Defect detection device, defect detection method, and program

Abstract

To accurately identify the components used in the equipment being inspected. [Solution] The defect detection device comprises: an image acquisition unit that acquires an image of the equipment to be inspected; an equipment identification unit that identifies the equipment as it appears in the acquired image; a parts information acquisition unit that acquires parts information relating to the parts used in the equipment by searching for correspondence information that associates the equipment identification information with the parts used in the equipment, based on the identification information identified by the equipment identification unit; and a defect detection unit that detects whether or not the parts used in the equipment as they appear in the image are defective, based on the acquired image and the acquired parts information.

Description

Technical Field

[0001] The present invention relates to a defect detection device, a defect detection method, and a program. Background Art

[0002] Conventionally, for inspection objects such as structures like steel towers, the state of the inspection object has been determined based on image information captured using an imaging device. It is not easy to capture images of every corner of an entire large structure such as a steel tower, and in recent years, imaging using an aircraft such as a drone has been performed. For example, Patent Document 1 describes inspecting a structure such as a steel tower using a drone. Prior Art Documents Patent Documents

[0003] Patent Document 1 Japanese Unexamined Patent Application Publication No. 2019-196980 Summary of the Invention Problems to be Solved by the Invention

[0004] When the technology described in Patent Document 1 is used, it is possible to determine that defects such as cracks or loosening have occurred in components such as bolts and nuts used in a steel tower, based on images captured using a drone. However, depending on the components used in the steel tower, it is assumed that misjudgment may occur depending on the defect state. For example, in a case where a double nut is used and one of the nuts is in a cracked defective state, the remaining single nut may cause image determination to judge it as a single nut (not in a defective state). That is, when the conventional technology is used, there has been a problem that it is not possible to accurately determine components used in equipment to be inspected.

[0005] This invention has been made in consideration of these circumstances, and its purpose is to provide a defect detection device, a defect detection method, and a program that can accurately determine the quality of parts used in equipment to be inspected. [Means for solving the problem]

[0006] (1) One aspect of the present invention is a defect detection device comprising: an image acquisition unit that acquires an image of equipment to be inspected; an equipment identification unit that identifies the equipment as depicted in the acquired image; a parts information acquisition unit that acquires parts information relating to parts used in the equipment by searching for correspondence information which associates the equipment identification information with information relating to parts used in the equipment, based on the identification information identified by the equipment identification unit; and a defect detection unit that detects whether or not the parts used in the equipment depicted in the image are defective, based on the acquired image and the acquired parts information. (2) In addition, in one aspect of the present invention, the defect detection device described in (1) above comprises an estimation unit that estimates the state of the parts used in the equipment as captured in the acquired image, and a determination unit that determines whether or not the parts used in the equipment are defective based on the state of the parts estimated by the estimation unit and the parts information acquired by the parts information acquisition unit. (3) In addition, one aspect of the present invention is the defect detection device described in (1) above, wherein the defect detection unit comprises an estimation unit that estimates the state of the parts used in the equipment based on the image acquired by the image acquisition unit and the parts information acquired by the parts information acquisition unit, and a determination unit that determines whether or not the parts used in the equipment are defective based on the state of the parts estimated by the estimation unit. (4) In addition, in one aspect of the present invention, in any of the defect detection devices described in (1) to (3) above, the equipment identification unit identifies the equipment based on the results of image processing of the acquired image. (5) In addition, in one aspect of the present invention, in any of the defect detection devices described in (1) to (4) above, the parts used in the equipment have different colors depending on the type of part, the part information includes correspondence information between the type of part and the color, and the defect detection unit detects whether or not the part is defective based on the color of the part used in the equipment captured in the acquired image and the part information. (6) In addition, in one aspect of the present invention, in any of the defect detection devices described in (1) to (5) above, the defect detection unit detects that a part is defective if the part used in the equipment that is captured in the acquired image is not present in the acquired part information. (7) In another aspect of the present invention, in the defect detection device described in (6) above, the parts used in the equipment that are captured in the acquired image are parts that are identified by estimation based on the results of image processing of the image. (8) In addition, one aspect of the present invention further comprises an output unit that outputs information about the correct part if the part used in the equipment that is captured in the acquired image is not present in the acquired part information. (9) In addition, in one aspect of the present invention, in any of the defect detection devices described in (1) to (8) above, the defect detection unit detects whether or not a part used in the equipment captured in the image is defective, based on predetermined criteria. (10) In another aspect of the present invention, in the defect detection device described in (9) above, the criteria for determining whether or not a part used in the equipment captured in the image is defective differs for each piece of equipment. (11) In addition, in one aspect of the present invention, in the defect detection device described in (9) above, the criteria for determining whether or not a part used in the equipment captured in the image is defective differ for each management company that manages the equipment. (12) In addition, in one aspect of the present invention, in the defect detection device described in (9) above, the criteria for determining whether or not a part used in the equipment captured in the image is defective differs depending on the environment in which the equipment is located. (13) In addition, in the defect detection device described in (9) above, the criteria for determining whether or not a part used in the equipment captured in the image is defective varies depending on the period since the last inspection of the equipment using the part. (14) Another aspect of the present invention is a defect detection method comprising: an image acquisition step of acquiring an image of equipment to be inspected; an equipment identification step of the equipment depicted in the acquired image; a parts information acquisition step of acquiring parts information relating to parts used in the equipment by searching for correspondence information which associates the equipment identification information with information relating to parts used in the equipment, based on the identification information identified in the equipment identification step; and a defect detection step of detecting whether or not the parts used in the equipment depicted in the image are defective, based on the acquired image and the acquired parts information. (15) Another aspect of the present invention is a program that causes a computer to execute an image acquisition step of acquiring an image of equipment to be inspected; an equipment identification step of the equipment depicted in the acquired image; a parts information acquisition step of acquiring parts information relating to parts used in the equipment by searching for correspondence information which associates the equipment identification information with information relating to parts used in the equipment, based on the identification information identified in the equipment identification step; and a defect detection step of detecting whether or not the parts used in the equipment depicted in the image are defective, based on the acquired image and the acquired parts information. [Effects of the Invention]

[0007] According to the present invention, it is possible to provide a defect detection device, a defect detection method, and a program that can accurately determine the components used in the equipment to be inspected. [Brief explanation of the drawing]

[0008] [Figure 1] This is a diagram illustrating a schematic of a system according to one embodiment. [Figure 2] This is a functional configuration diagram showing the functional configuration of the system according to this embodiment. [Figure 3] This is a functional configuration diagram showing the functional configuration of the defect detection device according to this embodiment. [Figure 4] This figure shows a first example of the functional configuration of the defect detection unit according to this embodiment. [Figure 5] This figure shows a second example of the functional configuration of the defect detection unit according to this embodiment. [Figure 6] This is a functional configuration diagram showing a first modified example of the functional configuration of the system according to this embodiment. [Figure 7] This is a functional configuration diagram showing a second modified example of the functional configuration of the system according to this embodiment. [Figure 8] This flowchart shows a series of steps in the defect detection method according to this embodiment. [Figure 9] This is a block diagram showing an example of the internal configuration of the defect detection device according to this embodiment. [Modes for carrying out the invention]

[0009] [Embodiment] Preferred embodiments of a defect detection apparatus, a defect detection method, and a program according to an aspect of the present invention will be described in detail below with reference to the accompanying drawings. Aspects of the present invention are not limited to these embodiments, and also include those with various modifications or improvements. That is, the components described below include those that can be easily conceived by those skilled in the art and those that are substantially the same, and the components described below can be combined as appropriate. Moreover, various omissions, substitutions, or modifications of the components can be made without departing from the gist of the present invention. In addition, in the following drawings, for the purpose of making each configuration easy to understand, the scale, number, and the like of each structure may be different from the scale, number, and the like in the actual structure.

[0010] [System Configuration] First, the system 1 according to the present embodiment will be described with reference to FIGS. 1 and 2.

[0011] FIG. 1 is a diagram schematically illustrating a system according to an embodiment. The system 1 includes a drone 10 and an administrator device 30, and inspects a facility 50. Although one facility 50 is shown in the figure for simplification of description, the system 1 may be configured to inspect a plurality of facilities 50. Further, although one drone 10 is shown in the figure for simplification of description, a plurality of drones 10 may be provided. In this case, the plurality of drones 10 may each perform wireless communication with a common administrator device 30, or may each perform wireless communication with an independent administrator device 30. That is, the relationship between the administrator device 30 and the drone 10 may be one-to-N (N is a natural number of 1 or more), or may be N-to-N.

[0012] Equipment 50 is equipment that is inspected by system 1. The equipment 50 may be a communication steel tower (which can also be referred to as a base station) used for wireless communication, or a power transmission steel tower used for overhead power transmission lines. Among the equipment 50, the components to be inspected include various components such as bolts and nuts. A plurality of pieces of equipment 50 may each be assigned identification information. It is preferable that information such as components used in each piece of equipment 50 is centrally managed.

[0013] The administrator device 30 manages the inspection according to the present embodiment. Specifically, the administrator device 30 outputs an inspection instruction to the drone 10. Further, the administrator device 30 acquires the result of inspection performed by the drone 10 in response to the output inspection instruction. Acquiring the result of inspection performed by the drone 10 may specifically be acquiring image information captured by the drone 10. The administrator device 30 performs component determination (for example, determination of presence or absence of an abnormality) based on the acquired image information. Note that the determination function may be provided in the drone 10 or may be provided in the administrator device 30.

[0014] The drone 10 inspects the equipment 50 based on an instruction from the administrator device 30. Specifically, the drone 10 flies around the equipment 50 and photographs the appearance of the equipment 50 at a predetermined position based on an instruction from the administrator device 30. The predetermined position where the drone 10 performs photographing may be programmed in advance, or the drone 10 itself may determine whether to perform photographing based on the appearance of the equipment 50. Note that components used in the equipment 50 are captured in part of the images photographed by the drone 10. It is preferable that at least one or more components are captured in one image, and a plurality of components may be captured therein.

[0015] Figure 2 is a functional configuration diagram showing the functional configuration of the system according to this embodiment. An example of the functional configuration of System 1 will be described with reference to the figure. The example shown in the figure is an example in which defect detection is performed by a drone 10. In this case, the drone 10 is equipped with at least an imaging device 40 and a defect detection device 20. Although the flight function, communication function, etc. of the drone 10 are not described here, it is preferable that the drone 10 has the functions of a typical drone.

[0016] The imaging device 40 captures an image. Specifically, the imaging device 40 captures an image of the exterior of the equipment 50. The imaging device 40 may capture an image of the entire equipment 50, or it may capture an image of a part of the equipment 50 (for example, a part of the bolts and nuts that make up the equipment 50). The imaging device 40 outputs the captured image to the defect detection device 20.

[0017] The defect detection device 20 detects the presence or absence of defects based on images captured by the imaging device 40. The detailed functional configuration of the defect detection device 20 will be described later with reference to Figure 3. The defect detection device 20 outputs the determined result to the administrator device 30. The result determined by the defect detection device 20 may be information regarding the presence or absence of a defect, or information regarding the degree of the defect. Information regarding the presence or absence of a defect may be information regarding the presence or absence of loosening between bolts and nuts, information regarding the presence or absence of cotter pins, or information regarding missing nuts. Information regarding the degree of the defect may be information regarding the degree of loosening.

[0018] [Defect detection device] Figure 3 is a functional configuration diagram showing the functional configuration of the defect detection device according to this embodiment. An example of the functional configuration of the defect detection device 20 will be described with reference to the figure. The defect detection device 20 includes an image acquisition unit 21, an equipment identification unit 22, a component information acquisition unit 23, a defect detection unit 24, an output unit 25, and a component information storage unit 29. Note that the defect detection device 20 is not necessarily required to include a component information storage unit 29; for example, a configuration in which the component information storage unit 29 is provided in a server or cloud space may be adopted. In the illustrated example, for the sake of simplicity, the explanation will be given assuming that the defect detection device 20 includes a component information storage unit 29.

[0019] The image acquisition unit 21 acquires images of the equipment 50 to be inspected. Specifically, the image acquisition unit 21 acquires images from the imaging device 40.

[0020] The equipment identification unit 22 identifies the equipment 50 captured in the acquired image. Identifying the equipment 50 may involve identifying a unique identification number pre-assigned to each piece of equipment 50, or it may involve identifying the type or model number of the equipment 50. Specifically, the equipment identification unit 22 may identify the equipment 50 by applying object recognition processing (object detection processing) to the acquired image. Existing technologies such as convolutional neural networks (CNNs) can be used for object recognition processing. The equipment identification unit 22 can also identify the equipment based on the results of image processing of the acquired image. The information identified by the equipment identification unit 22 can also be called an equipment ID.

[0021] The parts information acquisition unit 23 acquires parts information about the parts used in the equipment 50 based on the identification information identified by the equipment identification unit 22. Specifically, the parts information acquisition unit 23 may acquire parts information by searching the parts information storage unit 29. Here, the parts information storage unit 29 stores correspondence information that associates the identification information of the equipment 50 identified by the equipment identification unit 22 with information about the parts used in the equipment 50. The parts information acquisition unit 23 identifies the parts information by searching the correspondence information using the equipment ID as a key.

[0022] Here, the component information associated with the equipment 50 may include, for example, the type and number of components used. More specifically, the component information may include the type and number of bolts and nuts. Bolts and nuts are components used in the equipment 50 that are captured in the image acquired by the image acquisition unit 21, and are identified by estimation based on the results of image processing of the image. In other words, the component information acquisition unit 23 can also acquire correct data information about the components used by the equipment 50 that is the subject of inspection.

[0023] The defect detection unit 24 detects whether a part used in the equipment 50 shown in the image is defective, based on the image acquired by the image acquisition unit 21 and the part information acquired by the part information acquisition unit 23. In other words, the defect detection unit 24 compares the part identified based on the image acquired by the image acquisition unit 21 with the part acquired by the part information acquisition unit 23 and detects defects. Specifically, the defect detection unit 24 may detect that a part used in the equipment 50 shown in the acquired image is defective if it is not present in the acquired part information. Note that this embodiment is not limited to this example, and the defect detection unit 24 may also detect the presence or absence of defects, or the degree of defects.

[0024] In this case, depending on the parts used in the equipment 50, if a part of the part is missing, it may be identified as a different part. Missing part may be caused by damage to a part, such as it falling off. For example, if one nut constituting a double nut is missing, it may be identified as a single nut. In such cases, it is preferable that the parts used in the equipment 50 have different colors according to their type. Specifically, if the two nuts constituting a double nut are red and the single nut is yellow, even if one nut constituting a double nut is missing, only the red nut will remain, making it possible to distinguish it from the yellow single nut. In this case, the part information can include correspondence information between the type of part and its color. By adopting such a configuration, the defect detection unit 24 can detect whether a part is defective or not based on the color of the part used in the equipment 50 as captured in the acquired image and the color associated with the part information. In other words, by making a defect judgment according to such color information, the judgment can be easily made. Furthermore, this configuration can also be said to suppress detection errors.

[0025] The output unit 25 outputs the result determined by the fault detection unit 24 to the administrator device 30. The output unit 25 may also output information about the correct part if the part used in the equipment 50, as captured in the image acquired by the image acquisition unit 21, is not present in the part information acquired by the part information acquisition unit 23.

[0026] The defect detection unit 24 may also detect whether or not a part used in the equipment 50 captured in the image is defective, based on predetermined judgment criteria. In this case, it is preferable that the judgment criteria differ for each piece of equipment 50. For example, if equipment 50 requires stricter criteria, these requirements can be met by applying criteria determined for each piece of equipment 50. The judgment criteria for each piece of equipment 50 may be stored in the parts information storage unit 29 in association with corresponding information.

[0027] Furthermore, the criteria for judgment may differ for each management company that manages the equipment 50. In fact, the criteria are already in place for each management company that manages communication towers, etc., and by applying different criteria for judgment for each management company, it becomes possible for multiple management companies to use System 1.

[0028] Furthermore, the criteria for determining whether a part is defective may differ depending on the environment in which the equipment is located. For example, for equipment located near the sea, criteria that take into account the early occurrence of corrosion due to salt may be applied. In addition, the criteria may also differ depending on the altitude at which the equipment is installed. Furthermore, the criteria may also differ depending on the two-dimensional information (latitude and longitude information) of the location where the equipment is installed. Moreover, even for bolts and nuts, the criteria may differ depending on whether or not they are used in critical areas.

[0029] Furthermore, the judgment criteria may be adjusted depending on how much time has passed since the previous inspection before the current inspection was conducted. In other words, the judgment criteria may differ depending on the time elapsed since the previous inspection of the equipment 50 using the parts.

[0030] [Defect detection unit] Next, an example of the detailed functional configuration of the defect detection unit 24 will be described. The defect detection unit 24 comprises an estimation unit 241 and a determination unit 242. Depending on the functions of the estimation unit 241 and the determination unit 242 (depending on how the functions are assigned), two different functional configurations can be exemplified. The following will explain each case with reference to Figures 4 and 5.

[0031] Figure 4 shows a first example of the functional configuration of the defect detection unit according to this embodiment. The example shown in the figure illustrates a case where, in a state where the correct answer regarding what kind of parts are used is unknown, a preliminary estimate of the defect is made, and then a final judgment is made considering the correct answer. In this case, the estimation unit 241 is referred to as estimation unit 241A, and the determination unit 242 is referred to as determination unit 242A.

[0032] The estimation unit 241A estimates the condition of the parts used in the equipment as captured in the image acquired by the image acquisition unit 21. In other words, the estimation unit 241A makes a provisional (tentative) estimation of the condition of the parts when it is not possible to determine exactly what parts are used in the equipment 50 being inspected.

[0033] The determination unit 242A determines whether the parts used in the equipment 50 are defective based on the state of the parts estimated by the estimation unit 241A and the parts information acquired by the parts information acquisition unit 23. In other words, the determination unit 242A can also be said to make a final determination that takes into account the correct information of the parts used in the equipment 50. The determination unit 242A outputs the determination result to the output unit 25.

[0034] Figure 5 shows a second example of the functional configuration of the defect detection unit according to this embodiment. The example shown in the figure is one in which a defect is estimated after considering the correct answer as to what kind of parts are used, and then a final judgment is made. In this case, the estimation unit 241 is referred to as the estimation unit 241B, and the judgment unit 242 is referred to as the judgment unit 242B.

[0035] The estimation unit 241B estimates the state of the parts used in the equipment based on the image acquired by the image acquisition unit 21 and the parts information acquired by the parts information acquisition unit 23. In other words, the estimation unit 241B can also estimate the state of the parts while taking into account the correct information of the parts used in the equipment 50.

[0036] The determination unit 242B determines whether or not the parts used in the equipment are defective, based on the condition of the parts estimated by the estimation unit 241B. In other words, the determination unit 242B makes a final determination.

[0037] [First variation] Figure 6 is a functional configuration diagram showing a first modified example of the functional configuration of the system according to this embodiment. An example of the functional configuration of System 1A will be described with reference to this figure. System 1A is a modified example of System 1. In the description of System 1A, explanations that have already been given with reference to System 1 may be omitted by using the same reference numerals.

[0038] System 1A differs from System 1 in that it performs defect detection using a defect detection device 20A, which is configured separately and independently from the drone 10. In this case, the defect detection device 20A acquires an image of the equipment 50 to be inspected from at least one of the imaging device 40A, the drone 10A, or the storage device 60. Based on the acquired image, the defect detection device 20A performs the same processing as the defect detection device 20 described above and makes a determination about the equipment to be inspected as captured in the acquired image.

[0039] The fault detection device 20A transmits the results of the fault detection to the administrator device 30. The fault detection device 20A may, for example, be located near the equipment 50, perform a fault detection determination on images taken around the equipment 50, and transmit the determination result to the administrator device 30 via a network line.

[0040] The imaging device 40A may, for example, be held by an inspector of the equipment 50, and the inspector may use it to image the equipment 50. A commonly used camera can be used as an example of the functional configuration of the imaging device 40A. The imaging device 40A provides the captured images to the defect detection device 20A via a predetermined wireless network or an information storage medium.

[0041] Drone 10A is an aircraft with imaging capabilities. Drone 10A can also be described as having the same functions as Drone 10 described above, but without the function of the fault detection device 20. Drone 10A provides the captured images to the fault detection device 20A via a predetermined wireless network or information storage medium.

[0042] The storage device 60 is composed of a hard disk drive (HDD), a solid state drive (SSD), flash memory, ROM (read-only memory), etc. Images captured in advance by the imaging device 40A or the drone 10A are stored in the storage device 60. The storage device 60 may store multiple images. By using the storage device 60, defect detection processing can be performed on multiple images at once.

[0043] [Second variation] Figure 7 is a functional configuration diagram showing a second modified example of the functional configuration of the system according to this embodiment. An example of the functional configuration of System 1B will be described with reference to this figure. System 1B is a modified example of System 1. In the description of System 1B, explanations that have already been given with reference to System 1 may be omitted by using the same reference numerals.

[0044] System 1B differs from System 1 in that it works in conjunction with Server 70 to perform defect detection at multiple sites collectively on Server 70. In this case, the defect detection device 20B is provided on Server 70. The defect detection device 20B acquires images from various targets via a predetermined communication network NW. As an example of various targets, the figure illustrates multiple drones 10B. Specifically, the figure illustrates multiple drones 10B-1 and multiple drones 10B-2 as examples of multiple drones 10B. Drones 10B may have the same configuration as Drone 10A described above. Furthermore, as other examples of various targets, the imaging device 40A and the storage device 60 described above may be used.

[0045] The defect detection device 20B performs the same processing as the defect detection device 20 described above based on the acquired image and makes a determination about the inspection target captured in the acquired image. The defect detection device 20B may transmit the result of the defect detection to the image source (drone 10B) or an administrator device 30 (not shown), etc.

[0046] [Defect detection method] Figure 8 is a flowchart showing the sequence of steps in the defect detection method according to this embodiment. Referring to this figure, the sequence of steps in the process performed using the defect detection device 20, defect detection device 20A, or defect detection device 20B described above will be explained. When the defect detection device 20, defect detection device 20A, or defect detection device 20B are not distinguished, they may simply be referred to as defect detection device 20.

[0047] (Step S11) First, the defect detection device 20 acquires an image of the equipment to be inspected. The defect detection device 20 acquires an image taken by, for example, a drone 10. This process may be described as the image acquisition process or image acquisition step.

[0048] (Step S12) Next, the fault detection device 20 identifies the equipment 50 depicted in the image based on the acquired image. Specifically, the identification of the equipment 50 may be performed by object recognition processing using a CNN or the like. This process may be described as the equipment identification process or equipment identification step.

[0049] (Step S13) Next, the defect detection device 20 acquires information on the parts used in the identified equipment 50. Specifically, the defect detection device 20 may acquire part information on the parts used in the equipment by searching for correspondence information that associates the identification information of the equipment with information on the parts used in the equipment, based on the identification information identified in the equipment identification step. This step may be described as the part information acquisition step or part information acquisition step.

[0050] (Step S14) Finally, the defect detection device 20 determines whether the part shown in the image is defective. Specifically, the defect detection device 20 detects whether the part used in the equipment 50 shown in the image is defective, based on the acquired image and the acquired part information. This process may be described as the defect detection process or defect detection step.

[0051] [Internal structure] Figure 9 is a block diagram showing an example of the internal configuration of a fault detection device according to this embodiment. The computer shown in the figure shows an example of a specific hardware configuration for realizing the fault detection device 20. The computer consists of a central processing unit (processor) 901, RAM 902, input / output ports 903, input / output devices 904 and 905, etc., and a bus 906. The computer itself can be realized using existing technology. The central processing unit 901 executes instructions contained in programs read from RAM 902, etc. The central processing unit 901 writes data to RAM 902, reads data from RAM 902, and performs arithmetic and logical operations according to each instruction. RAM 902 stores data and programs. Each element contained in RAM 902 has an address and can be accessed using that address. RAM stands for "Random Access Memory". Input / output ports 903 are ports for the central processing unit 901 to exchange data with external input / output devices, etc. Input / output devices 904 and 905 are input / output devices. Input / output devices 904 and 905 exchange data with the central processing unit 901 via input / output ports 903. Bus 906 is a common communication channel used within the computer. For example, the central processing unit 901 reads and writes data to RAM 902 via bus 906. Also, for example, the central processing unit 901 accesses input / output ports via bus 906. Furthermore, all or part of the fault detection device 20 may be implemented using hardware such as ASICs, PLDs, or FPGAs. Furthermore, all or part of each functional unit may be implemented by a combination of software and hardware.

[0052] [Summary of Embodiments] According to the embodiment described above, the defect detection device 20 comprises an image acquisition unit 21, an equipment identification unit 22, a parts information acquisition unit 23, a defect detection unit 24, and an output unit 25. The image acquisition unit 21 acquires an image of the equipment 50 to be inspected. The equipment identification unit 22 identifies the equipment 50 as depicted in the acquired image. The parts information acquisition unit 23 acquires parts information relating to the parts used in the equipment 50 by searching for pre-prepared correspondence information based on the identification information identified by the equipment identification unit 22. The correspondence information is a combination of the identification information of the equipment 50 and information relating to the parts used in the equipment 50. The defect detection unit 24 detects whether the parts used in the equipment 50 depicted in the image are defective, based on the image acquired by the image acquisition unit 21 and the parts information acquired by the parts information acquisition unit 23.

[0053] By adopting this configuration, the defect detection device 20 takes into account information about the parts originally used in the equipment 50 and determines whether the parts used in the equipment 50 are good or not. Examples of defects that the defect detection device 20 targets for detection include defects such as cracks or looseness in parts such as bolts and nuts used in the equipment 50, the extent of the defect, and whether the wrong part is being used. According to this embodiment, for example, even if one nut is missing due to cracking or the like in a place where a double nut should be used, resulting in a single nut, it is possible to detect this as a defect. Therefore, according to this embodiment, it is possible to accurately determine the parts used in the equipment 50 that are to be inspected.

[0054] Furthermore, the above-described embodiment makes it possible to "accurately determine the components used in the equipment to be inspected." The equipment to be inspected according to this embodiment includes, for example, equipment used in wireless communication networks and power transmission towers used in overhead power transmission lines. Therefore, according to this embodiment, it is possible to contribute to Goal 9 of the United Nations Sustainable Development Goals (SDGs), "Build resilient infrastructure, promote sustainable industrialization and expand innovation."

[0055] Although embodiments of the present invention have been described in detail above with reference to the drawings, the specific configuration is not limited to these embodiments, and design modifications and the like are also included within the scope of the gist of the present invention.

[0056] Alternatively, computer programs for realizing the functions of each of the above-mentioned devices may be recorded on a computer-readable recording medium, and the programs recorded on this recording medium may be loaded into a computer system and executed. Note that the term "computer system" here may include hardware such as an operating system and peripheral devices. Furthermore, "computer-readable recording media" refers to writable non-volatile memory such as flexible disks, magneto-optical disks, ROMs, and flash memory, portable media such as DVDs (Digital Versatile Discs), and storage devices such as hard disks built into computer systems.

[0057] Furthermore, "computer-readable recording media" also includes volatile memory (e.g., DRAM (Dynamic Random Access Memory)) within a computer system that acts as a server or client when a program is transmitted via a network such as the Internet or a communication line such as a telephone line, which retains the program for a certain period of time. In addition, the above program may be transmitted from the computer system that stores the program in a storage device, etc., to another computer system via a transmission medium or by transmission waves within the transmission medium. Here, the "transmission medium" for transmitting the program refers to a medium that has the function of transmitting information, such as a network such as the Internet or a communication line such as a telephone line. Furthermore, the above program may be for the purpose of realizing a part of the above-mentioned functions. Moreover, it may be a so-called differential file (differential program) that can realize the above-mentioned functions in combination with a program already recorded in the computer system. [Explanation of Symbols]

[0058] 1...System, 10...Drone, 20...Defect detection device, 30...Administrator device, 40...Imaging device, 50...Equipment, 60...Storage device, 70...Server, 21...Image acquisition unit, 22...Equipment identification unit, 23...Parts information acquisition unit, 24...Defect detection unit, 25...Output unit, 29...Parts information storage unit

Claims

1. An image acquisition unit that acquires images of the equipment to be inspected, An equipment identification unit that identifies the equipment captured in the acquired image, A parts information acquisition unit acquires parts information relating to parts used in equipment by searching for correspondence information that associates the identification information of equipment with information relating to parts used in the equipment, based on the identification information identified by the equipment identification unit. A defect detection unit that detects whether or not a part used in the equipment shown in the image is defective, based on the acquired image and the acquired part information, A defect detection device equipped with the following features.

2. The aforementioned defect detection unit An estimation unit that estimates the condition of the parts used in the equipment as captured in the acquired image, A determination unit determines whether or not a part used in the equipment is defective, based on the state of the part estimated by the estimation unit and the part information acquired by the part information acquisition unit. A defect detection device according to claim 1, comprising:

3. The aforementioned defect detection unit An estimation unit estimates the state of the parts used in the equipment based on the image acquired by the image acquisition unit and the part information acquired by the part information acquisition unit. A determination unit determines whether or not the parts used in the equipment are defective based on the condition of the parts estimated by the estimation unit, A defect detection device according to claim 1, comprising:

4. The equipment identification unit identifies the equipment based on the results of image processing of the acquired image. A defect detection device according to any one of claims 1 to 3.

5. The parts used in the aforementioned equipment differ in color depending on the type of part. The aforementioned part information includes correspondence information between part type and color, The defect detection unit detects whether a part is defective based on the color of the part used in the equipment as captured in the acquired image and the part information. A defect detection device according to any one of claims 1 to 3.

6. The defect detection unit detects that a part used in the equipment, as captured in the acquired image, is defective if it is not present in the acquired part information. A defect detection device according to any one of claims 1 to 3.

7. The parts used in the equipment shown in the acquired image are parts that are identified by estimation based on the results of image processing of the image. The defect detection device according to claim 6.

8. The system further includes an output unit that outputs information about the correct part if the part used in the equipment shown in the acquired image is not present in the acquired part information. The defect detection device according to claim 6.

9. The defect detection unit detects whether or not a part used in the equipment captured in the image is defective, based on predetermined criteria. A defect detection device according to any one of claims 1 to 3.

10. The criteria for determining whether or not the parts used in the equipment shown in the aforementioned image are defective differ for each piece of equipment. The defect detection device according to claim 9.

11. The criteria for determining whether or not the parts used in the equipment shown in the aforementioned image are defective vary depending on the management company that manages the equipment. The defect detection device according to claim 9.

12. The criteria for determining whether or not the parts used in the equipment shown in the aforementioned image are defective vary depending on the environment in which the equipment is located. The defect detection device according to claim 9.

13. The criteria for determining whether or not a component used in the equipment shown in the aforementioned image is defective differ depending on the period since the last inspection of the equipment using that component. The defect detection device according to claim 9.

14. The process involves acquiring images of the equipment to be inspected, and An equipment identification step for identifying the equipment shown in the acquired image, A parts information acquisition step, which acquires parts information relating to parts used in equipment by searching for correspondence information that associates the identification information of equipment with information relating to parts used in the equipment, based on the identification information identified in the equipment identification step, A defect detection step that detects whether or not a part used in the equipment shown in the image is defective, based on the acquired image and the acquired part information, A defect detection method having the following characteristics.

15. On the computer, An image acquisition step in which images of the equipment to be inspected are obtained, An equipment identification step for identifying the equipment shown in the acquired image, A parts information acquisition step, which acquires parts information about parts used in the equipment by searching for correspondence information that associates the identification information of the equipment with information about the parts used in the equipment, based on the identification information identified in the equipment identification step, A defect detection step that detects whether or not a part used in the equipment shown in the image is defective, based on the acquired image and the acquired part information, A program that executes the command.

Images