Method, device and system for calculating real length of concrete crack and storage medium

Abstract

The invention discloses a concrete crack real length calculation method, device and system, and a storage medium, and the method comprises the steps: S1, enabling the boundary of a crack skeleton image to extend two pixels towards the periphery, and carrying out the statistics of the total number of pixels contained in a skeleton; s2, traversing all pixels in the skeleton, and determining a 5 * 5 neighborhood Nr-F where the pixel is located; s3, a graphic object formed by all pixels in the Nr-F neighborhood is determined, the main axis of an equivalent ellipse Ee-F with the same standard second-order central moment as the object is determined, and the inclination angle of the main axis is the macroscopic inclination angle of a line segment formed by the adjacent pixels; s4, calculating the distance between every two adjacent pixels; and S5, accumulating the distance between every two adjacent pixels to obtain the length of the crack skeleton. By the adoption of the technical scheme, the method has the advantages of being high in crack length precision, high in efficiency and wide in application prospect.

Description

Technical Field

[0001] The present invention belongs to the technical field of image processing, and in particular relates to a method and device, a system and a storage medium for calculating the true length of a concrete crack. Background Art

[0002] The appearance and expansion of concrete cracks will weaken the mechanical properties and durability of concrete, and even threaten the safety and service life of the structure. Therefore, quantitative analysis of crack structural characteristics to evaluate its impact on concrete performance and identify the degree of concrete aging damage is a hot topic in current research.

[0003] Crack length is an important indicator for quantitative crack analysis. Although ruler measurement is the most direct method to obtain crack length, the direct measurement result deviates greatly from the actual length of the crack because cracks are usually not straight segments, have variable inclination angles and have small branches. With the development of digital image processing technology, it is possible to accurately calculate the crack length based on images, which is also one of the research hotspots of intelligent technology in the field of concrete. The image method requires obtaining images containing cracks, and using image segmentation technology to identify, extract and skeletonize cracks. The length of the crack skeleton is the length of the crack. Therefore, the core of the image method is to calculate the length of the crack skeleton (a single-pixel wide line that can represent the crack and does not change the connectivity of the original crack image).

[0004] The calculation principle of the crack skeleton length is the accumulation method, that is, the microscopic distance between the pixel in the crack skeleton and its next adjacent pixel is calculated one by one in order, and then all the distances are summed. In the crack skeleton image, the calculation formula for the microscopic distance between adjacent pixels is:

[0005]

[0006] Among them, l is the microscopic spacing between adjacent pixels; θ is the microscopic inclination angle between adjacent pixels.

[0007] There are three traditional methods for calculating micro spacing:

[0008] 1. Pixel number method: All microscopic inclination angles are taken as 0°, and all microscopic spacings are considered to be 1. The essence of this method is to consider the number of pixels as the crack skeleton length, ignoring the macroscopic inclination angle of the crack, and is only applicable to the case where the macroscopic inclination angle of the crack is 0° or 90°.

[0009] 2. Microscopic inclination method: Set the microscopic inclination angle to 0°, 45° and 90°, and the corresponding microscopic spacing is 1, and 1. This method has improved accuracy compared with the pixel number method.

[0010] 3. Parameter correction method: Based on statistical data, the microscopic pitches corresponding to the microscopic inclination angles of 0°, 45° and 90° are set to 0.948, 1.340 and 0.948 respectively, and the accuracy is further improved.

[0011] Although the above three methods have small errors in calculating the crack length at a specific inclination angle, the length calculation results often have large errors for actual crack images with arbitrary and variable inclination angles. Summary of the invention

[0012] The technical problem to be solved by the present invention is to provide a method and device, system and storage medium for calculating the true length of concrete cracks, that is, when taking the value of the microscopic inclination angle, the macroscopic inclination angle of the crack area where the pixel is located is considered and then the skeleton length is obtained by accumulating the microscopic spacing. The method has the characteristics of high crack length accuracy, high efficiency and broad application prospects.

[0013] To achieve the above object, the present invention adopts the following technical solution:

[0014] A method for calculating the true length of a concrete crack comprises:

[0015] Step S1, expanding the boundary of the crack skeleton image by 2 pixels in all directions, and counting the total number of pixels contained in the skeleton;

[0016] Step S2, traverse all pixels in the skeleton and determine the 5×5 neighborhood Nr-F where the pixel is located;

[0017] Step S3, determining a graphic object composed of all pixels in the neighborhood of Nr-F, and determining the principal axis of an equivalent ellipse Ee-F having the same standard second-order central moment as the object, wherein the inclination angle of the principal axis is the macroscopic inclination angle θ of the line segment composed of the adjacent pixels;

[0018] Step S4: Calculate the distance L between every two adjacent pixels i ;

[0019] Step S5: Accumulate the distance L between every two adjacent pixels i , and obtain the length L of the crack skeleton.

[0020] Preferably, step S4 is:

[0021]

[0022] Among them, L i is the distance between the i-th pixel and the i+1-th pixel; θ is the macroscopic inclination angle, ranging from -90° to 90°;

[0023] Preferably, the graphic object is composed of pixel clusters of different lengths and angles, and is used to represent straight line segments, curve segments and mixed line segments of arbitrary inclination angles.

[0024] The present invention also provides a device for calculating the true length of a concrete crack, comprising:

[0025] The first processing module is used to expand the boundary of the crack skeleton image by 2 pixels in all directions and count the total number of pixels included in the skeleton;

[0026] The second processing module is used to traverse all pixels in the skeleton and determine the 5×5 neighborhood Nr-F where the pixel is located;

[0027] The third processing module is used to determine the graphic object composed of all pixels in the neighborhood of Nr-F, and determine the main axis of the equivalent ellipse Ee-F with the same standard second-order central moment as the object, and the inclination angle of the main axis is the macro inclination angle θ of the line segment composed of the adjacent pixels;

[0028] The fourth processing module is used to calculate the distance L between every two adjacent pixels. i ;

[0029] The fifth processing module is used to accumulate the distance L between every two adjacent pixels. i , and obtain the length L of the crack skeleton.

[0030] Preferably, the calculation process of the fourth processing module is:

[0031]

[0032] Among them, L i is the distance between the i-th pixel and the i+1-th pixel; θ is the macroscopic inclination angle, ranging from -90° to 90°.

[0033] Preferably, the graphic object is composed of pixel clusters of different lengths and angles, and is used to represent straight line segments, curve segments and mixed line segments of arbitrary inclination angles.

[0034] The present invention also provides a concrete crack true length calculation system, comprising: a memory and a processor, wherein the memory stores a computer program executed by the processor, and the computer program executes a concrete crack true length calculation method when executed by the processor.

[0035] The present invention also provides a storage medium, on which a computer program is stored, and the computer program executes the method for calculating the true length of concrete cracks when running.

[0036] The present invention takes into account the macroscopic inclination angle of the crack region where the pixel is located when calculating the microscopic spacing between adjacent pixels. The beneficial effects are:

[0037] (1) The algorithm is highly accurate and the calculated results are closer to the exact length of the crack;

[0038] (2) It has strong versatility and broad application prospects and can be applied to cracks with arbitrary macroscopic inclination angles. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0040] Figure 1 It is a flow chart of a method for calculating the true length of a concrete crack according to an embodiment of the present invention;

[0041] Figure 2 The figure is a calculation principle diagram of the method for calculating the true length of concrete cracks according to an embodiment of the present invention;

[0042] Figure 3 is a schematic diagram of a graphic object according to an embodiment of the present invention; wherein, Figure 3 (a), (b) and (c) are straight line segments with inclination angles of 22.5°, 36.9° and 45° respectively; Figure 3 (d) is a broken line segment containing two broken corners; Figure 3 (e) is a circle with r = 125 pixels; Figure 3 (f) and (g) are lines with different numbers of intersections; Figure 2 (h) and (i) are combinations of broken line segments and arc segments. DETAILED DESCRIPTION

[0043] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0044] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0045] Embodiment 1:

[0046] like Figure 1 , 2 As shown, an embodiment of the present invention provides a method for calculating the true length of a concrete crack, which considers the macroscopic inclination of the crack area where the pixel is located when calculating the microscopic spacing, and then accumulates the microscopic spacing to obtain the skeleton length, that is, the crack length. Specifically, it includes:

[0047] Step S1, expanding the boundary of the crack skeleton image by 2 pixels in all directions, and counting the total number of pixels n contained in the skeleton;

[0048] Step S2, traverse all pixels in the skeleton, select a pixel in the crack skeleton, take a specific pixel F as an example, and determine the 5×5 neighborhood Nr-F where the pixel is located;

[0049] Step S3, determining a graphic object composed of all pixels in the neighborhood of Nr-F, and determining the principal axis of an equivalent ellipse Ee-F having the same standard second-order central moment as the object, wherein the inclination angle of the principal axis is the macroscopic inclination angle of the line segment composed of the adjacent pixels;

[0050] Step S4: Calculate the distance between every two adjacent pixels.

[0051]

[0052] Among them, L i is the distance between the i-th pixel and the i+1-th pixel; θ is the macroscopic inclination angle, ranging from -90° to 90°;

[0053] Step S5: Accumulate the distance L between every two adjacent pixels i , and obtain the length L of the crack skeleton.

[0054] L=∑L i

[0055] The crack skeleton, as defined in the background technology section, refers to a single-pixel wide line that can represent a crack and does not change the connectivity of the original crack image;

[0056] Wherein, the length of the crack skeleton is the crack length;

[0057] The total number of pixels n contained in the statistical skeleton is Figure 1 Medium, n = 21;

[0058] In the above, a pixel in the crack skeleton is selected, taking a specific pixel F as an example, to determine the 5×5 neighborhood Nr-F where the pixel is located. This neighborhood is defined as a square area with a distance of two pixels extending around the pixel F to form a 25-pixel area.

[0059] Among them, the selection of a pixel in the crack skeleton, taking a specific pixel F as an example, determines the 5×5 neighborhood Nr-F where the pixel is located. The selection of this neighborhood size is based on experimental analysis, and the comparison of detailed neighborhood size test results will be shown in subsequent embodiments;

[0060] The graphic object is composed of a series of pixel clusters of different lengths and angles, which can represent straight line segments, curve segments and mixed line segments of any inclination angle. A pixel cluster is a unit composed of a group of closely connected pixels;

[0061] The distance between adjacent pixels, i.e., the microscopic spacing, is the length of the line connecting the midpoints of adjacent pixels;

[0062] The main axis inclination angle, the angle θ between the main axis direction and the x-axis, is the macroscopic inclination angle of the line segment composed of adjacent pixels, and the value range is -90°-90°, with the counterclockwise direction being positive;

[0063] The steps for determining the major axis of the equivalent ellipse Ee-F having the same standard second-order central moment as the object are as follows:

[0064] a. Determine coordinates and center of gravity: Determine the coordinates for each pixel in the graphic object and calculate the center of gravity of all pixels.

[0065] b. Calculate the second-order central moment: Calculate the second-order central moment M related to the center of gravity xx 、M yy and M xy ;

[0066] c. Calculate the spindle inclination angle θ:

[0067] The embodiment of the present invention aims to verify the influence of different neighborhood sizes on the calculation effect of the true length of concrete cracks. Four different neighborhood sizes of 3×3, 5×5, 7×7 and 11×11 are used for calculation. Figure 3 The crack lengths of 9 different graphic objects in the calculation are shown in Table 1.

[0068] As can be seen from Table 1, the relative error of the calculated length corresponding to the 3×3 neighborhood is large, the relative error of the calculated length corresponding to the 11×11 neighborhood is small, and the relative errors of the calculated length corresponding to the 5×5 neighborhood and the 7×7 neighborhood are very small; the components of the crack skeleton are mostly a combination of straight lines and curves, with fewer straight line segments; under the 5×5 neighborhood, the relative error of the calculated length of the combination of straight lines and curves is the smallest. In summary, considering the error and calculation efficiency, the neighborhood size is determined to be 5×5 in the calculation of cracks.

[0069] Table 1

[0070]

[0071] In order to test the applicability of the algorithm proposed in this invention, Figure 3 The lengths of 9 different graphic objects in the algorithm are calculated and compared with the existing algorithms. The comparison results are shown in Table 2.

[0072] As can be seen from Table 2, the average absolute value of the relative error of the macro inclination method is 0.4%, which is much smaller than that of other methods. When using this method to calculate, the absolute value of the relative error of each graphic object is less than 1%. Figure 3 (c), its relative error is 0.0%; the pixel number method, microscopic inclination method and parameter correction method have large relative errors and large relative error fluctuation ranges between different graphic objects, while when using the macroscopic inclination method, the relative error is extremely small and the fluctuation range is extremely small. The accuracy of the calculation results of the macroscopic inclination method is higher than that of other algorithms, and it can be well applied to different structural features and has universal applicability; the macroscopic inclination method improves the consistency between the macroscopic inclination of the crack skeleton and the inclination of the line segments composed of adjacent pixels in the skeleton, making the calculation of the distance between adjacent pixels and the cumulative summation results more consistent with the actual situation, and the calculation results are more accurate.

[0073] Table 2

[0074]

[0075] Embodiment 2:

[0076] The embodiment of the present invention further provides a device for calculating the true length of a concrete crack, comprising:

[0077] The first processing module is used to expand the boundary of the crack skeleton image by 2 pixels in all directions and count the total number of pixels included in the skeleton;

[0078] The second processing module is used to traverse all pixels in the skeleton and determine the 5×5 neighborhood Nr-F where the pixel is located;

[0079] The third processing module is used to determine the graphic object composed of all pixels in the neighborhood of Nr-F, and determine the main axis of the equivalent ellipse Ee-F with the same standard second-order central moment as the object, and the inclination angle of the main axis is the macro inclination angle θ of the line segment composed of the adjacent pixels;

[0080] The fourth processing module is used to calculate the distance L between every two adjacent pixels. i ;

[0081] The fifth processing module is used to accumulate the distance L between every two adjacent pixels. i , and obtain the length L of the crack skeleton.

[0082] As an implementation of the embodiment of the present invention, the calculation process of the fourth processing module is:

[0083]

[0084] Among them, L iis the distance between the i-th pixel and the i+1-th pixel; θ is the macroscopic inclination angle, ranging from -90° to 90°.

[0085] As an implementation method of an embodiment of the present invention, the graphic object is composed of pixel clusters of different lengths and angles, and is used to represent straight line segments, curve segments and mixed line segments of arbitrary inclination angles.

[0086] Embodiment 3:

[0087] An embodiment of the present invention further provides a system for calculating the true length of a concrete crack, comprising: a memory and a processor, wherein the memory stores a computer program executed by the processor, and the computer program executes a method for calculating the true length of a concrete crack when executed by the processor.

[0088] Embodiment 4:

[0089] An embodiment of the present invention further provides a storage medium, on which a computer program is stored, and the computer program executes a method for calculating the true length of a concrete crack when running.

[0090] The embodiments described above are only descriptions of the preferred embodiments of the present invention and are not intended to limit the scope of the present invention. Without departing from the design spirit of the present invention, various modifications and improvements made to the technical solutions of the present invention by ordinary technicians in this field should all fall within the protection scope determined by the claims of the present invention.

Claims

1. A method for calculating the true length of a concrete crack, characterized in that: include: Step S1, expanding the boundary of the crack skeleton image by 2 pixels in all directions, and counting the total number of pixels contained in the skeleton; Step S2, traverse all pixels in the skeleton and determine the 5×5 neighborhood Nr-F where the pixel is located; Step S3, determining a graphic object composed of all pixels in the neighborhood of Nr-F, and determining the principal axis of an equivalent ellipse Ee-F having the same standard second-order central moment as the object, wherein the inclination angle of the principal axis is the macroscopic inclination angle θ of the line segment composed of the adjacent pixels; Step S4: Calculate the distance L between every two adjacent pixels i ; Step S5: Accumulate the distance L between every two adjacent pixels i , and obtain the length L of the crack skeleton.

2. The method for calculating the true length of concrete cracks according to claim 1, characterized in that: Step S4 is: Among them, L i is the distance between the i-th pixel and the i+1-th pixel; θ is the macroscopic inclination angle, ranging from -90° to 90°.

3. The method for calculating the true length of concrete cracks according to claim 2, characterized in that: The graphic object is composed of pixel clusters of different lengths and angles, and is used to represent straight line segments, curve segments and mixed line segments of arbitrary inclination angles.

4. A device for calculating the true length of a concrete crack, characterized in that: include: The first processing module is used to expand the boundary of the crack skeleton image by 2 pixels in all directions and count the total number of pixels included in the skeleton; The second processing module is used to traverse all pixels in the skeleton and determine the 5×5 neighborhood Nr-F where the pixel is located; The third processing module is used to determine the graphic object composed of all pixels in the neighborhood of Nr-F, and determine the main axis of the equivalent ellipse Ee-F with the same standard second-order central moment as the object, and the inclination angle of the main axis is the macro inclination angle θ of the line segment composed of the adjacent pixels; The fourth processing module is used to calculate the distance L between every two adjacent pixels. i ; The fifth processing module is used to accumulate the distance L between every two adjacent pixels. i , and obtain the length L of the crack skeleton.

5. The device for calculating the true length of a concrete crack according to claim 4, characterized in that: The calculation process of the fourth processing module is: Among them, L i is the distance between the i-th pixel and the i+1-th pixel; θ is the macroscopic inclination angle, ranging from -90° to 90°.

6. The device for calculating the true length of a concrete crack according to claim 5, characterized in that: The graphic object is composed of pixel clusters of different lengths and angles, and is used to represent straight line segments, curve segments and mixed line segments of arbitrary inclination angles.

7. A concrete crack true length calculation system, characterized in that: include: A memory and a processor, wherein the memory stores a computer program executed by the processor, and when the computer program is executed by the processor, the method for calculating the true length of a concrete crack according to any one of claims 1 to 3 is executed.

8. A storage medium, characterized in that: The storage medium stores a computer program, which executes the method for calculating the true length of a concrete crack according to any one of claims 1 to 3 when running.

Images