination unit 254 may determine the ratio of the number of pixels constituting the deteriorated area to the number of pixels constituting the target area as the deterioration degree.

[0040] As an example, as shown in FIG. 4, the determination unit 254 determines whether the target region R iA (i = 1 to N (N is the number of objects to be inspected)) and the deterioration region R B By calculating the logical product with iB That is, the determination unit 254 calculates the number of pixels Yi in the target region R iA and the pixel that constitutes the degraded region R B The number of pixels Yi constituting the degraded region R iB Then, calculate the number of pixels Yi that make up the target region R iA The number of pixels Xi in the degraded region RiB The ratio Yi / Xi of the number of pixels Yi is determined as the degree of degradation.

[0041] The display data generating unit 255 generates display data indicating the degree of deterioration judged by the judging unit 254. The display data generating unit 255 may generate display data including a corrected image and the degree of deterioration of an inspection object corresponding to an image included in the corrected image. The display data generating unit 255 may generate display data indicating a processed image in which a process is performed to indicate a deteriorated area on the corrected image indicated by the corrected image data, and the degree of deterioration of each inspection object whose image is included in the processed image, as shown in FIG. 5. The display data generating unit 255 may perform a process to indicate a deteriorated area on the corrected image based on the degree of deterioration, in addition to indicating the degree of deterioration as in the example shown in FIG. 5, or instead of indicating the degree of deterioration. As an example, the display data generating unit 255 may indicate a deteriorated area with a degree of deterioration less than 10% in blue, indicate a deteriorated area with a degree of deterioration between 10% and 30% in yellow, and indicate a deteriorated area with a degree of deterioration 30% or more in red. Although the colors shown in the deteriorated areas according to the deterioration level are not limited to these, it is preferable to show the deteriorated areas in colors that are more likely to attract the attention of the inspector as the deterioration level increases. This allows the inspector to immediately recognize the inspection object that includes the deteriorated area with a high deterioration level, and to promptly carry out maintenance on the inspection object.

[0042] As described above, the correction unit 232 may assign an identifier to the corrected image data indicating the corrected image. In such a configuration, when the determination unit 254 determines a plurality of degradation levels for each of the corrected images indicated by the plurality of corrected image data, the correction unit 232 assigns an identifier to each of the plurality of corrected image data. This allows the display data generation unit 255 to associate each of the plurality of degradation levels with the corrected image data using the identifier. Therefore, the display data generation unit 255 may generate display data including the corrected image and the degradation level of the inspection object corresponding to the image included in the corrected image for each of the plurality of corrected image data using the identifier.

[0043] The output unit 26 outputs the display data generated by the display data generation unit 255. Specifically, the output unit 26 may output the display data to a display interface such as a liquid crystal panel, an organic EL display, etc. The output unit 26 may also output the display data to another device via a communication network, for example.

[0044] <Operation of the deterioration determination device> Here, the operation of the deterioration determination device 2 according to this embodiment will be described with reference to Fig. 6. Fig. 6 is a flowchart showing an example of the operation in the deterioration determination device 2 according to this embodiment. The operation in the deterioration determination device 2 described with reference to Fig. 6 corresponds to a congestion information processing method of the deterioration determination device 2 according to this embodiment.

[0045] In step S1, the input unit 21 accepts input of image data representing an image captured by the imaging device 1.

[0046] In step S2, the data storage unit 22 stores the image data.

[0047] In step S3, the correction unit 232 generates a corrected image by correcting the image so that the aspect ratio of the area surrounding at least a part of the image of the inspection object included in the image indicated by the image data is increased. At this time, the correction unit 232 generates a corrected image by correcting the image indicated by the image data read by the reading unit 231 from the data storage unit 22. In addition, the reading unit 231 may assign an identifier for uniquely identifying the read image data when reading the image data. In addition, the reading unit 231 may determine whether the format of the image data is a predetermined format. Then, when it is determined that the format of the image data is not the predetermined format, the reading unit 231 converts the format of the image data to the predetermined format. In addition, when it is determined that the format of the image data is not the predetermined format, the reading unit 231 does not convert the format of the image data, and in this case, the correction unit 232 does not need to generate a corrected image.

[0048] In step S4, the correction data storage unit 24 stores the corrected image data representing the corrected image generated by the correction unit 232.

[0049] In step S5, the target area extraction unit 252 extracts a target area indicating an image of the inspection target from the corrected image indicated by the corrected image data. At this time, the target area extraction unit 252 can extract the target area from the corrected image indicated by the corrected image data stored in the corrected data storage unit 24 and read by the reading unit 251.

[0050] In step S6, the deteriorated area detection unit 253 detects a deteriorated area indicating an image of a deteriorated part in the inspection object from the corrected image indicated by the corrected image data. At this time, the object area extraction unit 252 can detect the image of the inspection object from the corrected image indicated by the corrected image data stored in the correction data storage unit 24 and read by the reading unit 251.

[0051] In step S7, the determination unit 254 determines the degree of deterioration of the inspection object based on the target area and the deteriorated area in the corrected image indicated by the corrected image data.

[0052] In step S8, the display data generating unit 255 generates display data indicating the degree of deterioration determined by the determining unit 254. At this time, the display data generating unit 255 may use the identifier to generate display data including the corrected image and the degree of deterioration of the inspection object corresponding to the image included in the corrected image.

[0053] In step S9, the output unit 26 outputs the display data.

[0054] As described above, according to this embodiment, the deterioration determination device 2 generates a corrected image by correcting the image so that the aspect ratio of the area surrounding at least a part of the image of the inspection object included in the image is increased. Then, the deterioration determination device 2 extracts a target area showing the image of the inspection object included in the corrected image from the corrected image, and detects a deteriorated area showing an image of a deteriorated part of the inspection object from the corrected image. Then, the deterioration determination device 2 determines the deterioration degree of the inspection object based on the target area and the deteriorated area. Thereby, the deterioration determination device 2 can detect the target area with high accuracy. Therefore, the deteriorated area in the target area can be detected with high accuracy, and further, the deterioration degree based on the target area and the deteriorated area can be detected with high accuracy. Therefore, an inspector who inspects the inspection object can appropriately recognize the deterioration degree of the inspection object, and can appropriately maintain the inspection object based on the deterioration degree.

[0055] Furthermore, the deterioration determination device 2 may determine the ratio of the number of pixels constituting the deteriorated region to the number of pixels constituting the target region as the deterioration degree. In this way, in a configuration in which the deterioration determination device 2 detects deterioration of a portion of an object represented by each pixel using segmentation, the deterioration determination device 2 can calculate the area of ​​the deteriorated region by counting the number of pixels in which deterioration is detected. Therefore, the deterioration determination device 2 can efficiently calculate the area of ​​the deteriorated region, and therefore the deterioration degree.

[0056] Furthermore, the deterioration determination device 2 may assign an identifier to each corrected image data showing the corrected image, and use the identifier to generate display data including the corrected image and the deterioration level of the inspection object corresponding to the image included in the corrected image. This allows an inspector of the inspection object who refers to the display data to recognize which of the image data whose input has been accepted corresponds to the deterioration level included in the display data. Therefore, the inspector can recognize the inspection object whose image shown by the image data includes an image, and can perform appropriate maintenance according to the deterioration level.

[0057] <Program> The above-mentioned deterioration determination device 2 can be realized by a computer 101. A program for functioning as the deterioration determination device 2 may be provided. The program may be stored in a storage medium or provided through a network. FIG. 7 is a block diagram showing a schematic configuration of a computer 101 functioning as each of the control devices 3 and 3-1. Here, the computer 101 may be a general-purpose computer, a dedicated computer, a workstation, a PC (Personal Computer), an electronic notepad, or the like. The program instructions may be program code, code segments, or the like for performing necessary tasks.

[0058] 7, the computer 101 includes a processor 110, a read only memory (ROM) 120, a random access memory (RAM) 130, a storage 140, a reading unit 150, an output unit 160, and a communication interface (I / F) 170. Each component is connected to each other so as to be able to communicate with each other via a bus 180. The processor 110 is specifically a central processing unit (CPU), a micro processing unit (MPU), a graphics processing unit (GPU), a digital signal processor (DSP), a system on a chip (SoC), or the like, and may be composed of multiple processors of the same type or different types.

[0059] The processor 110 controls each component and executes various arithmetic processing. That is, the processor 110 reads a program from the ROM 120 or the storage 140, and executes the program using the RAM 130 as a working area. The processor 110 controls each component and executes various arithmetic processing according to the program stored in the ROM 120 or the storage 140. In this embodiment, the program according to the present disclosure is stored in the ROM 120 or the storage 140.

[0060] The program may be stored in a storage medium readable by the computer 101. By using such a storage medium, the program can be installed in the computer 101. Here, the storage medium in which the program is stored may be a non-transitory storage medium. The non-transitory storage medium is not particularly limited, and may be, for example, a CD-ROM, a DVD-ROM, or a USB (Universal Serial Bus) memory. In addition, the program may be in a form that is downloaded from an external device via a network.

[0061] The ROM 120 stores various programs and various data. The RAM 130 temporarily stores programs or data as a working area. The storage 140 is configured with a hard disk drive (HDD) or a solid state drive (SSD), and stores various programs including an operating system and various data.

[0062] The reading unit 150 includes one or more input interfaces that receive an input operation from a user and acquire information based on the user's operation. For example, the reading unit 150 is a pointing device, a keyboard, a mouse, etc., but is not limited to these.

[0063] The output unit 160 includes one or more output interfaces that output information. For example, the output unit 160 is a display that outputs information as a video or a speaker that outputs information as a sound, but is not limited to these. Note that, if the output unit 160 is a touch panel type display, it also functions as the readout unit 150.

[0064] The communication interface 170 is an interface for communicating with an external device.

[0065] The following supplementary notes are further disclosed regarding the above embodiment.

[0066] (Additional note 1) an input interface that accepts input of image data showing an image including an image of an inspection target; A control unit. The control unit is generating a corrected image by correcting the image so that an aspect ratio of an area surrounding an image of at least a part of the inspection object included in the image is increased; Extracting an object region from the corrected image, the object region indicating an image of the object to be inspected included in the corrected image; detecting a deteriorated area from the corrected image, the deteriorated area being indicative of an image of a deteriorated portion of the inspection object; A deterioration determination device that determines a degree of deterioration of the inspection object based on the target area and the deteriorated area. (Additional note 2) 2. The deterioration determination device according to claim 1, wherein the control unit determines the ratio of the area of ​​the deteriorated area to the area of ​​the target area as the deterioration degree of the inspection object. (Additional note 3) 3. The degradation determination device according to claim 2, wherein the control unit determines a ratio of the number of pixels constituting the degraded region to the number of pixels constituting the target region as a degradation degree. (Additional note 4) 4. The deterioration determination device according to claim 1, wherein the control unit generates display data including the corrected image and the deterioration degree. (Additional note 5) The control unit is assigning an identifier to each of the corrected image data representing the corrected image; 5. The deterioration determination device according to claim 4, which uses the identifier to generate display data including the corrected image and a deterioration level of an inspection object corresponding to an image included in the corrected image. (Additional note 6) Receiving input of image data indicative of an image including an image of an inspection object; generating a corrected image by correcting the image so that an aspect ratio of an area surrounding an image of at least a part of an object to be inspected included in the image is increased; extracting an object area from the corrected image, the object area indicating an image of the object to be inspected included in the corrected image; detecting a deteriorated area from the corrected image, the deteriorated area being indicative of an image of a deteriorated portion of the inspection object; and determining a degree of deterioration of the inspection object based on the target area and the deteriorated area. (Additional note 7) A non-transitory storage medium storing a program executable by a computer, the non-transitory storage medium storing the program causing the computer to function as the deterioration determination device described in any one of appended claims 1 to 5.

[0067] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, and standard was specifically and individually indicated to be incorporated by reference.

[0068] Although the above-mentioned embodiment has been described as a representative example, it is obvious to those skilled in the art that many modifications and substitutions can be made within the spirit and scope of the present disclosure. Therefore, the present invention should not be interpreted as being limited by the above-mentioned embodiment, and various modifications or changes can be made without departing from the scope of the claims. For example, it is possible to combine multiple building blocks shown in the configuration diagram of the embodiment into one, or to divide one building block. [Explanation of symbols]

[0069] 1. Imaging device 2 Deterioration determination device 11 Imaging unit 12 Output section 21 Input section 22 Data storage unit 23 Processing Department 24 Correction data storage section 25 Inspection Department 26 Output section 100 Deterioration Judgment System 101 Computer 110 Processor 120 ROM 130 RAM 140 Storage 150 Reading section 160 Output section 170 Communication Interface 180 Bus 231 Reading section 232 Correction section 251 Reading section 252 Target Region Extraction Unit 253 Degraded Area Detection Unit 254 Judgment section 255 Display data generator

Claims

1. An input unit that accepts input of image data indicating an image including an image of an inspection target; a correction unit that generates a corrected image by correcting the image so that the aspect ratio of a region surrounding the image of the inspection object is increased; an object region extraction unit that extracts an object region indicating an image of the inspection object included in the corrected image from the corrected image; a deteriorated area detection unit that detects a deteriorated area indicating an image of a deteriorated portion of the inspection object from the corrected image; A deterioration determination device comprising: a determination unit that determines a deterioration level of the inspection object based on the target area and the deteriorated area.

2. A deterioration determination device as described in claim 1, wherein the object to be inspected includes either an object to be attached or an attachment member for attaching another object to the object, or both.

3. A deterioration determination device as described in claim 1 or 2, wherein the correction unit generates the corrected image by correcting the image using projective transformation.

4. The deterioration determination device according to claim 1 , wherein the determination unit determines a ratio of an area of ​​the deteriorated region to an area of ​​the target region as the deterioration level of the inspection object.

5. The deterioration determining device according to claim 1 , further comprising a display data generating unit that generates display data including the corrected image and the deterioration degree.

6. Receiving input of image data indicative of an image including an image of an inspection object; generating a corrected image by correcting the image so that the aspect ratio of an area surrounding the image of the inspection object is increased; extracting an object area from the corrected image, the object area indicating an image of the object to be inspected included in the corrected image; detecting a deteriorated area from the corrected image, the deteriorated area being indicative of an image of a deteriorated portion of the inspection object; and determining a degree of deterioration of the inspection object based on the target area and the deteriorated area.

7. A program for causing a computer to function as the deterioration determination device according to any one of claims 1 to 5.

Citation Information

Patent Citations

  • Deterioration diagnostic system and deterioration diagnostic method

    JP2016223815A

  • Image processing device and image processing method

    JP2020197797A

  • Degraded state detector and degraded state detection method

    JP2021032650A

  • JPP6737371B

  • Reinforcing bar determination device and reinforcing bar determination method

    WO2021024499A1