Road surface health assessment method

Abstract

The embodiment of the invention relates to the technical field of pavement health assessment, in particular to a pavement health assessment method. The method comprises the following steps: acquiring road section data pavement detection data comprising a plurality of road sections, identifying disease types in each road section based on the road section data, acquiring original disease deduction scores and at least one severity evaluation index of each disease type, adjusting the original disease deduction scores by using the severity evaluation indexes to obtain new disease deduction scores, and if the disease types are not less than 2, determining that the new disease deduction scores are not less than 2. And searching a target disease type combination meeting a preset cooperative influence condition, adjusting new disease deducted scores of the disease types included in the target disease type combination, and generating a target lane health index based on the disease deducted scores of all the disease types in all the road sections. According to the embodiment of the invention, original disease deduction scores are corrected through multiple serious evaluation indexes, secondary correction is carried out on disease types with cooperative damage, health indexes capable of accurately representing complex disease influences are constructed, multi-dimensional quantitative evaluation and cooperative effect compensation calculation are realized, and modern road maintenance diagnosis requirements are met.

Description

Technical Field

[0001] The embodiments of the present application relate to the technical field of pavement health assessment, and in particular to a pavement health assessment method. Background Art

[0002] In the field of road maintenance, quantitative assessment of pavement health is a core basis for making scientific maintenance decisions. The PCI (Pavement Condition Index) assessment system, currently widely used in the industry, uses manual or automated methods to identify various pavement defects (such as cracks, potholes, and repairs). Based on pre-set rules, each defect is individually deducted based on its type, severity, and density. The cumulative deductions are then used to calculate a comprehensive PCI score.

[0003] However, the existing PCI assessment system has significant limitations. Its calculation model is essentially a simple linear superposition of deductions for different disease types. This approach is reasonable when the pavement only has a single or a small number of isolated diseases. However, when faced with the complex coexistence of diseases common in actual projects, its assessment results often deviate significantly from the actual road conditions. These flaws lead to a systematic deviation between traditional PCI assessment results and the actual health of the pavement, hindering the optimal allocation of maintenance resources and the effective implementation of preventive maintenance strategies. Summary of the Invention

[0004] One purpose of the embodiments of the present application is to provide a pavement health assessment method to solve the technical problem that there is a systematic deviation between the traditional PCI assessment results of complex diseased pavements and the actual health status of the pavement.

[0005] In a first aspect, an embodiment of the present application provides a pavement health assessment method, comprising: Obtain pavement detection data of a target lane, wherein the target lane includes multiple road sections of equal length, and the pavement detection data includes section data of the multiple road sections. Based on the section data, identify the types of damage contained in the road section, obtain original damage deduction points corresponding to each of the damage types and at least one severity evaluation index corresponding to the pavement disease of each of the disease types, wherein the original damage deduction points are used to indicate the degree of damage caused by the disease of each of the disease types to the road section, adjust the original damage deduction points corresponding to the disease type based on at least one of the severity evaluation indexes to obtain new damage deduction points, and in response to the number of disease types contained in the road section being greater than or equal to 2, search for a target disease type combination that meets a preset collaborative influence condition in at least two of the disease types, adjust the new disease deduction points of the disease types contained in the target disease type combination to obtain the adjusted disease deduction points, and generate a target lane health index for the target lane based on the disease deduction points of all the disease types in all road sections.

[0006] The embodiment of the present application introduces multiple severity evaluation indicators to perform an initial dynamic correction on the original disease deduction value, generating a new disease deduction value that is more in line with the actual degree of damage; then, for disease combinations with synergistic destructive effects in the road surface, a secondary correction is performed on the corrected new disease deduction value based on its coupling mechanism, and finally a target lane health index that accurately characterizes the comprehensive impact of complex diseases is constructed, achieving a dual breakthrough in multi-dimensional disease severity quantitative assessment and synergistic effect compensation calculation, meeting the needs of modern road maintenance for road health status diagnosis, and improving the credibility of health indicators and the scientific nature of maintenance decisions in complex disease scenarios.

[0007] Optionally, adjusting the original disease deduction score corresponding to the disease type based on at least one of the severity evaluation indicators to obtain a new disease deduction score includes: Obtaining at least one corresponding correction coefficient based on at least one of the severity evaluation indicators; Selecting a maximum correction coefficient from at least one of the correction coefficients as a target correction coefficient; The original disease deduction score corresponding to the disease type is adjusted based on the target correction coefficient to obtain a new disease deduction score.

[0008] Optionally, the severity evaluation index includes disease spacing, penetration, and disease development rate, and the correction coefficient includes a spacing correction coefficient and / or a penetration correction coefficient and / or a development rate correction coefficient. The step of obtaining at least one corresponding correction coefficient based on at least one severity evaluation index includes: For the same type of disease, pavement diseases with a disease spacing less than or equal to a preset distance threshold are set as clustered diseases, the total number of diseases of the disease type and the number of clustered diseases of the clustered diseases in the road section are obtained, and the spacing correction coefficient of the disease type is calculated based on the total number of diseases and the number of clustered diseases according to the spacing correction coefficient formula; and / or, the penetration of pavement diseases in the disease type is sorted to obtain the maximum value of the penetration of pavement diseases in the disease type, and the penetration correction coefficient of the disease type is calculated based on the maximum value of the penetration according to the penetration correction coefficient formula; and / or, the development rate of pavement diseases in the disease type is sorted to obtain the maximum value of the disease development rate of pavement diseases in the disease type, and the development rate correction coefficient of the disease type is calculated based on the maximum value of the disease development rate according to the development rate correction coefficient formula.

[0009] The embodiment of the present application obtains the corresponding spacing correction coefficient, penetration correction coefficient and development rate correction coefficient based on at least one severity evaluation index of pavement diseases, which is used to adjust the original disease deduction points of the disease type, thereby realizing a refined and multi-dimensional quantitative consideration of the degree of disease damage, and improving the accuracy and objectivity of the disease deduction results and the ability to characterize the actual road conditions.

[0010] Optionally, the correction coefficient includes a spacing correction coefficient, a penetration correction coefficient, and a development rate correction coefficient, and selecting a maximum correction coefficient as a target correction coefficient from at least one of the correction coefficients includes: The maximum value among the spacing correction coefficient, the penetration correction coefficient and the development rate correction coefficient is selected as the target correction coefficient.

[0011] This embodiment of the application selects the largest correction factor from the damage type's spacing correction factor, penetration correction factor, and growth rate correction factor as the target correction factor to adjust the original damage penalty score for that damage type. This method adheres to the weakest link principle and uses the most unfavorable correction factor for adjustment, ensuring that the assessment results are biased towards safety and preventing the correction results from deviating from the actual situation.

[0012] Optionally, the severity evaluation index includes the disease spacing and / or penetration and / or disease development rate, and obtaining at least one severity evaluation index corresponding to each type of pavement disease includes: Obtain the similar distance between two adjacent pavement diseases of each disease type in the road section, and among one or more similar distances belonging to the same pavement disease, determine the minimum similar distance as the disease distance of the pavement disease, and the disease distance is the minimum distance between adjacent pavement diseases of the same disease type in the same road section; and / or obtain the edge width and edge length of the road section, obtain the lateral extension length and longitudinal extension length of the pavement disease of each disease type in the road section, the lateral extension length is the maximum distance of the pavement disease in the edge width direction, and the longitudinal extension length is the maximum distance of the pavement disease in the edge length direction, and calculate the road A first ratio of the lateral extension length of the surface disease to the edge width is calculated, and a second ratio of the longitudinal extension length of the pavement disease to the edge length is calculated, and the maximum value of the two ratios is determined as the penetration of the pavement disease, and the penetration is the lateral / longitudinal extension ratio of the pavement disease along the road section; and / or, historical pavement detection data is obtained, and the historical pavement detection data includes the section data of the road section in at least the first two preset periods, and the disease development rate of the pavement disease of the disease type is calculated based on the section data of the road section and the historical pavement detection data in combination with linear regression, and the disease development rate is the expansion rate of the area / length of the pavement disease within the preset period.

[0013] The embodiment of the present application introduces serious evaluation indicators such as disease spacing, penetration and disease development rate, and constructs a multi-dimensional evaluation system covering spatial distribution, structural morphology and temporal evolution, which improves the accuracy of disease deduction in representing actual destructive power, provides a solid data foundation for accurately identifying key maintenance areas and optimizing resource allocation strategies, and enhances the reliability of the final pavement condition index's status assessment and maintenance decision-making support.

[0014] Optionally, searching for a target disease type combination that satisfies a preset synergistic impact condition among at least two of the disease types includes: Obtaining a disease coupling coefficient table, wherein the disease coupling coefficient table includes a plurality of disease type combinations and a disease coupling coefficient corresponding to each of the disease type combinations; Randomly selecting a target number of disease type combinations from at least two disease types included in the road section to form candidate disease type combinations; In response to the disease coupling coefficient table containing a disease type combination that is consistent with the candidate disease type combination, it is determined that the candidate disease type meets a preset synergistic influence condition, and the candidate disease type is used as a target disease type combination.

[0015] Optionally, adjusting the new disease deduction points of the disease types included in the target disease type combination to obtain adjusted disease deduction points includes: Based on the disease coupling coefficient table, obtaining the disease coupling coefficient corresponding to the target disease type combination; The new disease deduction points of the disease types included in the target disease type combination are adjusted using the disease coupling coefficient to obtain adjusted disease deduction points.

[0016] The embodiment of the present application introduces a disease coupling coefficient table to obtain the disease coupling coefficient corresponding to the target disease type combination, and based on this, performs a secondary correction on the new disease deduction points of the disease types included in the target disease type combination. The embodiment of the present application systematically incorporates the synergistic destructive effect between different disease types, improves the accuracy of the disease deduction results in representing the actual destructive power of complex diseases, can optimize the integrity of the PCI index calculation, enhance the ability to identify high-risk disease combinations and the targeted formulation of maintenance strategies.

[0017] Optionally, the generating of the target lane health index of the target lane based on the damage deduction points of all the damage types in all road sections includes: Calculating a road health index for each road section based on the deduction points for all types of damage within the road section; Calculate the average of the road health indexes of all road sections to obtain the candidate lane health index; A target lane health indicator of the target lane is generated based on the candidate lane health indicators.

[0018] Optionally, the target lane health index includes a first lane health index, and the target lane further includes a shoulder area and an edge area. Generating the target lane health index of the target lane based on the candidate lane health index includes: Obtain lane health indicators of the shoulder area and lane health indicators of the edge area of ​​each road section; Calculating an average lane health index of the shoulder area in all road sections to obtain the shoulder health index of the target lane; Calculating an average of lane health indicators of edge areas in all road sections to obtain an edge health indicator of the target lane; A weighted calculation is performed on the road shoulder health index, the edge health index, and the candidate lane health index to obtain a first lane health index of the target lane.

[0019] The embodiment of the present application introduces the shoulder health index and the edge health index, and performs weighted fusion calculation of the shoulder health index, the edge health index and the candidate lane health index based on the spatial dimension. This breaks through the limitation of the traditional PCI calculation architecture that only focuses on the lane pavement and ignores the influence of the associated structure. It realizes a comprehensive quantitative assessment of the spatial integrity of the road domain and significantly improves the representation accuracy, spatial correlation and maintenance decision-making support value of the PCI index of the target lane.

[0020] Optionally, the target lane health indicator includes a second lane health indicator, and generating the target lane health indicator of the target lane based on the candidate lane health indicator includes: Obtaining pre-stored historical lane health indicators, wherein the historical lane health indicators include candidate lane health indicators of the previous two preset periods; The candidate lane health index and the historical lane health index are weighted and calculated to obtain the second lane health evaluation index.

[0021] This embodiment of the application performs a weighted fusion calculation of the current candidate lane health index and historical lane health index, fully incorporating information from the time dimension. This method effectively captures and quantifies the dynamic characteristics of lane health, improving the timeliness of the target lane PCI index, its trend prediction capabilities, and its resistance to short-term fluctuations, providing a more reliable basis for forward-looking maintenance planning. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments of the present application. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0023] Figure 1 A schematic flow chart of a pavement health assessment method provided in an embodiment of the present application; Figure 2a A schematic diagram of a mask image of pavement damage on a certain road section provided in an embodiment of the present application; Figure 2b A schematic diagram of another mask image of pavement damage on a certain road section provided in an embodiment of the present application; Figure 3 A schematic diagram of similar distances of road surface defects provided in an embodiment of the present application; Figure 4 A schematic diagram of calculating the lateral and longitudinal extension lengths of pavement defects provided in an embodiment of the present application; Figure 5 It is a structural schematic diagram of a lane area provided by the prior art; Figure 6 This is a structural diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0024] In order to make the purpose, technical solutions and advantages of this application more clearly understood, the present application is further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0025] It should be noted that, if there is no conflict, the various features in the embodiments of the present application can be combined with each other and are all within the scope of protection of the present application. In addition, although the functional modules are divided in the device schematic and the logical order is shown in the flow chart, in some cases, the steps shown or described can be performed in a different order than the module division in the device or the order in the flow chart. Furthermore, the words "first", "second", "third", etc. used in this application do not limit the data and execution order, but only distinguish between the same items or similar items with basically the same functions and effects.

[0026] In the field of pavement engineering, the pavement condition index (PCI) is an important indicator for evaluating the health status of the pavement, and its calculation method has been clearly specified in the existing technology. The existing PCI calculation system is mainly based on quantitative assessment of pavement damage characteristics: the damage to the pavement (such as cracks, potholes, rutting, settlement, etc.) is converted into a calculable value. For different pavement damages, the single deduction value (DV) is determined by looking up the table. Specifically, by looking up the table, static characteristic parameters such as damage type, damage severity, and damage area are obtained. The single deduction value of the pavement damage can be obtained by performing corresponding calculations using a variety of static characteristic parameters. For multiple pavement damages of the same damage type, the one-way deduction value of the damage type is calculated by accumulating the damaged areas of multiple pavement damages. After obtaining the deduction value for each damage, the total deduction value (Total DV) is calculated by simple accumulation. In order to consider the superposition effect of multiple damages, the pavement condition index formula is finally used. , and the PCI value is calculated. Here, α0 and α1 are model coefficients. According to the "Highway Technical Condition Assessment Standard" (JTG 5210-2018), they are typically set at 15.00 and 0.412, respectively, for asphalt pavement assessments. This existing approach is reasonable when only a single or small number of isolated defects exist on the pavement. However, when faced with complex, coexisting defects, a common occurrence in actual projects, the assessment results often deviate significantly from the actual road conditions.

[0027] The inventors also found that the above-mentioned existing technologies have the following defects: 1. Insufficient consideration of the spatial distribution characteristics of defects: the existing PCI calculation model only counts the number and size of pavement damage, but ignores its aggregation in the pavement space; 2. The morphological characteristics of defects are not fully quantified: for example, when considering the impact of cracks and potholes on the pavement, the existing PCI calculation system only calculates the deduction points according to the length of the cracks or the area of ​​the potholes, ignoring the evaluation of the degree of development in the horizontal / vertical direction of the pavement structure; 3. Lack of dynamic evaluation in the time dimension: the existing PCI calculation model is a static instantaneous evaluation, which does not integrate historical disease evolution data and cannot predict the road condition decay trend, resulting in insufficient accuracy in the judgment of the pavement health status, making it difficult to meet the needs of refined maintenance decision-making.

[0028] Hereinafter, the present application provides a road health assessment method, please refer to Figure 1 , Figure 1 : This is a flow chart of a road health assessment method provided in an embodiment of the present application. The embodiment of the present application includes the following steps: S11: Acquire road surface detection data of a target lane, where the target lane includes multiple road sections of equal length, and the road surface detection data includes section data of the multiple road sections.

[0029] In step S11, according to the standard, the target lane is usually first divided into multiple equal-length sections as detection units (or adjusted according to actual needs, but generally not exceeding 100 square meters), and numbered. The length of each detection unit is 10 meters and the width is the lane width, for example 3.75 meters. Each section is then inspected, wherein each section can be inspected by manual or automated means to obtain multiple section data. Exemplarily, a mobile device equipped with an image acquisition device is used to acquire images within multiple sections. The mobile device includes but is not limited to automobiles, drones and other equipment. The image acquisition device includes a high-pixel industrial camera and an LED array fill light device. The shooting height of the image acquisition device is controlled at 2.5 meters, and its image area is controlled to cover a lane width of 3.75 meters. Acquiring the road surface detection data of the target lane means acquiring images within all sections.

[0030] S12: Identify the types of damage contained in the road section based on the road section data.

[0031] In step S12, the road section data includes multiple images captured for that road section. Image preprocessing is required before defect detection. Image preprocessing can specifically involve aligning and cropping images acquired at adjacent acquisition times. Alignment can be automatic based on preset longitudinal offset and lateral overlap parameters, or manually adjusted by dragging the images. Image size can be adjusted by cropping to remove any overlapping portions of two road images acquired at adjacent times, resulting in an image covering the entire road section. This reduces image noise and improves the accuracy of subsequent defect recognition.

[0032] After image preprocessing, the defect detection model detects the images of each road section to determine the type of defects present. The defect detection model identifies the presence and type of pavement defects in the images. Specifically, the defect detection model includes a built-in recognition algorithm for identifying defect types. In this embodiment, this model employs a modified YOLOv8 deep learning model that supports the identification of the six major categories and 21 subcategories of pavement defects specified in the Highway Technical Condition Assessment Standard.

[0033] S13: Obtaining original disease deduction points corresponding to each disease type and at least one severity evaluation index corresponding to each disease type of pavement disease, wherein the original disease deduction points are used to indicate the degree of damage caused by each disease type to the road section.

[0034] In step S13, the original defect deduction score is the individual deduction value (DV) for each defect type, calculated manually according to the Asphalt Pavement Defect Deduction Table in the "Highway Technical Condition Assessment Standard." The defect detection model also outputs the defect area. Specifically, the defect detection model includes a built-in recognition algorithm for identifying defect outlines. The defect area is calculated based on the number of pixels within the defect outline. In this embodiment of the present application, the improved YOLOv8 deep learning model, combined with the Mask R-CNN algorithm, identifies detected pavement defects. In addition to outputting a detection bounding box, it also outputs a pixel-level mask (mask) of the pavement defect, i.e., the defect outline of the defect area. Using the mask, a more accurate area can be calculated. Specifically, the number of pixels in the mask is first counted, with each pixel representing the defect area. The number of pixels within the mask is then directly counted, representing the pixel area of ​​the pavement defect. Then, using physical area conversion, the pixel area is converted to the actual physical area based on the physical scale of the image (this is prior art and will not be further elaborated here).

[0035] The operator calculates the individual deduction points for all types of defects within a road section based on the defect type and area, according to the Asphalt Pavement Defect Deduction Table. This is known as the original deduction points, and is recorded in the Defect Deduction Table. The Defect Deduction Table includes the road section number, the defect types within the section, and the original deduction points corresponding to each defect type. The original deduction points corresponding to each defect type can be obtained by searching the Original Deduction Table.

[0036] Severity evaluation indicators characterize pavement defects. Specifically, these indicators include defect spacing, penetration, and defect growth rate. Defect spacing is the minimum distance between adjacent defects of the same defect type within a road section. Penetration is the ratio of the horizontal / vertical extension of a pavement defect along the road section. Defect growth rate is the rate of expansion of the area / length of a pavement defect within a preset period. The defect detection model outputs a defect profile for all pavement defects within each road section. Based on this profile, at least one of these severity evaluation indicators can be calculated.

[0037] S14: Adjusting the original disease deduction score corresponding to the disease type based on at least one severity evaluation index to obtain a new disease deduction score.

[0038] In step S14, specifically, after obtaining at least one of the three serious evaluation indicators of pavement diseases, namely, disease spacing, penetration, and disease development rate, the corresponding correction coefficient is calculated according to the corresponding correction coefficient formula. Among the at least one correction coefficient, the maximum correction coefficient is selected to correct the original disease deduction points of the disease type, and a new disease deduction point for the disease type is obtained and saved in the disease deduction table. The disease deduction table also includes the new disease deduction points corresponding to the disease type.

[0039] S15: In response to the number of disease types included in the road section being greater than or equal to 2, searching for a target disease type combination that meets a preset synergistic impact condition among at least two disease types.

[0040] Specifically, in step S15, if the number of damage types within a road section is greater than 2, a damage coupling coefficient table is obtained. The damage coupling coefficient table includes multiple damage type combinations and the damage coupling coefficient corresponding to each of the damage type combinations. The damage type combinations in the damage coupling coefficient table include pavement damages with synergistic influence conditions, that is, the target damage type combinations include the damage type combinations in the damage coupling coefficient table. It is understandable that damages with synergistic influence conditions within the same road section will enhance their destructive effects. For example, the damage type combinations in the damage coupling coefficient table include {cracks, rutting}. Cracks can cause water to infiltrate, accelerating the development of the normal area surrounding the rutting. After obtaining the damage coupling coefficient table, the multiple damage types within the road section are detected to seep into the target damage type combination.

[0041] S16: Adjust the new disease deduction points of the disease types included in the target disease type combination to obtain adjusted disease deduction points.

[0042] In step S16, if any of the multiple damage types within the road section meet the target damage type combination, the corresponding damage coupling coefficient from the damage coupling coefficient table is obtained, and the new damage deduction points for the damage types included in the target damage type combination are adjusted using the damage coupling coefficient to obtain the adjusted damage deduction points. It should be understood that for damage types within the road section that do not meet the target damage type combination, no adjustment is required for their new damage deduction points.

[0043] S17: Generate a target lane health index for the target lane based on the damage deduction points of all damage types in all road sections.

[0044] In step S17, the target lane health indicator is the PCI index of the target lane. Specifically, the PCI index for each road section is calculated by calculating the total adjusted deduction value (TotaI DV) for all deterioration types within each road section and combining it with the road condition index formula (PCI = 100 - a0 × (TotaI DV)^a1). The PCI index for the target lane is then calculated by averaging the PCI indexes for all road sections.

[0045] The embodiment of the present application introduces multiple severity evaluation indicators to perform an initial dynamic correction on the original disease deduction value, generating a new disease deduction value that is more in line with the actual degree of damage; then, for disease combinations with synergistic destructive effects in the road surface, a secondary correction is performed on the corrected new disease deduction value based on its coupling mechanism, and finally a target lane health index that accurately characterizes the comprehensive impact of complex diseases is constructed, achieving a dual breakthrough in multi-dimensional disease severity quantitative assessment and synergistic effect compensation calculation, meeting the needs of modern road maintenance for road health status diagnosis, and improving the credibility of health indicators and the scientific nature of maintenance decisions in complex disease scenarios.

[0046] In some embodiments, adjusting the original disease deduction score corresponding to the disease type based on at least one severity evaluation indicator to obtain a new disease deduction score includes the following steps: S141: Obtain at least one corresponding correction coefficient based on at least one severity evaluation indicator.

[0047] S142: Selecting a maximum correction coefficient from at least one correction coefficient as a target correction coefficient.

[0048] S143: Adjusting the original disease deduction score corresponding to the disease type based on the target correction coefficient to obtain a new disease deduction score.

[0049] In S141, severity evaluation indicators include defect spacing, penetration, and defect growth rate, and each severity evaluation indicator corresponds to a correction coefficient. At least one severity evaluation indicator of the pavement defect, including defect spacing, penetration, and disease growth rate, is obtained, and the corresponding correction coefficient is calculated using the correction coefficient formula corresponding to the severity evaluation indicator.

[0050] In S142, the target correction coefficient is used to correct the original deduction score of the disease type. By comparing the magnitudes of at least one correction coefficient of the disease type, the correction coefficient with the largest value is selected as the target correction coefficient.

[0051] Specifically, in S143, the target correction coefficient is multiplied by the original disease deduction score of the disease type to obtain a new disease deduction score.

[0052] In some embodiments, severity evaluation indicators include disease spacing, penetration, and disease development rate, and correction factors include a spacing correction factor and / or a penetration correction factor and / or a development rate correction factor. Obtaining at least one corresponding correction factor based on at least one severity evaluation indicator includes: For the same type of disease, pavement diseases with a disease spacing less than or equal to a preset distance threshold are set as clustered diseases, the total number of diseases of the disease type and the number of clustered diseases of the clustered diseases in the road section are obtained, and the spacing correction coefficient of the disease type is calculated based on the total number of diseases and the number of clustered diseases according to the spacing correction coefficient formula; and / or, the penetration of pavement diseases in the disease type is sorted to obtain the maximum value of the penetration of pavement diseases in the disease type, and the penetration correction coefficient of the disease type is calculated based on the maximum value of the penetration according to the penetration correction coefficient formula; and / or, the development rate of pavement diseases in the disease type is sorted to obtain the maximum value of the disease development rate of pavement diseases in the disease type, and the development rate correction coefficient of the disease type is calculated based on the maximum value of the disease development rate according to the development rate correction coefficient formula.

[0053] It is understood that there is a one-to-one correspondence between severity evaluation indicators and correction coefficients: the distance between defects corresponds to the distance correction coefficient, the penetration corresponds to the penetration correction coefficient, and the development rate corresponds to the development rate correction coefficient. Therefore, based on at least one severity evaluation indicator, at least one corresponding correction coefficient is obtained. Specifically, based on at least one severity evaluation indicator of the pavement defect, among the distance between defects, penetration, and development rate, at least one of the corresponding distance correction coefficient, penetration correction coefficient, and development rate correction coefficient is obtained.

[0054] The spacing correction coefficient is obtained based on the disease spacing. Specifically, the disease spacing is the minimum distance between adjacent pavement diseases of the same disease type in the same road section. Within the road section, for the same disease type, if the disease spacing of pavement diseases is less than or equal to the preset distance threshold, and the preset distance threshold is set to 1 meter, it is set as a clustered disease. Then, the total number N of pavement diseases in this disease type and the number n of clustered diseases set as clustered diseases are obtained. The spacing correction coefficient Ks is calculated according to the spacing correction coefficient formula Ks=1+0.2×n / N.

[0055] For example, see Figure 2a , Figure 2a This is a schematic diagram of a mask image of pavement defects on a certain road section. The image includes four pavement defects, all of which are potholes. Among the distances between pothole 1 and potholes 2, 3, and 4, the distance between potholes 1 and 2 is the smallest. Therefore, the distance between potholes 1 and 2 is the defect spacing for pothole 1. Since the pothole spacing for pothole 1 is 1 meter, pothole 1 is classified as a cluster defect. It is understandable that pothole 2 will also be classified as a cluster defect. See [1]. Figure 2b, among the distances between pit 3 and pit 1, pit 2 and pit 4, the distance between pit 3 and pit 4 is the minimum distance, then the distance between pit 3 and pit 4 is the disease interval of pit 3, but if the distance between pit 3 and pit 4 is greater than 1 meter, then pit 3 is not set as a cluster disease. Similarly, by Figure 2b As shown, pothole 4 is not designated as a clustered defect and will not be further described here. The total number of pothole defects in this section is N = 4, and the number of clustered defects is n = 2. Based on the spacing correction coefficient formula Ks = 1 + 0.2 × n / N, the pothole spacing correction coefficient for this section, Ks, is calculated to be 1.1.

[0056] The penetration correction coefficient is obtained based on the penetration. Specifically, within the road section, for the same type of pavement damage, the penetration of the pavement damage is sorted to obtain the maximum penetration of the pavement damage in the damage type. It can be understood that if there is only one pavement damage in the damage type, the penetration of the pavement damage can be obtained without sorting. According to the penetration correction coefficient formula Kp=1+0.5×P max , where P max The maximum value of penetration is used to calculate the penetration correction coefficient Kp.

[0057] The development rate correction coefficient is obtained based on the disease development rate. Specifically, within a road section, for the same disease type, the disease development rates of the pavement diseases are sorted to obtain the maximum disease development rate of the pavement diseases in that disease type. It can be understood that if there is only one pavement disease in that disease type, the disease development rate of the pavement disease can be obtained without sorting. According to the development rate correction coefficient formula Kv=1+0.02×V max , where V max The maximum value of the disease development rate is used to calculate the development rate correction coefficient Kv.

[0058] The embodiment of the present application obtains the corresponding spacing correction coefficient, penetration correction coefficient and development rate correction coefficient based on at least one severity evaluation index of pavement diseases, which is used to adjust the original disease deduction points of the disease type, thereby realizing a refined and multi-dimensional quantitative correction of the degree of disease hazard, and improving the accuracy and objectivity of the disease deduction results and the ability to characterize the actual road conditions.

[0059] In some embodiments, the correction coefficients include a spacing correction coefficient, a penetration correction coefficient, and a development rate correction coefficient. Selecting the maximum correction coefficient among at least one correction coefficient as the target correction coefficient includes selecting the maximum value among the spacing correction coefficient, the penetration correction coefficient, and the development rate correction coefficient as the target correction coefficient. Specifically, within a road section, for the same defect type, the spacing correction coefficient, the penetration correction coefficient, and the development rate correction coefficient for that defect type are simultaneously obtained, and the maximum value among the three is selected as the target correction coefficient to be used to adjust the original defect deduction score for that defect type.

[0060] This embodiment of the application selects the largest correction factor from the damage type's spacing correction factor, penetration correction factor, and growth rate correction factor as the target correction factor to adjust the original damage penalty score for that damage type. This method adheres to the weakest link principle and uses the most unfavorable correction factor for adjustment, ensuring that the assessment results are biased towards safety and preventing the correction results from deviating from the actual situation.

[0061] In some embodiments, the severity evaluation index includes the disease spacing and / or penetration and / or disease development rate, and obtaining at least one severity evaluation index corresponding to each type of pavement disease includes: obtaining the similar distance between two adjacent pavement diseases of each disease type in the road section, and determining the minimum similar distance as the disease spacing of the pavement disease among one or more similar distances belonging to the same pavement disease. The disease spacing is the minimum distance between adjacent pavement diseases of the same disease type in the same road section; and / or obtaining the edge width and edge length of the road section, obtaining the lateral extension length and longitudinal extension length of the pavement disease of each disease type in the road section, and the lateral extension length is the distance of the pavement disease along the edge width direction. The maximum distance, the longitudinal extension length is the maximum distance of the pavement disease in the edge length direction, the first ratio of the lateral extension length of the pavement disease to the edge width is calculated, the second ratio of the longitudinal extension length of the pavement disease to the edge length is calculated, and the maximum value of the two ratios is determined as the penetration of the pavement disease, and the penetration is the lateral / longitudinal extension ratio of the pavement disease along the road section; and / or, historical pavement detection data is obtained, and the historical pavement detection data includes the section data of the road section in at least the first two preset periods, and the disease development rate of the pavement disease of the disease type is calculated based on the section data of the road section and the historical pavement detection data combined with linear regression. The disease development rate is the expansion rate of the area / length of the pavement disease within the preset period.

[0062] Severity evaluation indicators include disease spacing and / or penetration and / or disease development rate. At least one severity evaluation indicator corresponding to each type of pavement disease is obtained. Specifically, at least one of the disease spacing, penetration and disease development rate corresponding to each type of pavement disease is obtained.

[0063] Obtain the distance between road defects corresponding to each defect type. Specifically, obtain the similar distance between two adjacent road defects of each defect type within the road section. Similar distance is the distance between road defects of the same defect type within the road section. Specifically, in this embodiment of the application, the minimum Euclidean distance between the masked pixel pairs of the defect contours of two road defects can be calculated. Then, based on the number of pixels between the two masked pixel points that determine the minimum Euclidean distance and the physical scale of the image, the distance is converted into the real physical distance to obtain the similar distance between the two road defects. Please refer to Figure 3 , the figure contains crack 1 and crack 2, crack 1 is adjacent to crack 2, to obtain the same distance between crack 1 and crack 2, first calculate the minimum Euclidean distance between the mask pixel pairs of the disease contours of crack 1 and crack 2, by Figure 3 As shown in the figure, the minimum Euclidean distance between the masked pixel pairs of the defect outlines of Crack 1 and Crack 2 is the Euclidean distance between the masked pixel pair {11, 22}. This distance is then converted to a true physical distance based on the number of pixels between the masked pixel pair {11, 22} and the physical scale of the image, yielding the similar distance between Crack 1 and Crack 2. Among one or more similar distances belonging to the same pavement defect, the minimum similar distance is determined as the inter-defect distance for the pavement defect. Specifically, the minimum similar distance is obtained by traversing the similar distances obtained by pairwise combinations of the pavement defect and other pavement defects, and the minimum value is used as the inter-defect distance for the pavement defect.

[0064] This embodiment of the application quantifies the spatial distribution of pavement defects, effectively capturing their localized clustering characteristics. This overcomes the limitations of traditional PCI calculation models that rely solely on the number of defects, enabling the assessment of regionalized damage potential and enabling the deduction of defects to more realistically reflect the risk of accelerated deterioration due to dense distribution.

[0065] Obtain the penetration corresponding to each type of pavement disease. Specifically, first obtain the edge width and edge length of the road section. In the embodiment of the present application, the edge width is 3.75 meters and the edge length is 10 meters. Then obtain the lateral extension length and longitudinal extension length of the pavement disease of each type of disease in the road section. Specifically, in the embodiment of the present application, for the pavement disease, first extract the coordinates of the mask pixel points of the disease contour in the XOY coordinate system of the road section. Determine the maximum and minimum values ​​of the X coordinates of all pixel points, and calculate the difference (i.e., the pixel span in the X-axis direction). Combined with the physical scale of the image (such as the actual length represented by each pixel), perform a conversion, calculate the actual physical length of the difference, and obtain the lateral extension length of the pavement disease. Similarly, determine the maximum and minimum values ​​of the Y coordinates of all pixel points, calculate the difference (i.e., the pixel span in the Y-axis direction), and combine the same physical scale information for conversion, calculate the actual physical length of the difference, and obtain the longitudinal extension length of the pavement disease. Please refer to Figure 4The image contains a crack 41. To calculate the penetration of crack 41, we first need to obtain the maximum x2 and minimum x1 values ​​of the X coordinates of all masked pixels within the defect outline in the road section's XOY coordinate system. We then calculate their difference, and transform them using the image's physical scale (e.g., the actual length represented by each pixel) to obtain the lateral extension of crack 41. Similarly, we determine the maximum y2 and minimum y1 values ​​of the Y coordinates of all pixels, calculate their difference (i.e., the pixel span along the Y axis), and transform them using the same physical scale information to obtain the longitudinal extension of crack 41. We then calculate a first ratio of the lateral extension of the pavement defect to its edge width, and a second ratio of the longitudinal extension of the pavement defect to its edge length. The maximum of these two ratios is determined as the penetration of the pavement defect.

[0066] This embodiment of the application introduces penetration to quantify the depth of pavement damage within the pavement structure, surpassing the existing two-dimensional evaluation model that focuses solely on the area and length of the damage. This severity evaluation quantifies the extent to which pavement damage impairs structural integrity, addressing the shortcomings of traditional methods in assessing damage such as transverse cracks or structural potholes by considering the extent of structural damage. It also improves the directivity of the deduction points for the damage to the actual loss of bearing capacity.

[0067] In some embodiments, the penetration corresponding to each type of pavement disease is obtained. The disease type can be judged first and then the penetration is calculated. For example, if it is pre-determined that the disease type of the pavement disease is a transverse crack, only the first ratio can be calculated and the first ratio can be determined as the penetration of the pavement disease; if it is pre-determined that the disease type of the pavement disease is a longitudinal crack, only the second ratio can be calculated and the second ratio can be determined as the penetration of the pavement disease.

[0068] Obtain the corresponding pavement disease progression rate for each disease type. Specifically, obtain historical pavement inspection data, which includes road section data from at least the previous two preset periods. The preset period is one month. The historical pavement inspection data includes pre-saved road section data from at least the previous two months. The road section data includes the disease area / disease length of each disease type within the road section. A linear regression fit is performed based on the current road section data and the road section data from at least the previous two months to calculate the disease progression rate for each disease type.

[0069] The embodiment of the present application introduces the disease development rate to analyze the changing trend of pavement diseases over time, constructs the time dimension of the evolution of disease status, overcomes the instantaneous defect of static evaluation, and enables the disease deduction points to reflect the activity of pavement diseases and future deterioration tendencies, providing a key basis for identifying rapidly decaying areas and predicting remaining service life.

[0070] The embodiment of the present application introduces serious evaluation indicators such as disease spacing, penetration and disease development rate, and constructs a multi-dimensional evaluation system covering spatial distribution, structural morphology and temporal evolution, which improves the accuracy of disease deduction in representing actual destructive power, provides a solid data foundation for accurately identifying key maintenance areas and optimizing resource allocation strategies, and enhances the reliability of the final pavement condition index's status assessment and maintenance decision-making support.

[0071] In some embodiments, searching for a target disease type combination that satisfies a preset synergistic impact condition among at least two of the disease types comprises the following steps: S21: Obtain the disease coupling coefficient table.

[0072] S22: Randomly select a target number of disease types from at least two disease types included in the road section to form candidate disease type combinations.

[0073] S23: In response to the disease coupling coefficient table containing a disease type combination that is consistent with the candidate disease type combination, determining that the candidate disease type meets a preset synergistic impact condition, and using the candidate disease type as a target disease type combination.

[0074] In step S21, the disease coupling coefficient table is pre-stored in the memory of the electronic device and can be directly accessed to obtain the disease coupling coefficient table. The disease coupling coefficient table includes multiple disease type combinations and the disease coupling coefficient corresponding to each disease type combination. The values ​​of the disease coupling coefficients are set based on multiple experiments and expert experience. The specific contents are shown in Table 1: Table 1

[0075] In step S22, a target number of disease types are arbitrarily selected from at least two disease types contained in the road section to form a candidate disease type combination. The target number is two. Specifically, all disease types contained in the road section are extracted from the disease deduction table, and all disease types are combined in pairs to obtain a candidate disease type combination.

[0076] In step S23, the preset synergistic impact condition is the synergistic destructive effect of different disease types. In response to the disease coupling coefficient table containing a disease type combination that is consistent with the candidate disease type combination, the candidate disease type is determined to meet the preset synergistic impact condition and the candidate disease type is used as the target disease type combination. Specifically, all disease type combinations in the disease coupling coefficient table are first extracted, and the candidate disease type combination is matched with all disease type combinations in the disease coupling coefficient table. If a consistent disease type combination is found, the candidate disease type combination is determined to meet the preset synergistic impact condition and the candidate disease type combination is used as the target disease type combination.

[0077] In some embodiments, adjusting the new disease deduction score of the disease type included in the target disease type combination to obtain the adjusted disease deduction score includes the following steps: S31: Based on the disease coupling coefficient table, obtain the disease coupling coefficient corresponding to the target disease type combination; S32: Using the disease coupling coefficient, adjust the new disease deduction points of the disease types included in the target disease type combination to obtain adjusted disease deduction points.

[0078] Specifically, in step S31, the disease type combinations in the disease coupling coefficient table are traversed to find a disease type combination that is consistent with the target disease type combination, and obtain its corresponding disease coupling coefficient.

[0079] In step S32, specifically, the disease coupling coefficient is multiplied by the new disease deduction points of the two disease types included in the target disease type combination to obtain the adjusted disease deduction points of the two disease types.

[0080] The embodiment of the present application introduces a disease coupling coefficient table to obtain the disease coupling coefficient corresponding to the target disease type combination, and based on this, performs a secondary correction on the new disease deduction points of the disease types included in the target disease type combination. The embodiment of the present application systematically incorporates the synergistic destructive effect between different disease types, improves the accuracy of the disease deduction results in representing the actual destructive power of complex diseases, can optimize the integrity of the PCI index calculation, enhance the ability to identify high-risk disease combinations and the targeted formulation of maintenance strategies.

[0081] In some embodiments, generating a target lane health index for a target lane based on the damage deduction points for all damage types in all road segments includes the following steps: S41: Calculate the road health index of each road section based on the damage deduction points of all damage types in each road section.

[0082] S42: Calculate the average of the road health indicators of all road sections to obtain the candidate lane health indicators; S43: Generate a target lane health indicator for the target lane based on the candidate lane health indicators.

[0083] In step S41, specifically, the total deduction value of each road section is calculated based on the adjusted disease deduction points and / or new disease deduction points of all disease types in each road section, and the PCI index corresponding to each road section, that is, the road section health index, is calculated in combination with the road condition coefficient formula.

[0084] In step S42, specifically, the average value of the PCI index of all road sections is calculated, that is, the candidate lane health index is obtained.

[0085] In step S43, the target lane health index is the PCI index of the target lane. The target lane health index of the target lane is generated based on the candidate lane health indexes. Specifically, the average PCI index of all road segments is used as the PCI index of the target lane, i.e., the target lane health index.

[0086] In some embodiments, the target lane health indicator includes a first lane health indicator, and the target lane further includes a shoulder area and an edge area. Generating the target lane health indicator of the target lane based on the candidate lane health indicators includes the following steps: S51: Obtain lane health indicators of the shoulder area and the edge area in each road section.

[0087] S52: Calculate the average lane health index of the shoulder area in all road sections to obtain the shoulder health index of the target lane.

[0088] S53: Calculate the average lane health index of the edge areas of all road sections to obtain the edge health index of the target lane.

[0089] S54: Perform weighted calculation on the road shoulder health index, the edge health index, and the candidate lane health index to obtain the first lane health index of the target lane.

[0090] In step S51, the target lane also includes a shoulder area and a marginal area. The lane health index of the shoulder area is the PCI index of the shoulder area, and the lane health index of the marginal area is the PCI index of the marginal area. The PCI index of the shoulder area and the PCI index of the marginal area for each road section are manually calculated and pre-stored in the memory of the electronic device. The lane health index of the shoulder area and the lane health index of the marginal area for each road section can be directly obtained from the memory.

[0091] In step S52, the shoulder health index is the PCI index of the shoulder area of ​​the target lane. Specifically, the average PCI index of the shoulder area in all road sections is calculated to obtain the PCI index of the shoulder area of ​​the target lane.

[0092] In step S53, the edge health index is the PCI index of the edge area of ​​the target lane. Specifically, the average PCI index of the edge areas of all road sections is calculated to obtain the PCI index of the edge area of ​​the target lane.

[0093] In step S54, it is understood that, see Figure 5, the lane includes a pavement area 51, a shoulder area 52 and an edge area 53, and the functions and roles of the three are different. Based on the functional weight, the shoulder health index, the edge health index and the candidate lane health index are weightedly calculated to obtain the first lane health index of the target lane. The functional weights include pavement weight, shoulder weight and edge weight. In the embodiment of the present application, the pavement weight is set to 0.7, the shoulder weight is set to 0.2, and the edge weight is set to 0.1. The first lane health index is the PCI index of the target lane that introduces the spatial dimension calculation. Specifically, the first lane health index of the target lane is obtained by calculating the sum of the product of the pavement weight and the candidate lane health index, the product of the shoulder weight and the shoulder health index, and the product of the edge weight and the edge health index.

[0094] The embodiment of the present application introduces the shoulder health index and the edge health index, and performs weighted fusion calculation of the shoulder health index, the edge health index and the candidate lane health index based on the spatial dimension. This breaks through the limitation of the traditional PCI calculation architecture that only focuses on the lane pavement and ignores the influence of the associated structure. It realizes a comprehensive quantitative assessment of the spatial integrity of the road domain and significantly improves the representation accuracy, spatial correlation and maintenance decision-making support value of the PCI index of the target lane.

[0095] In some embodiments, the target lane health indicator includes a second lane health indicator, and generating the target lane health indicator of the target lane based on the candidate lane health indicators includes the following steps: S61: Obtain pre-stored historical lane health indicators.

[0096] S62: Perform weighted calculation on the candidate lane health index and the historical lane health index to obtain a second lane health evaluation index.

[0097] In step S61, the historical lane health indicators include the candidate lane health indicators for the previous two preset periods (one month). The preset period is a month. The second lane health indicator is the PCI index of the target lane calculated using the time dimension. Specifically, the historical lane health indicators include the candidate lane health indicators for the previous month and the candidate lane health indicators for the previous two months. The historical lane health indicators are stored in the memory of the electronic device and can be directly accessed from the memory.

[0098] In step S62, it can be understood that the development of pavement defects has a clear time trend. Based on the development weight, the candidate lane health index and the historical lane health index are weighted and calculated to obtain the second lane health evaluation index. The development weight includes the current period weight, the previous period weight, and the weights of the first two periods. In the embodiment of the present application, the current period weight is set to 0.6, the previous period weight is set to 0.3, and the first two periods weight is set to 0.1. Specifically, the second lane health evaluation index is obtained by calculating the sum of the product of the current period weight and the candidate lane health index in step S42, the product of the previous period weight and the candidate lane health index of the previous month, and the product of the first two periods weight and the candidate lane health index of the previous two months.

[0099] This embodiment of the application performs a weighted fusion calculation of the current candidate lane health index and historical lane health index based on development weights, fully incorporating information from the time dimension. This method effectively captures and quantifies the dynamic characteristics of lane health, improving the timeliness of the target lane PCI index, its trend prediction capabilities, and its resistance to short-term fluctuations, providing a more reliable basis for forward-looking maintenance planning.

[0100] It should be noted that, in each of the above-mentioned embodiments, there is not necessarily a certain order between the above-mentioned steps. A person skilled in the art can understand, based on the description of the embodiments of this application, that in different embodiments, the above-mentioned steps may have different execution orders, that is, they may be executed in parallel, or may be executed interchangeably, etc.

[0101] See also Figure 6 , Figure 6 6 is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. The computer device includes one or more processors 61 and a memory 62. The memory 62 is connected to the one or more processors 61, for example, via a bus.

[0102] The processor 61 is configured to support the computer device in executing the corresponding functions of the method in the above method embodiment. The processor 61 can be a central processing unit (CPU), a network processor (NP), a hardware chip, or any combination thereof. The hardware chip can be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or any combination thereof. The PLD can be a complex programmable logic device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL), or any combination thereof.

[0103] The memory 62 is used to store program code, etc. The memory 62 may include volatile memory (VM), such as random access memory (RAM); non-volatile memory (NVM), such as read-only memory (ROM), flash memory, hard disk drive (HDD), or solid-state drive (SSD); or a combination of the aforementioned types of memory.

[0104] The memory 62 can be used to store non-volatile software programs, non-volatile computer-executable programs, and modules, such as the program instructions / modules corresponding to the pavement health assessment method in the embodiments of the present application. The processor 61 executes the non-volatile software programs, instructions, and modules stored in the memory to execute the pavement health assessment method, thereby implementing the pavement health assessment method provided in the above-described method embodiments.

[0105] The memory 62 may include a program storage area and a data storage area. The program storage area may store an operating system and application programs required for at least one function. In some embodiments, the memory 62 may optionally include a memory remote from the processor. Examples of the aforementioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0106] The one or more modules are stored in the memory 62. When executed by the one or more processors, the pavement health assessment method in any of the above-mentioned method embodiments is executed, for example, the method steps described in the above-mentioned method embodiments are executed to realize the functions of the modules described in the above-mentioned device embodiments.

[0107] Those skilled in the art will appreciate that all or part of the processes in the above-described method embodiments can be implemented by instructing related hardware through a computer program. The program can be stored in a computer-readable storage medium, and when executed, the program can include the processes in the above-described method embodiments. The storage medium can be a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0108] The above disclosure is only a preferred embodiment of the present application, and certainly cannot be used to limit the scope of rights of the present application. Therefore, equivalent changes made according to the claims of the present application are still within the scope covered by the present application.

Claims

1. A road health assessment method, characterized in that: include: Acquire road surface detection data of a target lane, wherein the target lane includes a plurality of road sections of equal length, and the road surface detection data includes section data of the plurality of road sections; Identifying the type of damage contained in the road section based on the road section data; Obtaining original damage deduction points corresponding to each of the damage types and at least one severity evaluation index corresponding to each of the road surface damage types, wherein the original damage deduction points are used to indicate the degree of damage caused by each of the road surface damage types to the road section; Adjusting the original disease deduction score corresponding to the disease type based on at least one of the severity evaluation indicators to obtain a new disease deduction score; In response to the number of disease types included in the road section being greater than or equal to 2, searching for a target disease type combination that meets a preset synergistic impact condition among at least two of the disease types; Adjusting the new disease deduction points of the disease types included in the target disease type combination to obtain adjusted disease deduction points; Based on the damage deduction points of all the damage types in all road sections, a target lane health index of the target lane is generated.

2. The method according to claim 1, characterized in that The adjusting the original disease deduction score corresponding to the disease type based on at least one of the severity evaluation indicators to obtain a new disease deduction score includes: Obtaining at least one corresponding correction coefficient based on at least one of the severity evaluation indicators; Selecting a maximum correction coefficient from at least one of the correction coefficients as a target correction coefficient; The original disease deduction score corresponding to the disease type is adjusted based on the target correction coefficient to obtain a new disease deduction score.

3. The method according to claim 2, characterized in that The severity evaluation indicators include disease spacing, penetration, and disease development rate; the correction coefficients include a spacing correction coefficient and / or a penetration correction coefficient and / or a development rate correction coefficient; and obtaining at least one corresponding correction coefficient based on at least one of the severity evaluation indicators includes: For the same type of damage, pavement damages with a distance between them less than or equal to a preset distance threshold are defined as clustered damages, the total number of damages of the damage type and the number of clustered damages of the clustered damages in the road section are obtained, and the distance correction coefficient of the damage type is calculated based on the total number of damages and the number of clustered damages according to the distance correction coefficient formula; and / or, Sorting the penetrations of the pavement defects in the defect types to obtain the maximum penetration of the pavement defects in the defect types, and calculating the penetration correction coefficient of the defect type in combination with the maximum penetration according to a penetration correction coefficient formula; and / or, The development rates of the pavement diseases in the disease types are sorted to obtain the maximum value of the disease development rate of the pavement diseases in the disease types, and the development rate correction coefficient of the disease type is calculated based on the development rate correction coefficient formula and the maximum value of the disease development rate.

4. The method according to claim 2, characterized in that The correction coefficients include a spacing correction coefficient, a penetration correction coefficient, and a development rate correction coefficient. The step of selecting the maximum correction coefficient as the target correction coefficient from at least one of the correction coefficients includes: The maximum value among the spacing correction coefficient, the penetration correction coefficient and the development rate correction coefficient is selected as the target correction coefficient.

5. The method according to claim 1, wherein The severity evaluation index includes the disease spacing and / or penetration and / or disease development rate. The step of obtaining at least one severity evaluation index corresponding to each type of pavement disease includes: Obtaining the similar distance between two adjacent pavement defects of each defect type within the road section, and determining the minimum similar distance among one or more similar distances belonging to the same pavement defect as the defect spacing of the pavement defect, wherein the defect spacing is the minimum distance between adjacent pavement defects of the same defect type within the same road section; and / or, Obtaining the edge width and edge length of the road section, obtaining the lateral extension length and longitudinal extension length of the pavement defect of each defect type in the road section, wherein the lateral extension length is the maximum distance of the pavement defect along the edge width direction, and the longitudinal extension length is the maximum distance of the pavement defect along the edge length direction; calculating a first ratio of the lateral extension length of the pavement defect to the edge width; calculating a second ratio of the longitudinal extension length of the pavement defect to the edge length; determining the maximum value of the two ratios as the penetration of the pavement defect, wherein the penetration is the ratio of the lateral / longitudinal extension of the pavement defect along the road section; and / or, Historical pavement detection data is obtained, wherein the historical pavement detection data includes section data of the section in at least the first two preset periods, and the disease development rate of the pavement disease of the disease type is calculated based on the section data of the section and the historical pavement detection data in combination with linear regression, wherein the disease development rate is the expansion rate of the area / length of the pavement disease within the preset period.

6. The method according to claim 1, characterized in that The step of searching for a target disease type combination satisfying a preset synergistic impact condition among at least two of the disease types includes: Obtaining a disease coupling coefficient table, wherein the disease coupling coefficient table includes a plurality of disease type combinations and a disease coupling coefficient corresponding to each of the disease type combinations; Randomly selecting a target number of disease type combinations from at least two disease types included in the road section to form candidate disease type combinations; In response to the disease coupling coefficient table containing a disease type combination that is consistent with the candidate disease type combination, it is determined that the candidate disease type meets a preset synergistic influence condition, and the candidate disease type is used as a target disease type combination.

7. The method according to claim 6, characterized in that The new disease deduction points of the disease types included in the target disease type combination are adjusted to obtain the adjusted disease deduction points, including: Based on the disease coupling coefficient table, obtaining the disease coupling coefficient corresponding to the target disease type combination; The new disease deduction points of the disease types included in the target disease type combination are adjusted using the disease coupling coefficient to obtain adjusted disease deduction points.

8. The method according to claim 1, characterized in that The target lane health index of the target lane is generated based on the damage deduction points of all the damage types in all road sections, including: Calculating a road health index for each road section based on the deduction points for all types of damage within the road section; Calculate the average of the road health indexes of all road sections to obtain the candidate lane health index; A target lane health indicator of the target lane is generated based on the candidate lane health indicators.

9. The method according to claim 8, characterized in that The target lane health index includes a first lane health index, the target lane also includes a shoulder area and an edge area, and generating the target lane health index of the target lane based on the candidate lane health index includes: Obtain lane health indicators of the shoulder area and lane health indicators of the edge area of ​​each road section; Calculating an average lane health index of the shoulder area in all road sections to obtain the shoulder health index of the target lane; Calculating an average of lane health indicators of edge areas in all road sections to obtain an edge health indicator of the target lane; A weighted calculation is performed on the road shoulder health index, the edge health index, and the candidate lane health index to obtain a first lane health index of the target lane.

10. The method according to claim 8, characterized in that The target lane health indicator includes a second lane health indicator, and generating the target lane health indicator of the target lane based on the candidate lane health indicator includes: Obtaining pre-stored historical lane health indicators, wherein the historical lane health indicators include candidate lane health indicators of the previous two preset periods; A weighted calculation is performed on the candidate lane health index and the historical lane health index to obtain a second lane health evaluation index.

Images