CN117152135B - Road construction crack defect evaluation and detection method - Google Patents
Road construction crack defect evaluation and detection method Download PDFInfo
- Publication number
- CN117152135B CN117152135B CN202311412671.4A CN202311412671A CN117152135B CN 117152135 B CN117152135 B CN 117152135B CN 202311412671 A CN202311412671 A CN 202311412671A CN 117152135 B CN117152135 B CN 117152135B
- Authority
- CN
- China
- Prior art keywords
- edge
- value
- fuzzy
- road surface
- degree
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000011156 evaluation Methods 0.000 title claims abstract description 37
- 230000007547 defect Effects 0.000 title claims abstract description 35
- 238000010276 construction Methods 0.000 title claims abstract description 23
- 238000001514 detection method Methods 0.000 title claims abstract description 15
- 238000001914 filtration Methods 0.000 claims abstract description 40
- 238000000034 method Methods 0.000 claims description 50
- 238000013507 mapping Methods 0.000 claims description 5
- 238000003708 edge detection Methods 0.000 abstract description 17
- 238000004458 analytical method Methods 0.000 description 3
- 230000001413 cellular effect Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000739 chaotic effect Effects 0.000 description 1
- 238000005315 distribution function Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000012797 qualification Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20212—Image combination
- G06T2207/20216—Image averaging
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30248—Vehicle exterior or interior
- G06T2207/30252—Vehicle exterior; Vicinity of vehicle
- G06T2207/30256—Lane; Road marking
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention relates to the technical field of image edge detection, in particular to a road construction crack defect evaluation and detection method. The invention adjusts the filtering degree of each pixel point through the complexity degree of the road surface to obtain the fuzzy value of each pixel point, and obtains the fuzzy degree according to the gray value of the pixel point and the difference of the fuzzy value; obtaining a fuzzy threshold according to the distribution condition of the fuzzy degree of the crack edge pixel points in the road surface gray level image; and obtaining edge parameters of each pixel point according to the fuzzy value of each pixel point, the fuzzy threshold value of the gray level image of the road surface and the fuzzy degree of all the pixel points, obtaining a road edge image through the edge parameters, and carrying out crack defect evaluation. According to the invention, edge detection is carried out by combining the characteristics of complex edge distribution, so that more accurate crack edges are obtained, and the accuracy of crack defect evaluation is higher.
Description
Technical Field
The invention relates to the technical field of image edge detection, in particular to a road construction crack defect evaluation and detection method.
Background
The significance of road construction crack defect evaluation is to evaluate the crack defect condition on a construction road, so that timely maintenance and repair work is performed, and the fact that the finished road is not provided with crack defects affecting road safety is guaranteed, and the crack defects may seriously affect driving safety. The potential danger can be found early by evaluating the crack defects, the occurrence of accidents is prevented, and the driving safety of the road is ensured.
In the existing evaluation and detection of pavement cracks, edge detection is commonly used for acquiring and analyzing edges, but some texture details usually exist on the road surface, when the accuracy of edge detection is high, the acquisition of the edges of the cracks is interfered, even if the whole image edge characteristics are not reasonably considered through filtering for blurring, the robustness of the edges acquired by the edge detection is poor, more accurate edges of the cracks cannot be obtained, and the evaluation of the edges of the cracks is further inaccurate.
Disclosure of Invention
In order to solve the technical problem that in the prior art, more accurate crack edges cannot be obtained, so that the evaluation of the crack edges is inaccurate, the invention aims to provide a road construction crack defect evaluation and detection method, which adopts the following specific technical scheme:
the invention provides a road construction crack defect evaluation and detection method, which comprises the following steps:
acquiring a road surface gray level image;
filtering each pixel point by combining the gray value complexity degree of all the pixel points in the gray image of the road surface to obtain a fuzzy value of each pixel point; obtaining the blurring degree of each pixel point according to the difference condition of the gray value of the gray image of each pixel point on the road surface and the corresponding blurring value; obtaining a fuzzy threshold value of the road surface gray level image according to the distribution condition of the fuzzy degree corresponding to all pixel points in the road surface gray level image;
obtaining edge parameters of each pixel point according to the fuzzy value of each pixel point, the fuzzy threshold value of the road surface gray level image and the fuzzy degree of all the pixel points; obtaining a road crack edge image according to the edge parameters of each pixel point;
and carrying out crack defect evaluation through the road crack edge image.
Further, the method for acquiring the fuzzy value comprises the following steps:
obtaining adjustment weights according to the gray value complexity degree of all pixel points in the gray image of the road surface;
for any pixel point, filtering weights of all pixel points in a window are obtained by Gaussian filtering in a preset filtering window corresponding to the pixel point; taking the product of the filtering weight and the adjusting weight as the fuzzy weight of each pixel point in a preset filtering window;
and weighting the gray value of each pixel point in the preset filter window through the corresponding fuzzy weight to obtain the fuzzy weight value of each pixel point in the preset filter window, and calculating the average value of the fuzzy weight values of all the pixel points in the preset filter window to obtain the fuzzy value of the pixel point.
Further, the method for acquiring the blurring degree comprises the following steps:
the ratio of the blur value of each pixel point to the corresponding gray value in the road surface gray image is taken as the blur degree of each pixel point.
Further, the method for acquiring the fuzzy threshold value comprises the following steps:
acquiring edge pixel points in a road surface gray level image;
calculating the average value of gray values of all edge pixel points to be used as an edge average value; calculating the average value of the blurring degree of all the edge pixel points to obtain the edge blurring degree; taking the product of the edge average value and the edge ambiguity as an upper ambiguity threshold value of the road surface gray level image;
calculating the average value of gray values of all non-edge pixel points in the gray image of the road surface, and taking the average value as a pixel average value; calculating the average value of the blurring degree of all the non-edge pixel points to obtain the pixel blurring degree; taking the product of the pixel average value and the pixel ambiguity as a fuzzy lower threshold value of the road surface gray level image;
and taking the average value of the blurring lower threshold value and the blurring upper threshold value of the road surface gray level image as the blurring threshold value of the road surface gray level image.
Further, the method for acquiring the edge parameter comprises the following steps:
obtaining a characteristic adjustment value of the gray level image of the road surface according to the concentrated trend of the blurring degree of all the pixel points in the gray level image of the road surface; taking the difference value of the fuzzy value and the fuzzy threshold value of each pixel point as the fuzzy difference degree of each pixel point;
and obtaining the edge parameters of each pixel point according to the fuzzy difference degree and the characteristic adjustment value of the pixel point.
Further, the method for acquiring the characteristic adjustment value comprises the following steps:
and calculating the average value of the blurring degree of all pixel points in the gray level image of the road surface to obtain the average blurring degree, and carrying out negative correlation mapping on the average blurring degree to obtain the characteristic adjustment value.
Further, the expression of the edge parameter is:
the method comprises the steps of carrying out a first treatment on the surface of the In (1) the->Denoted as +.>Edge parameters of individual pixels, +.>Denoted as +.>Blur degree of each pixel, +.>Characteristic adjustment value expressed as a gray-scale image of the road surface, for example>Represented as an exponential function with a base of natural constant.
Further, the method for acquiring the adjustment weight comprises the following steps:
and carrying out negative correlation mapping on standard deviations of gray values of all pixel points in the gray image of the road surface to obtain adjustment weights.
Further, the method for acquiring the road crack edge image comprises the following steps:
when the edge parameter of the pixel point is larger than a preset first threshold value and smaller than a preset second threshold value, setting the gray value of the corresponding pixel point as a first parameter; the preset first threshold value is smaller than the preset second threshold value;
setting the gray values of the rest pixel points as second parameters to obtain a road crack edge image; the first parameter is different from the second parameter.
Further, the estimating the crack defect by the road crack edge image includes:
counting the number of edge pixel points in the road crack edge image to obtain the crack edge quantity; taking the ratio of the crack edge quantity to the total quantity of all pixel points as an evaluation index;
when the evaluation index is smaller than or equal to a preset crack threshold value, marking the corresponding road surface as qualified; and when the evaluation index is larger than the preset crack threshold value, marking the corresponding road surface as unqualified.
The invention has the following beneficial effects:
according to the invention, the filtering degree of each pixel point is adjusted to the complexity degree of the road surface, so that the fuzzy value of each pixel point is obtained, the line detail part in the gray level image of the road surface can be completely blurred, and the accuracy of analyzing the edge characteristics based on the fuzzy value is improved. According to the difference of the gray level value and the fuzzy value of the pixel points, the fuzzy degree is obtained, the fuzzy degree of the pixel points at the edge of the crack in the image is considered, the fuzzy threshold value is obtained according to the distribution condition of the fuzzy degree of the pixel points at the edge of the crack in the image, and the fuzzy threshold value is obtained more accurately by combining different distribution characteristics of the fuzzy degree of the road surface, so that the judgment of the edge of the crack is improved. Considering the influence of the complexity of the detail features of the road surface on the edge judgment accuracy, according to the fuzzy value of each pixel point, the fuzzy threshold value of the gray level image of the road surface and the fuzzy degree of all the pixel points, the accuracy degree of judgment is adjusted through the fuzzy degree, so that the edge parameters of each pixel point are more accurate, further, a more accurate and clear edge image of the road crack is obtained according to the edge parameters, and finally, the accuracy of crack defect evaluation is higher.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions and advantages of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flowchart of a method for evaluating and detecting a crack defect in a road construction according to an embodiment of the present invention;
FIG. 2 is a grayscale image of a road surface according to one embodiment of the present invention;
FIG. 3 is a primary edge image according to one embodiment of the present invention;
FIG. 4 is a filtered image according to one embodiment of the present invention;
fig. 5 is a flowchart of a method for detecting a crack defect edge in road construction according to an embodiment of the present invention.
Detailed Description
In order to further describe the technical means and effects adopted by the present invention to achieve the preset purpose, the following detailed description refers to specific embodiments, structures, features and effects of a road construction crack defect evaluation and detection method according to the present invention with reference to the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Unless defined otherwise, 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 invention belongs.
An embodiment of a road construction crack defect evaluation and detection method comprises the following steps:
the following specifically describes a specific scheme of the road construction crack defect evaluation and detection method provided by the invention with reference to the accompanying drawings.
Referring to fig. 1, a flowchart of a method for evaluating and detecting a road construction crack defect according to an embodiment of the invention is shown, the method includes the following steps:
s1: and acquiring a gray level image of the road surface.
In road construction, the road surface is required to be detected and evaluated in time so as to prevent some cracks with high danger degree from damaging the road safety. However, since the road surface features are generally rough or have grain details, if the edge detection is directly performed on the road image, a great amount of pavement detail information will exist in the obtained edge image, which interferes with the detection and evaluation of the crack, so that it is necessary to obtain a clearer crack edge while reducing the interference of grain details.
In the embodiment of the invention, the road image is acquired by adopting the image acquisition equipment such as a high-definition camera and the like, and an implementer can select different image acquisition equipment according to specific implementation conditions. Further, in order to facilitate the subsequent analysis of the image edge condition, the road image is subjected to the graying process to obtain the road surface gray image, please refer to fig. 2, which illustrates a road surface gray image provided by an embodiment of the present invention. The graying process of the image is a technique known to those skilled in the art, and a weighting method, an average method, or the like may be used, and is not limited thereto.
S2: filtering each pixel point by combining the gray value complexity degree of all the pixel points in the gray image of the road surface to obtain a fuzzy value of each pixel point; obtaining the blurring degree of each pixel point according to the difference condition of the gray value of the gray image of each pixel point on the road surface and the corresponding blurring value; and obtaining a blurring threshold value of the road surface gray level image according to the distribution condition of the blurring degree corresponding to all the pixel points in the road surface gray level image.
By using the existing edge algorithm, a great amount of grain details exist in the finally obtained edge detection image to influence the judgment of cracks, and in the embodiment of the invention, a canny operator is adopted for detection to obtain a primary edge image, please refer to fig. 3, which shows a primary edge image provided by an embodiment of the invention. In fig. 3 there is an edge analysis of the grain detail so that the crack edge portion is not noticeable. Therefore, in order to eliminate the influence of the details of the lines, the OFCA (Optimized Fuzzy Cellular Automata) method can be adopted for edge detection, the OFCA method is an edge detection algorithm based on a fuzzy cellular automaton, the edge information in the image is obtained by blurring and iterating each pixel in the image, the detail characteristics of the surface can be eliminated through blurring processing, and the edge detection is further carried out according to the blurring condition. In the OFCA method, edge details are blurred first, then edge points are screened through a set fuzzy rule to realize edge detection, and the set fuzzy rule cannot meet the requirements of different road surfaces due to different road characteristics, so that the setting of the fuzzy rule in the OFCA method needs to be considered and optimized, and more accurate crack edge images can be obtained conveniently. It should be noted that, the edge detection algorithm based on the fuzzy cellular automaton is a technical means well known to those skilled in the art, and will not be described herein.
Firstly, filtering each pixel point according to the gray value complexity of all pixel points in a gray image of a road surface to obtain a fuzzy value of each pixel point, firstly, blurring some grain detail parts by filtering and blurring the pixel points to reduce detail areas, and preferably, obtaining an adjustment weight according to the gray value complexity of all pixel points in the gray image of the road surface. In the embodiment of the invention, the expression for adjusting the weight is:
in the method, in the process of the invention,expressed as adjustment weights, +.>Expressed as standard deviation of gray values of all pixels in the road surface gray image.
For any pixel, in a preset filtering window corresponding to the pixel, filtering weights of all pixels in the window are obtained by adopting Gaussian filtering, the filtering weights reflect the contribution degree of each pixel to the pixel at the central position in the preset filtering window, in the embodiment of the invention, the size of the preset filtering window is 5×5, a specific size implementer can adjust according to specific implementation conditions, when filtering the pixel, filtering weight calculation is carried out in the filtering window taking the pixel as the central point, and the expression of the filtering weight acquisition is as follows:
in the method, in the process of the invention,expressed as +.f. in a preset filter window>Filtering weights of individual pixels, +.>Expressed as standard deviation of gray values of pixel points in a preset filter window, +.>Expressed as +.f. in a preset filter window>Difference of abscissa between each pixel point and central point of preset filter window, +.>Expressed as +.f. in a preset filter window>Difference of ordinate between each pixel point and central point of preset filter window, +.>Expressed as circumference ratio>Represented as an exponential function with a base of natural constant. It should be noted that, the calculation formula of the filtering weight is a two-dimensional gaussian distribution function formula, and the application of the formula is a technical means well known to those skilled in the art, so the meaning of the specific formula is not repeated.
The product of the filtering weight and the adjusting weight is used as the fuzzy weight of each pixel point in a preset filtering window, and the better the adjusting coefficient is, the more the chaotic description feature of the pixel points on the road surface is, the stronger the fuzzy effect is needed to carry out the blurring, so that the smaller the adjusting coefficient is, the smaller the fuzzy weight is, the smaller the contribution to the central point is, the less the detail part is reserved, and the higher the degree of blurring of the pixel points is.
The gray value of each pixel point in the preset filter window is weighted through the corresponding fuzzy weight, the fuzzy weight value of each pixel point in the preset filter window is obtained, the average value of the fuzzy weight values of all the pixel points in the preset filter window is calculated, the fuzzy value of the pixel point is obtained, and the pixel value of each pixel point after filtering, namely the fuzzy value, is obtained through weighting and averaging according to the adjusted fuzzy weight.
Referring to fig. 4, a filtered image according to an embodiment of the invention is shown. The filtered image is an image of all pixels composed of blurred values, and it can be seen in fig. 4 that after the pixels are filtered, the detailed portion of the lines is filtered, and for the road crack region, the region is preserved. Because the gray value in the crack area is far lower than the normal road surface area, after filtering, a gray value gradual change area exists between the crack area and the normal area, namely the gray value corresponding to the crack edge is higher than the crack area and lower than the normal area, and the edge area in the image is regularly set according to the characteristic.
The filtering can blur the line detail part, so that the blurred degree of the pixel points representing the edge detail is larger, and the blurred degree of the pixel points in other areas is smaller, so that the blurred degree of each pixel point is obtained according to the difference condition of the gray value of each pixel point in the gray image of the road surface and the corresponding blurred value, and preferably, the ratio of the blurred value of each pixel point to the corresponding gray value in the gray image of the road surface is used as the blurred degree of each pixel point. The greater the degree of blurring, the smaller the difference between the blurring value and the gray value, the smaller the degree of blurring, the more likely the pixel is the pixel of the normal region, and the lesser the degree of blurring, the greater the difference between the blurring value and the gray value, the greater the degree of blurring, and the more likely the pixel is the pixel of the edge detail portion.
Further, the possibility of the edge pixel point is judged according to the blurring degree, and the crack area is obvious, so that the crack area is reserved after filtering, and the edge of the crack area is reserved, so that the blurring degree of the crack edge is smaller than the average blurring degree of the edge pixel point.
The average value of gray values of all edge pixel points is calculated and used as an edge average value, the average value of the blurring degree of all edge pixel points is calculated, the edge blurring degree is obtained, the average pixel values and the average blurring degree of all edges are obtained through the edge average value and the edge blurring degree, the product of the edge average value and the edge blurring degree is further used as a blurring upper threshold value of a gray level image of a road surface, and the blurring degree of a crack edge is smaller than the blurring degree of an edge of a detail part, so that the final blurring value is smaller than the blurring upper threshold value. In the embodiment of the invention, the specific expression of the upper fuzzy threshold is as follows:
in the method, in the process of the invention,an upper threshold value of blur, denoted as gray level image of the road surface, ">Expressed as edge mean, +.>Denoted as +.>Degree of blurring of the individual edge pixels, +.>Expressed as the total number of edge pixels in the grayscale image of the road surface. Wherein,represented as edge ambiguity.
Further, since the crack edge is also a region with a higher degree of blurring than the normal region, the lowest blurred value of the crack edge can be obtained by the degree of blurring of the normal region of the non-edge portion, the average value of the gray values of all non-edge pixel points in the gray image of the road surface is calculated, the average value of the blur degree of all non-edge pixel points is calculated as the pixel average value, the pixel blur degree is obtained, the product of the pixel average value and the pixel blur degree is used as the blur lower threshold value of the gray image of the road surface, and the blur value of the crack edge is larger than the blur lower threshold value because the change degree of the crack edge is larger than the normal region. In the embodiment of the invention, the specific expression of the fuzzy lower threshold value is as follows:
in the method, in the process of the invention,a blur lower threshold value expressed as a gray level image of the road surface, < >>Expressed as pixel mean,/-, and>denoted as +.>Degree of blurring of non-edge pixels, < >>Expressed as the total number of non-edge pixels in the grayscale image of the road surface. Wherein (1)>Represented as pixel ambiguity.
Finally, the range of the fuzzy threshold where the crack edge is located can be obtained through the fuzzy lower threshold and the fuzzy upper threshold, the optimal fuzzy threshold of the crack edge is obtained according to the fuzzy upper threshold and the fuzzy lower threshold, when the fuzzy value of the pixel point is closer to the fuzzy threshold, the pixel point is more likely to be the crack edge pixel point, the complexity degree of the edge feature is different in different road surfaces, and the fuzzy threshold of the gray level image of the road surface is also different. In the embodiment of the invention, the average value of the lower threshold value and the upper threshold value of the road surface gray level image is used as the threshold value of the road surface gray level image.
By analyzing the blurring degree of the pixel points in the road, the position characteristics of the crack edge are considered to cause the blurring degree of the crack edge to be lower than the normal edge information and higher than the normal pixel points, so that a more suitable blurring threshold value is obtained for the edge condition of the current road surface.
S3: obtaining edge parameters of each pixel point according to the fuzzy value of each pixel point, the fuzzy threshold value of the road surface gray level image and the fuzzy degree of all the pixel points; and obtaining a road crack edge image according to the edge parameters of each pixel point.
According to the fuzzy value of each pixel point, the fuzzy threshold value of the road surface gray level image and the setting of the fuzzy rule in the OFCA method for optimizing the fuzzy degree of all the pixel points, the fuzzy rule is the screening rule of the edge points, in the embodiment of the invention, the fuzzy rule is an edge parameter acquisition expression of the pixel points, the judgment index setting in the fuzzy rule is adjusted through the image characteristics in the road surface gray level image, preferably, the difference value of the fuzzy value of each pixel point and the fuzzy threshold value is used as the fuzzy difference degree of each pixel point, the difference degree of the pixel points corresponding to the crack edge is reflected through the fuzzy difference degree, the characteristic adjustment value of the road surface gray level image is obtained according to the concentrated trend of the fuzzy degree of all the pixel points in the road surface gray level image, and the fine degree of the crack edge judgment is adjusted through the characteristic adjustment value.
In the embodiment of the invention, the average value of the blurring degree of all pixel points in the gray level image of the road surface is calculated, the average blurring degree is obtained, and the average blurring degree is subjected to negative correlation mapping to obtain the characteristic adjustment value. When the average blurring degree is larger, the blurring degree of the pixel points is smaller, the texture detail part of the road surface is smaller, the influence on the judgment of the crack edge is smaller, and therefore the characteristic adjustment value is smaller, and the judgment according to the blurring difference degree is finer. And when the average blurring degree is smaller, the blurring degree of the pixel points is larger, the texture detail part of the road surface is more, and judgment of crack edges is more affected, so that the feature adjustment value needs to be larger, and fault tolerance needs to be increased when judgment is carried out according to the blurring difference degree.
Finally, according to the fuzzy difference degree and the characteristic adjustment value of each pixel point, the edge parameter of the pixel point is obtained. In the embodiment of the invention, the specific expression of the edge parameter is:
in the method, in the process of the invention,denoted as +.>Edge parameters of individual pixels, +.>Denoted as +.>Blur degree of each pixel, +.>Characteristic adjustment value expressed as a gray-scale image of the road surface, for example>Represented as an exponential function with a base of natural constant.
When (when)The smaller, the description of->The smaller the difference between the pixel points and the pixel points corresponding to the crack edge is, the range is adjusted, when +>The more closely to 0.5, the description of +.>The more likely each pixel is a crack edge, and therefore further, a road crack edge image is obtained according to the edge parameters of each pixel.
Preferably, when the edge parameter of the pixel point is greater than a preset first threshold and less than a preset second threshold, it is indicated that the more likely the pixel point is a crack edge, the gray value of the corresponding pixel point is set to the first parameter, where the preset first threshold is less than the preset second threshold to ensure that the judgment is true. Setting the gray values of the rest pixel points as second parameters, wherein the first parameters are different from the second parameters, finishing binarization of the gray level image of the road surface, obtaining a road crack edge image, and obtaining a clearer and more accurate image only containing the crack edge, wherein in the embodiment of the invention, the first parameters are 255, the second parameters are 0, and the image obtained after updating the gray values of the pixel points is the road crack edge image.
Therefore, on the basis of the edge distribution characteristic condition of the road surface, the fuzzy rule set for edge detection is optimized according to the fuzzy threshold value and the fuzzy degree, and a clearer and more accurate road crack edge image containing the crack edge is obtained.
S4: and carrying out crack defect evaluation through the road crack edge image.
Finally, according to the road crack edge image, the crack defect can be evaluated, in the embodiment of the invention, the number of edge pixels in the road crack edge image is judged, the number of edge pixels in the road crack edge image is counted, the crack edge quantity is obtained, the ratio of the crack edge quantity to the total number of all pixels is used as an evaluation index, the existence degree of the crack is reflected by the evaluation index, and the qualification judgment is carried out on the road surface.
When the evaluation index is smaller than or equal to the preset crack threshold value, the fact that the cracks of the road table are smaller or no cracks is indicated, the road can be used normally, and the corresponding road surface is marked as qualified. When the evaluation index is larger than the preset crack threshold value, the existence of the crack defect is indicated to be required to be maintained, and the corresponding road surface is marked as unqualified. In other embodiments of the present invention, road surfaces may be classified into four evaluation criteria, namely, serious, moderate, mild and qualified, according to the evaluation index, and the evaluation criteria correspond to different maintenance methods, which are not limited herein.
In summary, the invention obtains the fuzzy value of each pixel point by adjusting the filtering degree of each pixel point on the complexity degree of the road surface, so that the line detail part in the image can be more completely blurred, and the accuracy of the subsequent edge feature analysis based on the fuzzy value is improved. The blurring degree is obtained by combining the difference of the gray level value and the blurring value of the pixel points, the blurring threshold value is obtained according to the distribution condition of the blurring degree of the pixel points at the edge of the crack in the image by considering the difference degree of the blurring degree between different pixel points, the obtaining of the blurring threshold value is more accurate by combining different distribution characteristics of the blurring degree of the road surface, and the judgment of the edge of the crack is improved. Considering the influence of the detail characteristics of the road surface on the edge judgment accuracy, according to the fuzzy value of each pixel point, the fuzzy threshold value of the gray level image of the road surface and the fuzzy degree of all the pixel points, the accuracy degree of judgment is adjusted through the fuzzy degree, so that the edge parameter of each pixel point is further obtained more accurately, a more accurate and clear road crack edge image is obtained, and finally the accuracy of crack defect evaluation is higher.
An embodiment of a method for detecting the edge of a road construction crack defect is provided:
in the existing evaluation detection of pavement cracks, edge detection is commonly used for acquiring and analyzing edges, but some texture details usually exist on the road surface, when the accuracy of edge detection is high, the acquisition of the crack edges is interfered, even if the whole image edge characteristics are blurred through filtering, the robustness of the edge detection for acquiring the edges is poor, the more accurate crack edges cannot be obtained, and the problem that the more accurate crack edges cannot be obtained is solved. The invention provides a method for detecting the edge of a road construction crack defect. Referring to fig. 5, a flowchart of a method for detecting a crack edge in road construction according to an embodiment of the invention is shown. The method comprises the following steps:
step S01: and acquiring a gray level image of the road surface.
Step S02: filtering each pixel point by combining the gray value complexity degree of all the pixel points in the gray image of the road surface to obtain a fuzzy value of each pixel point; obtaining the blurring degree of each pixel point according to the difference condition of the gray value of the gray image of each pixel point on the road surface and the corresponding blurring value; and obtaining a blurring threshold value of the road surface gray level image according to the distribution condition of the blurring degree corresponding to all the pixel points in the road surface gray level image.
Step S03: obtaining edge parameters of each pixel point according to the fuzzy value of each pixel point, the fuzzy threshold value of the road surface gray level image and the fuzzy degree of all the pixel points; and obtaining a road crack edge image according to the edge parameters of each pixel point.
The steps S01 to S03 are described in detail in the above embodiments of the method for evaluating and detecting a road construction crack defect, and are not described herein.
According to the invention, the filtering degree of each pixel point is adjusted to the complexity degree of the road surface, so that the fuzzy value of each pixel point is obtained, the line detail part in the gray level image of the road surface can be completely blurred, and the accuracy of analyzing the edge characteristics based on the fuzzy value is improved. According to the difference of the gray level value and the fuzzy value of the pixel points, the fuzzy degree is obtained, the fuzzy degree of the pixel points at the edge of the crack in the image is considered, the fuzzy threshold value is obtained according to the distribution condition of the fuzzy degree of the pixel points at the edge of the crack in the image, and the fuzzy threshold value is obtained more accurately by combining different distribution characteristics of the fuzzy degree of the road surface, so that the judgment of the edge of the crack is improved. Considering the influence of the complexity of the detail features of the road surface on the edge judgment accuracy, according to the fuzzy value of each pixel point, the fuzzy threshold value of the gray level image of the road surface and the fuzzy degree of all the pixel points, the accuracy degree of judgment is adjusted through the fuzzy degree, so that the edge parameter of each pixel point is more accurate, and further the more accurate and clear edge of the road crack is obtained according to the edge parameter.
It should be noted that: the sequence of the embodiments of the present invention is only for description, and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments.
Claims (4)
1. A method for evaluating and detecting a road construction crack defect, the method comprising:
acquiring a road surface gray level image;
filtering each pixel point by combining the gray value complexity degree of all the pixel points in the gray image of the road surface to obtain a fuzzy value of each pixel point; obtaining the blurring degree of each pixel point according to the difference condition of the gray value of the gray image of each pixel point on the road surface and the corresponding blurring value; obtaining a fuzzy threshold value of the road surface gray level image according to the distribution condition of the fuzzy degree corresponding to all pixel points in the road surface gray level image;
obtaining edge parameters of each pixel point according to the fuzzy value of each pixel point, the fuzzy threshold value of the road surface gray level image and the fuzzy degree of all the pixel points; obtaining a road crack edge image according to the edge parameters of each pixel point;
performing crack defect evaluation through the road crack edge image;
the fuzzy value acquisition method comprises the following steps:
obtaining adjustment weights according to the gray value complexity degree of all pixel points in the gray image of the road surface;
for any pixel point, filtering weights of all pixel points in a window are obtained by Gaussian filtering in a preset filtering window corresponding to the pixel point; taking the product of the filtering weight and the adjusting weight as the fuzzy weight of each pixel point in a preset filtering window;
weighting the gray value of each pixel point in a preset filter window through a corresponding fuzzy weight to obtain a fuzzy weighted value of each pixel point in the preset filter window, and calculating the average value of the fuzzy weighted values of all the pixel points in the preset filter window to obtain a fuzzy value of the pixel point;
the weight adjustment acquisition method comprises the following steps:
carrying out negative correlation mapping on standard deviations of gray values of all pixel points in the gray image of the road surface to obtain adjustment weights;
the method for acquiring the edge parameters comprises the following steps:
obtaining a characteristic adjustment value of the gray level image of the road surface according to the concentrated trend of the blurring degree of all the pixel points in the gray level image of the road surface; taking the difference value of the fuzzy value and the fuzzy threshold value of each pixel point as the fuzzy difference degree of each pixel point;
obtaining the edge parameters of each pixel point according to the fuzzy difference degree and the characteristic adjustment value of the pixel point;
the method for acquiring the characteristic adjustment value comprises the following steps:
calculating the average value of the blurring degree of all pixel points in the gray level image of the road surface to obtain the average blurring degree, and carrying out negative correlation mapping on the average blurring degree to obtain a characteristic adjustment value;
the expression of the edge parameter is as follows:
the method comprises the steps of carrying out a first treatment on the surface of the In (1) the->Denoted as +.>Edge parameters of individual pixels, +.>Denoted as +.>Blur degree of each pixel, +.>Characteristic adjustment value expressed as a gray-scale image of the road surface, for example>Expressed as an exponential function with a base of natural constant;
the method for acquiring the road crack edge image comprises the following steps:
when the edge parameter of the pixel point is larger than a preset first threshold value and smaller than a preset second threshold value, setting the gray value of the corresponding pixel point as a first parameter; the preset first threshold value is smaller than the preset second threshold value;
setting the gray values of the rest pixel points as second parameters to obtain a road crack edge image; the first parameter is different from the second parameter.
2. The road construction crack defect evaluation detection method according to claim 1, wherein the method for obtaining the degree of blurring comprises:
the ratio of the blur value of each pixel point to the corresponding gray value in the road surface gray image is taken as the blur degree of each pixel point.
3. The road construction crack defect evaluation detection method according to claim 1, wherein the obtaining method of the blur threshold value comprises:
acquiring edge pixel points in a road surface gray level image;
calculating the average value of gray values of all edge pixel points to be used as an edge average value; calculating the average value of the blurring degree of all the edge pixel points to obtain the edge blurring degree; taking the product of the edge average value and the edge ambiguity as an upper ambiguity threshold value of the road surface gray level image;
calculating the average value of gray values of all non-edge pixel points in the gray image of the road surface, and taking the average value as a pixel average value; calculating the average value of the blurring degree of all the non-edge pixel points to obtain the pixel blurring degree; taking the product of the pixel average value and the pixel ambiguity as a fuzzy lower threshold value of the road surface gray level image;
and taking the average value of the blurring lower threshold value and the blurring upper threshold value of the road surface gray level image as the blurring threshold value of the road surface gray level image.
4. The method for evaluating and detecting a crack defect in a road construction according to claim 1, wherein the step of evaluating the crack defect by using an image of an edge of the road crack comprises:
counting the number of edge pixel points in the road crack edge image to obtain the crack edge quantity; taking the ratio of the crack edge quantity to the total quantity of all pixel points as an evaluation index;
when the evaluation index is smaller than or equal to a preset crack threshold value, marking the corresponding road surface as qualified; and when the evaluation index is larger than the preset crack threshold value, marking the corresponding road surface as unqualified.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311412671.4A CN117152135B (en) | 2023-10-30 | 2023-10-30 | Road construction crack defect evaluation and detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311412671.4A CN117152135B (en) | 2023-10-30 | 2023-10-30 | Road construction crack defect evaluation and detection method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117152135A CN117152135A (en) | 2023-12-01 |
| CN117152135B true CN117152135B (en) | 2024-01-23 |
Family
ID=88910379
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311412671.4A Active CN117152135B (en) | 2023-10-30 | 2023-10-30 | Road construction crack defect evaluation and detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117152135B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117787561B (en) * | 2024-01-02 | 2024-06-21 | 国网浙江省电力有限公司杭州供电公司 | Power supply reliability assessment method and system |
| CN117541615B (en) * | 2024-01-09 | 2024-04-26 | 山东济矿鲁能煤电股份有限公司阳城煤矿 | Bolt loosening detection method of automatic lapping device |
| CN118052824B (en) * | 2024-04-16 | 2024-06-28 | 济宁丰玺生物材料有限公司 | Rice hull degradable cutlery box defect detection method |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103226826A (en) * | 2013-03-20 | 2013-07-31 | 西安电子科技大学 | Method for detecting changes of remote sensing image of visual attention model based on local entropy |
| CN104637064A (en) * | 2015-02-28 | 2015-05-20 | 中国科学院光电技术研究所 | Defocus blurred image definition detection method based on edge intensity weight |
| CN105139392A (en) * | 2015-08-18 | 2015-12-09 | 昆明理工大学 | Improved fuzzy inference rule edge detection method |
| CN109035158A (en) * | 2018-06-25 | 2018-12-18 | 东软集团股份有限公司 | Image fuzzy processing method, device, storage medium and electronic equipment |
| CN112215764A (en) * | 2020-09-02 | 2021-01-12 | 佛山科学技术学院 | Image processing method based on median filtering improved algorithm |
| KR102385087B1 (en) * | 2020-12-29 | 2022-04-12 | 경희대학교 산학협력단 | Method for latency minimization in a fuzzy-based mobile edge orchestrator and system using same |
| CN114972333A (en) * | 2022-07-19 | 2022-08-30 | 淄博市淄川区市政环卫服务中心 | Road crack detection method and system based on artificial intelligence |
| CN116740072A (en) * | 2023-08-15 | 2023-09-12 | 安徽省云鹏工程项目管理有限公司 | Road surface defect detection method and system based on machine vision |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111583157B (en) * | 2020-05-13 | 2023-06-02 | 杭州睿琪软件有限公司 | Image processing method, system and computer readable storage medium |
-
2023
- 2023-10-30 CN CN202311412671.4A patent/CN117152135B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103226826A (en) * | 2013-03-20 | 2013-07-31 | 西安电子科技大学 | Method for detecting changes of remote sensing image of visual attention model based on local entropy |
| CN104637064A (en) * | 2015-02-28 | 2015-05-20 | 中国科学院光电技术研究所 | Defocus blurred image definition detection method based on edge intensity weight |
| CN105139392A (en) * | 2015-08-18 | 2015-12-09 | 昆明理工大学 | Improved fuzzy inference rule edge detection method |
| CN109035158A (en) * | 2018-06-25 | 2018-12-18 | 东软集团股份有限公司 | Image fuzzy processing method, device, storage medium and electronic equipment |
| CN112215764A (en) * | 2020-09-02 | 2021-01-12 | 佛山科学技术学院 | Image processing method based on median filtering improved algorithm |
| KR102385087B1 (en) * | 2020-12-29 | 2022-04-12 | 경희대학교 산학협력단 | Method for latency minimization in a fuzzy-based mobile edge orchestrator and system using same |
| CN114972333A (en) * | 2022-07-19 | 2022-08-30 | 淄博市淄川区市政环卫服务中心 | Road crack detection method and system based on artificial intelligence |
| CN116740072A (en) * | 2023-08-15 | 2023-09-12 | 安徽省云鹏工程项目管理有限公司 | Road surface defect detection method and system based on machine vision |
Non-Patent Citations (3)
| Title |
|---|
| Edge Detection in Digital Images Using Fuzzy Logic Technique;Abdallah A. Alshennawy, and Ayman A. Aly;《World Academy of Science, Engineering and Technology International Journal of Computer and Information Engineering 》;第3卷(第3期);第540-548页 * |
| 一种新型的自适应模糊中值滤波算法;曾宪佑， 黄佐华;《计算机工程与应用》;第50卷(第17期);第134-136页 * |
| 基于模糊元胞自动机的图像边缘检测方法;张珂 等;《北京联合大学学报（自然科学版）》;第22卷(第3期);第49-54页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117152135A (en) | 2023-12-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117152135B (en) | Road construction crack defect evaluation and detection method | |
| CN114937055B (en) | Image self-adaptive segmentation method and system based on artificial intelligence | |
| CN106780486B (en) | Steel plate surface defect image extraction method | |
| CN115829883A (en) | Surface image denoising method for dissimilar metal structural member | |
| CN114387273B (en) | Environmental dust concentration detection method and system based on computer image recognition | |
| CN116452598B (en) | Axle production quality rapid detection method and system based on computer vision | |
| CN110288618B (en) | Multi-target segmentation method for uneven-illumination image | |
| CN114881915A (en) | Symmetry-based mobile phone glass cover plate window area defect detection method | |
| CN116630813B (en) | Highway road surface construction quality intelligent detection system | |
| CN116990323B (en) | High-precision printing plate visual detection system | |
| CN116883408B (en) | Integrating instrument shell defect detection method based on artificial intelligence | |
| CN117437219B (en) | Magnetic glue inductance irregular appearance defect detection method based on computer vision | |
| CN114549441A (en) | Sucker defect detection method based on image processing | |
| CN115909256B (en) | Road disease detection method based on road visual image | |
| CN114792316A (en) | Method for detecting spot welding defects of bottom plate of disc brake shaft | |
| CN117094975A (en) | Method and device for detecting surface defects of steel and electronic equipment | |
| CN117808799B (en) | Chamfering equipment processing quality detection method based on artificial intelligence | |
| CN117830139B (en) | High-strength stamping part defect detection method | |
| CN116485719A (en) | Self-adaptive canny method for crack detection | |
| CN115346126A (en) | Side slope crack identification method | |
| CN108805854B (en) | Method for rapidly counting tablets and detecting completeness of tablets in complex environment | |
| CN110765887A (en) | Automatic identification technology and detection method for tunnel lining cracks | |
| CN116664584B (en) | Intelligent feedback regulating system for production of thin-wall zinc alloy die casting die | |
| CN109272462B (en) | Image self-correction method, device and storage device suitable for metal workpiece identification | |
| CN116740065B (en) | Quick tracing method and system for defective products of artificial board based on big data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |