Quality monitoring method and system for road construction

Abstract

The invention relates to the technical field of road engineering construction, and discloses a quality monitoring method and system for road construction, and the method comprises the steps: obtaining a time sequence image sequence of a construction region, carrying out the processing of the image sequence based on an improved Canny edge detection process, obtaining a binary image containing texture features, and carrying out the processing of the binary image. The method comprises the steps of calculating edge offset data of edge line segments between adjacent frames based on a dynamic time warping algorithm, constructing a pavement texture change model based on the edge offset data, identifying an abnormal region and calculating an area proportion of the abnormal region, and obtaining a construction quality evaluation index based on an edge expansion index and fusing data collected by an Internet of Things sensor. And comparing the construction quality evaluation index with a quality preset threshold value, triggering a grading early warning mechanism, and synchronously pushing the grading early warning mechanism to a highlight area of the construction site model. Based on the improved algorithm, the road surface texture noise interference is effectively inhibited, the edge detection stability is improved, the compactness prediction accuracy is improved, and the road construction quality monitoring efficiency is improved.

Description

Technical Field

[0001] This invention relates to the field of road construction technology, and in particular to a quality monitoring method and system for road construction. Background Technology

[0002] In the field of road construction quality monitoring, traditional methods still dominate. Construction workers typically use random sampling and physical methods such as core drilling and ruler measurement to obtain key indicators such as pavement thickness and compaction. This manual operation-dependent model has significant drawbacks. On the one hand, the testing process requires interrupting the construction flow, with an average daily testing frequency of less than 20 times per lane, making it difficult to cover large work areas. On the other hand, manually recorded data is easily influenced by subjective experience, leading to a high rate of missed detections. Furthermore, the data deviation rate increases exponentially with the working hours of the testing personnel, ultimately resulting in the need for rework on some construction sections. While existing machine vision inspection technologies have replaced manual labor in some scenarios, they have failed to effectively solve the problem of noise interference in road surface textures. Current mainstream algorithms mostly employ the standard Canny edge detection operator, which suffers from excessively high confusion rates between noise signals and effective edge features when processing honeycomb surfaces in asphalt pavements or textured structures in cement pavements. Traditional algorithms also exhibit low edge extraction accuracy in asphalt pavement inspection with exposed coarse aggregates, far lower than the recognition level for smooth surfaces. The lack of dynamic feedback mechanisms during construction is a core obstacle to upgrading quality control. Existing monitoring systems often employ a serial process of construction-inspection-rectification, with an average lag time exceeding 4 hours from data acquisition to decision-making. During the construction of asphalt pavement, this lag will cause the temperature of at least 300 meters of the working section to drop below the standard threshold, forcing construction units to use non-standard measures such as overheating and mixing to compensate, ultimately leading to an increase in the incidence of early pavement defects. The fragmented application of intelligent monitoring systems further exacerbates the industry's pain points. Currently, most quality monitoring equipment on the market focuses on the detection of single indicators, such as independently operating compaction monitors and smoothness testers. Incompatibility of data interfaces between devices leads to the widespread phenomenon of "information silos." This decentralized technical architecture makes the overall assessment and prediction of construction quality a common problem in the industry. Therefore, there is an urgent need for a quality monitoring method and system for road construction. Summary of the Invention

[0003] The purpose of this invention is to overcome one or more of the above-mentioned existing technical problems and provide a quality monitoring method and system for road construction.

[0004] To achieve the above objectives, the present invention provides a quality monitoring method for road construction, comprising: Based on the collaborative acquisition of time-series image sequences of the construction area by vehicle-mounted image acquisition devices and fixed monitoring equipment along the road, a multi-view image library synchronized with timestamps is established. Image sequences from a multi-view image library are processed using an improved Canny edge detection process to obtain binarized edge images containing texture features; For binarized edge images containing texture features, edge offset data of adjacent frame edge segments is calculated based on the dynamic time warping algorithm. The edge offset data includes offset direction and offset amount. A road surface texture change model is constructed based on edge offset data. Abnormal regions are identified and their area proportions are calculated using the 8-neighborhood connected domain analysis method. The edge expansion index is obtained based on the area ratio of abnormal areas, and the construction quality evaluation index is obtained by integrating the temperature field distribution and compaction stress wave signals collected by IoT sensors. The construction quality evaluation index is compared with the preset quality threshold, triggering a graded early warning mechanism and simultaneously pushing it to the highlighted area of ​​the construction site model.

[0005] According to one aspect of the present invention, the improved Canny edge detection process includes inputting an image from a multi-view image library, performing grayscale conversion, adaptive filtering, and double-threshold edge concatenation on it, and obtaining a binarized edge image containing texture features. Adaptive filtering is used to calculate the local gray-level variance. ,like If the value is greater than 30, use an 11×11 Gaussian kernel; otherwise, use a 3×3 Gaussian kernel. The double-threshold edge connection uses the following formula: ; ; in, High threshold; Low threshold; This is the gradient magnitude matrix.

[0006] According to one aspect of the present invention, an edge feature vector is constructed to describe a structured data representation of image edge contours. The edge feature vector is constructed based on a hierarchical structure of line segment sets and feature tuples, representing each frame of edge image as a set of line segments. Each line segment Contains feature tuples ,in, For the length of this line segment, For this line segment, the direction angle , The coordinates of the starting point of this line segment; The distance matrix of edge segments between adjacent frames is calculated based on the dynamic temporal warping algorithm. Edge offset data is then obtained from the resulting distance matrix. The formula for calculating the distance matrix is ​​as follows: ; in, Let be the distance matrix between the line segment sets of two frames; The length of the adjacent line segment; The direction angle of adjacent line segments; , These are the coordinates of the starting points of adjacent line segments.

[0007] According to one aspect of the invention, a binarized edge image is scanned to mark connected components, and the features of each connected component are calculated and compared with a normal texture model. If the edge density of the connected components... or If the connection is abnormal, it is identified as an abnormal connected component and marked. The connected component features include area, perimeter, and centroid. The area is calculated by the following formula: S = total number of pixels in the connected component × actual area of ​​a single pixel. S represents the area in the connected component features. An abnormal connected components are marked using a four-stroke scanning method. The eight neighborhoods of each pixel are traversed to mark pixels belonging to the same connected component. The eight neighborhoods are the top, bottom, left, right and diagonal directions. The recognition area threshold is 0.01m².

[0008] According to one aspect of the present invention, an edge expansion index is obtained based on the area proportion of abnormal regions, wherein the formula is: ; Wherein, EEI is the edge expansion index; The area of ​​expansion of the abnormal region within 10 minutes; The area of ​​the initial anomaly region; This is the temperature decay coefficient; For time intervals.

[0009] According to one aspect of the present invention, a construction quality evaluation index is obtained based on the edge spread index and by fusing temperature field distribution and compaction stress wave signals collected by Internet of Things sensors, wherein the formula is: ; in, It serves as a construction quality evaluation index; The road surface smoothness coefficient; This represents the density deviation rate.

[0010] According to one aspect of the present invention, the quality preset threshold is divided into a first-level warning, a second-level warning, and a third-level warning. The first-level warning is when the construction quality evaluation index is <0.6, and the highlighted area is displayed in red. The second-level warning is when the construction quality evaluation index is 0.6 ≤ construction quality evaluation index <0.8, and the highlighted area is displayed in yellow. The third-level warning is when the construction quality evaluation index is 0.8 ≤ construction quality evaluation index <0.9, and the highlighted area is displayed in blue.

[0011] To achieve the above objectives, the present invention provides a quality monitoring system for road construction, comprising: Multi-view image library establishment module: Based on the collaborative acquisition of time-series image sequences of the construction area by vehicle-mounted image acquisition devices and fixed monitoring equipment along the road, a multi-view image library synchronized with timestamps is established. Binarized edge image generation module: Processes image sequences from a multi-view image library based on an improved Canny edge detection process to obtain binarized edge images containing texture features; Edge offset data acquisition module: Calculates edge offset data of adjacent frame edge segments based on dynamic time warping algorithm for binarized edge images containing texture features. The edge offset data includes offset direction and offset amount. Anomaly region selection module: Constructs a road surface texture change model based on edge offset data, identifies anomaly regions and calculates the area ratio of anomaly regions through 8-neighborhood connected component analysis; Construction quality evaluation module: Based on the area ratio of abnormal areas, the edge expansion index is obtained, and the temperature field distribution and compaction stress wave signals collected by IoT sensors are integrated to obtain the construction quality evaluation index; Quality early warning module: compares the construction quality evaluation index with the preset quality threshold, triggers a graded early warning mechanism, and pushes it to the highlighted area of ​​the construction site model at the same time.

[0012] To achieve the above objectives, the present invention provides an electronic device, including a processor, a memory, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, it implements the above-described quality monitoring method for road construction.

[0013] To achieve the above objectives, the present invention provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the above-described quality monitoring method for road construction.

[0014] Based on this, the beneficial effects of the present invention are as follows: through multi-dimensional technological innovation, the efficiency of road construction quality monitoring is significantly improved, the detection efficiency is significantly improved, automated collection and analysis are used to replace manual sampling, the daily detection frequency is increased, the data density is increased, and the acceptance cycle of the construction section is effectively shortened. The quality identification accuracy reaches the engineering practical standard. The improved algorithm effectively suppresses road texture noise interference, improves edge detection stability, enhances the accuracy of compaction prediction, reduces the misjudgment rate of the existing system, and helps construction units to identify and deal with potential defects such as segregation and cracks in a timely manner. The entire life cycle cost is significantly optimized. Through a real-time feedback mechanism, ineffective operations such as overpressure and underpressure are reduced, construction machinery energy consumption is reduced, material waste and rework costs are reduced, and the overall construction cost is significantly reduced. At the same time, the service life of the road surface is extended and the investment in later maintenance is reduced. This invention achieves a qualitative leap in key performance indicators such as detection response speed, edge recognition accuracy, construction cost control, and early disease prevention, providing an intelligent solution for road construction quality control and promoting the industry's transformation from passive rectification to proactive prevention. Attached Figure Description

[0015] Figure 1 This is a flowchart illustrating a quality monitoring method for road construction according to an exemplary embodiment; Figure 2 This is a flowchart illustrating a quality monitoring system for road construction according to an exemplary embodiment. Detailed Implementation

[0016] The invention will now be discussed with reference to exemplary embodiments. It should be understood that the described embodiments are merely intended to enable those skilled in the art to better understand and thus implement the invention, and are not intended to imply any limitation on the scope of the invention.

[0017] As used herein, the term “comprising” and its variations are to be interpreted as open-ended terms meaning “including but not limited to”. The term “based on” is to be interpreted as “at least partially based on”, and the terms “one embodiment” and “an embodiment” are to be interpreted as “at least one embodiment”.

[0018] According to one embodiment of the present invention, Figure 1 This is a flowchart illustrating a quality monitoring method for road construction according to an exemplary embodiment, such as... Figure 1 As shown, to achieve the above objectives, the present invention provides a quality monitoring method for road construction, comprising: Based on the collaborative acquisition of time-series image sequences of the construction area by vehicle-mounted image acquisition devices and fixed monitoring equipment along the road, a multi-view image library synchronized with timestamps is established. Image sequences from a multi-view image library are processed using an improved Canny edge detection process to obtain binarized edge images containing texture features; For binarized edge images containing texture features, edge offset data of adjacent frame edge segments is calculated based on the dynamic time warping algorithm. The edge offset data includes offset direction and offset amount. A road surface texture change model is constructed based on edge offset data. Abnormal regions are identified and their area proportions are calculated using the 8-neighborhood connected domain analysis method. The edge expansion index is obtained based on the area ratio of abnormal areas, and the construction quality evaluation index is obtained by integrating the temperature field distribution and compaction stress wave signals collected by IoT sensors. The construction quality evaluation index is compared with the preset quality threshold, triggering a graded early warning mechanism and simultaneously pushing it to the highlighted area of ​​the construction site model.

[0019] According to one embodiment of the present invention, the improved Canny edge detection process includes inputting an image from a multi-view image library, performing grayscale conversion, adaptive filtering, and double-threshold edge connection on it, and obtaining a binarized edge image containing texture features. Adaptive filtering is used to calculate the local gray-level variance. ,like If the value is greater than 30, use an 11×11 Gaussian kernel; otherwise, use a 3×3 Gaussian kernel. The double-threshold edge connection uses the following formula: ; ; in, High threshold; Low threshold; This is the gradient magnitude matrix.

[0020] According to one embodiment of the present invention, an edge feature vector is constructed to describe a structured data representation of image edge contours. The edge feature vector is constructed based on a hierarchical structure of line segment sets and feature tuples, representing each frame of edge image as a set of line segments. Each line segment Contains feature tuples ,in, For the length of this line segment, For this line segment, the direction angle , The coordinates of the starting point of this line segment; The distance matrix of edge segments between adjacent frames is calculated based on the dynamic temporal warping algorithm. Edge offset data is then obtained from the resulting distance matrix. The formula for calculating the distance matrix is ​​as follows: ; in, Let be the distance matrix between the line segment sets of two frames; The length of the adjacent line segment; The direction angle of adjacent line segments; , These are the coordinates of the starting points of adjacent line segments.

[0021] According to one embodiment of the present invention, the connected components of the scanned binarized edge image are marked, the features of each connected component are calculated and compared with a normal texture model, S 正常 =[0.001㎡,0.05㎡],S 正常 The area represents the normal texture model, if the edge density of the connected components is... or If it is an abnormal connected component, then it is determined to be an edge density. At times, separation occurs. For pixel-level aggregate accumulation, abnormal connected components are marked. The connected component features include area, perimeter, and centroid. The area is calculated using the following formula: S = total number of pixels in the connected component × actual area of ​​a single pixel, where S represents the area in the connected component features. The formula for calculating edge density is... ; An abnormal connected components are marked using a four-stroke scanning method. The eight neighborhoods of each pixel are traversed to mark pixels belonging to the same connected component. The eight neighborhoods are the top, bottom, left, right and diagonal directions. The recognition area threshold is 0.01m², which corresponds to an image pixel count ≥2500.

[0022] According to one embodiment of the present invention, the edge expansion index is obtained based on the area ratio of abnormal regions, wherein the formula is: ; Wherein, EEI is the edge expansion index; The area of ​​expansion of the abnormal region within 10 minutes; The area of ​​the initial anomaly region; This is the temperature decay coefficient; For time intervals.

[0023] According to one embodiment of the present invention, a construction quality evaluation index is obtained based on the edge spread index and by fusing temperature field distribution and compaction stress wave signals collected by IoT sensors, wherein the formula is: ; in, This is a construction quality evaluation index. The road surface smoothness uniformity coefficient characterizes the uniformity of the road surface's micro-texture and reflects the level of smoothness control during paving operations. The smaller the value, the better the smoothness of the asphalt pavement. cement road surface ; Density deviation rate, characterizing the degree of deviation between pavement compaction and design standard value, is used to reflect the compliance of structural strength with standards. If the value is outside the range, it is judged as insufficient compaction or over-compression. A positive value indicates over-compression and a negative value indicates under-compression.

[0024] According to one embodiment of the present invention, the quality preset threshold is divided into a first-level warning, a second-level warning, and a third-level warning. The first-level warning is when the construction quality evaluation index is <0.6, and the highlighted area is displayed in red. The second-level warning is when the construction quality evaluation index is 0.6 ≤ construction quality evaluation index <0.8, and the highlighted area is displayed in yellow. The third-level warning is when the construction quality evaluation index is 0.8 ≤ construction quality evaluation index <0.9, and the highlighted area is displayed in blue.

[0025] According to one embodiment of the present invention, the construction inspection data of a certain asphalt pavement is as follows: =0.28 (good flatness) =-2% (slight undervoltage), EEI=0.95 (no significant expansion of the abnormal area), then the construction quality evaluation index is, ; at this time, This triggers a Level 1 warning, and the system automatically instructs the paver to stop and pushes a compaction parameter adjustment plan.

[0026] According to one embodiment of the present invention, in the construction of asphalt pavement for a two-way six-lane highway, three ABG8820 pavers are used in a tiered formation, with the longitudinal spacing controlled within the range of 10-15m. Each paver is equipped with an IP67-rated image acquisition device at the center axis of its rear bumper, featuring an 8mm fixed-focus lens and a 1 / 1.7-inch CMOS sensor. A synchronous trigger controller ensures that the image acquisition time difference between the three pavers is ≤50ms. The paving operation adopts a "tightrope walking" reference control method. The asphalt mixture's exit temperature is strictly controlled at 165±5℃, and transport vehicles are covered with cotton blankets for insulation, ensuring an arrival temperature no lower than 155℃. Twelve rollers are divided into three tiers: initial compaction, intermediate compaction, and final compaction. Six Dynapac CC6200 double-drum rollers form the intermediate compaction unit, each integrating a triaxial acceleration sensor. The system uses a measuring instrument (range ±50g) and an infrared temperature probe. The IoT network adopts a star topology. The road roller is equipped with a 5GCPE. A communication link is established between the base station and the edge computing node, with a data upload rate ≥20Mbps. In the test section, the compaction speed is strictly controlled between 3-5km / h, the initial compaction temperature range is 140-160℃, and the final compaction surface temperature is not lower than 80℃. The quality data visualization system is based on a BIM model built with Autodesk Revit. The construction section is divided into 5m×5m grid units. Each unit displays parameters such as PQI index, compaction deviation, and temperature field distribution in real time. Taking the right lane of the test road as an example, the system detected a PQI of 0.58 (triggering a level 1 warning) in this area, with CE=0.6 and DE=5%. The initial abnormal area area... , , =0.05 / min, time interval t=10min, the calculation results are as follows: ; The construction quality evaluation index is: ; Therefore, when PQI=0.58 and PQI<0.6, which is a Level 1 warning, the area will be displayed in red, requiring adjustment of relevant parameters. The system will automatically instruct the paver to stop and push the corresponding compaction parameter adjustment plan.

[0027] Furthermore, to achieve the aforementioned objectives, this invention also provides a quality monitoring system for road construction. Figure 2 This is a flowchart illustrating a quality monitoring system for road construction according to an exemplary embodiment, such as... Figure 2 As shown, a quality monitoring system for road construction according to the present invention includes: Multi-view image library establishment module: Based on the collaborative acquisition of time-series image sequences of the construction area by vehicle-mounted image acquisition devices and fixed monitoring equipment along the road, a multi-view image library synchronized with timestamps is established. Binarized edge image generation module: Processes image sequences from a multi-view image library based on an improved Canny edge detection process to obtain binarized edge images containing texture features; Edge offset data acquisition module: Calculates edge offset data of adjacent frame edge segments based on dynamic time warping algorithm for binarized edge images containing texture features. The edge offset data includes offset direction and offset amount. Anomaly region selection module: Constructs a road surface texture change model based on edge offset data, identifies anomaly regions and calculates the area ratio of anomaly regions through 8-neighborhood connected component analysis; Construction quality evaluation module: Based on the area ratio of abnormal areas, the edge expansion index is obtained, and the temperature field distribution and compaction stress wave signals collected by IoT sensors are integrated to obtain the construction quality evaluation index; Quality early warning module: compares the construction quality evaluation index with the preset quality threshold, triggers a graded early warning mechanism, and pushes it to the highlighted area of ​​the construction site model at the same time.

[0028] To achieve the above-mentioned objectives, the present invention also provides an electronic device comprising: a processor, a memory, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, it implements the above-mentioned quality monitoring method for road construction.

[0029] To achieve the above-mentioned objectives, the present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the above-mentioned quality monitoring method for road construction.

[0030] Those skilled in the art will recognize that the modules and algorithm steps described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0031] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the above-described apparatus and equipment can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0032] In the embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or modules may be electrical, mechanical, or other forms.

[0033] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical modules; that is, they may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected to achieve the purpose of the embodiments of the present invention, depending on actual needs.

[0034] In addition, the functional modules in the embodiments of the present invention can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module.

[0035] If the aforementioned functions are implemented as software functional modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, essentially, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the energy-saving signal transmission / reception methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, ROM, RAM, magnetic disks, or optical disks.

[0036] The above description is merely a preferred embodiment of this application and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of the invention involved in this application is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the inventive concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features with similar functions disclosed in this application.

[0037] It should be understood that the sequence number of each step in the invention and embodiments of the present invention does not absolutely imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

Claims

1. A method for quality monitoring of road construction, characterized in that, The method comprises the following steps: Based on the vehicle-mounted image acquisition device and the fixed monitoring equipment along the road, the time sequence image sequence of the construction area is obtained, and a multi-view image library synchronized with the timestamp is established; The image sequence in the multi-view image library is processed based on the improved Canny edge detection process to obtain a binary edge image containing texture features; Based on the dynamic time warping algorithm, the edge bias data of the edge line segments between adjacent frames is calculated, and the edge bias data includes the bias direction and the bias amount; Based on the edge bias data, a pavement texture change model is constructed, and the abnormal area is identified and the area ratio of the abnormal area is calculated by using the 8-neighbor connected component analysis method; Based on the area ratio of the abnormal area, the edge expansion index is obtained, and the temperature field distribution and the compaction degree stress wave signal collected by the Internet of Things sensor are fused to obtain the construction quality evaluation index; The construction quality evaluation index is compared with the quality preset threshold value, the grading early warning mechanism is triggered, and the highlight area of the construction site model is pushed synchronously.

2. A quality monitoring method for road construction as claimed in claim 1 wherein, The improved Canny edge detection process includes inputting the image in the multi-view image library, performing grayscale, adaptive filtering and double-threshold edge connection to obtain a binary edge image containing texture features; Wherein, the adaptive filter is used to calculate the local area gray scale variance , if > 30, then use 11x11 Gaussian kernel, otherwise use 3 3 Gaussian kernel; The double-threshold edge connection uses the following formula, ； ； wherein is a high threshold value; is a low threshold; is the gradient magnitude matrix.

3. A quality monitoring method for road construction as claimed in claim 2, wherein, An edge feature vector is constructed for describing a structured data representation of an image edge contour, the edge feature vector is constructed based on a set of line segments and a hierarchy of feature tuples, each frame of edge image is represented as a set of line segments each line segment contains a feature tuple wherein, is a length of this line segment, is a direction angle of this line segment, , is a start point coordinate of this line segment; Based on the dynamic time warping algorithm, the distance matrix of the edge line segments between adjacent frames is calculated, and the edge bias data is obtained according to the obtained distance matrix, wherein the formula for calculating the distance matrix is, ； wherein, is a distance matrix for the two image line segment sets; is the length of the adjacent segment; is the direction angle of the adjacent line segment; , is the coordinate of the start point of the adjacent line segment.

4. A quality monitoring method for road construction as claimed in claim 3 wherein, The scanning binaryzation edge image is marked with connected domains, the features of each connected domain are calculated and compared with a normal texture model, if the edge density of the connected domain is or then the connected domain is determined as an abnormal connected domain, and the abnormal connected domain is marked, wherein the features of the connected domain include area, perimeter and barycenter, the area is calculated by the following formula, S = total number of pixels in the connected domain × actual area of a single pixel, and S represents the area in the features of the connected domain; The four-stroke scanning method is used to mark the abnormal connected component, and the 8-neighborhood of each pixel point is traversed to mark the pixels belonging to the same connected component, wherein the 8-neighborhood is the upper, lower, left, right and diagonal directions, and the area threshold is 0.01m².

5. A method for quality monitoring of road construction as claimed in claim 4 wherein, Based on the area ratio of the abnormal area, the edge expansion index is obtained, wherein the formula is, ； Wherein, EEI is the edge expansion index; is the area of the abnormal region at 10 minutes; A is the area of the initial abnormal region; T is the temperature decay coefficient; is a time interval.

6. A quality monitoring method for road construction as claimed in claim 5 wherein, Based on the edge expansion index and the temperature field distribution and the compaction degree stress wave signal collected by the Internet of Things sensor, the construction quality evaluation index is obtained, wherein the formula is, ； wherein, is the construction quality evaluation index; is the road surface flatness and balance coefficient; Density deviation rate.

7. A quality monitoring method for road construction as claimed in claim 6 wherein, The quality preset threshold value is divided into first warning, second warning and third warning, wherein the first warning is that the construction quality evaluation index is less than 0.6, the highlight area is displayed in red, the second warning is that 0.6 is less than or equal to the construction quality evaluation index and less than 0.8, and the highlight area is displayed in yellow, wherein the third warning is that 0.8 is less than or equal to the construction quality evaluation index and less than 0.9, and the highlight area is displayed in blue.

8. A quality monitoring system for road construction, characterized in that The method comprises the following steps: Multi-view image library establishment module: based on the vehicle-mounted image acquisition device and the fixed monitoring equipment along the road, the time sequence image sequence of the construction area is obtained, and a multi-view image library synchronized with the timestamp is established; Binary edge image generation module: the image sequence in the multi-view image library is processed based on the improved Canny edge detection process to obtain a binary edge image containing texture features; Edge bias data acquisition module: based on the dynamic time warping algorithm, the edge bias data of the edge line segments between adjacent frames is calculated, and the edge bias data includes the bias direction and the bias amount; The abnormal area selection module: based on the edge bias data to construct the pavement texture change model, through the 8-neighborhood connected domain analysis method to identify the abnormal area and calculate the area proportion of the abnormal area; The construction quality evaluation module: based on the area proportion of the abnormal area to obtain the edge expansion index, and fuse the temperature field distribution and the compaction degree stress wave signal collected by the Internet of Things sensor to obtain the construction quality evaluation index; The quality early warning module: compare the construction quality evaluation index with the quality preset threshold value, trigger the grading early warning mechanism and synchronously push to the highlight area of the construction site model.

9. An electronic device, comprising: A computer program product comprising a processor, a memory, and a computer program stored on the memory and executable on the processor, the computer program, when executed by the processor, implements a quality monitoring method for road construction according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, A computer program product comprising a processor, a memory, and a computer program stored on the memory and executable on the processor, the computer program, when executed by the processor, implements a quality monitoring method for road construction according to any one of claims 1 to 7.

Images