A method for calculating the width of a concrete surface crack based on the micro-element method

Abstract

The application discloses a concrete surface crack width calculation method based on the micro-element method, and comprises the following steps: acquiring a binary image of a crack to be calculated, and dividing the binary image into a plurality of micro units, and then calculating pixel coordinates of two side edges of each micro unit and center point coordinates of each micro unit; for each micro unit, the following steps are performed: obtaining a fitting edge line corresponding to the two side edges of the micro unit; obtaining the foot point coordinates of the micro unit; wherein the foot point coordinates refer to intersection point coordinates of the fitting edge line and its perpendicular line when the perpendicular lines of the two fitting edge lines intersect at the center point of the micro unit; based on the foot point coordinates, the Euclidean distance of the two foot points is calculated as the crack width of the current micro unit. The application realizes sub-pixel level precision of the crack width, improves the calculation efficiency, provides important support for quantitative evaluation of the concrete structure surface crack, and is favorable for revealing the structure stress mechanism and evaluating the structure safety.

Description

Technical Field

[0001] This invention relates to the field of concrete crack detection technology, and in particular to a method for calculating the width of concrete surface cracks based on the micro-element method. Background Technology

[0002] In recent years, cracks, as one of the most common defects in reinforced concrete structures, have been a major concern for technical personnel in the field of existing building structure inspection. Currently, on-site inspection of concrete cracks mainly relies on manual inspection, using equipment such as measuring tapes to trace the cracks. This method is not only costly and subjective, but also suffers from drawbacks such as inaccuracy, incomplete recording, and low efficiency.

[0003] With the rapid development of image processing and deep learning technologies, pixel-level segmentation and extraction of cracks using image processing or deep learning techniques has become a research hotspot.

[0004] However, after pixel-level segmentation and extraction of crack images, calculating parameters such as crack width becomes the next important task. Currently, common crack width calculation methods include those based on the vertical line of the central axis, the minimum distance from the edge lines, local average crack width, and crack width based on grayscale values. These methods primarily achieve integer pixel-level accuracy, and the thinning algorithms used for crack edges and the central axis have significant errors, especially at locations with abrupt changes in crack direction and at the two ends. Furthermore, some methods require preprocessing of the crack's orientation, such as image rotation. Therefore, finding a fast and accurate method for calculating concrete crack width is essential. Summary of the Invention

[0005] This invention provides a method for calculating the width of cracks on concrete surfaces based on the micro-element method, in order to solve the technical problems of large errors and low calculation efficiency in existing technologies.

[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution:

[0007] On one hand, the present invention provides a method for calculating the width of cracks on concrete surfaces based on the infinitesimal element method, the method comprising:

[0008] Obtain a binarized image of the crack width to be calculated, divide the binarized image into multiple micro-units, and then calculate the pixel coordinates of the two sides of each micro-unit and the center point coordinates of each micro-unit respectively.

[0009] For each micro-element, perform the following steps to calculate the crack width on each micro-element:

[0010] Based on the pixel coordinates of the two sides of the micro-unit, the fitted edge lines corresponding to the two sides of the micro-unit are obtained;

[0011] Obtain the coordinates of the perpendicular foot point of the micro-unit; wherein, the coordinates of the perpendicular foot point refer to the coordinates of the intersection point of the fitting edge line and its perpendicular line when the perpendicular lines of the two fitting edge lines intersect at the center point of the micro-unit;

[0012] Based on the coordinates of the perpendicular foot points, the distance between the two perpendicular foot points is calculated and used as the crack width of the current micro-element.

[0013] Further, obtaining the binarized image of the crack width to be calculated includes:

[0014] Acquire images of concrete surface cracks whose width is to be calculated;

[0015] The crack image is processed to obtain a binarized image of the crack.

[0016] Further, the crack image is processed to obtain a binarized image of the crack, including:

[0017] First, the crack image is converted to grayscale to obtain a grayscale image; then, an image filtering algorithm is used to filter the grayscale image; finally, a threshold segmentation algorithm is used to obtain a binary image of the crack.

[0018] Alternatively, the crack image can be input into a preset deep learning model to obtain a pixel-level segmented crack image, and then the image output by the model can be binarized to obtain a binarized crack image.

[0019] Furthermore, the calculation process for the pixel coordinates of the two edges of the micro-unit and the center point coordinates includes:

[0020] First, calculate the local pixel coordinates of the two edges of the micro-unit and the local coordinates of the center point of the micro-unit. Then, convert the calculated local pixel coordinates and the local coordinates of the center point of the micro-unit into global coordinates.

[0021] Further, obtaining the fitted edge lines corresponding to the two sides of the micro-unit based on the pixel coordinates of the two sides of the micro-unit includes:

[0022] Based on the pixel coordinates of the two sides of the micro-unit, a preset interpolation algorithm is used to interpolate the pixels on both sides of the micro-unit to obtain the interpolated pixels on both sides of the micro-unit.

[0023] A preset fitting algorithm is used to fit the interpolated edge pixels on both sides of the micro-unit to obtain the fitted edge lines corresponding to the edges on both sides of the micro-unit.

[0024] Furthermore, the preset interpolation algorithm is a bicubic spline interpolation algorithm.

[0025] Furthermore, the preset fitting algorithm is a least squares fitting algorithm.

[0026] Furthermore, the calculation of the distance between the two perpendicular points based on their coordinates includes:

[0027] The Euclidean distance between the two perpendicular points is calculated based on their coordinates.

[0028] In another aspect, the present invention also provides an electronic device comprising a processor and a memory; wherein the memory stores at least one instruction, which is loaded and executed by the processor to implement the above-described method.

[0029] In another aspect, the present invention also provides a computer-readable storage medium storing at least one instruction that is loaded and executed by a processor to implement the above-described method.

[0030] The beneficial effects of the technical solution provided by this invention include at least the following:

[0031] 1. This invention is based on the idea of ​​the finite element method and uses the micro-element method to calculate the width of concrete cracks. This can avoid the errors caused by the crack centerline refinement algorithm, as well as the errors caused at the crack direction change points and the two ends edge points. The micro-element of the crack can also more realistically reflect the actual width of the crack, and at the same time improve the calculation efficiency.

[0032] 2. By using a bicubic spline interpolation algorithm to interpolate the crack edge line and then using the least squares method to fit the edge line, subpixel-level accuracy can be achieved, thus resulting in high computational accuracy.

[0033] 3. The perpendicular lines of the fitted edge lines on both sides of the micro-unit intersect at the center point of the micro-unit. The distance between the feet of the two perpendiculars approximates the center line of the micro-unit to the greatest extent, thus maximizing the calculation accuracy. Attached Figure Description

[0034] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0035] Figure 1 This is a schematic diagram of the execution flow of the concrete surface crack width calculation method based on the micro-element method provided in the embodiment of the present invention;

[0036] Figure 2 This is a schematic diagram of the crack width micro-unit division provided in an embodiment of the present invention;

[0037] Figure 3 This is a schematic diagram of the micro-unit crack width calculation provided in an embodiment of the present invention. Detailed Implementation

[0038] To make the objectives, technical solutions, and advantages of the present invention clearer, the embodiments of the present invention will be described in further detail below with reference to the accompanying drawings.

[0039] First Embodiment

[0040] To address the issues of large errors and low computational efficiency in existing technologies, this embodiment provides a more accurate and efficient method for calculating concrete crack width based on the finite element method. This method, based on the fundamental principles of the finite element method, directly calculates the crack width on the concrete surface using the finite element method and interpolation algorithms. It eliminates the need for crack centerline refinement algorithms, thus mitigating errors caused by these algorithms and abrupt changes at single points. This achieves sub-pixel accuracy in crack width calculation while also improving computational efficiency. This provides crucial support for the quantitative assessment of surface cracks in concrete structures, facilitating the revelation of structural stress mechanisms and the evaluation of structural safety.

[0041] Specifically, the execution flow of this method is as follows: Figure 1 As shown, it includes the following steps:

[0042] S1, Acquire images of concrete surface cracks with the width to be calculated;

[0043] It should be noted that when acquiring images of cracks on the concrete surface, smartphones or SLR cameras, tripods, laser rangefinders, and other equipment can be used. Images of cracks at various locations on the concrete surface should be acquired according to the acquisition plan. During acquisition, the tripod with the camera should be placed in front of the object being photographed. The position of the camera should be adjusted based on the level bubble on the tripod and the laser rangefinder, ensuring that the main optical axis of the camera is perpendicular to the surface of the concrete structure being measured. The object distance should then be recorded.

[0044] Given that the shooting equipment information and object distance are known, the pixel unit can be converted into standard units such as millimeters based on the existing pixel calibration value conversion formula, which will not be elaborated here.

[0045] S2, process the acquired crack images to obtain a crack binarized image;

[0046] It should be noted that there are two main ways to process the acquired crack images to obtain a crack binarized image, and either one can be chosen in practice.

[0047] Firstly, the crack image is converted to grayscale to obtain a grayscale image. Then, image filtering algorithms (such as mean filtering, Gaussian filtering, median filtering, etc.) are used to filter the grayscale image. Finally, a threshold segmentation algorithm is used to obtain a binary image of the crack.

[0048] Secondly, the crack image is input into an existing deep learning model. The model automatically outputs a pixel-level segmented crack image, which is then binarized to obtain a binarized crack image. It's important to note that if a pre-trained deep learning model for cracks is unavailable, a dataset of concrete crack images can be collected, labeled, and used to train the deep learning model. The trained model can then directly segment crack images pixel-level.

[0049] S3, divide the crack binarized image into multiple micro-units, and then calculate the pixel coordinates of the two sides of each micro-unit and the center point coordinates of each micro-unit respectively.

[0050] Specifically, in this embodiment, such as Figure 2 As shown, firstly, the binarized crack image is divided into multiple micro-units i (i = 1, 2, ..., N), where N represents the number of micro-units. Secondly, the local coordinates of the edge pixels on both sides (side A and side B) and the local coordinates of the center point of each micro-unit are calculated. Then, the calculated local coordinates are converted into global coordinates. The global coordinate sets of the pixels on side A and side B of the micro-unit are respectively A ij ={(x ij ,y ij )|j∈M},B ij ={(X ij ,Y ij )|j∈M} (M is the number of edge pixels of the micro-unit), and the global coordinates of the center point of the micro-unit are P. i (x i ,y i ).

[0051] S4. The bicubic spline interpolation algorithm is used to interpolate the edge pixels on both sides of the current micro-unit. The least squares method is used to fit the interpolated pixels to obtain the fitted edge line of the current micro-unit with sub-pixel accuracy.

[0052] Specifically, in this embodiment, such as Figure 3 As shown, taking a micro-unit as an example, firstly, pixel A on the edge line of micro-unit A... ij Perform bicubic spline interpolation, and then fit the interpolated edge lines using the least squares method to obtain the slope k of the fitted edge lines on that side. Ai And the coordinates of any point A on the edge line i0 (x Ai0 ,y Ai0The fitted edge line equation is:

[0053] y = k Ai ×(xx Ai0 )+y Ai0

[0054] Similarly, perform the same operation on the edge pixels of micro-unit B as on side A to obtain the slope k of the fitted edge line. Bi And the coordinates of any point B on the edge line i0 (x Bi0 ,y Bi0 The fitted edge line equation is:

[0055] y = k Bi ×(xx Bi0 )+y Bi0

[0056] S5, when the perpendicular lines of the two fitted edge lines of the current micro-unit intersect at its center point, obtain the coordinates of the intersection point of the two perpendicular lines and the edge line, that is, the coordinates of the perpendicular foot point of the current micro-unit;

[0057] Specifically, in this embodiment, such as Figure 3 As shown, the method for finding the coordinates of the perpendicular foot point of the micro-element is as follows:

[0058] When k Ai When the value is not 0, the center point P of the micro-unit i (x i ,y i The slope is The equation of the straight line is:

[0059]

[0060] When k Ai When the value is 0, it passes through the center point P of the micro-unit. i (x i ,y i The equation of the straight line is:

[0061] x = x i

[0062] Then the point where the straight line intersects the fitted edge line on side A, i.e., the foot of the perpendicular, is A. i (x Ai ,y Ai ), to obtain x Ai y Ai They are respectively:

[0063]

[0064]

[0065] Similarly, we can obtain the intersection point B, which passes through the center point of the micro-unit and intersects perpendicularly with the fitted edge line on side B. i (x Bi ,y Bi ), where x Bi y Bi They are respectively:

[0066]

[0067]

[0068] S6, calculate the Euclidean distance between the two perpendicular points as the crack width of the current micro-element;

[0069] The Euclidean distance between the two perpendicular points is used as the crack width of the micro-element, and the calculation formula is as follows:

[0070]

[0071] Where, distance d i This is the crack width of micro-unit i.

[0072] S7. Traverse all micro-units and repeat S4 to S6 after each traversal to calculate the crack width on each micro-unit of the crack.

[0073] In summary, this embodiment provides a method for calculating concrete crack width based on the micro-element method. Combining the shape characteristics of cracks on the concrete structure surface, and based on the fundamental idea of ​​the finite element method, the micro-element method is used to calculate the crack width. This avoids errors caused by the crack centerline refinement algorithm, as well as errors at locations of abrupt changes in crack direction and at the edges. The micro-element of the crack more accurately reflects the actual crack width, while also improving computational efficiency. Using a bicubic spline interpolation algorithm to interpolate the crack edge lines and then fitting the edge lines using the least squares method achieves sub-pixel accuracy, thus yielding high computational precision. The perpendiculars of the fitted edge lines on both sides of the micro-element intersect at the center point of the micro-element. The distance between the two perpendicular feet approximates the centerline of the micro-element to the greatest extent possible, thus maximizing computational accuracy. This provides important support for the quantitative assessment of surface cracks in concrete structures, and is beneficial for revealing the structural stress mechanism and evaluating structural safety.

[0074] Second Embodiment

[0075] This embodiment provides an electronic device, which includes a processor and a memory; wherein the memory stores at least one instruction, which is loaded and executed by the processor to implement the method of the first embodiment.

[0076] The electronic device can vary considerably depending on its configuration or performance, and may include one or more processors (central processing units, CPUs) and one or more memories, wherein the memories store at least one instruction that is loaded by the processor and executed in accordance with the above method.

[0077] Third Embodiment

[0078] This embodiment provides a computer-readable storage medium storing at least one instruction, which is loaded and executed by a processor to implement the method of the first embodiment described above. The computer-readable storage medium may be a ROM, random access memory, CD-ROM, magnetic tape, floppy disk, or optical data storage device, etc. The instruction stored therein can be loaded and executed by a processor in a terminal.

[0079] Furthermore, it should be noted that the present invention can be provided as a method, apparatus, or computer program product. Therefore, embodiments of the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, embodiments of the present invention can take the form of a computer program product implemented on one or more computer-usable storage media containing computer-usable program code.

[0080] Embodiments of the present invention are described with reference to flowchart illustrations and / or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the invention. 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, embedded processor, or other programmable data processing terminal device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal device, generate instructions for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0081] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing terminal device to operate 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 1The functions specified in one or more boxes. These computer program instructions may also be loaded onto a computer or other programmable data processing terminal equipment to cause a series of operational steps to be performed on the computer or other programmable terminal equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable terminal 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.

[0082] It should also be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. The terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal device 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 terminal device. 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 terminal device that includes said element.

[0083] Finally, it should be noted that the above description represents a preferred embodiment of the present invention. It should be pointed out that although preferred embodiments have been described, those skilled in the art, once they understand the basic inventive concept of the present invention, can make various improvements and modifications without departing from the principles described herein. These improvements and modifications should also be considered within the scope of protection of the present invention. Therefore, the appended claims are intended to be interpreted as including both the preferred embodiments and all changes and modifications falling within the scope of the embodiments of the present invention.

Claims

1. A method for calculating the width of a crack in a concrete surface based on the microelement method, characterized by, The method comprises the following steps: acquire a binarized image of a crack to be calculated in width, and divide the binarized image into a plurality of micro-units, and then calculate the pixel coordinates of the edges on both sides of each micro-unit and the coordinates of the center point of each micro-unit; for each micro-unit, the following steps are performed to calculate the crack width on each micro-unit: use a bicubic spline interpolation algorithm to interpolate the pixels on both sides of the current micro-unit, and perform least squares fitting on the interpolated pixels to obtain a fitting edge line with sub-pixel accuracy for the current micro-unit; obtain the foot point coordinates of the micro-unit; wherein the foot point coordinates refer to the coordinates of the intersection point of the fitting edge line and its perpendicular line when the perpendicular lines of the two fitting edge lines intersect at the center point of the micro-unit; based on the foot point coordinates, calculate the distance between the two foot points as the crack width of the current micro-unit.

2. The microelement-based method for calculating the width of a crack in a concrete surface according to claim 1, wherein The method comprises the following steps: acquire a binarized image of a crack to be calculated in width, and divide the binarized image into a plurality of micro-units, and then calculate the pixel coordinates of the edges on both sides of each micro-unit and the coordinates of the center point of each micro-unit; for each micro-unit, the following steps are performed to calculate the crack width on each micro-unit:

3. The microelement-based method for calculating the width of a crack in a concrete surface according to claim 2, wherein use a bicubic spline interpolation algorithm to interpolate the pixels on both sides of the current micro-unit, and perform least squares fitting on the interpolated pixels to obtain a fitting edge line with sub-pixel accuracy for the current micro-unit; obtain the foot point coordinates of the micro-unit; wherein the foot point coordinates refer to the coordinates of the intersection point of the fitting edge line and its perpendicular line when the perpendicular lines of the two fitting edge lines intersect at the center point of the micro-unit; based on the foot point coordinates, calculate the distance between the two foot points as the crack width of the current micro-unit.

4. The microelement-based method for calculating the width of a crack in a concrete surface according to claim 1, wherein The method comprises the following steps: acquire a binarized image of a crack to be calculated in width, and divide the binarized image into a plurality of micro-units, and then calculate the pixel coordinates of the edges on both sides of each micro-unit and the coordinates of the center point of each micro-unit; 5. The microelement-based method for calculating the width of a crack in a concrete surface according to claim 1, wherein for each micro-unit, the following steps are performed to calculate the crack width on each micro-unit: use a bicubic spline interpolation algorithm to interpolate the pixels on both sides of the current micro-unit, and perform least squares fitting on the interpolated pixels to obtain a fitting edge line with sub-pixel accuracy for the current micro-unit; obtain the foot point coordinates of the micro-unit; wherein the foot point coordinates refer to the coordinates of the intersection point of the fitting edge line and its perpendicular line when the perpendicular lines of the two fitting edge lines intersect at the center point of the micro-unit; 6. The microelement-based method of calculating the width of a crack in a concrete surface according to claim 1, wherein, based on the foot point coordinates, calculate the distance between the two foot points as the crack width of the current micro-unit. The method comprises the following steps: acquire a binarized image of a crack to be calculated in width, and divide the binarized image into a plurality of micro-units, and then calculate the pixel coordinates of the edges on both sides of each micro-unit and the coordinates of the center point of each micro-unit; for each micro-unit, the following steps are performed to calculate the crack width on each micro-unit: use a bicubic spline interpolation algorithm to interpolate the pixels on both sides of the current micro-unit, and perform least squares fitting on the interpolated pixels to obtain a fitting edge line with sub-pixel accuracy for the current micro-unit; obtain the foot point coordinates of the micro-unit; wherein the foot point coordinates refer to the coordinates of the intersection point of the fitting edge line and its perpendicular line when the perpendicular lines of the two fitting edge lines intersect at the center point of the micro-unit; based on the foot point coordinates, calculate the distance between the two foot points as the crack width of the current micro-unit. The method comprises the following steps: acquire a binarized image of a crack to be calculated in width, and divide the binarized image into a plurality of micro-units, and then calculate the pixel coordinates of the edges on both sides of each micro-unit and the coordinates of the center point of each micro-unit; for each micro-unit, the following steps are performed to calculate the crack width on each micro-unit: use a bicubic spline interpolation algorithm to interpolate the pixels on both sides of the current micro-unit, and perform least squares fitting on the interpolated pixels to obtain a fitting edge line with sub-pixel accuracy for the current micro-unit; obtain the foot point coordinates of the micro-unit; wherein the foot point coordinates refer to the coordinates of the intersection point of the fitting edge line and its perpendicular line when the perpendicular lines of the two fitting edge lines intersect at the center point of the micro-unit; based on the foot point coordinates, calculate the distance between the two foot points as the crack width of the current micro-unit.

Images