A method for assessing the health of a road surface

Abstract

The embodiment of the application relates to the technical field of road surface health assessment, and particularly relates to a road surface health assessment method. The method comprises the following steps: acquiring road section data and road surface detection data comprising a plurality of road sections; identifying the disease types in each road section based on the road section data; acquiring original disease deduction points of each disease type and at least one serious evaluation index; adjusting the original disease deduction points to obtain new disease deduction points by using the serious evaluation index; if the disease types are not less than two, finding a target disease type combination meeting a preset synergistic influence condition, adjusting the new disease deduction points of the disease types contained in the target disease type combination; and generating a target lane health index based on the disease deduction points of all disease types in all road sections. The embodiment of the application adjusts the original disease deduction points by using a plurality of serious evaluation indexes, and then adjusts the disease types with synergistic damage for a second time, so as to construct a health index capable of accurately representing the influence of complex diseases, realize multi-dimensional quantitative evaluation and synergistic effect compensation calculation, and meet the modern road maintenance diagnosis requirements.

Description

TECHNICAL FIELD

[0001] Embodiments of the present application relate to the technical field of road surface health assessment, and in particular to a road surface health assessment method. BACKGROUND

[0002] In the field of road engineering maintenance, the quantitative evaluation of road surface health condition is the core basis for making scientific maintenance decisions. The PCI (Pavement Condition Index) evaluation system widely used in the industry at present has the basic principle of identifying various diseases (such as cracks, potholes, and repairs) on the road surface by manual or automatic means, and independently deducting points for the type, severity, and density of each type of disease according to preset rules, and finally calculating the comprehensive PCI score based on the cumulative result of the deduction points.

[0003] However, the existing PCI evaluation system has significant limitations. The calculation model is essentially a simple linear superposition of the deduction points for different disease types. This processing method has certain rationality when there is only a single or a small number of isolated diseases on the road surface, but when faced with the complex coexistence of diseases that are common in actual engineering, the evaluation results often deviate significantly from the true road conditions. The above defects result in systematic deviation between the traditional PCI evaluation results and the true health status of the road surface, which restricts the optimal allocation of maintenance resources and the effective implementation of preventive maintenance strategies. SUMMARY

[0004] An object of embodiments of the present application is to provide a road surface health assessment method to solve the technical problem of systematic deviation between the traditional PCI evaluation results of complex disease road surfaces and the true health status of the road surface.

[0005] In a first aspect, embodiments of the present application provide a road surface health assessment method, comprising:

[0006] Obtaining road surface detection data of a target lane, the target lane including a plurality of road segments of equal length, the road surface detection data including road segment data of the plurality of road segments, identifying a disease type contained by the road segment based on the road segment data, obtaining an original disease deduction corresponding to each disease type and at least one severity evaluation index corresponding to a road surface disease of each disease type, the original disease deduction being used to represent the damage degree of the disease of each disease type to the road segment, adjusting the original disease deduction corresponding to the disease type based on at least one severity evaluation index to obtain a new disease deduction, in response to the number of disease types contained by the road segment being greater than or equal to 2, finding a target disease type combination that satisfies a preset synergistic effect condition in at least two disease types, adjusting the new disease deduction of the disease types contained in the target disease type combination to obtain an adjusted disease deduction, and generating a target lane health index of the target lane based on the disease deductions of all the disease types in all the road segments.

[0007] The embodiments of the present application first dynamically correct the original disease deduction value by introducing a plurality of severity evaluation indexes to generate a new disease deduction value that is more consistent with the actual damage degree; then, for disease combinations with synergistic damage effect in the road surface, the new disease deduction value after correction is secondarily corrected based on the coupling mechanism, and finally the target lane health index accurately representing the comprehensive influence of complex diseases is constructed, realizing the dual breakthroughs of multi-dimensional disease severity quantitative evaluation and synergistic effect compensation calculation, meeting the demand of modern road maintenance for road health state diagnosis, and improving the health index reliability and scientific nature of maintenance decision-making in complex disease scenarios.

[0008] Optionally, the adjusting of the original disease deduction corresponding to the disease type based on at least one severity evaluation index to obtain a new disease deduction comprises:

[0009] Obtaining at least one corresponding correction coefficient based on at least one severity evaluation index;

[0010] Selecting a maximum correction coefficient as a target correction coefficient from the at least one correction coefficient;

[0011] Adjusting the original disease deduction corresponding to the disease type based on the target correction coefficient to obtain a new disease deduction.

[0012] Optionally, the severity evaluation indexes include disease spacing, penetration and disease development rate, the correction coefficients include spacing correction coefficient and / or penetration correction coefficient and / or development rate correction coefficient, and the obtaining of at least one corresponding correction coefficient based on at least one severity evaluation index comprises:

[0013] For the same type of disease, the road surface diseases with a disease distance less than or equal to a preset distance threshold are set as clustered diseases, the total number of diseases and the number of clustered diseases of the disease type in the road section are obtained, the distance correction coefficient of the disease type is calculated according to the distance correction coefficient formula combined with the total number of diseases and the number of clustered diseases; and / or, the penetration of the road surface diseases in the disease type is sorted to obtain the maximum value of the penetration of the road surface diseases in the disease type, the penetration correction coefficient of the disease type is calculated according to the penetration correction coefficient formula combined with the maximum value of the penetration; and / or, the development rate of the road surface diseases in the disease type is sorted to obtain the maximum value of the disease development rate of the road surface diseases in the disease type, the development rate correction coefficient of the disease type is calculated according to the development rate correction coefficient formula combined with the maximum value of the disease development rate.

[0014] The embodiments of the present application obtain the distance correction coefficient, the penetration correction coefficient and the development rate correction coefficient based on at least one severity evaluation index of the road surface diseases, which are used to adjust the original disease deduction of the disease type, realize the fine and multi-dimensional quantitative consideration of the disease damage degree, and improve the accuracy, objectivity and characterization ability of the disease deduction result.

[0015] Optionally, the correction coefficients include the distance correction coefficient, the penetration correction coefficient and the development rate correction coefficient, the maximum correction coefficient in at least one of the correction coefficients is selected as the target correction coefficient, and the method comprises:

[0016] The maximum value among the distance correction coefficient, the penetration correction coefficient and the development rate correction coefficient is selected as the target correction coefficient.

[0017] The embodiments of the present application select the maximum correction coefficient from the distance correction coefficient, the penetration correction coefficient and the development rate correction coefficient of the disease type as the target correction coefficient, which is used to adjust the original disease deduction of the disease type. The method follows the weakest link principle and uses the most unfavorable correction coefficient for adjustment to ensure that the evaluation result is biased to the safe side and avoids the deviation of the correction result from the actual situation.

[0018] Optionally, the severity evaluation index includes disease distance and / or penetration and / or disease development rate, and the method of obtaining at least one severity evaluation index corresponding to the road surface diseases of each disease type comprises:

[0019] obtaining a same-type distance between two adjacent pavement diseases of each disease type in the road section, determining a minimum same-type distance as a disease spacing between adjacent pavement diseases of the same disease type in the road section, the disease spacing being a minimum distance between adjacent pavement diseases of the same disease type in the road section; and / or, obtaining an edge width and an edge length of the road section, obtaining a transverse extension length and a longitudinal extension length of the pavement disease of each disease type in the road section, the transverse extension length being a maximum distance of the pavement disease in the edge width direction, and the longitudinal extension length being a maximum distance of the pavement disease in the edge length direction, calculating a first ratio of the transverse extension length of the pavement disease to the edge width, calculating a second ratio of the longitudinal extension length of the pavement disease to the edge length, and determining a maximum value of the two ratios as a penetration of the pavement disease, the penetration being an extension ratio of the pavement disease in the transverse / longitudinal direction of the road section; and / or, obtaining historical pavement detection data, the historical pavement detection data including road section data of the road section in at least the previous two preset periods, and calculating a disease development rate of the pavement disease of the disease type according to the road section data of the road section and the historical pavement detection data in combination with linear regression, the disease development rate being an expansion rate of the area / length of the pavement disease in a preset period.

[0020] The embodiments of the present application introduce disease spacing, penetration, and disease development rate and other severity evaluation indexes, construct a multi-dimensional evaluation system covering spatial distribution, structural morphology, and time sequence evolution, improve the accuracy of disease deduction in characterizing actual damage, provide a solid data foundation for accurately identifying key maintenance areas and optimizing resource allocation strategies, and enhance the state evaluation reliability of the final pavement condition index and the support for maintenance decision-making.

[0021] Optionally, the searching for a target disease type combination that meets a preset synergistic influence condition from the at least two disease types includes:

[0022] obtaining a disease coupling coefficient table, the disease coupling coefficient table including a plurality of disease type combinations and a disease coupling coefficient corresponding to each disease type combination;

[0023] selecting a target number of disease type combinations from the at least two disease types included in the road section as candidate disease type combinations;

[0024] in response to the disease coupling coefficient table containing a disease type combination consistent with the candidate disease type combination, determining that the candidate disease type combination meets a preset synergistic influence condition, and taking the candidate disease type combination as the target disease type combination.

[0025] Optionally, the adjusting the new disease deduction of the disease type included in the target disease type combination to obtain an adjusted disease deduction includes:

[0026] obtain a disease coupling coefficient corresponding to the target disease type combination based on the disease coupling coefficient table;

[0027] adjust a new disease deduction of a disease type included in the target disease type combination by using the disease coupling coefficient, to obtain an adjusted disease deduction.

[0028] The embodiment of the application introduces a disease coupling coefficient table, obtains a disease coupling coefficient corresponding to a target disease type combination, and accordingly performs secondary correction on a new disease deduction of a disease type included in the target disease type combination. The embodiment of the application systematically takes into account the synergistic damage effect between different disease types, improves the representation accuracy of the disease deduction result on the actual damage force of a complex disease, optimizes the integrity of PCI index calculation, and enhances the recognition ability of high-risk disease combinations and the pertinence of maintenance strategy formulation.

[0029] Optionally, the target lane health index of the target lane is generated based on the disease deductions of all the disease types in all road segments, and the method comprises the following steps.

[0030] Based on the disease deductions of all the disease types in each road segment, a road segment health index of each road segment is calculated.

[0031] An average value of the road segment health indexes of all the road segments is calculated to obtain a candidate lane health index.

[0032] The target lane health index of the target lane is generated based on the candidate lane health index.

[0033] Optionally, the target lane health index comprises a first lane health index, the target lane further comprises a shoulder area and an edge area, and the target lane health index of the target lane is generated based on the candidate lane health index, which comprises the following steps.

[0034] The lane health index of the shoulder area and the lane health index of the edge area in each road segment are obtained.

[0035] An average value of the lane health indexes of the shoulder areas in all the road segments is calculated to obtain a shoulder health index of the target lane.

[0036] An average value of the lane health indexes of the edge areas in all the road segments is calculated to obtain an edge health index of the target lane.

[0037] The shoulder health index, the edge health index, and the candidate lane health index are weighted to obtain a first lane health index of the target lane.

[0038] The embodiments of the present application introduce a shoulder health index and an edge health index, and perform weighted fusion calculation on the shoulder health index, the edge health index and the candidate lane health index based on a spatial dimension, thereby breaking through the limitation of the traditional PCI calculation architecture which only focuses on the road surface of the lane and ignores the influence of the associated structure, realizing comprehensive quantitative evaluation of the spatial integrity of the road domain, and significantly improving the representation accuracy, spatial correlation and maintenance decision support value of the target lane PCI index.

[0039] Optionally, the target lane health index includes a second lane health index, and the generating of the target lane health index of the target lane based on the candidate lane health index includes:

[0040] acquiring a pre-stored historical lane health index, the historical lane health index including candidate lane health indexes of the previous two preset periods;

[0041] performing weighted calculation on the candidate lane health index and the historical lane health index to obtain a second lane health evaluation index.

[0042] The embodiments of the present application perform weighted fusion calculation on the current candidate lane health index and the historical lane health index, and fully take into account the time dimension information. This method realizes effective capture and quantification of the dynamic change characteristics of the lane health condition, improves the representation timeliness, trend prediction ability and anti-short-term fluctuation interference of the target lane PCI index, and can provide a more reliable basis for prospective maintenance planning. BRIEF DESCRIPTION OF DRAWINGS

[0043] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the description of the embodiments of the present application will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0044] Figure 1 A flowchart of a pavement health evaluation method provided by the embodiments of the present application is shown in the figure;

[0045] Figure 2a A mask image of pavement diseases of a certain road section provided by the embodiments of the present application is shown in the figure;

[0046] Figure 2b Another mask image of pavement diseases of a certain road section provided by the embodiments of the present application is shown in the figure;

[0047] Figure 3 A same-class distance diagram of pavement diseases provided by the embodiments of the present application is shown in the figure;

[0048] Figure 4A schematic diagram of calculating the transverse extension length and longitudinal extension length of a road disease is provided in an embodiment of the present application.

[0049] Figure 5 A schematic diagram of a lane area structure is provided in the prior art.

[0050] Figure 6 A schematic diagram of an electronic device is provided in an embodiment of the present application. DETAILED DESCRIPTION

[0051] In order to make the purposes, technical solutions and advantages of the present application clearer and more comprehensible, the present application is further described in detail below in combination with the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and do not limit the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative labor fall within the scope of protection of the present application.

[0052] It should be noted that the various features in the embodiments of the present application can be combined with each other without conflict, and all fall within the scope of protection of the present application. In addition, although the functional modules are divided in the device schematic diagram, and the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order than the module division in the device or the order in the flowchart. Furthermore, the "first", "second", "third" and the like used in the present application do not limit the data and execution order, but only distinguish the same items or similar items with basically the same function and effect.

[0053] In the field of road 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 prior art. The existing PCI calculation system mainly quantitatively evaluates the pavement damage features: the pavement damage (such as cracks, potholes, ruts, settlement, etc.) is converted into a calculable value, and for different pavement damages, the single deduction value (DV) is determined by table lookup, specifically, the static characteristic parameters including damage type, damage severity and damage area are obtained by table lookup, and the single deduction value of the pavement damage is obtained by calculating a plurality of static characteristic parameters. For multiple pavement damages of the same damage type, the single deduction value of the damage type is calculated by accumulating the damage areas of the multiple pavement damages. After obtaining the deduction values of each damage, the total deduction value (Total DV) is calculated by simple accumulation, in order to consider the superposition effect of multiple damages, and finally the pavement condition index formula , the PCI value is calculated. Among them, a0, a1 are model coefficients, according to the “Highway Technical Condition Evaluation Standard” (JTG 5210-2018), in the evaluation of asphalt pavement, the values are usually 15.00 and 0.412 respectively. This processing method of the prior art has certain rationality when there is only a single or a small number of isolated diseases on the road surface, but when facing the complex disease coexistence scene commonly existing in actual engineering, the evaluation result often deviates seriously from the true road condition.

[0054] The inventors have also found that the above prior art has the following defects: 1. Insufficient consideration of the spatial distribution characteristics of the disease: the existing PCI calculation model only counts the number and size of road damage, but ignores its aggregation in the road surface space; 2. Disease morphology characteristics are not fully quantified: for example, the existing PCI calculation system only calculates the score of cracks or potholes according to the length of cracks or the area of potholes, ignoring the evaluation of the development degree of cracks or potholes in the transverse / longitudinal direction of the road surface 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 degradation trend, resulting in insufficient accuracy of road health state judgment, and difficulty in meeting the needs of refined maintenance decision-making.

[0055] Hereinafter, the present application embodiment provides a road surface health evaluation method, please refer to Figure 1 , Figure 1 is a flowchart of a road surface health evaluation method provided by the present application embodiment, the present application embodiment includes the following steps:

[0056] S11: Obtain road surface detection data of a target lane, the target lane includes a plurality of road sections of equal length, and the road surface detection data includes road section data of the plurality of road sections.

[0057] In step S11, according to the standard, the target lane is usually divided into a plurality of equal-length road sections as detection units (or adjusted according to actual needs, but generally not more than 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. Then each road section is detected, wherein each road section can be detected by manual or automatic means to obtain a plurality of road section data. For example, a mobile device equipped with an image acquisition device is used to obtain images in the plurality of road sections, the mobile device includes but is not limited to a car, a drone, etc. The image acquisition device includes a high-pixel industrial camera and an LED array light supplement device. The image acquisition device is controlled to have a shooting height of 2.5 meters, and the image area covered by the image acquisition device is controlled to be 3.75 meters wide. The road surface detection data of the target lane is obtained by obtaining the images in all road sections.

[0058] S12: Identify the disease types contained in the road section based on the road section data.

[0059] In step S12, the road section data includes a plurality of images taken for the road section, and image preprocessing is required before disease detection. The image preprocessing can specifically be aligning and cropping the images obtained at adjacent acquisition times. The specific alignment method can be automatically adjusted according to preset longitudinal offset and transverse coincidence parameters, or manually adjusted by manually dragging the images. The size of the image is adjusted by cropping to remove the overlapping part of the two road images obtained at adjacent acquisition times, to obtain a to-be-detected image covering the entire road section, thereby reducing picture interference and improving the subsequent recognition accuracy of the disease.

[0060] After the image preprocessing operation, the to-be-detected image of each road section is detected by the disease detection model to obtain the disease type in the to-be-detected image. The disease detection model is used to identify whether there is a road surface disease and the disease type in the to-be-detected image. Specifically, the disease detection model has an identification algorithm for identifying the disease type. In the embodiments of the present application, it can be specifically an improved YOLOv8 deep learning model, which supports the identification of 6 categories and 21 subcategories of road surface diseases specified in the “Highway Technical Condition Evaluation Standard”.

[0061] S13: Obtain the original disease deduction score corresponding to each disease type and at least one severity evaluation index corresponding to the road surface disease of each disease type. The original disease deduction score is used to represent the damage degree of each disease type to the road section.

[0062] In step S13, the original disease deduction score is a single deduction value (DV) of the disease type calculated manually according to the provisions of the asphalt pavement disease deduction table in the “Highway Technical Condition Evaluation Standard”. The disease detection model is also used to output the disease area. Specifically, the disease detection model has an identification algorithm for identifying the disease contour. The disease area is calculated by the number of pixel points contained in the disease contour of the road surface disease. In the embodiments of the present application, the improved YOLOv8 deep learning model combines the Mask R-CNN algorithm to identify the detected road surface disease, and outputs the pixel-level mask (Mask) of the road surface disease, i.e., the disease contour of the disease area. The mask can be used to calculate a more accurate area. Specifically, the number of pixels in the mask is counted first, and each pixel in the mask represents a disease area. The number of pixels in the mask is directly counted, which is the pixel area of the road surface disease. Then, the pixel area is converted into the actual physical area by physical area conversion combined with the physical scale of the image (which is a prior art and will not be described here).

[0063] The operator combines the disease type and the disease area according to the provisions of the asphalt pavement disease deduction table to calculate the single deduction value of all disease types in the road section, that is, the original disease deduction, and record it in the disease deduction table. The disease deduction table includes the number of the road section, the disease types included in the road section and the original disease deduction corresponding to the disease types. The original disease deduction corresponding to each disease type can be obtained by looking up the original disease deduction table.

[0064] The severity evaluation index is used to characterize the disease characteristics of the pavement disease. Specifically, the severity evaluation index includes disease spacing, penetration, and disease development rate. The disease spacing is the minimum distance between adjacent pavement diseases with the same disease type in the same road section. The penetration is the extension ratio of the pavement disease along the transverse / longitudinal direction of the road section. The disease development rate is the expansion rate of the area / length of the pavement disease in a predetermined period. The disease detection model outputs the disease profile of all pavement diseases in each road section. Based on the disease profile of the pavement disease, at least one of the above-mentioned severity evaluation indexes can be calculated.

[0065] S14: Adjusting the original disease deduction corresponding to the disease type based on at least one severity evaluation index to obtain a new disease deduction.

[0066] In step S14, specifically, after obtaining at least one of the disease spacing, penetration, and disease development rate of the pavement disease, the corresponding correction coefficient is calculated according to the corresponding correction coefficient formula. In at least one correction coefficient, the maximum correction coefficient is selected to correct the original disease deduction of the disease type to obtain the new disease deduction of the disease type, and saved to the disease deduction table. The disease deduction table also includes the new disease deduction corresponding to the disease type.

[0067] S15: In response to the number of disease types contained in the road section being greater than or equal to 2, finding a target disease type combination that meets a preset synergistic effect condition among at least two disease types.

[0068] In step S15, specifically, if the number of disease types in the road section is greater than 2, a disease coupling coefficient table is obtained. The disease coupling coefficient table includes a plurality of disease type combinations and a disease coupling coefficient corresponding to each disease type combination. The disease type combination in the disease coupling coefficient table includes pavement diseases with a synergistic effect condition, i.e. the target disease type combination includes the disease type combination in the disease coupling coefficient table. It can be understood that the diseases with a synergistic effect condition in the same road section will enhance their destructive effect. For example, the disease type combination in the disease coupling coefficient table includes {crack, rut}, and the crack will cause water to seep in and accelerate the development of the normal area around the rut. After obtaining the disease coupling coefficient table, it is detected whether the target disease type combination exists among the multiple disease types in the road section.

[0069] S16: Adjust the new disease deduction of the disease types included in the target disease type combination based on the disease coupling coefficient, to obtain an adjusted disease deduction.

[0070] In step S16, if there are disease types in the road section that satisfy the target disease type combination, the corresponding disease coupling coefficient in the disease coupling coefficient table is obtained, and the new disease deduction of the disease types included in the target disease type combination is adjusted based on the disease coupling coefficient to obtain an adjusted disease deduction. It can be understood that for the disease types in the road section that do not satisfy the target disease type combination, the new disease deduction does not need to be adjusted.

[0071] S17: Generate the target lane health index of the target lane based on the disease deductions of all disease types in all road sections.

[0072] In step S17, the target lane health index is the PCI index of the target lane. Specifically, the PCI index of each road section is calculated by calculating the total deduction value (Total DV) of the adjusted disease deductions of all disease types in each road section, and combining the pavement condition index formula PCI = 100 - a0 x (Total DV) a1. Then the PCI index of the target lane is obtained by calculating the average value of the PCI indexes of all road sections.

[0073] The embodiments of the present application first dynamically correct the original disease deduction value by introducing multiple severity evaluation indexes to generate a new disease deduction value that is more consistent with the actual damage degree. Then, for disease combinations with synergistic damage effect in the pavement, the corrected new disease deduction is secondarily corrected based on the coupling mechanism, and finally the target lane health index accurately representing the comprehensive influence of complex diseases is constructed, realizing the dual breakthroughs of multi-dimensional disease severity quantitative evaluation and synergistic effect compensation calculation, meeting the needs of modern road maintenance for pavement health state diagnosis, and improving the health index reliability and scientific nature of maintenance decision-making in complex disease scenarios.

[0074] In some embodiments, adjusting the original disease deduction corresponding to the disease type based on at least one severity evaluation index to obtain a new disease deduction includes the following steps:

[0075] S141: Obtain at least one corresponding correction coefficient based on at least one severity evaluation index.

[0076] S142: Select the maximum correction coefficient in the at least one correction coefficient as the target correction coefficient.

[0077] S143: Adjust the original disease deduction corresponding to the disease type based on the target correction coefficient to obtain a new disease deduction.

[0078] In S141, the severity evaluation indexes include disease spacing, penetration, and disease development rate, and one severity evaluation index corresponds to one correction coefficient. At least one severity evaluation index of the road disease is obtained, and the corresponding correction coefficient is calculated according to the correction coefficient formula corresponding to the severity evaluation index.

[0079] In S142, the target correction coefficient is used to correct the original disease deduction of the disease type. By comparing the values of at least one correction coefficient of the disease type, the correction coefficient with the largest value is selected as the target correction coefficient.

[0080] In S143, specifically, the target correction coefficient is multiplied by the original disease deduction of the disease type to obtain the new disease deduction.

[0081] In some embodiments, the severity evaluation indexes include disease spacing, penetration, and disease development rate, the correction coefficients include spacing correction coefficient and / or penetration correction coefficient and / or development rate correction coefficient, and at least one corresponding correction coefficient is obtained based on at least one severity evaluation index, including:

[0082] For the same disease type, road diseases with disease spacing less than or equal to a preset distance threshold are set as clustering diseases, the total number of diseases of the disease type in the road section and the number of clustering diseases of the clustering diseases are obtained, and the spacing correction coefficient of the disease type is calculated according to the spacing correction coefficient formula combined with the total number of diseases and the number of clustering diseases; and / or, the penetration of the road diseases in the disease type is sorted to obtain the maximum value of the penetration of the road diseases in the disease type, and the penetration correction coefficient of the disease type is calculated according to the penetration correction coefficient formula combined with the maximum value of the penetration; and / or, the development rate of the road diseases in the disease type is sorted to obtain the maximum value of the disease development rate of the road diseases in the disease type, and the development rate correction coefficient of the disease type is calculated according to the development rate correction coefficient formula combined with the maximum value of the disease development rate.

[0083] It can be understood that there is a one-to-one correspondence between the severity evaluation indexes and the correction coefficients: the disease spacing corresponds to the spacing correction coefficient, the penetration corresponds to the penetration correction coefficient, and the disease development rate corresponds to the development rate correction coefficient. Therefore, at least one corresponding correction coefficient is obtained based on at least one severity evaluation index, specifically, at least one of the spacing correction coefficient, the penetration correction coefficient, and the development rate correction coefficient corresponding to at least one of the disease spacing, the penetration, and the disease development rate of the road disease is obtained.

[0084] The interval correction coefficient is obtained based on the disease interval, specifically, the disease interval is the minimum distance between adjacent road surface diseases with the same disease type in the same road section. For the same disease type in the road section, if the disease interval of the road surface disease is less than or equal to a preset distance threshold, the preset distance threshold is 1 meter, the road surface disease is set as a clustered disease. Then, the total number of road surface diseases N and the number of clustered diseases n of the clustered disease are obtained. The interval correction coefficient Ks is calculated according to the interval correction coefficient formula Ks = 1 + 0.2 x n / N.

[0085] For example, please refer to Figure 2a , Figure 2a is a mask image diagram of road surface diseases of a road section. The diagram includes four road surface diseases, and the disease types of the four road surface diseases are all potholes. Among the distances between pothole 1 and pothole 2, pothole 3 and pothole 4, the distance between pothole 1 and pothole 2 is the minimum distance. Therefore, the distance between pothole 1 and pothole 2 is the disease interval of pothole 1, and the disease interval of pothole 1 is equal to 1 meter. Therefore, pothole 1 is set as a clustered disease. It can be understood that pothole 2 is also set as a clustered disease. Please refer to Figure 2b , among the distances between pothole 3 and pothole 1, pothole 2 and pothole 4, the distance between pothole 3 and pothole 4 is the minimum distance. Therefore, the distance between pothole 3 and pothole 4 is the disease interval of pothole 3, but the distance between pothole 3 and pothole 4 is greater than 1 meter. Therefore, pothole 3 is not set as a clustered disease. Similarly, as shown in Figure 2b , pothole 4 is also not set as a clustered disease, which will not be described here. The total number of potholes N in the road section is 4, and the number of clustered diseases n of the clustered disease is 2. According to the interval correction coefficient formula Ks = 1 + 0.2 x n / N, the interval correction coefficient Ks of the potholes in the road section is calculated to be 1.1.

[0086] The penetration correction coefficient is obtained based on the penetration. Specifically, for the same disease type in the road section, the penetration of the road surface disease is sorted to obtain the maximum value of the penetration of the road surface disease in the disease type. It can be understood that if there is only one road surface disease in the disease type, the penetration of the road surface disease is obtained, and sorting is not required. The penetration correction coefficient Kp is calculated according to the penetration correction coefficient formula Kp = 1 + 0.5 x P max , wherein P max is the maximum value of the penetration.

[0087] The development rate correction coefficient is obtained based on the disease development rate. Specifically, for the same disease type, the disease development rates of the pavement diseases in the road section are sorted to obtain the maximum value of the disease development rate of the pavement diseases in the disease type. It can be understood that if there is only one pavement disease in the disease type, the disease development rate of the pavement disease is obtained, and sorting is not needed. According to the development rate correction coefficient formula Kv = 1 + 0.02 x V max , wherein V max is the maximum value of the disease development rate, and the development rate correction coefficient Kv is calculated.

[0088] In the embodiments of the present application, the corresponding interval correction coefficient, the penetration correction coefficient and the development rate correction coefficient are obtained based on at least one severity evaluation index of the pavement disease, which are used to adjust the original disease deduction of the disease type, realize the fine and multi-dimensional quantitative correction of the disease hazard degree, and improve the accuracy, objectivity and characterization ability of the actual pavement condition of the disease deduction result.

[0089] In some embodiments, the correction coefficients include the interval correction coefficient, the penetration correction coefficient and the development rate correction coefficient, and the maximum correction coefficient is selected as the target correction coefficient in at least one correction coefficient, including: selecting the maximum value between the interval correction coefficient, the penetration correction coefficient and the development rate correction coefficient as the target correction coefficient. Specifically, for the same disease type, the interval correction coefficient, the penetration correction coefficient and the development rate correction coefficient of the disease type are obtained at the same time, and the maximum value among the three is selected as the target correction coefficient, which is used to adjust the original disease deduction of the disease type.

[0090] In the embodiments of the present application, the maximum correction coefficient is selected as the target correction coefficient from the interval correction coefficient, the penetration correction coefficient and the development rate correction coefficient of the disease type, which is used to adjust the original disease deduction of the disease type. The method follows the weakest link principle, and the most unfavorable correction coefficient is used for adjustment to ensure that the evaluation result is biased to the safe side and avoid the deviation of the correction result from the actual condition.

[0091] In some embodiments, the severity evaluation index includes disease spacing and / or penetration and / or disease development rate, and at least one severity evaluation index corresponding to the road surface disease of each disease type is obtained, including: obtaining the same distance between two adjacent road surface diseases of each disease type in the road section, determining the minimum same distance as the disease spacing of the road surface disease in one or more same distances belonging to the same road surface disease, and the disease spacing is the minimum distance between adjacent road surface diseases with 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 road surface disease of each disease type in the road section, the lateral extension length being the maximum distance of the road surface disease in the edge width direction, the longitudinal extension length being the maximum distance of the road surface disease in the edge length direction, calculating the first ratio of the lateral extension length of the road surface disease to the edge width, calculating the second ratio of the longitudinal extension length of the road surface disease to the edge length, and determining the maximum value of the two ratios as the penetration of the road surface disease, and the penetration is the extension ratio of the road surface disease in the lateral / longitudinal direction of the road section; and / or, obtaining historical road detection data, the historical road detection data including road section data of the road section in at least the previous two preset periods, calculating the disease development rate of the road surface disease of the disease type according to the road section data of the road section and the historical road detection data combined with linear regression, and the disease development rate is the expansion rate of the area / length of the road surface disease in the preset period.

[0092] The severity evaluation index includes disease spacing and / or penetration and / or disease development rate, and at least one severity evaluation index corresponding to the road surface disease of each disease type is obtained, specifically, at least one of the disease spacing, penetration and disease development rate corresponding to the road surface disease of each disease type is obtained.

[0093] The disease spacing corresponding to the road surface disease of each disease type is obtained, specifically, the same distance between two adjacent road surface diseases of each disease type in the road section is obtained, and the same distance is the distance between the road surface diseases with the same disease type in the road section. Specifically, in the embodiments of the present application, the minimum Euclidean distance between the mask pixel pairs of the disease contours of the two road surface diseases can be calculated, and then the number of pixel points between the two mask pixel points determining the minimum Euclidean distance is converted into a real physical distance combined with the physical scale of the image to obtain the same distance between the two road surface diseases. Please refer to Figure 3 , which contains crack 1 and crack 2, crack 1 and crack 2 are adjacent, the same distance between crack 1 and crack 2 is obtained, and the minimum Euclidean distance between the mask pixel pairs of the disease contours of crack 1 and crack 2 is calculated first, and then the number of pixel points between the two mask pixel points determining the minimum Euclidean distance is converted into a real physical distance combined with the physical scale of the image to obtain the same distance between the two road surface diseases. Please refer to Figure 3As shown, the minimum Euclidean distance between the mask pixel pairs of the disease profiles of crack 1 and crack 2 is the Euclidean distance between the mask pixel pair {11, 22}, and then according to the number of pixels between the mask pixel pair {11, 22}, combined with the physical scale of the image, the real physical distance is converted to obtain the same distance between crack 1 and crack 2. In one or more same distances belonging to the same pavement disease, the minimum same distance is determined as the disease spacing of the pavement disease. Specifically, the same distances obtained by combining the pavement disease with other pavement diseases two by two are traversed, and the minimum value among them is taken as the disease spacing of the pavement disease.

[0094] The embodiment of the present application effectively captures the local aggregation characteristics of the pavement disease by quantifying the spatial distribution relationship of the pavement disease. This breaks through the limitation of the traditional PCI calculation model which only relies on the number of diseases, realizes the evaluation of the regional damage potential, and makes the disease deduction more truly reflect the accelerated deterioration risk caused by dense distribution.

[0095] The penetration of the pavement disease corresponding to each disease type is obtained. Specifically, the edge width and the edge length of the road section are obtained first. In the embodiment of the present application, the edge width is 3.75 meters, and the edge length is 10 meters. Then the transverse extension length and the longitudinal extension length of the pavement disease in each disease type in the road section are obtained. Specifically, in the embodiment of the present application, for the pavement disease, the coordinates of the mask pixel points of the disease profile in the road section XOY coordinate system are extracted first. The maximum and minimum values of the X coordinates of all pixel points are determined, and the difference value (i.e. the pixel span in the X axis direction) is calculated. Combined with the physical scale of the image (such as the actual length represented by each pixel), the actual physical length of the difference value is calculated to obtain the transverse extension length of the pavement disease. Similarly, the maximum and minimum values of the Y coordinates of all pixel points are determined, the difference value (i.e. the pixel span in the Y axis direction) is calculated, and the same physical scale information is converted to calculate the actual physical length of the difference value to obtain the longitudinal extension length of the pavement disease. Please refer to Figure 4 , which contains a crack 41. To calculate the penetration of crack 41, the maximum value x2 and the minimum value x1 of the X coordinates of all mask pixel points of the disease profile in the road section XOY coordinate system are obtained first, the difference value is calculated, combined with the physical scale of the image (such as the actual length represented by each pixel), to obtain the transverse extension length of crack 41. Similarly, the maximum value y2 and the minimum value y1 of the Y coordinates of all pixel points are determined, the difference value (i.e. the pixel span in the Y axis direction) is calculated, and the same physical scale information is converted to obtain the longitudinal extension length of crack 41. Then the first ratio of the transverse 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.

[0096] The embodiments of the present application introduce the penetration degree, realize the quantification of the extension depth of the pavement disease in the pavement structure, and surpass the two-dimensional evaluation mode of the prior art which only focuses on the disease area / disease length. The severity evaluation index quantifies the degree of damage of the pavement disease to the structural integrity, makes up for the deficiency of the traditional method in evaluating the damage scale of diseases such as transverse cracks or structural potholes, and improves the directionality of the disease deduction to the actual loss of bearing capacity.

[0097] In some embodiments, the penetration degree corresponding to the pavement disease of each disease type is obtained, and the penetration degree can be calculated after the disease type is judged. For example, if it is judged in advance that the disease type of the pavement disease is a transverse crack, only the first ratio is calculated to determine the first ratio as the penetration degree of the pavement disease; if it is judged in advance that the disease type of the pavement disease is a longitudinal crack, only the second ratio is calculated to determine the second ratio as the penetration degree of the pavement disease.

[0098] The disease development rate corresponding to the pavement disease of each disease type is obtained. Specifically, historical pavement detection data is obtained, and the historical pavement detection data includes road section data of a road section in at least two previous preset periods. The preset period is one month. The historical pavement detection data includes at least two months of road section data saved in advance, and the road section data includes the disease area / disease length of the pavement disease of each disease type in the road section. Linear regression fitting is performed according to the current road section data and the road section data of at least two months, and the disease development rate of each disease type of the pavement disease is calculated.

[0099] The embodiments of the present application analyze the change trend of the pavement disease over time by introducing the disease development rate, construct the time dimension of the disease state evolution, overcome the instantaneous defect of the static evaluation, make the disease deduction reflect the activity and future deterioration tendency of the pavement disease, and provide a key basis for identifying the rapid degradation area and predicting the remaining service life.

[0100] The embodiments of the present application introduce the disease distance, the penetration degree, and the disease development rate, and construct a multi-dimensional evaluation system covering the spatial distribution, the structural morphology, and the time evolution, thereby improving the accuracy of the disease deduction in characterizing the actual damage, providing a solid data foundation for accurately identifying the maintenance key area and optimizing the resource allocation strategy, and enhancing the state evaluation reliability of the final pavement condition index and the support of the maintenance decision.

[0101] In some embodiments, a target disease type combination that meets a preset synergistic influence condition is searched for in at least two of the disease types, including the following steps:

[0102] S21: Obtain a disease coupling coefficient table.

[0103] S22: Select a target number of disease type combinations from the at least two disease types contained in the road section to form a candidate disease type combination.

[0104] S23: In response to the disease coupling coefficient table containing a disease type combination consistent with the candidate disease type combination, determine that the candidate disease type combination meets the preset synergistic effect condition, and take the candidate disease type combination as the target disease type combination.

[0105] In step S21, the disease coupling coefficient table is pre-stored in the memory of the electronic device, and the memory can be directly accessed to obtain the disease coupling coefficient table. The disease coupling coefficient table includes a plurality of disease type combinations and a disease coupling coefficient corresponding to each disease type combination. The value of the disease coupling coefficient is set based on multiple experiments and expert experience, and the specific content is shown in Table 1:

[0106] Table 1

[0107]

[0108] In step S22, a target number of disease type combinations are selected from the at least two disease types contained in the road section to form a candidate disease type combination. The target number is two, and specifically, all disease types contained in the road section are extracted from the disease deduction table, all disease types are combined in pairs to obtain the candidate disease type combination.

[0109] In step S23, the preset synergistic effect condition is the synergistic damage effect of different disease types. In response to the disease coupling coefficient table containing a disease type combination consistent with the candidate disease type combination, it is determined that the candidate disease type combination meets the preset synergistic effect condition, and the candidate disease type combination is taken as the target disease type combination. Specifically, all disease type combinations in the disease coupling coefficient table are extracted first, 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 matched, it is determined that the candidate disease type combination meets the preset synergistic effect condition, and the candidate disease type combination is taken as the target disease type combination.

[0110] In some embodiments, the new disease deduction of the disease type contained in the target disease type combination is adjusted to obtain an adjusted disease deduction, including the following steps:

[0111] S31: Based on the disease coupling coefficient table, obtain the disease coupling coefficient corresponding to the target disease type combination;

[0112] S32: Adjust the new disease deduction of the disease type contained in the target disease type combination using the disease coupling coefficient to obtain an adjusted disease deduction.

[0113] In step S31, specifically, the disease type combinations in the disease coupling coefficient table are traversed to find a disease type combination consistent with the target disease type combination, and the corresponding disease coupling coefficient is obtained.

[0114] 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, respectively, to obtain the adjusted disease deduction points of the two disease types.

[0115] The embodiments of the present application introduce a disease coupling coefficient table, obtain the disease coupling coefficient corresponding to the target disease type combination, and accordingly make secondary correction to the new disease deduction points of the disease types included in the target disease type combination. The embodiments of the present application systematically take into account the synergistic damage effect between different disease types, improve the representation accuracy of the damage force of the disease deduction result on the actual damage force of the composite disease, optimize the integrity of the PCI index calculation, and enhance the recognition ability of high-risk disease combinations and the pertinence of the maintenance strategy.

[0116] In some embodiments, based on the disease deduction points of all disease types in all road segments, a target lane health index of a target lane is generated, including the following steps:

[0117] S41: Based on the disease deduction points of all disease types in each road segment, a road segment health index of each road segment is calculated.

[0118] S42: The average value of the road segment health indexes of all road segments is calculated to obtain a candidate lane health index.

[0119] S43: The target lane health index of the target lane is generated based on the candidate lane health index.

[0120] In step S41, specifically, the total deduction value of each road segment is calculated according to the adjusted disease deduction points and / or the new disease deduction points of all disease types in each road segment, and the PCI index corresponding to each road segment is calculated by combining the pavement condition coefficient formula, i.e., the road segment health index.

[0121] In step S42, specifically, the average value of the PCI indexes of all road segments is calculated, i.e., the candidate lane health index is obtained.

[0122] 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 index, specifically, the average value of the PCI indexes of all road segments is taken as the PCI index of the target lane, i.e., the target lane health index.

[0123] In some embodiments, the target lane health index comprises a first lane health index, the target lane further comprises a shoulder area and an edge area, the target lane health index of the target lane is generated based on the candidate lane health index, comprising the following steps:

[0124] S51: Obtain the lane health index of the shoulder area and the lane health index of the edge area in each road section.

[0125] S52: Calculate the average value of the lane health index of the shoulder area in all road sections to obtain the shoulder health index of the target lane.

[0126] S53: Calculate the average value of the lane health index of the edge area in all road sections to obtain the edge health index of the target lane.

[0127] S54: Perform weighted calculation on the shoulder health index, the edge health index and the candidate lane health index to obtain the first lane health index of the target lane.

[0128] In step S51, the target lane further comprises a shoulder area and an edge area, the lane health index of the shoulder area is the PCI index of the shoulder area, and the lane health index of the edge area is the PCI index of the edge area. The PCI index of the shoulder area and the PCI index of the edge area in each road section are obtained by manual calculation and are pre-stored in the memory of the electronic device. The lane health index of the shoulder area and the lane health index of the edge area in each road section are obtained directly through the memory.

[0129] In step S52, the shoulder health index is the PCI index of the shoulder area of the target lane. Specifically, the average value of the 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.

[0130] In step S53, the edge health index is the PCI index of the edge area of the target lane. Specifically, the average value of the PCI index of the edge area in all road sections is calculated to obtain the PCI index of the edge area of the target lane.

[0131] In step S54, it can be understood that, please refer to Figure 5The lane includes a road surface area 51, a shoulder area 52, and an edge area 53, and the functions and roles borne by the three are different. The shoulder health index, the edge health index, and the candidate lane health index are weighted and calculated based on the function weight, to obtain a first lane health index of the target lane. The function weight includes a road surface weight, a shoulder weight, and an edge weight. In the embodiment of the application, the road surface 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 a PCI index of the target lane introduced in the spatial dimension. Specifically, the first lane health index of the target lane is obtained by calculating the sum of the product of the road surface 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.

[0132] The embodiment of the application breaks through the limitation of the traditional PCI calculation architecture that only focuses on the road surface of the lane and ignores the influence of the associated structure, realizes comprehensive quantitative evaluation of the spatial integrity of the road domain, and significantly improves the representation accuracy, spatial correlation, and maintenance decision support value of the PCI index of the target lane.

[0133] In some embodiments, the target lane health index includes a second lane health index, and the target lane health index of the target lane is generated based on the candidate lane health index, including the following steps:

[0134] S61: Obtain a pre-stored historical lane health index.

[0135] S62: Weight and calculate the candidate lane health index and the historical lane health index to obtain a second lane health evaluation index.

[0136] In step S61, the historical lane health index includes the candidate lane health index of the previous two preset periods, and the preset period is one month. The second lane health index is a PCI index of the target lane introduced in the time dimension, and specifically, the historical lane health index includes the candidate lane health index of the previous month and the candidate lane health index of the previous two months. The historical lane health index is saved in the memory of the electronic device and can be directly obtained through the memory.

[0137] In step S62, it can be understood that the development of the road disease has a clear time trend. The candidate lane health index and the historical lane health index are weighted and calculated based on the development weight to obtain the second lane health evaluation index. The development weight includes the current period weight, the last period weight, and the two previous period weights. In the embodiments of the present application, the current period weight is set to 0.6, the last period weight is set to 0.3, and the two previous period weights are 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 last period weight and the candidate lane health index of the last month, and the product of the two previous period weights and the candidate lane health index of the last two months.

[0138] The embodiments of the present application perform weighted fusion calculation on the current candidate lane health index and the historical lane health index based on the development weight, and fully take into account the time dimension information. This method effectively captures and quantifies the dynamic change characteristics of the lane health condition, improves the representation timeliness, trend prediction ability and anti-short-term fluctuation interference of the target lane PCI index, and can provide a more reliable basis for forward-looking maintenance planning.

[0139] It should be noted that in the above various embodiments, the above steps do not necessarily have a certain sequence. Those skilled in the art can understand from the description of the embodiments of the present application that the above steps can have different execution sequences in different embodiments, that is, they can be executed in parallel, or they can be exchanged and executed, and the like.

[0140] Referring to Figure 6 , Figure 6 is a structural schematic diagram of an electronic device provided by the embodiments 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, connected to the processor 61 through a bus.

[0141] The processor 61 is configured to support the computer device to perform the corresponding functions in the methods in the above method embodiments. The processor 61 can be a central processing unit (CPU), a network processor (NP), a hardware chip or any combination thereof. The above hardware chip can be an application specific integrated circuit (ASIC), a programmable logic device (PLD) or a combination thereof. The above PLD can be a complex programmable logic device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL) or any combination thereof.

[0142] The memory 62 is configured to store program codes and the like. The memory 62 can include a volatile memory (VM), such as a random access memory (RAM); the memory 62 can also include a non-volatile memory (NVM), such as a read-only memory (ROM), a flash memory, a hard disk drive (HDD) or a solid-state drive (SSD); and the memory 62 can further include a combination of the above-mentioned memories.

[0143] The memory 62 can be configured to store non-volatile software programs, non-volatile computer-executable programs and modules, such as program instructions / modules corresponding to the road surface health evaluation method in the embodiments of the present application. The processor 61 performs the road surface health evaluation method by running the non-volatile software programs, instructions and modules stored in the memory, that is, implements the road surface health evaluation method provided in the above method embodiments.

[0144] The memory 62 can include a program storage area and a data storage area, wherein the program storage area can store an operating system and at least one application required by a function. In some embodiments, the memory 62 can optionally include a memory remotely arranged with respect to the processor. Examples of the above network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network and a combination thereof.

[0145] The one or more modules are stored in the memory 62 and, when executed by the one or more processors, perform the road health assessment method in any of the above method embodiments, e.g., perform the method steps described in the above method embodiments, implement the functions of the modules described in the above device embodiments.

[0146] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be completed by a computer program instructing related hardware. The program can be stored in a computer readable storage medium. When the program is executed, the program can include the processes of the above-mentioned embodiments. The storage medium can be a magnetic disc, an optical disc, a read-only memory (ROM), a random access memory (RAM), or the like.

[0147] The above disclosure is only the preferred embodiments of the present application, and of course cannot limit the scope of the rights of the present application, so the equivalent changes made according to the claims of the present application still fall within the scope of the present application.

Claims

1. A method of pavement health assessment, characterized by, The method comprises the following steps: obtaining road surface detection data of a target lane, the target lane comprising a plurality of road sections of equal length, the road surface detection data comprising road section data of the plurality of road sections; identifying a disease type contained in the road section based on the road section data; obtaining an original disease deduction corresponding to each disease type and a severity evaluation index corresponding to the road surface disease of each disease type, the original disease deduction being used to represent the damage degree of the road surface disease of each disease type; adjusting the original disease deduction corresponding to the disease type based on the severity evaluation index to obtain a new disease deduction, comprising: obtaining a corresponding correction coefficient based on the severity evaluation index, the severity evaluation index comprising disease spacing, penetration and disease development rate, the correction coefficient comprising a spacing correction coefficient, a penetration correction coefficient and a development rate correction coefficient, the obtaining of the corresponding correction coefficient based on the severity evaluation index comprising: for the same disease type, setting road surface diseases with a disease spacing less than or equal to a preset distance threshold as clustered diseases, obtaining a total number of diseases of the disease type in the road section and a clustered disease number of the clustered diseases, and calculating the spacing correction coefficient of the disease type according to a spacing correction coefficient formula in combination with the total number of diseases and the clustered disease number; sorting the penetration of the road surface diseases in the disease type to obtain a maximum value of the penetration of the road surface diseases in the disease type, and calculating the penetration correction coefficient of the disease type according to a penetration correction coefficient formula in combination with the maximum value of the penetration; sorting the development rate of the road surface diseases in the disease type to obtain a maximum value of the disease development rate of the road surface diseases in the disease type, and calculating the development rate correction coefficient of the disease type according to a development rate correction coefficient formula in combination with the maximum value of the disease development rate; selecting a maximum value among the spacing correction coefficient, the penetration correction coefficient and the development rate correction coefficient as a target correction coefficient; adjusting the original disease deduction corresponding to the disease type based on the target correction coefficient to obtain a new disease deduction; in response to the number of disease types contained in the road section being greater than or equal to 2, finding a target disease type combination satisfying a preset synergistic influence condition among at least two disease types; adjusting the new disease deduction of the disease types contained in the target disease type combination to obtain an adjusted disease deduction; generating a target lane health index of the target lane based on the disease deductions of all the disease types in all the road sections.

2. The method of claim 1, wherein, The severity evaluation index comprises disease spacing, penetration and disease development rate, and the obtaining of the severity evaluation index corresponding to the road surface disease of each disease type comprises: obtaining a same-type distance between adjacent road surface diseases of each disease type in the road section, and determining a minimum same-type distance as a disease spacing of the road surface disease in one or more same-type distances belonging to the same road surface disease, the disease spacing being a minimum distance between adjacent road surface diseases with the same disease type in the same road section. obtaining an edge width and an edge length of the road section, obtaining a transverse extension length and a longitudinal extension length of the pavement disease in each disease type in the road section, the transverse extension length being a maximum distance of the pavement disease in the edge width direction, and the longitudinal extension length being a maximum distance of the pavement disease in the edge length direction, calculating a first ratio of the transverse extension length of the pavement disease to the edge width, calculating a second ratio of the longitudinal extension length of the pavement disease to the edge length, and determining a maximum value of the two ratios as a penetration degree of the pavement disease, the penetration degree being an extension ratio of the pavement disease in the transverse / longitudinal direction of the road section; obtaining historical pavement detection data, the historical pavement detection data including road section data of the road section in at least two previous preset periods, and calculating a disease development rate of the pavement disease of the disease type according to the road section data of the road section and the historical pavement detection data in combination with linear regression, the disease development rate being an expansion rate of the area / length of the pavement disease in a preset period.

3. The method of claim 1, wherein, The target disease type combination satisfying the preset synergistic influence condition is searched from at least two disease types, including: obtaining a disease coupling coefficient table, the disease coupling coefficient table including a plurality of disease type combinations and a disease coupling coefficient corresponding to each disease type combination; selecting a target number of disease type combinations from at least two disease types included in the road section as candidate disease type combinations; in response to the disease coupling coefficient table containing a disease type combination consistent with the candidate disease type combination, determining that the candidate disease type combination satisfies the preset synergistic influence condition, and taking the candidate disease type combination as the target disease type combination.

4. The method of claim 3, wherein, The target disease type combination includes adjusting the new disease deduction of the disease type, obtaining the adjusted disease deduction, including: obtaining the disease coupling coefficient corresponding to the target disease type combination based on the disease coupling coefficient table; adjusting the new disease deduction of the disease type included in the target disease type combination by using the disease coupling coefficient to obtain the adjusted disease deduction.

5. The method of claim 1, wherein, The target lane health index of the target lane is generated based on the disease deduction of all disease types in all road sections, including: calculating the road section health index of each road section based on the disease deduction of all disease types in each road section; calculating the average value of the road section health index of all road sections to obtain a candidate lane health index; generating the target lane health index of the target lane based on the candidate lane health index.

6. The method of claim 5, wherein, The target lane health index includes a first lane health index, and the target lane further includes a shoulder area and an edge area, and the target lane health index of the target lane is generated based on the candidate lane health index, including: obtaining the lane health index of the shoulder area and the lane health index of the edge area in each road section; calculating the average value of the lane health index of the shoulder area in all road sections to obtain the shoulder health index of the target lane; calculating the average value of the lane health index of the edge area in all road sections to obtain the edge health index of the target lane; The shoulder health index, the edge health index and the candidate lane health index are weighted to obtain a first lane health index of the target lane.

7. The method of claim 5, wherein, The target lane health index includes a second lane health index, and the target lane health index of the target lane is generated based on the candidate lane health index, including: A pre-stored historical lane health index is obtained, and the historical lane health index includes candidate lane health indexes of previous two preset periods. The candidate lane health index and the historical lane health index are weighted to obtain a second lane health evaluation index.

Images