A highway quality inspection method and system based on a UAV

Abstract

The application provides a kind of highway quality inspection method and system based on unmanned aerial vehicle, it is related to highway quality detection technical field.The method comprises: obtaining the three-dimensional coordinate data of target highway, establishing highway benchmark three-dimensional model, and the target highway is divided into multiple highway sections;Set the flight parameters and flight path of unmanned aerial vehicle;The unmanned aerial vehicle is carried with multiple detection devices, and the highway section data of the highway section is collected;According to the optical image, determine the crack comprehensive index;According to the three-dimensional point cloud data, construct the digital elevation model of pavement;According to the digital elevation model of pavement, determine the pavement evenness index;According to the visible light band reflection energy and the infrared band reflection energy, determine the material degradation index;Determine the highway section needing maintenance.According to the application, the highway quality can be comprehensively detected according to the crack, evenness, material degradation and the like, and the comprehensiveness, accuracy and safety of detection are improved.

Description

Technical Field

[0001] This invention relates to the field of highway quality inspection technology, and in particular to a highway quality inspection method and system based on unmanned aerial vehicles (UAVs). Background Technology

[0002] Current technologies, while using crack comparison and road images to detect highway quality, do not consider the impact of cracks, unevenness, and material degradation on the highway quality results. In other words, they cannot comprehensively detect highway quality based on cracks, unevenness, and material degradation.

[0003] The information disclosed in the background section of this application is intended only to enhance the understanding of the general background of this application and should not be construed as an admission or in any way implying that the information constitutes prior art known to those skilled in the art. Summary of the Invention

[0004] This invention provides a method and system for highway quality inspection based on unmanned aerial vehicles (UAVs), which can solve the technical problem that related technologies cannot comprehensively detect highway quality based on factors such as cracks, smoothness, and material degradation.

[0005] According to a first aspect of the present invention, a method for highway quality inspection based on unmanned aerial vehicles (UAVs) is provided, comprising: acquiring three-dimensional coordinate data of a target highway through a geographic information system, establishing a highway baseline three-dimensional model, and dividing the target highway into multiple highway sections; setting flight parameters and flight path of the UAV according to the highway baseline three-dimensional model; equipping the UAV with multiple detection devices and simultaneously collecting highway section data of the highway sections during flight, wherein the detection devices include a high-resolution optical camera, a three-dimensional laser scanner, and a multispectral sensor, and the highway section data includes optical images, three-dimensional point cloud data, visible light band reflection energy, and infrared band reflection energy; determining a comprehensive crack index based on the optical images; constructing a road surface digital elevation model based on the three-dimensional point cloud data; determining a road surface smoothness index based on the road surface digital elevation model; determining a material degradation index based on the visible light band reflection energy and the infrared band reflection energy; and determining the highway sections requiring maintenance based on the comprehensive crack index, the road surface smoothness index, and the material degradation index.

[0006] Further, based on the optical image, determining the comprehensive crack index includes: preprocessing the optical image to obtain image height, image width, and crack feature parameters, wherein the crack feature parameters include crack length and average crack width; and determining the comprehensive crack index based on the image height, the image width, and the crack feature parameters.

[0007] Further, based on the image height, the image width, and the crack feature parameters, a comprehensive crack index is determined, including: according to the formula: Determine the comprehensive crack index C, where, The length of the crack. The average width of the crack. Image height, This represents the image width.

[0008] Further, based on the road surface digital elevation model, the road surface smoothness index is determined, including: randomly selecting multiple first lines parallel to the road centerline from the road surface digital elevation model; extracting multiple sampling points on the first lines at preset horizontal intervals and obtaining the coordinates of the sampling points; obtaining the elevation value and curvature change rate of the sampling points based on the coordinates of the sampling points; and determining the road surface smoothness index based on the preset horizontal intervals, the elevation value, and the curvature change rate.

[0009] Further, based on the preset horizontal interval, the elevation value, and the rate of change of curvature, the road surface smoothness index is determined, including: according to the formula: Determine the road surface smoothness index R, where, Let be the rate of curvature change at the j-th sampling point of the i-th first line. To preset the rate of change of curvature, Let be the elevation value of the (j+1)th sampling point of the i-th first line. Let be the elevation value of the j-th sampling point of the i-th first line, d be the preset horizontal interval, and K be the number of first lines. Let K be the number of sampling points for the i-th first line, i ≤ K, j ≤ K. And i, j, K and All are positive integers, and min is the function that takes the minimum value.

[0010] Furthermore, based on the visible light band reflection energy and the infrared band reflection energy, material degradation indicators are determined, including: obtaining the healthy material density when the target highway was built; obtaining the current material density of the highway section through non-destructive testing methods; obtaining the daytime and nighttime surface temperatures of the highway section; obtaining the ambient temperature of the daytime inspection; and determining material degradation indicators based on the healthy material density, the current material density, the daytime surface temperature, the nighttime surface temperature, the ambient temperature, the visible light band reflection energy, and the infrared band reflection energy.

[0011] Further, based on the healthy material density, the current material density, the daytime surface temperature, the nighttime surface temperature, the ambient temperature, the visible light band reflection energy, and the infrared band reflection energy, a material degradation index is determined, including: according to the formula: Determine the material degradation index M, where, For visible light band reflected energy, For infrared band reflected energy, For the density of healthy materials, Given the current material density, This refers to the surface temperature during the day. The surface temperature at night. The ambient temperature.

[0012] Further, based on the comprehensive crack index, the pavement smoothness index, and the material degradation index, the highway sections requiring maintenance are determined, including: weighting and summing the comprehensive crack index, the pavement smoothness index, and the material degradation index to determine the quality indexes of multiple highway sections; and determining the highway sections requiring maintenance based on the quality indexes and preset quality indexes.

[0013] According to a second aspect of the present invention, a highway quality inspection system based on unmanned aerial vehicles (UAVs) is provided, comprising: a highway reference 3D model module, used to acquire 3D coordinate data of a target highway through a geographic information system, establish a highway reference 3D model, and divide the target highway into multiple highway sections; a flight setting module, used to set the flight parameters and flight path of the UAV according to the highway reference 3D model; and a highway section data module, used to carry multiple detection devices on the UAV and synchronously collect highway section data of the highway sections during flight, wherein the detection devices include a high-resolution optical camera, a 3D laser scanner, and a multispectral sensor, and the highway sections... The data includes optical images, 3D point cloud data, visible light band reflection energy, and infrared band reflection energy; a crack comprehensive index module, used to determine the crack comprehensive index based on the optical images; a road surface digital elevation model module, used to construct a road surface digital elevation model based on the 3D point cloud data; a road surface smoothness index module, used to determine the road surface smoothness index based on the road surface digital elevation model; a material degradation index module, used to determine the material degradation index based on the visible light band reflection energy and the infrared band reflection energy; and a maintenance module, used to determine the highway sections requiring maintenance based on the crack comprehensive index, the road surface smoothness index, and the material degradation index.

[0014] Technical Effects: According to this invention, by dividing the target highway into multiple highway sections and conducting inspections, blind spots in the inspection are reduced, and problems existing in the target highway can be detected in a timely manner. Multiple data are collected by using drones equipped with multiple inspection devices, eliminating the need for manual section-by-section inspection and improving inspection efficiency. By using comprehensive crack indices, pavement smoothness indices, and material degradation indices, the highway sections requiring maintenance can be determined, improving maintenance efficiency and reducing maintenance costs. Comprehensive inspection of highway quality can be conducted based on cracks, smoothness, and material degradation, improving the comprehensiveness, accuracy, and safety of the inspection. When determining the comprehensive crack indices, image height, image width, and crack feature parameters can be used to determine the comprehensive crack indices, more accurately assessing the crack condition and describing the degree of crack coverage within the highway area, enabling timely detection of damage problems in the highway area. When determining the pavement smoothness indices, preset horizontal intervals, elevation values, and curvature change rates can be used to determine the pavement smoothness indices. Combining the curvature change rate with elevation changes, and considering both vertical and longitudinal smoothness characteristics of the pavement, can more comprehensively characterize pavement fluctuations, improving the comprehensiveness and reliability of the inspection results. When determining material degradation indicators, the indicators can be determined by the density of healthy materials, the current density of materials, the surface temperature during the day, the surface temperature at night, the ambient temperature, the reflected energy in the visible light band, and the reflected energy in the infrared band. Based on the differences in multispectral energy and the physical quality and thermal inertia characteristics of materials, a non-destructive quantitative assessment of internal material degradation can be achieved, reducing traffic accidents and road damage caused by material degradation and improving the safety of testing.

[0015] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only, and are not intended to limit the invention. Other features and aspects of the invention will become clearer from the following detailed description of exemplary embodiments with reference to the accompanying drawings. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other embodiments can be obtained based on these drawings without creative effort.

[0017] Figure 1 An exemplary flowchart of a UAV-based highway quality inspection method according to an embodiment of the present invention is shown.

[0018] Figure 2 A flowchart for calculating the comprehensive crack index is shown as an example according to an embodiment of the present invention;

[0019] Figure 3An exemplary flowchart for calculating road surface smoothness indices according to an embodiment of the present invention is shown;

[0020] Figure 4 A flowchart for calculating material degradation indices according to an embodiment of the present invention is illustrated by way of example;

[0021] Figure 5 An exemplary flowchart illustrating the determination of highway sections requiring maintenance according to an embodiment of the present invention is shown;

[0022] Figure 6 A block diagram of a UAV-based highway quality inspection system according to an embodiment of the present invention is shown as an example. Detailed Implementation

[0023] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0024] The technical solution of the present invention will be described in detail below with reference to specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments.

[0025] Figure 1 An exemplary flowchart of a UAV-based highway quality inspection method according to an embodiment of the present invention is shown. The method includes: Step S1, acquiring three-dimensional coordinate data of a target highway through a geographic information system, establishing a highway baseline three-dimensional model, and dividing the target highway into multiple highway sections; Step S2, setting the flight parameters and flight path of the UAV according to the highway baseline three-dimensional model; Step S3, equipping the UAV with multiple detection devices and synchronously collecting highway section data of the highway sections during flight, wherein the detection devices include a high-resolution optical camera, a three-dimensional laser scanner, and a multi-lens resonator. The data from the highway section includes optical images, three-dimensional point cloud data, visible light band reflection energy, and infrared band reflection energy. Step S4: Determine the comprehensive crack index based on the optical image. Step S5: Construct a digital elevation model of the road surface based on the three-dimensional point cloud data. Step S6: Determine the road surface smoothness index based on the digital elevation model of the road surface. Step S7: Determine the material degradation index based on the visible light band reflection energy and the infrared band reflection energy. Step S8: Determine the highway sections requiring maintenance based on the comprehensive crack index, the road surface smoothness index, and the material degradation index.

[0026] The UAV-based highway quality inspection method according to embodiments of the present invention divides the target highway into multiple highway sections for inspection, reducing blind spots and enabling timely detection of problems. By using UAVs equipped with multiple inspection devices to collect various data, manual section-by-section inspection is eliminated, improving inspection efficiency. By using comprehensive crack indices, pavement smoothness indices, and material degradation indices, the method identifies highway sections requiring maintenance, improving maintenance efficiency and reducing maintenance costs. Comprehensive highway quality inspection based on cracks, smoothness, and material degradation enhances the comprehensiveness, accuracy, and safety of the inspection.

[0027] According to one embodiment of the present invention, in step S1, a Geographic Information System (GIS) is a spatial information system that integrates computer hardware, software, geographic data, and system administrators, possessing powerful data acquisition, processing, and analysis capabilities. It can acquire the three-dimensional coordinate data of the target highway, and using modeling software and algorithms within the GIS, establish a baseline three-dimensional model of the highway, dividing the target highway into multiple relatively independent highway segments, each with approximately the same length and width. Each highway segment can be assigned as an independent work order to different drones, or completed by a single drone in multiple runs.

[0028] According to one embodiment of the present invention, in step S2, the flight parameters of the UAV include flight altitude and flight speed. The flight altitude can be determined based on the elevation data in the road reference 3D model and the detection requirements. For example, on flat road sections, to ensure clear and comprehensive road images and data, the flight altitude can be set in a relatively low and appropriate range, such as 50-100 meters. In mountainous areas or road sections with large terrain undulations, to avoid collisions with mountains while ensuring the detection field of view, the flight altitude needs to be appropriately increased, and can be set at 100-200 meters. Because detailed crack detection of the target road surface is required, the flight speed should be relatively slow, and can be set at 2-4 meters per second. Based on the road reference 3D model, combined with the road's direction and layout, a general flight path framework for the UAV is planned. For example, if the target road is narrow, one UAV can fly along the centerline of the target road; if the target road is wide, multiple UAVs can fly in directions parallel to the centerline of the target road, covering the entire road area. Based on obstacle information displayed in the 3D model of the highway baseline, the flight path is optimized to avoid fixed obstacles such as tall buildings and power line towers. It also considers dynamic obstacles that may be encountered during flight, such as birds, and employs intelligent obstacle avoidance algorithms to enable the drone to automatically adjust its flight path when encountering obstacles, ensuring flight safety. After completing the flight path planning, simulation software can be used to verify and optimize the flight path.

[0029] According to one embodiment of the present invention, in step S3, the detection task can begin after the target highway is closed in good weather. When the UAV enters the airspace above the highway section to begin the detection task, the high-resolution optical camera, the 3D laser scanner, and the multispectral sensor simultaneously start working. The high-resolution optical camera continuously captures images of the highway section according to set shooting parameters, such as focal length, aperture, and shutter speed, to obtain clear optical images that reflect details such as texture, color, and cracks on the surface of the highway section. The 3D laser scanner scans the highway section to obtain a large amount of 3D point cloud data, accurately describing the geometry and spatial position of the highway section surface, providing a basis for 3D modeling of the highway section. The multispectral sensor simultaneously collects the reflected energy in the visible light band and the reflected energy in the infrared band (near-infrared band). Healthy materials (e.g., dense asphalt or concrete) typically have relatively stable reflected energy characteristics in the visible light band and the infrared band, with a baseline value for both. Degraded materials (e.g., those with microcracks, loose aggregates, and increased internal porosity) undergo changes in their surface structure and chemical composition, significantly affecting their absorption capacity in the infrared band. For example, internal porosity increases the scattering of infrared light, causing more light energy to be absorbed by the material. This results in a significant reduction in the reflected energy detected by multispectral sensors in the near-infrared band compared to a healthy state; in other words, the infrared reflected energy collected by multispectral sensors is reduced.

[0030] According to one embodiment of the present invention, in step S4, the crack comprehensive index is determined based on the optical image.

[0031] Figure 2 A flowchart for calculating the comprehensive crack index is shown as an example according to an embodiment of the present invention.

[0032] According to an embodiment of the present invention, step S4 includes: step S41, preprocessing the optical image to obtain image height, image width and crack feature parameters, wherein the crack feature parameters include crack length and average crack width; step S42, determining a comprehensive crack index based on the image height, the image width and the crack feature parameters.

[0033] According to one embodiment of the present invention, the image belonging to the highway section in the acquired optical image is extracted and preprocessed, including but not limited to grayscale conversion (converting the color image to a grayscale image to reduce data dimensionality), noise reduction (using filtering algorithms such as Gaussian filtering, median filtering, etc. to eliminate random noise in the image), and contrast enhancement (improving the distinction between cracks and background in the image through methods such as histogram equalization), to optimize image quality. The image height and width are obtained using image processing software (e.g., OpenCV library in Python, MATLAB, etc.), and then image segmentation is performed (e.g., thresholding, edge detection algorithms, etc.) to separate crack pixels (foreground) from non-crack pixels (background), resulting in a binary image of the crack (cracks are white, background is black). All white crack regions are skeletonized as a whole. Skeletonization involves thinning the white crack regions until their width is only one pixel. This thin line is the "skeleton line" of the crack, representing the center line of the crack. The number of pixels on the skeleton line is taken as the crack length. A distance transform is applied to the binary image of the crack. This distance transform calculates the distance from each crack pixel to the nearest background pixel. Along the crack's skeleton line, the distance transform value corresponding to each skeleton pixel is extracted. This distance transform value represents half the crack width at that skeleton pixel. Therefore, the crack width at a given point is equal to twice the distance transform value at that point. The average width of the crack is obtained by averaging the calculated widths of all skeleton pixels. The comprehensive crack index reflects the surface damage condition of a highway area.

[0034] According to one embodiment of the present invention, determining a comprehensive crack index based on the image height, the image width, and the crack feature parameters includes: determining the comprehensive crack index C according to formula (1).

[0035] (1),

[0036] in, The length of the crack. The average width of the crack. Image height, This represents the image width.

[0037] According to an embodiment of the present invention, in formula (1), The product of the crack length and the average crack width represents the total crack area. The product of the image height and the image width represents the image area of ​​the highway region. The ratio of the total crack area to the image area indicates the degree of crack coverage within the highway area, i.e., the comprehensive crack index. The higher the comprehensive crack index, the more severe the surface damage of the highway area and the greater the quality problem of the highway area.

[0038] In this way, the comprehensive index of cracks can be determined by using image height, image width, and crack feature parameters, which can more accurately assess the crack condition, describe the coverage of cracks in the highway area, and enable timely detection of damage problems in the highway area.

[0039] According to an embodiment of the present invention, in step S5, after preprocessing the three-dimensional point cloud data, a road surface digital elevation model is generated by using various processing techniques (e.g., differential GPS, inertial navigation calculation, point cloud registration). Each point on the road surface digital elevation model contains precise three-dimensional coordinates.

[0040] According to an embodiment of the present invention, in step S6, the road surface smoothness index is determined based on the road surface digital elevation model.

[0041] Figure 3 A flowchart for calculating road surface smoothness index is shown as an example according to an embodiment of the present invention.

[0042] According to an embodiment of the present invention, step S6 includes: step S61, randomly selecting multiple first lines parallel to the center line of the highway from the road surface digital elevation model; step S62, extracting multiple sampling points on the first lines at preset horizontal intervals and obtaining the coordinates of the sampling points; step S63, obtaining the elevation value and curvature change rate of the sampling points based on the coordinates of the sampling points; and step S64, determining the road surface smoothness index based on the preset horizontal intervals, the elevation value, and the curvature change rate.

[0043] According to one embodiment of the present invention, based on a pre-constructed digital elevation model of the road surface, a first line parallel to the centerline of the highway is randomly selected from the road surface area covered by the model, reflecting the characteristics of the highway area at different longitudinal positions. Along each first line, multiple sampling points are automatically extracted using software tools at preset horizontal intervals (outliers can be discarded), where the preset horizontal interval can be set to 0.5 meters. The coordinate information of each sampling point in the coordinate system of the digital elevation model of the road surface is recorded, including the coordinate values ​​in the horizontal direction (X and Y coordinates) and the vertical direction (Z coordinate). Since the digital elevation model of the road surface stores the elevation information of each location on the road surface, the corresponding elevation value can be directly queried and obtained from the model based on the vertical direction (Z coordinate) coordinate value of the sampling point. The elevation value reflects the height of the sampling point relative to the reference plane in the vertical direction. Curvature describes the degree of curvature of a curve, and the rate of change of curvature describes how fast the degree of curvature changes, reflecting the local undulations of the road surface. For discrete sampling points, the curvature can be estimated using the three-point method (previous point, current point, next point). The rate of change of curvature is calculated by comparing the curvature of adjacent sampling points. Road surface smoothness index reflects the smoothness of the road surface.

[0044] According to one embodiment of the present invention, determining a road surface smoothness index based on the preset horizontal interval, the elevation value, and the rate of change of curvature includes: determining the road surface smoothness index R according to formula (2).

[0045] (2),

[0046] in, Let be the rate of curvature change at the j-th sampling point of the i-th first line. To preset the rate of change of curvature, Let be the elevation value of the (j+1)th sampling point of the i-th first line. Let be the elevation value of the j-th sampling point of the i-th first line, d be the preset horizontal interval, and K be the number of first lines. Let K be the number of sampling points for the i-th first line, i ≤ K, j ≤ K. And i, j, K and All are positive integers, and min is the function that takes the minimum value.

[0047] According to an embodiment of the present invention, in formula (2), The ratio between the elevation value of the (j+1)th sampling point of the i-th first line and the elevation value of the j-th sampling point of the i-th first line, and the preset horizontal interval, represents the slope of the line connecting two adjacent sampling points. The larger the slope, the more uneven the area, such as a pothole. Conversely, a gentle slope will have a smaller slope value. The rate of curvature change of the j-th sampling point of the i-th first line is compared with the preset rate of curvature change (e.g., 0.04m). -2 The ratio between the slope values ​​is used to represent the weight of the slope values. Indicates taking The minimum of 1 and 2, with greater weight given to the section with a higher rate of change of curvature. For example, two road sections may have the same gradient (slope value), but if one is a straight, smooth slope, it has a lower weight, while the other is a wavy road with frequent undulations and a higher weight, resulting in a worse driving experience. The road surface smoothness index can be obtained by weighted averaging the slopes between any two points on the first line. The larger the road surface smoothness index, the more uneven the road surface is in the vertical and longitudinal directions, the more severe the road surface fluctuations, and the worse the driving quality of the road area. For example, large elevation differences (such as potholes and joints) and frequent changes in alignment (such as wavy roads) appear in a short distance.

[0048] In this way, road surface smoothness indicators can be determined by preset horizontal intervals, elevation values, and curvature change rates. By combining the curvature change rate with elevation changes, and considering the smoothness characteristics of the road surface in both the vertical and longitudinal directions, the road surface fluctuations can be more comprehensively characterized, improving the comprehensiveness and reliability of the test results.

[0049] According to one embodiment of the present invention, in step S7, the material degradation index is determined based on the visible light band reflection energy and the infrared band reflection energy.

[0050] Figure 4 A flowchart for calculating material degradation indices according to an embodiment of the present invention is shown as an example.

[0051] According to an embodiment of the present invention, step S7 includes: step S71, obtaining the healthy material density when the target highway was built; step S72, obtaining the current material density of the highway section through a non-destructive testing method; step S73, obtaining the daytime surface temperature and nighttime surface temperature of the highway section; step S74, obtaining the ambient temperature of the day's inspection; and step S75, determining the material degradation index based on the healthy material density, the current material density, the daytime surface temperature, the nighttime surface temperature, the ambient temperature, the visible light band reflection energy, and the infrared band reflection energy.

[0052] According to one embodiment of the present invention, the healthy material density of the target highway at the time of construction can be obtained by reviewing engineering archives from the highway construction period, including construction records and material testing reports. Common non-destructive testing methods include radiographic testing, ultrasonic testing, and radar testing. For example, for asphalt pavement, ground-penetrating radar can be used, which emits high-frequency electromagnetic waves and receives reflected waves, calculating the current material density based on the propagation time and intensity of the reflected waves. For cement concrete pavement, ultrasonic testing is more suitable, using the relationship between the propagation speed of ultrasonic waves in the material and the material density to calculate the current material density. During the day, the surface temperature of the highway section can be measured during periods of strong solar radiation, such as around noon, and the nighttime surface temperature can be measured at 9 pm. The highest weather temperature of the day's inspection is taken as the ambient temperature. Material degradation indicators can reveal changes in the performance of highway materials, providing a basis for long-term highway maintenance.

[0053] According to one embodiment of the present invention, a material degradation index is determined based on the healthy material density, the current material density, the daytime surface temperature, the nighttime surface temperature, the ambient temperature, the visible light band reflection energy, and the infrared band reflection energy, including: determining the material degradation index M according to formula (3).

[0054] (3),

[0055] in, For visible light band reflected energy, For infrared band reflected energy, For the density of healthy materials, Given the current material density, This refers to the surface temperature during the day. The surface temperature at night. The ambient temperature.

[0056] According to one embodiment of the present invention, in formula (3), This is the ratio of the difference between the reflected energy in the visible light band and the reflected energy in the infrared band to the sum of the two. A larger ratio indicates greater material degradation in the highway area, such as the appearance of microcracks, loose aggregates, and increased internal porosity. In these cases, the reflected energy in the infrared band is lower, and the difference between the reflected energy in the visible light band and the infrared band is greater. During long-term use, materials experience wear, spalling, and internal voids due to vehicle loads, temperature stress, and water damage, leading to a decrease in overall density. This is the relative difference between the density of a healthy material and the density of the current material. The larger this relative difference is, the greater the loss of physical mass and the greater the decrease in structural integrity of the material. The temperature variation of a road surface within a day is relatively small. For healthy, dense materials, the thermal inertia is high, and the temperature rises slowly after absorbing solar energy and dissipates slowly at night. For degraded, loose, and porous materials, the thermal inertia is low, and the temperature rises rapidly after absorbing heat during the day and dissipates rapidly at night. Therefore, the temperature variation of a road surface within a day is relatively large. This is the ratio between the temperature change of the road surface within a day and the ambient temperature. A larger ratio indicates a more porous internal structure and the presence of defects (such as cracks and voids) in the road surface. , and Multiplying these values ​​yields a material degradation index. The higher the index, the greater the degree of material degradation in the highway area; the closer the index is to 0, the less the degree of material degradation in the highway area.

[0057] In this way, material degradation indicators can be determined by the density of healthy materials, current material density, daytime surface temperature, nighttime surface temperature, ambient temperature, visible light band reflection energy, and infrared band reflection energy. Based on multispectral energy differences and the physical quality and thermal inertia characteristics of materials, non-destructive quantitative assessment of internal material degradation can be achieved, reducing traffic accidents and road damage caused by material degradation and improving the safety of testing.

[0058] According to an embodiment of the present invention, in step S8, the highway sections that need maintenance are determined based on the comprehensive crack index, the road surface smoothness index, and the material degradation index.

[0059] Figure 5 An exemplary flowchart illustrating the determination of highway sections requiring maintenance according to an embodiment of the present invention is shown.

[0060] According to an embodiment of the present invention, step S8 includes: step S81, weighted summing of the crack comprehensive index, the road surface smoothness index and the material degradation index to determine the quality index of multiple highway sections; step S82, determining the highway sections that need maintenance based on the quality index and preset quality index.

[0061] According to one embodiment of the present invention, for example, the comprehensive crack index is assigned a weight of 0.4, the pavement smoothness index is assigned a weight of 0.3, and the material degradation index is assigned a weight of 0.3. If the quality index of a certain highway section is greater than a preset quality index (e.g., 3.6), then the highway section is determined to be a highway section that needs maintenance.

[0062] The UAV-based highway quality inspection method according to embodiments of the present invention divides the target highway into multiple highway sections for inspection, reducing blind spots and enabling timely detection of problems. By using UAVs equipped with multiple inspection devices to collect various data, manual section-by-section inspection is eliminated, improving inspection efficiency. By using comprehensive crack indices, pavement smoothness indices, and material degradation indices, the highway sections requiring maintenance are identified, improving maintenance efficiency and reducing maintenance costs. Comprehensive inspection of highway quality based on cracks, smoothness, and material degradation improves the comprehensiveness, accuracy, and safety of the inspection. When determining the comprehensive crack indices, image height, image width, and crack feature parameters are used to determine the comprehensive crack indices, more accurately assessing the crack condition and describing the degree of crack coverage within the highway area, enabling timely detection of damage problems in the highway area. When determining the pavement smoothness indices, preset horizontal intervals, elevation values, and curvature change rates are used to determine the pavement smoothness indices. Combining the curvature change rate with elevation changes, and considering both vertical and longitudinal smoothness characteristics of the pavement, provides a more comprehensive characterization of pavement fluctuations, improving the comprehensiveness and reliability of the inspection results. When determining material degradation indicators, the indicators can be determined by the density of healthy materials, the current density of materials, the surface temperature during the day, the surface temperature at night, the ambient temperature, the reflected energy in the visible light band, and the reflected energy in the infrared band. Based on the differences in multispectral energy and the physical quality and thermal inertia characteristics of materials, a non-destructive quantitative assessment of internal material degradation can be achieved, reducing traffic accidents and road damage caused by material degradation and improving the safety of testing.

[0063] Figure 6An exemplary block diagram of a UAV-based highway quality inspection system according to an embodiment of the present invention is shown. The system includes: a highway baseline 3D model module, used to acquire 3D coordinate data of a target highway through a geographic information system, establish a highway baseline 3D model, and divide the target highway into multiple highway sections; a flight setting module, used to set the flight parameters and flight path of the UAV according to the highway baseline 3D model; and a highway section data module, used to carry multiple detection devices on the UAV and synchronously collect highway section data of the highway sections during flight, wherein the detection devices include a high-resolution optical camera, a 3D laser scanner, and a multispectral sensor. The highway section data includes optical images, 3D point cloud data, visible light band reflection energy, and infrared band reflection energy; a crack comprehensive index module is used to determine the crack comprehensive index based on the optical images; a pavement digital elevation model module is used to construct a pavement digital elevation model based on the 3D point cloud data; a pavement smoothness index module is used to determine the pavement smoothness index based on the pavement digital elevation model; a material degradation index module is used to determine the material degradation index based on the visible light band reflection energy and the infrared band reflection energy; and a maintenance module is used to determine the highway sections requiring maintenance based on the crack comprehensive index, the pavement smoothness index, and the material degradation index.

[0064] This invention can be a method, apparatus, system, and / or computer program product. The computer program product may include a computer-readable storage medium having computer-readable program instructions loaded thereon for performing various aspects of the invention.

[0065] Those skilled in the art should understand that the embodiments of the present invention described above and shown in the accompanying drawings are merely examples and do not limit the present invention. The objectives of the present invention have been fully and effectively achieved. The functions and structural principles of the present invention have been demonstrated and explained in the embodiments, and any variations or modifications may be made to the implementation of the present invention without departing from the stated principles.

Claims

1. A method for highway quality inspection based on unmanned aerial vehicles (UAVs), characterized in that, include: The three-dimensional coordinate data of the target highway is obtained through a geographic information system, a three-dimensional benchmark model of the highway is established, and the target highway is divided into multiple highway sections. Based on the aforementioned 3D model of the highway reference, the flight parameters and flight path of the UAV are set. The UAV is equipped with multiple detection devices, which simultaneously collect highway section data during flight. These detection devices include a high-resolution optical camera, a 3D laser scanner, and a multispectral sensor. The highway section data includes optical images, 3D point cloud data, visible light band reflection energy, and infrared band reflection energy. Based on the optical images, a comprehensive crack index is determined. Based on the 3D point cloud data, a digital elevation model of the road surface is constructed. Based on the digital elevation model of the road surface, a road surface smoothness index is determined. Based on the visible light band reflection energy and the infrared band reflection energy, a material degradation index is determined. Based on the comprehensive crack index, the pavement smoothness index, and the material degradation index, determine the highway sections requiring maintenance; based on the pavement digital elevation model, determine the pavement smoothness index, including: randomly selecting multiple first lines parallel to the highway centerline from the pavement digital elevation model; extracting multiple sampling points on the first lines at preset horizontal intervals and obtaining the coordinates of the sampling points; obtaining the elevation value and curvature change rate of the sampling points based on the coordinates of the sampling points; determining the pavement smoothness index based on the preset horizontal interval, the elevation value, and the curvature change rate; determining the pavement smoothness index based on the preset horizontal interval, the elevation value, and the curvature change rate, including: according to the formula: Determine the road surface smoothness index R, where, Let be the rate of curvature change at the j-th sampling point of the i-th first line. To preset the rate of change of curvature, Let be the elevation value of the (j+1)th sampling point of the i-th first line. Let be the elevation value of the j-th sampling point of the i-th first line, d be the preset horizontal interval, and K be the number of first lines. Let K be the number of sampling points for the i-th first line, i ≤ K, j ≤ K. And i, j, K and All are positive integers, and min is the function that takes the minimum value.

2. The highway quality inspection method based on unmanned aerial vehicles (UAVs) according to claim 1, characterized in that, Determining a comprehensive crack index based on the optical image includes: preprocessing the optical image to obtain image height, image width, and crack feature parameters, wherein the crack feature parameters include crack length and average crack width; and determining the comprehensive crack index based on the image height, the image width, and the crack feature parameters.

3. The highway quality inspection method based on unmanned aerial vehicles (UAVs) according to claim 2, characterized in that, Based on the image height, the image width, and the crack feature parameters, a comprehensive crack index is determined, including: according to the formula: Determine the comprehensive crack index C, where, The length of the crack. The average width of the crack. Image height, This represents the image width.

4. The highway quality inspection method based on unmanned aerial vehicles (UAVs) according to claim 1, characterized in that, The material degradation index is determined based on the visible light band reflection energy and the infrared band reflection energy, including: obtaining the healthy material density of the target highway when it was built; obtaining the current material density of the highway section through non-destructive testing methods; obtaining the daytime and nighttime surface temperatures of the highway section; obtaining the ambient temperature of the daytime inspection; and determining the material degradation index based on the healthy material density, the current material density, the daytime surface temperature, the nighttime surface temperature, the ambient temperature, the visible light band reflection energy, and the infrared band reflection energy.

5. The highway quality inspection method based on unmanned aerial vehicles (UAVs) according to claim 4, characterized in that, The material degradation index is determined based on the healthy material density, the current material density, the daytime surface temperature, the nighttime surface temperature, the ambient temperature, the visible light band reflectance energy, and the infrared band reflectance energy, including: according to the formula: Determine the material degradation index M, where, For visible light band reflected energy, For infrared band reflected energy, For the density of healthy materials, Given the current material density, This refers to the surface temperature during the day. The surface temperature at night. The ambient temperature.

6. The method for highway quality inspection based on unmanned aerial vehicles (UAVs) according to claim 1, characterized in that, The process of determining the highway sections requiring maintenance based on the comprehensive crack index, the pavement smoothness index, and the material degradation index includes: weighted summation of the comprehensive crack index, the pavement smoothness index, and the material degradation index to determine the quality indexes for multiple highway sections; and determining the highway sections requiring maintenance based on the quality indexes and preset quality indexes.

7. A UAV-based highway quality inspection system, used to execute the UAV-based highway quality inspection method as described in any one of claims 1-6, characterized in that, include: The highway baseline 3D model module is used to acquire 3D coordinate data of the target highway through a geographic information system, establish a highway baseline 3D model, and divide the target highway into multiple highway segments; the flight setting module is used to set the flight parameters and flight path of the UAV based on the highway baseline 3D model; the highway segment data module is used to carry multiple detection devices on the UAV and simultaneously collect highway segment data during flight, wherein the detection devices include a high-resolution optical camera, a 3D laser scanner, and a multispectral sensor, and the highway segment data includes optical images, 3D point cloud data, etc. The system includes: a visible light band reflection energy and an infrared band reflection energy module; a crack comprehensive index module for determining a crack comprehensive index based on the optical image; a road surface digital elevation model module for constructing a road surface digital elevation model based on the three-dimensional point cloud data; a road surface smoothness index module for determining a road surface smoothness index based on the road surface digital elevation model; a material degradation index module for determining a material degradation index based on the visible light band reflection energy and the infrared band reflection energy; and a maintenance module for determining the highway sections requiring maintenance based on the crack comprehensive index, the road surface smoothness index, and the material degradation index.

Images