An adaptive crack identification and quantification method around open pits

Abstract

The present invention discloses an adaptive crack identification and quantification method around an open-pit mine, including image preprocessing and crack identification steps. In view of the complexity of the open-pit mine environment, the present invention adopts a Gaussian pyramid to perform multi-scale analysis on the image, and realizes grayscale equalization through gamma transformation to adapt to the crack identification needs under different lighting conditions; in the crack identification part, the present invention uses an improved difference entropy to optimize the local threshold segmentation algorithm, aiming to achieve high-efficiency and high-precision detection of mine cracks. This method can dynamically determine the segmentation threshold according to the grayscale distribution of the local area of ​​the image, effectively improving the accuracy and robustness of crack identification; the method of the present invention not only greatly improves the automation level of crack detection, but also provides strong technical support for the safety management and risk warning of open-pit mines, and has important practical application value and broad market prospects.

Description

Technical Field

[0001] The present invention belongs to the field of computer vision technology, and in particular relates to an adaptive crack identification and quantification method around an open pit. Background Art

[0002] Slope safety is a core issue in open-pit mining operations. Slope stability is directly linked to operational safety and production efficiency. Slope instability can lead to geological disasters such as landslides and debris flows, which not only threaten worker safety but also cause significant economic losses and environmental damage. Therefore, effective slope stability monitoring and management are crucial measures to ensure safe mining operations.

[0003] Crack detection, as an early sign of slope instability, is crucial for preventing geological disasters. While image processing-based crack detection has improved detection efficiency to some extent, these technologies often lack sufficient adaptability, making them difficult to cope with the complex and changing conditions found in mining environments, and their recognition accuracy still needs to be improved. While deep learning technology has made significant progress in image recognition, its application in mining slope crack detection suffers from limited generalization and accuracy due to the complexity of the data and the variability of the environment. Furthermore, deep learning models' reliance on large amounts of annotated data and high demand for computing resources pose significant challenges in mining scenarios. For example, Zhao Yiqing et al. discussed the application of deep learning for crack detection in geotechnical engineering, but also noted the deep learning model's reliance on large amounts of annotated data, high computational resource consumption, and poor generalization in complex environments. Jing Ying et al. proposed an intelligent crack detection algorithm based on an improved Mask R-CNN. The article noted that traditional image processing algorithms often fail to detect crack images in open-pit mining slopes due to complex background textures, diverse noise, and irregular crack distribution. Although deep learning methods perform well in recognition accuracy, algorithm robustness, and generalization ability, in practical applications, model training requires a large amount of computing resources and a complex training process, which is impractical in resource-constrained field environments.

[0004] In view of this, it is particularly important to develop a detection method that can automatically adapt to the mining environment and accurately identify cracks. Summary of the Invention

[0005] In order to solve the above technical problems, the purpose of the present invention is to provide an adaptive crack identification and quantification method around open-pit mines. Through high-accuracy crack detection, an efficient and reliable solution is provided for the stability monitoring and management of mining slopes. This method does not require human intervention, can monitor the slope status in real time, and detect cracks in time, thereby providing strong technical support for safe production in mining areas.

[0006] The object of the present invention is achieved by comprising the following steps:

[0007] S100, image preprocessing: first convert the original image into a grayscale image, then construct a Gaussian image pyramid, use Gaussian filtering to smooth the image, and use adaptive gamma transform to perform image enhancement;

[0008] S200, crack identification:

[0009] S201, improved difference entropy: fitting the parameters of the local threshold segmentation algorithm based on the improved difference entropy method, specifically:

[0010] S2011. Calculate the weighted difference between the center pixel and other pixels based on a sliding window and a Gaussian weight matrix: Assume that a sliding window of arbitrary radius is used to traverse all pixels of the image, and calculate the difference between the grayscale values ​​of the center pixel of the window and the remaining pixels, that is, the grayscale difference matrix (DMij) of a single pixel. The grayscale difference value ranges from [0, 255], and the difference value of the center element of the grayscale difference matrix is ​​0. Based on the probability density function of the two-dimensional Gaussian distribution, generate an n×n weight matrix. Since the center of the difference matrix is ​​0, the weight of the center of the matrix is ​​distributed to the other elements according to the weights of the remaining elements. The probability density function of the two-dimensional Gaussian distribution is:

[0011] ,

[0012] in, is a two-dimensional random variable, μ is the mean vector, Σ is the covariance matrix, |Σ| represents the determinant of the covariance matrix;

[0013] S2012. Establish a distribution law of differences: Using the grayscale difference matrix (DM) and weight matrix of each pixel, record the weight of each difference in the grayscale difference matrix (DM), i.e., the weighted number of times each difference appears, and then obtain the distribution X of the grayscale value differences between each pixel of the image and its surrounding pixels;

[0014] S2013. Substitute the improved difference entropy formula: The calculation formula of the improved difference entropy H(x) is:

[0015] ,

[0016] Where i is the value of the difference, n is the number of gray levels, and P(x) is the distribution rate of the difference;

[0017] S202, parameter fitting:

[0018] S2021. Through the local threshold segmentation parameter analysis experiment, obtain sufficient optimal sensitivity and optimal minimum standard deviation threshold data when the crack recognition effect is best; the local threshold segmentation parameter analysis experiment is specifically performed by applying the local threshold segmentation algorithm to a set of experimental images, and finding the optimal segmentation parameters for each image when the segmentation effect is best.

[0019] S2022. Based on the least squares fitting method, the difference entropy of each experimental image is fitted with the optimal parameters of the image, and a functional relationship is established;

[0020] S203, adaptive threshold segmentation based on local threshold segmentation algorithm:

[0021] S2031. Using a sliding window of definable size, calculate the mean and standard deviation of the grayscale values ​​of pixels within the window;

[0022] S2032, calculating the mean and mode of the entire image, and comparing the mean and mode. If the mean is smaller, the foreground grayscale value is lower than the background, and if the mean is larger, the foreground grayscale value is higher than the background, thereby distinguishing whether the image foreground has a higher grayscale value or a lower grayscale value;

[0023] S2033. Segment the foreground and background in the sliding window using standard deviation segmentation, brightness parameters, and sensitivity parameters, where the foreground is the crack.

[0024] In step S202, the sensitivity parameter is the sensitivity of the local threshold segmentation algorithm when segmenting the image based on the standard deviation; the minimum calibration difference parameter is the minimum threshold when the local threshold segmentation algorithm segments the image based on the standard deviation; since the standard deviation is used to measure the degree of discreteness of a set of pixel values ​​and is closely related to the difference entropy, the optimal sensitivity of the sufficient image is fitted with the optimal minimum standard deviation threshold and the difference entropy based on the least squares fitting method, and a functional relationship is established.

[0025] Preferably, in step S100 , in constructing the Gaussian image pyramid, the grayscale image is downsampled three times to generate a four-layer pyramid structure, and the image of each layer of the structure is divided into the same size.

[0026] The grayscale mean values ​​of different parts of the original grayscale image are uneven. The present invention uses adaptive gamma transformation to perform grayscale stretching, and realizes the adaptation of gamma transformation parameters based on the average grayscale value of the image. Preferably, in step S100, when performing image enhancement using adaptive gamma transformation, the adaptive gamma transformation is used to perform grayscale stretching on all images. The gamma transformation formula is:

[0027] ,

[0028] Among them, P out(x, y) is the pixel value at the output (x, y); A is a constant (gain) used to adjust the range of the output brightness; P in (x, y) is the pixel value at the input (x, y); γ is the gamma value, which is a positive real number, 0 ≤ γ ≤ 5, used to control the shape of the gamma curve. When γ = 1, the gamma curve is a straight line, and the gray value of the image will not change after mapping;

[0029] Calculate the adaptive gamma value according to the average gray value. The formula is:

[0030] ,

[0031] where μ is the average gray value of the image, and T is the standard gray value; when T = μ, the image remains unchanged; t is a control parameter used to prevent over-enhancement of the image; when the average gray value of the image is too low, the gamma value calculated using is too small, resulting in an overly high average gray value of the image after gamma transformation. Therefore, the parameter t is introduced. When μ < t, use to calculate the gamma value.

[0032] Preferably, it further includes the post-processing step of S300, which specifically includes the following steps:

[0033] S301, Connected component analysis and screening: Perform connected component analysis on the foreground segmented in step S2033, and perform connected component screening based on the area of the region and the average gray value of the region, where the area threshold of the region is positively correlated with the image size;

[0034] S302, Construct a shadow area recognition method to remove the shadow area: Select an arbitrary region and determine its skeleton; Select evenly spaced seed points on its skeleton, set the gray difference threshold, and perform directional growth along the normal; Calculate the shadow area on both sides of the region based on the growth degree of the seed points. If the area of the grown region is too large, then this region is a shadow. The calculation formula for the shadow area S is:

[0035] ,

[0036] where l i is the growth length of the i-th seed, and d is the set interval of the seeds;

[0037] Remove the shadow area.

[0038] Preferably, it further includes S400 crack quantification, which specifically includes:

[0039] (1) Crack classification: Based on the number of crack intersections and branches, distinguish the crack category as a strip crack or a mesh crack;

[0040] (2) Direction and length calculation: The direction and length of the crack skeleton are calculated as the direction and length of the crack;

[0041] (3) Width calculation: uniformly spaced seed points are selected along the skeleton, and directional growth is performed along the normal line. The average growth length is calculated, which is the crack width;

[0042] The above (1), (2), and (3) are in no particular order.

[0043] Compared with the prior art, the present invention has the following technical effects:

[0044] 1. In view of the complexity of the open pit environment, the present invention adopts Gaussian pyramid to perform multi-scale analysis on the image and realizes grayscale equalization through gamma transform to meet the needs of crack identification under different lighting conditions;

[0045] 2. In the crack identification part, the present invention uses improved differential entropy to optimize the local threshold segmentation algorithm, aiming to achieve high-efficiency and high-precision detection of stope cracks. This method can dynamically determine the segmentation threshold based on the grayscale distribution of the local area of ​​the image, effectively improving the accuracy and robustness of crack identification;

[0046] 3. The present invention also includes post-processing after crack identification, which further refines crack characteristics through connected domain analysis and skeleton extraction, providing support for risk assessment and regional delineation;

[0047] 4. The method of the present invention not only greatly improves the automation level of crack detection, but also provides strong technical support for open-pit mine safety management and risk warning, and has important practical application value and broad market prospects. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 It is a schematic diagram of the process of the present invention;

[0049] Figure 2 Schematic diagram of two types of cracks: light and dark;

[0050] Figure 3 Identify the schematic diagram for the shaded area;

[0051] Figure 4 Schematic diagram for crack width calculation;

[0052] Figure 5 This is the crack identification effect diagram. DETAILED DESCRIPTION

[0053] The present invention will be further described below with reference to the accompanying drawings, but the present invention is not limited in any way. Any changes or substitutions made based on the teachings of the present invention fall within the scope of protection of the present invention.

[0054] Example 1

[0055] As attached Figure 1 As shown, the adaptive crack identification and quantification method around an open pit in this embodiment includes the following steps:

[0056] S100, image preprocessing: first convert the original image into a grayscale image, then construct a Gaussian image pyramid, use Gaussian filtering to smooth the image, and use adaptive gamma transform to perform image enhancement;

[0057] S200, crack identification:

[0058] S201, improved difference entropy: fitting the parameters of the local threshold segmentation algorithm based on the improved difference entropy method, specifically:

[0059] S2011. Calculate the weighted difference between the center pixel and other pixels based on a sliding window and a Gaussian weight matrix: Assume that an image is traversed through all pixels of the image using a sliding window of arbitrary radius, and obtain the difference in grayscale value between the center pixel of the window and the remaining pixels, i.e., the grayscale difference matrix of a single pixel; wherein the grayscale difference value ranges from [0, 255], and the difference value of the center element of the grayscale difference matrix is ​​0; based on the probability density function of a two-dimensional Gaussian distribution, generate an n×n weight matrix; since the center of the difference matrix is ​​0, the weight of the center of the matrix is ​​distributed to the other elements according to the weights of the remaining elements; the probability density function of a two-dimensional Gaussian distribution is:

[0060] ,

[0061] in, is a two-dimensional random variable, μ is the mean vector, Σ is the covariance matrix, |Σ| represents the determinant of the covariance matrix;

[0062] S2012. Establishing a distribution law of differences: Using the grayscale difference matrix and weight matrix of each pixel, recording the weight of each difference in the grayscale difference matrix, i.e., the weighted number of times, to obtain the distribution X of the grayscale difference between each pixel of the image and its surrounding pixels;

[0063] S2013. Substitute the improved difference entropy formula: The calculation formula of the improved difference entropy H(x) is:

[0064] ,

[0065] Where i is the value of the difference, n is the number of gray levels, and P(x) is the distribution rate of the difference;

[0066] S202, parameter fitting:

[0067] S2021. Through the local threshold segmentation parameter analysis experiment, obtain sufficient optimal sensitivity and optimal minimum standard deviation threshold data when the crack recognition effect is best; the local threshold segmentation parameter analysis experiment is specifically performed by applying the local threshold segmentation algorithm to a set of experimental images, and finding the optimal segmentation parameters for each image when the segmentation effect is best.

[0068] S2022. Based on the least squares fitting method, the difference entropy of each experimental image is fitted with the optimal parameters of the image, and a functional relationship is established;

[0069] S203, adaptive threshold segmentation based on local threshold segmentation algorithm:

[0070] S2031. Using a sliding window of definable size, calculate the mean and standard deviation of the grayscale values ​​of pixels within the window;

[0071] S2032. Calculate the mean and mode of the entire image and compare the mean and mode. If the mean is smaller, the grayscale value of the foreground (crack) is lower than the background. If the mean is larger, the grayscale value of the foreground (crack) is higher than the background. This allows you to determine whether the image foreground has a higher grayscale value or a lower grayscale value. See the attached figure for details. Figure 2 As shown;

[0072] S2033, using standard deviation segmentation, brightness and sensitivity parameters, segment the foreground and background in the sliding window, the foreground is the crack, see the attached Figure 5 As shown, Figure 5 There are 4 groups of recognition results in total, and the colored lines represent the identified cracks.

[0073] Example 2

[0074] The adaptive crack identification and quantification method around an open pit in this embodiment is based on Example 1. In step S100, in constructing a Gaussian image pyramid, the grayscale image is downsampled three times to generate a four-layer pyramid structure, and the image of each layer is divided into the same size.

[0075] Example 3

[0076] The adaptive crack identification and quantification method around the open pit in this embodiment is based on the embodiment 2. In step S100, the adaptive gamma transform is used to perform grayscale stretching on all images during image enhancement. The gamma transform formula is:

[0077] ,

[0078] Among them, P out (x, y) is the pixel value at (x, y) of the output; A is a constant used to adjust the range of output brightness; P in(x, y) is the pixel value at the input (x, y); γ is the gamma value, 0≤γ≤5, which is used to control the shape of the gamma curve. When γ=1, the gamma curve is a straight line, and the grayscale value of the image does not change after mapping;

[0079] Calculate the adaptive gamma value based on the average grayscale value. The formula is:

[0080] ,

[0081] Among them, μ is the average gray value of the image; T is the standard gray value, and t is the control parameter; when T=μ, the image does not change.

[0082] Example 4

[0083] The adaptive crack identification and quantification method around the open pit in this embodiment is based on the embodiment 3 and further includes a post-processing step S300, specifically including the following steps:

[0084] S301, connected domain analysis and screening: Perform connected domain analysis on the foreground segmented in step S2033, and screen connected domains based on region area and region average grayscale value, where the region area threshold is positively correlated with the image size;

[0085] S302. Construct a shadow area recognition method to remove shadow areas: select an arbitrary area and determine its skeleton; select evenly spaced seed points on its skeleton, set a grayscale difference threshold, and perform directional growth along the normal; calculate the shadow area on both sides of the area based on the growth degree of the seed points. If the area of ​​the grown area is too large, the area is a shadow. The calculation formula for the shadow area S is:

[0086] ,

[0087] Among them, l i is the growth length of the i-th seed, and d is the setting interval of the seeds;

[0088] Remove the shadow area; see the attached Figure 3 shown.

[0089] Example 5

[0090] As attached Figure 4 As shown, the adaptive crack identification and quantification method around the open pit in this embodiment is based on Example 4 and also includes S400 crack quantification, specifically including:

[0091] (1) Crack classification: Based on the number of crack intersections and branches, the cracks are classified into strip cracks or network cracks;

[0092] (2) Direction and length calculation: The direction and length of the crack skeleton are calculated as the direction and length of the crack;

[0093] (3) Width calculation: uniformly spaced seed points are selected along the skeleton, and directional growth is performed along the normal line. The average growth length is calculated, which is the crack width;

[0094] The above (1), (2), and (3) are in no particular order.

Claims

1. An adaptive crack identification and quantification method around an open pit, characterized by The following steps are involved: S100, image preprocessing: first convert the original image into a grayscale image, then construct a Gaussian image pyramid, use Gaussian filtering to smooth the image, and use adaptive gamma transform to perform image enhancement; S200, crack identification: S201, improved difference entropy: fitting the parameters of the local threshold segmentation algorithm based on the improved difference entropy method, specifically: S2011. Calculate the weighted difference between the center pixel and other pixels based on a sliding window and a Gaussian weight matrix: Assume that an image is traversed through all pixels of the image using a sliding window of arbitrary radius, and obtain the difference in grayscale value between the center pixel of the window and the remaining pixels, i.e., the grayscale difference matrix of a single pixel; wherein the grayscale difference value ranges from [0, 255], and the difference value of the center element of the grayscale difference matrix is ​​0; based on the probability density function of a two-dimensional Gaussian distribution, generate an n×n weight matrix; since the center of the difference matrix is ​​0, the weight of the center of the matrix is ​​distributed to the other elements according to the weights of the remaining elements; the probability density function of a two-dimensional Gaussian distribution is: ， in, is a two-dimensional random variable, μ is the mean vector, Σ is the covariance matrix, |Σ| represents the determinant of the covariance matrix; S2012. Establishing a distribution law of differences: Using the grayscale difference matrix and weight matrix of each pixel, recording the weight of each difference in the grayscale difference matrix, i.e., the weighted number of times, to obtain the distribution X of the grayscale difference between each pixel of the image and its surrounding pixels; S2013. Substitute the improved difference entropy formula: The calculation formula of the improved difference entropy H(x) is: ， Where i is the value of the difference, n is the number of gray levels, and P(x) is the distribution rate of the difference; S202, parameter fitting: S2021. Through local threshold segmentation parameter analysis experiments, obtain sufficient data on the optimal sensitivity and the optimal minimum standard deviation threshold value when the crack identification effect is the best; S2022. Based on the least squares fitting method, the difference entropy of each experimental image is fitted with the optimal parameters of the image, and a functional relationship is established; S203, adaptive threshold segmentation based on local threshold segmentation algorithm: S2031. Using a sliding window of definable size, calculate the mean and standard deviation of the grayscale values ​​of pixels within the window; S2032, calculating the mean and mode of the entire image, and comparing the mean and mode. If the mean is smaller, the foreground grayscale value is lower than the background, and if the mean is larger, the foreground grayscale value is higher than the background, thereby distinguishing whether the image foreground has a higher grayscale value or a lower grayscale value; S2033. Segment the foreground and background in the sliding window using standard deviation segmentation, brightness parameters, and sensitivity parameters, where the foreground is the crack.

2. The method for adaptive crack identification and quantification around an open pit according to claim 1, characterized in that In step S100, in constructing the Gaussian image pyramid, the grayscale image is downsampled three times to generate a four-layer pyramid structure, and the image of each layer of the structure is divided into the same size.

3. The method for adaptive crack identification and quantification around an open pit according to claim 1, characterized in that In step S100, when performing image enhancement using adaptive gamma transform, the adaptive gamma transform is used to perform grayscale stretching on all images. The gamma transform formula is: ， Among them, P out (x, y) is the pixel value at (x, y) of the output; A is a constant used to adjust the range of output brightness; P in (x, y) is the pixel value at the input (x, y); γ is the gamma value, 0≤γ≤5, which is used to control the shape of the gamma curve. When γ=1, the gamma curve is a straight line, and the grayscale value of the image does not change after mapping; Calculate the adaptive gamma value based on the average grayscale value. The formula is: ， Among them, μ is the average gray value of the image; T is the standard gray value, and t is the control parameter; when T=μ, the image does not change.

4. The method for adaptive crack identification and quantification around an open pit according to claim 1, characterized in that The step S300 is also included, which specifically includes the following steps: S301, connected domain analysis and screening: Perform connected domain analysis on the foreground segmented in step S2033, and screen connected domains based on region area and region average grayscale value, where the region area threshold is positively correlated with the image size; S302. Construct a shadow area recognition method to remove shadow areas: select an arbitrary area and determine its skeleton; select evenly spaced seed points on its skeleton, set a grayscale difference threshold, and perform directional growth along the normal; calculate the shadow area on both sides of the area based on the growth degree of the seed points. If the area of ​​the grown area is too large, the area is a shadow. The calculation formula for the shadow area S is: ， Among them, l i is the growth length of the i-th seed, and d is the setting interval of the seeds; Remove the shadow areas.

5. The method for adaptive crack identification and quantification around an open pit according to claim 1, characterized in that Also included is S400 crack quantification, specifically including: (1) Crack classification: Based on the number of crack intersections and branches, the cracks are classified into strip cracks or network cracks; (2) Direction and length calculation: The direction and length of the crack skeleton are calculated as the direction and length of the crack; (3) Width calculation: uniformly spaced seed points are selected along the skeleton, and directional growth is performed along the normal line. The average growth length is calculated, which is the crack width; The above (1), (2), and (3) are in no particular order.

Images