Rock sample crack detection and identification method based on image visual saliency

Abstract

The invention relates to the technical field of oil and gas exploration and development and image processing, in particular to a rock sample crack detection and identification method based on image visual saliency, which comprises the following steps: S1, inputting original rock core image data; s2, acquiring a crack research area image from the original core image through image segmentation and manual clipping; s3, adopting morphological quotient operation processing and a dark channel prior principle to calculate and obtain an initial crack saliency map of the crack research area image; and S4, performing superpixel segmentation on the crack research area image, and establishing a cellular automaton updating mechanism through color features and initial saliency information to realize optimization processing of an initial crack saliency map. According to the method, a visual saliency principle and a cellular automaton optimization mechanism are introduced, and rapid detection and extraction of fractures in large-batch fractured rock sample photos are realized.

Description

Technical Field

[0001] The present invention relates to the technical fields of oil and gas exploration and development and image processing, and specifically relates to a method for detecting and identifying rock sample fractures based on image visual saliency. Background Art

[0002] Natural fractures are an important structure existing in geology, with important reservoir and migration functions. They are one of the important conditions for the formation and preservation of oil and gas, have a direct impact on the productivity of oil and gas wells, determine the oil drainage capacity of the matrix and the oil supply area of the oil well, and are the focus of the research on oil and gas reservoir development plans. Therefore, in the exploration and development of fractured oil and gas reservoirs, it is necessary to comprehensively and accurately understand the development and distribution law of the fracture system.

[0003] At present, the existing methods for detecting and identifying natural fractures in rock samples are mainly core observation methods. This method uses directional coring technology to directly observe and measure the whole core of the taken core, or observes it under a microscope through a core thin section to achieve the detection and identification of fractures, and then obtains fracture characteristic parameters. Although the core observation method is the most accurate method for detecting and identifying fractures, it is time-consuming, has a large amount of manual identification work, and extremely low efficiency. At the same time, there are also problems such as the chaotic distribution and irregular shape of core fractures, which exacerbate the difficulty of manual detection and identification of fractures (Li Shaohua et al., 2006; Li Airong and Hu Shuyong, 2021). Other methods for detecting and identifying natural fractures include production dynamic analysis methods (Jiang Ruizhong et al., 2013), in-situ stress analysis methods (Huang Tao et al., 2024), and logging identification methods (Zhao Junlong et al., 2012), but these methods are mainly for indirectly identifying unknown underground fractures and are not applicable to the detection and identification of fractures in surface rock samples. Considering the problems of low efficiency of manual identification of surface rock sample fractures and complex fracture distribution, etc., it is urgent to establish an intelligent and rapid detection method for a large number of rock sample fractures by means of artificial intelligence technology.

[0004] Image visual saliency detection is to use a computer to simulate the human visual attention mechanism, calculate the importance of each part of the information in the picture, and then obtain a grayscale image with the same size as the original image. The pixel value of each point in the grayscale image represents the saliency value of the original image pixel. The brightness is positively correlated with the size of the saliency value. This grayscale image is also called a saliency map. Through the saliency map, the saliency region of human interest can be quickly found (Yuan Ye et al., 2020). Rock sample photos are an important carrier for carrying reservoir fracture information. The fracture region has unique visual features in the image, such as color, texture, and shape features that are different from the rock background. With the help of visual saliency detection algorithms, it is expected to quickly and accurately highlight the fracture region from the complex core photo background, achieve the efficient detection and identification of rock sample fractures, reduce the manual detection workload of core fractures, significantly improve the fracture detection and identification efficiency, and support the intelligent and rapid detection of a large number of rock samples in the oilfield. Summary of the Invention

[0005] The object of the present invention is to overcome the deficiencies of the prior art and propose a method for detecting and identifying rock sample fractures based on image visual saliency, introducing the principle of visual saliency and the optimization mechanism of cellular automata to achieve the detection of core fractures in oil and gas field reservoirs.

[0006] To achieve the above object, the technical solution specifically adopted by the present invention is as follows: A method for detecting and identifying rock sample fractures based on image visual saliency, comprising the following steps: S1. Input the original core image data; S2. Obtain the fracture research area image from the original core image through image segmentation and manual cropping; S3. Calculate and obtain the initial fracture saliency map of the fracture research area image by using morphological quotient operation processing and the dark channel prior principle; S3.1. Morphological quotient operation processing S3.1-1: Input the fracture research area image ; S3.1-2: Perform multi-scale morphological closing operation processing on the image to obtain the background image ; S3.1-3: Perform quotient operation processing on the image and the background image to obtain the quotient image ; S3.1-4: Obtain the fracture saliency map of the quotient image through image inversion and normalization processing ; S3.2. Dark channel prior calculation S3.2-1: Construct a new atmospheric scattering model; S3.2-2: Generate a dark channel prior fracture saliency map based on the new atmospheric scattering model for fracture images with uneven illumination and low illumination ; S3.2-3: Fuse the fracture saliency map of the quotient image and the dark channel prior fracture saliency map to obtain the initial fracture saliency map ; .

[0007] S4. Perform superpixel segmentation on the fracture research area image, establish a cellular automata update mechanism through color features and initial saliency information, and realize the optimization processing of the initial fracture saliency map; S41. Segment the fracture research area by using the superpixel segmentation algorithm LSC , and then an influence factor matrix is established by using the Lab color space features of the image, the saliency map of the dark channel prior, and the saliency map of the quotient image respectively ; S42. Cross-diffusion processing is performed on the three influence factor matrices , and to obtain a fused influence factor matrix; S43. The influence factor matrix is row-normalized to obtain a normalized influence factor matrix ; S44. A confidence matrix is established and the confidence matrix is constrained within a certain range; S45. A synchronous update and optimization mechanism is established based on the normalized influence factor matrix and the confidence matrix ; .

[0008] In the method for detecting and identifying rock sample fractures based on image visual saliency according to the present invention, step S3.1 specifically includes the following steps: S3.1-1: Input the image of the fracture research area ; S3.1-2: Perform multi-scale morphological closing operation on the image to obtain a background image ; ; In the formula, represents the morphological closing operation, represents the structural element of the closing operation, represents the set of structural elements.

[0009] S3.1-3: Perform a quotient operation on the image and the background image to obtain a quotient image ; ; In the formula, represents the pixel value of the th i row and j th column of the quotient image represents the pixel value of the th i row and j th column of the fracture research area image represents the pixel value of the th i row and j th column of the background image

[0010] S3.1-4: Obtain the quotient image through image inversion and normalization processing of the crack saliency map ; ; ; wherein represents the pixel value of the i th row and j th column of the inverted image, represents the pixel value of the th row and i th column of the quotient image j i j

[0011] In a rock sample crack detection and recognition method based on image visual saliency according to the present invention, in step S3.2-1, a new atmospheric scattering model is constructed: ; wherein represents image imaging, represents a clear image under ideal clear weather, represents the transmittance function value, represents the atmospheric light value, represents a pixel.

[0012] In a rock sample crack detection and recognition method based on image visual saliency according to the present invention, step S3.2-2 includes the following steps: Obtain the R, G, and B channels of the crack research area image Based on the new atmospheric scattering model, there is: ; wherein represents the image imaging of the three channels, represents the atmospheric light values of the three channels, represents the R, G, and B channels of the crack research area image represents the clear images of the three channels under ideal clear weather, represents the transmittance function value, represents a pixel.

[0013] Assume the transmittance function is a fixed value and the atmospheric light value is a constant value. Taking the minimum value on both sides of Equation (6), we have: ; In the formula, represents a local area in the image, represents the local area of the elements, represents the image formation and the atmospheric light value ratio, represents the clear image and the atmospheric light value ratio, represents the transmittance function value, represents the pixel.

[0014] The dark channel prior theory believes that the dark channel is composed of the points with the minimum pixel values in the three color channels and can be expressed as: ; In the formula, represents the dark channel of the pixel , represents the clear images of the three channels under ideal clear weather, represents a local area in the image.

[0015] Substituting Equation (8) into Equation (7) to obtain the transmittance function ; At the same time, by introducing the defogging degree adjustment coefficient , the estimated transmittance function is obtained: ; Perform the following normalization processing on Equation (9) to generate the crack saliency map of the dark channel prior , ; In the formula, represents the pixel value of the crack saliency map , represents the estimated transmittance function.

[0016] In the method for detecting and identifying rock sample cracks based on image visual saliency according to the present invention, in step S3.2-3, by fusing the crack saliency map of the quotient image and the crack saliency map of the dark channel prior, the initial crack saliency map is obtained: ; In the method for detecting and identifying rock sample fractures based on image visual saliency according to the present invention, step S4 includes the following steps: S41. Segment the fracture research area using the superpixel segmentation algorithm LSC , and then establish an influence factor matrix using the Lab color space features, the saliency map of dark channel prior, and the saliency map of quotient image of the image respectively : ; In the formula, represents the class eigenvalue of superpixel , and the class color eigenvalue of superpixel represents superpixel , represents the neighborhood set of superpixel ; From this, the influence factor matrix of Lab color space features , the influence factor matrix of dark channel prior saliency map and the influence factor matrix of quotient image saliency map can be obtained.

[0017] S42. Perform cross-diffusion processing on the three influence factor matrices , and to obtain a fused influence factor matrix: ; ; In the formula, represents the number of iterations of cross-diffusion processing, , and represent the row normalization processing of the three influence factor matrices. The fused influence factor matrix is expressed as follows: ; S43. Perform row standardization processing on the influence factor matrix to obtain a standardized influence factor matrix : ; In the formula, , , represents the element of the influence factor matrix F.

[0018] S44. Establish a confidence matrix , and its element is: ; In the formula, represents the element of the influence factor matrix F.

[0019] The confidence matrix is constrained within a certain range, that is , where the element is: ; In the formula, , , represents the element of the confidence matrix .

[0020] S45. Based on the standardized influence factor matrix and the confidence matrix a synchronous update and optimization mechanism is established , that is: ; In the formula, represents the crack saliency map after the -th update and optimization. When , n ; I represents the

[0021] The present invention has the following characteristics and beneficial effects: 1) In the regional image, the morphological quotient operation and the dark channel prior principle are respectively used to calculate the initial crack saliency map of the image, which can not only overcome uneven illumination, but also effectively extract a large number of reservoir core cracks in batches.

[0022] 2) By performing superpixel segmentation on the original image, and then calculating the influence factor matrix through color features and initial saliency information, a cellular automaton synchronous update mechanism is established to optimize the initial crack saliency map, realizing the rapid detection and extraction of cracks in a large number of crack rock sample photos, laying a solid foundation for the subsequent efficient and intelligent identification of crack parameters. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 is the experimental result diagram of a method for detecting and identifying rock sample cracks based on image visual saliency of the present invention; In the figure: (a) Core photo (with scale); (b) Extracted crack image; (c) Initial crack saliency map; (d) Optimized crack saliency map.

[0024] Figure 2 is the original core crack image in the embodiment of the present invention.

[0025] Figure 3It is the image of the crack research area in the embodiment of the present invention.

[0026] Figure 4 It is the initial crack saliency map in the embodiment of the present invention.

[0027] Figure 5 It is the initial saliency map of core cracks after optimization in the embodiment of the present invention.

[0028] Figure 6 It is for the image of the crack research area in the embodiment of the present invention It is the flow chart of the multi-scale morphological closing operation processing for the image. Detailed implementation manners

[0029] The present invention will be described in detail below in conjunction with specific embodiments. The following embodiments will help those skilled in the art to further understand the present invention, but do not limit the present invention in any form. It should be noted that, without conflict, the embodiments in the present invention and the features in the embodiments can be combined with each other.

[0030] For the detection of fine cracks on the core scale of oil and gas reservoir, the present invention introduces the visual saliency principle and the cellular automaton optimization mechanism, and provides a method for detecting and identifying core cracks based on image visual saliency. First, aiming at the current problems of the chaotic distribution of original crack images and the large workload of manual identification in the detection of cracks in a large number of reservoir core photos, the visual saliency detection theory is used to quickly and intelligently detect reservoir core cracks. During operation, according to the physical core photo with a scale ( Figure 1 (a)), the crack research area image with specific length and width is intercepted ( Figure 1 (b)). In the area image, the morphological quotient operation processing and the dark channel prior principle are respectively adopted to calculate the initial crack saliency map of the image ( Figure 1 (c)). The results are as shown in Figure 1 (c), indicating that the morphological quotient operation processing and the dark channel prior can not only overcome the uneven illumination, but also effectively extract core cracks in large quantities. Then, aiming at the problems of incomplete and discontinuous cracks detected in the initial crack saliency map, the original image is subjected to superpixel segmentation, and the influence factor matrix is calculated through color features and initial saliency information, so as to establish a cellular automaton synchronous update mechanism to optimize the initial crack saliency map, so as to obtain the final high-quality crack saliency map ( Figure 1 (d)). The experimental results are as shown in Figure 1 (d), indicating that the cellular automaton can optimize the initial crack saliency map and obtain more complete core cracks. This method realizes the rapid detection and extraction of cracks in a large number of cracked core photos, laying a solid foundation for the subsequent efficient and intelligent identification of crack parameters.

[0031] The specific processing procedure of the present invention will be further described below in conjunction with the accompanying drawings and embodiments: S1. Input the original core image data, such as Figure 2 shown; S2. Obtain the crack research area image from the original core image through image segmentation and manual cropping. The crack research area image in this embodiment is as Figure 3 shown; S3. Adopt morphological quotient operation processing and dark channel prior principle to calculate and obtain the initial crack saliency map ( Figure 3 ) of the crack research area image ( Figure 4 ). Specifically, it includes the following steps: S3.1 Morphological quotient operation processing Step 1: Input the crack research area image ( Figure 3 ) Step 2: As Figure 6 shown, perform multi-scale morphological closing operation processing on the image to obtain the background image ; ; In the formula, in the formula, represents morphological closing operation processing, represents the structural element of the closing operation, represents the set of structural elements, where: ; Step 3: Perform quotient operation processing on the image and the background image to obtain the quotient image ; ; In the formula, represents the pixel value of the th row and the i th column of the quotient image j , represents the pixel value of the th row and the i th column of the crack research area image j , represents the pixel value of the th row and the i th column of the background image j .

[0032] Step 4: Obtain the crack saliency map of the quotient image through image inversion and normalization processing; ; ; In the formula, represents the pixel value of the i th row and j th column of the inverted image, represents the pixel value of the th row and i th column of the quotient image j represents the pixel value of the th row and i th column of the crack saliency map j represents the maximum pixel value in the inverted image, represents the minimum pixel value in the inverted image.

[0033] S3.2 Dark channel prior calculation Step 1: For the crack image of uneven illumination and low illumination images, use the dark channel prior to calculate the saliency map of the crack image and extract the cracks. For low illumination images, construct a new atmospheric scattering model: ; In the formula, represents image imaging, represents the clear image under ideal sunny weather, represents the transmittance function value, represents the atmospheric light value, represents the pixel.

[0034] Step 2: Obtain the R, G, and B channels of the crack research area image . Based on the new atmospheric scattering model, we have: ; In the formula, represents the image imaging of the three channels, represents the atmospheric light value of the three channels, represents the R, G, and B channels of the crack research area image represents the clear image of the three channels under ideal sunny weather, represents the transmittance function value, represents the pixel.

[0035]

[0035] Assume that the transmittance function is a fixed value and the atmospheric light value is a constant . Take the minimum value of both sides of Equation (6), then: ; In the formula, represents the local area in the image, Elements representing a local area of representing the ratio of image imaging to the atmospheric light value is representing the ratio of the clear image to the atmospheric light value is representing the transmittance function value representing pixels. The dark channel prior theory holds that the dark channel consists of the points with the minimum pixel values in the three color channels and can be expressed as: ; wherein represents the pixel of the dark channel represents the clear images of the three channels under ideal clear weather represents the local area in the image.

[0036] Substituting Equation (8) into Equation (7) gives the transmittance function ; meanwhile, by introducing a parameter , called the defogging degree adjustment coefficient, with a range of , usually taking a value of 0.95, the estimated transmittance function is obtained: ; The following normalization processing is performed on Equation (9) to generate the crack saliency map of the dark channel prior , ; wherein represents the pixel value of the crack saliency map and represents the estimated transmittance function.

[0037] Step 3: By fusing the crack saliency map of the quotient image and the crack saliency map of the dark channel prior, the initial crack saliency map is obtained (as shown in Figure 4 ): ; S4. Perform superpixel segmentation on the crack research area image, establish a cellular automaton update mechanism through color features and initial saliency information, and realize the optimization processing of the initial crack saliency map ( Figure 5 ). Specifically, in order to optimize the initial crack saliency map ( Figure 4), the initial saliency map will be optimized using the cellular automaton synchronous update mechanism to obtain the final crack saliency map. First, the superpixel segmentation algorithm LSC is used to segment the crack research area , and then the influence factor matrices of dimensions are established respectively using the Lab color space features of the image, the saliency map of the dark channel prior, and the saliency map of the quotient image , where represents the similarity value of each superpixel block and the adjacent superpixel block under the class eigenvalue, and its calculation method is as follows: ; In the formula, represents the class eigenvalue of the superpixel , represents the class color eigenvalue of the superpixel , represents the neighborhood set of the superpixel .

[0038] Further, the similarity value of the Lab color space features and the influence factor matrix of dimensions , the similarity value of the dark channel prior saliency map and the influence factor matrix of dimensions , and the similarity value of the quotient image saliency map and the influence factor matrix of dimensions can be obtained.

[0039] Cross-diffusion processing is performed on the three influence factor matrices , and to obtain the fused influence factor matrix: ; ; In the formula, represents the number of iterations of cross-diffusion processing, represents the transpose of the matrix, , and represent the similarity influence factor matrix of the Lab color space features, the similarity influence factor matrix of the dark channel prior saliency map, and the similarity influence factor matrix of the quotient image saliency map after times of cross-diffusion processing, , and denotes the similarity influence factor matrix of the Lab color space features, the similarity influence factor matrix of the dark channel prior saliency map, and the similarity influence factor matrix of the quotient image saliency map after the -th cross-diffusion processing. When , and . denotes the row normalization processing of the influence factor matrix of the Lab color space features, denotes the row normalization processing of the influence factor matrix of the dark channel prior saliency map; denotes the row normalization processing of the influence factor matrix of the quotient image saliency map; denotes the -dimensional influence factor matrix of the Lab color space features after the normalization processing, denotes the -dimensional influence factor matrix of the dark channel prior saliency map after the normalization processing, denotes the -dimensional influence factor matrix of the quotient image saliency map after the normalization processing. The fusion influence factor matrix is expressed as follows: ; Next, the influence factor matrix is subjected to row standardization processing to obtain the standardized influence factor matrix : ; In the formula, , , denotes the element of the influence factor matrix F.

[0040] In the cellular automaton synchronous update mechanism, the next evolution state of each cell is jointly determined by its current state and the set of adjacent cells. Here, a confidence matrix is established to ensure the effectiveness and stability of the update evolution. The confidence matrix is expressed as , and its element is: ; In the formula, denotes the element of the influence factor matrix F.

[0041] Based on Equation (17), to ensure that the saliency value of each superpixel can be updated to a relatively stable and accurate state, the confidence matrix is constrained within a certain range, that is, , where the element is: ; In the formula, , , represents the elements of the confidence matrix .

[0042] Based on the standardized influence factor matrix and the confidence matrix a synchronous update and optimization mechanism is established , that is: ; In the formula, represents the crack saliency map after the -th update and optimization. When , n ; I represents the identity matrix of order

[0043] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments. The above embodiments and the descriptions in the specification are only preferred examples of the present invention and are not used to limit the present invention. Without departing from the spirit and scope of the present invention, the present invention will have various changes and improvements, and these changes and improvements all fall within the scope of the present invention claimed. The scope of the present invention claimed is defined by the appended claims and their equivalents.

Claims

1. A rock sample crack detection and identification method based on image visual saliency, characterized by: The steps include: S1, input original core image data; S2, obtaining the fracture study area image from the original core image through image segmentation and manual cropping; S3, using morphological quotient operation and dark channel prior principle to calculate and obtain the initial crack significance map of the crack study area image; S4. Perform superpixel segmentation on the image of the crack study area, establish a cellular automaton update mechanism through color features and initial saliency information, and achieve optimization processing of the initial crack saliency map.

2. A rock sample crack detection and identification method based on image visual saliency according to claim 1, characterized in that: The step S3 comprises the following steps: S3.

1. Morphological quotient operation processing S3.1-1: Input crack study area image ; S3.1-2: Image Perform multi-scale morphological closing operations to obtain the background image ; S3.1-3: Image and background image Perform quotient operation to obtain quotient image ; S3.1-4: Obtaining the quotient image by image inversion and normalization Crack Significance Map ; S3.

2. Dark channel prior calculation S3.2-1: Construct a new atmospheric scattering model; S3.2-2: For crack images with uneven illumination and low illumination, generate a dark channel prior crack saliency map based on the new atmospheric scattering model ; S3.2-3: Fusion Quotient Image Crack Significance Map Crack saliency map with dark channel prior , and obtain the initial crack significance map.

3. A rock sample crack detection and identification method based on image visual saliency according to claim 2, characterized in that: The step S3.1 specifically includes the following steps: S3.1-1: Input crack study area image ; S3.1-2: Image Perform multi-scale morphological closing operations to obtain the background image ; ； In the formula, represents the morphological closing operation processing, A structural element representing a closing operation, Represents a collection of structural elements; S3.1-3: Image and background image Perform quotient operation to obtain quotient image ; ； In the formula, Representation quotient image No. i Row, No. j The pixel value of the column, Image showing the fracture study area No. i Row, No. j The pixel value of the column, Represents a background image No. i Row, No. j The pixel value of the column; S3.1-4: Obtaining the quotient image by image inversion and normalization Crack Significance Map ; ； ； In the formula, Indicates the reverse image i Row, No. j The pixel value of the column, Represents the quotient image i Row, No. j The pixel value of the column, The crack significance map i Row, No. j The pixel value of the column, Represents the maximum pixel value in the inverted image, Indicates the minimum pixel value in the inverted image.

4. A rock sample crack detection and identification method based on image visual saliency according to claim 2, characterized in that: In step S3.2-1, a new atmospheric scattering model is constructed: ； In the formula, Indicates image imaging, Indicates a clear image in ideal sunny weather. represents the transmittance function value, represents the atmospheric light value, Represents pixels.

5. A rock sample crack detection and identification method based on image visual saliency according to claim 2, characterized in that: The step S3.2-2 comprises the following steps: Get an image of the fracture study area The R, G, and B channels of the new atmospheric scattering model are: ； In the formula, Represents the image imaging of three channels, Represents the atmospheric light values ​​of the three channels, Image showing the fracture study area The R, G, and B channels, A clear image of three channels under ideal clear weather. represents the transmittance function value, Represents pixels; Assuming the transmittance function is a fixed value and the atmospheric light value is a constant, take the minimum value on both sides of equation (6), then: ； In the formula, represents a local area in the image, Represents a local area Elements of Represents image imaging Atmospheric light value The ratio of Indicates clear image Atmospheric light value The ratio of represents the transmittance function value, Represents pixels; The dark channel prior theory believes that the dark channel is composed of points with the smallest pixel values ​​in the three color channels and can be expressed as: ； In the formula, Represents pixels The dark channel, A clear image of three channels under ideal clear weather. Represents a local area in an image; Substituting equation (8) into equation (7) yields the transmittance function ; At the same time, by introducing the defogging degree adjustment coefficient , and obtain the estimated transmittance function : ； Normalize equation (9) as follows to generate the dark channel prior crack saliency map: , ； In the formula, Crack Significance Map The pixel value of represents the estimated transmittance function.

6. A rock sample crack detection and identification method based on image visual saliency according to claim 2, characterized in that: In the step S3.2-3, the crack saliency map of the fusion quotient image is Crack saliency map with dark channel prior , and obtain the initial crack saliency map : 。 7. A rock sample crack detection and identification method based on image visual saliency according to claim 2, characterized in that: The step S4 comprises the following steps: S41. Use superpixel segmentation algorithm LSC to segment the crack study area Then, the influence factor matrix is ​​established by using the Lab color space features of the image, the dark channel prior saliency map and the quotient image saliency map. : ； In the formula, Represents each superpixel block and adjacent superpixel blocks exist Similarity value under class feature value, Represents superpixel of Class eigenvalues, Represents superpixel of Class color feature value, Represents superpixel The neighborhood set of Lab color space features can be obtained from this and Dimensional Impact Factor Matrix , similarity value of dark channel prior saliency map and Dimensional Impact Factor Matrix , and the similarity value of the saliency map of the quotient image and Dimensional Impact Factor Matrix ; S42, three impact factor matrices , and Cross-diffusion processing is performed to obtain the fusion impact factor matrix: ； ； In the formula, represents the number of iterations of the cross-diffusion process, , and Indicates the row normalization processing of the three impact factor matrices; represents the transpose of a matrix, , and express The similarity influence factor matrix of Lab color space features after cross-diffusion processing, the similarity influence factor matrix of dark channel prior saliency map, and the similarity influence factor matrix of quotient image saliency map, , and express The similarity influence factor matrix of Lab color space features after cross-diffusion processing, the similarity influence factor matrix of dark channel prior saliency map, and the similarity influence factor matrix of quotient image saliency map; Represents the normalized The influencing factor matrix of the Lab color space characteristics of Represents the normalized The influence factor matrix of the dark channel prior saliency map of Represents the normalized The impact factor matrix of the saliency map of the quotient image of the dimension; Fusion Impact Factor Matrix It is expressed as follows: ； S43. Impact Factor Matrix Perform row standardization to obtain the standardized impact factor matrix : ； In the formula, , , Represents the elements of the impact factor matrix F; S44. Establish confidence matrix , whose elements for: ； In the formula, Represents the elements of the impact factor matrix F; Constrain the confidence matrix to a certain range, that is , where the elements for: ； In the formula, , , Represents the confidence matrix Elements of S45, based on the standardized impact factor matrix and the confidence matrix Establish a synchronous update optimization mechanism ,Right now: ； In the formula, express The crack saliency map after the optimization is updated. hour, ; express n The identity matrix of order.

Images