Concrete crack detection method for bridge engineering

Abstract

The invention relates to the technical field of bridge visual inspection, in particular to a concrete crack detection method for bridge engineering. The method comprises the following steps: firstly, extracting a suspected crack region from a bridge surface image; according to the long and narrow characteristics of the crack, screening out a key crack region from the suspected crack regions; comparing the key crack area with the skeleton fitting straight line, and determining the extension rule degree of the key crack area; analyzing the brightness change of two adjacent layers of edge lines in the multiple layers of edge lines in the key crack area, and determining the compactness of the key crack area; determining a crack defect credible index of the key crack area according to the compactness and the extension rule degree of the key crack area and other surrounding key crack areas, and adjusting a significance value of the key crack area obtained through a CA algorithm to obtain a corrected significance value; and screening out a real crack region from the key crack region according to the corrected significance value. According to the invention, the accuracy of crack authenticity identification is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of bridge visual inspection, and particularly to a method for detecting concrete cracks for bridge engineering. Background Art

[0002] Bridge crack detection can timely discover potential safety hazards, prevent the occurrence of safety accidents such as bridge collapse, and ensure the safety of pedestrians and vehicles. In addition, by monitoring bridge cracks, the fatigue condition, bearing capacity and stability of the bridge structure can be evaluated, providing a basis for maintenance. As one of the most common and serious diseases in bridge construction, cracks are an important indicator for judging the safety of the bridge structure. They will damage the integrity of the bridge structure, reduce the overall strength of the bridge, and are prone to safety accidents, which need to be discovered and solved in time. When using machine vision to detect cracks on the bridge surface, the change of the shadow area formed by stains on the bridge surface may be similar to the manifestation of cracks, interfering with the detection of cracks and increasing the difficulty of crack detection.

[0003] Currently, the CA saliency detection algorithm is usually used to detect cracks on the bridge surface. However, the CA saliency detection algorithm requires that the detected defect area should occur accidentally. Therefore, multi-scale analysis is needed to judge whether there is one around. However, cracks are continuous and do not meet the condition of accidental occurrence required by the CA algorithm. Therefore, when using the CA saliency detection algorithm to detect cracks on the bridge, the accuracy is relatively low. Summary of the Invention

[0004] In order to solve the technical problem of inaccurate crack detection results when using the CA saliency detection algorithm to detect cracks on the bridge surface, the purpose of the present invention is to provide a method for detecting concrete cracks for bridge engineering, and the specific technical solution adopted is as follows:

[0005] In a first aspect, an embodiment of the present invention provides a method for detecting concrete cracks for bridge engineering, and the method includes:

[0006] Obtain an image of the bridge surface of the bridge road, and extract a suspected crack area from the bridge surface image;

[0007] According to the long and narrow characteristics of cracks, analyze the area length and area width of the suspected crack area, and screen out the key crack area from the suspected crack area;

[0008] Perform skeleton fitting on the key crack area to obtain a corresponding skeleton fitting straight line; compare the key crack area with the skeleton fitting straight line to determine the degree of extension law of the key crack area;

[0009] Analyze the brightness and darkness changes between adjacent layers of the multi-layer edge lines in the key crack area to determine the tightness of the key crack area; determine the crack defect credibility index of the key crack area according to the tightness and the degree of extension law of the key crack area and other surrounding key crack areas.

[0010] Adjust the significance value of the key crack area obtained by the CA algorithm according to the crack defect credibility index to obtain the corrected significance value of the key crack area; screen out the real crack area from the key crack area according to the corrected significance value.

[0011] Further, the method of analyzing the regional length and regional width of the suspected crack area according to the long and narrow characteristics of the crack, and screening out the key crack area from the suspected crack area includes:

[0012] Analyze the width at different positions of the suspected crack area to determine the width stability feature; combine the width stability feature and the length of the skeleton line of the suspected crack area to determine the long and narrow feature of the suspected crack area; combine the width stability feature and the long and narrow feature to determine the crack defect degree of the suspected crack area; screen out the key crack area from the suspected crack area according to the crack defect degree.

[0013] Further, the method of analyzing the width at different positions of the suspected crack area to determine the width stability feature includes:

[0014] Calculate the average value of the widths at different positions in the suspected crack area as the width mean value.

[0015] Determine the width instability according to the difference between the widths at different positions in the suspected crack area and the width mean value.

[0016] Perform a negative correlation mapping on the width instability to obtain the width stability feature of the suspected crack area.

[0017] Further, the method of combining the width stability feature and the length of the skeleton line of the suspected crack area to determine the long and narrow feature of the suspected crack area includes:

[0018] Obtain the length of the skeleton line of the suspected crack area.

[0019] Calculate the aspect ratio of the length of the skeleton line to the width at each position in the suspected crack area to obtain the local long and narrow feature at each position in the suspected crack area.

[0020] Calculate the difference between the maximum local long and narrow feature and the minimum local long and narrow feature of the suspected crack area as the local long and narrow feature range.

[0021] The product of the negative correlation mapping value of the local narrow and long feature extreme difference and the mean value of the local narrow and long feature is used to determine the narrow and long feature of the suspected crack area.

[0022] Furthermore, the combining of the width stability feature and the narrow and long feature to determine the degree of crack defects in the suspected crack area includes:

[0023] The normalized value of the product of the width stable feature and the narrow and long feature is used as the crack defect degree of the suspected crack area.

[0024] Furthermore, the step of selecting a key crack region from the suspected crack region according to the crack defect degree includes:

[0025] The suspected crack areas with crack defect degree greater than the preset significance threshold are regarded as key crack areas.

[0026] Further, the comparing the key crack region with the skeleton fitting straight line to determine the extension regularity of the key crack region includes:

[0027] Calculate the variance of the shortest distance between different skeleton pixel points and the skeleton fitting straight line in the skeleton line of the key crack area as the skeleton lateral fluctuation value;

[0028] Taking any skeleton pixel point on the skeleton line of the key crack area as the target skeleton pixel point, the skeleton local tilt value is determined according to the angle value between the line segment formed by the target skeleton pixel point and the rear skeleton pixel point and the horizontal line; the sum of the skeleton local tilt values ​​of all skeleton pixel points on the skeleton line of the key crack area is calculated as the skeleton tilt value;

[0029] The product of the skeleton lateral fluctuation value and the skeleton inclination value is negatively correlated and normalized and mapped, and the resulting value after mapping is used as the extension regularity degree of the key crack area.

[0030] Furthermore, the analyzing the light and dark changes of two adjacent layers of edge lines in the multiple layers of edge lines in the key crack region to determine the tightness of the key crack region includes:

[0031] When the brightness of two adjacent edge lines in the multi-layer edge lines in the key crack area changes from dark to light from inside to outside, the adjustment coefficients corresponding to the two adjacent edge lines are set as the small threshold coefficients;

[0032] When two adjacent edge lines in the multi-layer edge lines in the critical crack area do not experience light-dark changes or the light-dark changes from light to dark from inside to outside, the adjustment coefficients corresponding to the two adjacent edge lines are set as the large threshold coefficients;

[0033] Using the adjustment coefficient as the weight, the gray value differences between adjacent two-layer edge lines among the multi-layer edge lines in the key crack area are weighted and summed to obtain the compactness of the key crack area.

[0034] Further, determining the crack defect credibility index of the key crack area according to the compactness and the degree of extension law of the key crack area and other surrounding key crack areas includes:

[0035] Calculating the sum of the absolute values of the differences in the compactness between the key crack area and other surrounding key crack areas as the surrounding compactness difference of the key crack area.

[0036] Taking the degree of extension law as the numerator and the sum of the surrounding compactness difference and a preset adjustment value as the denominator, and taking the normalized value of the obtained ratio as the crack defect credibility index of the key crack area.

[0037] Further, screening out the real crack area from the key crack areas according to the corrected significance value includes:

[0038] Taking the key crack area with the corrected significance value greater than the preset corrected significance threshold as the real crack area.

[0039] In a second aspect, a concrete crack detection system for bridge engineering is provided. The system includes the following modules:

[0040] An image preprocessing module for acquiring an image of the bridge surface of the bridge road and extracting a suspected crack area from the bridge surface image;

[0041] A morphology analysis module for analyzing the regional length and regional width of the suspected crack area according to the narrow and long characteristics of the crack, and screening out the key crack area from the suspected crack area;

[0042] An extension analysis module for performing skeleton fitting on the key crack area to obtain a corresponding skeleton fitting straight line; comparing the key crack area and the skeleton fitting straight line to determine the degree of extension law of the key crack area;

[0043] A credibility analysis module for analyzing the light and dark changes between adjacent two-layer edge lines among the multi-layer edge lines in the key crack area to determine the compactness of the key crack area; determining the crack defect credibility index of the key crack area according to the compactness and the degree of extension law of the key crack area and other surrounding key crack areas;

[0044] A crack determination module, configured to adjust the significance value of the key crack area obtained by the CA algorithm according to the crack defect credibility index, so as to obtain the corrected significance value of the key crack area; and screen out the real crack area from the key crack area according to the corrected significance value.

[0045] In a third aspect, an embodiment of the present invention provides an electronic device, including a memory and a processor. An executable code is stored in the memory. When the processor executes the executable code, the methods in all possible implementation embodiments of the first aspect are implemented.

[0046] In a fourth aspect, an embodiment of the present invention provides a computer program product, which includes: computer program code. When the computer program code runs on a computer, the computer is enabled to execute the method in the first aspect or any possible implementation manner of the first aspect.

[0047] In a fifth aspect, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed in a computer, the computer is enabled to execute the methods in all possible implementation embodiments of the first aspect.

[0048] The embodiments of the present invention at least have the following beneficial effects:

[0049] By analyzing the morphological characteristics of cracks, the present invention preliminarily screens out the key crack areas and reduces the interference of the noise-rough areas formed by concrete. Also, by analyzing the characteristics that the key crack areas are relatively long and narrow in shape and the width changes relatively stably, and there are differences between the key crack areas and the shadow areas formed by the noise-rough areas and stain shadow areas formed by concrete, the degree of extension law of the key crack areas is determined; then, by analyzing that the shadow areas formed by stains are usually formed when liquids flow through the surface of the concrete bridge, such as rainwater and oil flowing through the surface of the concrete bridge, and their distribution is often irregular and has no obvious directionality, while the cracks on the bridge surface usually have a relatively obvious crack extension direction due to the influence of the bridge stress structure, the compactness of the key crack areas is further determined. Then, by further analyzing the degree of extension law and compactness of the key crack areas, the crack defect credibility index of the key crack areas is obtained, and the final crack defect degree of the key crack areas is obtained, which maximally improves the accuracy of crack authenticity identification and reduces the interference of the shadow pseudo-cracks formed by stains. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0051] Figure 1 The method flowchart of a concrete crack detection method for bridge engineering provided by an embodiment of the present invention;

[0052] Figure 2 The schematic diagram of the bridge surface image obtained after grayscale processing provided by an embodiment of the present invention;

[0053] Figure 3 The method flowchart of the steps for obtaining the key crack area provided by an embodiment of the present invention;

[0054] Figure 4 The schematic diagram of each layer of edge lines of the key crack area provided by an embodiment of the present invention. Detailed implementation manners

[0055] In order to further elaborate on the technical means and effects adopted by the present invention to achieve the intended invention purpose, the following, in combination with the accompanying drawings and preferred embodiments, details the specific implementation manners, structures, features and effects of a concrete crack detection method for bridge engineering proposed according to the present invention.

[0056] In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures or characteristics in one or more embodiments can be combined in any suitable form.

[0057] Among them, in the description of the embodiments of the present invention, unless otherwise specified, " / " means "or". For example, A / B can represent A or B. The "and / or" in the text is only a description of the association relationship of the associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. In addition, in the description of the embodiments of the present invention, "a plurality" means two or more than two.

[0058] Hereinafter, the terms "first" and "second" are only used for descriptive purposes and cannot be understood as implying or suggesting relative importance or implicitly indicating the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of such features.

[0059] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the technical field to which this invention belongs.

[0060] The embodiments of the present invention will be described below with reference to the accompanying drawings. As can be known to those of ordinary skill in the art, with the development of technology and the emergence of new scenarios, the technical solutions provided by the embodiments of the present invention are equally applicable to similar technical problems.

[0061] The embodiments of the present invention provide a specific implementation method for a concrete crack detection method for bridge engineering, and this method is applicable to the crack detection scenario of bridges constructed of concrete.

[0062] The following specifically describes the specific solution of a concrete crack detection method for bridge engineering provided by the present invention with reference to the accompanying drawings.

[0063] Please refer to Figure 1 , which shows a flowchart of the steps of a concrete crack detection method for bridge engineering provided by an embodiment of the present invention. This method includes the following steps:

[0064] Step S100, obtain an image of the bridge surface of the bridge road, and extract a suspected crack area from the image of the bridge surface.

[0065] The surface of the bridge road is photographed by a drone equipped with an industrial camera to obtain an RGB image of the bridge surface. The RGB image is subjected to semantic segmentation to obtain an image of the bridge road. The image of the bridge road is grayed and Gaussian filtered to obtain an image of the bridge surface. Please refer to Figure 2 , Figure 2 which is a schematic diagram of the image of the bridge surface obtained after graying.

[0066] There are mainly cracks, rough noise areas of bridge concrete, and shadow areas formed by stains on the bridge surface image, and all three present the characteristic of darker color. Since the bridge surface image is usually large, directly segmenting the entire bridge surface image has a poor effect, so it is necessary to analyze in blocks.

[0067] The size of the bridge surface image is adjusted to 2100*1500 by bicubic interpolation method, and the bridge surface image is evenly divided according to a preset ratio to obtain a number of sub-images with a size of 300*300.

[0068] The color of the cracks on the bridge road is darker, and the suspected crack area can be obtained by threshold segmentation. Specifically, the Otsu threshold segmentation is performed on the sub-images, and the connected domain with a gray value of 0 and the number of pixel points greater than 20 in the sub-images is used as the suspected crack area. By extracting the suspected crack area from the bridge surface image, the purpose of excluding some rough noise areas is achieved.

[0069] Step S200: According to the narrow and long characteristics of the crack, analyze the regional length and regional width of the suspected crack area, and screen out the key crack area from the suspected crack area.

[0070] Analyze the suspected crack area through the morphological characteristics of the crack to obtain the crack defect degree of the suspected crack area, so as to screen out the key crack area with obvious crack characteristics.

[0071] The shape presented by the crack area is relatively narrow and long, with a relatively stable width change, which is different from the noise rough area formed by the concrete and the shadow area formed by the stain.

[0072] In some embodiments, by respectively analyzing the regional length and regional width of the suspected crack area, the key crack area is screened out from the suspected crack area. That is, the above-mentioned step S200 can be implemented through Figure 3 the steps shown as follows:

[0073] Step S210: Analyze the width at different positions in the suspected crack area to determine the width stability feature.

[0074] Obtain the skeleton line of the suspected crack area through the skeleton extraction algorithm.

[0075] Calculate the average value of the widths at different positions in the suspected crack area as the width mean value. Specifically: Obtain the points passing through the skeleton line, and the width distances where the straight lines perpendicular to the skeleton line intersect with the pixel points on both sides of the suspected crack area. Each point on the skeleton line corresponds to a width distance, which is also denoted as the width. Starting from any end of the skeleton line, arrange all the widths to obtain the crack morphology sequence.

[0076] Calculate the mean value of the width distances of all points on the skeleton line to obtain the width mean value.

[0077] Determine the width instability according to the difference between the widths at different positions in the suspected crack area and the width mean value. Specifically: Calculate the average value of the differences between the widths corresponding to each point on the skeleton line of the suspected crack area and the width mean value as the width instability. When the difference between the width corresponding to each point and the width mean value is larger, the corresponding width fluctuation will be larger, and the state presented by the width is more unstable. Perform a negative correlation mapping on the width instability to obtain the width stability feature of the suspected crack area. In the embodiments of the present invention, the negative correlation mapping is realized by taking the reciprocal of the width instability. In other embodiments, other methods of negative correlation mapping can also be selected by the implementer according to the actual situation. It should be noted that when taking the reciprocal of the width instability, a constant 1 is added to the denominator. The purpose of adding the constant 1 is to avoid the situation where the denominator is 0.

[0078] In some embodiments, the calculation formula for the width stability feature A of the suspected crack region is:

[0079]

[0080] where d i is the width of the i-th position in the crack shape sequence; is the average width; I is the number of elements in the crack shape sequence, that is, the number of points on the skeleton line of the suspected crack region; is the width stability feature of the suspected crack region.

[0081] where, the smaller the |d i - d|, the more stable the width change of the suspected crack region, and the more likely the corresponding suspected crack region is a crack.

[0082] Step S220: Determine the narrow and long feature of the suspected crack region by combining the width stability feature and the length of the skeleton line of the suspected crack region.

[0083] Obtain the length of the skeleton line of the suspected crack region. In the embodiments of the present invention, the method for obtaining the length of the skeleton line is as follows: First, perform skeleton fitting on the key crack region to obtain the corresponding skeleton fitting straight line, and use the length of this skeleton fitting straight line as the length of the skeleton line.

[0084] Calculate the aspect ratio of the length of the skeleton line to the width at each position in the suspected crack region to obtain the local narrow and long feature at each position in the suspected crack region. Specifically:

[0085] Calculate the difference between the maximum local narrow and long feature and the minimum local narrow and long feature of the suspected crack region as the range of the local narrow and long feature; Multiply the negative correlation mapping value of the range of the local narrow and long feature by the average value of the local narrow and long feature to determine the narrow and long feature of the suspected crack region.

[0086] In some embodiments, the calculation formula for the narrow and long feature C of the suspected crack region is:

[0087]

[0088] where B max is the maximum value of the local narrow and long feature of the suspected crack region, that is, the maximum local narrow and long feature; B min is the minimum value of the local narrow and long feature of the suspected crack region, that is, the minimum local narrow and long feature; B max - B min is the range of the local narrow and long feature;

[0089] where B max - B minIt reflects the variation range of the overall local narrow and long characteristics of the suspected crack area. The smaller the variation range, the narrower the suspected crack area. It reflects a reference value of the local narrow and long characteristics of the suspected crack area. The larger the reference value and the smaller the variation range, it indicates that the overall suspected crack area is narrower and longer.

[0090] Step S230: Combine the width stability feature and the narrow and long feature to determine the crack defect degree of the suspected crack area. According to the crack defect degree, screen out the key crack area from the suspected crack area.

[0091] Use the normalized value of the product of the width stability feature and the narrow and long feature as the crack defect degree of the suspected crack area.

[0092] In some embodiments, the calculation formula for the crack defect degree D is:

[0093] D = norm(A × C);

[0094] Wherein, A is the width stability feature of the suspected crack area; C is the narrow and long feature of the suspected crack area; norm is a linear normalization function.

[0095] Among them, the wider and more stable the width of the suspected crack area is, and at the same time, the narrower and longer it is, the more likely it is a crack; the suspected crack area with a larger corresponding crack defect degree is more likely to be a crack.

[0096] As an embodiment of the present invention, the crack defect degree of the suspected crack area can also be used as the significance value of the CA significance detection algorithm for determining the suspected crack area.

[0097] Regard the suspected crack area with a crack defect degree greater than the preset significance threshold as the key crack area. In the embodiment of the present invention, the value of the preset significance threshold is 0.7, and in other embodiments, it can be adjusted by the implementer according to the actual situation. Regard the suspected crack area with a significance value greater than the 0.7 threshold as the key crack area.

[0098] Step S300: Perform skeleton fitting on the key crack area to obtain the corresponding skeleton fitting line; compare the key crack area with the skeleton fitting line to determine the degree of extension law of the key crack area.

[0099] The CA significance detection algorithm requires that the detected defect area should appear accidentally. Therefore, it is necessary to perform multi-scale analysis to judge whether there is any around. However, cracks are continuous and do not meet the condition of accidental appearance required by the CA algorithm. Therefore, based on the extension law and tightness of the key crack area, the significance value result of the CA detection algorithm is weighted and adjusted, so that the CA algorithm can better fit the current application scenario.

[0100] The change of the shadow area formed by stains in the gray-scale image of the bridge surface may be similar to the manifestation of cracks, interfering with the detection of cracks, that is, both are the key crack areas obtained in the above steps. The shadow area formed by stains is usually caused by the flow of liquid over the concrete bridge surface, such as the flow of rainwater and oil stains over the concrete bridge surface, and its distribution is often irregular and has no obvious directionality. Due to the influence of the bridge stress structure, the cracks on the bridge surface usually have a relatively obvious crack extension direction as a whole. By analyzing the angular change of adjacent pixel points in the skeleton line of the key crack area and the closeness between the skeleton line and the fitted line, the degree of the extension law of the key crack area is obtained.

[0101] Analyze any key crack area, obtain the skeleton line of the key crack area through the skeleton extraction algorithm, and perform the least squares fitting on all the skeleton pixel points on the skeleton line to obtain the skeleton fitting line.

[0102] Calculate the variance of the shortest straight-line distance between different skeleton pixel points on the skeleton line of the key crack area and the skeleton fitting line as the skeleton lateral fluctuation value F;

[0103] Take any skeleton pixel point on the skeleton line of the key crack area as the target skeleton pixel point, and determine the local skeleton inclination degree value according to the included angle value between the line segment formed by the target skeleton pixel point and the rear skeleton pixel point and the horizontal line; calculate the sum value of the local skeleton inclination degree values of all the skeleton pixel points on the skeleton line of the key crack area as the skeleton inclination degree value.

[0104] In the embodiment of the present invention, the calculation method of the local skeleton inclination degree value is: calculate the included angle value between the line segment formed by the target skeleton pixel point and the first rear skeleton pixel point and the horizontal line as the first included angle value; calculate the included angle value between the line segment formed by the target skeleton pixel point and the second rear skeleton pixel point and the horizontal line as the second included angle value, and take the absolute value of the difference between the first included angle value and the second included angle value as the local skeleton inclination degree value of the target skeleton pixel point;

[0105] Perform negative correlation normalization mapping on the product value of the skeleton lateral fluctuation value and the skeleton inclination degree value, and the mapped result value is used as the degree of the extension law of the key crack area.

[0106] In some embodiments, the calculation formula of the degree G of the extension law of the key crack area is:

[0107]

[0108] where I is the number of skeleton pixel points on the skeleton line of the key crack area; E a-1,ais the minimum included angle value between the direction ray from the a-th skeleton pixel point to the (a + 1)-th skeleton pixel point on the skeleton line of the key crack area and the horizontal line, that is, the first included angle value of the a-th skeleton pixel point on the skeleton line of the key crack area; E a,a+2 is the minimum included angle value between the direction ray from the a-th skeleton pixel point to the (a + 2)-th skeleton pixel point on the skeleton line of the key crack area and the horizontal line, that is, the second included angle value of the a-th skeleton pixel point on the skeleton line of the key crack area; |E a,a+1 -E a,a+2 | is the local inclination degree value of the skeleton of the a-th skeleton pixel point on the skeleton line of the key crack area; F is the lateral fluctuation value of the skeleton; is the skeleton inclination degree value; exp is the exponential function with the natural constant as the base.

[0109] Among them, |E a,a+1 -E a,a+2 | reflects the change of the angle formed by three adjacent skeleton pixel points on the skeleton line of the key crack area. When |E a,a+1 -E a,a+2 | is smaller, the extension of the skeleton pixel points is more regular; F reflects the overall change regularity of the skeleton line of the key crack area. When F is smaller, the extension trend of the key crack area is better; the inverse relationship is realized through the model of exp(-x), where x is the model input. In the calculation formula of the extension regularity degree of the key crack area, is the model input x.

[0110] Step S400, analyze the brightness and darkness changes between adjacent two layers of edge lines in the multi-layer edge lines within the key crack area to determine the tightness of the key crack area; determine the crack defect credibility index of the key crack area according to the tightness and extension regularity degree of the key crack area and other surrounding key crack areas.

[0111] Although the shadow cracks formed by stains are similar to cracks in the segmented block images in terms of being narrow and long, in the grayscale image, the crack shadows formed by stains will have a certain degree of diffusion, which is reflected as poor tightness, while cracks have good gray-scale aggregation without diffusion or slight diffusion. At the same time, due to the good extensibility of cracks, in adjacent block images with similar surrounding trends, the tightness situations are similar. By analyzing the tightness of the key crack area and combining the extension regularity degree, the crack defect credibility index of the key crack area is obtained.

[0112] First, analyze the brightness and darkness changes between adjacent two layers of edge lines in the multi-layer edge lines within the key crack area to determine the tightness of the key crack area.

[0113] When the light and dark change from deep to shallow from the inside to the outside for two adjacent edge lines among the multi-layer edge lines in the key crack area, the adjustment coefficient corresponding to the two adjacent edge lines is set as the small threshold coefficient; in the embodiment of the present invention, the value of the small threshold coefficient is 0.1, and in other embodiments, the implementer adjusts this value according to the actual situation.

[0114] When there is no light and dark change or the light and dark change from shallow to deep from the inside to the outside for two adjacent edge lines among the multi-layer edge lines in the key crack area, the adjustment coefficient corresponding to the two adjacent edge lines is set as the large threshold coefficient; in the embodiment of the present invention, the value of the large threshold coefficient is 1, and in other embodiments, the implementer adjusts this value according to the actual situation.

[0115] Using the adjustment coefficient as the weight, the gray value differences of two adjacent edge lines among the multi-layer edge lines in the key crack area are weighted and summed to obtain the compactness of the key crack area.

[0116] More specifically: Obtain the gray mean value of each layer of edge line in the key crack area. Please refer to Figure 4 , Figure 4 which is a schematic diagram of each layer of edge line in the key crack area, only for understanding the embodiment of the present invention, Figure 3 which contains three layers of edge lines, the innermost layer is the first layer of edge line, and so on outwards.

[0117] In some embodiments, the calculation formula for the compactness J of the key crack area is:

[0118]

[0119] where H is the number of all layers of edges in the key crack area; α b,b+1 is the adjustment coefficient between the (b + 1)-th layer of edge line and the b-th layer of edge line in the key crack area; h b+1 is the gray mean value of the (b + 1)-th layer of edge line in the key crack area; h b is the gray mean value of the b-th layer of edge line in the key crack area.

[0120] where, |h b+1 -h b | reflects the gray change of two adjacent edge lines in the key crack area. When h b+1 -h b > 0, it indicates that there is diffusion between two adjacent layers and they are not compact, and the compactness should be smaller, which is adjusted by the adjustment coefficient; when h b+1 -h b ≤ 0, it indicates that there is no diffusion between two adjacent layers, and the compactness should be relatively larger. In the embodiment of the present invention, it remains unchanged, that is, the adjustment coefficient is set to 1.

[0121] Then, according to the compactness and the degree of extension law between the key crack area and other key crack areas around it, determine the crack defect credibility index of the key crack area.

[0122] Specifically: In the sub-block images around the sub-block image where the key crack area is located, obtain the key crack areas connected to the key crack area. In the embodiment of the present invention, a key crack area with a distance less than a preset distance threshold from the key crack area can be set as other key crack areas around it. Among them, the value of the preset distance threshold is 20, and in other embodiments, it can be set by the implementer according to the actual situation. It should be noted that the distance between the key crack areas here refers to the number of pixel points corresponding to the shortest distance between two key crack areas.

[0123] Calculate the sum of the absolute values of the differences in compactness between the key crack area and other key crack areas around it as the surrounding compactness difference of the key crack area;

[0124] Take the degree of extension law as the numerator and the sum of the surrounding compactness difference and the preset adjustment value as the denominator, and take the normalized value of the obtained ratio as the crack defect credibility index of the key crack area.

[0125] In some embodiments, taking the example that there are two other key crack areas around the key crack area, the calculation formula for the crack defect credibility index L of the key crack area is:

[0126]

[0127] Among them, J is the compactness of the key crack area; J1 is the compactness of the key crack area in one of the other key crack areas around it; J2 is the compactness of the key crack area in the other key crack area around it; G is the degree of extension law of the key crack area; tanh() is the hyperbolic tangent function used for normalization.

[0128] Among them, |J - J1| + |J - J2| reflects the compactness difference between the current key crack area and the connected key crack areas. The smaller the difference, the more likely the current key crack area is a crack. At the same time, the greater the degree of extension law of the key crack area, the more likely it is a crack, and the more credible the crack defect is, and the greater the credibility index.

[0129] Step S500, according to the crack defect credibility index, adjust the significance value of the key crack area obtained by the CA algorithm to obtain the corrected significance value of the key crack area; according to the corrected significance value, screen out the real crack areas from the key crack areas.

[0130] In one embodiment of the present invention, the crack defect degree of the key crack area is corrected by the crack defect credibility index to obtain the final crack defect degree of the key crack area. According to the final crack defect degree, the true crack area is screened out from the key crack area. The method for obtaining the final crack defect degree is: the normalized value of the product of the crack defect credibility index and the crack defect degree of the key crack area. The key crack area with a larger final crack defect degree is also likely to be a real crack.

[0131] Set a preset crack recognition threshold for crack authenticity discrimination When the crack defect degree of the key crack area is greater than or equal to the preset crack recognition threshold it is determined that the key crack area is a real crack area. When the crack defect degree of the key crack area is less than the preset crack recognition threshold it is determined that the key crack area in the current sub-block image is a false crack; all sub-block images are discriminated to obtain all cracks in the bridge surface image. The preset crack recognition threshold can be optimized through a large number of statistical tests to maximize the accuracy of crack authenticity recognition. In this embodiment, the preset crack recognition threshold

[0132] In another embodiment of the present invention, the significance value of the key crack area is corrected by the crack defect credibility index to obtain the corrected significance value of the key crack area. According to the corrected significance value, the true crack area is screened out from the key crack area. The method for obtaining the corrected significance value is: the normalized value of the product of the crack defect credibility index and the significance value of the key crack area obtained by the CA algorithm. The key crack area with a larger final corrected significance value is also likely to be a real crack.

[0133] Set a preset corrected significance threshold for crack authenticity discrimination. When the corrected significance value of the key crack area is greater than or equal to the preset corrected significance threshold, it is determined that the key crack area is a real crack area. When the corrected significance value of the key crack area is less than the preset corrected significance threshold, it is determined that the key crack area in the current sub-block image is a false crack. In the embodiment of the present invention, the value of the preset corrected significance threshold is 0.8. In other embodiments, the implementer can adjust this value according to the actual situation.

[0134] An embodiment of the present invention provides a concrete crack detection system for bridge engineering. The system includes:

[0135] An image preprocessing module, configured to obtain a bridge surface image of a bridge road and extract a suspected crack area from the bridge surface image;

[0136] A morphological analysis module, configured to analyze the regional length and regional width of a suspected crack area according to the long and narrow characteristics of the crack, and screen out a key crack area from the suspected crack area;

[0137] An extension analysis module, configured to perform skeleton fitting on the key crack area to obtain a corresponding skeleton fitting line; compare the key crack area with the skeleton fitting line to determine the degree of extension law of the key crack area;

[0138] A credibility analysis module, configured to analyze the brightness change between adjacent two layers of edge lines among multiple layers of edge lines in the key crack area to determine the tightness of the key crack area; determine a crack defect credibility index of the key crack area according to the tightness and the degree of extension law of the key crack area and other surrounding key crack areas;

[0139] A crack determination module, configured to adjust the significance value of the key crack area obtained by the CA algorithm according to the crack defect credibility index to obtain a corrected significance value of the key crack area; screen out a real crack area from the key crack area according to the corrected significance value.

[0140] Optionally, the transmission medium may be a wired link, such as but not limited to, coaxial cable, optical fiber, digital subscriber line, etc., or a wireless link, such as but not limited to, Wireless Fidelity (WIFI), Bluetooth, mobile device network, etc.

[0141] It should be noted that: for the device provided in the above embodiment, only the above division of each functional module is used for illustration. In actual application, the above functions may be allocated to different functional modules according to needs, that is, the internal structure of the computer device is divided into different functional modules to complete all or part of the functions described above.

[0142] A schematic structural diagram of a computer device provided by an embodiment of the present invention. Exemplarily, the computer device includes: a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, the computer device can execute any one of the concrete crack detection methods for bridge engineering introduced above.

[0143] In addition, an embodiment of the present invention also protects a device, which may include a memory and a processor. Among them, an executable program code is stored in the memory, and the processor is configured to call and execute the executable program code to execute a concrete crack detection method for bridge engineering provided by an embodiment of the present invention.

[0144] Embodiments of the present invention can divide the device into functional modules according to the above method examples. For example, each functional module can be corresponding, or two or more functions can be integrated into one processing module. The above integrated module can be implemented in the form of hardware. It should be noted that the division of modules in this embodiment is illustrative, only a logical function division, and there can be other division methods in actual implementation.

[0145] In the case of dividing each module according to each function, the device can also include a signal uploading module, a determination module, an adjustment module, etc. It should be noted that all relevant contents of each step involved in the above method embodiment can be cited in the function description of the corresponding functional module, and will not be elaborated here.

[0146] It should be understood that the device provided by the embodiments of the present invention is used to execute the above concrete crack detection method for bridge engineering, so the same effects as the above implementation method can be achieved.

[0147] In the case of adopting integrated units, the device can include a processing module and a storage module. Among them, when the device is applied to a device, the processing module can be used to control and manage the actions of the device. The storage module can be used to support the device to execute mutual program codes, etc. Among them, the processing module can be a processor or a controller, which can implement or execute various exemplary logical blocks, modules, and circuits described in combination with the disclosure of the present invention. The processor can also be a combination that realizes computing functions, such as including a combination of one or more microprocessors, a combination of digital signal processing (DSP) and a microprocessor, etc. The storage module can be a memory.

[0148] In addition, the device provided by the embodiments of the present invention can specifically be a chip, a component, or a module. The chip can include a connected processor and a memory; among them, the memory is used to store instructions, and when the processor calls and executes the instructions, the chip can execute the above concrete crack detection method for bridge engineering provided by the above embodiments.

[0149] Embodiments of the present invention also provide a computer-readable storage medium, in which computer program code is stored. When the computer program code runs on a computer, the computer is enabled to execute the above relevant method steps to implement the above concrete crack detection method for bridge engineering provided by the above embodiments.

[0150] Embodiments of the present invention also provide a computer program product. When the computer program product runs on a computer, the computer is enabled to execute the above relevant steps to implement the above concrete crack detection method for bridge engineering provided by the above embodiments.

[0151] Among them, the device, computer-readable storage medium, computer program product or chip provided by the embodiments of the present invention are all used to execute the corresponding methods provided above. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding methods provided above, and will not be elaborated here. Through the description of the above embodiments, those skilled in the art can understand that for the convenience and conciseness of description, only the above division of each functional module is used as an example. In actual applications, the above functions can be allocated to different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In the embodiments provided by the present invention, it should be understood that the disclosed device and method can be implemented in other ways.

[0152] The device embodiments described above are merely illustrative. For example, the division of modules or units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection between each other can be through some interfaces. The indirect coupling or communication connection of the device or unit can be in electrical, mechanical or other forms.

[0153] It should also be noted that in this article, the terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or terminal device. Without further limitation, an element defined by the statement "including a..." does not exclude the existence of additional identical elements in the process, method, article or terminal device including the said element.

[0154] It should be noted that: the above sequence of the embodiments of the present invention is only for description and does not represent the superiority or inferiority of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0155] Each embodiment in this specification is described in a progressive manner. The same or similar parts between each embodiment can be referred to each other, and the key point of each embodiment is to illustrate the differences from other embodiments.

[0156] The above content is only a specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered within the protection scope of the present invention.

Claims

1. A concrete crack detection method for bridge engineering, characterized in that: The method comprises the following steps: Acquire a bridge surface image of a bridge road, and extract suspected crack areas from the bridge surface image; According to the narrow and long characteristics of the cracks, the length and width of the suspected crack area are analyzed, and the key crack area is screened out from the suspected crack area; Performing skeleton fitting on the key crack region to obtain a corresponding skeleton fitting straight line; comparing the key crack region with the skeleton fitting straight line to determine the extension regularity of the key crack region; Analyze the light and dark changes of two adjacent edge lines in the multi-layer edge lines in the key crack area to determine the compactness of the key crack area; determine the crack defect credibility index of the key crack area according to the compactness and extension regularity of the key crack area and other surrounding key crack areas; According to the crack defect credibility index, the significance value of the key crack area obtained by the CA algorithm is adjusted to obtain a modified significance value of the key crack area; according to the modified significance value, the real crack area is screened out from the key crack area.

2. The concrete crack detection method for bridge engineering according to claim 1, characterized in that: The method of analyzing the length and width of the suspected crack region according to the narrow and long characteristics of the crack, and screening out the key crack region from the suspected crack region, includes: Analyze the widths at different positions of the suspected crack area to determine the width stability feature; determine the narrow and long feature of the suspected crack area by combining the width stability feature and the length of the skeleton line of the suspected crack area; determine the degree of crack defects in the suspected crack area by combining the width stability feature and the narrow and long feature; and screen out key crack areas from the suspected crack area based on the crack defect degree.

3. The concrete crack detection method for bridge engineering according to claim 2, characterized in that: The analyzing the widths of the suspected crack region at different positions to determine the width stability feature includes: Calculate the average value of the widths at different positions in the suspected crack area as the mean width; Determine the width instability based on the difference between the width at different locations in the suspected crack area and the width mean; The width instability is negatively correlated and mapped to obtain the width stability characteristics of the suspected crack area.

4. The concrete crack detection method for bridge engineering according to claim 2, characterized in that: The method of combining the width stability feature and the length of the skeleton line of the suspected crack area to determine the narrow and long feature of the suspected crack area includes: Obtain the length of the skeleton line of the suspected crack area; Calculate the aspect ratio of the length of the skeleton line to the width at each position in the suspected crack area to obtain the local narrow and long feature at each position in the suspected crack area; Calculate the difference between the maximum local narrow and long feature and the minimum local narrow and long feature in the suspected crack area as the local narrow and long feature range; The product of the negative correlation mapping value of the local narrow and long feature extreme difference and the mean value of the local narrow and long feature is used to determine the narrow and long feature of the suspected crack area.

5. The concrete crack detection method for bridge engineering according to claim 2, characterized in that: The combining of the width stability feature and the narrow and long feature to determine the degree of crack defects in the suspected crack area includes: The normalized value of the product of the width stable feature and the narrow and long feature is used as the crack defect degree of the suspected crack area.

6. The concrete crack detection method for bridge engineering according to claim 2, characterized in that: The step of selecting a key crack region from the suspected crack region according to the crack defect degree includes: The suspected crack areas with crack defect degree greater than the preset significance threshold are regarded as key crack areas.

7. The concrete crack detection method for bridge engineering according to claim 1, characterized in that: The comparing the key crack region with the skeleton fitting straight line to determine the extension regularity of the key crack region includes: Calculate the variance of the shortest distance between different skeleton pixel points and the skeleton fitting straight line in the skeleton line of the key crack area as the skeleton lateral fluctuation value; Taking any skeleton pixel point on the skeleton line of the key crack area as the target skeleton pixel point, the skeleton local tilt value is determined according to the angle value between the line segment formed by the target skeleton pixel point and the rear skeleton pixel point and the horizontal line; the sum of the skeleton local tilt values ​​of all skeleton pixel points on the skeleton line of the key crack area is calculated as the skeleton tilt value; The product of the skeleton lateral fluctuation value and the skeleton inclination value is negatively correlated and normalized and mapped, and the resulting value after mapping is used as the extension regularity degree of the key crack area.

8. The concrete crack detection method for bridge engineering according to claim 1, characterized in that: The analyzing the light and dark changes of two adjacent layers of edge lines in the multiple layers of edge lines in the key crack area to determine the tightness of the key crack area includes: When the brightness of two adjacent edge lines in the multi-layer edge lines in the key crack area changes from dark to light from inside to outside, the adjustment coefficients corresponding to the two adjacent edge lines are set as the small threshold coefficients; When two adjacent edge lines in the multi-layer edge lines in the critical crack area do not experience light-dark changes or the light-dark changes from light to dark from inside to outside, the adjustment coefficients corresponding to the two adjacent edge lines are set as the large threshold coefficients; The adjustment coefficient is used as the weight to perform weighted summation on the grayscale value differences of two adjacent layers of edge lines in the multi-layer edge lines within the key crack area to obtain the compactness of the key crack area.

9. The concrete crack detection method for bridge engineering according to claim 1, characterized in that: Determining the reliable index of crack defects in the key crack area based on the compactness and extension regularity of the key crack area and other surrounding key crack areas includes: Calculate the sum of the absolute values ​​of the differences between the tightness of the key crack area and other surrounding key crack areas as the surrounding tightness difference of the key crack area; The degree of extension regularity is used as a numerator, the sum of the surrounding tightness difference and the preset adjustment value is used as a denominator, and the normalized value of the obtained ratio is used as a reliable indicator of crack defects in the key crack area.

10. The concrete crack detection method for bridge engineering according to claim 1, characterized in that: The method of screening out the real crack area from the key crack area according to the modified significance value includes: The key crack area whose corrected significance value is greater than the preset corrected significance threshold is regarded as the real crack area.

Images