A Visual Inspection Method for Building Exterior Wall Thermal Insulation Materials

Abstract

A visual inspection method for building exterior wall thermal insulation materials, which relates to the field of visual inspection technology, obtains the material properties and external environment data of the building exterior wall materials to be inspected, and judges whether to perform the visual inspection operation on the building exterior wall materials. When the external environment data meets the operation standards, the shooting parameters of the building exterior wall materials to be inspected are obtained; it is judged whether the external environment data of the building exterior wall materials to be inspected can perform infrared image detection operations, visual image detection operations are carried out on the areas with undetermined thermal insulation performance, color abnormal pixel points and texture analysis angles are obtained, local area texture analysis is carried out on the areas with undetermined thermal insulation performance, and texture abnormal areas are obtained; edge detection is carried out using the Canny algorithm to obtain damaged abnormal areas, and at the same time, the change trend of the complexity level of the local areas not marked as damaged abnormal areas is predicted to obtain potential damaged areas, improving the accuracy and reliability of the detection.

Description

Technical Field

[0001] The present invention relates to the technical field of visual detection, and specifically to a visual detection method for building exterior wall thermal insulation materials. Background Art

[0002] The prior art CN114882038A "A detection method and detection equipment for building exterior wall thermal insulation materials" obtains the surface grayscale image of expanded perlite, divides it into multiple window areas of the same size, obtains the energy eigenvalue according to the gray-level co-occurrence matrix of each window area, obtains the gray-level pair of the pixel point with the largest autocorrelation in each window area as the characteristic gray-level pair, obtains the complexity of each window area according to the frequency of the characteristic gray-level pair and the gray-level difference of each gray-level pair, calculates the complexity correlation between each window area and other window areas according to the complexity of each window area, obtains the quality evaluation value of the expanded perlite according to the complexity of the window area with the largest complexity correlation and the energy eigenvalue of the gray-level co-occurrence matrix of each window area, and uses the quality evaluation value to detect the quality of the expanded perlite.

[0003] There are some problems with the existing visual detection methods for building exterior wall thermal insulation materials. For example, changes in lighting conditions during the visual detection process of building exterior wall thermal insulation materials can lead to changes in color and brightness, which may affect the effects of color detection and edge detection. Multiple types of thermal insulation materials may be used on the building exterior wall, and these materials may have different colors and textures, which increases the difficulty of detection. High-level visual detection algorithms may require a large amount of computing resources, which may limit their practicality. These problems may affect the accuracy and efficiency of detection. Summary of the Invention

[0004] In order to solve the above technical problems, the purpose of the present invention is to provide a visual detection method for building exterior wall thermal insulation materials, including the following steps:

[0005] Step s1: Obtain the material properties and external environment data of the building exterior wall material to be detected, determine whether to perform the visual detection operation of the building exterior wall material according to the external environment data, and when the external environment data meets the operation standard, obtain the shooting parameters of the building exterior wall material to be detected;

[0006] Step s2: Determine whether the external environment data of the building exterior wall material to be detected can perform the infrared image detection operation, and obtain the areas with unqualified thermal insulation performance and the areas with undetermined thermal insulation performance according to the judgment result;

[0007] Step s3: Perform a visual image detection operation on the areas with undetermined thermal insulation performance, obtain the color abnormal pixel points and the texture analysis angle, perform local area texture analysis on the areas with undetermined thermal insulation performance according to the texture analysis angle, and obtain the texture abnormal areas;

[0008] Step s4: Use the Canny algorithm to perform edge detection on each local area of the area with undetermined thermal insulation performance to obtain the damaged abnormal area. At the same time, predict the trend of the complexity level change of the local areas not marked as damaged abnormal areas to obtain potential damaged areas.

[0009] Further, the process of obtaining the material properties of the building exterior wall material to be detected and the external environment data and judging whether to perform the visual detection operation of the building exterior wall material according to the external environment data includes:

[0010] Obtain the material properties of the building exterior wall material to be detected and the external environment data. The material properties include color characteristics, reflective properties, and texture structure. The external environment data includes the indoor temperature of the building, the outdoor temperature of the building, light intensity, wind speed, and precipitation intensity. Obtain the outdoor temperature, wind speed, and precipitation intensity corresponding to the building exterior wall material to be detected. Compare the outdoor temperature, wind speed, and precipitation intensity corresponding to the building exterior wall material to be detected with the preset temperature limit threshold, preset wind speed limit threshold, and preset precipitation intensity limit threshold respectively. If the outdoor temperature, wind speed, and precipitation intensity corresponding to the building exterior wall material to be detected are all less than the corresponding temperature limit threshold, wind speed limit threshold, and precipitation intensity limit threshold, then perform the visual detection operation of the building exterior wall material to be detected. If there is an outdoor temperature, wind speed, or precipitation intensity corresponding to the building exterior wall material to be detected that is greater than the corresponding temperature limit threshold, wind speed limit threshold, and precipitation intensity limit threshold, then suspend the visual detection operation of the building exterior wall material to be detected.

[0011] Further, the process of obtaining the shooting parameters of the building exterior wall material to be detected includes:

[0012] Take the wind speed and precipitation intensity corresponding to the building exterior wall material to be detected as evaluation indicators, set the index weights of the evaluation indicators, and obtain the membership degree matrix of the building exterior wall material to be detected for the preset interference level through fuzzy comprehensive evaluation;

[0013] Obtain the interference level of the building exterior wall material to be detected through the membership degree matrix and index weights. Pre-construct an adaptive shooting parameter comparison table, where the adaptive shooting parameter comparison table includes shooting parameters corresponding to different interference levels. The shooting parameters include resolution and frame rate. Determine the shooting parameters of the building exterior wall material to be detected according to the interference level of the building exterior wall material to be detected.

[0014] Further, the process of judging whether the external environment data of the building exterior wall material to be detected can perform infrared image detection operations and obtaining the area with unqualified thermal insulation performance and the area with undetermined thermal insulation performance according to the judgment result includes:

[0015] Obtain the temperature difference between the indoor temperature and the outdoor temperature of the building according to the external environment data of the building exterior wall material to be detected, mark the temperature difference as the first temperature difference, compare the first temperature difference with a preset temperature difference threshold. When the temperature difference is greater than or equal to the temperature difference threshold, select threshold points within the first temperature difference to divide it into temperature difference sub-intervals of different insulation performance levels. Set the emissivity of the UAV camera terminal according to the material properties of the building exterior wall material to be detected. Use the UAV camera terminal to perform infrared scanning on the building exterior wall material to be detected, obtain an infrared image, and obtain the temperature corresponding to the gray value of each pixel point in the infrared image based on the preset temperature lookup table of the UAV camera terminal. Obtain the temperature difference between the temperature corresponding to each pixel point and the outdoor temperature of the building, mark the temperature difference as the second temperature difference, match the second temperature difference with the temperature difference sub-intervals of different insulation performance levels, obtain the insulation performance level corresponding to each pixel point, compare the insulation performance level corresponding to each pixel point with a preset insulation performance level threshold, mark the distribution area of the pixel points with an insulation performance level less than the insulation performance level threshold as the unqualified area of insulation performance, and mark the distribution area of the pixel points with an insulation performance level greater than or equal to the insulation performance level threshold as the area to be determined for insulation performance, and perform visual image detection operations on the area to be determined for insulation performance;

[0016] When the temperature difference is less than the temperature difference threshold, mark all the areas covered by the building exterior wall material to be detected as the area to be determined for insulation performance, and perform visual image detection operations on the area to be determined for insulation performance.

[0017] Furthermore, the process of performing visual image detection operations on the area to be determined for insulation performance to obtain color abnormal pixel points and texture analysis angles includes:

[0018] Use the UAV camera terminal to perform multi-angle image scanning on the area to be determined for insulation performance of the building exterior wall material to be detected, obtain the multi-angle surface color image of the area to be determined for insulation performance, and convert the multi-angle surface color image from the preset BGR color space to the HSV color space. Subsequently, extract the color features of each pixel point in the multi-angle surface color image. The color features include hue, saturation, and light value. Compare the hue and saturation of each pixel point with the corresponding hue and saturation of the material properties respectively, obtain the color difference value of each pixel point, and mark the pixel points with a color difference value greater than the preset color difference value threshold as color abnormal pixel points;

[0019] According to the light value corresponding to each pixel point in the multi-angle surface color image, obtain the average light value and the standard deviation of the light value corresponding to different angles in the multi-angle surface color image. Obtain the texture feature judgment value based on the average light value and the standard deviation of the light value, and select the angle corresponding to the maximum texture feature judgment value among different angles as the texture analysis angle.

[0020] Further, the process of performing local area texture analysis on the heat preservation performance to-be-determined area from the texture analysis perspective and obtaining the texture abnormal area includes:

[0021] Perform denoising and grayscale processing on the surface color image corresponding to the texture analysis angle in the multi-angle surface color image of the heat preservation performance to-be-determined area to obtain a grayscale image. Set the fixed parameters of the region detection window and the gray-level co-occurrence matrix, and obtain the gray-level co-occurrence matrix of each local area in the grayscale image by sliding the region detection window. Obtain the texture structure of each local area in the grayscale image according to the gray-level co-occurrence matrix, compare the texture structure of each local area with the corresponding texture structure in the material properties to obtain the texture structure similarity of each local area, and mark the local areas with texture structure similarity less than the preset similarity threshold as texture abnormal areas.

[0022] Further, the process of using the Canny algorithm to perform edge detection on each local area of the heat preservation performance to-be-determined area and obtaining the damaged abnormal area includes:

[0023] Use the Canny algorithm to perform edge detection on each local area in the grayscale image to obtain the edge image of each local area, extract the features of the edge image of each local area to obtain the edge feature set of the edge image. The various types of edge features in the edge feature set include edge length, edge branch number, continuity measure, edge curvature, and edge roughness.

[0024] Taking the various types of edge features in the edge feature set of the edge image as evaluation indicators, set the index weight matrix of the evaluation indicators, obtain the membership degree matrix of the edge feature set for the preset complexity level through fuzzy comprehensive evaluation, obtain the complexity level corresponding to the edge feature set according to the membership degree matrix and the index weight matrix, mark the local areas corresponding to the edge feature sets with complexity levels greater than the preset complexity level threshold as damaged abnormal areas, and at the same time predict the change trend of the complexity level of the local areas not marked as damaged abnormal areas.

[0025] Further, the process of predicting the change trend of the complexity level of the local areas not marked as damaged abnormal areas and obtaining the potential damaged areas includes:

[0026] Pre-construct a visual inspection database, which is used to store historical visual inspection records of several building exterior wall materials. Obtain the historical complexity level time series of each local area that is not marked as a damaged abnormal area based on the historical visual inspection records. Build a complexity level prediction model based on deep learning. Use the historical complexity level time series of each local area that is not marked as a damaged abnormal area as the training set and the test set. Input the training set into the complexity level prediction model for training until the loss function is trained stably, and save the model parameters. Test the complexity level prediction model with the test set until it meets the preset requirements, and output the complexity level prediction model;

[0027] Obtain the predicted complexity level of each local area that is not marked as a damaged abnormal area according to the complexity level prediction model. Compare the predicted complexity level with the complexity level threshold. If the predicted complexity level of the local area that is not marked as a damaged abnormal area is greater than the complexity level threshold, mark the local area that is not marked as a damaged abnormal area as a potential damaged area.

[0028] Compared with the prior art, the beneficial effects of the present invention are:

[0029] The present invention provides a systematic method for detecting the thermal insulation performance and appearance quality of building exterior wall materials, especially for the detection of areas with undetermined thermal insulation performance. This method combines various technical means such as external environmental condition judgment, infrared image detection, visual image detection, and edge detection, aiming to improve the accuracy and reliability of detection. Among them, step s1: Obtain the material properties and external environmental data of the building exterior wall materials to be detected to ensure detection under suitable external environmental conditions, avoid misjudgment caused by environmental factors (such as light, temperature, etc.), reduce the detection error caused by external environmental changes, and improve the reliability and accuracy of the detection results. Step s2: Determine whether infrared image detection operations can be performed on the external environmental data, and use infrared images to detect areas with unqualified thermal insulation performance and undetermined areas. This is because in infrared images, the contrast of different temperature areas is relatively high, which helps to distinguish areas with poor thermal insulation performance and can effectively detect areas with poor thermal insulation performance, providing areas of key concern for subsequent visual image detection. Step s3: Perform visual image detection operations on the areas with undetermined thermal insulation performance, and identify areas that may have problems from the perspectives of color abnormal pixel points and texture analysis. Using color abnormal pixel points can detect possible problems such as pollution and discoloration. From the perspective of texture analysis, defects can be more clearly identified at specific angles, improving the pertinence of detection. Step s4: Use the Canny algorithm to perform edge detection on each local area of the area with undetermined thermal insulation performance, use the Canny algorithm to detect edges to identify damaged abnormal areas, and predict potential damaged areas. Predict the trend of complexity level change for local areas not marked as damaged abnormal areas, which helps to discover possible problem areas in advance. By comprehensively considering external environmental conditions and various detection technologies, the accuracy and reliability of detection are improved. Moreover, by pre-screening areas with undetermined thermal insulation performance, unnecessary detection workload is reduced, and the detection efficiency is improved. By predicting potential damaged areas, it helps to take measures in advance to avoid the deterioration of problems. Description of the Drawings

[0030] Figure 1 It is a schematic diagram of a visual detection method for a building exterior wall thermal insulation material according to an embodiment of the present application. Detailed Implementation Modes

[0031] Next, in combination with the drawings in the embodiments of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described. Obviously, the described embodiments are part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative efforts shall fall within the protection scope of the present application.

[0032] As Figure 1 shown, a visual detection method for a building exterior wall thermal insulation material includes the following steps:

[0033] Step s1: Obtain the material properties and external environment data of the building exterior wall material to be detected. Determine whether to perform a visual inspection operation on the building exterior wall material based on the external environment data. When the external environment data meets the operation standard, obtain the shooting parameters of the building exterior wall material to be detected;

[0034] Step s2: Determine whether the external environment data of the building exterior wall material to be detected can be used for infrared image detection operation, and obtain the areas with unqualified heat preservation performance and the areas with undetermined heat preservation performance according to the judgment result;

[0035] Step s3: Perform a visual image detection operation on the areas with undetermined heat preservation performance, obtain the color abnormal pixel points and the texture analysis angles, perform local area texture analysis on the areas with undetermined heat preservation performance according to the texture analysis angles, and obtain the texture abnormal areas;

[0036] Step s4: Use the Canny algorithm to perform edge detection on each local area of the areas with undetermined heat preservation performance to obtain the damaged abnormal areas. At the same time, predict the changing trend of the complexity level of the local areas not marked as damaged abnormal areas to obtain the potential damaged areas.

[0037] It should be further noted that in the specific implementation process, the process of obtaining the material properties and external environment data of the building exterior wall material to be detected and determining whether to perform a visual inspection operation on the building exterior wall material based on the external environment data includes:

[0038] Obtain material properties and external environment data of the building exterior wall materials to be detected, wherein the material properties include color characteristics, reflective properties and texture structures, and the building exterior wall materials to be detected include metal plates, stones, tiles, polystyrene foam plastics, mineral wool boards, etc. Different types of exterior wall insulation materials will have different effects on visual detection due to different material properties. The external environment data include building indoor temperature, building outdoor temperature, light intensity, wind speed and precipitation intensity. Obtain the building outdoor temperature, wind speed and precipitation intensity corresponding to the building exterior wall materials to be detected, and compare the building outdoor temperature, wind speed and precipitation intensity corresponding to the building exterior wall materials to be detected with the preset temperature limit threshold, the preset wind speed limit threshold and the preset precipitation The visual inspection of the exterior wall materials to be inspected is performed by comparing the outdoor temperature, wind speed and precipitation intensity of the building to be inspected with the intensity limit thresholds. If the outdoor temperature, wind speed and precipitation intensity of the building to be inspected corresponding to the exterior wall materials to be inspected are all lower than the corresponding temperature limit thresholds, wind speed limit thresholds and precipitation intensity limit thresholds, the visual inspection of the exterior wall materials to be inspected is performed; if the outdoor temperature, wind speed or precipitation intensity of the building to be inspected corresponding to the exterior wall materials to be inspected are higher than the corresponding temperature limit thresholds, wind speed limit thresholds and precipitation intensity limit thresholds, the visual inspection of the exterior wall materials to be inspected is suspended. The inspection is performed under stable weather conditions and avoids testing under extreme temperatures or high wind speeds to reduce the impact of external factors on the visual inspection results, thereby ensuring the accuracy of the visual inspection results.

[0039] It should be further explained that, in the specific implementation process, the process of obtaining the shooting parameters of the building exterior wall material to be inspected includes:

[0040] According to the wind speed and precipitation intensity corresponding to the building exterior wall materials to be tested as evaluation indicators, the indicator weights of the evaluation indicators are set, and the membership matrix of the building exterior wall materials to be tested for the preset interference level is obtained through fuzzy comprehensive evaluation;

[0041] The interference level of the building exterior wall material to be detected is obtained through the membership matrix and the indicator weight, and an adaptive shooting parameter comparison table is pre-constructed. The adaptive shooting parameter comparison table includes shooting parameters corresponding to different interference levels. The shooting parameters include resolution and frame number. The shooting parameters of the building exterior wall material to be detected are determined according to the interference level of the building exterior wall material to be detected.

[0042] It should be further explained that, in the specific implementation process, the process of obtaining the interference level of the building exterior wall material to be tested according to the membership matrix and the index weight matrix includes:

[0043] Fuse the index weight matrix and membership degree matrix of the evaluation index through a formula to obtain the fuzzy comprehensive evaluation matrix of the evaluation index. According to the fuzzy comprehensive evaluation matrix, obtain the membership degree of the building exterior wall material to be detected for different interference levels, screen out the interference level with the highest membership degree corresponding to the building exterior wall material to be detected, and use the interference level with the highest membership degree corresponding to the building exterior wall material to be detected as the interference level of the building exterior wall material to be detected;

[0044] Among them, the formula is:

[0045] M = αM1×βM2;

[0046] Among them, M is the fuzzy comprehensive evaluation matrix of the evaluation index, M1 is the index weight matrix of the evaluation index, M2 is the membership degree matrix, "×" represents the multiplication of the elements at the corresponding positions of the weight matrix and the membership degree matrix of the evaluation index, and α and β are weighting parameters used to control the balance between the weight matrix and the membership degree matrix in the fuzzy comprehensive evaluation matrix of the evaluation index.

[0047] It should be further noted that in the specific implementation process, the process of judging whether the external environment data of the building exterior wall material to be detected can be subjected to infrared image detection operations and obtaining the area with unqualified heat preservation performance and the area with undetermined heat preservation performance according to the judgment result includes:

[0048] Obtain the temperature difference between the indoor temperature and the outdoor temperature of the building according to the external environment data of the building exterior wall material to be detected, mark the temperature difference as the first temperature difference, compare the first temperature difference with a preset temperature difference threshold. When the temperature difference is greater than or equal to the temperature difference threshold, select threshold points within the first temperature difference and divide them into temperature difference sub-intervals of different thermal insulation performance levels. Set the emissivity of the UAV camera terminal according to the material properties of the building exterior wall material to be detected. The emissivity is the ability of an object to emit infrared radiation. Different materials have different emissivities, which directly affect the temperature values displayed in the infrared image. For example, the emissivity of metals is usually low, while that of most non-metallic materials is high. If the emissivity is not set correctly, the temperature readings in the infrared image will be inaccurate. For example, if the emissivity of a metal is set too high, it may result in a lower measured temperature. Therefore, adjust the emissivity of the UAV camera terminal in advance according to the material properties to ensure the accuracy of the infrared image. Use the UAV camera terminal to perform an infrared scan on the building exterior wall material to be detected, obtain the infrared image of the building exterior wall material to be detected, and obtain the temperature corresponding to the gray value of each pixel point in the infrared image based on the preset temperature lookup table of the UAV camera terminal. The temperature lookup table includes the temperatures corresponding to different gray values. Obtain the temperature difference between the temperature corresponding to each pixel point and the outdoor temperature of the building, mark the temperature difference as the second temperature difference, match the second temperature difference with the temperature difference sub-intervals of different thermal insulation performance levels, obtain the thermal insulation performance level corresponding to each pixel point, compare the thermal insulation performance level corresponding to each pixel point with the preset thermal insulation performance level threshold, mark the distribution area of the pixel points with a thermal insulation performance level less than the thermal insulation performance level threshold as the unqualified area of thermal insulation performance, and mark the distribution area of the pixel points with a thermal insulation performance level greater than or equal to the thermal insulation performance level threshold as the area to be determined for thermal insulation performance. Perform a visual image detection operation on the area to be determined for thermal insulation performance;

[0049] When the temperature difference is less than the temperature difference threshold, mark all the areas covered by the building exterior wall material to be detected as the area to be determined for thermal insulation performance, and perform a visual image detection operation on the area to be determined for thermal insulation performance; First, detect the areas with poor thermal insulation performance through the infrared thermal imager of the UAV camera terminal, and determine whether there is damage or missing of the thermal insulation layer by comparing the temperature differences of different pixel points. Pre-screen the areas with unqualified thermal insulation performance, avoid performing visual image detection on all areas of the building exterior wall material to be detected, reduce the consumption of shooting resources, and improve the efficiency, accuracy and comprehensiveness of the visual detection of building exterior wall thermal insulation materials.

[0050] It should be further noted that in the specific implementation process, the process of performing a visual image detection operation on the area to be determined for thermal insulation performance and obtaining color abnormal pixel points and texture analysis angles includes:

[0051] Use a drone camera terminal to perform multi-angle image scanning on the area with undetermined thermal insulation performance of the building exterior wall material to be detected, obtain multi-angle surface color images of the area with undetermined thermal insulation performance, and convert the multi-angle surface color images from the preset BGR color space to the HSV color space. Subsequently, extract the color features of each pixel point in the multi-angle surface color images. The color features include hue, saturation, and light value. Compare the hue and saturation of each pixel point with the corresponding hue and saturation of the material properties to obtain the color difference value of each pixel point. Mark the pixel points with a color difference value greater than the preset color difference value threshold as color abnormal pixel points;

[0052] According to the light value corresponding to each pixel point in the multi-angle surface color images, obtain the average light value and the standard deviation of the light value corresponding to different angles in the multi-angle surface color images. Obtain the texture feature judgment value based on the average light value and the standard deviation of the light value. Screen out the angle corresponding to the maximum texture feature judgment value among different angles as the texture analysis angle. A higher average light value usually means that the overall image is brighter, the contrast is better, and the texture features are easier to identify. While a lower average light value may mean that the overall image is darker, the contrast is lower, and the texture features may not be obvious enough. A larger standard deviation of the light value indicates that there are large light changes in the image, which usually means that there are rich details and contrast in the image, which is beneficial to texture analysis. A smaller standard deviation of the light value indicates that the light changes in the image are smaller, which may lead to unclear texture features and is not conducive to texture analysis. By analyzing the average light value and the standard deviation of the light value corresponding to different angles in the multi-angle surface color images, screen out the image angle most suitable for texture analysis, reduce the influence of shadows and reflections on texture analysis, and improve the accuracy of texture analysis;

[0053] Among them, the calculation formulas for obtaining the color difference value of each pixel point and the texture feature judgment value of different angles are as follows:

[0054]

[0055] yp g = ω3 * js g + ω4 * rd g ;

[0056] Among them, sf i represents the color difference value of pixel point i, gh i represents the hue of pixel point i, gh represents the hue corresponding to the material properties, ur i represents the saturation of pixel point i, ur represents the saturation corresponding to the material properties, yp g represents the texture feature judgment value corresponding to angle g, js g represents the average light value corresponding to angle g, rd gDenote the standard deviation of the brightness value corresponding to the angle g, and ω1, ω2, ω3, and ω4 denote weighting factors.

[0057] It should be further noted that in the specific implementation process, the process of performing local area texture analysis on the area to be determined for heat preservation performance according to the texture analysis angle and obtaining the texture abnormal area includes:

[0058] Perform denoising and grayscale processing on the surface color image corresponding to the texture analysis angle in the multi-angle surface color image of the area to be determined for heat preservation performance to obtain a grayscale image. It should be further noted that in the specific implementation process, the multi-angle surface color images captured by the UAV camera terminal may have noise problems. Therefore, in an embodiment of the present invention, after obtaining the image data, it is necessary to perform image preprocessing operations on it to improve the quality of the image data in order to obtain the image data for subsequent analysis. Improving the image quality through image preprocessing operations is a well-known image processing means for those skilled in the art. In the embodiment of the invention, the noise in the image is removed by the Gaussian filtering method, and then the image data is equalized to improve the contrast in the image, and the image data is grayscaled to convert the color image into a grayscale image. The grayscaling process is usually achieved by averaging the weights of the color channels. Among them, denoising and equalization processing, semantic segmentation network, and grayscaling are well-known technical means for those skilled in the art, and the specific steps will not be elaborated. Other image preprocessing means may also be used in other embodiments of the present invention, which are not limited herein. Set the fixed parameters of the region detection window and the gray-level co-occurrence matrix, and obtain the gray-level co-occurrence matrix of each local area in the grayscale image by sliding the region detection window. Obtain the texture structure of each local area in the grayscale image according to the gray-level co-occurrence matrix, compare the texture structure of each local area with the corresponding texture structure in the material properties to obtain the texture structure similarity of each local area, and mark the local areas with texture structure similarity less than the preset similarity threshold as texture abnormal areas.

[0059] It should be further noted that in the specific implementation process, the process of obtaining the texture structure of each local area in the grayscale image according to the gray-level co-occurrence matrix includes:

[0060] The gray-level co-occurrence matrix of each local region in the grayscale image is obtained by sliding the region detection window. The specific details are as follows: Quantize the gray-level of the surface image data into discrete gray-levels, divide the gray-value range into several levels. For example, an 8-bit image can be divided into 16, 32, or 64 levels, and determine the parameters required to define the gray-level co-occurrence matrix, including distance (d) and direction (θ), according to the actual application requirements. The specific steps are not elaborated here. Subsequently, based on the calculated gray-level co-occurrence matrix, a series of texture feature values are extracted to construct a texture structure. The texture feature values in the texture structure include: contrast, inverse variance, energy, homogeneity, and entropy;

[0061] The calculation formula for obtaining the texture structure similarity of each local region at the same time is:

[0062]

[0063]

[0064] where rl(e, v) represents the texture structure similarity between local region e and local region v, zf (e，v) represents the contrast between local region e and local region v, eh e represents the energy of local region e, eh v represents the energy of local region v, tk e represents the entropy of local region e, tk v represents the entropy of local region v, wp e represents the inverse variance of local region e, wp v represents the inverse variance of local region v, af e represents the homogeneity of local region e, af v represents the homogeneity of local region v, and ω3, ω4, ω5, ω6, and ω7 represent weight factors.

[0065] It should be further noted that in the specific implementation process, the Canny algorithm is used to perform edge detection on each local region of the area to be determined for heat preservation performance, and the process of obtaining the damaged abnormal area includes:

[0066] Use the Canny algorithm to perform edge detection on each local region in the grayscale image, obtain the edge image of each local region, extract features from the edge image of each local region, obtain the edge feature set of the edge image. The various types of edge features in the edge feature set include edge length (i.e., the total length of the edge, which can be used to evaluate the integrity of the edge), the number of edge branches (i.e., the number of branches of the edge, and broken edges usually have more branches), continuity measure (used to define a measure to evaluate the continuity of the edge, and the continuity measure is equal to the ratio of the total length of the edge breaks to the total length), edge curvature (i.e., the curvature distribution of the edge, and smooth edges usually have small curvature changes), and edge roughness (i.e., the standard deviation between edge pixels, used to evaluate the smoothness of the edge).

[0067] Using the various types of edge features in the edge feature set of the edge image as evaluation indicators, set the index weight matrix of the evaluation indicators, obtain the membership degree matrix of the edge feature set for the preset complexity level through fuzzy comprehensive evaluation, obtain the corresponding complexity level of the edge feature set according to the membership degree matrix and the index weight matrix, mark the local regions corresponding to the edge feature sets with complexity levels greater than the preset complexity level threshold as damaged abnormal regions, and at the same time predict the change trend of the complexity level of the local regions not marked as damaged abnormal regions.

[0068] It should be further noted that in the specific implementation process, the process of predicting the change trend of the complexity level of the local regions not marked as damaged abnormal regions to obtain potential damaged regions includes:

[0069] Pre-construct a visual detection database, which is used to store the historical visual detection records of several building exterior wall materials. Obtain the historical complexity level time series of each local region not marked as damaged abnormal regions according to the historical visual detection records. Build a complexity level prediction model based on deep learning. Use the historical complexity level time series of each local region not marked as damaged abnormal regions as the training set and the test set. Input the training set into the complexity level prediction model for training until the loss function is trained stably, and save the model parameters. Test the complexity level prediction model through the test set until it meets the preset requirements, and output the complexity level prediction model.

[0070] Obtain the predicted complexity level of each local region not marked as damaged abnormal regions according to the complexity level prediction model, compare the predicted complexity level with the complexity level threshold. If the predicted complexity level of the local region not marked as damaged abnormal regions is greater than the complexity level threshold, then mark the local region not marked as damaged abnormal regions as potential damaged regions.

[0071] Subsequently, the areas with abnormal color pixel distributions, abnormal texture areas, abnormal damage areas, and potential damage areas in the areas with unqualified heat preservation performance and the areas with undetermined heat preservation performance are fed back to the relevant management personnel. The relevant management personnel provide repair suggestions based on the feedback information. For example, for small-scale damage, it can be directly repaired. For large-scale damage to the heat preservation material, overall replacement needs to be considered. For potential damage areas that are prone to problems, additional waterproof or heat preservation measures can be considered.

[0072] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical method of the present invention can be modified or replaced without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A visual inspection method for building exterior wall thermal insulation materials, characterized in that, It includes the following steps: Step S1: Obtain the material properties and external environment data of the building exterior wall material to be detected. Determine whether to perform a visual inspection operation on the building exterior wall material based on the external environment data. When the external environment data meets the operation standard, obtain the shooting parameters of the building exterior wall material to be detected; Step S2: Determine whether the external environment data of the building exterior wall material to be detected can perform an infrared image detection operation, and obtain the area with unqualified heat preservation performance and the area with undetermined heat preservation performance according to the judgment result; Step S3: Perform a visual image detection operation on the area with undetermined heat preservation performance, obtain color abnormal pixel points and texture analysis angles, and perform local area texture analysis on the area with undetermined heat preservation performance according to the texture analysis angles to obtain the texture abnormal area; Step S4: Use the Canny algorithm to perform edge detection on each local area of the area with undetermined heat preservation performance to obtain the damaged abnormal area. At the same time, predict the change trend of the complexity level of the local areas not marked as damaged abnormal areas to obtain the potential damaged areas; The process of using the Canny algorithm to perform edge detection on each local area of the area with undetermined heat preservation performance to obtain the damaged abnormal area includes: Use the Canny algorithm to perform edge detection on each local area in the grayscale image to obtain the edge image of each local area. Extract the features of the edge image of each local area to obtain the edge feature set of the edge image. The various types of edge features in the edge feature set include edge length, edge branch number, continuity measure, edge curvature, and edge roughness; Taking the various types of edge features in the edge feature set of the edge image as evaluation indicators, set the index weight matrix of the evaluation indicators. Obtain the membership degree matrix of the edge feature set for the preset complexity level through fuzzy comprehensive evaluation. According to the membership degree matrix and the index weight matrix, obtain the complexity level corresponding to the edge feature set. Mark the local area corresponding to the edge feature set with a complexity level greater than the preset complexity level threshold as the damaged abnormal area. At the same time, predict the change trend of the complexity level of the local areas not marked as damaged abnormal areas; The process of predicting the change trend of the complexity level of the local areas not marked as damaged abnormal areas to obtain the potential damaged areas includes: Pre-construct a visual detection database, which is used to store the historical visual detection records of several building exterior wall materials. Obtain the historical complexity level time series of each local area not marked as damaged abnormal areas according to the historical visual detection records. Build a complexity level prediction model based on deep learning. Use the historical complexity level time series of each local area not marked as damaged abnormal areas as the training set and the test set. Input the training set into the complexity level prediction model for training until the loss function is trained stably, and save the model parameters. Test the complexity level prediction model through the test set until it meets the preset requirements, and output the complexity level prediction model; According to the complexity level estimation model, the estimated complexity level of each local area not marked as a damaged abnormal area is obtained, and the estimated complexity level is compared with the complexity level threshold. If the estimated complexity level of the local area not marked as a damaged abnormal area is greater than the complexity level threshold, the local area not marked as a damaged abnormal area is marked as a potential damaged area.

2. The visual inspection method for an exterior wall thermal insulation material of a building according to claim 1, characterized in that, The process of obtaining material properties and external environment data of the building exterior wall material to be inspected and determining whether to perform visual inspection of the building exterior wall material according to the external environment data includes: Obtain material properties and external environment data of the building exterior wall material to be detected, wherein the material properties include color characteristics, reflective characteristics and texture structure, and the external environment data include indoor building temperature, outdoor building temperature, light intensity, wind speed and precipitation intensity, obtain the building outdoor temperature, wind speed and precipitation intensity corresponding to the building exterior wall material to be detected, and compare the building outdoor temperature, wind speed and precipitation intensity corresponding to the building exterior wall material to be detected with the preset temperature limit threshold, the preset wind speed limit threshold and the preset precipitation intensity limit threshold respectively; if the building outdoor temperature, wind speed and precipitation intensity corresponding to the building exterior wall material to be detected are all less than the corresponding temperature limit threshold, wind speed limit threshold and precipitation intensity limit threshold, then perform a visual inspection operation on the building exterior wall material to be detected; if the building outdoor temperature, wind speed or precipitation intensity corresponding to the building exterior wall material to be detected is greater than the corresponding temperature limit threshold, wind speed limit threshold and precipitation intensity limit threshold, then suspend the visual inspection operation on the building exterior wall material to be detected.

3. The visual inspection method for an exterior wall thermal insulation material of a building according to claim 2, wherein The process of obtaining the shooting parameters of the building exterior wall material to be inspected includes: According to the wind speed and precipitation intensity corresponding to the building exterior wall materials to be tested as evaluation indicators, the indicator weights of the evaluation indicators are set, and the membership matrix of the building exterior wall materials to be tested for the preset interference level is obtained through fuzzy comprehensive evaluation; The interference level of the building exterior wall material to be detected is obtained through the membership matrix and the indicator weight, and an adaptive shooting parameter comparison table is pre-constructed. The adaptive shooting parameter comparison table includes shooting parameters corresponding to different interference levels. The shooting parameters include resolution and frame number. The shooting parameters of the building exterior wall material to be detected are determined according to the interference level of the building exterior wall material to be detected.

4. A visual inspection method for an exterior wall thermal insulation material of a building according to claim 3, characterized in that, The process of judging whether the external environment data of the building exterior wall material to be inspected can be subjected to infrared image inspection operation, and obtaining the area with unqualified thermal insulation performance and the area with undetermined thermal insulation performance according to the judgment result includes: Obtain the temperature difference between the indoor temperature and the outdoor temperature of the building based on the external environmental data of the building exterior wall material to be detected, mark the temperature difference as the first temperature difference, compare the first temperature difference with a preset temperature difference threshold. When the temperature difference is greater than or equal to the temperature difference threshold, select threshold points within the first temperature difference to divide it into temperature difference sub-intervals with different heat insulation performance levels. Set the emissivity of the UAV camera terminal according to the material properties of the building exterior wall material to be detected. Use the UAV camera terminal to perform infrared scanning on the building exterior wall material to be detected, obtain an infrared image, and based on the preset temperature lookup table of the UAV camera terminal, obtain the temperature corresponding to the gray value of each pixel point in the infrared image. Obtain the temperature difference between the temperature corresponding to each pixel point and the outdoor temperature of the building, mark the temperature difference as the second temperature difference, match the second temperature difference with the temperature difference sub-intervals of different heat insulation performance levels, obtain the heat insulation performance level corresponding to each pixel point, compare the heat insulation performance level corresponding to each pixel point with a preset heat insulation performance level threshold, mark the distribution area of the pixel points with a heat insulation performance level lower than the heat insulation performance level threshold as the unqualified area of heat insulation performance, and mark the distribution area of the pixel points with a heat insulation performance level greater than or equal to the heat insulation performance level threshold as the area of undetermined heat insulation performance, and perform visual image detection operations on the area of undetermined heat insulation performance; When the temperature difference is less than the temperature difference threshold, mark all areas covered by the building exterior wall material to be detected as the area of undetermined heat insulation performance, and perform visual image detection operations on the area of undetermined heat insulation performance.

5. A visual inspection method for an exterior wall thermal insulation material of a building according to claim 4, characterized in that The process of performing visual image detection operations on the area of undetermined heat insulation performance to obtain color abnormal pixel points and texture analysis angles includes: Use the UAV camera terminal to perform multi-angle image scanning on the area of undetermined heat insulation performance of the building exterior wall material to be detected, obtain the multi-angle surface color image of the area of undetermined heat insulation performance, and convert the multi-angle surface color image from the preset BGR color space to the HSV color space. Subsequently, extract the color features of each pixel point in the multi-angle surface color image. The color features include hue, saturation, and light value. Compare the hue and saturation of each pixel point with the corresponding hue and saturation of the material properties respectively to obtain the color difference value of each pixel point, and mark the pixel points with a color difference value greater than the preset color difference value threshold as color abnormal pixel points; According to the light value corresponding to each pixel point in the multi-angle surface color image, obtain the average light value and the standard deviation of the light value corresponding to different angles in the multi-angle surface color image. Obtain the texture feature judgment value based on the average light value and the standard deviation of the light value, and select the angle corresponding to the maximum texture feature judgment value among different angles as the texture analysis angle.

6. The visual inspection method for an exterior wall thermal insulation material of a building according to claim 5, characterized in that, The process of performing local area texture analysis on the area of undetermined heat insulation performance according to the texture analysis angle to obtain the texture abnormal area includes: Perform denoising and grayscale processing on the surface color image corresponding to the texture analysis angle in the multi-angle surface color image of the area with undetermined heat preservation performance to obtain a grayscale image. Set the fixed parameters of the region detection window and the gray-level co-occurrence matrix. Obtain the gray-level co-occurrence matrix of each local region in the grayscale image by sliding the region detection window. Obtain the texture structure of each local region in the grayscale image according to the gray-level co-occurrence matrix. Compare the texture structures of each local region with the corresponding texture structures in the material properties to obtain the texture structure similarity of each local region. Mark the local regions with texture structure similarity less than the preset similarity threshold as texture abnormal regions.

Images