CN117094703B - Road network maintenance sequence determining method for road cracks - Google Patents

Road network maintenance sequence determining method for road cracks Download PDF

Info

Publication number
CN117094703B
CN117094703B CN202311336922.5A CN202311336922A CN117094703B CN 117094703 B CN117094703 B CN 117094703B CN 202311336922 A CN202311336922 A CN 202311336922A CN 117094703 B CN117094703 B CN 117094703B
Authority
CN
China
Prior art keywords
image
crack
road
cracks
change rate
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
Application number
CN202311336922.5A
Other languages
Chinese (zh)
Other versions
CN117094703A (en
Inventor
杨宇星
陈振武
贾磊
孟安鑫
安茹
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Urban Transport Planning Center Co Ltd
Original Assignee
Shenzhen Urban Transport Planning Center Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shenzhen Urban Transport Planning Center Co Ltd filed Critical Shenzhen Urban Transport Planning Center Co Ltd
Priority to CN202311336922.5A priority Critical patent/CN117094703B/en
Publication of CN117094703A publication Critical patent/CN117094703A/en
Application granted granted Critical
Publication of CN117094703B publication Critical patent/CN117094703B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/20—Administration of product repair or maintenance
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/0464—Convolutional networks [CNN, ConvNet]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/048—Activation functions
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
    • G06Q10/06316—Sequencing of tasks or work
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G06Q10/06395—Quality analysis or management
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/08—Construction
    • 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
    • G06T7/60—Analysis of geometric attributes
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/90—Determination of colour characteristics
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/28—Quantising the image, e.g. histogram thresholding for discrimination between background and foreground patterns
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/10—Terrestrial scenes
    • G06V20/176—Urban or other man-made structures
    • 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
    • G06T2207/10—Image acquisition modality
    • G06T2207/10004—Still image; Photographic image
    • 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
    • G06T2207/10—Image acquisition modality
    • G06T2207/10024—Color image
    • 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
    • G06T2207/30108—Industrial image inspection
    • G06T2207/30132—Masonry; Concrete
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V2201/00—Indexing scheme relating to image or video recognition or understanding
    • G06V2201/06—Recognition of objects for industrial automation

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Human Resources & Organizations (AREA)
  • Economics (AREA)
  • Strategic Management (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Tourism & Hospitality (AREA)
  • Marketing (AREA)
  • Software Systems (AREA)
  • Computing Systems (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Quality & Reliability (AREA)
  • Artificial Intelligence (AREA)
  • General Business, Economics & Management (AREA)
  • Operations Research (AREA)
  • Multimedia (AREA)
  • Data Mining & Analysis (AREA)
  • Educational Administration (AREA)
  • Mathematical Physics (AREA)
  • General Engineering & Computer Science (AREA)
  • Development Economics (AREA)
  • Molecular Biology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Game Theory and Decision Science (AREA)
  • Primary Health Care (AREA)
  • Geometry (AREA)
  • Medical Informatics (AREA)
  • Databases & Information Systems (AREA)
  • Road Repair (AREA)

Abstract

The invention provides a road network maintenance sequence determining method for road cracks, and belongs to the technical field of maintenance sequence determining methods. Comprising the following steps: s1, collecting a pavement image, and identifying and extracting a crack image to obtain a binarized image; s2, converting the binarized image into a coordinate system, splitting the coordinate system into a plurality of combinations of sine functions and cosine functions, obtaining energy distribution of a crack image, and analyzing the crack energy of the road surface; s3, determining pavement crack state evaluation indexes of cracks; s4, determining the road maintenance sequence according to the road surface crack state evaluation indexes of the cracks. The problem that the optimization of the decision effect is difficult to ensure by manually deciding according to the information such as the length and the width of the crack or directly adopting the history decision is solved. The road network maintenance sequence determination for the road cracks is realized, the maintenance priority sequences of different road sections are determined through investigation, analysis and evaluation of road crack diseases, maintenance resources are reasonably configured, and the maintenance efficiency and quality are improved.

Description

Road network maintenance sequence determining method for road cracks
Technical Field
The application relates to a maintenance sequence determining method, in particular to a road network maintenance sequence determining method facing to road cracks, and belongs to the technical field of maintenance sequence determining methods.
Background
The road network is a road system which is formed by mutually connecting and interweaving various roads in a certain area to form a net-shaped distribution, and the formation and development of the road network are closely related to the politics, economy, production and living development of cities. Therefore, maintenance of the service performance state of the road in the road network is an important task of road maintenance.
Among pavement defects, the earliest cracks occur in the largest number, with the whole life of the road, and are aggravated as the road age increases. The damage of the road cracks not only affects the beautiful appearance of the road and the comfort level of driving, but also is easier to further expand if the cracks are not timely sealed and repaired, so that rainwater and other sundries enter the surface layer structure and the roadbed along the cracks, structural damage is caused to the road, the bearing capacity of the road is reduced, the local or sheet damage of the road is accelerated, and the service life of the road is shortened.
At present, in the road network oriented crack maintenance decision process, maintenance decision is usually performed manually according to the information such as the crack length, the crack width and the like, or by directly adopting a historical decision scheme. The method has strong subjectivity and is difficult to ensure the optimization of decision effect. The road service environment is relatively complex, and for professional technicians, the dimension and energy information of cracks are fully considered through industrial knowledge and experience accumulation, the distribution of the cracks in the road network is comprehensively considered, and the scientificity of road maintenance decision is improved.
Disclosure of Invention
The following presents a simplified summary of the invention in order to provide a basic understanding of some aspects of the invention. It should be understood that this summary is not an exhaustive overview of the invention. It is not intended to identify key or critical elements of the invention or to delineate the scope of the invention. Its purpose is to present some concepts in a simplified form as a prelude to the more detailed description that is discussed later.
In view of the above, in order to solve the technical problems in the prior art, the invention provides a road network maintenance sequence determining method for road cracks, and provides a comprehensive evaluation index for crack maintenance decision in a road network and a crack maintenance comprehensive decision method for the road network, which solve the problems in the prior art.
The first scheme is a road network maintenance sequence determining method facing to road cracks, which comprises the following steps:
s1, collecting a pavement image, and identifying and extracting a crack image to obtain a binarized image;
s2, converting the binarized image into a coordinate system, splitting the coordinate system into a plurality of combinations of sine functions and cosine functions, obtaining energy distribution of a crack image, and analyzing the crack energy of the road surface;
s3, determining pavement crack state evaluation indexes of cracks;
s4, determining the road maintenance sequence according to the road surface crack state evaluation indexes of the cracks.
Preferably, the method for collecting the pavement image and identifying and extracting the crack image comprises the following steps:
s11, acquiring a road surface image by adopting a way that a road detection vehicle is carried with an industrial camera;
s12, identifying images containing cracks by using a neural network, and sequentially encoding the images into A1-An, wherein n is the total number of the images containing the cracks;
s13, converting the RGB image into a gray image; the method for converting the RGB image into the gray scale image comprises the following steps: extracting the numerical values of three channels of an RGB image in R, G, B, sequentially marking the numerical values as a, b and c, and calculating an image gray value d by adopting the following formula in combination with the relation between a color image and a gray image determined by a psychological formula:
；
s14, distinguishing a linear crack region and a background region of the gray level image to obtain a new binarized image, sequentially encoding the binarized image into F1-Fn, wherein n is the total number of the images containing the linear crack, and the method comprises the following steps:
s141, counting all image pixel values, determining a distribution range of the pixel values, wherein the minimum value is recorded as dmin, the maximum value is recorded as dmax, and the pixel distribution range is (dmin, dmax);
s142, setting a gray value threshold dt, and dividing a pixel distribution range into two sections by taking the gray value threshold dt as an initial critical point: c-interval (dmin, dt) and D-interval (dt, dmax), counting the number of pixels n1 and n2 in the range of the C-interval and D-interval, calculating C, D weights E1 and E2 of the number of pixels in the whole image in the two intervals, calculating average pixel values dc1 and dd2 in the two intervals, and calculating C, D interval image pixel variance E:
；
the gray value threshold dt is in the range of [ dmin, dmax ], and the pixel increasing step length is 1 pixel;
s143, traversing all gray value thresholds dt to sequentially obtain pixel variances of the C, D interval images, recording the maximum value Emax in the variances, wherein the gray value threshold dt corresponding to the variances is a critical pixel value of a linear crack image background and a linear crack region, and the gray value threshold corresponding to the linear crack image background and the critical pixel value of the linear crack region is recorded as a final gray value threshold dtm;
s144, taking a final gray value threshold dtm as a final demarcation point, dividing the image into a binary image consisting of pixel values 0 and 1, wherein all pixel points with gray values smaller than dtm become 0; and (3) the pixel point with the gray value larger than or equal to dtm is changed to 1, so that a new binarized image is obtained, the binarized images are sequentially encoded into F1-Fn, and n is the total number of images containing cracks.
Preferably, the binary image is converted into a coordinate system, split into a plurality of combinations of sine functions and cosine functions, the energy distribution of the crack image is obtained, and the pavement crack energy is analyzed, and the method comprises the following steps:
s21, converting the binary image into a coordinate system: establishing a coordinate system by taking an upper left corner point of an image as a coordinate origin, taking a horizontal right direction as an x-axis positive direction, taking a vertical downward direction as a y-axis positive direction, and marking an image matrix formed by the binarized image as g (x, y);
s22, splitting the binarized image into a plurality of sine functions and cosine functions, and splitting the binarized image into a plurality of sums of sine functions and cosine functions with known frequencies and amplitudes;
s23, obtaining energy distribution of crack images, and analyzing energy magnitudes corresponding to different frequency functions.
Preferably, the binary image is split into a sum of a plurality of sine and cosine functions with known frequencies and amplitudes, and the solving method is as follows:
；
wherein J is an imaginary unit, e=0, 1,2, …, J-1, f=0, 1,2, …, K-1; j is an image matrixThe number of pixels in the x-axis direction, K is the image matrix +.>The number of pixels along the y-axis; JS is the angular frequency in the x-direction and KS is the angular frequency in the y-direction.
Preferably, the energy distribution of the crack image is obtained, and the method for analyzing the energy corresponding to different frequency functions is as follows: the energy distribution of the image in one periodic signal is calculated as follows:
；
wherein L is the x-direction image signal period, and M is the y-direction image signal period;
the energy value corresponding to each frequency is the energy distribution of the crack image, the i-th frequency is recorded as Pi, the energy corresponding to the i-th frequency is recorded as Hi, and the number of frequencies in the image is recorded as h; the average energy index Ha of the crack is proposed:
；
the average energy index of the crack represents the energy of the crack of the pavement in the image, and the larger the energy is, the larger the severity is, and the greater the potential of the crack for further expansion is.
Preferably, the method for determining the pavement crack state evaluation index of the crack is as follows:
the pavement crack state evaluation indexes of the crack comprise crack length S, width T, average crack energy Ha, length change rate Sv, width change rate Tv and average energy change rate Hav;
the length change rate Sv, the width change rate Tv, and the average energy change rate Hav are determined from the fracture length S, the width T, and the fracture average energy Ha;
the method of calculating the corresponding length change rate Sv, width change rate Tv, and average energy change rate Hav between times t1 and t2 is as follows:
；
；
；
in the formula, st2 and St1 are the lengths of the cracks corresponding to the times t2 and t1 respectively; tt2 and Tt1 are crack widths corresponding to times t2 and t1, respectively; hat2 and Hat1 are average energies of cracks corresponding to times t2 and t1, respectively.
Preferably, the method for determining the road maintenance sequence according to the road surface crack state evaluation index of the crack comprises the following steps:
s41, quantifying the importance degree of different indexes relative to road maintenance by using numerical values: the quantization range is 1-9,1 represents unimportant, 9 represents very important, 2-8 represents between unimportant and very important, and 2-8 are arranged in sequence; constructing an evaluation index importance matrix, and marking as：
；
In the method, in the process of the invention,the importance degree of the ith index relative to the jth index is respectively taken as a value of 1-9, wherein the average energy of the crack, the length, the width, the average energy of the crack, the length change rate and the average energy change rate of the width change rate are sequentially encoded into 1-6;
s42, solving a feature vector of the maximum feature value of the importance matrix of the evaluation index: solving forMaximum characteristic value +.>Further solving the maximum eigenvalue of the importance matrix of the obtained evaluation index>Feature vector +.>Feature vector of maximum feature value of evaluation index importance matrix>The relative importance of the fracture length, width, average fracture energy, length change rate, width change rate, and average energy change rate is characterized;
s43, constructing a road weight matrix: comparing the selected nn roads according to each index, wherein the road codes in the road network are RN1, RN2, … and RNnn, and nn is the number of the roads to be maintained in the road network; constructing a road weight matrixThe following are provided:
；
in the method, in the process of the invention,the pointer is used for indicating the importance degree of the crack length, i road relative to j road, wherein i and j are respectively 1-nn;
s44, repeating S43, and establishing each road weight matrix of width, average energy of cracks, length change rate, width change rate and average energy change rate、/>、/>、/>、/>；
S45, respectively solving weight matrixes、/>、/>、/>、/>、/>Maximum eigenvalue of (2), and weight matrix corresponding to the maximum eigenvalue +.>、/>、/>、/>、/>、/>And combined into a weight matrix of the whole index>：
；
S46, based on feature vectorsAnd weight matrix->Constructing a ranking matrix->：
；
Will beThe elements of the method are developed as follows:
；
in the method, in the process of the invention,refers to the degree of importance of the ith road for maintenance.
The second scheme is an electronic device, which comprises a memory and a processor, wherein the memory stores a computer program, and the processor realizes the first scheme of the road network maintenance sequence determining method facing the road cracks when executing the computer program.
A third aspect is a computer readable storage medium, on which a computer program is stored, where the computer program when executed by a processor implements a road network maintenance sequence determining method for a road crack according to the first aspect.
The beneficial effects of the invention are as follows: the road network maintenance sequence determining method and device for the road cracks achieve road network maintenance sequence determining for the road cracks. The maintenance priority sequence of different road sections can be determined through investigation, analysis and evaluation of road crack diseases, maintenance resources are reasonably configured, maintenance efficiency and quality are improved, decisions are scientifically made, interference of human subjective factors is avoided, accuracy and rationality of decisions are improved, and the purposes of saving maintenance cost and prolonging the service life of a road are achieved. The invention can be used for quantitative analysis of road crack distribution states of complex environments, large-scale road networks and the like, and improves the scientificity and accuracy of maintenance decisions.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiments of the application and together with the description serve to explain the application and do not constitute an undue limitation to the application. In the drawings:
FIG. 1 is a schematic flow chart of a road network maintenance sequence determination method for road cracks;
fig. 2 is a schematic flow chart of S2.
Detailed Description
In order to make the technical solutions and advantages of the embodiments of the present application more apparent, the following detailed description of exemplary embodiments of the present application is given with reference to the accompanying drawings, and it is apparent that the described embodiments are only some of the embodiments of the present application and not exhaustive of all the embodiments. It should be noted that, in the case of no conflict, the embodiments and features in the embodiments may be combined with each other.
Example 1, the present embodiment will be described with reference to fig. 1 to 2, which is a road network maintenance order determining method for a road crack, comprising the steps of:
s1, collecting a pavement image, identifying and extracting a crack image to obtain a binarized image, wherein the method comprises the following steps of:
s11, acquiring a road surface image by adopting a way that a road detection vehicle is carried with an industrial camera;
s12, identifying images containing cracks by using a neural network, and sequentially encoding the images into A1-An, wherein n is the total number of the images containing the cracks;
specifically, a conventional convolutional neural network is selected for the algorithm, a pavement crack data set is firstly selected for training a model, and all parameters in the model are determined, wherein the parameters comprise the number of network layers, the number of neuron nodes of each layer, the learning rate, the weight, the bias, the activation function, the loss function, the convolutional kernel and the like. Performing intelligent recognition on the images by adopting a trained convolutional neural network model, extracting images which all contain cracks, wherein the images are sequentially encoded into A1-An, and n is the total number of images containing the cracks;
s13, converting the RGB image into a gray image; in the process of image processing, the difficulty is high, so that the RGB image is converted into a gray image for processing: extracting the numerical values of three channels of an RGB image in R, G, B, sequentially marking the numerical values as a, b and c, and calculating an image gray value d by adopting the following formula in combination with the relation between a color image and a gray image determined by a psychological formula:
；
s14, distinguishing a crack region from a background region in order to eliminate the interference of the background, and dividing the two partial regions by determining a pixel gray value threshold dt of the crack region and the background region;
specifically, the gray level image is distinguished from the linear crack area and the background area to obtain a new binarized image, the binarized image is sequentially encoded into F1-Fn, and n is the total number of the images containing the linear crack, and the method comprises the following steps:
s141, counting all image pixel values, determining a distribution range of the pixel values, wherein the minimum value is recorded as dmin, the maximum value is recorded as dmax, and the pixel distribution range is (dmin, dmax);
s142, setting a gray value threshold dt, and dividing a pixel distribution range into two sections by taking the gray value threshold dt as an initial critical point: c-interval (dmin, dt) and D-interval (dt, dmax), counting the number of pixels n1 and n2 in the range of the C-interval and D-interval, calculating C, D weights E1 and E2 of the number of pixels in the whole image in the two intervals, calculating average pixel values dc1 and dd2 in the two intervals, and calculating C, D interval image pixel variance E:
；
the gray value threshold dt is in the range of [ dmin, dmax ], and the pixel increasing step length is 1 pixel;
s143, traversing all gray value thresholds dt to sequentially obtain pixel variances of the C, D interval images, recording the maximum value Emax in the variances, wherein the gray value threshold dt corresponding to the variances is a critical pixel value of a linear crack image background and a linear crack region, and the gray value threshold corresponding to the linear crack image background and the critical pixel value of the linear crack region is recorded as a final gray value threshold dtm;
s144, dividing the image into a binary image consisting of pixel values 0 and 1 by taking a final gray value threshold dtm as a final demarcation point, wherein all pixel points with gray values smaller than dtm become 0; and (3) the pixel point with the gray value larger than or equal to dtm is changed to 1, so that a new binarized image is obtained, the binarized images are sequentially encoded into F1-Fn, and n is the total number of images containing cracks.
S2, splitting the two-dimensional image into a plurality of sine functions and cosine functions, and converting the sine functions and the cosine functions into complex exponential functions for expression based on Euler formulas for convenience. For sine and cosine functions, it is most important to determine the frequency, amplitude of the function;
specifically, the binary image is converted into a coordinate system, split into a plurality of combinations of sine functions and cosine functions, the energy distribution of the crack image is obtained, and the pavement crack energy is analyzed, and the method comprises the following steps:
s21, converting the binary image into a coordinate system: establishing a coordinate system by taking an upper left corner point of an image as a coordinate origin, taking a horizontal right direction as an x-axis positive direction, taking a vertical downward direction as a y-axis positive direction, and marking an image matrix formed by the binarized image as g (x, y);
s22, splitting the binary image into a plurality of sine functions and cosine functions, splitting the binary image into a plurality of sums of sine functions and cosine functions with known frequencies and amplitudes, and solving the problems that:
；
wherein J is an imaginary unit, e=0, 1,2, …, J-1, f=0, 1,2, …, K-1; j is an image matrixAlong the x-axisThe number of pixels in the direction, K is the image matrix +.>The number of pixels along the y-axis; JS is the angular frequency in the x-direction and KS is the angular frequency in the y-direction.
S23, a binary image of the crack is composed of sine functions and cosine functions of a plurality of frequencies and amplitudes, so that the energy magnitudes corresponding to different frequency functions are analyzed next. In the analysis process, in order to ensure that the image signal energy calculation has a solution, one period of a function is selected for analysis;
specifically, the energy distribution of the crack image is obtained, and the energy corresponding to different frequency functions is analyzed, wherein the method comprises the following steps: the energy distribution of the image in one periodic signal is calculated as follows:
；
wherein L is the x-direction image signal period, and M is the y-direction image signal period;
the energy value corresponding to each frequency is the energy distribution of the crack image, the i-th frequency is recorded as Pi, the energy corresponding to the i-th frequency is recorded as Hi, and the number of frequencies in the image is recorded as h; the average energy index Ha of the crack is proposed:
；
in the image represented by the average energy index of the crack, the larger the energy of the crack on the road surface is, the larger the severity is, the greater the potential of further expanding the crack is, and the important attention is needed in maintenance. Meanwhile, in the road maintenance decision process, the energy of the pavement cracks can be combined, the maintenance scheme is optimized, the maintenance cost is reasonably planned, and the maintenance quality is improved.
S3, in a maintenance decision scheme for the road crack, static information such as the length, the width and the average energy of an image of the crack cannot be considered, and the change condition of the information along with time needs to be considered simultaneously, so that the road crack state evaluation index of the crack is determined, and the method comprises the following steps:
the pavement crack state evaluation indexes of the crack comprise crack length S, width T, average crack energy Ha, length change rate Sv, width change rate Tv and average energy change rate Hav;
the length change rate Sv, the width change rate Tv, and the average energy change rate Hav are determined from the fracture length S, the width T, and the fracture average energy Ha;
the method of calculating the corresponding length change rate Sv, width change rate Tv, and average energy change rate Hav between times t1 and t2 is as follows:
；
；
；
in the formula, st2 and St1 are the lengths of the cracks corresponding to the times t2 and t1 respectively; tt2 and Tt1 are crack widths corresponding to times t2 and t1, respectively; hat2 and Hat1 are average energies of cracks corresponding to times t2 and t1, respectively.
Specifically, the method for calculating the length and width of the crack may be:
1) Collecting road surface images by adopting a way that a road detection vehicle carries an industrial camera;
2) And identifying pavement cracks by adopting a convolutional neural network intelligent identification algorithm. And then extracting a crack region by adopting an image binarization method.
3) And (3) finding four corner coordinates of the crack according to the extracted crack region, and determining the length S and the width T of the crack through the distance between the coordinates.
S4, determining a road maintenance sequence according to the road surface crack state evaluation index of the crack, wherein the method comprises the following steps:
s41, quantifying the importance degree of different indexes relative to road maintenance by using numerical values: the quantization range is 1-9,1 is not important, 9 is very important, 2-
8 represents a sequence ranging from unimportant to very important, 2-8; constructing an evaluation index importance matrix, and marking as：
；
In the method, in the process of the invention,the importance degree of the ith index relative to the jth index is respectively taken as a value of 1-9, wherein the average energy of the crack, the length, the width, the average energy of the crack, the length change rate and the average energy change rate of the width change rate are sequentially encoded into 1-6;
s42, solving a feature vector of the maximum feature value of the importance matrix of the evaluation index: solving forMaximum characteristic value +.>Further solving the maximum eigenvalue of the importance matrix of the obtained evaluation index>Feature vector +.>Feature vector of maximum feature value of evaluation index importance matrix>The relative importance of the fracture length, width, average fracture energy, length change rate, width change rate, and average energy change rate is characterized;
s43, for each index, selecting n to further improve the effectiveness of the comparison resultComparing n roads; thus, a road weight matrix is constructed: comparing the selected nn roads according to each index, wherein the road codes in the road network are RN1, RN2, … and RNnn, and nn is the number of the roads to be maintained in the road network; constructing a road weight matrixThe following are provided:
；
in the method, in the process of the invention,the pointer is used for indicating the importance degree of the crack length, i road relative to j road, wherein i and j are respectively 1-nn;
s44, repeating S43, and establishing each road weight matrix of width, average energy of cracks, length change rate, width change rate and average energy change rate、/>、/>、/>、/>；
S45, respectively solving a weight matrix in order to obtain the weight corresponding to each road in all indexes、/>、、/>、/>、/>Maximum eigenvalue of (2), and weight matrix corresponding to the maximum eigenvalue +.>、/>、/>、/>、/>、/>And combined into a weight matrix of the whole index>：
；
S46, based on feature vectorsAnd weight matrix->Constructing a ranking matrix->：
；
Will beThe elements of the method are developed as follows:
；
in the method, in the process of the invention,refers to the degree of importance of the ith road for maintenance. />The greater the value, the higher the maintenance level, the more the need for priority maintenance. Thus, by comparison->And (3) determining the priority and the sequence of maintenance and repair of all roads in the road network.
The earliest and most numerous pavement cracks occur during the road operation process, with the whole life of the road and aggravating as the age of the road increases. In the road-oriented maintenance decision process, a road network-level maintenance decision is often encountered, and at present, comprehensive analysis indexes about the road network-level crack maintenance decision are lacked; the method comprehensively considers the information such as the crack length, the crack width, the crack energy and the like, and firstly identifies the pavement crack based on an intelligent identification algorithm; then, in order to improve the processing efficiency of the crack image, converting the pavement crack RGB image into a gray scale image; the pixel gray value threshold determining method is provided, a crack image is divided into a crack area and a background area, interference of background factors is eliminated, and characteristics of cracks are enhanced. Splitting the crack image into a combination of a sine function and a cosine function with frequency and amplitude characteristics based on the relation between the two-dimensional image and the sine function and the cosine function; and a crack energy analysis method is provided, and an average crack energy index is provided, so that the calculation of the pavement crack energy is realized. And providing indexes such as comprehensive crack length, width, average crack energy, length change rate, width change rate, average energy change rate and the like, and being used for guiding comprehensive maintenance of road cracks in a road network. The scientificity and the accuracy of maintenance decisions are improved, and the maintenance cost is reduced.
In embodiment 2, the computer device of the present invention may be a device including a processor and a memory, for example, a single chip microcomputer including a central processing unit. And the processor is used for realizing the steps of the road network maintenance sequence determining method facing the road cracks when executing the computer program stored in the memory.
The processor may be a central processing unit (Central Processing Unit, CPU), other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), off-the-shelf programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program (such as a sound playing function, an image playing function, etc.) required for at least one function, and the like; the storage data area may store data (such as audio data, phonebook, etc.) created according to the use of the handset, etc. In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as a hard disk, memory, plug-in hard disk, smart Media Card (SMC), secure Digital (SD) Card, flash Card (Flash Card), at least one disk storage device, flash memory device, or other volatile solid-state storage device.
Embodiment 3, computer-readable storage Medium embodiment
The computer readable storage medium of the present invention may be any form of storage medium that is read by a processor of a computer device, including but not limited to a nonvolatile memory, a volatile memory, a ferroelectric memory, etc., on which a computer program is stored, and when the processor of the computer device reads and executes the computer program stored in the memory, the steps of a road network maintenance order determining method for road cracks described above may be implemented.
The computer program comprises computer program code which may be in source code form, object code form, executable file or in some intermediate form, etc. The computer readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), an electrical carrier signal, a telecommunications signal, a software distribution medium, and so forth. It should be noted that the computer readable medium contains content that can be appropriately scaled according to the requirements of jurisdictions in which such content is subject to legislation and patent practice, such as in certain jurisdictions in which such content is subject to legislation and patent practice, the computer readable medium does not include electrical carrier signals and telecommunication signals.
While the invention has been described with respect to a limited number of embodiments, those skilled in the art, having benefit of the above description, will appreciate that other embodiments are contemplated within the scope of the invention as described herein. Furthermore, it should be noted that the language used in the specification has been principally selected for readability and instructional purposes, and may not have been selected to delineate or circumscribe the inventive subject matter. Accordingly, many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the appended claims. The disclosure of the present invention is intended to be illustrative, but not limiting, of the scope of the invention, which is defined by the appended claims.

Claims (5)

1. The road network maintenance sequence determining method for the road cracks is characterized by comprising the following steps of:
s1, collecting a pavement image, and identifying and extracting a crack image to obtain a binarized image;
s2, converting the binarized image into a coordinate system, splitting the coordinate system into a plurality of combinations of sine functions and cosine functions, obtaining energy distribution of a crack image, and analyzing the crack energy of the road surface, wherein the method comprises the following steps:
s21, converting the binary image into a coordinate system: establishing a coordinate system by taking an upper left corner point of an image as a coordinate origin, taking a horizontal right direction as an x-axis positive direction, taking a vertical downward direction as a y-axis positive direction, and marking an image matrix formed by the binarized image as g (x, y);
s22, splitting the binary image into a plurality of sine functions and cosine functions, and specifically splitting the binary image into a sum of a plurality of sine functions and cosine functions with known frequencies and amplitudes; the solving method is as follows:
；
wherein j is an imaginary unit; j is an image matrixThe number of pixels in the x-axis direction, K is the image matrix +.>The number of pixels along the y-axis;
s23, obtaining energy distribution of crack images, and analyzing energy magnitudes corresponding to different frequency functions, wherein the method comprises the following steps: the energy distribution of the image in one periodic signal is calculated as follows:
；
wherein L is the x-direction image signal period, and M is the y-direction image signal period;
the energy value corresponding to each frequency is the energy distribution of the crack image, the i-th frequency is recorded as Pi, the energy corresponding to the i-th frequency is recorded as Hi, and the number of frequencies in the image is recorded as h; the average energy index Ha of the crack is proposed:
；
in the image represented by the average energy index of the crack, the larger the energy of the crack on the road surface is, the larger the severity is, and the greater the potential of the crack for further expansion is;
s3, determining pavement crack state evaluation indexes of cracks;
s4, determining a road maintenance sequence according to the road surface crack state evaluation index of the crack, wherein the method comprises the following steps:
s41, quantifying the importance degree of different indexes relative to road maintenance by using numerical values: the quantization range is 1-9,1 represents unimportant, 9 represents very important, 2-8 represents between unimportant and very important, and 2-8 are arranged in sequence; constructing an evaluation index importance matrix, and marking as：
；
In the method, in the process of the invention,the importance degree of the o index relative to the s index is represented by the values of o and s respectively being 1-9, wherein the lengths, widths, average energy of the cracks, length change rate, width change rate and average energy change rate of the cracks are sequentially encoded to be 1-6;
s42, solving a feature vector of the maximum feature value of the importance matrix of the evaluation index: solving forMaximum characteristic value of (2)And then solveObtaining the maximum eigenvalue of the evaluation index importance matrix +.>Feature vector +.>Feature vector of maximum feature value of evaluation index importance matrix>The relative importance of the fracture length, width, average fracture energy, length change rate, width change rate, and average energy change rate is characterized;
s43, constructing a road weight matrix: comparing the selected nn roads according to each index, wherein the road codes in the road network are RN1, RN2, … and RNnn, and nn is the number of the roads to be maintained in the road network; constructing a road weight matrixThe following are provided:
；
in the method, in the process of the invention,the pointer is used for indicating the importance degree of the crack length, i road relative to j road, wherein i and j are respectively 1-nn;
s44, repeating S43, and establishing each road weight matrix of width, average energy of cracks, length change rate, width change rate and average energy change rate；
S45, respectively solving weight matrixesMaximum eigenvalue of (2), and weight matrix corresponding to the maximum eigenvalue +.>And combined into a weight matrix of the whole index>：
；
S46, based on feature vectorsAnd weight matrix->Constructing a ranking matrix->：
；
Will beThe elements of the method are developed as follows:
；
in the method, in the process of the invention,refers to the degree of importance of the ith road for maintenance.
2. The road network maintenance repair order determining method for road cracks according to claim 1, wherein the method for collecting road surface images, identifying and extracting the crack images comprises the following steps:
s11, acquiring a road surface image by adopting a way that a road detection vehicle is carried with an industrial camera;
s12, identifying images containing cracks by using a neural network, and sequentially encoding the images into A1-An, wherein n is the total number of the images containing the cracks;
s13, converting the RGB image into a gray image; the method for converting the RGB image into the gray scale image comprises the following steps: extracting the numerical values of three channels of an RGB image in R, G, B, sequentially marking the numerical values as a, b and c, and calculating an image gray value d by adopting the following formula in combination with the relation between a color image and a gray image determined by a psychological formula:
；
s14, distinguishing a linear crack region and a background region of the gray level image to obtain a new binarized image, and sequentially encoding the binarized image into F1-Fn, wherein the method comprises the following steps:
s141, counting all image pixel values, determining a distribution range of the pixel values, wherein the minimum value is recorded as dmin, the maximum value is recorded as dmax, and the pixel distribution range is (dmin, dmax);
s142, setting a gray value threshold dt, and dividing a pixel distribution range into two sections by taking the gray value threshold dt as an initial critical point: c interval (dmin, dt) and D interval (dt, dmax), count the number of pixels n1 and n2 in the C interval and D interval range, calculate C, D the weights E1 and E2 of the two interval pixel numbers in the whole image, calculate the average pixel values dc1 and dc2 of the two intervals, calculate C, D interval image pixel variance E:
；
the gray value threshold dt is in the range of [ dmin, dmax ], and the pixel increasing step length is 1 pixel;
s143, traversing all gray value thresholds dt to sequentially obtain pixel variances of the C, D interval images, recording the maximum value Emax in the variances, wherein the gray value threshold dt corresponding to the variances is a critical pixel value of a linear crack image background and a linear crack region, and the gray value threshold corresponding to the linear crack image background and the critical pixel value of the linear crack region is recorded as a final gray value threshold dtm;
s144, dividing the image into a binary image consisting of pixel values 0 and 1 by taking a final gray value threshold dtm as a final demarcation point, wherein the gray value is smaller than the pixel point of dtm, and the pixel values are all changed into 0; and (3) the pixel point with the gray value larger than or equal to dtm is changed to 1, so that a new binarized image is obtained, the binarized images are sequentially encoded into F1-Fn, and n is the total number of images containing cracks.
3. The road network maintenance repair order determining method for road cracks according to claim 2, wherein the method for determining the road crack state evaluation index of the crack is:
the pavement crack state evaluation indexes of the crack comprise crack length S, width T, average crack energy Ha, length change rate Sv, width change rate Tv and average energy change rate Hav;
the length change rate Sv, the width change rate Tv, and the average energy change rate Hav are determined from the fracture length S, the width T, and the fracture average energy Ha;
the method of calculating the corresponding length change rate Sv, width change rate Tv, and average energy change rate Hav between times t1 and t2 is as follows:
；
；
；
in the formula, st2 and St1 are the lengths of the cracks corresponding to the times t2 and t1 respectively; tt2 and Tt1 are crack widths corresponding to times t2 and t1, respectively; hat2 and Hat1 are average energies of cracks corresponding to times t2 and t1, respectively.
4. An electronic device comprising a memory and a processor, the memory storing a computer program, the processor implementing the steps of a road network maintenance sequence determination method for a road crack according to any one of claims 1-3 when executing the computer program.
5. A computer readable storage medium having stored thereon a computer program, wherein the computer program when executed by a processor implements a road network maintenance order determination method for road cracks according to any one of claims 1-3.
CN202311336922.5A 2023-10-17 2023-10-17 Road network maintenance sequence determining method for road cracks Active CN117094703B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202311336922.5A CN117094703B (en) 2023-10-17 2023-10-17 Road network maintenance sequence determining method for road cracks

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202311336922.5A CN117094703B (en) 2023-10-17 2023-10-17 Road network maintenance sequence determining method for road cracks

Publications (2)

Publication Number Publication Date
CN117094703A CN117094703A (en) 2023-11-21
CN117094703B true CN117094703B (en) 2024-03-26

Family

ID=88772031

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202311336922.5A Active CN117094703B (en) 2023-10-17 2023-10-17 Road network maintenance sequence determining method for road cracks

Country Status (1)

Country Link
CN (1) CN117094703B (en)

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110246130A (en) * 2019-06-21 2019-09-17 中国民航大学 Based on infrared and visible images data fusion airfield pavement crack detection method
CN110288137A (en) * 2019-06-11 2019-09-27 中国公路工程咨询集团有限公司 Road network grade road infrastructure structure composition Maintenance Decision making method and system
KR20190141322A (en) * 2018-06-14 2019-12-24 위프코 주식회사 Crack detection system of road surface using neural network and detection method therefor
CN112419250A (en) * 2020-11-13 2021-02-26 湖北工业大学 Pavement crack digital image extraction, crack repair and crack parameter calculation method
CN115393727A (en) * 2022-10-31 2022-11-25 深圳市城市交通规划设计研究中心股份有限公司 Pavement linear crack identification method, electronic equipment and storage medium
CN115841225A (en) * 2022-11-17 2023-03-24 华中科技大学 Road maintenance priority ranking method in road network
CN116206156A (en) * 2023-03-07 2023-06-02 长安大学 Pavement crack classification and identification method under shadow interference

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7587099B2 (en) * 2006-01-27 2009-09-08 Microsoft Corporation Region-based image denoising

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20190141322A (en) * 2018-06-14 2019-12-24 위프코 주식회사 Crack detection system of road surface using neural network and detection method therefor
CN110288137A (en) * 2019-06-11 2019-09-27 中国公路工程咨询集团有限公司 Road network grade road infrastructure structure composition Maintenance Decision making method and system
CN110246130A (en) * 2019-06-21 2019-09-17 中国民航大学 Based on infrared and visible images data fusion airfield pavement crack detection method
CN112419250A (en) * 2020-11-13 2021-02-26 湖北工业大学 Pavement crack digital image extraction, crack repair and crack parameter calculation method
CN115393727A (en) * 2022-10-31 2022-11-25 深圳市城市交通规划设计研究中心股份有限公司 Pavement linear crack identification method, electronic equipment and storage medium
CN115841225A (en) * 2022-11-17 2023-03-24 华中科技大学 Road maintenance priority ranking method in road network
CN116206156A (en) * 2023-03-07 2023-06-02 长安大学 Pavement crack classification and identification method under shadow interference

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
网级路面养护维修管理系统的设计;殷建军, 李晓明;西安公路交通大学学报(第01期);第1-7页 *

Also Published As

Publication number Publication date
CN117094703A (en) 2023-11-21

Similar Documents

Publication Publication Date Title
CN109936582B (en) Method and device for constructing malicious traffic detection model based on PU learning
Hoang Image Processing‐Based Spall Object Detection Using Gabor Filter, Texture Analysis, and Adaptive Moment Estimation (Adam) Optimized Logistic Regression Models
CN115393727B (en) Pavement linear crack identification method, electronic equipment and storage medium
CN111259444B (en) Track data label clustering method fusing privacy protection
Zhang et al. Efficient system of cracking-detection algorithms with 1-mm 3D-surface models and performance measures
CN112309126B (en) License plate detection method and device, electronic equipment and computer readable storage medium
CN111881243B (en) Taxi track hot spot area analysis method and system
CN117078738B (en) Linear crack width calculation method
WO2024139287A1 (en) Road disease prediction method and apparatus, electronic device and storage medium
CN111415336A (en) Image tampering identification method and device, server and storage medium
CN115100739A (en) Man-machine behavior detection method, system, terminal device and storage medium
CN108830302B (en) Image classification method, training method, classification prediction method and related device
CN114492590A (en) Boundary channel generation method and device based on track clustering
CN117094703B (en) Road network maintenance sequence determining method for road cracks
CN114283383A (en) Smart city highway maintenance method, computer equipment and medium
CN112200684B (en) Method, system and storage medium for detecting medical insurance fraud
CN117077453A (en) Road pavement service life assessment method, electronic equipment and storage medium
CN117078233B (en) Maintenance decision method based on road network maintenance comprehensive evaluation index
CN113158084A (en) Method and device for processing movement track data, computer equipment and storage medium
CN117115576B (en) Pavement crack energy analysis method based on image
CN115512098B (en) Bridge electronic inspection system and inspection method
CN117115665B (en) Static influence parameter analysis method based on pavement crack analysis method
CN116361974A (en) Data source importance discriminating method based on highway service and data network
CN116341059A (en) Tunnel intelligent design method based on similarity
CN117079062B (en) Dynamic and static influence parameter analysis method based on pavement crack analysis method

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