A method and system for detecting impermeability of polyurethane materials

Abstract

The present application relates to the technical field of image detection of impermeability materials, and specifically to a method and system for detecting impermeability of polyurethane materials, the method comprising: obtaining the test image of a test piece coated with polyurethane material at each moment during the process of impermeability detection; obtaining the light spot regular coefficient according to the area of ​​each light spot area in the test image of the test piece at each moment, the uniformity of the grayscale distribution inside it, and the difference in shape characteristics between each light spot area and all other light spot areas; obtaining the material reflection coefficient of each light spot area by combining the intensity of the grayscale change trend from the edge to the center of each light spot area, the similarity of the contour shape of each light spot area with all other light spot areas, and the light spot regular coefficient; obtaining the impermeability detection result of the test piece according to the threshold analysis of the material reflection coefficient of all light spot areas. The present application can improve the accuracy of impermeability detection of polyurethane materials.

Description

Technical Field

[0001] The present application relates to the technical field of image detection of impermeability materials, and in particular to a method and system for detecting the impermeability of polyurethane materials. Background Art

[0002] Polyurethane material is a polymer compound formed by the reaction of polyisocyanate and polyhydroxy compound. Polyurethane material is widely used in many fields of national economy due to its excellent properties, such as wear resistance, high mechanical strength, high elasticity, aging resistance, corrosion resistance, impermeability, etc. Among them, polyurethane material is usually used as a coating and applied to the surface of concrete as a protective layer of concrete to improve its impermeability due to its good impermeability.

[0003] For the step-by-step pressure test of polyurethane materials, a camera is usually used to collect image data on the surface of the specimen, and the water seepage on the surface of the specimen is analyzed to determine the water seepage level. When the polyurethane material is covered on the surface of the concrete specimen, since the polyurethane material is usually smooth after solidification, it is easy to reflect light under ambient light, thus forming a light spot on the surface of the specimen. When water seepage occurs on the surface of the specimen, water droplets or accumulated water on the surface of the specimen will also reflect light under ambient light to form a light spot. In the collected image, the two light spots are relatively similar, making it difficult to distinguish the actual water seepage, which leads to errors in judging the water seepage resistance of the polyurethane material and affects the accuracy of the test. Summary of the invention

[0004] In order to solve the above technical problems, the purpose of this application is to provide a method and system for detecting the impermeability of polyurethane materials. The technical solutions adopted are as follows:

[0005] In a first aspect, an embodiment of the present application provides a method for detecting the impermeability of a polyurethane material, the method comprising the following steps:

[0006] S1, obtaining the test image of the test piece coated with polyurethane material at each moment during the anti-permeability test process;

[0007] S2, threshold analysis is performed on the test image of the specimen at each moment to obtain each light spot area, and the natural reflection coefficient of each light spot area is obtained according to the area of ​​each light spot area and the uniformity of the grayscale distribution inside it; the reflection characteristic coefficient of each light spot area is obtained according to the shape characteristic difference and distance between each light spot area and all other light spot areas; the light spot conventional coefficient is obtained by combining the natural reflection coefficient and the reflection characteristic coefficient of each light spot area;

[0008] S3, according to the intensity of the grayscale change trend from the edge to the center of each light spot area, the internal complexity of each light spot area is obtained; according to the similarity of the contour shape of each light spot area with all other light spot areas, the morphological regularity of each light spot area is obtained; the morphological regularity, internal complexity and light spot regularity coefficient of each light spot area are combined to obtain the material reflection coefficient of each light spot area;

[0009] S4, obtaining the anti-permeability test result of the test piece according to the threshold analysis of the material reflection coefficient of all the light spot areas.

[0010] Furthermore, the method for obtaining the natural reflection coefficient of each light spot area includes:

[0011] Perform threshold segmentation on the test piece detection image at each moment to obtain a binary image of the test piece surface; obtain all closed contours in the binary image of the test piece surface; record the inner area of ​​each closed contour in the test piece detection image as a light spot area;

[0012] The grayscale value variance of all pixels in each light spot area is calculated; the total number of pixels contained in each light spot area is counted; and the sum of the total number of pixels and the grayscale value variance is used as the natural reflection coefficient of each light spot area.

[0013] Furthermore, the reflection characteristic coefficient of each light spot area is obtained according to the shape characteristic difference and distance between each light spot area and all other light spot areas, including:

[0014] For each spot area, obtain the distance between the two pixel points with the largest and smallest horizontal coordinates in the spot area, and record it as the horizontal distance; obtain the distance between the two pixel points with the largest and smallest vertical coordinates in the spot area, and record it as the vertical distance; record the two pixel points corresponding to the maximum values ​​of the horizontal distance and the vertical distance as direction points; connect the two direction points to obtain the direction line of the spot area;

[0015] For any two light spot areas, the minimum angle between the extension lines of the direction lines of the two light spot areas is taken as the tilt direction angle between the two light spot areas;

[0016] According to the tilt direction angle and distance between each light spot area and all other light spot areas, the reflection characteristic coefficient of each light spot area is obtained.

[0017] Further, the step of obtaining the reflection characteristic coefficient of each light spot area according to the tilt direction angle and distance between each light spot area and all other light spot areas includes: recording the reflection characteristic coefficient of the i-th light spot area as ; ;in, is the average value of the tilt direction angle between the i-th light spot area and all other light spot areas; is the mean distance between the i-th spot area and the center points of all other spot areas.

[0018] Furthermore, the method for obtaining the conventional coefficient of the light spot includes: the conventional coefficient of each light spot area is the product of the natural reflection coefficient of each light spot area and the reflection characteristic coefficient.

[0019] Furthermore, the method for obtaining the internal complexity of each light spot area includes:

[0020] For each spot area, obtain the line between the pixel point with the smallest horizontal coordinate on the edge of the spot area and the center point of the spot area, which is recorded as the brightness distribution line of the spot area; starting from the pixel point with the smallest horizontal coordinate on the edge of the spot area, arrange the grayscale values ​​of all pixels on the brightness distribution line to obtain a brightness gradient sequence;

[0021] The trend intensity obtained by trend analysis of the brightness variation sequence in the spot area is used as the internal complexity of the spot area.

[0022] Furthermore, the method for obtaining the morphological regularity of each light spot area includes:

[0023] For any two light spot areas, shape matching is performed on the edges of the two light spot areas to obtain the similarity of the edges of the two light spot areas;

[0024] Calculate the mean similarity between the edge of each light spot area and the edges of all other light spot areas; obtain the difference between the edge of each light spot area and the total number of all pixels on the edges of other light spot areas; obtain the sum of the differences between the edge of each light spot area and the edges of all other light spot areas; add the sum to the mean similarity to obtain the morphological regularity of each light spot area.

[0025] Furthermore, the method for obtaining the material reflection coefficient of each light spot area specifically includes:

[0026] The sum of the internal complexity and morphological regularity of each light spot area is calculated and recorded as the light spot characteristic coefficient; the product of the light spot regular coefficient and the light spot characteristic coefficient of each light spot area is taken as the material reflection coefficient of each light spot area.

[0027] Furthermore, the anti-permeability test result of the test piece is obtained according to the threshold analysis of the material reflection coefficient of all the light spot areas, including:

[0028] Perform threshold analysis on the material reflectance coefficients of all light spot areas to obtain a segmentation threshold; record the light spot areas where the material reflectance coefficient is less than the segmentation threshold as water seepage reflective areas; if the number of water seepage reflective areas is greater than or equal to the preset number, mark the specimen as a water seepage specimen; otherwise, the specimen's anti-seepage performance is qualified.

[0029] In the second aspect, an embodiment of the present application also provides a polyurethane material impermeability detection system, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor implements the steps of any one of the above-mentioned polyurethane material impermeability detection methods when executing the computer program.

[0030] This application has at least the following beneficial effects:

[0031] The present application analyzes the differences in the characteristics of the light spot area produced by the reflection of water droplets or water accumulation when the test piece surface has ordinary reflection and water seepage when the polyurethane material is tested for impermeability. First, it is analyzed that the shape of the light spot area produced by the reflection of water droplets is more regular than the ordinary reflection produced by the test piece material and has no obvious tilt direction. The light spot regular coefficient and are constructed to represent the shape and direction characteristics of the light spot area, and the distinguishing features of the two reflection situations are extracted. Further, it is analyzed that when the test piece surface has ordinary reflection, the light spot area produced has a certain brightness gradient. According to the brightness change characteristics combined with the light spot regular coefficient, the light spot area is generated. The light spot area is generated by the reflection of water droplets, and the light spot area is generated by the reflection of water droplets ... The spot characteristic coefficient is constructed based on the shape similarity between the spot areas, which reflects the characteristics of ordinary reflection caused by the material; finally, the material reflection coefficient is further constructed by combining the conventional spot coefficient and the spot characteristic coefficient, which is used to distinguish the spot area caused by ordinary reflection and water droplet or water accumulation reflection in a single specimen, and then judge whether there is water seepage in the current specimen. This solves the problem that when the current polyurethane material covers the surface of the concrete specimen, the ordinary reflection on the specimen surface and the spot area formed by water droplet or water accumulation reflection during water seepage in the image are similar and difficult to distinguish, thereby improving the accuracy of anti-permeability testing of polyurethane materials. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present application or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0033] Figure 1 A flowchart of a method for detecting the impermeability of a polyurethane material provided in one embodiment of the present application;

[0034] Figure 2 A schematic diagram of a binarized image of a specimen surface provided by an embodiment of the present application;

[0035] Figure 3 A schematic diagram of edge detection results of a binary image of a specimen surface provided in one embodiment of the present application;

[0036] Figure 4A schematic diagram of the direction connection of the light spot area provided in one embodiment of the present application;

[0037] Figure 5 A schematic diagram of the tilt direction angle between two light spot areas provided in one embodiment of the present application;

[0038] Figure 6 A schematic diagram comparing the reflection of accumulated water and the reflection of materials provided in one embodiment of the present application. DETAILED DESCRIPTION

[0039] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. In the absence of conflict, the embodiments of the present application and the technical features in the embodiments can be combined with each other. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0040] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.

[0041] The specific scheme of a polyurethane material impermeability detection method and system provided by the present application is described in detail below with reference to the accompanying drawings.

[0042] See also Figure 1 , which shows a flow chart of a method for detecting the impermeability of a polyurethane material provided by an embodiment of the present application, the method comprising the following steps:

[0043] S1, obtaining test image of the test piece coated with polyurethane material at each moment during the anti-permeability test process.

[0044] According to the "Standard for Test Methods of Ordinary Concrete Long-term Performance and Durability" (GB / T 50082-2009) and the relevant contents of "JG 237 Concrete Test Mold", 6 concrete truncated cone specimens were made. After the specimens were made, water-based polyurethane material was evenly applied on the surface of the specimens. After the specimens were formed, they were covered with plastic film and cured in a cool place indoors for 14 days. At this point, the specimens of polyurethane material were made.

[0045] All 6 test pieces are covered with 4 rubber rings after immersion in water, and the test pieces are pressed into the test mold by a pressurizer, and the prepared test mold is installed on the concrete impermeability tester. The lower limit of the concrete impermeability tester pressure is set to 0.1MPa, and the upper limit is set to 0.8MPa. The implementer can set it according to the actual material impermeability grade requirements. After the impermeability tester is started, the water pressure is increased by 0.1MPa every 8h. A high-definition camera is fixed just above the concrete impermeability tester, and the RGB images of the surfaces of each test piece are obtained every 30min. The surface RGB images of each test piece are respectively used as input, and the weighted average method is adopted, and the grayscale image of the test piece surface is output, which is recorded as the test piece detection image. The weighted average method is a known technology, and this application will not repeat it.

[0046] S2, perform threshold analysis on the test piece detection image at each moment to obtain each light spot area, and obtain the natural reflection coefficient of each light spot area according to the area of ​​each light spot area and the uniformity of the grayscale distribution inside it; obtain the reflection characteristic coefficient of each light spot area according to the shape feature difference and distance between each light spot area and all other light spot areas; and obtain the light spot conventional coefficient by combining the natural reflection coefficient and the reflection characteristic coefficient of each light spot area.

[0047] When ordinary reflective spots appear on the surface of the specimen, the overall area of ​​the spot is larger than the reflection produced by water droplets when water seeps into the specimen surface. Due to the different roughness of the specimen surface, the uniformity of the brightness of the ordinary reflective spots is relatively low, while the reflection produced by water droplets when water seeps into the specimen is more uniform and brighter.

[0048] In order to extract the distinguishing features between the two, this embodiment first performs threshold segmentation on the test piece detection image at each moment to obtain a binary image of the test piece surface; specifically, the grayscale image of the test piece surface is used as input, and the grayscale threshold value of the grayscale image of the test piece surface is output using the Otsu threshold method. Figure 2 As shown, the grayscale values ​​of all pixels in the surface grayscale image whose grayscale values ​​are greater than the threshold are set to 255, and the rest are set to 0, so as to obtain a binary image of the specimen surface.

[0049] Obtain all closed contours in the binary image of the specimen surface; record the inner area of ​​each closed contour in the specimen detection image as a spot area; specifically, Figure 3 As shown, the specimen surface binarization image is used as input, and the Canny edge detection algorithm is used to obtain all the edges in the specimen detection image. Finally, all the edges are used as input, and the contour tracking algorithm is used to output all the closed contours in the specimen detection image. Among them, the Otsu threshold method, the Canny edge detection algorithm and the contour tracking algorithm are all well-known technologies, and the specific implementation process is not repeated in this application. Finally, the closed contour pixel points obtained are marked in the original specimen detection image, and all the pixel points in each closed contour constitute the spot area in the specimen detection image.

[0050] According to the difference in the characteristics of the ordinary reflection of the surface of the above-mentioned specimen and the reflection produced by water droplets during water seepage, the natural reflection coefficient of a single light spot area is constructed. The natural reflection coefficient can be determined by the area size and brightness uniformity of a single light spot area, and the specific calculation method is:

[0051]

[0052] in, is the natural reflection coefficient of the i-th light spot area; is the total number of pixels contained in the i-th spot area; is the gray value variance of all pixels in the i-th spot area.

[0053] If the area of ​​the light spot generated on the surface of the specimen is larger and the uniformity of the brightness in the light spot is lower, that is, the natural reflection coefficient is larger, it means that the light spot generated on the surface of the specimen is more likely to be a light spot generated by ordinary reflection.

[0054] Since the position of the light source is usually fixed, the light spot area produced by ordinary reflection will have a more similar tilt direction. When the surface of the specimen is infiltrated with water, the light spot area produced by the reflection of water droplets is more regular in shape, and the light spot produced by the reflection has no obvious tilt direction. In addition, the light spot distribution produced by ordinary reflection is more concentrated, while the light spot area distribution produced by the reflection of water droplets may be more discrete.

[0055] Therefore, in order to characterize the approximate characteristics of the inclination between the spot areas, this embodiment obtains, for each spot area, the distance between the two pixel points with the largest and smallest horizontal coordinates in the spot area, which is recorded as the horizontal distance; the distance between the two pixel points with the largest and smallest vertical coordinates in the spot area is obtained, which is recorded as the vertical distance; the two pixel points corresponding to the maximum values ​​of the horizontal distance and the vertical distance are recorded as direction points; and the two direction points are connected to obtain the direction line of the spot area.

[0056] In this embodiment, the distance between two pixel points is the Euclidean distance; the direction lines of each light spot area can be obtained by the above method. Figure 4 As shown in the figure, 1 is the spot area produced by ordinary reflection, 2 is the direction line of the spot area, 3 is the spot area produced by water droplets or water reflection, and 4 is the surface image of the specimen. Furthermore, for any two spot areas, the minimum angle between the extension lines of the direction line of the two spot areas is taken as the tilt direction angle between the two spot areas. Figure 5As shown in the figure, 1 is the spot area generated by ordinary reflection, 2 is the direction line of the spot area, 3 is the spot area generated by water droplets or water reflection, 4 is the surface image of the specimen, and 5 is the tilt direction angle. It should be noted that if the extension lines of the direction lines of the two spot areas do not intersect, the tilt direction angle is 0.

[0057] Based on the above-mentioned light spot tilt direction characteristics and distribution characteristics generated by ordinary reflection, the reflection characteristic coefficient of the light spot area is constructed. The reflection characteristic coefficient can be determined by the degree of inclination approximation between a single light spot area and the rest of the light spot areas and the distribution of the light spot areas. The specific calculation method is:

[0058]

[0059] in, is the reflection characteristic coefficient of the i-th light spot area; is the average value of the tilt direction angle between the i-th light spot area and all other light spot areas; is the mean Euclidean distance between the i-th spot area and the center points of all other spot areas.

[0060] If the light spot area on the surface of the specimen is a light spot area produced by ordinary reflection, the closer the direction lines between the light spot areas are to parallel, that is, the smaller the tilt direction angle is, and the denser the distribution is, the smaller the Euclidean distance between the light spot areas is, that is, the larger the reflection characteristic coefficient is, indicating that the light spot area is more likely to be a light spot area produced by ordinary reflection.

[0061] The natural reflection coefficient and the reflection characteristic coefficient of the light spot area are combined to construct the light spot regular coefficient that represents the light spot area as a normal reflection situation. The light spot regular coefficient of each light spot area is the product of the natural reflection coefficient and the reflection characteristic coefficient of each light spot area.

[0062] When a single light spot area is a light spot area generated when the polyurethane material on the specimen surface has ordinary reflection, the larger the area of ​​the light spot area and the more complex the brightness change therein, the closer the inclination direction is to the other light spots in the specimen detection image and the denser the distribution is, that is, the larger the light spot regular coefficient is, the more likely it is that the light spot area is a light spot area generated when ordinary reflection occurs on the specimen surface.

[0063] S3, according to the intensity of the grayscale change trend from the edge to the center of each light spot area, the internal complexity of each light spot area is obtained; according to the similarity of the contour shape of each light spot area with all other light spot areas, the morphological regularity of each light spot area is obtained; the morphological regularity, internal complexity and light spot regularity coefficient of each light spot area are integrated to obtain the material reflection coefficient of each light spot area.

[0064] In the process of slowly increasing the pressure of the impermeability tester, due to the different quality of concrete used to make the samples, there may be certain deviations in its impermeability effect, which may lead to uneven water seepage speed when water seepage occurs after coating the polyurethane material. When water seepage occurs, water droplets that may penetrate in a short time will form a large area of ​​water on the surface of the specimen, and a larger light spot area will be generated when reflecting light. The larger the water accumulation area, the better the reflection effect of the light source, and the light spot area characteristics generated are more similar to the light spot area generated by ordinary reflection. The larger the conventional coefficient of the light spot calculated by the above method, the more difficult it is to distinguish the light spot area generated by water accumulation reflection and ordinary reflection, resulting in errors in the judgment of water seepage, so further analysis is needed.

[0065] When ordinary material reflection appears on the surface of the specimen, the light spot area produced has a certain brightness gradient, such as Figure 6 As shown in (b) in the figure, the brightness is highest in the middle area, and the brightness decreases as it is farther from the center of the spot area. Figure 6 The light spot area produced by the reflection of accumulated water shown in (a) has a more uniform brightness distribution and higher brightness.

[0066] In order to characterize the characteristic that the brightness of the spot area increases as it approaches the center of the spot area, for each spot area, the line between the pixel point with the smallest horizontal coordinate on the edge of the spot area and the center point of the spot area is obtained, which is recorded as the brightness distribution line of the spot area; starting from the pixel point with the smallest horizontal coordinate on the edge of the spot area, the grayscale values ​​of all the pixels on the brightness distribution line are arranged to obtain a brightness gradient sequence. Specifically, the brightness gradient sequence of the spot area is constructed by arranging the positions from the pixel point with the smallest horizontal coordinate to the center point of the spot area.

[0067] Furthermore, the trend intensity obtained by performing trend analysis on the brightness variation sequence in the light spot area is used as the internal complexity of the light spot area; this embodiment adopts the SLT decomposition algorithm to perform trend analysis, and the trend intensity can be calculated by the trend intensity calculation formula in the SLT decomposition algorithm, wherein the SLT decomposition algorithm is a well-known technology and will not be repeated in this application.

[0068] If the trend intensity of the spot area is greater, it means that the edge brightness closer to the center point of the spot area is higher, that is, the internal complexity is greater, which means that the spot area is more likely to be a spot area caused by ordinary reflection on the surface of the specimen.

[0069] Since there may be multiple seepage points when the specimen is seeping, when the seeped water droplets gather into accumulated water, the overall shape of the light spot area produced by the accumulated water is highly irregular, while the shape of the light spot area produced by ordinary reflection on the specimen surface is relatively regular and similar.

[0070] Therefore, this embodiment determines the morphological regularity of the spot area by analyzing the contour similarity and contour length similarity of a single spot area and the rest of the spot areas based on the morphological features of the spot area generated in the above different situations. First, for any two spot areas, the edges of the two spot areas are shape matched, specifically, the edges of the two spot areas are matched using a shape context algorithm to obtain the similarity of the edges of the two spot areas; the shape context algorithm is a well-known technology, and this application will not repeat its process.

[0071] Calculate the mean similarity between the edge of each light spot area and the edges of all other light spot areas; obtain the difference between the edge of each light spot area and the total number of all pixels on the edges of other light spot areas; obtain the sum of the differences between the edge of each light spot area and the edges of all other light spot areas; add the sum to the mean similarity to obtain the morphological regularity of each light spot area.

[0072] If the spot area is the light spot area produced by the reflection of water on the surface of the specimen, the lower the degree of similarity between the edge shape of the light spot area and the edge shape of other light spot areas, the lower the degree of similarity of the edge length, that is, the smaller the regularity of the shape, which means that the light spot area is more likely to be the light spot area produced by the reflection of water when water seeps on the surface of the specimen.

[0073] The spot characteristic coefficient of the spot area is obtained by combining the internal complexity and morphological regularity of the spot area. The common spot coefficient can be obtained by summing the internal complexity and morphological regularity of a single spot area.

[0074] When there are more edges in a single spot area and the edge brightness is greater closer to the center of the spot area, that is, the internal complexity is higher, and the overall shape is more regular and the difference with the other spot areas is smaller, that is, the greater the morphological regularity, that is, the larger the spot characteristic coefficient, it means that the spot area is more likely to be the spot area generated by ordinary reflection on the surface of the specimen.

[0075] According to the spot regular coefficient and the spot characteristic coefficient of the single spot area, the material reflection coefficient of the single spot area is constructed. The material reflection coefficient can be calculated by multiplying the spot regular coefficient and the spot characteristic coefficient of the single spot area.

[0076] When a single light spot area is a light spot area caused by ordinary reflection on the specimen surface, the larger the area of ​​the light spot area, the denser the distribution, the more uneven the brightness distribution inside the area, and the larger the gradient characteristics, and the more similar the morphology to the other light spot areas, that is, the larger the material reflection coefficient, the more likely the light spot area is to be a light spot area caused by ordinary reflection on the specimen surface.

[0077] S4, obtaining the anti-permeability test result of the test piece according to the threshold analysis of the material reflection coefficient of all the light spot areas.

[0078] In summary, the material reflection coefficient represents the probability that the light spot area is caused by the ordinary material reflection on the surface of the specimen; in order to further divide the material reflection and the water seepage reflection, the water seepage reflection area is extracted; this embodiment takes the material reflection coefficients of all light spot areas as input, and uses the cross-validation method to output the segmentation threshold of the material reflection coefficient. When the material reflection coefficient of a single light spot area is less than the segmentation threshold, it means that the light spot area is a light spot area caused by the ordinary reflection on the surface of the specimen, otherwise the area is considered to be a water seepage reflection area. When there are m=3 or more water seepage reflection areas in the specimen, it is considered that the specimen has water seepage, and the specimen is marked as a water seepage specimen; otherwise, the specimen has qualified impermeability. The cross-validation method is a well-known technology, and this application will not repeat it. The total number of water seepage specimens is counted, and the impermeability grade of the specimen is calculated. The calculation method of the impermeability grade is a well-known technology, and this application will not repeat its process.

[0079] Based on the same inventive concept as the above method, an embodiment of the present application also provides a polyurethane material impermeability detection system, including a memory, a processor, and a computer program stored in the memory and running on the processor, and when the processor executes the computer program, the steps of any one of the above-mentioned polyurethane material impermeability detection methods are implemented.

[0080] Through the above description of the implementation method in combination with the accompanying drawings, technical personnel in the relevant field can understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0081] The above contents are only specific implementation methods of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be covered by the protection scope of the present application.

Claims

1. A method for detecting the impermeability of a polyurethane material, characterized in that: The method comprises the following steps: S1, obtaining the test image of the test piece coated with polyurethane material at each moment during the anti-permeability test process; S2, threshold analysis is performed on the test image of the specimen at each moment to obtain each light spot area, and the natural reflection coefficient of each light spot area is obtained according to the area of ​​each light spot area and the uniformity of the grayscale distribution inside it; the reflection characteristic coefficient of each light spot area is obtained according to the shape characteristic difference and distance between each light spot area and all other light spot areas; the light spot conventional coefficient is obtained by combining the natural reflection coefficient and the reflection characteristic coefficient of each light spot area; S3, according to the intensity of the grayscale change trend from the edge to the center of each light spot area, the internal complexity of each light spot area is obtained; according to the similarity of the contour shape of each light spot area with all other light spot areas, the morphological regularity of each light spot area is obtained; the morphological regularity, internal complexity and light spot regularity coefficient of each light spot area are combined to obtain the material reflection coefficient of each light spot area; S4, obtaining the anti-permeability test result of the test piece according to the threshold analysis of the material reflection coefficient of all the light spot areas; The method for obtaining the conventional coefficient of the light spot includes: the conventional coefficient of each light spot area is the product of the natural reflection coefficient of each light spot area and the reflection characteristic coefficient; The method for obtaining the material reflection coefficient of each light spot area specifically includes: The sum of the internal complexity and morphological regularity of each light spot area is calculated and recorded as the light spot characteristic coefficient; the product of the light spot regular coefficient and the light spot characteristic coefficient of each light spot area is taken as the material reflection coefficient of each light spot area; The anti-permeability test result of the test piece is obtained according to the threshold analysis of the material reflection coefficient of all the light spot areas, including: Perform threshold analysis on the material reflectance coefficients of all light spot areas to obtain a segmentation threshold; record the light spot areas where the material reflectance coefficient is less than the segmentation threshold as water seepage reflective areas; if the number of water seepage reflective areas is greater than or equal to the preset number, mark the specimen as a water seepage specimen; otherwise, the specimen's anti-seepage performance is qualified.

2. A method for detecting the impermeability of a polyurethane material according to claim 1, characterized in that: The method for obtaining the natural reflection coefficient of each light spot area includes: Perform threshold segmentation on the test piece detection image at each moment to obtain a binary image of the test piece surface; obtain all closed contours in the binary image of the test piece surface; record the inner area of ​​each closed contour in the test piece detection image as a light spot area; The grayscale value variance of all pixels in each light spot area is calculated; the total number of pixels contained in each light spot area is counted; and the sum of the total number of pixels and the grayscale value variance is used as the natural reflection coefficient of each light spot area.

3. A method for detecting the impermeability of a polyurethane material according to claim 1, characterized in that: The reflection characteristic coefficient of each light spot area is obtained according to the shape characteristic difference and distance between each light spot area and all other light spot areas, including: For each spot area, obtain the distance between the two pixel points with the largest and smallest horizontal coordinates in the spot area, and record it as the horizontal distance; obtain the distance between the two pixel points with the largest and smallest vertical coordinates in the spot area, and record it as the vertical distance; record the two pixel points corresponding to the maximum values ​​of the horizontal distance and the vertical distance as direction points; connect the two direction points to obtain the direction line of the spot area; For any two light spot areas, the minimum angle between the extension lines of the direction lines of the two light spot areas is taken as the tilt direction angle between the two light spot areas; According to the tilt direction angle and distance between each light spot area and all other light spot areas, the reflection characteristic coefficient of each light spot area is obtained.

4. A method for detecting the impermeability of a polyurethane material as claimed in claim 3, characterized in that: The step of obtaining the reflection characteristic coefficient of each light spot area according to the tilt direction angle and distance between each light spot area and all other light spot areas includes: recording the reflection characteristic coefficient of the i-th light spot area as ; ;in, is the average value of the tilt direction angle between the i-th light spot area and all other light spot areas; is the mean distance between the i-th spot area and the center points of all other spot areas.

5. A method for detecting the impermeability of a polyurethane material as claimed in claim 1, characterized in that: The method for obtaining the internal complexity of each light spot area includes: For each spot area, obtain the line between the pixel point with the smallest horizontal coordinate on the edge of the spot area and the center point of the spot area, which is recorded as the brightness distribution line of the spot area; starting from the pixel point with the smallest horizontal coordinate on the edge of the spot area, arrange the grayscale values ​​of all pixels on the brightness distribution line to obtain a brightness gradient sequence; The trend intensity obtained by trend analysis of the brightness variation sequence in the spot area is used as the internal complexity of the spot area.

6. A method for detecting the impermeability of a polyurethane material according to claim 1, characterized in that: The method for obtaining the morphological regularity of each light spot area includes: For any two light spot areas, shape matching is performed on the edges of the two light spot areas to obtain the similarity of the edges of the two light spot areas; Calculate the mean similarity between the edge of each light spot area and the edges of all other light spot areas; obtain the difference between the edge of each light spot area and the total number of all pixels on the edges of other light spot areas; obtain the sum of the differences between the edge of each light spot area and the edges of all other light spot areas; add the sum to the mean similarity to obtain the morphological regularity of each light spot area.

7. A polyurethane material impermeability detection system, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of a method for detecting the impermeability of a polyurethane material as described in any one of claims 1 to 6 are implemented.

Images