Image processing device, image processing method, and image processing program

Abstract

This image processing device is provided with: an acquisition unit which acquires a transmission image of a pipe to be processed and a defect-free pipe image which is an image of the pipe having no defect and corresponding to the transmission image; a generation unit which generates a difference image indicating the difference between the acquired transmission image and the defect-free pipe image; and a visualization unit which creates a visualization of the defect level in the pipe on the basis of the pixel value of the difference image.

Description

Image processing device, image processing method, and image processing program

[0001] The present disclosure relates to an image processing device, an image processing method, and an image processing program.

[0002] Conventionally, pipe inspections have utilized measured values ​​of transmission information obtained by radiography. In particular, inspections using radiation such as X-rays are highly valued as an efficient inspection method compared to ultrasonic inspections, because their high transmission eliminates the need to remove protective materials around pipes and they provide clearer images of the subject.

[0003] The main target of inspection when inspecting pipes is wall thinning. Here, "wall thinning" refers to a phenomenon in which the thickness of the pipe, especially the inside, decreases due to some factor. Excessive wall thinning can cause the pipe to break and cause serious damage to the facility in which the pipe is installed, so early detection and countermeasures are required, and regular inspections are carried out.

[0004] Since piping is generally a huge structure in the axial direction, there is a need for efficient inspection. The following technologies can be applied to achieve this.

[0005] Japanese Patent Application Laid-Open No. 2008-256603 discloses a non-destructive inspection device that is intended to enable non-destructive detection of deterioration or damage to a tubular test object before a leak occurs.

[0006] This non-destructive testing device includes a radiation source that irradiates a tubular specimen from the side with radiation, an image sensor that detects radiation that has passed through the tubular specimen to obtain a transmission image, a pipe wall information generation means that generates pipe wall information of the tubular specimen from the transmission image obtained by the image sensor, and an evaluation means that evaluates the integrity of the tubular specimen based on the pipe wall information generated by the pipe wall information generation means.

[0007] In addition, Japanese Patent Application Laid-Open No. 2021-148755 discloses a structure inspection method aimed at reliably detecting defects present in a structure.

[0008] This method for inspecting a structure includes step 1 of irradiating the structure to be inspected with X-rays to obtain a digital X-ray transmission image, step 2 of discriminating between defective portions and healthy portions from an image obtained by image processing the digital X-ray transmission image and the digital X-ray transmission image, step 3 of storing position information of the defective portions and healthy portions, step 4 of calculating, based on the position information, an average brightness over a predetermined area for each of the defective portions and healthy portions in the digital X-ray transmission image before the image processing, and further calculating a difference in average brightness between the defective portions and healthy portions, and step 5 of calculating the thicknesses of the defective portions and healthy portions from the average brightnesses of the defective portions and healthy portions and the brightness difference therebetween.

[0009] In a radiographic image of a pipe to be inspected, the side area of ​​the pipe has low transparency and appears white, while the interior area of ​​the pipe has higher transparency toward the center and appears black. On the other hand, the background area in the radiographic image has the highest transparency and appears black.

[0010] In this way, in a transmission image, the side area of ​​the pipe is close to white and the background area is the darkest, so it is easy to detect the state of thinning in the side area, but the inner area of ​​the pipe becomes closer to black the closer to the center, making it difficult to detect the state of thinning. Note that this issue is not limited to when the detection target is thinning, but can also occur when detecting other defects such as cracks and clogs.

[0011] The present disclosure provides an image processing device, an image processing method, and an image processing program that can detect the state of defects inside a pipe with higher accuracy than conventional techniques.

[0012] A first aspect of the present disclosure is an image processing device comprising at least one processor, which acquires a transmission image of a pipe to be processed and a defect-free pipe image which is an image of the pipe without defects corresponding to the transmission image, generates a difference image showing the difference between the transmission image and the defect-free pipe image, and visualizes the level of defects in the pipe based on the pixel values ​​of the difference image.

[0013] A second aspect of the present disclosure is the first aspect, wherein the defect-free piping image may be a pseudo-generated image.

[0014] A third aspect of the present disclosure is that, in the second aspect, the defect-free piping image may be generated based on averaging pixel values ​​of a transmission image in the axial direction of the piping.

[0015] A fourth aspect of the present disclosure is the second aspect, wherein the defect-free piping image may be generated based on at least one of a position and an area on the transmission image received from a user.

[0016] A fifth aspect of the present disclosure is the second aspect, wherein the defect-free piping image may be generated by simulating a transmission image.

[0017] In a sixth aspect of the present disclosure, in the first or second aspect, the processor may remove noise by performing a filtering process on the difference image.

[0018] A seventh aspect of the present disclosure is the first or second aspect, wherein the defect may be a thinning in the pipe.

[0019] According to an eighth aspect of the present disclosure, in the seventh aspect, the processor may perform visualization by creating a heat map based on pixel values ​​of the difference image.

[0020] A ninth aspect of the present disclosure is the seventh aspect, wherein the processor may perform visualization by adjusting at least one of brightness and contrast of the difference image to emphasize thinning.

[0021] A tenth aspect of the present disclosure is the seventh aspect, wherein the processor may perform a binarization process on the difference image to emphasize thinning, thereby performing visualization.

[0022] An eleventh aspect of the present disclosure is the first or second aspect, wherein the defect-free piping image may be an image having the same angle of view as the transmitted image.

[0023] In addition, a twelfth aspect of the present disclosure is an image processing method in which a processor provided in an image processing device acquires a transmission image of a pipe to be processed and a defect-free pipe image which is an image of the pipe without defects corresponding to the transmission image, generates a difference image showing the difference between the transmission image and the defect-free pipe image, and visualizes the level of defects in the pipe based on the pixel values ​​of the difference image.

[0024] In addition, a thirteenth aspect of the present disclosure is an image processing program that causes a processor provided in an image processing device to perform the following process: acquire a transmission image of a pipe to be processed and a defect-free pipe image that is an image of the pipe without defects corresponding to the transmission image; generate a difference image showing the difference between the transmission image and the defect-free pipe image; and visualize the level of defects in the pipe based on the pixel values ​​of the difference image.

[0025] According to the above aspects, the image processing device, image processing method, and image processing program of the present disclosure can detect the state of defects inside a pipe with higher accuracy than conventional techniques.

[0026] 1 is a block diagram showing a schematic configuration of a radiographic imaging device according to an exemplary embodiment; FIG. 2 is a block diagram showing an example of a hardware configuration of an image processing device according to an exemplary embodiment; FIG. 3 is a diagram used to explain the related art, where the left diagram shows an example of a transmission image obtained in the state shown in FIG. 1 , and the right diagram is a graph showing a distribution of brightness values ​​in the left-right direction of the transmission image shown in the left diagram; FIG. 4 is a side view showing an example of another imaging state by a radiographic imaging device, where the left diagram is used to explain the related art, where the left diagram shows an example of a transmission image obtained in the state shown in FIG. 4 , and the right diagram is a graph showing a distribution of brightness values ​​in the left-right direction of the transmission image shown in the left diagram; FIG. 5 is a block diagram showing an example of a functional configuration of an image processing device according to an exemplary embodiment; FIG. 6 is a diagram showing examples of an original image, a defect-free piping image, and a difference image according to an exemplary embodiment; FIG. 7 is a diagram used to explain a method for generating a defect-free piping image according to an exemplary embodiment; FIG. 8 is a diagram showing an example of a visualization screen according to an exemplary embodiment; FIG. 9 is a schematic diagram showing an example of a configuration of an image information database according to an exemplary embodiment; FIG. 10 is a flowchart showing an example of image processing according to an exemplary embodiment; FIG. 11 is a diagram used to explain another method for generating a defect-free piping image according to an exemplary embodiment; 10A to 10C are diagrams illustrating another method for generating a defect-free piping image according to an exemplary embodiment; FIG. 11A to 11C are diagrams illustrating another example of a visualization screen according to an exemplary embodiment; FIG. 12A to 12C are diagrams illustrating another example of a visualization screen according to an exemplary embodiment;

[0027] Hereinafter, exemplary embodiments for implementing the technology of the present disclosure will be described in detail with reference to the drawings. In the exemplary embodiment, an image processing device and an image processing program according to the technology disclosed herein are described as being applied to a radiographic imaging device that performs non-destructive inspection of a pipe made of metal or the like for a state of wall thinning (hereinafter referred to as "wall thinning inspection") from a radiographic image of the pipe.

[0028] First, the configuration of a radiographic image capturing apparatus 1 according to this exemplary embodiment will be described with reference to Fig. 1. Fig. 1 is a block diagram showing a schematic configuration of the radiographic image capturing apparatus 1 according to this exemplary embodiment.

[0029] 1 , the radiographic imaging device 1 includes an image processing device 10, a radiation source 12, and a radiation detector 14. The image processing device 10, the radiation source 12, and the radiation detector 14 are connected to each other so as to be able to communicate with each other. The image processing device 10 is, for example, a computer such as a personal computer or a server computer.

[0030] The radiation source 12 irradiates the pipe O with radiation R, such as X-rays. The radiation source 12 according to this exemplary embodiment irradiates the pipe O with radiation R in the form of a cone beam.

[0031] The radiation detector 14 includes a scintillator as an example of a light-emitting layer that emits light when irradiated with radiation R, and a TFT (Thin Film Transistor) substrate. The scintillator and TFT substrate are stacked. The TFT substrate has a plurality of pixels arranged two-dimensionally, and each pixel has a sensor unit and a field-effect thin-film transistor as an example of a conversion element that generates an increasing amount of charge as the amount of radiation irradiated increases. The sensor unit absorbs light emitted by the scintillator to generate charge and accumulates the generated charge. The field-effect thin-film transistor converts the charge accumulated in the sensor unit into an electrical signal and outputs it. With the above configuration, the radiation detector 14 generates a two-dimensional transmission image corresponding to the radiation R irradiated onto the piping O from the radiation source 12, and outputs the generated transmission image to the image processing device 10.

[0032] In this manner, in the radiographic image capturing device 1 , a transmission image captured by irradiating the pipe O with radiation R from the radiation source 12 is stored in the image processing device 10 .

[0033] In this exemplary embodiment, a case where an indirect conversion type is applied as the radiation detector 14 will be described, but this is not limited to this form, and a direct conversion type may also be applied as the radiation detector 14.

[0034] Next, the hardware configuration of the image processing device 10 according to this exemplary embodiment will be described with reference to Fig. 2. Fig. 2 is a block diagram showing an example of the hardware configuration of the image processing device 10 according to this exemplary embodiment.

[0035] 2 , the image processing device 10 includes a CPU (Central Processing Unit) 20, a memory 21 serving as a temporary storage area, and a non-volatile storage unit 22. The image processing device 10 also includes a display 23 such as a liquid crystal display, an input device 24 such as a keyboard and a mouse, and a network I / F (Interface) 25 connected to a network. The image processing device 10 also includes an external I / F 26 to which the radiation source 12 and the radiation detector 14 are connected. The CPU 20, the memory 21, the storage unit 22, the display 23, the input device 24, the network I / F 25, and the external I / F 26 are connected to a bus 27. The CPU 20 is an example of a processor according to the disclosed technology.

[0036] The storage unit 22 is realized by a hard disk drive (HDD), a solid state drive (SSD), a flash memory, or the like. The storage unit 22 serves as a storage medium and stores an image processing program 30. The CPU 20 reads the image processing program 30 from the storage unit 22, loads it into the memory 21, and executes the loaded image processing program 30.

[0037] The storage unit 22 also stores an image information database 32. The image information database 32 will be described in detail later.

[0038] Incidentally, when inspecting pipe wall thinning, in the case of an imaging system that images a pipe O from a distance as shown in Fig. 1, for example, a transmission image as shown in the left diagram of Fig. 3 is obtained, and the distribution of brightness values ​​in the left-right direction in the transmission image is as shown in the right diagram of Fig. 3. Fig. 3 is a diagram used to explain the prior art, in which the left diagram shows an example of a transmission image obtained in the state shown in Fig. 1, and the right diagram is a graph showing the distribution of brightness values ​​in the left-right direction of the transmission image shown in the left diagram.

[0039] As an example, as shown in Figure 3, in this imaging system, the side area of ​​the pipe has low transparency and appears close to white, while the area inside the pipe has higher transparency closer to the center and appears close to black. On the other hand, the background area in the transmission image has the highest transparency and appears closest to black.

[0040] Therefore, in this imaging system, by focusing on the thickness of the white pixels, it is possible to detect and measure the state of thinning on the side surface of the pipe O. Furthermore, even in the interior region of the pipe O, it is possible to detect the state of thinning by changes in pixel values ​​compared to surrounding pixels.

[0041] On the other hand, when the space for imaging is relatively narrow, an example is an imaging system that images from near the pipe O, as shown in Fig. 4. With this imaging system, for example, a transmission image as shown in the left diagram of Fig. 5 is obtained, and the distribution of brightness values ​​in the left-right direction in the transmission image is as shown in the right diagram of Fig. 5. Fig. 4 is a diagram provided for explaining the conventional technology, and is a side view showing an example of another imaging state by the radiographic image imaging device 1. Also, Fig. 5 is a diagram provided for explaining the conventional technology, where the left diagram is a diagram showing an example of a transmission image obtained in the state shown in Fig. 4, and the right diagram is a graph showing the distribution of brightness values ​​in the left-right direction of the transmission image shown in the left diagram.

[0042] As an example, as shown in FIG. 5, this imaging system can detect the state of thinning in the internal region of the pipe O by focusing on the change in pixel value compared to the surrounding pixels.

[0043] In this way, in the transmission image, the side area of ​​the pipe O is close to white and the background area is the darkest, so it is easy to detect the state of thinning in the side area. However, in the transmission image, the inner area of ​​the pipe O becomes closer to black as it gets closer to the center, creating a gradation, making it difficult to detect the state of thinning.

[0044] The image processing device 10 according to this exemplary embodiment performs image processing to solve the above problems. Next, the functional configuration of the image processing device 10 according to this exemplary embodiment will be described with reference to Fig. 6. Fig. 6 is a block diagram showing an example of the functional configuration of the image processing device 10 according to this exemplary embodiment.

[0045] 6, the image processing device 10 includes an acquisition unit 20A, a generation unit 20B, a noise removal unit 20C, and a visualization unit 20D. The CPU 20 executes the image processing program 30 to function as the acquisition unit 20A, the generation unit 20B, the noise removal unit 20C, and the visualization unit 20D.

[0046] The acquisition unit 20A according to this exemplary embodiment acquires a transmission image of the piping O to be processed and an image of the defect-free piping O corresponding to the transmission image, which has the same angle of view as the transmission image.

[0047] In this exemplary embodiment, the transmission image of the piping O is acquired by reading it out from the storage unit 22, but this is not limited to this. Alternatively, the transmission image of the piping O may be acquired by reading it out from an external device connected to the network I / F 25. In this exemplary embodiment, the defect-free piping image is acquired by pseudo-generating it, but this is not limited to this. For example, the defect-free piping image may be acquired by capturing a transmission image of the piping O in an unused state using the radiographic imaging device 1 and storing it in the storage unit 22, and then reading the transmission image from the storage unit 22.

[0048] Then, the generating unit 20B according to this exemplary embodiment generates a difference image showing the difference between the transmission image acquired by the acquiring unit 20A (hereinafter also referred to as the "original image") and the defect-free piping image.

[0049] In this exemplary embodiment, as shown in Fig. 7 , the difference image 44 is generated by dividing the original image 40 by the defect-free piping image 42 for each corresponding pixel, but this is not limited to this. For example, the difference image 44 may be generated by dividing the defect-free piping image 42 by the original image 40 for each corresponding pixel, or the difference image 44 may be generated by calculating the difference (subtraction) between the original image 40 and the defect-free piping image 42 for each corresponding pixel. Fig. 7 is a diagram showing an example of the original image 40, the defect-free piping image 42, and the difference image 44 according to this exemplary embodiment.

[0050] Here, the acquisition unit 20A according to this exemplary embodiment generates the defect-free piping image 42 based on the average pixel values ​​of the transmission image (original image 40) in the axial direction of the piping O. More specifically, as shown in FIG. 8 as an example, the region of the piping O in the original image 40 is divided into multiple parts in the axial direction of the piping O, and the average pixel value in the axial direction is calculated for each of the partial regions obtained thereby. The calculated average value is then applied as the pixel value of each pixel in the axial direction of the corresponding partial image, and the partial images obtained thereby are joined together to generate the defect-free piping image 42 of the same size as the original transmission image. FIG. 8 is a diagram for explaining a method for generating the defect-free piping image 42 according to this exemplary embodiment.

[0051] On the other hand, the noise removal unit 20C according to this exemplary embodiment removes noise by performing a filter process on the difference image 44. In this exemplary embodiment, a Gaussian filter is applied as the filter used in the above filtering process, but the present invention is not limited to this. For example, a median filter may be applied as the filter used in the above filtering process.

[0052] The visualization unit 20D according to this exemplary embodiment then visualizes the level of defects (wall thinning in this exemplary embodiment) in the pipe O based on the pixel values ​​of the difference image 44. The visualization unit 20D according to this exemplary embodiment performs visualization by creating a heat map based on the pixel values ​​of the difference image 44. More specifically, the heat map is created so that the larger the pixel value of each pixel in the difference image 44, i.e., the larger the difference, the closer the color to red. This visualized image will be referred to below as a "visualized image," and the screen on which the visualized image is displayed by the display 23 will be referred to below as a "visualized screen."

[0053] 9 shows an example of a visualization screen according to this exemplary embodiment. As shown in FIG. 9, in this visualization screen, a difference image 44 and a visualization image 46 that is a heat map corresponding to the difference image 44 are displayed side by side on the display 23. Therefore, by referring to this visualization screen, the user can intuitively grasp the state of wall thinning of the pipe O.

[0054] Next, the image information database 32 according to this exemplary embodiment will be described with reference to Fig. 10. Fig. 10 is a schematic diagram showing an example of the configuration of the image information database 32 according to this exemplary embodiment.

[0055] The image information database 32 according to this exemplary embodiment is a database in which information indicating the above-described transmitted images is registered. As shown in Fig. 10 , the image information database 32 according to this exemplary embodiment stores information such as piping identification (ID) and image information.

[0056] The piping ID is information assigned in advance to each piping O in order to individually identify the piping O corresponding to the radiographic imaging device 1. The image information is information that indicates the image information itself that indicates the above-mentioned transmitted image.

[0057] Next, the operation of the image processing device 10 according to this exemplary embodiment will be described with reference to Fig. 11. The CPU 20 of the image processing device 10 executes the image processing program 30, thereby performing the image processing shown in Fig. 11. The image processing shown in Fig. 11 is performed, for example, when a command to perform the image processing is input by a user of the image processing device 10. Note that, in order to avoid confusion, the following description will be given assuming that the image information database 32 has already been constructed. Also, the following description will be given assuming that the piping ID of the piping O to be processed has been specified in advance.

[0058] 11, the CPU 20 acquires image information corresponding to a pre-specified piping ID by reading it from the image information database 32. In step 102, the CPU 20 acquires the defect-free piping image 42 by generating it as described above using the read image information.

[0059] In step 104, the CPU 20 generates image information representing the difference image 44 as described above using the acquired image information, i.e., image information representing the original image 40 of the piping O to be processed and image information representing the acquired defect-free piping image 42. In step 106, the CPU 20 performs the above-described filter processing on the image information representing the generated difference image 44.

[0060] In step 108, the CPU 20 creates the visualized image 46 as described above, and executes the visualization process of displaying the visualized screen on the display 23 as described above using the visualized image 46 and the filtered differential image 44, and then ends this image processing. As a result of this visualization process, the visualized screen shown in Fig. 9 as an example is displayed on the display 23, as described above.

[0061] As described above, the image processing device according to this exemplary embodiment acquires a transmission image of a pipe to be processed and a defect-free pipe image, which is an image of the pipe without defects corresponding to the transmission image, and generates a difference image showing the difference between the transmission image and the defect-free pipe image. Therefore, by using the generated difference image, it is possible to detect the state of wall thinning inside the pipe with higher accuracy than conventional techniques.

[0062] Furthermore, according to the image processing device of this exemplary embodiment, the defect-free piping image is generated pseudo-wise, so that the defect-free piping image can be obtained more easily than when an actual image is used as the defect-free piping image.

[0063] Furthermore, according to the image processing device of this exemplary embodiment, the defect-free piping image is generated based on the average pixel values ​​of the transmission images in the axial direction of the piping, which makes it easier to generate the defect-free piping image compared to when the user is required to specify the defect-free portion of the piping.

[0064] Furthermore, according to the image processing device of this exemplary embodiment, noise is removed by filtering the difference image, so that the state of wall thinning can be detected with higher accuracy than when filtering is not performed on the difference image.

[0065] Furthermore, the image processing device according to this exemplary embodiment visualizes the level of defects (thinning in this exemplary embodiment) in the pipe based on the pixel values ​​of the differential image. Therefore, by referring to the visualized thinning level, the state of thinning can be grasped more intuitively.

[0066] In particular, the image processing device according to this exemplary embodiment creates a heat map based on the pixel values ​​of the differential image to visualize the difference, thereby making it possible to grasp the state of wall thinning using the heat map.

[0067] In the above exemplary embodiment, the defect-free piping image 42 is generated based on the average pixel values ​​of the transmission image (original image 40) along the axial direction of the pipe O. However, this is not limiting. For example, the defect-free piping image 42 may be generated based on at least one of a position and an area on the transmission image received from the user. More specifically, as shown in FIG. 12 , the target transmission image (original image 40) is displayed on the display 23, and the user is prompted to specify at least one of a position and an area (in the example shown in FIG. 12 ) in the displayed transmission image where no wall thickness reduction is expected to occur. Next, the area specified by the user is used as a reference area, and an average pixel value is calculated along the axial direction for the reference area. The calculated average pixel value is then applied as the pixel value of each pixel along the axial direction of the reference area. The image of the reference area obtained in this manner is connected in the axial direction until it becomes the same size as the original transmission image, thereby generating a defect-free piping image 42 of the same size as the original transmission image. FIG. 12 is a diagram for explaining another method of generating a defect-free piping image 42 according to the above exemplary embodiment.

[0068] According to this embodiment, the defect-free piping image 42 can be generated more accurately than when the defect-free piping image 42 is generated by calculation using a transmission image.

[0069] Furthermore, for example, the defect-free piping image 42 may be generated by imitating a transmission image. Examples of this form include a form in which the defect-free piping image 42 is generated using three-dimensional information representing the imaging environment and information indicating the dimensions of the piping O (hereinafter referred to as a "first form"), and a form in which the defect-free piping image 42 is generated by machine learning (hereinafter referred to as a "second form").

[0070] FIG. 13 is a diagram illustrating a method for generating a defect-free piping image 42 according to the first embodiment.

[0071] In this embodiment, an imaging environment is simulated as shown in FIG. 13 as an example, based on the positions and orientations of the radiation source 12, the pipe O, and the radiation detector 14, as well as the dimensions of the pipe O, and the distance that radiation penetrates the wall of the pipe O is derived. The longer this distance, the closer to white the pixels in the defect-free piping image 42 become. Therefore, the defect-free piping image 42 is generated by converting this distance into the pixel value of each pixel.

[0072] As a modified example of this embodiment, the defect-free piping image 42 may be generated taking into account the radiation dose from the radiation source 12 and the material of the piping O in addition to the positions and postures of the radiation source 12, piping O, and radiation detector 14 described above and the dimensions of the piping O.

[0073] FIG. 14 is a diagram illustrating a method for generating a defect-free piping image 42 according to the second embodiment.

[0074] In this embodiment, as shown in Fig. 14 as an example, an AI (Artificial Intelligence) model is created in advance by performing machine learning in advance using an existing transmission image (original image 40) as input information and a defect-free transmission image from the transmission image as output information. In this embodiment, a defect-free piping image 42 is generated by inputting a transmission image to be processed to the AI ​​model. Note that examples of machine learning models that can be applied in this case include an autoencoder and a generative adversarial network (GAN).

[0075] According to these embodiments, the defect-free piping image 42 can be generated more easily than when the user is required to specify the defect-free portion of the piping O.

[0076] In the above exemplary embodiment, visualization is performed by creating a heat map based on pixel values ​​of the difference image 44, but the present invention is not limited to this. For example, as shown in Fig. 15, visualization may be performed by adjusting at least one of the brightness and contrast of the difference image 44 to emphasize thinning. Fig. 15 is a diagram showing another example of a visualization screen according to this exemplary embodiment.

[0077] According to this aspect, visualization can be performed more easily compared to visualization using a heat map.

[0078] Furthermore, for example, as shown in Fig. 16, visualization may be performed by performing binarization processing on the difference image 44 to emphasize the thinning. Fig. 16 is a diagram showing another example of a visualization screen according to this exemplary embodiment.

[0079] According to this embodiment, visualization can be performed more easily compared to when at least one of the brightness and contrast of the differential image 44 is adjusted.

[0080] In the above exemplary embodiment, a case where thinning is applied as a defect in the technology of the present disclosure has been described, but the present disclosure is not limited to this. For example, other defects such as cracks or clogs in the pipe O may be applied as defects in the technology of the present disclosure.

[0081] Furthermore, in the above exemplary embodiment, the following various processors can be used as the hardware structure of processing units that perform various processes, such as the acquisition unit 20A, the generation unit 20B, the noise removal unit 20C, and the visualization unit 20D. As described above, the various processors include a CPU, which is a general-purpose processor that executes software (programs) and functions as various processing units, as well as dedicated electrical circuits, such as a programmable logic device (PLD), a processor whose circuit configuration can be changed after manufacture, such as an FPGA (Field Programmable Gate Array), and an ASIC (Application Specific Integrated Circuit), which is a processor having a circuit configuration designed specifically for performing specific processes.

[0082] A single processing unit may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, multiple processing units may be configured with a single processor.

[0083] Examples of configuring multiple processing units with a single processor include: first, a form in which one processor is configured with a combination of one or more CPUs and software, and this processor functions as multiple processing units, as typified by computers such as client and server; second, a form in which a processor is used to realize the functions of an entire system including multiple processing units with a single IC (Integrated Circuit) chip, as typified by systems on chips (SoCs); and thus, various processing units are configured using one or more of the above-mentioned various processors as a hardware structure.

[0084] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements.

[0085] In the above exemplary embodiment, the image processing program 30 is pre-stored (installed) in the storage unit 22 of the image processing device 10, but this is not limiting. The image processing program 30 may be provided in a form recorded on a recording medium such as a CD-ROM (Compact Disc Read Only Memory), a DVD-ROM (Digital Versatile Disc Read Only Memory), or a USB (Universal Serial Bus) memory. The image processing program 30 may also be downloaded from an external device via a network.

[0086] From the above description, the invention described in the following appendix can be understood.

[0087] [Supplementary Note 1] An image processing device including at least one processor, wherein the processor acquires a transmission image of a pipe to be processed and a defect-free pipe image that is an image of the pipe without defects corresponding to the transmission image, generates a difference image that shows the difference between the transmission image and the defect-free pipe image, and visualizes the level of defects in the pipe based on pixel values ​​of the difference image. [Supplementary Note 2] The image processing device according to Supplementary Note 1, wherein the defect-free pipe image is generated in a pseudo manner. [Supplementary Note 3] The image processing device according to Supplementary Note 2, wherein the defect-free pipe image is generated based on an average of pixel values ​​of the transmission image in the axial direction of the pipe. [Supplementary Note 4] The image processing device according to Supplementary Note 2, wherein the defect-free pipe image is generated based on at least one of a position and an area on the transmission image received from a user. [Supplementary Note 5] The image processing device according to Supplementary Note 2, wherein the defect-free pipe image is generated by imitating the transmission image. [Supplementary Note 6] The image processing device according to any one of Supplements 1 to 5, wherein the processor removes noise by performing a filter process on the difference image. [Supplementary Note 7] The image processing device according to any one of Supplementary Notes 1 to 6, wherein the defect is thinning of the pipe. [Supplementary Note 8] The image processing device according to Supplementary Note 7, wherein the processor performs the visualization by creating a heat map based on pixel values ​​of the difference image. [Supplementary Note 9] The image processing device according to Supplementary Note 7, wherein the processor performs the visualization by adjusting at least one of brightness and contrast of the difference image to emphasize thinning. [Supplementary Note 10] The image processing device according to Supplementary Note 7, wherein the processor performs the visualization by performing a binarization process on the difference image to emphasize thinning. [Supplementary Note 11] The image processing device according to any one of Supplementary Notes 1 to 10, wherein the defect-free pipe image is an image with the same angle of view as the transmitted image.[Supplementary Note 12] An image processing method, performed by a processor included in an image processing device, comprising: acquiring a transmission image of a pipe to be processed and a defect-free pipe image that is an image of the pipe without defects corresponding to the transmission image, generating a difference image that shows the difference between the transmission image and the defect-free pipe image, and visualizing the level of defects in the pipe based on pixel values ​​of the difference image. [Supplementary Note 13] An image processing program, for causing a processor included in an image processing device to perform the following processes.

[0088] The disclosure of Japanese Patent Application No. 2024-047956, filed March 25, 2024, is incorporated herein by reference in its entirety.

[0089] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

Claims

1. An image processing device comprising at least one processor, which acquires a transmission image of a pipe to be processed and a defect-free pipe image which is an image of the pipe without defects corresponding to the transmission image, generates a difference image showing the difference between the transmission image and the defect-free pipe image, and visualizes the level of defects in the pipe based on the pixel values ​​of the difference image.

2. The image processing device according to claim 1, wherein the defect-free piping image is generated artificially.

3. The image processing device according to claim 2, wherein the defect-free piping image is generated based on an average of pixel values ​​of the transmission image in the axial direction of the piping.

4. The image processing device according to claim 2, wherein the defect-free piping image is generated based on at least one of a position and an area on the transmission image received from a user.

5. The image processing device according to claim 2, wherein the defect-free piping image is generated by simulating the transmission image.

6. The image processing device according to claim 1 or 2, wherein the processor removes noise by filtering the difference image.

7. The image processing device according to claim 1 or 2, wherein the defect is thinning of the pipe.

8. The image processing device according to claim 7, wherein the processor performs the visualization by creating a heat map based on pixel values ​​of the difference image.

9. The image processing device according to claim 7, wherein the processor performs the visualization by adjusting at least one of the brightness and contrast of the difference image to emphasize the thinning.

10. The image processing device according to claim 7, wherein the processor performs the visualization by performing binarization processing on the difference image to emphasize thinning.

11. The image processing device according to claim 1 or 2, wherein the defect-free piping image has the same angle of view as the transmitted image.

12. An image processing method in which a processor provided in an image processing device performs the following processes: acquiring a transmission image of a pipe to be processed and a defect-free pipe image which is an image of the pipe without defects corresponding to the transmission image; generating a difference image showing the difference between the transmission image and the defect-free pipe image; and visualizing the level of defects in the pipe based on the pixel values ​​of the difference image.

13. An image processing program for causing a processor provided in an image processing device to perform the following process: acquiring a transmission image of a pipe to be processed and a defect-free pipe image which is an image of the pipe without defects corresponding to the transmission image; generating a difference image showing the difference between the transmission image and the defect-free pipe image; and visualizing the level of defects in the pipe based on the pixel values ​​of the difference image.

Images