A quantitative detection method, system and medium for concrete panel cracks

Abstract

This application relates to a method, system, and medium for quantitative detection of cracks in concrete panels. The method includes the following specific steps: (1) deploying a laser projection target device on the surface of the concrete panel; (2) using an image acquisition device to capture an image containing the crack and the laser target; (3) processing the captured image to identify the crack and the target, and determining their positions in the image; (4) calculating the actual size of the crack by proportional conversion based on the size of the identified target and the size of the crack in the image, thereby achieving quantitative detection of cracks in the concrete panel. This solves the problem of difficulty in quantifying crack length and judging the degree of crack damage in concrete panel crack identification. Furthermore, it uses an automated method to quantify cracks, greatly reducing manual operation and improving the efficiency and accuracy of crack detection. It can be widely applied to crack detection and assessment in concrete construction.

Description

Technical Field

[0001] This application relates to the field of water conservancy engineering quality testing technology, and in particular to a method, system and medium for quantitative detection of cracks in concrete panels. Background Technology

[0002] Concrete panel structures play a crucial role in hydraulic engineering, serving as key components of dams, canals, energy dissipation structures, and other hydraulic facilities. Over time, concrete panel structures may develop cracks, which can be caused by various factors such as material aging, environmental influences, and load variations. The presence of cracks can affect the safety, durability, and reliability of the structure; therefore, regular inspection, identification, and measurement of cracks in concrete panel structures are essential.

[0003] Traditional crack detection methods typically include manual visual inspection and non-destructive testing techniques. However, these methods have certain limitations, such as being time-consuming, labor-intensive, subjective, and difficult to detect in areas with height and environmental constraints. To overcome these limitations, image processing technology has been introduced into the field of crack detection in recent years. By processing and analyzing images of captured concrete panel structures, crack locations can be automatically identified, thereby improving detection efficiency and accuracy.

[0004] However, existing image processing techniques face difficulties in estimating the actual length of cracks. These techniques typically require significant investment, including introducing reference objects of known size or creating complex models to determine the ratio between image pixels and actual size. However, in real-world engineering sites, it is often impossible to introduce suitable reference objects for quantitative measurement, nor are there sufficient resources to build such complex models. Therefore, methods relying on reference objects or models are not suitable for detecting concrete cracks on construction sites. Summary of the Invention

[0005] The purpose of this application is to provide a method, system and medium for quantitative detection of cracks in panel concrete. By using laser projection target technology to provide accurate dimensional reference for image recognition, the crack recognition and quantitative measurement process is made more accurate and efficient. It is applicable to crack detection in panel concrete structures and can solve the problems of lack of accurate reference objects, inaccurate crack measurement and cumbersome manual operation in the prior art.

[0006] To achieve the above objectives, this application provides the following technical solution:

[0007] In a first aspect, embodiments of this application provide a method for quantitative detection of cracks in concrete panels, comprising the following specific steps:

[0008] (1) Deploy a laser projection target device on the concrete surface of the panel;

[0009] (2) Use image acquisition equipment to capture images containing cracks and laser targets;

[0010] (3) Process the captured images to identify cracks and targets and determine their positions in the images;

[0011] (4) Based on the identified target size and the size of the crack in the image, the actual size of the crack is calculated by proportional conversion, thereby realizing the quantitative detection of cracks in the concrete panel.

[0012] Specifically, step (3) is as follows:

[0013] a. The original image is I(x,y). A Gaussian filter G(x,y,σ) is applied for denoising to obtain the processed image I′(x,y):

[0014]

[0015] I′(x,y)=∑∑I(x,y)*G(x,y,σ)

[0016] Where x and y represent the transverse and longitudinal coordinates on the concrete surface of the panel, respectively, and σ represents the standard deviation.

[0017] b. Process the image I′(x,y) into an edge image E(x,y), and detect the set of line segments EB of the target in the image:

[0018] EB(ρ,θ)={(x,y)|E(x,y)≠0,ρ=xcos(θ)+ysin(θ)}

[0019] Where EB(ρ,θ) represents the target edge.

[0020] The method for calculating E(x,y) is as follows:

[0021]

[0022] Where ψ represents double threshold processing, T low and T high These are the two thresholds used in dual-threshold processing.

[0023] c. Perform polygon approximation on EB(ρ,θ). When the approximating polygon has 8 vertices, the contour is considered to be the projection of the laser target onto the concrete panel, and the feature pixel where the target is located is B(x,y).

[0024] d. Use the trained convolutional neural network model to extract the crack feature pixels F(x,y).

[0025] Step (4) specifically involves:

[0026] Calculate the ratio between pixels and actual size; the laser target is set to a size of B. real The size of B(x,y) on the image is B pixel

[0027] k = B real / B pixel

[0028] Crack length quantization: The pixel length of the crack in the image obtained from F(x,y) is F. pixel Convert it to actual size F real :

[0029] F real =F pixel *k.

[0030] Secondly, embodiments of this application provide a quantitative detection system for cracks in panel concrete, including a laser target projection device, an image acquisition device, a data storage device, a laser target pixel extraction module, a crack pixel extraction module, and a crack length quantification calculation module. The laser target projection device is deployed on the surface of the panel concrete. The image acquisition device captures an image of the panel concrete containing cracks and a laser target. The laser target pixel extraction module and the crack pixel extraction module process the image captured by the image acquisition device to obtain the positions of the laser target and cracks in the image. The crack length quantification calculation module realizes the quantitative detection of cracks in the panel concrete based on the positions of the laser target and cracks in the image. The data storage device stores the acquired images and the calculation results.

[0031] Thirdly, embodiments of this application provide a computer-readable storage medium storing program code, which, when executed by a processor, implements the steps of the quantitative detection method for panel concrete cracks as described above.

[0032] Compared with the prior art, the beneficial effects of the present invention are as follows: The present invention uses laser target projection technology to provide an effective size reference for the identification of cracks in concrete panels, which solves the problem that it is difficult to quantify the crack length and determine the degree of damage of cracks in the identification of cracks in concrete panels. Furthermore, the present invention uses an automated method to quantify cracks, which greatly reduces manual operation and improves the efficiency and accuracy of crack detection. It can be widely used in crack detection and evaluation in concrete construction. Attached Figure Description

[0033] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0034] Figure 1 This is a flowchart of the quantitative measurement process for concrete cracks in the panel of this invention;

[0035] Figure 2 This is a flowchart of the target extraction process in this invention;

[0036] Figure 3 This is the overall system architecture diagram of this invention. Detailed Implementation

[0037] The technical solutions of the embodiments of this application will now be described with reference to the accompanying drawings. It should be noted that similar reference numerals and letters in the following drawings indicate similar items; therefore, once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings.

[0038] The terms “comprising,” “including,” or any other variations thereof are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase “comprising one…” does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0039] The terms “first,” “second,” etc., are used only to distinguish one entity or operation from another, and should not be construed as indicating or implying relative importance, nor as requiring or implying any such actual relationship or order between these entities or operations.

[0040] like Figure 1 As shown in the figure, this application provides a method for quantitative detection of cracks in concrete panels, including the following specific steps:

[0041] (1) Deploy a laser projection target device on the concrete surface of the panel;

[0042] (2) Use image acquisition equipment to capture images containing cracks and laser targets;

[0043] (3) Process the captured images to identify cracks and targets and determine their positions in the images;

[0044] (4) Based on the identified target size and the size of the crack in the image, the actual size of the crack is calculated by proportional conversion, thereby realizing the quantitative detection of cracks in the concrete panel.

[0045] like Figure 2 As shown, step (3) specifically involves:

[0046] a. The original image is I(x,y). A Gaussian filter G(x,y,σ) is applied for denoising to obtain the processed image I′(x,y):

[0047]

[0048] I′(x,y)=∑∑I(x,y)*G(x,y,σ)

[0049] Where x and y represent the transverse and longitudinal coordinates on the concrete surface of the panel, respectively, and σ represents the standard deviation.

[0050] b. Process the image I′(x,y) into an edge image E(x,y), and detect the set of line segments EB of the target in the image:

[0051] EB(ρ,θ)={(x,y)|E(x,y)≠0,ρ=xcos(θ)+ysin(θ)}

[0052] Where EB(ρ,θ) represents the target edge.

[0053] The method for calculating E(x,y) is as follows:

[0054]

[0055] Where ψ represents double threshold processing, T low and T high These are the two thresholds used in dual-threshold processing.

[0056] c. Perform polygon approximation on EB(ρ,θ). When the approximating polygon has 8 vertices, the contour is considered to be the projection of the laser target onto the concrete panel, and the feature pixel where the target is located is B(x,y).

[0057] d. Use the trained convolutional neural network model to extract the crack feature pixels F(x,y).

[0058] Step (4) specifically involves:

[0059] Calculate the ratio between pixels and actual size; the laser target is set to a size of B. real The size of B(x,y) on the image is B pixel

[0060] k = B real / B pixel

[0061] Crack length quantization: The pixel length of the crack in the image obtained from F(x,y) is F. pixel Convert it to actual size F real :

[0062] F real =F pixel *k.

[0063] like Figure 3 As shown in the figure, this application provides a quantitative detection system for cracks in concrete panels, including a laser target projection device 1, an image acquisition device 2, a data storage device 3, a laser target pixel extraction module 4, a crack pixel extraction module 5, and a crack length quantification calculation module 6. The laser target projection device 1 is deployed on the surface of the concrete panel. The image acquisition device 2 captures an image of the concrete panel containing cracks and a laser target. The laser target pixel extraction module 4 and the crack pixel extraction module 5 process the image captured by the image acquisition device to obtain the positions of the laser target and cracks in the image. The crack length quantification calculation module 6 realizes the quantitative detection of cracks in the concrete panel based on the positions of the laser target and cracks in the image. The data storage device 3 stores the acquired images and the calculation results.

[0064] This application provides a computer-readable storage medium storing program code. When the program code is executed by a processor, it implements the steps of the quantitative detection method for cracks in panel concrete as described above.

[0065] This application uses laser target projection technology to provide an effective dimensional reference for crack identification in concrete panels, solving the problems of difficulty in quantifying crack length and judging the degree of crack damage in concrete panel crack identification. Furthermore, it uses an automated method to quantify cracks, greatly reducing manual operation and improving crack detection efficiency and accuracy. It can be widely used in crack detection and assessment in concrete construction.

[0066] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0067] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0068] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0069] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0070] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0071] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0072] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0073] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0074] The above description is merely an embodiment of this application and is not intended to limit the scope of protection of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A method for quantitatively detecting a concrete crack of a panel, characterized by, The specific steps include the following: (1) Deploy a laser target projection device on the concrete surface of the panel; (2) Use image acquisition equipment to capture images of the concrete panel containing cracks and laser targets; (3) Process the captured images to identify cracks and laser targets, and determine their positions in the images; (4) Based on the size of the identified laser target and the size of the crack in the image, the actual size of the crack is calculated by proportional conversion, thereby realizing the quantitative detection of cracks in the concrete panel. Step (3) specifically involves: a. The original image is , a Gaussian filter is applied to denoise, obtaining a processed image : ， ， where x and y represent the transverse and longitudinal coordinates on the surface of the panel concrete respectively, denotes the standard deviation, b. graphically processing into an edge image , detecting a set of line segments EB of the laser target in the edge image ， wherein is the laser target edge, The calculation method is as follows: ， in This indicates double threshold processing, T low and T high These are the two thresholds used in dual-threshold processing. c. When performing polygon approximation, and the approximated polygon has 8 vertices, the polygon's outline is considered to be the projection of the laser target onto the concrete panel, and the feature pixel containing the laser target is... , d. Extract crack feature pixels using a trained convolutional neural network model. ; Step (4) specifically involves: Calculate the ratio between pixels and actual size; the laser target is set to a size of B. real， The size on the image is B pixel ， Crack length quantification: From The crack obtained in the image has a pixel length of 1000 pixels. Convert it to actual size : 。 2. A quantitative detection system for concrete panel cracks, employing the quantitative detection method for concrete panel cracks as described in claim 1, characterized in that, The system includes a laser target projection device, an image acquisition device, a data storage device, a laser target pixel extraction module, a crack pixel extraction module, and a crack length quantification calculation module. The laser target projection device is deployed on the surface of the concrete panel. The image acquisition device captures images of the concrete panel containing cracks and the laser target. The laser target pixel extraction module and the crack pixel extraction module process the images captured by the image acquisition device to obtain the positions of the laser target and cracks in the images. The crack length quantification calculation module realizes quantitative detection of cracks in the concrete panel based on the positions of the laser target and cracks in the images. The data storage device stores the acquired images and the calculation results.

3. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores program code, which, when executed by a processor, implements the steps of the quantitative detection method for concrete cracks in a panel as described in claim 1.

Images