A real-time monitoring method for the construction quality of asphalt road projects

Abstract

The present invention relates to the technical field of engineering construction quality monitoring, and specifically discloses a method for real-time monitoring of the construction quality of asphalt roads, including the following steps: S1: Acquisition of asphalt road image information, S2: Extraction of asphalt road image features, S3: Monitoring and analysis of abnormal flatness of asphalt roads, S4: Monitoring and analysis of abnormal density of asphalt roads, S5: Monitoring and analysis of the construction quality of asphalt roads, and S6: Early warning of abnormal construction quality of asphalt roads; by extracting the image equalization feature information and the image density feature information, the present invention analyzes to obtain the road surface flatness balance coefficient and the road surface density evaluation coefficient, and further analyzes to obtain the construction quality evaluation index, comprehensively evaluates the construction quality, displays the monitoring results in real time and issues an early warning in case of abnormalities. By introducing image processing technology, the real-time monitoring and intelligent evaluation of construction quality are realized, the monitoring efficiency and accuracy are improved, and strong support is provided for the construction and management of road projects.

Description

Technical Field

[0001] The present invention relates to the technical field of engineering construction quality monitoring, and particularly to a method for real-time monitoring of the construction quality of asphalt road projects. Background Art

[0002] As an important part of the modern transportation network, the construction quality of asphalt roads is directly related to the service life of the road, driving safety, and maintenance costs. With the acceleration of urbanization and the continuous increase in traffic flow, the requirements for the construction quality of asphalt roads are also getting higher and higher. At the same time, the rapid development of technology has brought new opportunities for the monitoring of asphalt road construction quality. Image processing technology can quickly and accurately acquire and analyze a large amount of image information, providing strong technical support for the real-time monitoring of asphalt road construction quality. Through high-resolution image acquisition devices, characteristic information during the road construction process can be obtained, providing a rich data basis for subsequent quality assessment.

[0003] Traditional real-time monitoring methods for the construction quality of asphalt road projects mainly rely on manual inspection and sampling inspection. In terms of manual inspection, professional personnel evaluate the paving quality of asphalt mixtures through on-site inspections and means such as observation and touch; while sampling inspection is to regularly extract samples of asphalt mixtures and send them to the laboratory for physical and chemical property tests. In addition, for raw materials such as asphalt and aggregates, sampling is also used to send them to the laboratory to test performance indicators. During the construction process, tools such as levels and theodolites are also used to measure geometric parameters such as the flatness of the road surface. However, although these methods can reflect the construction quality to a certain extent, there are still many limitations.

[0004] Limitations of traditional real-time monitoring methods for the construction quality of asphalt road projects: First, the sampling inspection method is not only inefficient but also difficult to comprehensively and real-time reflect the true situation of the construction quality. Second, the quality judgment of manual inspection depends on the experience and subjective judgment of the inspectors, lacking objective and unified standards, which may lead to differences in the evaluation of the same construction section by different inspectors, affecting the accuracy of quality control. In addition, traditional methods lack convenient data recording means, making it difficult to trace and analyze the construction quality, which is not conducive to the continuous improvement and optimization of construction quality. Summary of the Invention

[0005] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a method for real-time monitoring of the construction quality of asphalt road projects to solve the problems raised in the above background art.

[0006] To achieve the above object, the present invention provides the following technical solutions: A method for real-time monitoring of the construction quality of asphalt roads, comprising the following steps: S1: Collection of asphalt road image information, S2: Extraction of asphalt road image features, S3: Monitoring and analysis of asphalt road flatness anomalies, S4: Monitoring and analysis of asphalt road compaction anomalies, S5: Monitoring and analysis of asphalt road construction quality, and S6: Early warning of asphalt road construction quality anomalies.

[0007] S1: Collection of asphalt road image information: Install a high-definition camera to capture the target area during the construction of the asphalt road, obtain the asphalt monitoring road surface image, and mark it as the first monitoring road surface image;

[0008] S2: Extraction of asphalt road image features: Perform preprocessing operations on the first monitoring road surface image to obtain the second monitoring road surface image, and extract the feature information of the asphalt road image based on the second monitoring road surface image. The feature information includes image equalization feature information and image density feature information;

[0009] S3: Monitoring and analysis of asphalt road flatness anomalies: Analyze the asphalt road flatness balance based on the image equalization feature information to obtain the road surface flatness balance coefficient of the asphalt road, and determine whether it is abnormal based on the road surface flatness balance coefficient. Send a warning message for the data with an abnormal judgment result;

[0010] S4: Monitoring and analysis of asphalt road compaction anomalies: Analyze the asphalt road compaction based on the image density feature information to obtain the road surface compaction evaluation coefficient of the asphalt road, and determine whether it is abnormal based on the road surface compaction evaluation coefficient. Send a warning message for the data with an abnormal judgment result;

[0011] S5: Monitoring and analysis of asphalt road construction quality: Analyze the construction quality of the asphalt road project based on the road surface flatness balance coefficient and the road surface compaction evaluation coefficient to obtain the construction quality evaluation index of the asphalt road, and perform quality assessment on it, and output the monitoring result of the asphalt road project construction quality;

[0012] S6: Early warning of asphalt road construction quality anomalies: Display the monitoring result of the asphalt road project construction quality on the visualization interface of the monitoring center in real time, and send an alarm message for abnormal data.

[0013] Preferably, the specific implementation method of the asphalt road image information collection is as follows:

[0014] Determine the asphalt construction road as the target monitoring area, capture the target monitoring area, obtain the asphalt monitoring road surface image, and divide the asphalt monitoring road surface image into n monitoring sub-areas, where i = 1, 2, 3,..., n, and i is the number of each monitoring sub-area.

[0015] Preferably, the specific implementation manner of preprocessing the first monitored road surface image is as follows:

[0016] Based on the obtained first monitored road surface image, the first monitored road surface image is preprocessed by a grayscale processing unit, a filtering and denoising processing unit, and a histogram equalization processing unit to obtain a second monitored road surface image.

[0017] Preferably, the image equalization degree feature information includes an image particle roundness factor and an image particle area dispersion degree, and the specific extraction implementation manner of the image equalization degree feature information is as follows:

[0018] In the first step, image segmentation technology is used to separate the particles from the background of the second monitored road surface image, and each particle is marked to obtain image particle marking points, and the image particle areas of each monitored sub-region are calculated. Pa i , and the calculation model is specifically: , where Pa i represents the image particle area of the i-th monitored sub-region, M represents the height of the image, N represents the width of the image, represents the pixel value of the image of the i-th monitored sub-region at the position ;

[0019] The second monitored road surface image is imported into an edge detection algorithm to identify the edge lines of each particle in the second monitored road surface image, and a curve is fitted to the image particle edge lines, and the length of the curve is calculated as the perimeter of the image particle edge lines. Lp ;

[0020] Read the image particle area Pa i of the i-th monitored sub-region and the perimeter Lp i of the image particle edge lines of the i-th monitored sub-region, and calculate the image particle roundness factor Prf i of the i-th monitored sub-region. The calculation model is specifically: , where represents pi;

[0021] In the second step, each image particle area is respectively marked as , m represents the total number of image particles, j = 1, 2, 3,..., m, and j is the number of each image particle;

[0022] Calculate the image particle area dispersion degree. The calculation model is specifically: , where Pdd iRepresents the discreteness of the image particle area in the i-th monitoring sub-region. Pa ij Represents the area of the j-th image particle in the i-th monitoring sub-region.

[0023] Preferably, the image density characteristic information includes the image road surface crack rate and the image road surface porosity rate. The specific extraction execution method of the image density characteristic information is as follows:

[0024] First step, import the second monitored road surface image into the edge detection algorithm to identify the crack edge lines in the second monitored road surface image. Use the threshold segmentation technique to convert the second monitored road surface image into a binary image, where the crack area is white and the background is black. Count the number of pixels in the crack area of each monitoring sub-region Nc i and the number of pixels in the monitored road surface image area of each monitoring sub-region Nt i , and substitute them into the formula to obtain the road surface image crack rate of the i-th monitoring sub-region Cr i ;

[0025] Second step, divide the image into pore and non-pore regions by binarizing the second monitored road surface image. Count the number of pixels in the pore region of each monitoring sub-region Np i and the number of pixels in the monitored road surface image area of each monitoring sub-region Nt i , and substitute them into the formula to obtain the road surface image porosity rate of the i-th monitoring sub-region Pr i .

[0026] Preferably, the specific execution method of the asphalt road surface flatness anomaly monitoring and analysis is as follows:

[0027] S31: Read the image particle circularity factor of the i-th monitoring sub-region in the image equalization characteristic information Prf i , and substitute it into the formula to obtain the image particle circularity deviation factor of the i-th monitoring sub-region Rdr i , where Prf 0 represents the preset standard image particle circularity factor;

[0028] S32: Read the discreteness of the image particle area in the i-th monitoring sub-region in the image equalization characteristic information Pdd i , and substitute it into the formula Obtain the coefficient of variation of the image particle area of the i-th monitoring sub-region Cov i , where represents the average value of the image particle area of the i-th monitoring sub-region;

[0029] S33: Calculate the pavement flatness and balance coefficient of the asphalt road FEC , and the calculation model is as follows:

[0030] , where Rdr 0 represents the maximum value of the preset image particle roundness deviation factor, e represents the natural constant, n represents the total number of monitoring sub-regions, and i represents the number of each monitoring sub-region;

[0031] S34: Extract the pavement flatness and balance coefficient of the asphalt road and compare it with the preset pavement flatness and balance coefficient threshold to evaluate the pavement flatness and balance of the asphalt road. If the pavement flatness and balance coefficient is greater than or equal to the preset pavement flatness and balance coefficient threshold, it is determined that the pavement flatness of the asphalt road is normal. If the pavement flatness and balance coefficient is less than the preset pavement flatness and balance coefficient threshold, it is determined that the pavement flatness of the asphalt road is abnormal, and a warning message is sent for the data with abnormal judgment results.

[0032] Preferably, the specific implementation method of the asphalt road density abnormality monitoring and analysis is as follows:

[0033] S41: Read the pavement image crack rate of the i-th monitoring sub-region in the image density characteristic information Cr i , and substitute it into the formula to obtain the image crack deviation degree of the i-th monitoring sub-region Cdd i , where Cr 0 represents the maximum crack rate of the preset pavement image;

[0034] S42: Calculate the pavement density evaluation coefficient of the asphalt road DEC , and the calculation model is as follows:

[0035] , where Pr i represents the pavement image porosity of the i-th monitoring sub-region, e represents the natural constant, n represents the total number of monitoring sub-regions, and i represents the number of each monitoring sub-region;

[0036] S43: Compare the extracted pavement compactness evaluation coefficient of the asphalt road with the preset threshold of the pavement compactness evaluation coefficient to evaluate the pavement compactness of the asphalt road. If the pavement compactness evaluation coefficient is greater than or equal to the preset threshold of the pavement compactness evaluation coefficient, it is determined that the pavement compactness of the asphalt road is normal. If the pavement compactness evaluation coefficient is less than the preset threshold of the pavement compactness evaluation coefficient, it is determined that the pavement compactness of the asphalt road is abnormal, and a warning message is sent for the data with the judgment result of abnormality.

[0037] Preferably, the specific implementation method of the construction quality monitoring and analysis of the asphalt road is as follows:

[0038] S51: Extract the pavement flatness and balance coefficient of the asphalt road FEC and the pavement compactness evaluation coefficient of the asphalt road DEC , monitor the construction quality of the asphalt road project, analyze and obtain the construction quality evaluation index of the asphalt road QEI , and the calculation model is specifically: ;

[0039] S52: Evaluate the construction quality of the asphalt road project, extract the construction quality evaluation index of the asphalt road and compare it with the preset threshold of the construction quality evaluation index. If the construction quality evaluation index of the asphalt road is greater than or equal to the preset threshold of the construction quality evaluation index, it is determined that the construction quality of the asphalt road project is qualified. If the construction quality evaluation index of the asphalt road is less than the preset threshold of the construction quality evaluation index, it is determined that the construction quality of the asphalt road project is unqualified. A warning message is sent for the data with the judgment result of unqualified, and the monitoring result of the construction quality of the asphalt road project is output.

[0040] The technical effects and advantages of the present invention:

[0041] 1. By installing high-definition cameras to collect real-time image information during the construction process of the asphalt road, the present invention can quickly capture and process key information during the construction process, timely detect and warn potential flatness and density abnormalities, significantly improve the monitoring efficiency and response speed of construction quality, and use image processing technology to automatically extract the characteristic information of the pavement image, replacing the traditional manual detection and sampling inspection methods, reducing errors caused by human factors, and improving the accuracy and objectivity of monitoring;

[0042] 2. Based on the extracted characteristic information of the pavement image, the present invention analyzes and obtains the pavement flatness and balance coefficient and the pavement compactness evaluation coefficient, comprehensively evaluates the construction quality of the asphalt road project, and displays the monitoring result of the construction quality of the asphalt road project on the visualization interface of the monitoring center in real time, enabling managers to intuitively and clearly understand the construction quality situation, facilitating quick decision-making and adjustment, and improving the management efficiency and convenience;

[0043] 3. Through the real-time monitoring and early warning mechanism, the present invention can detect and take intervention measures in a timely manner before the occurrence of quality problems, effectively preventing the increase in rework and repair costs caused by construction quality problems, and improving the economic and social benefits of the project. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] The present invention will be further described with reference to the accompanying drawings. However, the embodiments in the drawings do not constitute any limitation to the present invention. For those of ordinary skill in the art, other drawings can also be obtained based on the following drawings without creative efforts.

[0045] Figure 1 It is a schematic flow chart of a method for real-time monitoring of the construction quality of an asphalt road project of the present invention.

[0046] Figure 2 It is an information extraction diagram of the asphalt road image features of a method for real-time monitoring of the construction quality of an asphalt road project of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0047] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0048] Please refer to Figure 1 As shown, the present invention provides a method for real-time monitoring of the construction quality of an asphalt road project, including the following steps: S1: Collection of asphalt road image information, S2: Extraction of asphalt road image features, S3: Monitoring and analysis of asphalt road flatness anomalies, S4: Monitoring and analysis of asphalt road compaction anomalies, S5: Monitoring and analysis of asphalt road construction quality, and S6: Early warning of asphalt road construction quality anomalies.

[0049] S1: Collection of asphalt road image information: Install a high-definition camera to take pictures of the target area during the construction process of the asphalt road, obtain the asphalt monitoring road surface image, and mark it as the first monitoring road surface image;

[0050] In this embodiment, it should be specifically noted that the specific implementation method of the collection of asphalt road image information is as follows:

[0051] Determine the asphalt construction road as the target monitoring area, take pictures of the target monitoring area, obtain the asphalt monitoring road surface image, divide the asphalt monitoring road surface image into n monitoring sub-areas, i = 1, 2, 3,..., n, and i is the number of each monitoring sub-area;

[0052] Install a high-definition camera on the construction equipment at the asphalt road construction site, take pictures of the asphalt road construction site at a frequency of once every three seconds, and control the distance between the installed camera and the ground within five meters to obtain asphalt monitoring road surface images.

[0053] S2: Asphalt road image feature extraction: Perform preprocessing operations on the first monitoring road surface image to obtain a second monitoring road surface image, and extract the feature information of the asphalt road image based on the second monitoring road surface image. The feature information includes image equalization feature information and image density feature information;

[0054] Please refer to Figure 2 As shown, the asphalt road image feature extraction includes image equalization feature information and image density feature information;

[0055] In this embodiment, it should be specifically noted that the specific implementation method of performing preprocessing operations on the first monitoring road surface image is as follows:

[0056] Based on the obtained first monitoring road surface image, perform preprocessing on the first monitoring road surface image through a grayscale processing unit, a filtering and denoising processing unit, and a histogram equalization processing unit to obtain a second monitoring road surface image;

[0057] The grayscale processing unit converts the RGB color image of the first monitoring road surface image into a grayscale image by the weighted average method;

[0058] The filtering and denoising processing unit applies the Gaussian filtering algorithm to reduce or eliminate the noise in the grayscale image and improve the clarity and quality of the image;

[0059] The histogram equalization processing unit adjusts the grayscale distribution of the grayscale image of the first monitoring road surface image to make it more uniform, thereby improving the contrast and brightness of the image.

[0060] In this embodiment, it should be specifically noted that the specific content of the asphalt road image feature extraction is as follows:

[0061] Extract the feature information of the asphalt road image based on the second monitoring road surface image. The feature information includes image equalization feature information and image density feature information;

[0062] The image equalization feature information includes the image particle circularity factor and the image particle area dispersion degree;

[0063] The specific extraction implementation method of the image equalization feature information is as follows:

[0064] In the first step, use image segmentation technology (such as the connected region labeling algorithm) to separate the particles from the background of the second monitored road surface image, label each particle, obtain the image particle labeling points, and calculate the image particle area of each monitored sub-region Pa i , and the calculation model is specifically: , where Pa i represents the image particle area of the i-th monitored sub-region, M represents the height of the image, N represents the width of the image, represents the pixel value of the image of the i-th monitored sub-region at the position ;

[0065] In this embodiment, it should be specifically noted that the number of pixels of each particle marked as such is counted, and each pixel represents a unit area, so the total number of pixels is equal to the image particle area.

[0066] Import the second monitored road surface image into an edge detection algorithm (such as the Canny edge detection), identify the edge lines of each particle in the second monitored road surface image, fit a curve to the image particle edge lines, and calculate the length of the curve as the perimeter of the image particle edge lines Lp ;

[0067] Read the image particle area of the i-th monitored sub-region Pa i and the perimeter of the image particle edge lines of the i-th monitored sub-region Lp i , and calculate the circularity factor of the image particles in the i-th monitored sub-region Prf i , and the calculation model is specifically: , where represents pi;

[0068] In the second step, label each image particle area as , m represents the total number of image particles, j = 1, 2, 3,..., m, and j is the number of each image particle;

[0069] Calculate the degree of dispersion of the image particle areas, and the calculation model is specifically: , where Pdd i represents the degree of dispersion of the image particle areas in the i-th monitored sub-region, Pa ij represents the area of the j-th image particle in the i-th monitored sub-region;

[0070] In this embodiment, it should be specifically noted that the image density characteristic information includes the image road surface crack rate and the image road surface porosity rate;

[0071] The specific extraction execution method of the image density characteristic information is as follows:

[0072] In the first step, the second monitored road surface image is imported into an edge detection algorithm (such as Canny edge detection) to identify the crack edge lines in the second monitored road surface image. The second monitored road surface image is converted into a binary image using threshold segmentation techniques (such as Otsu's method, local threshold method), where the crack area is white and the background is black. The number of pixels in the crack area of each monitored sub-region is counted Nc i and the number of pixels in the monitored road surface image area of each monitored sub-region Nt i , and they are substituted into the formula to obtain the road surface image crack rate of the i-th monitored sub-region Cr i ;

[0073] In the second step, the second monitored road surface image is divided into pore and non-pore regions through binarization processing, and the number of pixels in the pore region of each monitored sub-region is counted Np i and the number of pixels in the monitored road surface image area of each monitored sub-region Nt i , and they are substituted into the formula to obtain the road surface image porosity rate of the i-th monitored sub-region Pr i .

[0074] S3: Asphalt road flatness anomaly monitoring and analysis: Based on the image equalization characteristic information, the road surface flatness equilibrium coefficient of the asphalt road is analyzed, and it is judged whether it is abnormal according to the road surface flatness equilibrium coefficient, and a warning message is sent for the data with the judgment result of abnormal;

[0075] In this embodiment, it should be specifically noted that the specific execution method of the asphalt road flatness anomaly monitoring and analysis is as follows:

[0076] S31: Read the image particle circularity factor of the i-th monitored sub-region in the image equalization characteristic information Prf i , and substitute it into the formula to obtain the image particle circularity deviation factor of the i-th monitored sub-region Rdr i , where Prf 0 represents the preset standard image particle circularity factor;

[0077] S32: Read the degree of dispersion of the image particle area in the i-th monitoring sub-region in the image equalization feature information Pdd i , and substitute it into the formula to obtain the coefficient of variation of the image particle area in the i-th monitoring sub-region Cov i , where represents the average value of the image particle area in the i-th monitoring sub-region;

[0078] S33: Calculate the pavement flatness and evenness coefficient of the asphalt road FEC , and the calculation model is as follows:

[0079] , where Rdr 0 represents the maximum value of the preset image particle circularity deviation factor, e represents the natural constant, n represents the total number of monitoring sub-regions, and i represents the number of each monitoring sub-region;

[0080] S34: Extract the pavement flatness and evenness coefficient of the asphalt road and compare it with the preset pavement flatness and evenness coefficient threshold to evaluate the pavement flatness and evenness of the asphalt road. If the pavement flatness and evenness coefficient is greater than or equal to the preset pavement flatness and evenness coefficient threshold, it is determined that the pavement flatness of the asphalt road is normal. If the pavement flatness and evenness coefficient is less than the preset pavement flatness and evenness coefficient threshold, it is determined that there is an abnormality in the pavement flatness of the asphalt road, and a warning message is sent for the data with the abnormal judgment result.

[0081] S4: Asphalt road density abnormality monitoring and analysis: Analyze the density of the asphalt road based on the image density feature information to obtain the pavement density evaluation coefficient of the asphalt road, and determine whether it is abnormal according to the pavement density evaluation coefficient, and send a warning message for the data with the abnormal judgment result;

[0082] In this embodiment, it should be specifically noted that the specific implementation method of the asphalt road density abnormality monitoring and analysis is as follows:

[0083] S41: Read the pavement image crack rate in the i-th monitoring sub-region in the image density feature information Cr i , and substitute it into the formula to obtain the image crack deviation degree in the i-th monitoring sub-region Cdd i , where Cr 0 represents the maximum crack rate of the preset pavement image;

[0084] S42: Calculate the pavement density evaluation coefficient of the asphalt road DEC , and the calculation model is as follows:

[0085] , where Pr i represents the porosity of the road surface image of the i-th monitored sub-region, e represents the natural constant, n represents the total number of monitored sub-regions, and i represents the number of each monitored sub-region;

[0086] S43: Extract the pavement density evaluation coefficient of the asphalt road and compare it with the preset pavement density evaluation coefficient threshold to evaluate the pavement density of the asphalt road. If the pavement density evaluation coefficient is greater than or equal to the preset pavement density evaluation coefficient threshold, it is determined that the pavement density of the asphalt road is normal. If the pavement density evaluation coefficient is less than the preset pavement density evaluation coefficient threshold, it is determined that the pavement density of the asphalt road is abnormal, and a warning message is sent for the data with the abnormal judgment result.

[0087] S5: Asphalt road construction quality monitoring and analysis: Based on the pavement flatness balance coefficient and the pavement density evaluation coefficient, analyze the construction quality of the asphalt road project to obtain the construction quality evaluation index of the asphalt road, and conduct quality assessment on it, and output the monitoring result of the construction quality of the asphalt road project;

[0088] In this embodiment, it should be specifically noted that the specific implementation method of the asphalt road construction quality monitoring and analysis is as follows:

[0089] S51: Extract the pavement flatness balance coefficient of the asphalt road FEC and the pavement density evaluation coefficient of the asphalt road DEC , monitor the construction quality of the asphalt road project, analyze and obtain the construction quality evaluation index QEI of the asphalt road, and the calculation model is specifically: ;

[0090] S52: Evaluate the construction quality of the asphalt road project, extract the construction quality evaluation index of the asphalt road and compare it with the preset construction quality evaluation index threshold. If the construction quality evaluation index of the asphalt road is greater than or equal to the preset construction quality evaluation index threshold, it is determined that the construction quality of the asphalt road project is qualified. If the construction quality evaluation index of the asphalt road is less than the preset construction quality evaluation index threshold, it is determined that the construction quality of the asphalt road project is unqualified, and a warning message is sent for the data with the unqualified judgment result, and the monitoring result of the construction quality of the asphalt road project is output.

[0091] S6: Asphalt road construction quality anomaly warning: Display the monitoring result of the asphalt road project construction quality on the visualization interface of the monitoring center in real time, and send an alarm message for the abnormal data.

[0092] In this embodiment, it should be specifically noted that the specific implementation method of the abnormal warning for the construction quality of asphalt roads is as follows:

[0093] The monitoring results of the construction quality of the asphalt road project are displayed in real time on the visualization interface of the monitoring center. Construction management personnel can intuitively see the construction quality status, which is convenient for timely discovering problems and taking measures; according to the alarm information, construction management personnel timely direct on-site construction personnel to adjust the construction process to ensure the construction quality.

[0094] Finally: The above are only the preferred embodiments of the present invention and are not used to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

[0095] The above is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed in the present application can easily think of changes or replacements, which should all be covered by the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A real-time monitoring method for asphalt road construction quality, characterized in that: The following steps are involved: S1: Asphalt road image information collection: Install a high-definition camera to shoot the target area during the asphalt road construction process, obtain the asphalt monitoring road surface image, and mark it as the first monitoring road surface image; S2: Extracting features of asphalt road images: performing a preprocessing operation on the first monitored road image to obtain a second monitored road image, and extracting feature information of the asphalt road image based on the second monitored road image, wherein the feature information includes image balance feature information and image density feature information; The image balance characteristic information includes the image particle circularity factor and the image particle area discreteness. The specific extraction execution method of the image balance characteristic information is as follows: In the first step, the image segmentation technology is used to separate the particles from the background of the second monitored road surface image, and each particle is marked to obtain the image particle marking point, and the image particle area Pai of each monitored sub-area is calculated. The specific calculation model is: , where Pai represents the image particle area of ​​the ith monitoring sub-region, M represents the height of the image, and N represents the width of the image. Indicates that the image of the i-th monitoring sub-area is at position The pixel value at ; Importing the second monitored road surface image into an edge detection algorithm, identifying the edge line of each particle in the second monitored road surface image, and calculating the length of the curve as the perimeter Lp of the edge line of the image particle by fitting a curve to the edge line of the image particle; Read the image particle area Pai of the i-th monitoring sub-area and the image particle edge line perimeter Lpi of the i-th monitoring sub-area, and calculate the image particle circularity factor Prfi of the i-th monitoring sub-area. The specific calculation model is: ,in, represents pi; In the second step, the area of ​​each image particle is marked as , m represents the total number of image particles, j=1, 2, 3, ..., m, j is the number of each image particle; Calculate the discrete degree of image particle area, the calculation model is as follows: , where Pddi represents the discrete degree of the image particle area of ​​the ith monitoring sub-region, and Paij represents the jth image particle area of ​​the ith monitoring sub-region; The image density feature information includes the image road surface crack rate and the image road surface porosity. The specific extraction execution method of the image density feature information is as follows: The first step is to import the second monitored road surface image into the edge detection algorithm to identify the crack edge line in the second monitored road surface image. The second monitored road surface image is converted into a binary image using the threshold segmentation technology, with the crack area being white and the background being black. The number of pixels Nci in the crack area of ​​each monitored sub-area and the number of pixels Nti in the monitored road surface image area of ​​each monitored sub-area are counted and substituted into the formula Get the road surface image crack rate Cri of the i-th monitoring sub-area; In the second step, the second monitored road surface image is divided into pore and non-pore areas by binarization processing, and the number of pixels Npi of the pore area of ​​each monitored sub-area and the number of pixels Nti of the monitored road surface image area of ​​each monitored sub-area are counted, and the numbers are substituted into the formula Get the pavement image porosity Pri of the i-th monitoring sub-area; S3: Asphalt road flatness abnormality monitoring and analysis: Based on the image balance feature information, the asphalt road flatness balance is analyzed to obtain the road surface flatness balance coefficient of the asphalt road, and whether it is abnormal is determined according to the road surface flatness balance coefficient, and an early warning message is issued for data with abnormal judgment results; S4: Monitoring and analysis of abnormal compactness of asphalt roads: Based on the image density feature information, the compactness of asphalt roads is analyzed to obtain the pavement compactness evaluation coefficient of asphalt roads, and the pavement compactness evaluation coefficient is used to determine whether it is abnormal, and a warning message is issued for data with abnormal judgment results; S5: Asphalt road construction quality monitoring and analysis: Based on the road surface flatness balance coefficient and road surface compaction evaluation coefficient, the asphalt road construction quality is analyzed to obtain the asphalt road construction quality evaluation index, and the quality is evaluated to output the asphalt road construction quality monitoring results; S6: Asphalt road construction quality abnormality warning: The asphalt road construction quality monitoring results are displayed in real time on the visual interface of the monitoring center, and alarm information is issued for abnormal data.

2. A method for real-time monitoring of asphalt road construction quality according to claim 1, characterized in that: The specific implementation method of the asphalt road image information collection is as follows: The asphalt construction road is determined as the target monitoring area, the target monitoring area is photographed, and an asphalt monitoring road surface image is obtained. The asphalt monitoring road surface image is divided into n monitoring sub-areas, i=1, 2, 3, ..., n, i is the number of each monitoring sub-area.

3. A method for real-time monitoring of asphalt road construction quality according to claim 1, characterized in that: The specific implementation method of performing the preprocessing operation on the first monitored road surface image is as follows: Based on the acquired first monitored road surface image, the first monitored road surface image is preprocessed by a grayscale processing unit, a filtering and denoising processing unit, and a histogram equalization processing unit to obtain a second monitored road surface image.

4. A method for real-time monitoring of asphalt road construction quality according to claim 1, characterized in that: The specific implementation method of the asphalt road leveling abnormality monitoring and analysis is as follows: S31: Read the image particle circularity factor Prfi of the i-th monitoring sub-area in the image balance feature information, and substitute it into the formula Obtaining the image particle circularity deviation factor Rdri of the i-th monitoring sub-area, wherein Prf0 represents a preset standard image particle circularity factor; S32: Read the image particle area discrete degree Pddi of the i-th monitoring sub-area in the image balance feature information, and substitute it into the formula Get the coefficient of variation Covi of the image particle area of ​​the i-th monitoring sub-area, where: represents the average value of the particle area of ​​the image in the i-th monitoring sub-region; S33: Calculate the pavement smoothness equilibrium coefficient FEC of the asphalt road. The calculation model is as follows: , where Rdr0 represents the preset maximum value of the circularity deviation factor of the image particles, e represents a natural constant, n represents the total number of each monitoring sub-area, and i represents the number of each monitoring sub-area; S34: Extract the pavement smoothness balance coefficient of the asphalt road and compare it with the preset pavement smoothness balance coefficient threshold to evaluate the pavement smoothness balance of the asphalt road. If the pavement smoothness balance coefficient is greater than or equal to the preset pavement smoothness balance coefficient threshold, it is determined that there is no abnormality in the pavement smoothness of the asphalt road. If the pavement smoothness balance coefficient is less than the preset pavement smoothness balance coefficient threshold, it is determined that there is an abnormality in the pavement smoothness of the asphalt road, and a warning message is issued for data with abnormal judgment results.

5. The method for real-time monitoring of asphalt road construction quality according to claim 1, characterized in that: The specific implementation method of the asphalt road compaction abnormality monitoring and analysis is as follows: S41: Read the pavement image crack rate Cri of the i-th monitoring sub-area in the image density feature information, and substitute it into the formula The image crack deviation Cddi of the i-th monitoring sub-area is obtained, where Cr0 represents the preset maximum crack rate of the road surface image; S42: Calculate the pavement compaction evaluation coefficient DEC of the asphalt road. The calculation model is as follows: , where Pri represents the porosity of the pavement image of the ith monitoring sub-area, e represents a natural constant, n represents the total number of monitoring sub-areas, and i represents the number of each monitoring sub-area; S43: Extract the pavement density evaluation coefficient of the asphalt road and compare it with the preset pavement density evaluation coefficient threshold to evaluate the pavement density of the asphalt road. If the pavement density evaluation coefficient is greater than or equal to the preset pavement density evaluation coefficient threshold, it is determined that there is no abnormality in the pavement density of the asphalt road. If the pavement density evaluation coefficient is less than the preset pavement density evaluation coefficient threshold, it is determined that there is an abnormality in the pavement density of the asphalt road, and a warning message is issued for data with abnormal judgment results.

6. A method for real-time monitoring of asphalt road construction quality according to claim 1, characterized in that: The specific implementation method of the asphalt road construction quality monitoring and analysis is as follows: S51: Extract the pavement flatness balance coefficient FEC and the pavement compactness evaluation coefficient DEC of the asphalt road, monitor the construction quality of the asphalt road project, and analyze and obtain the construction quality evaluation index QEI of the asphalt road. The specific calculation model is: ; S52: Assess the construction quality of the asphalt road project, extract the construction quality evaluation index of the asphalt road and compare it with the preset construction quality evaluation index threshold. If the construction quality evaluation index of the asphalt road is greater than or equal to the preset construction quality evaluation index threshold, the construction quality of the asphalt road project is judged to be qualified. If the construction quality evaluation index of the asphalt road is less than the preset construction quality evaluation index threshold, the construction quality of the asphalt road project is judged to be unqualified. Issue a warning message for the data judged to be unqualified, and output the asphalt road project construction quality monitoring results.

Images