JP2021067617A - Corrosion diagnostic device, corrosion diagnostic system, corrosion diagnostic method, and program - Google Patents

Abstract

To provide: a corrosion diagnostic device capable of easily diagnosing a corrosion state of a steel material; and the like.SOLUTION: A corrosion diagnosis device 300 includes an image information acquisition unit 311, a calculation unit 312, and a diagnosis unit 313 as functions of a control unit 310. The image information acquisition unit 311 acquires an image obtained by photographing a steel material with imaging means. The calculation unit 312 calculates a simultaneous occurrence matrix for a pixel group constituting the image acquired by the image information acquisition unit 311 and calculates a feature amount from the calculated simultaneous occurrence matrix. The diagnosis unit 313 diagnoses a corrosion state of the steel material based on a feature amount calculated by the calculation unit 312. The feature amount calculated by the calculation unit 312 includes at least one of ASM (Angular Second Moment), contrast, correlation, IDM (Inverse Difference Moment), and entropy.SELECTED DRAWING: Figure 2

Description

The present invention relates to a corrosion diagnostic apparatus, a corrosion diagnostic system, a corrosion diagnostic method, and a program for diagnosing the corrosion status of steel materials.

Diagnosis of the corrosion status of steel materials used in structures is mainly performed by visual observation. In this way, not only is the diagnosis by visual observation time-consuming, but also the evaluation results vary depending on the person in charge of inspection. Based on such a problem, for example, Patent Document 1 discloses a method of simultaneously photographing a steel material constituting a steel tower or the like and a color sample and determining the deterioration level of the steel material using the detected color feature amount. ing.

Japanese Patent No. 3329767

In the method disclosed in Patent Document 1, it takes time and effort to prepare a color sample and to photograph a steel material and a color sample at the same time. Therefore, it is convenient if there is a method for diagnosing the corrosion state of the steel material more easily.

The present invention has been made in view of the above circumstances, and an object of the present invention is to provide a corrosion diagnosis device, a corrosion diagnosis system, a corrosion diagnosis method, and a program capable of easily diagnosing a corrosion state of a steel material.

In order to achieve the above object, the corrosion diagnostic apparatus according to the first aspect of the present invention is
An image acquisition means for acquiring an image obtained by photographing a steel material by an imaging means,
A calculation means for calculating a simultaneous occurrence matrix for a group of pixels constituting the image acquired by the image acquisition means and calculating a feature amount from the calculated simultaneous occurrence matrix.
A diagnostic means for diagnosing the corrosion state of the steel material based on the feature amount calculated by the calculation means is provided.
The feature amount includes at least one of ASM (Angular Second Moment), Control, Correlation, IDM (Inverse Difference Moment), and Entropy.

The image acquisition means acquires, as the image, a two-dimensional image of the steel material and a three-dimensional image including information in the depth direction with respect to the two-dimensional plane defined by the two-dimensional image.
The calculation means targets the first feature amount based on the simultaneous occurrence matrix for the pixel groups constituting the two-dimensional image and the pixel group in the depth direction of the three-dimensional image as the feature amount. Calculate the second feature quantity based on the simultaneous occurrence matrix,
The diagnostic means may diagnose the corrosion state of the steel material based on the first feature amount and the second feature amount.

The calculation means binarizes the two-dimensional image using a threshold value determined by the mode method with respect to the brightness distribution of the two-dimensional image, and occurs in the steel material based on the binarized two-dimensional image. Calculate the estimated area of pitting
The diagnostic means may diagnose the corrosion state of the steel material based on the feature amount and the estimated area.

The image acquisition means may acquire the two-dimensional image by extracting information on a specific primary color defined in advance from a color image represented by a plurality of primary colors.

The diagnostic means may diagnose the corrosion state of the steel material based on at least the value of ASM as the feature amount.

In order to achieve the above object, the corrosion diagnosis system according to the second aspect of the present invention is
The corrosion diagnostic apparatus and the photographing means are provided.
The photographing means includes a three-dimensional camera including a pattern irradiation type or TOF (Time Of Flight) type depth sensor.

In order to achieve the above object, the corrosion diagnosis method according to the third aspect of the present invention is
The step of acquiring an image obtained by photographing a steel material by an imaging means,
A step of calculating a simultaneous occurrence matrix for the pixel group constituting the acquired image and calculating a feature amount from the calculated simultaneous occurrence matrix.
A step of diagnosing the corrosion state of the steel material based on the calculated feature amount is provided.
The feature amount includes at least one of ASM (Angular Second Moment), Control, Correlation, IDM (Inverse Difference Moment), and Entropy.

In order to achieve the above object, the program according to the fourth aspect of the present invention is
Computer,
An image acquisition means for acquiring an image obtained by photographing a steel material by an imaging means,
A calculation means for calculating a simultaneous occurrence matrix for a group of pixels constituting the image acquired by the image acquisition means and calculating a feature amount from the calculated simultaneous occurrence matrix.
A program that functions as a diagnostic means for diagnosing a corrosion state of the steel material based on the feature amount calculated by the calculation means.
The feature amount includes at least one of ASM (Angular Second Moment), Control, Correlation, IDM (Inverse Difference Moment), and Entropy.

According to the present invention, the corrosion state of a steel material can be easily diagnosed.

It is a figure which shows the whole structure of the corrosion diagnosis system which concerns on one Embodiment of this invention. It is a block diagram which shows the structure of the corrosion diagnostic apparatus. It is a figure for demonstrating image processing by an image information acquisition part. It is a figure for demonstrating image processing by an image information acquisition part. It is a figure for demonstrating the calculation method of a simultaneous occurrence matrix. (A) is a diagram for explaining a method for determining a threshold value by the mode method, and (b) is a diagram showing an example of an image binarized with the determined threshold value. It is a flowchart which shows an example of the corrosion diagnosis processing. (A) and (b) are graphs derived to verify the measurement accuracy in the experiment. (A) to (d) are diagrams showing images to be analyzed in an experiment. (A) and (b) are graphs showing various features calculated based on GLCM in the xy plane. (A) to (c) are graphs showing various feature quantities calculated based on GLCM in the xy plane. (A) and (b) are graphs showing various feature quantities calculated based on GLCM in the z direction. (A) to (c) are graphs showing various feature quantities calculated based on GLCM in the z direction. It is a figure of the graph which shows the correlation between the estimated area of pitting corrosion calculated by image analysis, and the area of an actual pitting corrosion area.

An embodiment of the present invention will be described with reference to the drawings.

FIG. 1 shows the overall configuration of the corrosion diagnosis system 100 according to the present embodiment. The corrosion diagnosis system 100 photographs the steel material 2 constituting the structure used in the irrigation facility 1 such as an agricultural waterway, and diagnoses the corrosion state of the steel material 2. The steel material 2 is, for example, a steel sheet pile. Reference numeral 3 in FIG. 1 indicates a water channel. As shown in FIG. 1, the corrosion diagnosis system 100 includes a photographing unit 200 and a corrosion diagnosis device 300. The photographing unit 200 and the corrosion diagnosis device 300 are communicably connected to each other via a wired or wireless communication network.

The photographing unit 200 is an imaging device that photographs the diagnosis target region 2a of the steel material 2 and acquires a two-dimensional color image (RGB image) of the steel material 2 and a three-dimensional shape of the steel material 2. The photographing unit 200 is composed of, for example, a three-dimensional camera (also referred to as a depth camera) having a depth sensor of a pattern irradiation method (structured-light). The photographing unit 200 has two infrared cameras, an RGB camera (visible light camera), and an infrared light projector as depth sensors. The photographing unit 200 acquires a two-dimensional color image S as shown in FIGS. 3 and 4 by an RGB camera. Further, the photographing unit 200 projects a predetermined pattern of dots or borders on the surface of the steel material 2 by an infrared light projector, and photographs the change of the projected pattern by two infrared cameras. The three-dimensional shape D of the steel material 2 as shown in 4 is acquired.

In this embodiment, as shown in FIG. 4, the two-dimensional plane defined by the two-dimensional color image S is a plane having an x-axis and a y-axis orthogonal to each other. Further, the axis extending in the depth direction with respect to the two-dimensional plane and orthogonal to the x-axis and the y-axis is defined as the z-axis. Therefore, the data showing the three-dimensional shape D includes the z-direction data which is the information in the z-direction which is the depth direction. The photographing unit 200 supplies image information including data indicating a two-dimensional color image S and data indicating a three-dimensional shape D to the corrosion diagnostic apparatus 300.

The corrosion diagnosis device 300 is a terminal device composed of a personal computer, a tablet terminal, or the like and operated by an operator. As shown in FIG. 2, the corrosion diagnosis device 300 includes a control unit 310, a storage unit 320, an operation unit 330, a display unit 340, and a communication unit 350. Each of these parts is connected by a bus for transmitting a signal. The corrosion diagnosis device 300 may be composed of a plurality of computers capable of communicating with each other.

The control unit 310 includes a CPU (Central Processing Unit), a ROM (Read Only Memory), and a RAM (Random Access Memory). The CPU is, for example, a microprocessor or the like, and is a central processing unit that executes various processes and operations. In the control unit 310, the CPU reads the control program stored in the ROM and controls the operation of the entire corrosion diagnosis device 300 while using the RAM as the work memory.

The storage unit 320 is a non-volatile memory such as a flash memory or a hard disk. The storage unit 320 stores programs and data used by the control unit 310 to perform various processes, including an OS (Operating System) and an application program. Further, the storage unit 320 stores data generated or acquired by the control unit 310 performing various processes.

The operation unit 330 includes input devices such as a keyboard, mouse, buttons, touch pad, and touch panel, and accepts operations by the operator. The operator can input a command to the corrosion diagnosis device 300 by operating the operation unit 330.

The display unit 340 includes a display device such as a liquid crystal display and an organic EL (Electro Luminescence) display, and a display drive circuit for displaying an image on the display device. The display unit 340 displays a two-dimensional color image, a three-dimensional image, or the like acquired by the control unit 310 from the photographing unit 200. In this way, the display unit 340 displays various information obtained as a result of the processing by the control unit 310.

The communication unit 350 is an interface for communicating with an external device including the photographing unit 200. The corrosion diagnosis 300 is connected to the photographing unit 200 by, for example, a wired LAN (Local Area Network), a wireless LAN, or a communication line according to other communication standards. The communication unit 350 communicates with the photographing unit 200 under the control of the control unit 310, and acquires the above-mentioned image information from the photographing unit 200. Further, the communication unit 350 can be connected to a wide area network such as the Internet via wired or wireless communication.

As shown in FIG. 2, the control unit 310 includes an image information acquisition unit 311, a calculation unit 312, a diagnosis unit 313, and an output unit 314 as functions. In the control unit 310, the CPU functions as each of these units by reading the program stored in the ROM into the RAM, executing the program, and controlling the program.

The image information acquisition unit 311 acquires the image information obtained by the photographing unit 200 photographing the steel material 2. Specifically, the image information acquisition unit 311 communicates with the photographing unit 200 via the communication unit 350, and acquires image information from the photographing unit 200. The image information acquired by the image information acquisition unit 311 is stored in the storage unit 320. The image information acquisition unit 311 is realized by the control unit 310 cooperating with the communication unit 350. The image information acquisition unit 311 may control the shooting operation of the shooting unit 200 and may acquire image information from the shooting unit 200. In addition, the image information acquisition unit 311 also performs an image analysis process of the image indicated by the image information acquired from the photographing unit 200, as described below.

The image information acquisition unit 311 extracts information on a predetermined specific primary color from the RGB data (values of (R, G, B) in the RGB color system) of the pixel group constituting the two-dimensional color image S. By doing so, a specific color extracted image as a two-dimensional image is acquired. Specifically, as shown in FIG. 3, the image information acquisition unit 311 decomposes the RGB data in the two-dimensional color image S into R (Red), G (Green), and B (Blue) channels. A specific color extracted image Sr is generated by grayscale-converting an image obtained by extracting the value of R as a specific primary color (dividing the pixel value into 0 to 255). The reason for using the value of R is that the image analysis described later can be performed satisfactorily by considering the red rust generated in the steel material 2. The color image S in FIG. 3 is actually a full-color image. Further, in FIG. 3, Sg is an image obtained by extracting the value of G, and Sb is an image obtained by extracting the value of B.

Further, the image information acquisition unit 311 synthesizes a two-dimensional color image S and a three-dimensional shape D based on the image information acquired from the photographing unit 200, as shown in FIG. 4, to form a three-dimensional color image. Generate C. Then, the image information acquisition unit 311 grayscale-converts the generated three-dimensional image C. The image information acquisition unit 311 may acquire the three-dimensional color image C generated by the image processing device included in the photographing unit 200. As described above, the specific color extraction image Sr and the three-dimensional image C grayscaled by the image information acquisition unit 311 are used for the calculation of the simultaneous occurrence matrix (GLCM) by the calculation unit 312. ..

The calculation unit 312 calculates a GLCM for a pixel group constituting a grayscaled image (in this embodiment, a specific color extracted image Sr or a three-dimensional image C), and various feature quantities are calculated from the calculated GLCM. Is calculated. Specifically, the calculation unit 312 collects statistics on the densities of two pixels (hereinafter, referred to as pixel pairs) at specific positions in the pixel group constituting the grayscale image. Create a matrix by doing so. As shown in FIG. 5, the relative position of the pixel pair is defined by the angle θ and the inter-pixel distance d. The reference numeral E in FIG. 5 represents a pixel. The calculation unit 312 reads the luminance value for the pixel pair and sets this as (i, j). Then, the calculation unit 312 performs the same calculation for the pixel pairs satisfying all the relative positional relationships, and records the cumulative number as the (i, j) component of the GLCM. Hereinafter, the GLCM calculated in this way is referred to as p (i, j).

Then, the calculation unit 312 calculates each feature amount of ASM (Angular Second Moment), Control, Correlation, IDM (Inverse Difference Moment), and Entropy based on the calculated GLCM. Each of these feature quantities is represented by each formula shown in the following (Equation 1) to (Equation 5). ASM is a feature quantity that represents the homogeneity of the image. Contrast and IDM are features that represent the degree of local brightness of an image. Correlation is a feature quantity that represents a local correlation of luminance values. Entropy is a feature quantity that represents the disorder of distribution of luminance values to pixels.

The calculation unit 312 calculates the GLCM for the pixel group (pixel group arranged in the x and y directions) constituting the grayscaled specific color extracted image Sr (two-dimensional image), and calculates the GLCM into the calculated GLCM. Based on this, each of the above feature quantities is calculated. Hereinafter, each feature amount calculated based on the specific color extracted image Sr is also referred to as a "first feature amount". Further, the calculation unit 312 calculates a GLCM for a pixel group (for example, a pixel group arranged in the z and x directions) in the depth direction of the grayscaled three-dimensional image C, and calculates the GLCM. Based on this, each of the above feature quantities is calculated. Hereinafter, each feature amount calculated based on the three-dimensional image C is also referred to as a “second feature amount”.

Further, the calculation unit 312 determines a threshold value for binarizing the grayscaled specific color extracted image Sr by the mode method, and uses the determined threshold value to binarize the specific color extracted image Sr. The estimated area of pitting generated in the steel material 2 is calculated based on the binarized image.
Specifically, the calculation unit 312 obtains the brightness distribution of the pixels constituting the grayscaled specific color extracted image Sr, and uses a moving average of an arbitrary number of pixels (for example, 3 pixels) to obtain FIG. 6 (a). ), The frequency with respect to the lightness (0 to 255) is smoothed until it shows two maximum values. Next, the calculation unit 312 calculates the minimum value of the frequency and executes the binarization process of the grayscaled specific color extracted image Sr with the value as the threshold value. Then, the calculation unit 312 calculates the area of the color (whether white or black is used) of the portion below the threshold value, and uses this area as the estimated area of pitting corrosion generated in the steel material 2. FIG. 6B shows an example of an image after the binarization process is executed. In this example, the pitting corrosion is white.

The diagnosis unit 313 diagnoses the corrosion state of the steel material 2 based on the feature amount calculated by the calculation unit 312 and the estimated area of pitting corrosion generated in the steel material 2. The diagnostic method will be described in the section “8. Corrosion diagnosis” in the examples described later.

The output unit 314 is calculated by various images (two-dimensional color image S, specific color extraction image Sr, three-dimensional shape D, three-dimensional image C, etc.) acquired or generated by the image information acquisition unit 311 and calculation unit 312. The result, the diagnosis result by the diagnosis unit 313, and the like are displayed on the display unit 340.

The configuration of the corrosion diagnosis system 100 is as described above. Subsequently, the corrosion diagnosis process executed by the control unit 310 of the corrosion diagnosis device 300 will be described with reference to FIG. 7.

(Corrosion diagnosis processing)
The corrosion diagnosis process is started, for example, by the operator operating the operation unit 330 and inputting an instruction to the photographing unit 200 to start photographing the diagnosis target area 2a in the steel material 2. The double line in FIG. 7 indicates parallel processing.

First, the control unit 310 acquires image information (data of the two-dimensional color image S and the three-dimensional shape D) from the photographing unit 200 by the function as the image information acquisition unit 311 (step S1).

The image information acquisition unit 311 that acquired the image information in step S1 decomposes the two-dimensional color image S of the two-dimensional color image S into R, G, and B channels, and extracts the value of R as a specific primary color. A specific color extracted image Sr is generated by grayscale conversion of the obtained image (step S2).

The control unit 310 that generated the specific color extracted image Sr in step S2 functions as the calculation unit 312, and as described above, the pixel group (pixel group arranged in the x and y directions) constituting the specific color extracted image Sr. ) Is calculated, and each of the above feature quantities (first feature quantity) is calculated based on the calculated GLCM (step S3). Further, as described above, the calculation unit 312 determines the threshold value for binarizing the specific color extracted image Sr by the mode method, and uses the determined threshold value to binarize the specific color extracted image Sr. (Step S4). Then, the calculation unit 312 calculates the estimated area of pitting corrosion generated in the steel material 2 based on the binarized image (step S5).

Further, the image information acquisition unit 311 that acquired the image information in step S1 generates a color three-dimensional image C by synthesizing the two-dimensional color image S and the three-dimensional shape D (step S6). Then, the image information acquisition unit 311 grayscales the image based on the z-direction data in the three-dimensional image C (step S7). Specifically, in step S7, the image information acquisition unit 311 is arranged on a plane of the three-dimensional image C including the z direction, which is the depth direction, and an arbitrary direction (for example, the x direction) orthogonal to the z direction. A two-dimensional image (hereinafter referred to as a depth reflection image) composed of a group of pixels is grayscaled. The image information acquisition unit 311 may acquire the depth reflection image after grayscale the three-dimensional image C. Following step S7, the control unit 310 performs a function as a calculation unit 312 to perform a GLCM targeting a pixel group (pixel group arranged in the z and x directions) constituting a grayscaled depth reflection image. Calculate and calculate each of the above feature amounts (second feature amount) based on the calculated GLCM (step S8).

The control unit 310 that has executed each of the above processes is based on the first feature amount, the estimated area of pitting corrosion, and the second feature amount calculated in each of steps S3, S5, and S8 by the function as the diagnosis unit 313. , Diagnose the corrosion state of the steel material 2 (step S9). As will be described in detail later, the diagnostic unit 311 can evaluate the state of the steel material 2 stepwise, for example, uncorroded, corroded, and pitted.

The control unit 310 can appropriately display the captured image of the diagnosis target area 2a, the image analysis screen, the diagnosis result, and the like on the display unit 340 by the function as the output unit 314. Further, in the above, an example in which the control unit 310 calculates each value of the first feature amount, the estimated area of pitting corrosion, and the second feature amount by parallel processing is shown, but the order of processing is arbitrary, and each of these values The values may be calculated sequentially. The above is the corrosion diagnosis process.

Here, the characteristic of the performance deterioration of the steel sheet pile canal, which is an example of the irrigation facility 1, is that corrosion progresses in the water level fluctuation region. In particular, in the steel sheet pile canals for agriculture, many facilities where corrosion becomes apparent about 10 years after installation have been confirmed due to extensive facility management, and the risk of pitting corrosion and buckling fracture due to the progress of corrosion has been pointed out. By using the corrosion diagnosis method described above, it is possible to diagnose the corrosion state of the steel material 2 used in the steel sheet pile channel by non-destructive and non-contact inspection. Hereinafter, an embodiment of the corrosion diagnostic apparatus 300, the stress estimation process using the corrosion diagnostic apparatus 300, and the stress estimation method will be described. As an example, the inventors of the present application conducted an experiment under the conditions described below.

(Example)
1. 1. Measurement conditions The steel material 2 (steel sheet pile) was irradiated with a dot pattern of near-infrared rays, and the plate surface of the steel material 2 was photographed from directly above by the photographing unit 200 composed of a three-dimensional camera. Specifically, the steel material 2 was photographed from heights of 116 cm and 56 cm. A RealSense Depth Camera 435i (manufactured by intel) was used as the three-dimensional camera, and the number of pixels was 1280 x 720 pixels.

2. Examination Case Cases 1 to 3 were prepared as examination cases. Case 1 is an unused steel sheet pile. Case 2 is a corroded steel sheet pile (with plate thickness measurement) after cleaning. Case 3 is a corroded steel sheet pile (without plate thickness measurement) before cleaning.

3. 3. Analysis flow The analysis flow is the same as the corrosion diagnosis process shown in FIG. 7 described above. In this experiment, the influence of the light source was not taken into consideration, so the analysis focused on the shape and texture in the image information.

4. Verification of measurement accuracy (1) Method Using an aluminum section (20 mm × 20 mm) attached to Case 1, the measurement accuracy based on the imaging distance was verified. From the above-mentioned three-dimensional image C (an image obtained by synthesizing a two-dimensional color image S (RGB image) and an image showing a three-dimensional shape D), RGB information from 0 to 255 was added and divided by three. Using the value as an index, only aluminum sections were extracted with a threshold value of 240 or more. The lengths of the four sides of the aluminum section were calculated, and the data of the aluminum section in the z direction (depth direction) was extracted to verify the measurement accuracy. The error in the z direction was the difference between the maximum value and the minimum value of the z direction data of the aluminum intercept.
(2) Results and Discussion Fig. 8 (a) shows the relationship between the shooting distance and the length of one side of the aluminum section calculated by image analysis. FIG. 8B shows the relationship with the error in the z direction with respect to the shooting distance. As a result of the examination, the length of one side of the aluminum intercept is calculated excessively when the imaging distance is short, while the length of one side of the aluminum intercept approaches the true value when the imaging distance is long, but there is an error in the z direction. It turned out to be bigger. In the subsequent experiments, the analysis was performed using the data when the shooting distance was 56 cm, which had a small error in the z direction.

5. Evaluation of corrosion status using simultaneous occurrence matrix (xy plane)
(1) Evaluation method In this experiment, the corrosion status was evaluated using the simultaneous occurrence matrix (GLCM). As described above, the GLCM for the image to be analyzed (pixel group arranged in the xy plane) is calculated, and based on the calculated GLCM, a total of five feature quantities of ASM, Contrast, Correlation, IDM, and Entry are used. (Corresponding to the above-mentioned first feature amount.) Was calculated. The analysis target was an image of the steel sheet piles of Cases 1 to 3, and the convex plane of the steel sheet pile was cut out at 80 × 170 pixel. In particular, two images of a portion where pitting corrosion occurred and a portion where pitting corrosion did not occur were cut out from Case3. Since Case2 is marked with white paint and may not be evaluated accurately, it was excluded from the analysis target of the xy plane (Case2 was used in the analysis in the z direction described later). The images to be analyzed are shown in FIGS. 9 (a) to 9 (d). The images of FIGS. 9A to 9D are actually full-color RGB, and correspond to the above-mentioned two-dimensional color image S.
(2) Results and discussion The calculation results of the feature amount are shown in FIGS. 10 (a) and 10 (b) and FIGS. 11 (a) to 11 (c). In the graphs of each of these figures, the vertical axis represents the value of the feature amount, and the pixel on the horizontal axis represents the inter-pixel distance d (when the angle θ = 0 °) that defines the relative position of the pixel pair as described above. Shown. As can be seen from the graphs in each figure, there was a difference in all the features depending on the presence or absence of corrosion. In particular, in ASM, Case 1 showed a substantially constant value regardless of the distance. ASM is an index showing the homogeneity of the image, and it was clarified that it is homogeneous regardless of the distance when corrosion does not occur. In addition, when compared with and without pitting corrosion, the homogeneity is lower when there is pitting corrosion, but the ASM curve (the curve showing the change in the ASM value with respect to the inter-pixel distance d) shows almost the same tendency. Became clear. Differences were also confirmed in other features, indicating that GLCM is useful for evaluating the state of corrosion.

6. Evaluation in the depth direction (z direction) using a simultaneous occurrence matrix (1) Evaluation method Using the same method as in the previous section, an image containing numerical values in the z direction (images arranged in the zx plane) is converted into a grayscale image. It was converted and an attempt was made to evaluate the area spread in the depth direction by GLCM. Again, based on the calculated GLCM, a total of five features (corresponding to the above-mentioned second feature) of ASM, Control, Correlation, IDM, and Entropy were calculated. The analysis target was an image of the steel sheet piles of Cases 1 to 3, and the convex plane of the steel sheet pile was cut out at 40 × 120 pixel. In the evaluation in the z direction, Case 3 was used as an image of a portion where pitting corrosion did not occur. Considering that the maximum value of Case 3 in the z direction was 0.02 m, 0.02 m was set to a pixel value of 255 (white) and 0 m was set to a pixel value of 0 (black) to convert to a grayscale image. ..
(2) Results and Discussion The calculation results of the feature amount are shown in FIGS. 12 (a) and 12 (b) and FIGS. 13 (a) to 13 (c). In the graphs of each of these figures, the vertical axis represents the value of the feature amount, and the pixel on the horizontal axis represents the inter-pixel distance d (when the angle θ = 0 °) that defines the relative position of the pixel pair as described above. Shown. As can be seen from the graphs in each figure, there was a difference in all the features depending on the presence or absence of corrosion. In particular, it was revealed that ASM, IDM, and Entropy differ significantly depending on the presence or absence of corrosion. ASM indicates the homogeneity of the image, IDM indicates the degree of local brightness, and Entropy indicates the disorder of distribution of the brightness value (in this case, the degree of unevenness) to the pixels. It is considered that it is possible to index the progress of the degree of unevenness of. In addition, it is considered that the difference between the presence and absence of cleaning can be evaluated by using Control.

7. Evaluation of pitting corrosion area In the same manner as described above, the two-dimensional color image S (which may be the combined three-dimensional image C) is decomposed into RGB channels, and only the R (Red) value is extracted. A specific color extracted image Sr was generated by grayscale conversion of the obtained image (see FIG. 3). Then, the binarization process was performed at the threshold value determined by using the mode method. The estimated area of pitting corrosion generated in the steel material 2 was calculated using the image after the binarization treatment shown in FIG. 6 (b). In FIG. 6B, since the white portion is pitting corrosion, the estimated area of pitting corrosion was calculated from the number of pixels in the white portion. FIG. 14 shows a graph in which the estimated area of pitting corrosion calculated in this way is taken on the horizontal axis (the area calculated by image analysis in the figure) and the actual area of pitting corrosion is taken on the vertical axis. The actual area of pitting corrosion on the vertical axis is a value converted by measuring the same sample with a 3D scanner and using the size of a square aluminum tape (2 cm x 2 cm) installed at the time of on-site measurement. .. As shown in FIG. 14, it can be seen that the estimated area of pitting corrosion (the area that can be calculated by the process of step S5 in FIG. 7) is calculated with high accuracy.

8. Corrosion diagnosis (1) Corrosion diagnosis based on the xy plane Regarding the corrosion diagnosis based on the xy plane of the steel material 2, focusing on the ASM shown in FIG. 10 (a), for example, the ASM in an arbitrary pixel section When the value or the average value of ASM in an arbitrary pixel section falls below a predetermined threshold value, it can be diagnosed that the steel material 2 may be corroded or pitted. Alternatively, when the fluctuation of the ASM value with respect to an arbitrary pixel is lower than the predetermined rate of change, it can be diagnosed that the steel material 2 is uncorroded (that is, sound). Further, although Case 3 and Case 3 (with pitting corrosion) show the same tendency, the value of the ASM curve is different, so whether it is corroded or pitting corrosion occurs based on the magnitude of the ASM value. Can be determined. As for other feature quantities, as shown in FIGS. 10 and 11, there are gaps between the cases, so the corrosion status (uncorroded, corroded, or pitted corrosion) of the steel material 2 is evaluated in the same way. be able to. As the feature amount used for the corrosion diagnosis of the steel material 2, all of the above five feature amounts may be used, or at least one of them may be used. However, as the feature amount used in the corrosion diagnosis of the steel material 2, it is preferable to use at least one of ASM, IDM, and Entropy, which causes a remarkable difference depending on the situation of the steel material 2, and further, it is more preferable to use at least ASM. preferable.
(2) Corrosion diagnosis in the z direction Regarding the corrosion diagnosis of the steel material 2 in the z direction, focusing on the ASM shown in FIG. 12 (a), for example, the value of ASM in an arbitrary pixel section and ASM in an arbitrary pixel section. When the average value of is less than a predetermined value, it can be diagnosed that the degree of unevenness on the surface of the steel material 2 may progress and corrosion or pitting corrosion may occur. Alternatively, when the fluctuation of the ASM value with respect to an arbitrary pixel is lower than the predetermined rate of change, it can be diagnosed that the surface of the steel material 2 is almost flat and is not corroded (that is, sound). Further, not only ASM but also IDM and Entropy have remarkable gaps between Case 1 and Cases 2 and 3, so that the feature amount used in the corrosion diagnosis considering the degree of surface unevenness of the steel material 2 is It is preferable to use at least one of ASM, IDM, and Entropy, which makes a remarkable difference depending on the situation of the steel material 2, and it is more preferable to use at least ASM. Further, by paying attention to Control as a feature amount, it is possible to determine whether or not the steel material 2 has been washed and whether or not it is dirty. By using each feature amount calculated based on GLCM in the z direction, it is possible to diagnose not only the corrosion state but also whether or not the steel material 2 is curved.
(3) Corrosion diagnosis based on the estimated area of pitting corrosion occurring in the steel material 2 When the calculated estimated area of pitting corrosion exceeds a predetermined value, it is possible to diagnose that there is pitting corrosion.
(4) Summary In consideration of the above, the ROM and storage unit 320 of the control unit 310 have data of values that serve as a reference for discrimination when performing the above-mentioned corrosion diagnosis, the discrimination result, and the state of the steel material 2 (not yet). Corrosion, corrosion, pitting corrosion, etc.) and table data and mathematical formula data for obtaining the rate of change of each feature amount are determined and stored in advance by conducting experiments, etc., and the control unit The 310 can diagnose the corrosion state of the steel material 2 by functioning as a diagnostic unit 313. In addition, the diagnostic accuracy may be improved by artificial intelligence or deep learning. The diagnostic unit 313 does not have to diagnose the corrosion state of the steel material 2 by using all of the first feature amount, the second feature amount, and the estimated area of pitting corrosion, and the first feature amount, the second feature amount, And at least one of the estimated areas of pitting corrosion may be used to diagnose corrosion conditions. Further, the diagnosis unit 313 uses the values of the first feature amount, the second feature amount, and the estimated area of pitting corrosion as they are as the diagnosis result, and even if the operator who sees the diagnosis result determines the corrosion state of the steel material 2. Good.

The present invention is not limited to the above embodiments and drawings. Modifications (including deletion of components) can be appropriately added without changing the gist of the present invention. An example of the modification will be described below.

(Modification example)
Of the parts constituting the corrosion diagnosis system 100, a part of the photographing unit 200, or the photographing unit 200 and the corrosion diagnosis device 300 is mounted on a UAV (unmanned aerial vehicle) (commonly referred to as a drone). , The steel material 2 may be photographed by remote operation. Further, the configuration of the photographing unit 200 and the like may be mounted on another moving body such as a land traveling robot that can be remotely controlled.

In the above, the example in which the steel material 2 is a steel sheet pile used in the irrigation facility has been described, but the type of the steel material 2 subject to the corrosion diagnosis is arbitrary and is not limited to this. The steel material 2 to be diagnosed by the corrosion diagnosis system 100 or the corrosion diagnosis device 300 may be a steel sheet pile for earth retaining, an iron plate for civil engineering, a steel material for a steel tower, or the like.

In the above, an example in which the photographing unit 200 is composed of a three-dimensional camera including a pattern irradiation type depth sensor has been described, but the photographing unit 200 is not limited to this. The photographing unit 200 may be composed of a three-dimensional camera including a TOF (Time Of Flight) depth sensor. Further, the photographing unit 200 is not limited to the integrated three-dimensional camera, and may be composed of a combination of a separate visible light camera and a depth sensor.

In the above embodiment, when calculating various feature quantities, an example of obtaining a value corresponding to the inter-pixel distance d when the angle θ = 0 ° has been described, but the setting of θ is arbitrary depending on the purpose. Yes, but not limited to this.

In the above, the image information acquisition unit 311 has a predetermined specific primary color among the RGB data (values of (R, G, B) in the RGB color system) of the pixel group constituting the two-dimensional color image S. As information, an example of generating a specific color extracted image by extracting the value of R has been shown, but the present invention is not limited to this. The image information acquisition unit 311 may generate a specific color extraction image by extracting the value of G or the value of B. For example, when the steel material 2 contains copper, it is assumed that patina (blue-green rust) may occur.

Further, an example of calculating the feature amount using RGB data has been shown, but the present invention is not limited to this. For example, XYZ (Yxy) chromaticity coordinates standardized by the International Commission on Illumination may be used. Further, the feature amount and the like may be calculated based on the data in the CMYK format. As described above, the data format of the color coordinates is not limited to RGB data and is arbitrary. In addition, the number of bits for expressing the brightness of each color is arbitrary.

Further, the process of step S2 in the corrosion diagnosis process may be omitted. That is, the control unit 310 does not extract information on a specific primary color from the two-dimensional color image S (RGB image), converts the two-dimensional color image S into grayscale, and then calculates GLCM and various feature quantities. You may. Further, the control unit 310 may binarize the color image S instead of the specific color extracted image in the process of step S4. Further, the control unit 310 calculates the GLCM for the pixel groups arranged in the z and y directions in the grayscaled three-dimensional image C by the function as the calculation unit 312, and based on the calculated GLCM. Each feature amount may be calculated. The evaluation in the depth direction of the steel material 2 may be performed using GLCM for a pixel group including data in the z direction.

The program for executing the corrosion diagnosis process described above is stored in the ROM of the control unit 310 in advance, but may be distributed and provided by a detachable recording medium. Further, the program may be downloaded from another device connected to the corrosion diagnostic apparatus 300. Further, the corrosion diagnosis device 300 may execute each process according to the program by exchanging various data with other devices via a telecommunication network or the like.

[1] The corrosion diagnostic apparatus 300 described above has, as functions of the control unit 310, an image acquisition means (for example, image information acquisition unit 311), a calculation means (for example, calculation unit 312), and a diagnostic means (for example, for example). Diagnostic unit 313) and. The image acquisition means acquires an image obtained by photographing the steel material 2 by the photographing means (for example, the photographing unit 200). The calculation means calculates a simultaneous occurrence matrix (GLCM) for the pixel group constituting the image acquired by the image acquisition means, and calculates a feature amount from the calculated simultaneous occurrence matrix. The diagnostic means diagnoses the corrosion state of the steel material 2 based on the feature amount calculated by the calculation means. The feature amount calculated by the calculation means includes at least one of ASM (Angular Second Moment), Control, Correlation, IDM (Inverse Difference Moment), and Entropy.
According to the corrosion diagnostic apparatus 300, it is only necessary to analyze the image acquired by the image acquisition means, so that the corrosion state of the steel material 2 can be easily diagnosed by the non-destructive / non-contact inspection.

[2] Specifically, the image acquisition means is a two-dimensional image of the steel material 2 (for example, a two-dimensional color image S or a specific color extraction image) as an image (an image obtained by photographing the steel material 2 by the photographing means). Sr) and a three-dimensional image (for example, three-dimensional image C) including information in the depth direction (z direction) with respect to the two-dimensional plane (xy plane) defined by the two-dimensional image may be acquired. .. The calculation means is based on the first feature amount based on the simultaneous occurrence matrix for the pixel groups constituting the two-dimensional image and the simultaneous occurrence matrix for the pixel group in the depth direction of the three-dimensional image as the feature amount. The second feature amount may be calculated. The diagnostic means may diagnose the corrosion state of the steel material 2 based on the first feature amount and the second feature amount.

[3] Further, the calculation means binarizes the two-dimensional image using the threshold value determined by the mode method for the brightness distribution of the two-dimensional image, and uses the binarized two-dimensional image as the basis for the steel material 2. The estimated area of pitting corrosion that has occurred may be calculated. The diagnostic means may diagnose the corrosion state of the steel material 2 based on the feature amount (at least one of the first feature amount and the second feature amount) and the estimated area.

[4] Further, the image acquisition means extracts predetermined specific primary color information (for example, the value of R) from a color image (for example, a two-dimensional color image S) represented by a plurality of primary colors. A two-dimensional image (for example, a specific color extracted image Sr) may be acquired with.

[5] Further, the diagnostic means may diagnose the corrosion state of the steel material 2 based on at least the value of ASM as a feature amount.

[6] The corrosion diagnosis system 100 described above includes a corrosion diagnosis device 300 and an imaging means (for example, an imaging unit 200), and the imaging means uses a pattern irradiation method or a TOF (Time Of Flight) depth sensor. Consists of a 3D camera including.
[7] The corrosion diagnosis method using the corrosion diagnosis device 300 described above targets a step of acquiring an image obtained by photographing the steel material 2 by an imaging means and a pixel group constituting the acquired image. A step of calculating a simultaneous occurrence matrix and calculating a feature amount (at least one of the above five feature amounts) from the calculated simultaneous occurrence matrix, and a step of diagnosing the corrosion state of the steel material 2 based on the calculated feature amount. And.
[8] The program described above causes the computer to function as an image information acquisition means, a calculation means, and a diagnostic means.
According to the corrosion diagnosis system 100, the corrosion diagnosis method, and the program described above, it is only necessary to analyze the image acquired by the image acquisition means. Therefore, the corrosion status of the steel material 2 can be easily checked by non-destructive / non-contact inspection. Can be diagnosed.

In the above description, in order to facilitate the understanding of the present invention, the description of known technical matters has been omitted as appropriate.

100 ... Corrosion diagnosis system 200 ... Imaging unit 300 ... Corrosion diagnosis device 310 ... Control unit 311 ... Image information acquisition unit 312 ... Calculation unit 313 ... Diagnosis unit 314 ... Output unit 320 ... Storage unit 330 ... Operation unit 340 ... Display Part 350 ... Communication part 1 ... Water facility, 2 ... Steel material, 2a ... Diagnosis target area, 3 ... Waterway S ... Two-dimensional color image, Sr ... Specific color extraction image D ... Three-dimensional shape C ... Three-dimensional image

Claims (8)

An image acquisition means for acquiring an image obtained by photographing a steel material by an imaging means,
A calculation means for calculating a simultaneous occurrence matrix for a group of pixels constituting the image acquired by the image acquisition means and calculating a feature amount from the calculated simultaneous occurrence matrix.
A diagnostic means for diagnosing the corrosion state of the steel material based on the feature amount calculated by the calculation means is provided.
The feature amount includes at least one of ASM (Angular Second Moment), Control, Correlation, IDM (Inverse Difference Moment), and Entropy.
Corrosion diagnostic equipment. The image acquisition means acquires, as the image, a two-dimensional image of the steel material and a three-dimensional image including information in the depth direction with respect to the two-dimensional plane defined by the two-dimensional image.
The calculation means targets the first feature amount based on the simultaneous occurrence matrix for the pixel groups constituting the two-dimensional image and the pixel group in the depth direction of the three-dimensional image as the feature amount. Calculate the second feature quantity based on the simultaneous occurrence matrix,
The diagnostic means diagnoses the corrosion state of the steel material based on the first feature amount and the second feature amount.
The corrosion diagnostic apparatus according to claim 1. The calculation means binarizes the two-dimensional image using a threshold value determined by the mode method with respect to the brightness distribution of the two-dimensional image, and occurs in the steel material based on the binarized two-dimensional image. Calculate the estimated area of pitting
The diagnostic means diagnoses the corrosion state of the steel material based on the feature amount and the estimated area.
The corrosion diagnostic apparatus according to claim 2. The image acquisition means acquires the two-dimensional image by extracting information on a specific primary color predetermined from a color image represented by a plurality of primary colors.
The corrosion diagnostic apparatus according to claim 2 or 3. The diagnostic means diagnoses the corrosion state of the steel material based on at least the value of ASM as the feature amount.
The corrosion diagnostic apparatus according to any one of claims 1 to 4. The corrosion diagnostic apparatus according to any one of claims 1 to 5 and the photographing means are provided.
The photographing means comprises a three-dimensional camera including a pattern irradiation type or TOF (Time Of Flight) type depth sensor.
Corrosion diagnostic system. The step of acquiring an image obtained by photographing a steel material by an imaging means,
A step of calculating a simultaneous occurrence matrix for the pixel group constituting the acquired image and calculating a feature amount from the calculated simultaneous occurrence matrix.
A step of diagnosing the corrosion state of the steel material based on the calculated feature amount is provided.
The feature amount includes at least one of ASM (Angular Second Moment), Control, Correlation, IDM (Inverse Difference Moment), and Entropy.
Corrosion diagnostic method. Computer,
An image acquisition means for acquiring an image obtained by photographing a steel material by an imaging means,
A calculation means for calculating a simultaneous occurrence matrix for a group of pixels constituting the image acquired by the image acquisition means and calculating a feature amount from the calculated simultaneous occurrence matrix.
A program that functions as a diagnostic means for diagnosing a corrosion state of the steel material based on the feature amount calculated by the calculation means.
The feature amount includes at least one of ASM (Angular Second Moment), Control, Correlation, IDM (Inverse Difference Moment), and Entropy.
program.

Images