A method for detecting a concrete crack for bridge engineering

Abstract

The present application relates to bridge visual detection technical field, specifically to a kind of concrete crack detection method for bridge engineering.The method first extracts suspected crack area from bridge surface image;According to the long and narrow feature of crack, key crack area is screened from suspected crack area;The extension regularity degree of key crack area is determined by comparing key crack area and skeleton fitting straight line;The tightness of key crack area is determined by analyzing the light and dark change of adjacent two layers of edge lines in the multilayer edge line in key crack area;According to the tightness, extension regularity degree of key crack area and other key crack areas around, the crack defect credibility index of key crack area is determined, the saliency value of key crack area obtained by CA algorithm is adjusted, and the corrected saliency value is obtained;The real crack area is screened from key crack area according to corrected saliency value.The present application improves the accuracy of crack true and false identification.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of bridge visual detection, and particularly relates to a concrete crack detection method for bridge engineering. BACKGROUND

[0002] Bridge crack detection can timely find potential safety hazards and prevent bridge collapse and other safety accidents, thereby ensuring the safety of pedestrians and vehicles. In addition, through monitoring of bridge cracks, the fatigue condition, bearing capacity and stability of the bridge structure can be evaluated to provide a basis for maintenance. As one of the most common and most serious diseases in bridge construction, cracks are an important indicator for judging whether the bridge structure is safe, can damage the integrity of the bridge structure, reduce the overall strength of the bridge, and easily cause safety accidents, which need to be timely discovered and solved. When cracks on the bridge surface are detected by using machine vision, the shadow area change caused by stains on the bridge surface may be similar to the crack performance, which interferes with the crack detection and increases the difficulty of crack detection.

[0003] The existing crack detection on the bridge surface usually uses the CA saliency detection algorithm, but the CA saliency detection algorithm requires that the defect area to be detected should be accidental, and therefore a multi-scale analysis is required to determine whether there is a surrounding, but the crack is continuous and does not meet the accidental occurrence condition required by the CA algorithm, so the accuracy of the crack detection on the bridge by using the CA saliency detection algorithm is low. SUMMARY

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

[0005] In the first aspect, the present application provides a concrete crack detection method for bridge engineering, which comprises the following steps:

[0006] Obtaining a bridge surface image of a bridge road, and extracting a suspected crack area from the bridge surface image;

[0007] According to the long and narrow characteristics of the crack, analyzing the area length and the area width of the suspected crack area, and screening a key crack area from the suspected crack area;

[0008] Skeleton fitting is performed on the key crack area to obtain a corresponding skeleton fitting straight line; the key crack area and the skeleton fitting straight line are compared to determine the extension regularity degree of the key crack area;

[0009] analyzing the light and dark changes of two adjacent edge lines of multiple layers in the key crack region to determine the compactness of the key crack region; determining a crack defect credibility index of the key crack region according to the compactness and the extension regularity degree of the key crack region and other key crack regions around the key crack region;

[0010] According to the crack defect credibility index, the saliency value of the key crack region obtained by the CA algorithm is adjusted to obtain a modified saliency value of the key crack region; and a real crack region is selected from the key crack region according to the modified saliency value.

[0011] Further, the key crack region is selected from the suspected crack region according to the length and width of the suspected crack region.

[0012] The width stability feature of the suspected crack region is determined by analyzing the width of different positions of the suspected crack region; the length of the skeleton line of the suspected crack region is combined with the width stability feature to determine the length and width of the suspected crack region; the crack defect degree of the suspected crack region is determined according to the width stability feature and the length and width of the suspected crack region; and the key crack region is selected from the suspected crack region according to the crack defect degree.

[0013] Further, the width stability feature of the suspected crack region is determined by analyzing the width of different positions of the suspected crack region.

[0014] The average value of the width of different positions of the suspected crack region is calculated as the width average value;

[0015] The width instability is determined according to the difference between the width of different positions of the suspected crack region and the width average value.

[0016] The width instability is negatively correlated to obtain the width stability feature of the suspected crack region.

[0017] Further, the length and width of the suspected crack region are determined by combining the width stability feature and the length of the skeleton line of the suspected crack region.

[0018] The length of the skeleton line of the suspected crack region is obtained;

[0019] The length-width ratio of the length of the skeleton line and the width of each position in the suspected crack region is calculated to obtain the local length and width of each position in the suspected crack region;

[0020] The difference between the maximum local length and width and the minimum local length and width of the suspected crack region is calculated as the local length and width difference;

[0021] The product of the negative correlation mapping value of the local narrow feature extreme difference and the mean value of the local narrow feature determines the narrow feature of the suspected crack region.

[0022] Further, the combination of the width stable feature and the narrow feature determines the crack defect degree of the suspected crack region, comprising:

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

[0024] Further, the crack defect degree is used to screen out a key crack region from the suspected crack region, comprising:

[0025] The suspected crack region with a crack defect degree greater than a preset significant threshold is taken as the key crack region.

[0026] Further, the comparison of the key crack region and the skeleton fitting straight line determines the extension regularity degree of the key crack region, comprising:

[0027] The variance of the straight line shortest distance between different skeleton pixel points in the skeleton line of the key crack region and the skeleton fitting straight line is taken as the skeleton transverse fluctuation value;

[0028] Taking any skeleton pixel point on the skeleton line of the key crack region as a target skeleton pixel point, the skeleton local inclination degree value is determined according to the included angle value between the line segment composed of the target skeleton pixel point and the rear skeleton pixel point and the horizontal line; the sum value of the skeleton local inclination degree values of all skeleton pixel points on the skeleton line of the key crack region is taken as the skeleton inclination degree value;

[0029] The product value of the skeleton transverse fluctuation value and the skeleton inclination degree value is negatively correlated and normalized, and the mapped result value is taken as the extension regularity degree of the key crack region.

[0030] Further, the analysis of the light and dark changes of adjacent two layers of edge lines in the multi-layer edge lines in the key crack region determines the tightness of the key crack region, comprising:

[0031] When the light and dark changes of adjacent two layers of edge lines in the multi-layer edge lines in the key crack region change from deep to shallow from inside to outside, the adjustment coefficient corresponding to the adjacent two layers of edge lines is set as a small threshold coefficient;

[0032] When the light and dark changes of adjacent two layers of edge lines in the multi-layer edge lines in the key crack region do not occur or change from shallow to deep from inside to outside, the adjustment coefficient corresponding to the adjacent two layers of edge lines is set as a large threshold coefficient;

[0033] The gray value difference between two adjacent edge lines in the multi-layer edge lines in the key crack region is weighted and summed by using the adjustment coefficient as the weight, to obtain the compactness of the key crack region.

[0034] Further, the crack defect credibility index of the key crack region is determined according to the compactness and the extension regularity degree of the key crack region and other key crack regions around the key crack region, and the crack defect credibility index of the key crack region is determined.

[0035] The sum of absolute values of the difference between the compactness of the key crack region and the compactness of other key crack regions around the key crack region is calculated as the surrounding compactness difference of the key crack region.

[0036] The ratio of the extension regularity degree to the sum of the surrounding compactness difference and a preset adjustment value is calculated, and the normalized value of the obtained ratio is taken as the crack defect credibility index of the key crack region.

[0037] Further, the real crack region is screened from the key crack region according to the modified saliency value, and the real crack region is screened from the key crack region according to the modified saliency value.

[0038] The key crack region with the modified saliency value greater than a preset modified saliency threshold value is taken as the real crack region.

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

[0040] An image preprocessing module is configured to acquire a bridge surface image of a bridge road and extract a suspected crack region from the bridge surface image.

[0041] A shape analysis module is configured to analyze the region length and the region width of the suspected crack region according to the narrow and long characteristics of the crack, and screen a key crack region from the suspected crack region.

[0042] An extension analysis module is configured to perform skeleton fitting on the key crack region to obtain a corresponding skeleton fitting straight line, compare the key crack region with the skeleton fitting straight line, and determine the extension regularity degree of the key crack region.

[0043] A credibility analysis module is configured to analyze the light and dark changes between two adjacent edge lines in the multi-layer edge lines in the key crack region, determine the compactness of the key crack region, and determine the crack defect credibility index of the key crack region according to the compactness and the extension regularity degree of the key crack region and other key crack regions around the key crack region.

[0044] The crack determination module is used to adjust the significance value of the key crack region obtained by the CA algorithm according to the crack defect confidence index to obtain the corrected significance value of the key crack region; and to filter out the real crack region from the key crack region according to the corrected significance value.

[0045] Thirdly, embodiments of the present invention provide an electronic device, including a memory and a processor, wherein the memory stores executable code, and when the processor executes the executable code, it implements the various possible implementations of the first aspect.

[0046] Fourthly, embodiments of the present invention provide a computer program product comprising: computer program code, which, when executed on a computer, causes the computer to perform the method described in the first aspect or any possible implementation thereof.

[0047] Fifthly, embodiments of the present invention provide a computer-readable storage medium having a computer program stored thereon, which, when executed in a computer, causes the computer to perform the various possible implementations of the first aspect.

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

[0049] This invention analyzes the morphological characteristics of cracks to initially screen key crack areas, reducing interference from noisy, rough areas formed by concrete. Further analysis reveals that the key crack areas exhibit a relatively long and narrow shape with stable width variations, differing from the shadow areas of noisy, rough areas and stain-induced shadow areas, thus determining the extension pattern of the key crack areas. Further analysis shows that stain-induced shadow areas are typically formed by liquid flows over the concrete bridge surface, such as rainwater and oil, and their distribution is often irregular and lacks clear directionality. Cracks on the bridge surface, due to the stress structure, usually have a relatively clear direction of extension, thus determining the density of the key crack areas. Further analysis of the extension pattern and density of the key crack areas yields a reliable index of crack defects, ultimately determining the final crack defect level, maximizing the accuracy of crack authenticity identification and reducing interference from false cracks caused by stain shadows. Attached Figure Description

[0050] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, and the advantages thereof, below will briefly introduce the drawings needed in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0051] Figure 1 A method flow chart of a concrete crack detection method for bridge engineering provided by an embodiment of the present application;

[0052] Figure 2 A schematic diagram of a bridge surface image obtained after graying provided by an embodiment of the present application;

[0053] Figure 3 A method flow chart of a key crack area acquisition step provided by an embodiment of the present application;

[0054] Figure 4 A schematic diagram of an edge line of each layer of a key crack area provided by an embodiment of the present application. DETAILED DESCRIPTION

[0055] In order to further illustrate the technical means and effects taken by the present application to achieve the predetermined purpose, the specific implementation, structure, features and effects of a concrete crack detection method for bridge engineering according to the present application are described in detail below in combination with the drawings and preferred embodiments.

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

[0057] In the description of the embodiments of the present application, unless otherwise specified, " / " represents the meaning of or, for example, A / B can represent A or B: "and / or" in the text only describes the association relationship of the associated objects, which means that there can be three relationships, for example, A and / or B, which means that there are three cases of A alone, A and B together, and B alone. In addition, in the description of the embodiments of the present application, "multiple" means two or more than two.

[0058] Hereinafter, the terms "first" and "second" are only used for description purposes, and cannot be understood as implying or suggesting relative importance or implicitly indicating the number of indicated technical features. Therefore, the features defined with "first" and "second" can explicitly or implicitly include one or more 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 art to which this application belongs.

[0060] The embodiments of the present application are described below in conjunction with the accompanying drawings. It is obvious to those skilled in the art that, with the development of technology and the emergence of new scenarios, the technical solutions provided by the embodiments of the present application are also applicable to similar technical problems.

[0061] The embodiments of the present application provide a specific implementation method of a concrete crack detection method for bridge engineering.

[0062] The specific scheme of the concrete crack detection method for bridge engineering provided by the present application is described below in conjunction with the accompanying drawings.

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

[0064] Step S100, obtaining a bridge surface image of a bridge road, and extracting a suspected crack area from the bridge surface image.

[0065] The bridge road surface is photographed by a UAV equipped with an industrial camera to obtain an RGB image of the bridge surface. The RGB image is subjected to semantic segmentation to obtain a bridge road image. The bridge road image is subjected to grayscale and Gaussian filtering processing to obtain a bridge surface image. Please refer to Figure 2 , Figure 2 A schematic view of the bridge surface image obtained after grayscale processing.

[0066] The bridge surface image mainly includes crack, rough noise area of bridge concrete, and shadow area formed by stains, all of which have the feature of dark color. Since the bridge surface image is usually large, direct segmentation of the entire bridge surface image has poor effect, so block analysis is needed.

[0067] The size of the bridge surface image is adjusted to 2100*1500 by using bicubic interpolation. The bridge surface image is equally divided according to a preset ratio to obtain a plurality of block images with a size of 300*300.

[0068] The color of the crack of the bridge road appears dark, and the suspected crack area can be obtained by threshold segmentation. Specifically, the block image is subjected to Otsu threshold segmentation. The connected domain with a gray value of 0 and a pixel point number greater than 20 in the block image is regarded as the suspected crack area. By extracting the suspected crack area from the bridge surface image, the purpose of excluding part of the rough noise area is achieved.

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

[0070] By analyzing the suspected crack area through the morphological characteristics of the crack, the crack defect degree of the suspected crack area is obtained, so as to screen out the key crack area with obvious crack characteristics.

[0071] The crack area presents a long and narrow shape, and the width changes relatively stably, which is different from the noise rough area formed by the concrete and the shadow area formed by the stain.

[0072] In some embodiments, the key crack area is screened out from the suspected crack area by analyzing the area length and the area width of the suspected crack area, that is, the above step S200 can be realized by Figure 3 the steps shown in the figure:

[0073] Step S210, analyze the width of different positions of the suspected crack area to determine the width stability feature.

[0074] The skeleton line of the suspected crack area is obtained through the skeleton extraction algorithm.

[0075] The average value of the width of different positions in the suspected crack area is calculated as the width average value, specifically: the width distance of the straight line perpendicular to the skeleton line and the two side edge pixel points of the suspected crack area is obtained, and each point on the skeleton line corresponds to a width distance, also recorded as the width. Starting from any end of the skeleton line, arrange all the widths to obtain the crack morphology sequence.

[0076] The average value of the width distance of all points on the skeleton line is calculated to obtain the width average value.

[0077] According to the difference between the width of different positions in the suspected crack area and the width average value, the width instability is determined, specifically: the average value of the difference between the width corresponding to each point on the skeleton line of the suspected crack area and the width average value is calculated as the width instability. When the difference between the width corresponding to each point and the width average value is greater, the fluctuation of the corresponding width will be greater, and the state of the width is more unstable. The width stability feature of the suspected crack area is obtained by negatively correlating the width instability. In the embodiment of the application, the reciprocal of the width instability is calculated to realize the negative correlation mapping, and in other embodiments, the implementer can select other methods of negative correlation mapping according to the actual situation. It should be noted that when the reciprocal of the width instability is calculated, a constant 1 is added to the denominator, and the purpose of adding the constant 1 is to avoid the case that the denominator is 0.

[0078] In some embodiments, the width stability feature A of the suspected crack region is calculated as follows:

[0079]

[0080] wherein d i is the i-th width in the crack morphology sequence; is the mean width; and I is the number of elements in the crack morphology sequence, i.e., the number of points on the skeleton line of the suspected crack region; is the width stability feature of the suspected crack region.

[0081] wherein |d i The smaller |d max is, the more stable the width of the suspected crack region is, and the more likely the corresponding suspected crack region is a crack.

[0082] Step S220, in combination with the width stability feature and the length of the skeleton line of the suspected crack region, the elongation feature of the suspected crack region is determined.

[0083] The length of the skeleton line of the suspected crack region is obtained. In the embodiments of the present application, the length of the skeleton line is obtained by first performing skeleton fitting on the key crack region to obtain a corresponding skeleton fitting straight line, and taking the length of the skeleton fitting straight line as the length of the skeleton line.

[0084] The length-width ratio of the length of the skeleton line and the width at each position in the suspected crack region is calculated to obtain the local elongation feature of each position in the suspected crack region, specifically:

[0085] The difference between the maximum local elongation feature and the minimum local elongation feature of the suspected crack region is calculated as the local elongation feature range; and the product of the negative correlation mapping value of the local elongation feature range and the mean value of the local elongation feature is determined as the elongation feature of the suspected crack region.

[0086] In some embodiments, the elongation feature C of the suspected crack region is calculated as follows:

[0087]

[0088] wherein B max is the maximum value of the local elongation feature of the suspected crack region, i.e., the maximum local elongation feature; B min is the minimum value of the local elongation feature of the suspected crack region, i.e., the minimum local elongation feature; B max -B min is the local elongation feature range;

[0089] wherein B max -B minReflects the change range of the overall local narrow feature of the suspected crack area, and the smaller the change range, the narrower the suspected crack area. Reflects a reference value of the local narrow feature of the suspected crack area, and the greater the reference value, the smaller the change range, indicating that the overall suspected crack area is longer.

[0090] Step S230, in combination with the width stability feature and the narrow feature, 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] The normalized value of the product of the width stability feature and the narrow feature is taken as the crack defect degree of the suspected crack area.

[0092] In some embodiments, the calculation formula of 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 feature of the suspected crack area; norm is a linear normalization function.

[0095] Wherein, the more stable the width of the suspected crack area is, the longer it is, and the more likely it is to be a crack; the suspected crack area with the greater crack defect degree is more likely to be a crack.

[0096] As an embodiment of the present application, the crack defect degree of the suspected crack area can also be used as the CA saliency detection algorithm to determine the saliency value of the suspected crack area.

[0097] The suspected crack area with a crack defect degree greater than a preset saliency threshold is taken as a key crack area. In the embodiment of the present application, the value of the preset saliency threshold is 0.7, which can be adjusted by the implementer according to the actual situation in other embodiments. The suspected crack area with a saliency value greater than the threshold of 0.7 is taken as a key crack area.

[0098] Step S300, skeleton fitting is performed on the key crack area to obtain a corresponding skeleton fitting straight line; the key crack area and the skeleton fitting straight line are compared to determine the extension regularity degree of the key crack area.

[0099] The CA saliency detection algorithm requires that the detected defect area should be accidental, so multi-scale analysis is required to determine whether there is a surrounding, but the crack is continuous and does not meet the accidental condition required by the CA algorithm, so the saliency value result of the CA detection algorithm is weighted and adjusted based on the extension regularity and tightness of the key crack area, so that the CA algorithm can better fit the current application scenario.

[0100] The shadow area change of the stain formed in the gray image of the bridge surface can be similar to the crack performance, which interferes with the detection of the crack, that is, the key crack area obtained in the above steps. The shadow area of the stain is usually formed due to the flow of liquid such as rainwater and oil stain on the concrete bridge surface, which is often irregular and has no obvious direction. The overall crack of the bridge surface usually has a more obvious crack extension direction due to the influence of the stress structure of the bridge. The extension regularity degree of the key crack area is obtained by analyzing the angle change of adjacent pixel points in the skeleton line of the key crack area and the closeness of the skeleton line to the fitting straight line.

[0101] The skeleton line of the key crack area is obtained by the skeleton extraction algorithm, and the least square fitting is performed on all skeleton pixel points on the skeleton line to obtain a skeleton fitting straight line.

[0102] The variance of the shortest distance between different skeleton pixel points in the skeleton line of the key crack area and the skeleton fitting straight line is calculated as a skeleton transverse fluctuation value F.

[0103] The local inclination degree value of the skeleton is determined 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, and the sum of the skeleton local inclination degree values of all skeleton pixel points on the skeleton line of the key crack area is calculated as a skeleton inclination degree value.

[0104] In the embodiment of the present application, the calculation method of the skeleton local inclination degree value is as follows: 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 is calculated as a first included angle value; 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 is calculated as a second included angle value, and the absolute value of the difference between the first included angle value and the second included angle value is taken as the skeleton local inclination degree value of the target skeleton pixel point.

[0105] The product value of the skeleton transverse fluctuation value and the skeleton inclination degree value is negatively correlated and normalized, and the result value after mapping is taken as the extension regularity degree of the key crack area.

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

[0107]

[0108] wherein I is the number of skeleton pixel points on the skeleton line of the key crack area; E a-1,aE represents the minimum angle between the directional ray from the a-th skeleton pixel to the (a+1)-th skeleton pixel on the skeleton line of the critical crack region and the horizontal line, which is also the first angle value of the a-th skeleton pixel on the skeleton line of the critical crack region; a,a+2 The angle between the directional ray from the a-th skeleton pixel to the (a+2)-th skeleton pixel on the skeleton line of the critical crack region and the horizontal line is the minimum angle value, which is also the second angle value of the a-th skeleton pixel on the skeleton line of the critical crack region; |E a,a+1 -E a,a+2 | represents the local tilt value of the skeleton at the a-th skeleton pixel on the skeleton line of the critical crack region; F represents the lateral fluctuation value of the skeleton. is the value of the skeletal tilt; exp is an exponential function with the natural constant as the base.

[0109] Among them, |E a,a+1 -E a,a+2 | reflects the change in the angle formed by three adjacent skeleton pixels on the skeleton line of the key crack area, when |E a,a+1 -E a,a+2 The smaller the value of F, the more regular the extension of the skeleton pixels; F reflects the overall regularity of the skeleton lines in the key crack region. The smaller F is, the better the extension direction of the key crack region; the inverse relationship is achieved through the exp(-x) model, where x is the model input. In the formula for calculating the regularity of the extension of the key crack region, ... Input x into the model.

[0110] Step S400: Analyze the light and dark changes of adjacent edge lines in the multi-layer edge lines within the critical crack area to determine the density of the critical crack area; based on the density and extension regularity of the critical crack area and other surrounding critical crack areas, determine the reliability index of the crack defect in the critical crack area.

[0111] Although the shadow cracks formed by stains appear similar to cracks in the segmented images—both being long and narrow—the shadows of stain cracks show some diffusion in the grayscale images, indicating poor density. Cracks, on the other hand, exhibit good grayscale aggregation with little or no diffusion. Furthermore, due to the good extension of cracks, their density is similar in adjacent image segments with similar orientations. By analyzing the density of key crack areas and combining it with the degree of extension regularity, a reliable index of crack defects in key crack areas is obtained.

[0112] First, the light and dark variations of adjacent edge lines in the multi-layered edge lines within the critical crack area are analyzed to determine the density of the critical crack area.

[0113] When the light and shade of the adjacent two layer edge lines in the multi-layer edge lines in the key crack region changes from dark to light from inside to outside, the adjustment coefficient corresponding to the adjacent two layer edge lines is set as a small threshold coefficient; in the embodiment of the application, the value of the small threshold coefficient is 0.1, and in other embodiments, the value is adjusted by the implementer according to the actual situation.

[0114] When the light and shade of the adjacent two layer edge lines in the multi-layer edge lines in the key crack region does not change or changes from light to dark from inside to outside, the adjustment coefficient corresponding to the adjacent two layer edge lines is set as a large threshold coefficient; in the embodiment of the application, the value of the large threshold coefficient is 1, and in other embodiments, the value is adjusted by the implementer according to the actual situation.

[0115] The gray value difference of the adjacent two layer edge lines in the multi-layer edge lines in the key crack region is weighted and summed by taking the adjustment coefficient as the weight, to obtain the compactness of the key crack region.

[0116] More specifically: the gray mean value of each layer edge line of the key crack region is obtained. Please refer to Figure 4 , Figure 4 is a schematic view of each layer edge line of the key crack region, only for understanding the embodiment of the application, Figure 3 contains three layer edge lines, the innermost layer is the first layer edge line, and the outer layer is the third layer edge line.

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

[0118]

[0119] Wherein, H is the number of all layer edges of the key crack region; α b,b+1 is the adjustment coefficient of the b+1th layer edge line and the bth layer edge line of the key crack region; h b+1 is the gray mean value of the b+1th layer edge line of the key crack region; h b is the gray mean value of the bth layer edge line of the key crack region.

[0120] Wherein, |h b+1 -h b | reflects the gray change of the adjacent two layer edge lines of the key crack region, when h b+1 -h b > 0, it means that there is diffusion between the adjacent two layers, which is not compact, and the compactness should be smaller, which is adjusted by the adjustment coefficient; when h b+1 -h b ≤ 0, it means that there is no diffusion between the adjacent two layers, and the compactness should be larger, which is kept unchanged in the embodiment of the application, that is, the adjustment coefficient is set to 1.

[0121] Then, according to the compactness and the extension regularity degree of the key crack region and other key crack regions around the key crack region, a crack defect credibility index of the key crack region is determined.

[0122] Specifically, in the block image around the block image where the key crack region is located, a key crack region connected with the key crack region is obtained. In the embodiment of the present application, the key crack region with a distance less than a preset distance threshold from the key crack region is set as the other key crack region around the key crack region, wherein the preset distance threshold is 20, and in other embodiments, the preset distance threshold can be set by the implementer according to the actual situation. It should be noted that the distance between the key crack regions here refers to the number of pixel points corresponding to the shortest distance between the two key crack regions.

[0123] The sum of absolute values of differences between the compactness of the key crack region and the compactness of the other key crack regions around the key crack region is calculated as a surrounding compactness difference of the key crack region.

[0124] The ratio of the extension regularity degree to the sum of the surrounding compactness difference and a preset adjustment value is taken as a normalized value of the ratio as a crack defect credibility index of the key crack region.

[0125] In some embodiments, taking the key crack region corresponding to two other key crack regions around the key crack region as an example, the calculation formula of the crack defect credibility index L of the key crack region is as follows:

[0126]

[0127] Wherein, J is the compactness of the key crack region, J1 is the compactness of the key crack region in one of the other key crack regions around the key crack region, J2 is the compactness of the key crack region in the other of the other key crack regions around the key crack region, G is the extension regularity degree of the key crack region, and tanh() is a hyperbolic tangent function for normalization.

[0128] Wherein, |J-J1|+|J-J2| reflects the compactness difference between the current key crack region and the connected key crack region, the smaller the difference is, the more likely the current key crack region is a crack, and the greater the extension regularity degree of the key crack region is, the more likely the key crack region is a crack, the more credible the crack defect is, and the greater the credibility index is.

[0129] Step S500, according to the crack defect credibility index, the saliency value of the key crack region obtained by the CA algorithm is adjusted to obtain a modified saliency value of the key crack region, and a real crack region is selected from the key crack region according to the modified saliency value.

[0130] In an embodiment of the present application, the crack defect degree of the key crack region is corrected by the crack defect credibility index to obtain a final crack defect degree of the key crack region. According to the final crack defect degree, a real crack region is screened from the key crack region. The final crack defect degree is obtained by normalizing the product of the crack defect credibility index and the crack defect degree of the key crack region. The greater the final crack defect degree, the more likely the key crack region is a real crack.

[0131] A preset crack identification threshold is set for crack authenticity discrimination When the crack defect degree of the key crack region is greater than or equal to the preset crack identification threshold , the key crack region is determined to be a real crack region, and when the crack defect degree of the key crack region is less than the preset crack identification threshold , the key crack region in the current sub-block image is determined to be a false crack. All sub-block images are discriminated to obtain all cracks in the bridge surface image. The preset crack identification threshold may be optimized through a large number of statistical experiments to maximize the accuracy of crack authenticity discrimination. In the present embodiment, the preset crack identification threshold

[0132] In another embodiment of the present application, the saliency value of the key crack region is corrected by the crack defect credibility index to obtain a corrected saliency value of the key crack region. According to the corrected saliency value, a real crack region is screened from the key crack region. The corrected saliency value is obtained by normalizing the product of the crack defect credibility index and the saliency value of the key crack region obtained by the CA algorithm. The greater the final corrected saliency value, the more likely the key crack region is a real crack.

[0133] A preset corrected saliency threshold is set for crack authenticity discrimination. When the corrected saliency value of the key crack region is greater than or equal to the preset corrected saliency threshold, the key crack region is determined to be a real crack region, and when the corrected saliency value of the key crack region is less than the preset corrected saliency threshold, the key crack region in the current sub-block image is determined to be a false crack. In the present embodiment, the preset corrected saliency threshold has a value of 0.8, and in other embodiments, the value can be adjusted by the implementer according to the actual situation.

[0134] The embodiment of the present application provides a concrete crack detection system for bridge engineering, which comprises:

[0135] An image preprocessing module is configured to obtain a bridge surface image of a bridge road and extract a suspected crack region from the bridge surface image.

[0136] The morphological analysis module is configured to analyze the length and width of the suspected crack region according to the long and narrow feature of the crack, and screen out a key crack region from the suspected crack region;

[0137] The extension analysis module is configured to perform skeleton fitting on the key crack region to obtain a corresponding skeleton fitting straight line, and compare the key crack region with the skeleton fitting straight line to determine the extension regularity degree of the key crack region.

[0138] The credibility analysis module is configured to analyze the light and dark changes of adjacent two layers of edge lines in the key crack region to determine the compactness of the key crack region, and determine a crack defect credibility index of the key crack region according to the compactness and the extension regularity degree of the key crack region and other key crack regions around the key crack region.

[0139] The crack determination module is configured to adjust the saliency value of the key crack region obtained by the CA algorithm according to the crack defect credibility index to obtain a modified saliency value of the key crack region, and screen out a real crack region from the key crack region according to the modified saliency value.

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

[0141] It should be noted that: the apparatus provided in the above embodiments is only exemplified by the division of the above functional modules, and in actual application, the above functions can be completed by 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 above described functions.

[0142] The computer device provided in the embodiment of the present application is shown in a structural schematic diagram. For example, the computer device includes a memory, a processor, and a computer program stored in the memory and running on the processor, wherein when the processor executes the computer program, the computer device can execute any of the above-mentioned bridge engineering concrete crack detection methods.

[0143] In addition, the embodiment of the present application also protects an apparatus, which can include a memory and a processor, wherein the memory stores executable program code, and the processor is configured to call and execute the executable program code to execute the bridge engineering concrete crack detection method provided in the embodiment of the present application.

[0144] The embodiment of the present application can divide the functions of the device according to the above method examples, for example, each function module can be divided, two or more functions can be integrated in one processing module, and the integrated module can be realized in the form of hardware. It should be noted that the division of the modules in the embodiment is illustrative, and is only a logical function division. In actual implementation, another division mode can be used.

[0145] In the case of dividing each module corresponding to each function, the device can further include a signal uploading module, a determining module, an adjusting module, and the like. It should be noted that all related contents of each step involved in the above method embodiment can be cited to the function description of the corresponding function module, and will not be described here.

[0146] It should be understood that the device provided by the embodiment of the present application is used to execute the above-mentioned bridge engineering concrete crack detection method, and thus the same effect as the above-mentioned implementation method can be achieved.

[0147] In the case of using an integrated unit, the device can include a processing module and a storage module. When the device is applied to equipment, the processing module can be used to control and manage the actions of the equipment. The storage module can be used to support the equipment to execute mutual program codes and the like. The processing module can be a processor or a controller, which can realize or execute various exemplary logical blocks, modules and circuits described in combination with the disclosure of the present application. The processor can also be a combination of computing functions, such as one or more microprocessor combinations, a combination of digital signal processing (Digital Signal Processing, DSP) and microprocessors, and the like. The storage module can be a memory.

[0148] In addition, the device provided by the embodiment of the present application can be a chip, an assembly or a module. The chip can include a connected processor and a memory. The memory is used to store instructions. When the processor calls and executes the instructions, the chip can execute the bridge engineering concrete crack detection method provided in the above embodiment.

[0149] The embodiment of the present application also provides a computer readable storage medium, which stores computer program codes. When the computer program codes run on a computer, the computer executes the above-mentioned related method steps to realize the bridge engineering concrete crack detection method provided in the above embodiment.

[0150] The embodiment of the present application also provides a computer program product. When the computer program product runs on a computer, the computer executes the above-mentioned related steps to realize the bridge engineering concrete crack detection method provided in the above embodiment.

[0151] Among them, the device, computer readable storage medium, computer program product or chip provided by the embodiments of the present application are used to execute the corresponding methods provided above, so the beneficial effects that can be achieved are referred to the beneficial effects of the corresponding methods provided above, which will not be repeated here. Through the description of the above implementation mode, those skilled in the art can understand that, for the convenience and brevity of description, only the above-mentioned division of functional modules is taken as an example, and in actual application, the above-mentioned functions can be completed by 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 application, it should be understood that the disclosed device and method can be implemented in other ways.

[0152] The device embodiments described above are only schematic, for example, the division of modules or units is only a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another device, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the shown or discussed each other can be indirect coupling or communication connection through some interface, device or unit, which can be electrical, mechanical or other forms.

[0153] It should be further understood that the terms "comprise", "comprise", or any other variant thereof are intended to cover non-exclusive inclusion, so that processes, methods, articles or terminal devices including a series of elements not only include those elements, but also include other elements not explicitly listed or inherent to such processes, methods, articles or terminal devices. Without more limitations, the element defined by the statement "comprises a" does not exclude the presence of additional identical elements in the process, method, article or terminal device comprising the element.

[0154] It should be noted that: the above-mentioned sequence of the embodiments of the present application is only for description, not representing the advantages and disadvantages of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multi-task processing and parallel processing are also possible or can be advantageous.

[0155] Each embodiment in the specification is described in a progressive manner, and the same or similar parts between each embodiment can be referred to each other, and each embodiment mainly describes the difference from other embodiments.

[0156] The above merely illustrates the specific embodiments of the present application, but the protection scope of the present application is not limited thereto, any person skilled in the art can easily think of the changes or replacements within the technical range disclosed by the present application, which should be covered in the protection scope of the present application.

Claims

1. A method for detecting concrete cracks in bridge engineering, characterized in that, The method includes the following steps: Acquire images of the bridge surface of the bridge road and extract suspected crack areas from the bridge surface images; Based on the narrow and elongated characteristics of the cracks, the length and width of the suspected crack areas are analyzed, and key crack areas are selected from the suspected crack areas. A skeleton is fitted to the critical crack region to obtain the corresponding skeleton fitting line; the critical crack region and the skeleton fitting line are compared to determine the degree of extension regularity of the critical crack region. Analyze the light and dark changes of adjacent edge lines in the multi-layer edge lines within the critical crack area to determine the density of the critical crack area; based on the density and extension regularity of the critical crack area and other surrounding critical crack areas, determine the reliability index of the crack defect in the critical crack area. Based on the crack defect credibility index, the significance value of the key crack region obtained by the CA significance detection algorithm is adjusted to obtain the corrected significance value of the key crack region; based on the corrected significance value, the true crack region is screened out from the key crack region. The method for obtaining the density is as follows: when the brightness of two adjacent edge lines in the multi-layer edge lines within the critical crack area changes from dark to light from the inside out, the adjustment coefficient corresponding to the two adjacent edge lines is set as a small threshold coefficient; when there is no brightness change or the brightness of two adjacent edge lines in the multi-layer edge lines within the critical crack area changes from light to dark from the inside out, the adjustment coefficient corresponding to the two adjacent edge lines is set as a large threshold coefficient; using the adjustment coefficient as a weight, the difference in gray values ​​between two adjacent edge lines in the multi-layer edge lines within the critical crack area is weighted and summed to obtain the density of the critical crack area.

2. The method for detecting concrete cracks in bridge engineering according to claim 1, characterized in that, The process involves analyzing the length and width of suspected crack regions based on the elongated characteristics of the cracks, and then selecting key crack regions from these suspected crack regions. Analyze the width at different locations 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 elongated feature of the suspected crack area; combine the width stability feature and the elongated feature to determine the degree of crack defect in the suspected crack area; based on the degree of crack defect, select key crack areas from the suspected crack area.

3. The method for detecting concrete cracks in bridge engineering according to claim 2, characterized in that, The analysis of the width at different locations within the suspected crack area to determine width stability characteristics includes: Calculate the average width at different locations within the suspected crack area, and use this as the average width. Width instability is determined by the difference between the width at different locations in the suspected crack area and the mean width. By performing a negative correlation mapping on the width instability, the width stability characteristics of the suspected crack region are obtained.

4. The method for detecting concrete cracks in bridge engineering according to claim 2, characterized in that, The determination of the elongated characteristics of the suspected crack region by combining the width stability characteristics and the length of the skeleton line of the suspected crack region includes: Obtain the length of the skeleton line in the suspected crack area; Calculate the aspect ratio between the length of the skeleton line and the width at each location in the suspected crack area to obtain the local elongated feature at each location in the suspected crack area; The difference between the maximum and minimum local elongation features in the suspected crack region is calculated as the local elongation feature range. The narrow features of the suspected crack region are determined by multiplying the negative correlation mapping value of the local narrow feature range with the mean value of the local narrow features.

5. The method for detecting concrete cracks in bridge engineering according to claim 2, characterized in that, The determination of the degree of crack defect in the suspected crack region by combining the width stability feature and the elongation feature includes: The normalized value of the product of the width stability feature and the elongation feature is used as the degree of crack defect in the suspected crack region.

6. The method for detecting concrete cracks in bridge engineering according to claim 2, characterized in that, The step of selecting key crack areas from suspected crack areas based on the degree of crack defects includes: Areas with suspected cracks whose crack defects exceed a preset significance threshold are designated as critical crack areas.

7. The method for detecting concrete cracks in bridge engineering according to claim 1, characterized in that, The step of comparing the key crack region with the fitted straight line of the skeleton to determine the degree of regularity of the extension of the key crack region includes: Calculate the variance of the shortest distance between different skeleton pixels in the skeleton line of the key crack region and the skeleton fitting line, and use it as the skeleton lateral fluctuation value. Take any skeleton pixel on the skeleton line of the key crack region as the target skeleton pixel, and determine the local tilt value of the skeleton based on the angle between the line segment formed by the target skeleton pixel and the skeleton pixel behind it and the horizontal line; calculate the sum of the local tilt values ​​of all skeleton pixels on the skeleton line of the key crack region as the skeleton tilt value. The product of the lateral fluctuation value and the tilt value of the skeleton is negatively correlated and normalized. The resulting value is used as the degree of extension regularity of the key crack area.

8. The method for detecting concrete cracks in bridge engineering according to claim 1, characterized in that, The determination of crack defect reliability indicators for the critical crack region based on the density and extension regularity of the critical crack region and other surrounding critical crack regions includes: The sum of the absolute values ​​of the differences in density between the critical crack region and other surrounding critical crack regions is used as the density difference of the critical crack region. Using the degree of extension regularity as the numerator and the sum of the surrounding density difference and the preset adjustment value as the denominator, the normalized value of the obtained ratio is used as the reliable index of crack defects in the key crack area.

9. The method for detecting concrete cracks in bridge engineering according to claim 1, characterized in that, The step of filtering out true crack regions from key crack regions based on the corrected significance value includes: Key crack regions with a correction significance value greater than a preset correction significance threshold are considered as true crack regions.

Images