A crack recognition method and device based on multi-scale infrared thermal feature fusion

Abstract

A crack identification method and device based on multi-scale infrared thermal feature fusion, the method comprising: obtaining a grayscale image of cracks and noise for a single-frame infrared thermal image; adjusting the grayscale distribution of the image using histogram equalization to obtain a grayscale enhanced image; setting a larger local feature sensitivity weight coefficient for the background dominant window and the noise dominant window, and setting a smaller local feature sensitivity weight coefficient for the target composite window; counting the number of foreground pixels in each window, and calculating the ratio of the number of foreground pixels to the total number of pixels; identifying the background dominant window, the noise dominant window, and the target composite window; setting the background dominant window, the noise dominant window, and the target composite window; and The local feature sensitivity weight coefficients of the dominant window, noise dominant window, and target composite window are calculated; the grayscale enhanced image is segmented to obtain a binary image, and the connected domain of the foreground pixels is extracted; for each foreground pixel connected domain, the total number of pixels is calculated, several seed points are randomly selected, the corresponding maximum inscribed circle is determined, the mean of the diameters of all maximum inscribed circles is used as the width, the ratio of the total number of pixels to the width is used as the length, and the connected domain with an aspect ratio less than 10 is considered as noise and screened out; the foreground pixel connected domain is optimized, small noise is removed, and the contour is smoothed. The final foreground pixel connected domain is considered as a crack.

Description

Technical Field

[0001] The present invention relates to the field of defect detection technology, and in particular to a crack identification method and device based on multi-scale infrared thermal feature fusion. Background Art

[0002] Cracks are one of the most common forms of structural surface damage. Their characteristics, such as type, density, and width, reflect the extent of structural damage and serve as key indicators for assessing their condition. Therefore, crack detection is a crucial component of structural maintenance. The microenvironment at the crack site interferes with heat flow distribution, resulting in temperature anomalies. Infrared thermal imaging, a nondestructive testing technique that infers the surface condition and internal structure of an object by detecting surface temperature differences caused by varying thermal properties, is gaining increasing attention in the crack detection field.

[0003] Although infrared thermal imaging crack detection technology has been applied to some extent, the level of automation and intelligence in crack identification remains low, making it difficult to achieve fast and efficient crack identification in infrared thermal images. Threshold segmentation is a common image segmentation algorithm that has been widely used for crack identification. Based on the segmentation strategy, threshold segmentation algorithms can be divided into global threshold segmentation and local threshold segmentation algorithms. However, due to the low signal-to-noise ratio of crack infrared thermal images, which leads to severe noise interference, global threshold segmentation algorithms are difficult to implement for crack identification. In comparison, local threshold segmentation algorithms have stronger noise immunity, but the local threshold still requires empirical determination, which cannot meet the requirements of automated and intelligent crack identification, limiting their large-scale application. In recent years, deep learning has gradually gained attention for infrared thermal image defect recognition due to its powerful feature learning capabilities and environmental adaptability. However, deep learning uses image features such as color, shape, and texture to identify cracks. However, the low resolution and heavy noise interference of infrared thermal images result in insufficient crack feature information, limiting crack identification accuracy. Furthermore, the lack of large-scale and diverse infrared thermal image datasets further restricts the application of deep learning for infrared thermal image crack identification. It can be seen that infrared thermal image crack recognition still needs an automated and intelligent recognition method. Summary of the Invention

[0004] The present invention aims to overcome the problems existing in the above-mentioned prior art and provides a crack identification method and device based on multi-scale infrared thermal feature fusion, which realizes rapid and automatic crack identification.

[0005] The key to this invention is to use the local statistical features of the binarized image obtained by the global threshold segmentation algorithm to establish an adaptive threshold determination criterion for the local threshold segmentation algorithm, overcoming the common methods' reliance on manual labor and models, and having the advantages of strong adaptability, low computing power requirements, and high robustness.

[0006] In order to achieve the above technical objectives, the technical solutions adopted by the present invention are:

[0007] A crack identification method based on multi-scale infrared thermal feature fusion includes the following steps:

[0008] (1) For a single-frame infrared thermal image, weighted average grayscale conversion is performed. If the crack appears as a low-temperature "cold spot", grayscale inversion is further performed to obtain a grayscale image in which the crack and noise have high grayscale values and the background has low grayscale values.

[0009] (2) For the grayscale image obtained by processing in step (1), histogram equalization is used to adjust the grayscale distribution of the image, enhance the contrast of the cracks in the image, and obtain a grayscale enhanced image.

[0010] (3) For the grayscale enhanced image obtained by step (2), a sliding window is used to traverse the image, and local statistical features such as the mean and standard deviation of the grayscale in each window are calculated. A larger local feature sensitivity weight coefficient is set for the background dominant window and the noise dominant window, and a relatively smaller local feature sensitivity weight coefficient is set for the target composite window.

[0011] (4) For the grayscale enhanced image obtained by processing in step (2), the Otsu algorithm is used to obtain a binary image. A sliding window of the same size as in step (3) is used to traverse the image, and the number of foreground pixels in each window is counted. The ratio of the number of foreground pixels to the total number of pixels, i.e., the foreground pixel ratio, is calculated.

[0012] (5) Calculate the quartiles for the foreground pixel ratios of all windows obtained in step (4). The windows corresponding to the foreground pixel ratios in the lower quartile are identified as background-dominated windows, the windows corresponding to the foreground pixel ratios in the upper quartile are identified as noise-dominated windows, and the windows corresponding to the foreground pixel ratios in the middle quartile are identified as target composite windows.

[0013] (6) According to the window type identified in step (5), the background-dominant window uses the background pixel ratio as the local feature sensitivity weight coefficient, the noise-dominant window uses the foreground pixel ratio as the local feature sensitivity weight coefficient, and the target composite window also uses the foreground pixel ratio as the local feature sensitivity weight coefficient.

[0014] (7) The grayscale mean value of the sliding window obtained by step (3) is added to the grayscale standard deviation and multiplied by the local feature sensitivity weight coefficient obtained by step (6) to obtain the grayscale threshold of each window, and the grayscale enhanced image obtained by step (2) is segmented to obtain a binary image, and the connected domain of the foreground pixels is extracted.

[0015] (8) For each connected domain of foreground pixels obtained by step (7), calculate the total number of pixels, randomly select several seed points, determine the corresponding maximum inscribed circle, take the mean of the diameters of all the maximum inscribed circles as the width, take the ratio of the total number of pixels to the width as the length, and consider the connected domain with an aspect ratio less than 10 as noise and filter it out.

[0016] (9) For the binary image processed in step (8), the morphological opening operation is used to optimize the foreground pixel connected domain, remove small noise, and smooth the contour. The final foreground pixel connected domain is regarded as the crack.

[0017] Furthermore, in step (3), when the size of the sliding window is between 1 / 8 and 1 / 12 of the corresponding side length of the original image, there is no significant difference in the binary images obtained by segmentation. Therefore, a sliding window with a size of 1 / 10 of the corresponding side length of the original image can be used to traverse the image. In addition, when the background ratio in the window is high, the weight coefficient is small and the threshold is reduced, which is conducive to extracting small targets; when the noise ratio in the window is high, the weight coefficient is large and the threshold is increased, which is conducive to suppressing noise. Therefore, the crack recognition method based on multi-scale infrared thermal feature fusion also has excellent small target segmentation and noise suppression capabilities.

[0018] Furthermore, in step (4), there are differences in the foreground pixel ratios of the three types of windows in the Otsu binarized image. The foreground pixel ratio of the background-dominated window is extremely small, the foreground pixel ratio of the noise-dominated window is extremely large, and the foreground pixel ratio of the target composite window is between the two. Therefore, the foreground pixel ratios of each sliding window can be used for window classification later.

[0019] Furthermore, in step (5), for the Otsu binary image, its foreground pixel ratio histogram will show a clear U-shaped distribution. Therefore, the foreground pixel ratio quartiles can be used to divide it into the left high-frequency region (lower quartile region), the middle low-frequency region (middle quartile region), and the right high-frequency region (upper quartile region), which correspond to the background dominant window, the target composite window, and the noise dominant window, respectively.

[0020] Furthermore, in step (6), the expected value of the local feature sensitivity weight coefficient of each sliding window is basically consistent with the distribution characteristics of the sliding window pixel ratio. Therefore, the local feature sensitivity weight coefficient of each sliding window can be adaptively determined according to the determination criterion of step (6). Specifically, it can be calculated by the following formula:

[0021]

[0022] Where k is the weight coefficient of local feature sensitivity, r is the foreground pixel ratio in the Otsu binarized image window, Q1 is the lower quartile, and Q3 is the upper quartile.

[0023] The second aspect of the present invention relates to a crack identification device based on multi-scale infrared thermal feature fusion, comprising a memory and one or more processors, wherein the memory stores executable code, and when the one or more processors execute the executable code, they are used to implement the crack identification method based on multi-scale infrared thermal feature fusion of the present invention.

[0024] A third aspect of the present invention relates to a computer-readable storage medium having a program stored thereon, which, when executed by a processor, implements the crack identification method based on multi-scale infrared thermal feature fusion of the present invention.

[0025] Compared with the prior art, the present invention has the following beneficial effects:

[0026] (1) Based on the infrared thermal images of cracks, an adaptive determination criterion for the local threshold is developed by utilizing its multi-scale infrared thermal characteristics. It can adapt to a variety of complex working conditions and has excellent environmental adaptability.

[0027] (2) The present invention realizes fully automatic crack recognition of single-frame infrared thermal images through an adaptive threshold determination mechanism, without the need for human intervention throughout the process. It has the advantages of strong adaptability, low computing power requirements, and high robustness.

[0028] (3) The results of the present invention are highly readable, user-friendly, and have fast recognition efficiency. They can be used as an edge computing module for infrared thermal imaging technology, avoiding the transmission of large-scale image data, and are particularly suitable for edge computing scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 is a flow chart of the steps of the present invention.

[0030] Figure 2 It is a schematic diagram of the device of the present invention. DETAILED DESCRIPTION

[0031] The specific implementation of the present invention will be further described below with reference to specific embodiments and in conjunction with the accompanying drawings.

[0032] Example 1

[0033] This embodiment relates to a crack identification method based on multi-scale infrared thermal feature fusion, comprising the following steps:

[0034] (1) Since infrared thermal images use RGB three-channel pseudo-color to represent the temperature information in the image, in order to simplify the subsequent image processing process and restore the one-to-one correspondence between temperature and color, the grayscale algorithm is used to restore the infrared thermal image to a grayscale image, that is, an image composed of pixels with grayscale values ranging from 0 to 255. First, the RGB three-channel components of each pixel in the infrared pseudo-color image are extracted. Then, the grayscale value of each pixel is calculated using the weighted average method, that is:

[0035] I(x,y)=αR(x,y)+βG(x,y)+γB(x,y) (2)

[0036] Where I(x,y) is the pixel grayscale value, R(x,y), G(x,y), and B(x,y) are the red, green, and blue channel components, respectively. α, β, and γ are the corresponding weighting coefficients. This paper uses commonly used weighting coefficients of 0.30, 0.59, and 0.11, respectively. Finally, a grayscale image is obtained in which the grayscale value fully reflects the temperature. For images with cracks that appear as low-temperature "cold spots," grayscale inversion is further used to convert the target (crack) and noise into high-grayscale areas, while the background is converted into low-grayscale areas.

[0037] (2) If the RGB color distribution of the crack infrared thermal image is too concentrated, the grayscale value difference between the pixels of the corresponding grayscale image is not significant, which will make it difficult to distinguish the target crack from the background in the image, which is not conducive to subsequent crack identification. Therefore, for the grayscale image obtained by step (1), histogram equalization is used to enhance the grayscale image. Specifically, histogram equalization is an image processing method that redistributes the grayscale levels of the image to make the grayscale value distribution of the image more uniform, thereby improving the image contrast. First, calculate the grayscale histogram of the image, count the frequency of occurrence of each grayscale level and normalize the histogram:

[0038]

[0039] Where p(k) represents the probability of gray level k, and N is the total number of pixels in the image. Then, calculate the Cumulative Distribution Function (CDF):

[0040]

[0041] Where C(k) represents the cumulative probability of gray level k. As a key step in histogram equalization, it is used to accumulate the probabilities of each gray level to determine the new gray value of each pixel. Then, a new gray value is calculated for each original gray level through the cumulative distribution function. The new gray value is linearly transformed according to the cumulative distribution function, with the aim of stretching the gray level distribution of the original image so that all gray levels are evenly distributed over the entire range [0,255]. The transformation function S(v) of histogram equalization is calculated as follows:

[0042] S(v)=round(255C(v)) (5)

[0043] Where the round operator rounds to the nearest integer. The transformation function S(v) maps the grayscale values in the input image to the equalized grayscale values. Finally, the output image is obtained through the following transformation relationship:

[0044] I e (x,y)=S(I f (x,y)) (6)

[0045] Where, I e (x, y) is the grayscale value after histogram equalization processing, I f (x,y) is the grayscale value of the input image. After histogram equalization, the grayscale distribution of the output image is more uniform and the contrast is enhanced.

[0046] (3) For the grayscale enhanced image obtained by step (2), in the noise-dominated window, the grayscale mean is large and the standard deviation is small; in the target composite window, the grayscale mean is small and the standard deviation is large. Taking advantage of this difference in local statistical features, a sliding window with a size of 1 / 10 of the corresponding side length of the original image is used to traverse the grayscale enhanced image, and local statistical features such as the mean and standard deviation of each sliding window in the grayscale enhanced image are obtained.

[0047] For each type of window, a window with a large background ratio is a background-dominant window, which exhibits the statistical characteristics of low grayscale mean and small standard deviation. A larger weight coefficient is set to increase the threshold and thus separate the background. A window with a large noise ratio is a noise-dominant window, which exhibits the statistical characteristics of high grayscale mean but small standard deviation. Similarly, a larger weight coefficient is set to obtain a higher threshold and thus suppress noise. A window containing a target, background, and noise is a target composite window. Its grayscale mean is between that of the background-dominant window and the noise-dominant window, and its standard deviation is larger than that of these two types of windows. Therefore, a relatively small weight coefficient is set to obtain a smaller threshold to identify small targets. Based on this feature, the local threshold segmentation method can be used to segment cracks and separate them from the target and background.

[0048] (4) In order to adaptively set the segmentation thresholds of the three types of windows in step (3). For the grayscale enhanced image obtained by step (2), the Otsu algorithm is first used to segment the low grayscale area (background) and the high grayscale area (target and noise) to obtain the Otsu binary image. The Otsu algorithm is a threshold segmentation algorithm based on global statistical features. The algorithm adopts the maximization of the inter-class variance criterion and uses the statistical information of the image grayscale histogram to determine the optimal segmentation threshold to segment the grayscale image into foreground (high grayscale category) and background (low grayscale category). The inter-class variance is defined as

[0049] σ 2 (T) = ω0(T) [μ0(T) - μ T ] 2 +ω1(T)[μ1(T)-μ T ] 2 (7)

[0050] Where, σ 2 (T) is the inter-class variance when the segmentation threshold is T, ω0(T) and ω1(T) are the pixel ratios of foreground and background when the segmentation threshold is T, μ0(T) and μ1(T) are the average grayscale values of foreground and background pixels when the segmentation threshold is T, and μ T is the average grayscale value of the input image. The algorithm sequentially selects segmentation thresholds ranging from 0 to 255 and calculates the inter-class variance corresponding to each segmentation threshold. The optimal segmentation threshold is the one that maximizes the inter-class variance. Then, a sliding window with a size of 1 / 10 the corresponding side length of the original image is used to traverse the Otsu binarized image, and the foreground pixel ratio of each window is calculated.

[0051] (5) For the foreground pixel ratios of all windows obtained in step (4), the foreground pixel ratio histogram shows an obvious U-shaped distribution. The quartiles of the foreground pixel ratio are calculated and divided into four regions. The quartiles of the foreground pixel ratio can be used to divide it into a high-frequency region on the left, a low-frequency region in the middle, and a high-frequency region on the right. The high-frequency regions on both sides correspond to the foreground pixel ratios of the background-dominated window and the noise-dominated window in the grayscale enhanced image, respectively, and the middle continuous low-frequency region corresponds to the foreground pixel ratio of the target composite window. Accordingly, the foreground pixel ratio of the lower quartile region is extremely small and is identified as a background-dominated window; the foreground pixel ratio of the upper quartile region is extremely large and is identified as a noise-dominated window; the foreground pixel ratio of the middle quartile region (including the lower middle quartile region and the lower middle quartile region) is between the background-dominated window and the noise-dominated window and is identified as a target composite window.

[0052] (6) According to the window type identified in step (5), it can be seen that the expected value of the local feature sensitivity weight coefficient of each sliding window is basically consistent with the distribution characteristics of the sliding window pixel ratio. Therefore, the local feature sensitivity weight coefficient of each sliding window can be adaptively determined according to the determination criteria of step (5). The background dominant window uses the background pixel ratio as its local feature sensitivity weight coefficient, the noise dominant window uses the foreground pixel ratio as its local feature sensitivity weight coefficient, and the target composite window also uses the foreground pixel ratio as its local feature sensitivity weight coefficient. The specific setting method is shown in formula (1)

[0053] (7) The grayscale mean value of the sliding window obtained by step (3) plus the grayscale standard deviation is multiplied by the local feature sensitivity weight coefficient obtained by step (6) to obtain the segmentation threshold of each window, that is,

[0054] T=μ+k×σ (8)

[0055] Where T is the segmentation threshold, μ is the grayscale mean within the sliding window, σ is the grayscale standard deviation within the sliding window, and k is the weight coefficient for adjusting the sensitivity of the local features of the sliding window. The grayscale enhanced image obtained by step (2) is segmented using the local threshold to obtain a binary image. For targets with high grayscale values, in order to avoid the target being misidentified as background due to excessively high thresholds, the weight coefficient is usually set to 0-1. When the background ratio in the target composite window is high, the weight coefficient is small and the threshold is reduced, which is conducive to extracting small targets; when the noise ratio in the target composite window is high, the weight coefficient is large and the threshold is increased, which is conducive to suppressing noise. Therefore, the crack recognition method based on multi-scale infrared thermal feature fusion can also achieve small target segmentation and noise suppression within the target composite window, and has excellent adaptive performance. Therefore, for the binary image segmented by this step, the crack part is completely retained, the uniform background and noise parts are almost completely divided into background, and the non-uniform noise and background parts are divided into isolated noise points.

[0056] (8) For the binary image obtained by step (7), only cracks and isolated noise points exist in the image. For the isolated noise points after being broken and segmented, they often do not have slender morphological features and their shapes are completely irregular. At this time, there is a significant difference in morphological features between noise and cracks. By using this difference, all the foreground pixel connected areas in the image are traversed to extract the length and width corresponding to each foreground pixel connected domain. The length and width size ratio is used as the screening condition for cracks to perform noise discrimination on the target area. Among them, the width of the foreground pixel connected domain is extracted using the maximum inscribed circle. For each foreground pixel connected domain obtained by step (7), the total number of pixels is calculated, and several seed points are randomly selected to determine the corresponding maximum inscribed circle. The average of the diameters of all the maximum inscribed circles is used as the width, and the ratio of the total number of pixels to the width is used as the length. The connected domain with an aspect ratio less than 10 is regarded as noise and screened out.

[0057] (9) After the denoising process of the binary image in step (8), only the target area corresponding to the crack remains in the binary image. However, the edge contour of this area has a jagged feature due to the characteristics of the local traversal segmentation algorithm. This is because the thresholds used for the pixels near the edge contour line are not consistent. In order to smooth the crack edge contour line, morphological processing is performed on the denoised binary image to make the recognition results of the crack recognition algorithm more user-friendly and readable.

[0058] Morphological processing is a mathematical algorithm based on set theory that manipulates the shape, structure, and topological relationships in images. It uses basic algorithms such as dilation and erosion to modify and extract image features. In morphological processing, a structuring element is first defined. Using the dilation algorithm, the structuring element is overlaid with the image, the maximum pixel value in the image is found, and the value is assigned to the corresponding pixel in the resulting image. Dilation expands the image and fills holes. Using the erosion algorithm, the structuring element is overlaid with the image, the minimum pixel value in the image is found, and the value is assigned to the corresponding pixel in the resulting image. Erosion reduces the image area and removes isolated pixels. Furthermore, erosion and dilation operations can be combined to perform opening and closing operations. Since the boundary discontinuity of the crack binary image after denoising is low, the jagged features on the boundary are mainly due to small protrusions of foreground pixels. Therefore, an opening morphological processing method using erosion followed by dilation is used to smooth the crack boundary contours, resulting in a binary image of the crack, which can be used to further determine the cracking condition.

[0059] Example 2

[0060] Reference Figure 2This embodiment relates to a crack identification device based on multi-scale infrared thermal feature fusion, including a memory and one or more processors, wherein the memory stores executable code, and when the one or more processors execute the executable code, they are used to implement the crack identification method based on multi-scale infrared thermal feature fusion of Example 1.

[0061] Example 3

[0062] This embodiment relates to a computer-readable storage medium having a program stored thereon. When the program is executed by a processor, the crack identification method based on multi-scale infrared thermal feature fusion of embodiment 1 is implemented.

[0063] The specific description of the present invention in the above embodiments is only used to further illustrate the present invention and cannot be understood as limiting the scope of protection of the present invention. Technical engineers in this field may make some non-essential improvements and adjustments to the present invention based on the contents of the above invention, which fall within the scope of protection of the present invention.

Claims

1. A crack identification method based on multi-scale infrared thermal feature fusion, comprising the following steps: (1) For a single-frame infrared thermal image, weighted average grayscale conversion is performed. If the crack is a low-temperature "cold spot", grayscale inversion is further performed to obtain a grayscale image in which the crack and noise have high grayscale values and the background has low grayscale values; (2) For the grayscale image obtained by step (1), histogram equalization is used to adjust the grayscale distribution of the image, enhance the contrast of the cracks in the image, and obtain a grayscale enhanced image; (3) For the grayscale enhanced image obtained by step (2), use a sliding window to traverse the image, calculate the mean and standard deviation of the grayscale in each window, set a larger local feature sensitivity weight coefficient for the background dominant window and the noise dominant window, and set a relatively smaller local feature sensitivity weight coefficient for the target composite window; (4) For the grayscale enhanced image obtained by step (2), the Otsu algorithm is used to obtain a binary image. A sliding window of the same size as in step (3) is used to traverse the image, and the number of foreground pixels in each window is counted. The ratio of the number of foreground pixels to the total number of pixels is calculated, i.e., the foreground pixel ratio. (5) Calculate the quartiles of the foreground pixel ratios of all windows obtained in step (4). The windows corresponding to the foreground pixel ratios in the lower quartile are identified as background-dominated windows, the windows corresponding to the foreground pixel ratios in the upper quartile are identified as noise-dominated windows, and the windows corresponding to the foreground pixel ratios in the middle quartile are identified as target composite windows. (6) According to the window type identified in step (5), the background-dominant window uses the background pixel ratio as the local feature sensitivity weight coefficient, the noise-dominant window uses the foreground pixel ratio as the local feature sensitivity weight coefficient, and the target composite window also uses the foreground pixel ratio as the local feature sensitivity weight coefficient; (7) Add the grayscale mean value of the sliding window obtained by step (3) to the grayscale standard deviation and multiply it by the local feature sensitivity weight coefficient obtained by step (6) to obtain the grayscale threshold of each window, segment the grayscale enhanced image obtained by step (2) to obtain a binary image, and extract the connected domain of the foreground pixels; (8) For each connected domain of foreground pixels obtained by step (7), calculate the total number of pixels, randomly select several seed points, determine the corresponding maximum inscribed circle, take the mean of the diameters of all the maximum inscribed circles as the width, take the ratio of the total number of pixels to the width as the length, and consider the connected domains with an aspect ratio less than 10 as noise and filter them out; (9) For the binary image processed in step (8), the morphological opening operation is used to optimize the foreground pixel connected domain, remove small noise, and smooth the contour. The final foreground pixel connected domain is regarded as the crack.

2. The crack identification method based on multi-scale infrared thermal feature fusion according to claim 1, characterized in that: In step (3), a sliding window with a size of 1 / 10 of the side length of the original image is used to traverse the image. When the background ratio in the window is high, the weight coefficient is small and the threshold is reduced, which is conducive to extracting small targets.

3. The crack identification method based on multi-scale infrared thermal feature fusion according to claim 1, characterized in that: In step (5), for the Otsu binary image, its foreground pixel ratio histogram will show an obvious U-shaped distribution. The quartiles of the foreground pixel ratio are used to divide it into the left high-frequency area, the middle low-frequency area and the right high-frequency area, which correspond to the background dominant window, the target composite window and the noise dominant window respectively.

4. The crack identification method based on multi-scale infrared thermal feature fusion according to claim 1, characterized in that: In step (6), the expected value of the local feature sensitivity weight coefficient of each sliding window is consistent with the distribution characteristics of the sliding window pixel ratio. The local feature sensitivity weight coefficient of each sliding window is adaptively determined according to the determination criteria of step (6): Where, k is the weight coefficient of local feature sensitivity, r is the ratio of foreground pixels in the Otsu binary image window, Q 1 is the lower quartile, Q 3 is the upper quartile.

5. A crack identification device based on multi-scale infrared thermal feature fusion, characterized in that: The method comprises a memory and one or more processors, wherein the memory stores executable code, and when the one or more processors execute the executable code, the method is used to implement the crack identification method based on multi-scale infrared thermal feature fusion according to any one of claims 1 to 4.

6. A computer-readable storage medium, characterized in that A program is stored thereon, and when the program is executed by a processor, the crack identification method based on multi-scale infrared thermal feature fusion according to any one of claims 1 to 4 is implemented.

Images