A method, device, equipment and medium for detecting cracks and defects in hydropower station dams.

Abstract

This invention relates to the field of hydropower station technology, and discloses a method, apparatus, equipment, and medium for detecting crack defects in hydropower station dams. The invention calculates the maximum value of the ridge variation coefficient through single-layer discrete two-dimensional wavelet decomposition and ridge transform, and then determines the true crack edge direction based on this maximum value, improving the edge feature enhancement effect and making the edge boundaries clearer. Furthermore, a crack edge image is constructed based on multiple pixels corresponding to the absolute values ​​of multiple gradients along the crack edge direction, and the crack defect detection result of the hydropower station dam to be detected is determined based on the constructed crack edge image. Therefore, by implementing this invention, the edge strength and recognition rate of image recognition are improved by enhancing edge features, thereby improving the accuracy of crack defect detection results.

Description

Technical Field

[0001] This invention relates to the field of hydropower station technology, specifically to a method, device, equipment, and medium for detecting crack defects in hydropower station dams. Background Technology

[0002] Detecting cracks and defects in hydropower dams, especially in the underwater sections, typically involves using sonar detection combined with computer-aided image recognition technology to promptly identify existing cracks and defects on the dam.

[0003] To improve the accuracy of sonar detection image recognition, existing technologies are based on transform domain methods, such as wavelet transform (WT), to achieve accurate identification of spatial local details. However, wavelet transform-based methods only perform well in representing point singularities, failing to take into account the geometric characteristics of structures and not utilizing the regularity of defect edges. To address this issue, researchers have applied curve transform (CVT) to enhance the contrast of the image recognition process, resulting in better adaptability in terms of sensitivity and anisotropy.

[0004] However, when detecting cracks in hydropower dams, the edges of the cracks are mostly sloping. Existing curve transform denoising methods can destroy these sloping edges, resulting in unclear or even distorted edge boundaries detected by sonar images, which in turn leads to low accuracy of crack defect detection results. Summary of the Invention

[0005] In view of this, the present invention provides a method, apparatus, equipment and medium for detecting crack defects in hydropower station dams, in order to solve the problem that existing curve transformation denoising methods destroy these sloping edges, resulting in unclear or even distorted edge boundaries detected by sonar images, and thus leading to low accuracy of crack defect detection results.

[0006] In a first aspect, the present invention provides a method for detecting crack defects in a hydropower station dam, the method comprising:

[0007] The process involves: acquiring the original image of the dam to be inspected; obtaining the maximum value of the ridge coefficient through single-layer discrete two-dimensional wavelet decomposition and ridge transform based on the original image; determining the direction of the crack edge based on the maximum value of the ridge coefficient; constructing a crack edge image based on multiple pixels corresponding to the absolute values ​​of multiple gradients along the crack edge direction; and determining the crack defect detection result of the dam to be inspected based on the crack edge image.

[0008] The present invention provides a method for detecting crack defects in hydropower station dams. This method calculates the maximum value of the ridge variation coefficient through single-layer discrete two-dimensional wavelet decomposition and ridge transform, and then determines the true crack edge direction based on this maximum value, improving the edge feature enhancement effect and resulting in clearer edge boundaries. Furthermore, a crack edge image is constructed based on multiple pixels corresponding to the absolute values ​​of multiple gradients along the crack edge direction, and the crack defect detection result of the hydropower station dam to be detected is determined based on the constructed crack edge image. Therefore, by implementing this invention, the edge strength and recognition rate of image recognition are improved by enhancing edge features, thereby improving the accuracy of crack defect detection results.

[0009] In one optional implementation, based on the original image, the maximum value of the ridge transform coefficient is obtained through single-layer discrete two-dimensional wavelet decomposition and ridge transform, including:

[0010] The original image is subjected to single-layer discrete two-dimensional wavelet decomposition and equalization to obtain the target image; the target image is then subjected to ridge wave transform to obtain the maximum value of the ridge transform coefficient.

[0011] The method for detecting crack defects in hydropower station dams provided by this invention obtains the processed target image by performing single-layer discrete two-dimensional wavelet decomposition and equalization on the original image. Then, the target image is subjected to ridge wave transform to calculate the maximum value of the corresponding ridge transform coefficient, which provides support for determining the true crack edge direction.

[0012] In one optional implementation, the original image is subjected to single-layer discrete two-dimensional wavelet decomposition and equalization processing to obtain the target image, including:

[0013] The original image is subjected to single-layer discrete two-dimensional wavelet decomposition to obtain low-frequency subband decomposition coefficients, horizontal high-frequency subband decomposition coefficients, vertical high-frequency subband decomposition coefficients, and diagonal high-frequency subband decomposition coefficients. The low-frequency subband decomposition coefficients are then equalized to obtain low-frequency subband equalized decomposition coefficients. The original image is then reconstructed using the low-frequency subband equalized decomposition coefficients, horizontal high-frequency subband decomposition coefficients, vertical high-frequency subband decomposition coefficients, and diagonal high-frequency subband decomposition coefficients to obtain the target image.

[0014] The method for detecting cracks and defects in hydropower station dams provided by this invention can reconstruct the original image through single-layer discrete two-dimensional wavelet decomposition and equalization processing, thereby improving image accuracy.

[0015] In one optional implementation, ridge transform is performed on the target image to obtain the maximum value of the ridge transform coefficient, including:

[0016] The target image is divided into blocks to obtain multiple sub-images; the two-dimensional image signals of each sub-image are subjected to Randon transform to obtain multiple Randon transform data; the multiple Randon transform data are subjected to wavelet transform to obtain multiple ridge coefficients; the maximum value of the ridge coefficients is determined based on the multiple ridge coefficients.

[0017] The method for detecting crack defects in hydropower station dams provided by this invention can calculate the maximum value of the corresponding ridge transformation coefficient through ridge wave transformation, which provides support for subsequently determining the true direction of the crack edge.

[0018] In one optional implementation, determining the crack edge direction based on the maximum value of the ridge strain coefficient includes: calculating the azimuth angle based on the maximum value of the ridge strain coefficient; and determining the crack edge direction based on the azimuth angle.

[0019] The method for detecting crack defects in hydropower station dams provided by this invention can determine the true crack edge direction based on the azimuth angle corresponding to the maximum value of the ridge coefficient, thereby improving the edge feature enhancement effect and making the edge boundary clearer.

[0020] Secondly, the present invention provides a device for detecting crack defects in hydropower station dams, the device comprising:

[0021] The system comprises: an acquisition module for acquiring the original image of the dam to be inspected; a processing module for obtaining the maximum value of the ridge coefficient based on the original image through single-layer discrete two-dimensional wavelet decomposition and ridge transform; a first determination module for determining the direction of the crack edge based on the maximum value of the ridge coefficient; a construction module for constructing a crack edge image based on multiple pixels corresponding to the absolute values ​​of multiple gradients along the crack edge direction; and a second determination module for determining the crack defect detection result of the dam to be inspected based on the crack edge image.

[0022] In one alternative implementation, the processing module includes:

[0023] The processing submodule is used to perform single-layer discrete two-dimensional wavelet decomposition and equalization on the original image to obtain the target image; the transform submodule is used to perform ridge wave transform on the target image to obtain the maximum value of the ridge transform coefficient.

[0024] Thirdly, the present invention provides a computer device, comprising: a memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the computer instructions to perform the method for detecting crack defects in hydropower station dams described in the first aspect or any corresponding embodiment.

[0025] Fourthly, the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to execute the method for detecting crack defects in a hydropower station dam as described in the first aspect or any corresponding embodiment.

[0026] Fifthly, the present invention provides a computer program product, including computer instructions, which are used to cause a computer to execute the method for detecting crack defects in a hydropower station dam as described in the first aspect or any corresponding embodiment. Attached Figure Description

[0027] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0028] Figure 1 This is a flowchart illustrating a method for detecting cracks and defects in a hydropower station dam according to an embodiment of the present invention.

[0029] Figure 2 This is a flowchart illustrating another method for detecting cracks and defects in a hydropower station dam according to an embodiment of the present invention.

[0030] Figure 3 This is a flowchart illustrating another method for detecting cracks and defects in a hydropower station dam according to an embodiment of the present invention.

[0031] Figure 4 This is a structural block diagram of a hydropower station dam crack defect detection device according to an embodiment of the present invention;

[0032] Figure 5 This is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. Detailed Implementation

[0033] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0034] This invention provides a method for detecting crack defects in hydropower station dams. By determining the true crack edge direction through the maximum value of the ridge coefficient, the edge features are enhanced, improving the edge strength and recognition rate of image recognition, thereby improving the accuracy of crack defect detection results.

[0035] According to an embodiment of the present invention, a method for detecting crack defects in a hydropower station dam is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0036] This embodiment provides a method for detecting cracks and defects in hydropower station dams, which can be used in electronic devices such as computers, mobile phones, and tablets. Figure 1 This is a flowchart of a method for detecting cracks and defects in a hydropower station dam according to an embodiment of the present invention, as follows: Figure 1 As shown, the process includes the following steps:

[0037] Step S101: Obtain the original image of the hydropower station dam to be inspected.

[0038] Specifically, high-definition imaging sonar technology, such as cameras and sonar detection, can be used to acquire original images of the dam of the hydropower station to be inspected.

[0039] Step S102: Based on the original image, the maximum value of the ridge transformation coefficient is obtained through single-layer discrete two-dimensional wavelet decomposition and ridge wave transformation.

[0040] Among them, single-layer discrete two-dimensional wavelet decomposition is a signal processing method that decomposes a two-dimensional signal (such as an image) into multiple frequency bands, each composed of different frequencies and amplitudes.

[0041] Furthermore, the Ridgelet Transform is a transformation method for image denoising. It is based on an extension of the wavelet transform and can better capture local features in the image.

[0042] Specifically, single-layer discrete two-dimensional wavelet decomposition can effectively capture features such as edges and textures in an image. Furthermore, ridge wave transform can decompose the image into ridge transform coefficients of different scales and directions and obtain the maximum value of the ridge transform coefficients.

[0043] Step S103: Determine the direction of the crack edge based on the maximum value of the ridge strain coefficient.

[0044] Specifically, the direction of the crack edge can be inferred by using information corresponding to the maximum value of the ridge coefficient. Generally speaking, if the maximum value of the ridge coefficient appears in a specific direction, it is likely that the crack has a relatively obvious characteristic in that direction.

[0045] For example, when processing a raw image of a road surface, if the maximum value of the ridge coefficient appears in the horizontal direction, it may mean that the crack mainly extends in the horizontal direction. In the inspection image of a bridge structure, if the maximum value appears in the diagonal direction, it suggests that the edge direction of the crack is inclined.

[0046] Furthermore, relevant algorithms can be combined to more accurately determine the direction of the crack edge.

[0047] Step S104: Construct a crack edge image based on multiple pixels corresponding to the absolute values ​​of multiple gradients along the crack edge direction.

[0048] Specifically, when constructing the crack edge image, the absolute gradient value of each pixel is precisely calculated and filtered. Pixels with larger absolute gradient values ​​are more likely to be located at the crack edge. Effectively connecting and combining these pixels can initially outline the approximate shape of the crack.

[0049] For example, when processing an image of a dam surface, the absolute gradient values ​​of a series of pixels are calculated along a specific crack edge direction. Some pixels have significantly higher absolute gradient values ​​than their surrounding pixels. Connecting these prominent pixels allows for the preliminary depiction of a clear crack edge line.

[0050] In this embodiment, a corresponding crack edge image can be constructed by comparing pixels near the absolute values ​​of multiple gradients along the crack edge direction.

[0051] Step S105: Determine the crack defect detection results of the hydropower station dam to be inspected based on the crack edge image.

[0052] Specifically, crack edge images can represent the trajectory of crack edges. The area inside the edge is the crack, and the area outside the edge is the good area. Further evaluation and judgment of the crack morphology inside the edge can yield the crack defect detection results of the hydropower station dam to be inspected.

[0053] The method for detecting crack defects in hydropower station dams provided in this embodiment calculates the maximum value of the ridge variation coefficient through single-layer discrete two-dimensional wavelet decomposition and ridge wavelet transform, and then determines the true crack edge direction based on this maximum value, improving the edge feature enhancement effect and making the edge boundary clearer. Furthermore, a crack edge image is constructed based on multiple pixels corresponding to the absolute values ​​of multiple gradients along the crack edge direction, and the crack defect detection result of the hydropower station dam to be detected is determined based on the constructed crack edge image. Therefore, by implementing this invention, the edge strength and recognition rate of image recognition are improved by enhancing edge features, thereby improving the accuracy of crack defect detection results.

[0054] This embodiment provides a method for detecting cracks and defects in hydropower station dams, which can be used in electronic devices such as computers, mobile phones, and tablets. Figure 2 This is a flowchart of a method for detecting cracks and defects in a hydropower station dam according to an embodiment of the present invention, as follows: Figure 2 As shown, the process includes the following steps:

[0055] Step S201: Obtain the original image of the dam of the hydropower station to be inspected. For details, please refer to [link to relevant documentation]. Figure 1 Step S101 of the illustrated embodiment will not be described again here.

[0056] Step S202: Based on the original image, the maximum value of the ridge transformation coefficient is obtained through single-layer discrete two-dimensional wavelet decomposition and ridge wave transformation.

[0057] Specifically, step S202 includes:

[0058] Step S2021: Perform single-layer discrete two-dimensional wavelet decomposition and equalization on the original image to obtain the target image.

[0059] Specifically, single-layer discrete two-dimensional wavelet decomposition can decompose the original image into sub-bands of different frequencies and directions. It's like breaking down a complex image into multiple simpler parts, allowing for a clearer view of the image's features at different scales and in different directions.

[0060] Equalization, on the other hand, focuses on adjusting the pixel distribution of an image, thereby enhancing the image's contrast and allowing darker or brighter areas to reveal more details.

[0061] For example, after the above processing, the outlines and textures of trees that were not very clear in the shadows may become more obvious in the target image.

[0062] Therefore, the original image can be processed and the processed target image can be obtained by combining single-layer discrete two-dimensional wavelet decomposition and equalization.

[0063] In some optional implementations, step S2021 above includes:

[0064] Step a1: Perform single-layer discrete two-dimensional wavelet decomposition on the original image to obtain low-frequency subband decomposition coefficients, horizontal high-frequency subband decomposition coefficients, vertical high-frequency subband decomposition coefficients, and diagonal high-frequency subband decomposition coefficients.

[0065] Step a2: Equalize the low-frequency subband decomposition coefficients to obtain the low-frequency subband equalized decomposition coefficients.

[0066] Step a3: The original image is reconstructed using the low-frequency subband equalization decomposition coefficients, horizontal high-frequency subband decomposition coefficients, vertical high-frequency subband decomposition coefficients, and diagonal high-frequency subband decomposition coefficients to obtain the target image.

[0067] Among them, the low-frequency subband decomposition coefficients typically contain the general outline and main information of the image; the horizontal high-frequency subband decomposition coefficients reflect the details and edge information of the image in the horizontal direction; the vertical high-frequency subband decomposition coefficients reflect the details and edges in the vertical direction; and the diagonal high-frequency subband decomposition coefficients describe the high-frequency information of the image in the diagonal direction. For example, in an image of mountains, the low-frequency subband may present the general outline of the mountains, the horizontal high-frequency subband may highlight the horizontal edge where the mountains meet the sky, the vertical high-frequency subband may highlight the vertical texture of the mountains, and the diagonal high-frequency subband may show some diagonal details.

[0068] Specifically, the original image is subjected to single-layer discrete two-dimensional wavelet decomposition to obtain the decomposition coefficients cA of the low-frequency subband, which correspond to the decomposition coefficients cH, cV, and cD of the three high-frequency subbands in the horizontal, vertical, and diagonal directions, respectively.

[0069] Furthermore, the decomposition coefficients of the low-frequency subband were analyzed. c A undergoes equalization processing to obtain new equalization coefficients. This equalization process enhances the contrast and brightness distribution in the low-frequency range, resulting in a more uniform overall brightness of the image and highlighting features that were previously less noticeable.

[0070] Furthermore, the original image is reconstructed using the new equalization coefficients and the high-frequency subband decomposition coefficients cH, cV, and cD to obtain the reconstructed target image. Through reconstruction, the information of each subband can be integrated, so that the final target image retains the main features of the original image while improving the image quality and visibility through the equalization processing of the low-frequency subband.

[0071] Step S2022: Perform ridge wave transformation on the target image to obtain the maximum value of the ridge wave transformation coefficient.

[0072] In some optional implementations, step SS2022 above includes:

[0073] Step b1: Divide the target image into blocks to obtain multiple sub-images.

[0074] Step b2: Perform Randon transform on the two-dimensional image signals of each sub-image to obtain multiple Randon transform data.

[0075] Step b3: Perform wavelet transform on multiple Randon transform data to obtain multiple ridge transform coefficients.

[0076] Step b4: Determine the maximum value of the ridge variation coefficient based on multiple ridge variation coefficients.

[0077] First, the entire target image is divided into blocks, so that the singular boundaries in each small image block can be approximated by straight lines.

[0078] Next, perform Randon transform on the two-dimensional image signals of each sub-image block, as shown in the following equation (1):

[0079] R{f(x,y)}=∫∫f(x,y)δ(tx cosθ-y sinθ)dxdy=pθ(t)(1)

[0080] In the formula: f(x, y) represents the two-dimensional image signal; t represents the distance along the straight line; θ represents the rotation angle; δ represents the Dirac function; the projection pθ(t) represents the integral along a series of parallel lines (projection lines), and the Randon transform is the set of all projections {pθ(t), θ∈(0, π]}.

[0081] Furthermore, based on the above relation (1), the unrotated original image is first subjected to Randon transformation (angle is 0 degrees) to obtain a reference vector, which is used as the original reference vector R0 to prepare for the next step of comparison;

[0082] Furthermore, a set of 360 Randon transforms are performed on the image to be detected, with the transformation projection angle ranging from 0° to 359°, and the step size increasing by 1° each time. Performing 360 Randon transforms yields 360 Randon transform vectors R(θ), where θ∈[0, 359].

[0083] Furthermore, the obtained 360 detection vectors R(θ) are compared with the reference vector R0, and the correlation coefficient NC(i) between each test vector and R0 is calculated using the following relationship (2):

[0084]

[0085] Furthermore, 360 correlation coefficients can be calculated using the above relationship (3). The projection angle corresponding to the maximum value of the correlation coefficient is the rotation attack angle that the image to be detected may have experienced, denoted by θ. Then, the image is rotated inversely by an angle θ, which can correct the rotation of the image that has been subjected to rotation attack.

[0086] Secondly, the wavelet transform is then performed on the Randon transform data to obtain the ridge coefficients of the two-dimensional image, as shown in the following equation (3):

[0087]

[0088] Then: a represents the scale parameter of a ridge wave; b represents the position parameter; CRTf(a, b, θ) represents the ridge variation coefficient; The ridge wave generated by the admissibility conditions is a basic function generator that can be separated into different variables and can generate a family of target-oriented ridge waves.

[0089] Finally, the maximum value α is calculated using the ridge coefficients on each corner line. max (a, b, θ), as shown in the following relation (4):

[0090] α max (a, b, θ) = argmax θ α Q，y (a, b, θ) (4)

[0091] Where, α Q，y (a, b, θ) is the ridge coefficient CRTf(a, b, θ) calculated by the above relation (3).

[0092] Step S203: Determine the crack edge direction based on the maximum value of the ridge strain coefficient. For details, please refer to [link to relevant documentation]. Figure 1 Step S103 of the illustrated embodiment will not be described again here.

[0093] Step S204: Construct a crack edge image based on multiple pixels corresponding to the absolute values ​​of multiple gradients along the crack edge direction. See details below. Figure 1 Step S104 of the illustrated embodiment will not be described again here.

[0094] Step S205: Determine the crack defect detection results of the hydropower station dam to be inspected based on the crack edge image. For details, please refer to [link to relevant documentation]. Figure 1 Step S105 of the illustrated embodiment will not be described again here.

[0095] The method for detecting crack defects in hydropower station dams provided in this embodiment can reconstruct the original image through single-layer discrete two-dimensional wavelet decomposition and equalization processing, improving image accuracy. Then, ridge transform is applied to the reconstructed target image to calculate the maximum value of the corresponding ridge transform coefficient. This maximum value is then used to determine the true crack edge direction, improving edge feature enhancement and resulting in clearer edge boundaries. Furthermore, a crack edge image is constructed based on multiple pixels corresponding to the absolute values ​​of multiple gradients along the crack edge direction, and the crack defect detection result of the hydropower station dam to be detected is determined based on the constructed crack edge image. Therefore, by implementing this invention, edge feature enhancement improves the edge strength and recognition rate of image recognition, thereby improving the accuracy of crack defect detection results.

[0096] This embodiment provides a method for detecting cracks and defects in hydropower station dams, which can be used in electronic devices such as computers, mobile phones, and tablets. Figure 3 This is a flowchart of a method for detecting cracks and defects in a hydropower station dam according to an embodiment of the present invention, as follows: Figure 3 As shown, the process includes the following steps:

[0097] Step S301: Obtain the original image of the dam of the hydropower station to be inspected. For details, please refer to [link to relevant documentation]. Figure 1 Step S101 of the illustrated embodiment will not be described again here.

[0098] Step S302: Based on the original image, the maximum value of the ridge transform coefficient is obtained through single-layer discrete two-dimensional wavelet decomposition and ridge transform. For details, please refer to [link to relevant documentation]. Figure 2 Step S202 of the illustrated embodiment will not be described again here.

[0099] Step S303: Determine the direction of the crack edge based on the maximum value of the ridge strain coefficient.

[0100] Specifically, step S303 includes:

[0101] Step S3031: Calculate the azimuth angle based on the maximum value of the ridge strain coefficient.

[0102] Specifically, the azimuth angle θ can be calculated using the gradient of the applied maximum value. A The following relation (5) is shown:

[0103]

[0104] In the formula: This represents the gradient of any point on the ridge line in two-dimensional coordinates.

[0105] Step S3032: Determine the direction of the crack edge based on the azimuth angle.

[0106] Specifically, it can be based on the azimuth angle θA Determine the direction of the crack edge The following relation (6) is shown:

[0107]

[0108] In the formula: Q max Indicates the edge azimuth angle θ A The maximum point.

[0109] Step S304: Construct a crack edge image based on multiple pixels corresponding to the absolute values ​​of multiple gradients along the crack edge direction. See details below. Figure 1 Step S104 of the illustrated embodiment will not be described again here.

[0110] Step S305: Determine the crack defect detection results of the hydropower station dam to be inspected based on the crack edge image. For details, please refer to [link to relevant documentation]. Figure 1 Step S105 of the illustrated embodiment will not be described again here.

[0111] The method for detecting crack defects in hydropower station dams provided in this embodiment calculates the maximum value of the ridge variation coefficient through single-layer discrete two-dimensional wavelet decomposition and ridge wavelet transform. Then, based on the azimuth angle corresponding to the maximum value of the ridge variation coefficient, the true crack edge direction can be determined, improving the edge feature enhancement effect and making the edge boundary clearer. Furthermore, a crack edge image is constructed based on multiple pixels corresponding to the absolute values ​​of multiple gradients along the crack edge direction, and the crack defect detection result of the hydropower station dam to be detected is determined based on the constructed crack edge image. Therefore, by implementing this invention, the edge strength and recognition rate of image recognition are improved by enhancing edge features, thereby improving the accuracy of crack defect detection results.

[0112] This embodiment also provides a device for detecting crack defects in hydropower station dams. This device is used to implement the above embodiments and preferred embodiments, and details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0113] This embodiment provides a device for detecting cracks and defects in hydropower station dams, such as... Figure 4 As shown, it includes:

[0114] The acquisition module 401 is used to acquire the original image of the hydropower station dam to be inspected.

[0115] Processing module 402 is used to obtain the maximum value of the ridge transformation coefficient based on the original image through single-layer discrete two-dimensional wavelet decomposition and ridge wave transformation.

[0116] The first determining module 403 is used to determine the direction of the crack edge based on the maximum value of the ridge strain coefficient.

[0117] Module 404 is used to construct a crack edge image based on multiple pixels corresponding to the absolute values ​​of multiple gradients in the crack edge direction.

[0118] The second determining module 405 is used to determine the crack defect detection result of the hydropower station dam to be inspected based on the crack edge image.

[0119] In some alternative implementations, the processing module 402 includes:

[0120] The processing submodule is used to perform single-layer discrete two-dimensional wavelet decomposition and equalization on the original image to obtain the target image.

[0121] The transform submodule is used to perform ridge wave transform on the target image to obtain the maximum value of the ridge wave coefficient.

[0122] In some alternative implementations, the processing submodule includes:

[0123] The decomposition unit is used to perform single-layer discrete two-dimensional wavelet decomposition on the original image to obtain low-frequency subband decomposition coefficients, horizontal high-frequency subband decomposition coefficients, vertical high-frequency subband decomposition coefficients, and diagonal high-frequency subband decomposition coefficients.

[0124] The processing unit is used to perform equalization processing on the low-frequency subband decomposition coefficients to obtain the low-frequency subband equalization decomposition coefficients.

[0125] The reconstruction unit is used to reconstruct the original image using low-frequency subband equalization decomposition coefficients, horizontal high-frequency subband decomposition coefficients, vertical high-frequency subband decomposition coefficients, and diagonal high-frequency subband decomposition coefficients to obtain the target image.

[0126] In some optional implementations, the transformation submodule includes:

[0127] The segmentation unit is used to divide the target image into blocks to obtain multiple sub-images.

[0128] The first transformation unit is used to perform Randon transformation on the two-dimensional image signals of each sub-image to obtain multiple Randon transformation data.

[0129] The second transform unit is used to perform wavelet transform on multiple Randon transform data to obtain multiple ridge transform coefficients.

[0130] A determining unit is used to determine the maximum value of the ridge coefficient based on multiple ridge coefficients.

[0131] In some alternative implementations, the first determining module 403 includes:

[0132] The calculation submodule is used to calculate the azimuth angle based on the maximum value of the ridge strain coefficient.

[0133] The determination submodule is used to determine the direction of the crack edge based on the azimuth angle.

[0134] Further functional descriptions of the above modules and units are the same as those in the corresponding embodiments described above, and will not be repeated here.

[0135] In this embodiment, the hydropower station dam crack defect detection device is presented in the form of a functional unit. Here, a unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that execute one or more software or fixed programs, and / or other devices that can provide the above functions.

[0136] This invention also provides a computer device having the above-described features. Figure 4 The device shown is for detecting cracks and defects in a hydropower station dam.

[0137] Please see Figure 5 , Figure 5 This is a schematic diagram of the structure of a computer device provided in an optional embodiment of the present invention, such as... Figure 5 As shown, the computer device includes one or more processors 10, memory 20, and interfaces for connecting the components, including high-speed interfaces and low-speed interfaces. The components communicate with each other via different buses and can be mounted on a common motherboard or otherwise installed as needed. The processors can process instructions executed within the computer device, including instructions stored in or on memory to display graphical information of a GUI on external input / output devices (such as display devices coupled to the interfaces). In some alternative implementations, multiple processors and / or multiple buses can be used with multiple memories and multiple memory modules, if desired. Similarly, multiple computer devices can be connected, each providing some of the necessary operations (e.g., as a server array, a group of blade servers, or a multiprocessor system). Figure 5 Take a processor 10 as an example.

[0138] Processor 10 may be a central processing unit, a network processor, or a combination thereof. Processor 10 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The programmable logic device may be a complex programmable logic device (CAMP), a field-programmable gate array (FPGA), a general-purpose array logic (GDA), or any combination thereof.

[0139] The memory 20 stores instructions executable by at least one processor 10 to cause at least one processor 10 to perform the method shown in the above embodiments.

[0140] The memory 20 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the computer device. Furthermore, the memory 20 may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some alternative embodiments, the memory 20 may optionally include memory remotely located relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0141] The memory 20 may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as flash memory, hard disk or solid-state drive; the memory 20 may also include a combination of the above types of memory.

[0142] The computer device also includes a communication interface 30 for communicating with other devices or communication networks.

[0143] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code, which, when accessed and executed by the computer, processor, or hardware, implements the methods shown in the above embodiments.

[0144] A portion of this invention can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to the invention through the operation of the computer. Those skilled in the art will understand that the forms in which computer program instructions exist in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executing the instructions, or the computer compiling the instructions and then executing the corresponding compiled program, or the computer reading and executing the instructions, or the computer reading and installing the instructions and then executing the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to a computer.

[0145] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A method for detecting crack defects of a dam of a hydropower station, characterized in that, The method comprises: obtaining an original image of a hydropower station dam to be detected; based on the original image, through single-layer discrete two-dimensional wavelet decomposition and ridgelet transform, the maximum ridge variable coefficient is obtained; determine the crack edge direction based on the maximum ridge variable coefficient; construct a crack edge image according to the absolute values of the gradients corresponding to a plurality of pixels in the crack edge direction, the crack edge image being used to represent the strike trajectory of the crack edge; determine the crack defect detection result of the hydropower station dam to be detected according to the crack edge image; wherein, based on the original image, through single-layer discrete two-dimensional wavelet decomposition and ridgelet transform, the maximum ridge variable coefficient is obtained, comprising: performing single-layer discrete two-dimensional wavelet decomposition and equalization processing on the original image to obtain a target image; performing ridgelet transform on the target image to obtain the maximum ridge variable coefficient; wherein, performing ridgelet transform on the target image to obtain the maximum ridge variable coefficient, comprising: performing block processing on the target image to obtain a plurality of sub-images; performing Randon transform on the two-dimensional image signals of each sub-image to obtain a plurality of Randon transform data, the Randon transform being used to perform rotation correction on the image, specifically comprising: performing Randon transform on the original image in each sub-image that has not been rotated to obtain a reference vector, and performing Randon transform on the image that needs to be detected in each sub-image to obtain a plurality of transform vectors; calculating a plurality of correlation coefficients according to the reference vector and the plurality of transform vectors; determining a rotation attack angle according to the projection angle corresponding to the maximum correlation coefficient in the plurality of correlation coefficients; and performing rotation correction on the image subjected to rotation attack by using the rotation attack angle; performing wavelet transform on the plurality of Randon transform data to obtain a plurality of ridge variable coefficients; determine the maximum ridge variable coefficient according to the plurality of ridge variable coefficients.

2. The method of claim 1, wherein, performing single-layer discrete two-dimensional wavelet decomposition and equalization processing on the original image to obtain a target image, comprising: performing single-layer discrete two-dimensional wavelet decomposition on the original image to obtain low-frequency sub-band decomposition coefficients, horizontal high-frequency sub-band decomposition coefficients, vertical high-frequency sub-band decomposition coefficients, and diagonal high-frequency sub-band decomposition coefficients; performing equalization processing on the low-frequency sub-band decomposition coefficients to obtain low-frequency sub-band equalization decomposition coefficients; reconstructing the original image by using the low-frequency sub-band equalization decomposition coefficients, the horizontal high-frequency sub-band decomposition coefficients, the vertical high-frequency sub-band decomposition coefficients, and the diagonal high-frequency sub-band decomposition coefficients to obtain the target image.

3. The method of claim 1, wherein, determine the crack edge direction based on the maximum ridge variable coefficient, comprising: calculating an azimuth angle based on the maximum ridge variable coefficient; determine the crack edge direction based on the azimuth angle.

4. A device for detecting cracks in a dam of a hydroelectric power station, characterized in that, The device comprises: an acquisition module configured to acquire an original image of a hydropower station dam to be detected; a processing module configured to obtain a maximum ridge variable coefficient based on the original image through single-layer discrete two-dimensional wavelet decomposition and ridgelet transform; a first determination module configured to determine a crack edge direction based on the maximum ridge variable coefficient; The constructing module is configured to construct a crack edge image according to a plurality of pixels corresponding to absolute values of a plurality of gradients in the crack edge direction; The second determining module is configured to determine a crack defect detection result of the to-be-detected hydropower station dam according to the crack edge image; The processing module includes: The processing sub-module is configured to perform single-layer discrete two-dimensional wavelet decomposition and equalization processing on the original image to obtain a target image; The transformation sub-module is configured to perform ridgelet transform on the target image to obtain the maximum ridgelet coefficient; The transformation sub-module includes: The block unit is configured to block the target image to obtain a plurality of sub-images; The first transformation unit is configured to perform Randon transform on two-dimensional image signals of each sub-image to obtain a plurality of Randon transform data, the Randon transform being used for rotation correction of the image, and specifically including: performing Randon transform on original images that are not rotated in each sub-image to obtain a reference vector, and performing Randon transform on images that need to be detected in each sub-image to obtain a plurality of transformation vectors; calculating a plurality of correlation coefficients according to the reference vector and the plurality of transformation vectors; determining a rotation attack angle according to a projection angle corresponding to a maximum value of the correlation coefficients in the plurality of correlation coefficients; and performing rotation correction on images subjected to rotation attack by using the rotation attack angle; The second transformation unit is configured to perform wavelet transform on the plurality of Randon transform data to obtain a plurality of ridgelet coefficients; The determining unit is configured to determine the maximum ridgelet coefficient according to the plurality of ridgelet coefficients.

5. A computer device, comprising: The memory and the processor are in communication connection with each other, the memory stores computer instructions, and the processor executes the computer instructions to perform the hydropower station dam crack defect detection method in any one of claims 1 to 3. The computer readable storage medium stores computer instructions, and the computer instructions are used to make a computer execute the hydropower station dam crack defect detection method in any one of claims 1 to 3.

6. A computer-readable storage medium, characterized in that, The computer instructions are used to make a computer execute the hydropower station dam crack defect detection method in any one of claims 1 to 3.

7. A computer program product, characterised in that, ​

Images