Method and device for evaluating the quality of concrete

Abstract

The application provides a method and device for evaluating the quality of concrete. The method comprises the following steps: obtaining a binary image of a to-be-tested surface of the concrete; dividing the binary image into a first image comprising holes and a second image not comprising holes according to the holes in the binary image; extracting the holes in the combination of micro cracks and holes in the second image to obtain a third image comprising holes; obtaining a fourth image comprising micro cracks according to the second image and the third image; determining a statistical calculation result according to the first image, the third image and the fourth image; and evaluating the quality of the concrete according to the statistical calculation result. The application can accurately evaluate the quality of the concrete.

Description

Technical Field

[0001] This application relates to the field of quality analysis technology, and in particular to a method and apparatus for evaluating the quality of concrete. Background Technology

[0002] Concrete, as a low-cost and easily produced engineering material, is widely used in various harsh environments due to its excellent material properties. However, concrete can suffer internal damage under the influence of external environmental factors, which not only reduces its mechanical properties or durability but also shortens the service life of concrete components.

[0003] Concrete, as a typical porous material, typically exhibits internal damage manifested as changes in pore structure parameters and the initiation and propagation of microcracks. Therefore, quantitative analysis of the pore structure and microcracks within damaged concrete has become an important approach to studying internal concrete damage. The core idea of ​​traditional quantitative analysis methods is to use a microscope to observe the microstructure of the sample. Images of the sample's surface under the microscope are acquired, and objects with aspect ratios within a certain range are identified as pores, while those exceeding this range are identified as microcracks. This allows for quantitative analysis of pores and microcracks, leading to statistical calculations. Based on these statistical results, the degree of internal damage to the concrete can be determined, thereby enabling the evaluation of concrete quality.

[0004] The image also contains a combination of microcracks and pores. The above method cannot accurately identify the combination, resulting in inaccurate statistical calculation results based on pores and microcracks, and thus an inability to accurately evaluate the quality of concrete. Summary of the Invention

[0005] In view of this, this application provides a method and apparatus for evaluating concrete quality, which can accurately evaluate the quality of concrete.

[0006] To achieve the above objectives, this application mainly provides the following technical solutions:

[0007] In a first aspect, this application provides a method for evaluating concrete quality, the method comprising:

[0008] Obtain a binarized image of the concrete surface to be tested;

[0009] Based on the holes in the binarized image, the binarized image is divided into a first image including the holes and a second image excluding the holes;

[0010] The pores are extracted from the combination of microcracks and pores in the second image to obtain a third image including the pores;

[0011] Based on the second image and the third image, a fourth image including microcracks is obtained;

[0012] The statistical calculation results are determined based on the first image, the third image, and the fourth image;

[0013] The quality of the concrete is evaluated based on the statistical calculation results.

[0014] Secondly, this application provides an apparatus for evaluating the quality of concrete, the apparatus comprising:

[0015] The acquisition unit is used to acquire a binarized image of the concrete surface to be tested;

[0016] The segmentation unit is used to divide the binarized image obtained by the acquisition unit into a first image including holes and a second image excluding holes, based on the holes in the binarized image.

[0017] The first extraction unit is used to extract pores from the combination of microcracks and pores in the second image divided by the division unit, so as to obtain a third image including pores.

[0018] The second extraction unit is used to obtain a fourth image including microcracks based on the second image and the third image determined by the first extraction unit.

[0019] The first determining unit is used to determine the statistical calculation result based on the first image obtained by the segmentation unit, the third image obtained by the extraction unit, and the fourth image;

[0020] The second determining unit is used to evaluate the quality of the concrete based on the statistical calculation results determined by the first determining unit.

[0021] Thirdly, this application provides a terminal for running a program, wherein the terminal executes the method for evaluating concrete quality described in the first aspect.

[0022] Fourthly, this application provides a storage medium for storing a computer program, wherein the computer program, when running, controls the device on which the storage medium is located to execute the method for evaluating concrete quality as described in the first aspect.

[0023] By employing the above technical solution, this application provides a method and apparatus for evaluating concrete quality. The method involves extracting pores from the combination of microcracks and pores in a second image to obtain a third image including the pores. Based on the second and third images, a fourth image including the microcracks is obtained. Therefore, since the fourth image no longer includes pores or pores within the combination of microcracks and pores, it only includes individually existing microcracks and microcracks within the combination. This ensures that microcracks within the combination are not ignored, allowing for accurate statistical calculation of microcracks. Simultaneously, the third image only includes pores within the combination, and the first image only includes individually existing pores. When statistically calculating pores based on the first and third images, pores within each combination are not ignored, allowing for accurate statistical calculation of pores. Thus, the quality of the concrete can be accurately evaluated based on the accurate statistical calculation results.

[0024] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, the following are specific embodiments of this application. Attached Figure Description

[0025] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0026] Figure 1 This is a flowchart illustrating a method for evaluating concrete quality disclosed in this application;

[0027] Figure 2 This is a flowchart illustrating another method for evaluating concrete quality disclosed in this application.

[0028] Figure 3 This is a schematic diagram of an RGB image disclosed in this application;

[0029] Figure 4 This is a schematic diagram of a binarized image disclosed in this application;

[0030] Figure 5 This is a schematic diagram of a first image disclosed in this application;

[0031] Figure 6 This is a schematic diagram of a fourth image disclosed in this application;

[0032] Figure 7This is a schematic diagram of the structure of a device for evaluating concrete quality disclosed in this application;

[0033] Figure 8 This is a structural schematic diagram of another device for evaluating concrete quality disclosed in this application. Detailed Implementation

[0034] Exemplary embodiments of the present application will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present application are shown in the drawings, it should be understood that the present application may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this application will be thorough and complete, and will fully convey the scope of the present application to those skilled in the art.

[0035] Concrete, as a typical porous material, typically exhibits internal damage manifested as changes in pore structure parameters and the initiation and propagation of microcracks. Therefore, quantitative analysis of the pore structure and microcracks within damaged concrete has become an important approach to studying internal concrete damage. The core idea of ​​traditional quantitative analysis methods is to use a microscope to observe the microstructure of the sample. Images of the sample's surface under the microscope are acquired, and objects with aspect ratios within a certain range are identified as pores, while those exceeding this range are identified as microcracks. This allows for quantitative analysis of pores and microcracks, determining the statistical results of the concrete. Based on these statistical results, the degree of internal damage to the concrete can be determined, thereby enabling the evaluation of concrete quality.

[0036] The image also contains a combination of microcracks and pores, meaning that the microcracks are connected to the pores. However, the method described above would directly ignore the microcracks connected to the pores, or ignore the pores connected to the microcracks, resulting in inaccurate statistical calculations based on pores and microcracks, and thus failing to accurately evaluate the quality of the concrete.

[0037] To address the aforementioned problems, this application provides a method for evaluating concrete quality. This method can accurately evaluate the quality of concrete, and is not limited thereto. The specific execution steps are as follows: Figure 1 As shown, it includes:

[0038] Step 101: Obtain a binarized image of the concrete surface to be tested.

[0039] Step 102: Based on the holes in the binarized image, divide the binarized image into a first image including the holes and a second image excluding the holes.

[0040] In the specific implementation of this step, the holes in the binarized image are extracted to obtain a first image including the holes, and the image after the holes are extracted is determined as a second image excluding the holes.

[0041] Step 103: Extract the pores from the combination of microcracks and pores in the second image to obtain a third image including the pores.

[0042] Step 104: Based on the second image and the third image, obtain a fourth image including the microcracks.

[0043] The fourth image includes all the microcracks in the binarized image.

[0044] Step 105: Determine the statistical calculation results based on the first image, the third image, and the fourth image.

[0045] The statistical calculation results include those based on the holes in the first and third images, and those based on the microcracks in the fourth image.

[0046] Step 106: Evaluate the quality of the concrete based on the statistical calculation results.

[0047] In this embodiment, pores are extracted from the combination of microcracks and pores in the second image to obtain a third image including pores. Based on the second and third images, a fourth image including microcracks is obtained. Therefore, since the fourth image no longer includes pores or pores within the combination of microcracks and pores, it only includes individual microcracks and microcracks within the combination. This ensures that microcracks within the combination are not ignored, allowing for accurate statistical calculation of microcracks. Simultaneously, the third image only includes pores within the combination, and the first image only includes individual pores. When performing statistical calculations on pores based on the first and third images, pores within each combination are not ignored, allowing for accurate statistical calculation of pores. Thus, the quality of concrete can be accurately evaluated based on the accurate statistical calculation results.

[0048] Furthermore, in Figure 1 Based on the embodiments shown, this application also provides a method for evaluating concrete quality, which is used for... Figure 1 The steps involved are described in detail, and the specific steps are as follows: Figure 2 As shown, it includes:

[0049] Step 201: Obtain a digital RGB image of the concrete surface to be tested.

[0050] In this specific implementation step, a concrete specimen is first obtained and cut to expose the internal microstructure of the concrete, resulting in a rough test surface. To expose the microstructural features on the rough test surface, it can be polished with a grinding wheel to obtain a smooth surface. The phosphor is uniformly dispersed in anhydrous acetone or alcohol, and a sufficient amount of the suspension is poured onto the smooth test surface. The sample is then placed in a fume hood, and removed after the anhydrous acetone has completely evaporated. The silica gel on the sample surface is cleaned using a flat scraper. The test surface is then irradiated with an ultraviolet lamp, and the central area is photographed using a CCD camera to obtain digital RGB images of the test surface with different fluorescence intensities, such as... Figure 3 As shown.

[0051] For example, when concrete is used as a cement mortar specimen formed under test conditions, the specific steps for obtaining a digital RGB image of the cement mortar specimen are as follows: (1) Cut the cement mortar specimen to expose the internal microstructure and obtain a rough test surface. (2) Polish the rough test surface sequentially with grinding discs of 50 mesh, 300 mesh, 500 mesh, 1500 mesh and 2500 mesh. Continuously rinse the surface with running water throughout the process to obtain a smooth and flat test surface, at which point the microstructural features on the test surface can be exposed. (3) Surround the sample with waterproof tape, ensuring that the tape height exceeds the test surface by 15 mm. Disperse the phosphor evenly in anhydrous acetone, where the phosphor particle size is 1 μm and the ratio of phosphor to silica gel is 1:10. (4) Pour a sufficient amount of suspension onto the test surface, ensuring that the suspension height is 5 mm. Place the sample in a fume hood and remove it after all anhydrous acetone has evaporated. Cover the surface with liquid transparent silicone with a viscosity of 2000 cps and cure it at room temperature. (5) Remove the sample and clean the silicone off the surface with a flat scraper. Irradiate a 50 mm × 50 mm area in the center of the surface to be tested with a 365 nm ultraviolet lamp. Record the surface to be tested with a CCD camera to obtain digital RGB images of the surface to be tested with different fluorescence intensities. The resolution of the image is 7680 × 7680, indicating that each pixel in the image represents an actual length of 6.36 μm.

[0052] When taking a concrete specimen formed under a single-sided salt-freezing test as an example, the specific steps for obtaining a digital RGB image of the concrete specimen formed under a single-sided salt-freezing test are as follows: (1) Cut the concrete specimen to expose the internal microstructure of the concrete and obtain a rough test surface. (2) Polish the rough test surface in sequence with grinding discs of fineness of 50 mesh, 150 mesh, 300 mesh, 500 mesh, 800 mesh, 1500 mesh and 3000 mesh. Continuously rinse the surface with running water throughout the process to obtain a smooth test surface. At this time, features such as pores and microcracks on the test surface can be exposed. (3) Surround the sample with waterproof tape, ensuring that the tape height exceeds the test surface by 15 mm. Disperse the fluorescent powder evenly in anhydrous ethanol, wherein the fluorescent powder particle size is 5 μm and the ratio of fluorescent powder to silica gel is 1:20. (4) Pour a sufficient amount of suspension onto the test surface, ensuring that the suspension height is 5 mm. Place the sample in a fume hood and remove it after all the anhydrous ethanol has evaporated. Cover the surface with liquid transparent silicone with a viscosity of 1500 cps and cure at room temperature for 5 hours. (5) Remove the sample and clean the silicone off the surface with a flat scraper. Irradiate a 60 mm × 60 mm area in the center of the surface under test with a 365 nm ultraviolet lamp. Record the surface under test with a CCD camera to obtain digital RGB images of the surface under test with different fluorescence intensities. The resolution of the image is 4724 × 4724, indicating that each pixel in the image represents an actual length of 12.7 μm.

[0053] When taking the cement paste specimen formed under the test conditions as an example, the specific steps for obtaining the digital RGB image of the concrete specimen formed under the single-sided salt freezing test are as follows: (1) Cut the concrete specimen to expose the internal microstructure of the concrete and obtain a rough test surface. (2) Polish the rough test surface with grinding discs of 300 mesh, 1000 mesh and 3000 mesh in sequence. Continuously rinse the surface with running water throughout the process to obtain a smooth and flat test surface, at which point the microstructural features on the test surface can be exposed. (3) Surround the sample with waterproof tape, ensuring that the tape height exceeds the test surface by 15 mm. Disperse the phosphor evenly in anhydrous acetone, where the phosphor particle size is 1 μm and the ratio of phosphor to silica gel is 1:6. (4) Pour a sufficient amount of suspension onto the test surface, ensuring that the suspension height is 5 mm. Place the sample in a fume hood, and after all the anhydrous acetone has evaporated, remove the sample, cover the surface with liquid transparent silica gel with a viscosity of 800 cps, and cure at room temperature. (5) Take out the sample, clean the silicone on the surface with a flat spatula, irradiate the central 40mm×40mm area of ​​the surface to be tested with a 365nm ultraviolet lamp, record the area with a CCD camera, and obtain digital RGB images of the surface to be tested with different fluorescence intensities. The resolution of the image is 7680×7680, indicating that each pixel in the image represents an actual length of 6.36μm.

[0054] Step 202: Create a grayscale value frequency distribution histogram based on the grayscale value of each pixel in the RGB image.

[0055] In the specific implementation of this step, the grayscale value of each pixel in the RGB image is first determined, and the number of identical grayscale values ​​in each pixel of the RGB image is counted to create a grayscale value frequency distribution histogram.

[0056] Step 203: In the gray value frequency distribution histogram, determine the gray value corresponding to the first peak and the gray value corresponding to the second peak.

[0057] Since the test surface in step 201 is covered with a liquid mixed with fluorescent dye, the pores and microcracks on the test surface, being filled with fluorescent dye, appear as bright fluorescent colors in the image, while the denser substrate, not being penetrated by the fluorescent dye, appears as darker colors. An RGB image is composed of pixels corresponding to pores, microcracks, and the substrate, respectively. Therefore, in the grayscale frequency distribution histogram obtained based on the RGB image, there are generally two peaks: one corresponding to the substrate and the other corresponding to the pores and microcracks.

[0058] Step 204: Based on the gray values ​​corresponding to the first peak and the second peak, perform binarization processing on all pixels in the RGB image to obtain a binarized image of the surface to be tested.

[0059] In the specific implementation of this step, the grayscale value corresponding to the first peak and the average grayscale value corresponding to the second peak are determined; in the RGB image, the color of the pixels with grayscale values ​​less than or equal to the average value is set as the first color, and the color of the pixels with grayscale values ​​greater than the average value is set as the second color.

[0060] Furthermore, the grayscale value P corresponding to the first peak and the grayscale value C corresponding to the second peak are extracted. The average grayscale value T of the two values ​​is calculated using the formula T = (C + P) / 2. Pixels with grayscale values ​​less than or equal to the average grayscale value T are set to black, and pixels with grayscale values ​​greater than the average grayscale value T are set to white. This converts the RGB image into a binarized image. Specifically... Figure 4 As shown, the black area represents the matrix, while the white area represents the non-matrix areas, namely the areas containing pores, microcracks, and assemblies.

[0061] Step 205: Obtain the area and perimeter of all objects in the binarized image.

[0062] In this specific implementation, the area of ​​each object in the binarized image can be calculated based on the number of pixels corresponding to each object and the area corresponding to each pixel. The perimeter of each object in the binarized image can be calculated based on the number of pixels corresponding to each object and the side length of each pixel. Other methods for determining the area and perimeter of objects in a binarized image can also be used in this step, and are not limited to these methods here.

[0063] Step 206: Calculate the roundness of each object based on its area and perimeter.

[0064] In this specific implementation, the roundness of each object is calculated based on its area S, perimeter L, and a calculation formula. The calculation formula is as follows:

[0065] Step 207: Define the object whose roundness is within the preset range as a hole.

[0066] In the specific implementation of this step, objects with a roundness of 0.785≤R≤1.000 are defined as holes.

[0067] Step 208: In the binarized image, the holes are extracted to obtain a first image including the holes, and the remaining image after the holes are extracted is determined as a second image excluding the holes.

[0068] In this specific implementation, the binarized image includes holes, microcracks, and combinations of holes and microcracks. Thus, when only the holes are extracted from the binarized image, the resulting first image only includes the holes, as shown below. Figure 5 As shown, the remaining image after extracting the pores only includes the combination of microcracks and pores, that is, the second image only includes the combination of microcracks and pores.

[0069] Step 209: Based on the preset structure, erosion is performed on all objects in the second image to obtain the fifth image.

[0070] The preset structure is a graphic composed of several pixels. Generally, the width of a microcrack is less than 50mm. In order to erode the microcracks in the second image and the composite based on the structure, the width of the structure is generally set to (25*N)mm. After using the structure to erode the object in the second image N times, all the microcracks in the second image can be eroded away to obtain the fifth image.

[0071] In this specific implementation, the number of pixels included in the structure differs for images of different resolutions. Therefore, during image recognition, the size and shape of the structure are pre-stored, and the number of pixels included in the structure is determined based on the size and shape of the structure and the resolution of the current image, thus generating the structure. In this way, after using this structure to perform N erosions on the object in the second image, the fifth image is obtained.

[0072] Step 210: Based on the preset structure, the objects in the fifth image are restored to obtain a third image including the hole.

[0073] In this specific implementation, since all microcracks in the second image have been etched away, the objects in the fifth image are all holes. Since step 210 also etched the holes in the second image, the objects in the fifth image are restored based on a preset structure, resulting in a third image that only includes the holes.

[0074] Step 211: Delete the content in the second image that overlaps with the third image to obtain a fourth image including microcracks.

[0075] In this specific implementation, the content overlapping with the third image in the second image is deleted, resulting in a fourth image that only includes microcracks, as shown below. Figure 6 As shown.

[0076] Step 212: Overlay the first image and the third image to obtain a fifth image that includes all the holes.

[0077] Step 213: Determine the statistical calculation results based on the fourth and fifth images.

[0078] In this specific implementation, the microcrack skeleton in the microcrack in the fourth image can be extracted, the total number of microcracks n can be counted, and the total length L of the microcracks can be calculated according to the following formula. q Average width L d The fractal dimension d of microcracks L The formulas required in the above calculation process include:

[0079]

[0080]

[0081] lg n EP =k2 lg L min +C0′

[0082] dL=|k2|

[0083] Among them, L q Let A be the total length of all microcracks, n be the total number of microcracks, i be the i-th microcrack among n microcracks, m be the number of pixels in the i-th microcrack, and j be the j-th pixel in the i-th microcrack. q L represents the total area of ​​all microcracks. min n is the minimum length of the microcrack. EP C0′ represents the equivalent number of microcracks replaced by microcracks of minimum length, and is a constant.

[0084] Meanwhile, in the fifth image, the number of holes is counted, and the area A of each hole is calculated according to the following formula. p Aperture D p The average aperture D of all holes mean The fractal dimension d of the hole p The formulas required for the above calculation process include:

[0085]

[0086]

[0087] lg N Ep =k1lg D min +C0

[0088] d p =|k1|

[0089] Among them, D P Let A be the diameter of the P-th hole, K be the total number of holes in the image, and A be the diameter of the hole. P Let D be the area of ​​the P-th hole.min For the minimum aperture, N Ep C0 represents the equivalent number of holes of different diameters after being replaced by the smallest diameter hole, and is a constant.

[0090] It should be noted that the fractal dimension is generally calculated using the box dimension counting method, which requires defining the size of the "box," i.e., the minimum aperture D in this application. min The box-counting method works by filling the object under test with boxes, and obtaining the maximum number of boxes required to fill the object, denoted as N. ep1 Change the size of the box and count again to get N. ep2 The least squares method is used to perform a linear fit on the two counts, and the absolute value of the slope of the fitted line is the fractal dimension.

[0091] Step 214: Evaluate the quality of the concrete based on the statistical calculation results.

[0092] The average pore diameter and pore size distribution of concrete can both reflect its density. For example, the smaller the average pore diameter in concrete, the higher its density. Conversely, the larger the average pore diameter, the lower its density. The fractal dimension of the pores reflects the complexity of the pore structure, ranging from 1 to 2. A fractal dimension closer to 1 indicates a smoother pore structure and a more regular pore shape; a fractal dimension closer to 2 indicates a coarser pore structure and a more irregular pore shape.

[0093] The number and length of microcracks can reflect the quality of concrete. For example, the more numerous and longer the microcracks, the worse the quality of the concrete. Conversely, the fewer and shorter the microcracks, the better the quality of the concrete. The fractal dimension of microcracks indicates their tortuosity; a higher value indicates a more complex microcrack network in the concrete, making it more susceptible to damage. Greater connectivity of microcracks indicates more intense moisture migration in the concrete, accelerating freeze-thaw damage and necessitating repair or maintenance.

[0094] In the specific implementation of this step, different methods are used to evaluate the quality of concrete in different states. For example, for freshly hardened concrete, since microcracks are damage caused by environmental factors, concrete that has not undergone environmental effects can be considered as not yet exhibiting microcracks. The number of pores, average pore diameter, and fractal dimension in the concrete can be determined solely based on the first and third images. The quality of the concrete is then evaluated based on these parameters. Specifically, the density of the concrete is evaluated based on the pore data and average pore diameter. The smoothness of the concrete is evaluated based on the fractal dimension.

[0095] For example, in hardened concrete, when pores smaller than 500 μm account for more than 80% of the total pores, it indicates good concrete density and resistance to internal damage from freeze-thaw cycles. Pores larger than 1000 μm are considered defects in the concrete; the higher the proportion of such pores, the worse the concrete density, requiring adjustments to the mix design or improvements to the molding process. A high fractal dimension (generally greater than 1.5) indicates poor pore morphology, necessitating further adjustments to the mix design.

[0096] In practice, besides freshly formed and hardened concrete, there is also concrete that has been exposed to the environment for a period of time, i.e., concrete that has undergone environmental effects. For this type of concrete, since damage has already occurred under environmental influences, the length, average width, and fractal dimension of microcracks in the concrete can be determined based on the fourth image. Furthermore, these data can be used to determine the degree of damage to the concrete and thus evaluate its quality. Of course, when evaluating the quality of concrete based on its degree of damage, the number of pores, average pore diameter, and fractal dimension can also be used to simultaneously evaluate the quality of the concrete.

[0097] For example, in concrete that has undergone freeze-thaw cycles, the greater the number and length of microcracks, the worse the concrete's freeze-thaw resistance. Higher connectivity of microcracks indicates more intense moisture migration within the concrete, accelerating freeze-thaw damage and necessitating repair or maintenance. The fractal dimension of microcracks indicates their tortuosity; a higher value indicates a more complex microcrack network, making further damage more likely. For concrete unaffected by environmental or mechanical loads, a greater number and length of internal microcracks indicates greater shrinkage deformation and more severe water loss, requiring mix design adjustments to mitigate shrinkage. The aspect ratio of microcracks can determine the primary direction of shrinkage deformation in the concrete, aiding in identifying weak areas of damage.

[0098] In addition to damage caused by environmental factors, concrete subjected to mechanical loads will also suffer damage under mechanical action. Therefore, based on the fourth image, the length, average width, and fractal dimension of microcracks in concrete can be determined. Furthermore, these data can be used to determine the degree of damage to the concrete and to evaluate its quality.

[0099] In this embodiment, after acquiring a digitized RGB image of the concrete surface to be tested, directly setting a grayscale threshold and setting pixels above the threshold to black and pixels below the threshold to white can lead to missing information due to varying brightness levels in different images, rendering subsequent analysis unusable. This application, however, constructs a grayscale frequency distribution histogram based on the grayscale value of each pixel. Since the pixels in the RGB image are divided into two parts—pixels corresponding to the background color and pixels corresponding to non-background colors—two peaks are formed in the histogram: a first peak and a second peak. The average grayscale value determined based on the grayscale values ​​corresponding to the first and second peaks is then used as the optimal segmentation threshold for the RGB image, ensuring the accuracy of subsequent analysis.

[0100] In this application, to ensure that the combination of pores and microcracks does not affect the statistical calculations related to pores and microcracks, the pores are first extracted from the binarized image to obtain a first image including the pores. The remaining image after pore extraction is then designated as the second image. Since the second image does not include pores, it only includes the combination of microcracks and pores. To identify the combination in the second image, segmentation positions can be found first, and the objects at these positions can be designated as the combination. This allows for segmentation based on the segmentation positions, resulting in multiple segmented objects. The pores are then extracted from these segmented objects to obtain a third image including the pores. The remaining image after pore extraction is designated as the fourth image excluding the pores. The resulting fourth image only includes microcracks, while the first and third images only include pores. This allows for accurate statistical calculations of microcracks and pores in concrete, thereby enabling accurate evaluation of concrete quality.

[0101] Furthermore, in Figure 1 Based on the illustrated embodiment, when a combination of microcracks and pores is divided into one pore and multiple microcracks, some microcracks that were originally one may be split into two due to the division. Statistical calculations based on these two microcracks may lead to inaccurate data. Therefore, it is necessary to identify the two microcracks that were originally one and restore them to a single microcrack. The specific determination method is as follows: determine the division position corresponding to each microcrack; for each microcrack, determine the slope of the line connecting the division position of the microcrack to the division positions of other microcracks; compare the slope of each line with the slope of the microcrack; if there is a line where the difference between the slope of the line and the slope of the microcrack is less than a preset value, then the two microcracks connected by that line are restored to a single microcrack.

[0102] Furthermore, as a response to the above Figure 1-6 The implementation of the method embodiment shown in this application provides a device for evaluating concrete quality, which can accurately evaluate the quality of concrete. The embodiment of this device corresponds to the foregoing method embodiment. For ease of reading, this embodiment will not repeat the details of the foregoing method embodiment, but it should be understood that the device in this embodiment can correspondingly implement all the contents of the foregoing method embodiment. Specifically, as shown... Figure 7 As shown, the device includes:

[0103] The first acquisition unit 701 is used to acquire a binarized image of the concrete surface to be tested.

[0104] The segmentation unit 702 is used to divide the binarized image into a first image including holes and a second image excluding holes based on the holes in the binarized image obtained by the acquisition unit 701.

[0105] The first extraction unit 703 is used to extract holes from the combination of microcracks and holes in the second image divided by the division unit 702, so as to obtain a third image including holes.

[0106] The second extraction unit 704 is used to obtain a fourth image including microcracks based on the second image and the third image determined by the first extraction unit 703.

[0107] The first determining unit 705 is used to determine the statistical calculation result based on the first image obtained by the dividing unit 702, the third image obtained by the extraction unit 704, and the fourth image.

[0108] The second determining unit 706 is used to evaluate the quality of the concrete based on the statistical calculation results determined by the first determining unit 705.

[0109] Furthermore, such as Figure 8 As shown, before acquiring a binarized image of the concrete surface to be tested, the device further includes a second acquisition unit 707, which is used for:

[0110] Acquire a digital RGB image of the concrete surface to be tested;

[0111] Draw a grayscale value frequency distribution histogram based on the grayscale value of each pixel in the RGB image;

[0112] In the grayscale value frequency distribution histogram, determine the grayscale value corresponding to the first peak and the grayscale value corresponding to the second peak;

[0113] Based on the gray values ​​corresponding to the first peak and the second peak, all pixels in the RGB image are binarized to obtain a binarized image of the surface to be tested.

[0114] Furthermore, such as Figure 8 As shown, the second acquisition unit 707 is also used for

[0115] Determine the average gray value of the gray values ​​corresponding to the first peak and the gray values ​​corresponding to the second peak.

[0116] In the RGB image, the color of pixels with grayscale values ​​less than or equal to the average grayscale value is set as the first color, and the color of pixels with grayscale values ​​greater than the average grayscale value is set as the second color.

[0117] Furthermore, such as Figure 8 As shown, the partitioning unit 702 further includes:

[0118] The acquisition module 7021 is used to acquire the area and perimeter of all objects in the binarized image;

[0119] The calculation module 7022 is used to calculate the roundness of each object based on the area and perimeter of each object obtained by the acquisition module 7021;

[0120] The first determining module 7023 is used to determine an object whose roundness calculated by the calculation module 7022 is within a preset range as a hole;

[0121] Extraction module 7024 is used to extract the holes determined by the first determination module 7023 in the binarized image to obtain a first image including the holes, and to determine the remaining image after extracting the holes as a second image excluding the holes.

[0122] Furthermore, such as Figure 8 As shown, the first determining unit 705 further includes:

[0123] The overlay module 7051 is used to overlay the first image and the third image to obtain a fifth image including all the holes;

[0124] The second determining module 7052 is used to determine the statistical calculation result based on the fourth image and the fifth image obtained by the overlay module 7051.

[0125] Furthermore, such as Figure 8 As shown, the first extraction unit 703 includes:

[0126] The erosion module 7031 is used to erode all objects in the second image based on a preset structure to obtain a fifth image;

[0127] The recovery module 7032 is used to recover the object in the fifth image obtained by the corrosion unit 7031 based on a preset structure, so as to obtain a third image including the hole.

[0128] Furthermore, such as Figure 8 As shown, the second extraction unit 704 is also used for:

[0129] The content in the second image that overlaps with the third image is deleted to obtain a fourth image that includes microcracks.

[0130] Furthermore, embodiments of this application also provide a processor for running a program, wherein the program executes the above-described... Figure 1-6 The method for evaluating concrete quality described herein.

[0131] Furthermore, embodiments of this application also provide a storage medium for storing a computer program, wherein the computer program, when running, controls the device where the storage medium is located to execute the above-described... Figure 1-6 The method for evaluating concrete quality described herein.

[0132] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0133] It is understood that the relevant features in the above methods and apparatus can be referenced interchangeably. Furthermore, the terms "first," "second," etc., in the above embodiments are used to distinguish between embodiments and do not represent the superiority or inferiority of any particular embodiment.

[0134] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0135] The algorithms and displays provided herein are not inherently related to any particular computer, virtual system, or other device. Various general-purpose systems can also be used in conjunction with the teachings herein. The required structure for constructing such systems is apparent from the above description. Furthermore, this application is not directed to any particular programming language. It should be understood that the content of this application described herein can be implemented using various programming languages, and the above description of specific languages ​​is for the purpose of disclosing the best mode of implementation of this application.

[0136] In addition, the memory may include non-permanent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0137] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0138] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0139] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0140] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0141] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0142] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0143] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0144] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0145] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0146] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A method for evaluating concrete quality, characterized in that, The method includes: Obtain a binarized image of the concrete surface to be tested; Based on the holes in the binarized image, the binarized image is divided into a first image including the holes and a second image excluding the holes. This includes obtaining the area and perimeter of all objects in the binarized image; calculating the roundness of each object based on its area and perimeter; identifying objects with roundness within a preset range as holes; extracting the holes from the binarized image to obtain the first image including the holes; and identifying the remaining image after hole extraction as the second image excluding the holes. Extracting pores from the combination of microcracks and pores in the second image to obtain a third image including pores includes: eroding all objects in the second image based on a preset structure to obtain a fifth image; and restoring the objects in the fifth image based on the preset structure to obtain the third image including pores. Based on the second image and the third image, a fourth image including microcracks is obtained, including: deleting the content in the second image that overlaps with the third image to obtain the fourth image including microcracks; The statistical calculation results are determined based on the first image, the third image, and the fourth image; The quality of the concrete is evaluated based on the statistical calculation results.

2. The method according to claim 1, characterized in that, Before acquiring a binarized image of the concrete surface to be tested, the method further includes: Acquire a digital RGB image of the concrete surface to be tested; Draw a grayscale value frequency distribution histogram based on the grayscale value of each pixel in the RGB image; In the grayscale value frequency distribution histogram, determine the grayscale value corresponding to the first peak and the grayscale value corresponding to the second peak; Based on the gray values ​​corresponding to the first peak and the second peak, all pixels in the RGB image are binarized to obtain a binarized image of the surface to be tested.

3. The method according to claim 2, characterized in that, The step of binarizing all pixels in the RGB image based on the gray values ​​corresponding to the first peak and the second peak to obtain a binarized image of the surface to be tested includes: Determine the average gray value of the gray values ​​corresponding to the first peak and the gray values ​​corresponding to the second peak. In the RGB image, the color of pixels with grayscale values ​​less than or equal to the average grayscale value is set as the first color, and the color of pixels with grayscale values ​​greater than the average grayscale value is set as the second color.

4. The method according to claim 1, characterized in that, The step of determining the statistical calculation result based on the first image, the third image, and the fourth image includes: The first image and the third image are superimposed to obtain a fifth image that includes all the holes; The statistical calculation results are determined based on the fourth and fifth images.

5. A device for evaluating the quality of concrete, characterized in that, The device includes: The acquisition unit is used to acquire a binarized image of the concrete surface to be tested; The segmentation unit is used to divide the binarized image obtained by the acquisition unit into a first image including holes and a second image excluding holes, based on the holes in the binarized image. The partitioning unit further includes: an acquisition module for acquiring the area and perimeter of all objects in the binarized image; a calculation module for calculating the circularity of each object based on the area and perimeter of each object acquired by the acquisition module; a first determination module for determining objects whose circularity calculated by the calculation module is within a preset range as holes; and an extraction module for extracting the holes determined by the first determination module from the binarized image to obtain a first image including the holes, and determining the remaining image after extracting the holes as a second image excluding the holes. The first extraction unit is used to extract pores from the combination of microcracks and pores in the second image divided by the division unit, so as to obtain a third image including pores. The first extraction unit includes: an erosion module, used to erode all objects in the second image based on a preset structure to obtain a fifth image; and a recovery module, used to recover objects in the fifth image obtained by the erosion module based on a preset structure to obtain a third image including holes. The second extraction unit is used to obtain a fourth image including microcracks based on the second image and the third image determined by the first extraction unit. The second extraction unit is further configured to: delete the content in the second image that overlaps with the third image to obtain a fourth image including microcracks; The first determining unit is used to determine the statistical calculation result based on the first image obtained by the segmentation unit, the third image obtained by the extraction unit, and the fourth image; The second determining unit is used to evaluate the quality of the concrete based on the statistical calculation results determined by the first determining unit.

6. A terminal, characterized in that, The terminal is used to run a program, wherein the terminal executes the method for evaluating concrete quality as described in any one of claims 1-4.

7. A storage medium, characterized in that, The storage medium is used to store a computer program, wherein when the computer program is executed, it controls the device where the storage medium is located to perform the method for evaluating concrete quality as described in any one of claims 1-4.

Images