Road service state evaluation method, device and equipment based on low-altitude digital image and medium

Abstract

The application provides a road service state evaluation method, device, equipment and medium based on low-altitude digital images, and relates to the technical field of road state evaluation. The method comprises the following steps: acquiring a low-altitude digital image of a road; extracting crack features, drainage features and road surface settlement features of the road from the low-altitude digital image, and determining a comprehensive damage factor of the road according to the crack features, the drainage features and the road surface settlement features; determining a change rate of the comprehensive damage factor with time in a preset time period, and determining a decay rate of the road according to the change rate of the comprehensive damage factor with time; and determining a road service state based on the current comprehensive damage factor and the decay rate. The application can more efficiently and accurately evaluate the road service state.

Description

Technical Field

[0001] This invention relates to the field of road condition assessment technology, and in particular to a method, apparatus, equipment and medium for assessing the service condition of roads based on low-altitude digital images. Background Technology

[0002] Road service condition assessment is a core component of the full life-cycle management of road engineering. Its purpose is to comprehensively understand the road's usage status and structural performance through scientific and systematic testing and evaluation, providing a basis for decision-making regarding road maintenance, repair, reconstruction, and even new construction planning.

[0003] Traditional road service condition assessment methods based on low-altitude digital images have significant limitations: firstly, their detection scope often focuses only on a single indicator like road cracks, failing to comprehensively reflect the true condition of the road and resulting in a significant reduction in accuracy; secondly, crack identification and recording rely excessively on manual visual judgment and traditional measurement tools, which is not only inefficient and lacks data accuracy but also requires substantial manpower. More importantly, manual inspection results are easily influenced by the subjective factors of the inspectors, making it difficult to guarantee stability and reliability. Therefore, developing a more efficient and accurate comprehensive road service condition assessment method has become an urgent need for the industry. Summary of the Invention

[0004] In view of this, embodiments of the present invention provide a method, apparatus, device and medium for assessing the service status of roads based on low-altitude digital images, so as to evaluate the service status of roads more efficiently and accurately.

[0005] In a first aspect, embodiments of the present invention provide a method for assessing the service status of roads based on low-altitude digital images, comprising: Acquire low-altitude digital images of the road; From the low-altitude digital image, the crack features, drainage features, and pavement settlement features of the road are extracted, and the comprehensive damage factor of the road is determined based on the crack features, drainage features, and pavement settlement features. Determine the rate of change of the comprehensive damage factor over time within a preset time period, and determine the decay rate of the road based on the rate of change of the comprehensive damage factor over time. Based on the current comprehensive damage factor and the decay rate, the road service status is determined.

[0006] In one possible implementation, determining the comprehensive damage factor of the road based on the crack characteristics, the drainage characteristics, and the pavement settlement characteristics includes: Based on the crack characteristics, determine the pavement structure condition indicators; Based on the drainage characteristics, determine the drainage function indicators; Based on the aforementioned pavement settlement characteristics, the roadbed stability index is determined; Based on the first preset weight, the road surface structure condition index, the drainage function index, and the roadbed stability index are weighted and summed to obtain the comprehensive damage factor of the road.

[0007] In one possible implementation, the crack features include at least one of the following: crack length, width, and depth; The step of determining the pavement structure condition index based on the crack characteristics includes: Calculate the total length of the cracks based on the length of each crack in the road, and determine the crack density based on the ratio of the total crack length to the road area. The average width of the cracks is determined based on the width of each crack in the road. The average depth of the cracks is determined based on the depth of each crack in the road. After standardizing the crack density, the average crack width, and the average crack depth, the pavement structure condition indicators are determined using a machine learning regression model.

[0008] In one possible implementation, the drainage feature includes: water accumulation coverage; The step of determining drainage function indicators based on the drainage characteristics includes: The water coverage rate is standardized and used as the drainage function indicator.

[0009] In one possible implementation, the pavement settlement characteristics include: pavement settlement rate and maximum settlement amount; The determination of roadbed stability indices based on the road surface settlement characteristics includes: After standardizing the pavement settlement rate and the maximum settlement, the roadbed stability index is obtained by weighted summation based on the second preset weight.

[0010] In one possible implementation, extracting the depth of the cracks in the road from the low-altitude digital image includes: The gray-level gradient at the crack edge is calculated using the Sobel operator; The texture roughness of the crack is calculated using the gray-level co-occurrence matrix; Calculate the width gradient of the crack along its length; The grayscale gradient, texture roughness, width gradient, and image pixel features are fused and input into a pre-trained depth measurement model to output the depth of the cracks in the road.

[0011] In one possible implementation, after outputting the depth of the crack in the road, the method further includes: Obtain the type of the road; Determine the depth correction factor based on the type described; Based on the depth correction factor, the depth output by the depth calculation model is corrected, and the corrected depth is taken as the true depth of the crack in the road.

[0012] Secondly, embodiments of the present invention provide a road service status assessment device based on low-altitude digital images, comprising: The acquisition module is used to acquire low-altitude digital images of roads; The first processing module is used to extract crack features, drainage features and road surface settlement features of the road from the low-altitude digital image, and determine the comprehensive damage factor of the road based on the crack features, drainage features and road surface settlement features. The second processing module is used to determine the rate of change of the comprehensive damage factor over time within a preset time period, and to determine the decay rate of the road based on the rate of change of the comprehensive damage factor over time. The third processing module is used to determine the road service status based on the current comprehensive damage factor and the decay rate.

[0013] Thirdly, embodiments of the present invention provide an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the method described in the first aspect or any possible implementation thereof.

[0014] Fourthly, embodiments of the present invention provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the method described in the first aspect or any possible implementation thereof.

[0015] Fifthly, embodiments of the present invention provide a computer program product, including a computer program that, when executed by a processor, implements the method described in the first aspect or any possible implementation thereof.

[0016] The advantages of this invention compared to the prior art are: This invention uses low-altitude digital image acquisition as its core data foundation. By accurately extracting road crack features, drainage function features, and pavement settlement features, it constructs and quantifies a comprehensive road damage factor. This comprehensive damage factor intuitively reflects the current static damage state of the road, achieving a comprehensive characterization of the existing road defects. Based on this, by calculating the rate of change of the comprehensive damage factor within a preset time period, the road decay rate is determined, dynamically capturing the deterioration trend of road performance over time. Finally, through the synergistic analysis of the comprehensive damage factor and decay rate, a scientific assessment of the road's service condition is completed. This invention significantly improves the efficiency and accuracy of road condition assessment through automated low-altitude digital image recognition technology. Compared to traditional methods, it not only overcomes the limitation of focusing solely on a single road crack indicator but also achieves a comprehensive, multi-dimensional, and accurate reflection of the road's actual service condition by integrating drainage features, pavement settlement features, and dynamic change trends, providing more reliable technical support for road maintenance decisions. Attached Figure Description

[0017] Figure 1 This is a flowchart illustrating the implementation of the road service status assessment method based on low-altitude digital images provided in this embodiment of the invention. Figure 2 This is a flowchart of the depth extraction process provided in an embodiment of the present invention; Figure 3 This is a schematic diagram of a road service status assessment device based on low-altitude digital images provided in an embodiment of the present invention; Figure 4 This is a schematic diagram of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0018] The embodiments of the present invention will now be described in detail with reference to the accompanying drawings.

[0019] See Figure 1 The document illustrates a flowchart of the road service status assessment method based on low-altitude digital images provided in an embodiment of the present invention, which is described in detail below: Step S101: Obtain a low-altitude digital image of the road.

[0020] In this embodiment, low-altitude digital images of the road can be acquired multiple times via drone within a certain time period (e.g., one month) to provide a basis for subsequent data analysis. Since this solution requires calculating drainage characteristics, data can be collected once after each rainfall.

[0021] For example, the data collection process includes: Flight path design: The drone adopts an "S" shaped round-trip flight path, and the flight altitude is dynamically adjusted according to the road width (for example, 10-15m for single-lane roads and 15-30m for multi-lane roads). The forward overlap is ≥80%, and the lateral overlap is ≥70%, to ensure that there are no blind spots in the image stitching.

[0022] Data acquisition conditions control: Select a period of time with uniform lighting after rain, and avoid rainy days, foggy days and strong backlight environments; wind speed ≤ level 5 to ensure that the image has no motion blur.

[0023] Data annotation: Synchronously record data such as collection time, location, weather parameters, road type (asphalt / cement), and maintenance history to provide an environmental baseline for subsequent analysis.

[0024] In this embodiment, a multi-rotor UAV with high-precision GPS positioning capability can be selected, with a positioning error ≤10cm and a flight time ≥30 minutes, meeting the requirements for continuous long-distance road data collection. This UAV system integrates core components such as an industrial-grade SLR camera, a high-precision inertial measurement unit, a large-capacity data storage unit, and a real-time communication unit to achieve automated shooting, accurate storage, and efficient transmission of low-altitude digital images of roads, providing high-quality raw data support for subsequent feature extraction and analysis.

[0025] In some embodiments, image preprocessing and correction can also be performed on the acquired low-altitude digital images of roads, for example: Coordinate transformation: Combining UAV positioning data and high-precision inertial measurement unit attitude data, the image pixel coordinates are converted into geodetic coordinates, and the transformation accuracy is optimized by ground control points.

[0026] Radiometric correction: Homomorphic filtering algorithm is used to eliminate the effects of uneven illumination, and dark channel prior method is used to remove haze interference, so that the mean deviation of image grayscale is ≤5%.

[0027] Image stitching and cropping: Based on feature point matching algorithms, stitching software is used to stitch images together to generate a panoramic orthophoto of the road. According to the actual road boundaries, non-road areas (such as green belts and shoulders) are cropped out, retaining the effective road surface area for subsequent defect identification.

[0028] Step S102: Extract the crack features, drainage features, and pavement settlement features of the road from the low-altitude digital image, and determine the comprehensive damage factor of the road based on the crack features, drainage features, and pavement settlement features.

[0029] In this embodiment of the invention, for crack detection and identification, the YOLOv8 model can be used to detect low-altitude digital images. Training is performed using labeled samples such as "transverse cracks, longitudinal cracks, mesh cracks, and block cracks" to output bounding boxes of crack regions. The high reflectivity (grayscale value > 200) and low texture (variance < 10) of accumulated water can be utilized to segment water-covered areas using an adaptive thresholding algorithm. Settlement areas experience texture stretching due to road inclination (dense texture in concave areas and sparse texture in convex areas). Candidate regions can be located and settlement amounts predicted through texture feature clustering or entropy analysis. After identifying these regions, further feature recognition is performed.

[0030] In this embodiment, crack characteristics, drainage characteristics, and pavement settlement characteristics are the three core dimensions constituting the comprehensive road damage factor. They reflect the "current state, causes, and trends" of road damage from three levels: structural integrity, environmental durability, and deep stability, respectively, jointly supporting the comprehensive quantitative assessment of the road's service status by the comprehensive damage factor. Cracks are the most direct manifestation of road damage; their characteristic parameters are directly related to the integrity of the pavement structure and the risk of functional failure, serving as the core basis for measuring the "current damage state" in the comprehensive damage factor. Drainage characteristics are directly related to the road's functional state. Settlement is a direct manifestation of structural failure of the subgrade or base course; its characteristic parameters reflect the fundamental reduction in the road's bearing capacity, serving as the core basis for measuring the "safety risk level" in the comprehensive damage factor. Based on this, this embodiment constructs a three-level evaluation system: "target layer - criterion layer - indicator layer." Target layer: Overall service status of roads.

[0031] Criterion layer: pavement structure condition, drainage function, and subgrade stability.

[0032] Indicator layer: crack density, average crack width, average crack depth, water coverage, pavement settlement rate, and maximum settlement.

[0033] This embodiment focuses on cracks as a core structural defect. By quantifying three key parameters—crack density (total length / road area), average width, and average depth—and standardizing them (eliminating dimensional differences), the data is input into a machine learning regression model (such as linear regression or random forest) to fit the nonlinear relationship between features and structural damage, outputting pavement structural condition indicators to quantify the degree of damage to the surface and base layers. Waterlogging coverage (waterlogged area / total road area) is used as a core indicator, and after standardization, it is directly used as a drainage function indicator, intuitively reflecting the actual effectiveness of the road drainage system. For deep subgrade damage, two parameters are selected: pavement settlement rate (settlement area / total road area) and maximum settlement. After standardization, a weighted summation is used to comprehensively assess the degree of subgrade stability degradation.

[0034] Finally, the three dimensions of indicators are weighted and summed to obtain a comprehensive damage factor reflecting the overall damage state of the road. For example, the damage factor D is defined as 0.4 × crack index + 0.2 × drainage index + 0.4 × settlement index (the weights can be determined by the analytic hierarchy process).

[0035] Step S103: Determine the rate of change of the comprehensive damage factor over time within a preset time period, and determine the road decay rate based on the rate of change of the comprehensive damage factor over time.

[0036] The comprehensive damage factor is a static quantitative indicator reflecting the current damage state of a road (its value range is typically 0-1, with larger values ​​indicating more severe damage). The rate of change over a preset time period (e.g., one month) essentially captures the dynamic evolution trend of damage through time-series data. Traditional road assessments rely solely on the damage state at a single point in time, failing to distinguish between "long-term slow deterioration" and "short-term rapid deterioration." The decay rate in this embodiment can be used to predict the future damage state of roads, identify "high-risk road sections" in advance, and achieve a comprehensive "current state-trend" assessment of road service status.

[0037] Step S104: Determine the road service status based on the current comprehensive damage factor and decay rate.

[0038] Neither damage factor (static) nor decay rate (dynamic) alone can fully determine the service condition. For example: A certain road has a comprehensive damage factor D=0.5 (moderate damage) and a decay rate V=0.05 (slow decay) – although there is damage, it is stable and can be routinely maintained. Another comprehensive damage factor, D=0.4 (moderate damage), but decay rate, V=0.25 (rapid decay) – although the current damage is not severe, it may deteriorate to a dangerous state in the short term, requiring urgent intervention.

[0039] For example, as shown in Table 1, this embodiment constructs a two-dimensional evaluation framework of "current damage level + performance degradation rate" - the damage factor reflects the current static damage level of the road, and the decay rate reflects the dynamic deterioration trend of performance over time. The two work together to more comprehensively determine whether the road is stable, whether emergency intervention is needed, or whether it is in a controllable slow decay stage.

[0040] Table 1 Road Service Status Evaluation Table

[0041] According to Table 1, the road assessment and maintenance logic includes: (1) Prioritize the combination of "high damage + high rate": When D>0.6 and V>0.2, the road has entered the stage of "severe damage and rapid deterioration", which may be accompanied by structural risks (such as roadbed instability). Emergency measures (such as temporary traffic restrictions and local emergency repairs) should be taken immediately, and a reconstruction plan for the entire road section should be initiated.

[0042] (2) Be wary of the potential risks of "medium damage + high rate": The current damage to this type of road has not reached its limit, but the rate of decay is rapid (e.g., cracks expand rapidly due to drainage failure). Without intervention, it may reach a severe state within 6 to 12 months. A targeted repair plan (such as replacing with a permeable base course and sealing and waterproofing cracks) needs to be developed through "cause diagnosis" (e.g., testing the drainage system and roadbed moisture content).

[0043] (3) Differentiate the stability of "high damage + low rate": If a road is severely damaged for a long time (e.g., D=0.7) but the decay rate is extremely low (V=0.03), it may be "old damage stabilization" (e.g., cracks have penetrated the structural layer and the damage no longer extends). The timing of major repairs can be determined according to traffic demand (e.g., non-main roads can be delayed for 1-2 years).

[0044] (4) Emphasize early intervention with "low damage + high rate": If a newly constructed road exhibits a D=0.2 but V=0.15 within a short period (e.g., within 3 years of opening to traffic), it may be due to "early rapid degradation" caused by construction defects (e.g., insufficient compaction of the base layer). Local reinforcement (e.g., grouting reinforcement) is needed to curb the degradation and prevent premature entry into the major repair cycle.

[0045] This invention uses low-altitude digital image acquisition as its core data foundation. By accurately extracting road crack features, drainage function features, and pavement settlement features, it constructs and quantifies a comprehensive road damage factor. This comprehensive damage factor intuitively reflects the current static damage state of the road, achieving a comprehensive characterization of the existing road defects. Based on this, by calculating the rate of change of the comprehensive damage factor within a preset time period, the road decay rate is determined, dynamically capturing the deterioration trend of road performance over time. Finally, through the synergistic analysis of the comprehensive damage factor and decay rate, a scientific assessment of the road's service condition is completed. This invention significantly improves the efficiency and accuracy of road condition assessment through automated low-altitude digital image recognition technology. Compared to traditional methods, it not only overcomes the limitation of focusing solely on a single road crack indicator but also achieves a comprehensive, multi-dimensional, and accurate reflection of the road's actual service condition by integrating drainage features, pavement settlement features, and dynamic change trends, providing more reliable technical support for road maintenance decisions.

[0046] Since low-altitude digital images are 2D, this embodiment proposes a depth calculation method to extract crack depth information, such as... Figure 2 As shown.

[0047] Step S201: Deeper cracks typically have clearer edges (more drastic grayscale changes). The grayscale gradient at the crack edge is calculated using the Sobel operator: The gradient magnitude of the crack region is calculated using the Sobel operator. , , (x and y direction gradients); calculate the gradient distribution of the crack edge region (segmented crack outline); the quantification index can be: average gradient and / or maximum gradient value.

[0048] In step S202, cracks with greater depth may have more complex surface textures due to irregular internal expansion. By extracting sub-images within the crack area, the texture roughness of the crack area, such as contrast, entropy, and energy, is calculated using a gray-level co-occurrence matrix.

[0049] Step S203: Since there is a strong correlation between crack surface width and depth, a skeleton extraction algorithm is used to obtain the central skeleton line of the crack. N sampling points are uniformly selected along the skeleton line. For each sampling point, the distance to the crack edge (i.e., width) perpendicular to the skeleton direction is calculated. The width change rate is calculated along the crack length direction to obtain the width gradient. Cracks with greater depth exhibit more gradual width changes due to more uniform structural damage.

[0050] Step S204 concludes by using a machine learning / deep learning model pre-trained with a large amount of labeled data (e.g., image features of 10,000 cracks + ultrasonically measured depth) to learn the nonlinear mapping between "image feature combination and crack depth". Gray-level gradient, texture roughness, width gradient, and image pixel features are fused and input into a pre-trained depth measurement model to output the depth of cracks in the road. Common models include convolutional neural networks, random forest regression, and gradient boosting trees.

[0051] In some embodiments, considering that the material properties of roads (asphalt pavement, cement concrete pavement, gravel pavement, etc.) directly affect the correlation between the appearance of cracks in images and their actual depth, coefficients are set for specific road types to correct the deviation between the "original output of the depth measurement model" and the "actual depth." The magnitude of these coefficients is determined by the characteristics of the road type, essentially quantifying the "degree of interference of different road types on the correlation between the visual features of cracks and their actual depth." For example, if the model predicts the depth of a crack in an asphalt pavement to be 5mm, with a corresponding correction factor of 1.2, then the actual depth is 5 × 1.2 = 6mm, which is closer to the actual depth obtained through ultrasonic testing (assuming the actual depth is 6.2mm). Using prior knowledge of road types, the correction factor eliminates the interference of different material / structural properties on crack depth measurement. From "identifying the road type" to "determining the correction factor" and then to "correcting the depth result," a set of error compensation mechanisms combining scene characteristics is formed, ultimately outputting a crack depth closer to the actual physical state, providing more reliable data support for road maintenance decisions (such as repair priority and material selection).

[0052] It should be understood that the sequence number of each step in the above embodiments does not 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.

[0053] The following are device embodiments of the present invention. For details not described in detail, please refer to the corresponding method embodiments described above.

[0054] Figure 3 A schematic diagram of the road service status assessment device based on low-altitude digital images provided in an embodiment of the present invention is shown. For ease of explanation, only the parts related to the embodiment of the present invention are shown, and are described in detail below: like Figure 3 As shown, the road service status assessment device 3 based on low-altitude digital images includes: Acquisition module 31 is used to acquire low-altitude digital images of the road; The first processing module 32 is used to extract crack features, drainage features and pavement settlement features of the road from the low-altitude digital image, and determine the comprehensive damage factor of the road based on the crack features, drainage features and pavement settlement features. The second processing module 33 is used to determine the rate of change of the comprehensive damage factor over time within a preset time period, and to determine the road decay rate based on the rate of change of the comprehensive damage factor over time. The third processing module 34 is used to determine the road service status based on the current comprehensive damage factor and decay rate.

[0055] In one possible implementation, the first processing module 32 is used for: Based on the characteristics of the cracks, determine the pavement structural condition indicators; Determine drainage function indicators based on drainage characteristics; Determine the roadbed stability index based on the road surface settlement characteristics; Based on the first preset weight, the pavement structure condition index, drainage function index and subgrade stability index are weighted and summed to obtain the comprehensive damage factor of the road.

[0056] In one possible implementation, the crack features include at least one of the following: crack length, width, and depth; The first processing module 32 is used for: Calculate the total length of the cracks based on the length of each crack in the road, and determine the crack density based on the ratio of the total crack length to the road area. Determine the average width of the cracks based on the width of each crack in the road. Determine the average depth of the cracks based on the depth of each crack in the road. After standardizing the crack density, average crack width, and average crack depth, the pavement structure condition indicators are determined by machine learning regression models.

[0057] In one possible implementation, the drainage features include: waterlogging coverage; The first processing module 32 is used for: After standardizing the water accumulation coverage rate, it is used as an indicator of drainage function.

[0058] In one possible implementation, pavement settlement characteristics include: pavement settlement rate and maximum settlement. The first processing module 32 is used for: After standardizing the pavement settlement rate and maximum settlement, the roadbed stability index is obtained by weighted summation based on the second preset weight.

[0059] In one possible implementation, the first processing module 32 is used for: The gray-level gradient at the crack edge is calculated using the Sobel operator; The texture roughness of the crack is calculated using the gray-level co-occurrence matrix; Calculate the width gradient of the crack along its length; The grayscale gradient, texture roughness, width gradient, and image pixel features are fused together and input into a pre-trained depth measurement model to output the depth of cracks in the road.

[0060] The first processing module 32 is also used for: Get the road type; Determine the depth correction factor based on the type; Based on the depth correction factor, the depth output by the depth measurement model is corrected, and the corrected depth is taken as the true depth of the cracks in the road.

[0061] This invention uses low-altitude digital image acquisition as its core data foundation. By accurately extracting road crack features, drainage function features, and pavement settlement features, it constructs and quantifies a comprehensive road damage factor. This comprehensive damage factor intuitively reflects the current static damage state of the road, achieving a comprehensive characterization of the existing road defects. Based on this, by calculating the rate of change of the comprehensive damage factor within a preset time period, the road decay rate is determined, dynamically capturing the deterioration trend of road performance over time. Finally, through the synergistic analysis of the comprehensive damage factor and decay rate, a scientific assessment of the road's service condition is completed. This invention significantly improves the efficiency and accuracy of road condition assessment through automated low-altitude digital image recognition technology. Compared to traditional methods, it not only overcomes the limitation of focusing solely on a single road crack indicator but also achieves a comprehensive, multi-dimensional, and accurate reflection of the road's actual service condition by integrating drainage features, pavement settlement features, and dynamic change trends, providing more reliable technical support for road maintenance decisions.

[0062] Figure 4 This is a schematic diagram of an electronic device provided in an embodiment of the present invention. For example... Figure 4 As shown, the electronic device 4 in this embodiment includes a processor 40 and a memory 41. The memory 41 stores a computer program 42. When the processor 40 executes the computer program 42, it implements the steps in the various method embodiments described above. Alternatively, when the processor 40 executes the computer program 42, it implements the functions of each module in the various device embodiments described above.

[0063] For example, computer program 42 may be divided into one or more modules / units, which are stored in memory 41 and executed by processor 40 to complete the present invention. The one or more modules / units may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of computer program 42 in electronic device 4.

[0064] Electronic device 4 may include, but is not limited to, processor 40 and memory 41. Those skilled in the art will understand that... Figure 4 This is merely an example of electronic device 4 and does not constitute a limitation on electronic device 4. It may include more or fewer components than shown, or combine certain components, or different components. For example, electronic device 4 may also include input / output devices, network access devices, buses, etc.

[0065] The processor 40 can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor.

[0066] The memory 41 can be an internal storage unit of the electronic device 4, such as a hard disk or RAM. The memory 41 can also be an external storage device of the electronic device 4, such as a plug-in hard disk, Smart Media Card (SMC), Secure Digital (SD) card, or Flash Card. Furthermore, the memory 41 can include both internal and external storage units of the electronic device 4. The memory 41 is used to store the computer program 42 and other programs and data required by the electronic device 4. The memory 41 can also be used to temporarily store data that has been output or will be output.

[0067] For the sake of simplicity and clarity, only the above-described functional modules / units are used as examples. In practical applications, the functions described above can be assigned to different functional modules / units as needed. These modules / units can be implemented in hardware, software, or a combination of both.

[0068] This invention also provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it implements the methods described in the above-described method embodiments.

[0069] This invention also provides a computer program product, including a computer program. When the computer program is executed by a processor, it implements the methods described in the above-described method embodiments.

[0070] Computer programs include computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. Computer-readable media can include: any entity or device capable of carrying computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc.

[0071] In the above embodiments, the descriptions of each embodiment have their own emphasis. Parts not detailed or described in a particular embodiment can be referred to in the relevant descriptions of other embodiments. Unless otherwise specified or in conflict with logic, the terminology and / or descriptions between different embodiments are consistent and can be referenced interchangeably. Technical features in different embodiments can be combined to form new embodiments based on their inherent logical relationships.

[0072] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included within the protection scope of the present invention.

Claims

1. A method for evaluating the service state of a road based on low-altitude digital images, characterized in that, include: Acquire low-altitude digital images of the road; From the low-altitude digital image, the crack features, drainage features, and pavement settlement features of the road are extracted, and the comprehensive damage factor of the road is determined based on the crack features, drainage features, and pavement settlement features. Determine the rate of change of the comprehensive damage factor over time within a preset time period, and determine the decay rate of the road based on the rate of change of the comprehensive damage factor over time. Based on the current comprehensive damage factor and the decay rate, the road service status is determined.

2. The low-altitude digital image-based road service state evaluation method according to claim 1, characterized by, The determination of the comprehensive damage factor of the road based on the crack characteristics, drainage characteristics, and pavement settlement characteristics includes: Based on the crack characteristics, determine the pavement structure condition indicators; Based on the drainage characteristics, determine the drainage function indicators; Based on the aforementioned pavement settlement characteristics, the roadbed stability index is determined; Based on the first preset weight, the road surface structure condition index, the drainage function index, and the roadbed stability index are weighted and summed to obtain the comprehensive damage factor of the road.

3. The road service status assessment method based on low-altitude digital images according to claim 2, characterized in that, The crack features include at least one of the following: crack length, width, and depth; The step of determining the pavement structure condition index based on the crack characteristics includes: Calculate the total length of the cracks based on the length of each crack in the road, and determine the crack density based on the ratio of the total crack length to the road area. The average width of the cracks is determined based on the width of each crack in the road. The average depth of the cracks is determined based on the depth of each crack in the road. After standardizing the crack density, the average crack width, and the average crack depth, the pavement structure condition indicators are determined using a machine learning regression model.

4. The road service status assessment method based on low-altitude digital images according to claim 2, characterized in that, The drainage characteristics include: waterlogging coverage; The step of determining drainage function indicators based on the drainage characteristics includes: The water coverage rate is standardized and used as the drainage function indicator.

5. The road service status assessment method based on low-altitude digital images according to claim 2, characterized in that, The road surface settlement characteristics include: road surface settlement rate and maximum settlement amount; The determination of subgrade stability indices based on the pavement settlement characteristics includes: After standardizing the pavement settlement rate and the maximum settlement, the roadbed stability index is obtained by weighted summation based on the second preset weight.

6. The road service status assessment method based on low-altitude digital images according to any one of claims 2 to 5, characterized in that, Extracting the depth of the cracks in the road from the low-altitude digital image includes: The gray-level gradient at the crack edge is calculated using the Sobel operator; The texture roughness of the crack is calculated using the gray-level co-occurrence matrix; Calculate the width gradient of the crack along its length; The grayscale gradient, texture roughness, width gradient, and image pixel features are fused and input into a pre-trained depth measurement model to output the depth of the cracks in the road.

7. The road service status assessment method based on low-altitude digital images according to claim 6, characterized in that, After outputting the depth of the crack in the road, the method further includes: Obtain the type of the road; Determine the depth correction factor based on the type described; Based on the depth correction factor, the depth output by the depth calculation model is corrected, and the corrected depth is taken as the true depth of the crack in the road.

8. A road service status assessment device based on low-altitude digital images, characterized in that, include: The acquisition module is used to acquire low-altitude digital images of roads; The first processing module is used to extract crack features, drainage features and road surface settlement features of the road from the low-altitude digital image, and determine the comprehensive damage factor of the road based on the crack features, drainage features and road surface settlement features. The second processing module is used to determine the rate of change of the comprehensive damage factor over time within a preset time period, and to determine the decay rate of the road based on the rate of change of the comprehensive damage factor over time. The third processing module is used to determine the road service status based on the current comprehensive damage factor and the decay rate.

9. An electronic device, characterized in that, It includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the method as described in any one of claims 1 to 7.

Images