Traffic and infrastructure monitoring system based on optical fiber

Abstract

The invention discloses an optical fiber-based traffic and infrastructure monitoring system, which relates to the technical field of road marking monitoring and can comprehensively acquire wear information and other related data of road marking in real time through an optical fiber sensing technology. By means of the deep learning model or the support vector machine technology, the abrasion condition of the road marking can be predicted in advance, a primary early warning instruction is issued in time when the marking abrasion index Msz exceeds the abrasion threshold value A, and potential safety hazards caused by marking failure are avoided. The system provides personalized repair strategies according to the repair indexes Xfzs of different monitoring areas, so that the pertinence and effectiveness of repair are improved, and unnecessary maintenance cost and resource waste are reduced. The road marking is clear and complete through accurate marking abrasion monitoring and timely and effective repairing, the road safety and the traffic efficiency are improved, and the occurrence rate of traffic accidents is reduced.

Description

Technical Field

[0001] The invention relates to the technical field of road marking monitoring, in particular to an optical fiber-based traffic and infrastructure monitoring system. Background Art

[0002] The maintenance and management of transportation infrastructure plays a vital role in ensuring road safety and improving traffic efficiency. As an important part of transportation infrastructure, road markings are mainly used to guide and regulate driving behavior, improve road use efficiency, and ensure traffic safety. However, with the increase in traffic volume and the impact of bad weather, road markings will be worn and damaged to varying degrees, resulting in blurred markings, falling off, or even failure, which seriously affects traffic order and driving safety. Therefore, the monitoring and repair of road markings have become an important part of transportation infrastructure maintenance.

[0003] The main reasons for road marking wear include: a large number of vehicles passing by will cause wear on the road markings, especially the frequent passage of heavy vehicles, which will accelerate the wear and fall of the markings. Weather conditions such as rain, snow, freezing and high temperature will cause different degrees of damage to road markings. For example, rain will cause the markings to fade, freezing will cause the markings to crack and fall off, and high temperature will cause the markings to soften and deform. Factors such as the flatness of the road surface and cracks in the road surface will also affect the durability and clarity of the road markings. The unevenness of the road surface and the density of cracks will aggravate the wear of the markings. Traditional road marking monitoring mainly relies on manual inspections and vehicle video monitoring, which makes it difficult to obtain real-time and comprehensive information on the wear of the markings. Manual inspections are inefficient and costly, and are limited by human resources and are difficult to cover all roads. Summary of the invention

[0004] In view of the deficiencies of the prior art, the present invention provides a traffic and infrastructure monitoring system based on optical fiber to solve the problems mentioned in the background technology.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: a traffic and infrastructure monitoring system based on optical fiber, comprising: The traffic intersection acquisition module is used to pre-select the monitoring traffic street range according to the traffic facility management requirements, collect the intersection latitude and longitude coordinates and structural information, and divide each intersection into independent monitoring areas; A real-time monitoring module is used to monitor the wear information of road markings to establish a first data set; and to monitor the road flatness information, weather impact information, and traffic behavior information in the corresponding monitoring area to establish a second data set; A processing module, used for performing data preprocessing on the first data set and the second data set, wherein the preprocessing includes data cleaning, data synchronization and dimensionless data processing, and then transmitting and storing the data to a facility management data set; A prediction module is used to extract the road marking wear characteristics in the corresponding monitoring area based on the first data set by using the trained road surface prediction model, and construct a road marking wear index Msz. When the road marking wear index Msz exceeds the wear threshold A, a preliminary warning instruction is issued externally; and the road flatness information, weather impact information and vehicle flow behavior information are feature extracted to respectively obtain the road surface roughness Ccd, road surface crack density lfmd, pothole density kwmd, average change value of vehicle vertical acceleration Jsdb, rainfall Jyl, ice thickness Bchd, road surface temperature PT, traffic density Jtmd, lane change frequency Bdpc, heavy vehicle flow Zxcl and lane emergency braking frequency Jspc in the corresponding monitoring area, and calculate and obtain the road surface flatness influence factor L, thermal expansion and contraction influence factor Rs and vehicle flow behavior influence factor Xw; the road marking wear index Msz, road surface flatness influence factor L, thermal expansion and contraction influence factor Rs and vehicle flow behavior influence factor Xw in the corresponding monitoring area are associated, and the repair index Xfzs of the corresponding monitoring area is calculated; A management module is used to pre-set a first repair threshold Q 1 and the second repair threshold Q 2 and the restoration index Xfzs in the corresponding monitoring area is compared with the first restoration threshold Q 1 and the second repair threshold Q 2 Conduct comparative analysis and adopt management measures within the corresponding monitoring area based on the results of the comparative analysis.

[0006] Preferably, the traffic intersection acquisition module includes a region segmentation unit and a deployment unit; The area segmentation unit is used for traffic facility management needs, determining the intersections and street ranges of traffic infrastructure that need to be monitored; and dividing the streets around each traffic intersection into monitoring areas, setting the streets within a radius of 50 meters with the intersection as the center as the monitoring area; The deployment unit is used to deploy monitoring points in each monitoring area, specifically including: setting distributed optical fiber sensors along the markings and road surfaces to monitor changes in marking temperature and road surface height; Rainfall sensors are deployed in the monitoring area, and the optical fiber network transmits rainfall data; Temperature sensors and optical fiber ice detection sensors are laid on the road surface to monitor the thickness of the ice layer; Temperature sensors are laid on the road surface to transmit temperature data via optical fiber; Pressure sensors and traffic flow sensors are laid on the road surface, and optical fibers transmit traffic density data; Distributed fiber optic sensors are deployed along the lane lines to detect vehicle lane-changing behavior; Deploy weight sensors on the road surface to transmit heavy vehicle data via optical fiber; Acceleration sensors are placed on the road surface and emergency braking frequency data is transmitted via a fiber optic network.

[0007] Preferably, the prediction module includes a model building unit and a first calculation unit; The model building unit is used to select a deep learning model or a support vector machine (SVM) technology to build a road surface prediction model, and divide the first data set and the second data set into a 70% training set and a 30% validation set to train and evaluate the road surface prediction model; The first calculation unit is used to extract the road marking deformation characteristics in the corresponding monitoring area according to the first data set, calculate and obtain the road marking deformation degree Bxd, and use the road marking deformation degree in the i-th monitoring area as the Take this as an example, and obtain it as follows: S11. First, the original marking shape area is obtained through CAD drawings or original construction data, and the actual shape data of the current marking is obtained using image processing technology and sensors to obtain the actual marking contour point set and the original marking contour point set: Assume that the actual line contour point set is , represents n discrete points extracted from the actual marking contour; Assume that the original line contour point set is , represents m discrete points extracted from the original design marking contour; S12, and calculate the maximum value of the minimum distances from all actual marking points to the original marking points : ; S13, and calculate the average value of the minimum distances from all actual marking points to the original marking points : ; In the formula, It means to sum the minimum value of the distance from each actual marking point p to all original marking points q. It means averaging the sum and calculating the average value of the minimum distance from each actual marking point to the original marking point; S14. The maximum value of the minimum distances from all actual marking points to the original marking points And the average value of the minimum distance from all actual marking points to the original marking points The deformation degree of the marking line in the i-th monitoring area is calculated by the following formula: : ; In the formula, and is the weight coefficient, and .

[0008] Preferably, the prediction module further includes a second calculation unit and a first early warning unit; The second calculation unit is used to extract the road marking wear characteristics in the corresponding monitoring area based on the first data set, associate the road marking deformation Bxd in the corresponding monitoring area, calculate and obtain the road marking wear index Msz, and use the light marking wear index in the i-th monitoring area as the Take this as an example, and obtain it as follows: ; In the formula, It is expressed as the reduction in the thickness of the marking line in the i-th monitoring area, It is expressed as the brightness attenuation value of the marking color in the i-th monitoring area, represents the deformation degree of the marking line in the i-th monitoring area, It is expressed as the number of broken segments of the marking line in the i-th monitoring area, and They are all weight coefficients, which are adjusted and set by the user, and the sum of the weight coefficients is 1. Expressed as the first correction constant.

[0009] Preferably, the first warning unit is used to compare and analyze the wear threshold A with the road marking wear index Msz in the corresponding monitoring area to preliminarily determine whether the road marking wear in the current monitoring area is in an abnormal state, and the specific contents are as follows: If the marking wear index in the i-th monitoring area When the wear threshold A is exceeded, it indicates that the road marking wear in the current monitoring area is in an abnormal state, and a primary warning instruction is issued; If the marking wear index in the i-th monitoring area When the wear threshold value A is not exceeded, it indicates that the road marking wear in the current monitoring area is in a normal wear state.

[0010] Preferably, the prediction module further includes a road surface smoothness calculation unit; The road surface smoothness calculation unit is used to extract features based on the road surface smoothness information after receiving the primary warning instruction, so as to obtain the road surface roughness Ccd, road surface crack density lfmd, pothole density kwmd, and average change value of vehicle vertical acceleration Jsdb in the corresponding monitoring area, perform dimensionless processing, and calculate and obtain the road surface smoothness influence factor L in the corresponding monitoring area, and use the road surface smoothness influence factor L in the i-th monitoring area as the road surface smoothness influence factor L. Take this as an example, and obtain it as follows: ; ; In the formula, is the road surface height in the ith monitoring area, represents the average height of k sampling points, where k represents the number of sampling points; It is expressed as the road surface roughness in the i-th monitoring area, It is expressed as the pavement crack density in the i-th monitoring area, represents the pothole density in the i-th monitoring area, It is expressed as the average change value of the vertical acceleration of the traffic flow in the i-th monitoring area, and They are all weight coefficients, which are adjusted and set by the user, and the sum of the weight coefficients is 1. Expressed as the second correction constant.

[0011] Preferably, the prediction module further includes a thermal expansion and contraction influence calculation unit; the thermal expansion and contraction influence calculation unit is used to calculate and obtain the thermal expansion and contraction influence factor Rs of the corresponding monitoring area after dimensionless processing based on the rainfall Jyl, the ice layer thickness Bchd and the road surface temperature PT, and to calculate the thermal expansion and contraction influence factor Rs in the i-th monitoring area. Take this as an example, and obtain it as follows: ; In the formula, It is expressed as the rainfall in the i-th monitoring area, It is represented by the ice thickness of the road surface in the i-th monitoring area, PT is the road surface temperature in the i-th monitoring area, Indicates the maximum temperature that the road surface can withstand. and are weight coefficients, Expressed as the third correction constant.

[0012] Preferably, the prediction module further includes a vehicle flow behavior impact calculation unit and a correlation unit; The vehicle flow behavior impact calculation unit is used to calculate and obtain the vehicle flow behavior impact factor Xw based on the traffic density Jtmd, the lane change frequency Bdpc, the heavy vehicle flow Zxcl and the lane emergency braking frequency Jspc after dimensionless processing; the vehicle flow behavior impact factor Xw in the i-th monitoring area Take this as an example, and obtain it as follows: ; In the formula, It is expressed as the traffic density in the i-th monitoring area, It is represented as the frequency of lane changes in the i-th monitoring area, represents the heavy vehicle flow in the i-th monitoring area, represents the frequency of emergency braking in the lane within the i-th monitoring area, and are weight coefficients, Expressed as the fourth correction constant; The association unit is used to associate the road surface flatness influence factor L, the thermal expansion and contraction influence factor Rs, the traffic behavior influence factor Xw and the road marking wear index Msz of the corresponding monitoring area, and calculate the repair index Xfzs of the corresponding monitoring area. i Take this as an example, and obtain it as follows: ; In the formula, They are all weight coefficients, e is the base of natural numbers, and its value is 2.71828.

[0013] Preferably, the management module comprises a first level assessment unit and a second repair unit; The first level evaluation unit compares the restoration index Xfzs in the corresponding monitoring area with the first restoration threshold Q 1 and the second repair threshold Q 2 Comparative analysis is performed to determine the corresponding level of road marking wear in the current monitoring area. The specific contents are as follows: If the repair index Xfzs < the first repair threshold Q 1 , generate the first level evaluation results; If the first repair threshold Q 1 ≤Repair index Xfzs≤Second repair threshold Q 2 , generate the second level evaluation results; If the repair index Xfzs> the second repair threshold Q 2 , generate the third level evaluation results.

[0014] Preferably, the second repair unit is used to generate a corresponding repair strategy according to the first level evaluation result, the second level evaluation result and the third level evaluation result, including: The first level assessment results generate the first repair strategy, including: dispatching a maintenance team to clean and dry the road surface within 36 hours, clean the damaged area of ​​the marking, remove the loose part of the marking, and repair the damaged area to make the connection between the repaired part and the original marking smooth and avoid unevenness. Then, use cold spray paint to add a layer of paint on the original surface and spray a layer of anti-skid granule protective layer; The second level assessment results generate the second repair strategy, including: dispatching maintenance teams to clean and dry the road surface, fill potholes and uneven areas, and repaint the road markings in the corresponding monitoring area within 48 hours using thermal spray paint; using thermal spray paint to add one layer of paint on the original surface and spray two layers of anti-skid granule protective layer; The third-level assessment results generate the third repair strategy, including: immediately starting the emergency maintenance procedure, dispatching an emergency maintenance team to use heating equipment to melt and remove the old markings within 24 hours, and then removing the old markings, including grinding or high-pressure water washing; and redrawing new markings, including at least 1 layer of primer, 1 layer of hot-melt mid-coat, 1 layer of reflective ceramic particle surface layer and 1 layer of anti-skid particle protective layer.

[0015] The present invention provides a traffic and infrastructure monitoring system based on optical fiber, which has the following beneficial effects: (1) This optical fiber-based traffic and infrastructure monitoring system can obtain the wear information and other relevant data of road markings in real time and comprehensively through optical fiber sensing technology, solving the problems of low efficiency and limited coverage of traditional manual inspections and video surveillance. By using deep learning models or support vector machine technology, it can predict the wear of road markings in advance and issue primary warning instructions in time when the marking wear index Msz exceeds the wear threshold A, avoiding the safety hazards caused by marking failure. The system provides personalized repair strategies based on the repair index Xfzs of different monitoring areas, which not only improves the pertinence and effectiveness of repairs, but also reduces unnecessary maintenance costs and resource waste. Through accurate marking wear monitoring and timely and effective repairs, the clarity and integrity of road markings are ensured, road safety and traffic efficiency are improved, and the incidence of traffic accidents is reduced.

[0016] (2) The road surface smoothness calculation unit is used to extract features based on the road smoothness information after receiving the primary warning instruction, so as to obtain the road surface roughness Ccd, road surface crack density lfmd, pothole density kwmd, and average change value of vehicle vertical acceleration Jsdb in the corresponding monitoring area, and perform dimensionless processing to calculate and obtain the road surface smoothness influence factor L in the corresponding monitoring area. The road surface smoothness influence factor L can monitor and evaluate the smoothness of the road surface in real time, discover and repair problems in time, reduce the negative impact on road markings, and ensure the good operation of transportation infrastructure.

[0017] (3) Calculating the thermal expansion and contraction factor Rs can comprehensively evaluate the combined effects of temperature changes, rainfall, and ice on road markings, and help understand the actual impact of these factors on road marking materials and functions. Based on the calculation results of the thermal expansion and contraction factor, a more accurate maintenance plan can be formulated, and road markings can be repaired or repainted in a timely manner to reduce road marking failures caused by temperature changes. Determining the thermal expansion and contraction factor Rs can adjust maintenance and repair plans, taking into account the effects of seasonal changes and extreme weather conditions on road markings, and ensuring that road markings are always kept in good condition.

[0018] (4) By calculating the traffic behavior impact factor Xw, we can more accurately identify traffic-intensive areas and high-risk areas, thereby optimizing road marking maintenance and repair strategies. Identifying high-impact areas helps to rationally allocate maintenance resources and priorities, reducing unnecessary maintenance costs and time waste. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 The present invention is a block diagram of a traffic and infrastructure monitoring system based on optical fiber. DETAILED DESCRIPTION

[0020] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0021] Example 1, please refer to Figure 1 The present invention provides a traffic and infrastructure monitoring system based on optical fiber, please refer to Figure 1 ,include, The traffic intersection acquisition module is used to pre-select the monitoring traffic street range according to the traffic facility management requirements, collect the intersection latitude and longitude coordinates and structural information, and divide each intersection into independent monitoring areas; A real-time monitoring module is used to monitor the wear information of road markings to establish a first data set; and to monitor the road flatness information, weather impact information, and traffic behavior information in the corresponding monitoring area to establish a second data set; A processing module, used for performing data preprocessing on the first data set and the second data set, wherein the preprocessing includes data cleaning, data synchronization and dimensionless data processing, and then transmitting and storing the data to a facility management data set; A prediction module is used to extract the road marking wear characteristics in the corresponding monitoring area based on the first data set by using the trained road surface prediction model, and construct a road marking wear index Msz. When the road marking wear index Msz exceeds the wear threshold A, a preliminary warning instruction is issued externally; and the road flatness information, weather impact information and vehicle flow behavior information are feature extracted to respectively obtain the road surface roughness Ccd, road surface crack density lfmd, pothole density kwmd, average change value of vehicle vertical acceleration Jsdb, rainfall Jyl, ice thickness Bchd, road surface temperature PT, traffic density Jtmd, lane change frequency Bdpc, heavy vehicle flow Zxcl and lane emergency braking frequency Jspc in the corresponding monitoring area, and calculate and obtain the road surface flatness influence factor L, thermal expansion and contraction influence factor Rs and vehicle flow behavior influence factor Xw; the road marking wear index Msz, road surface flatness influence factor L, thermal expansion and contraction influence factor Rs and vehicle flow behavior influence factor Xw in the corresponding monitoring area are associated, and the repair index Xfzs of the corresponding monitoring area is calculated; A management module is used to pre-set a first repair threshold Q 1 and the second repair threshold Q 2 and the restoration index Xfzs in the corresponding monitoring area is compared with the first restoration threshold Q 1 and the second repair threshold Q 2 Conduct comparative analysis and adopt management measures within the corresponding monitoring area based on the results of the comparative analysis.

[0022] In this embodiment, the wear information and other relevant data of road markings can be obtained in real time and comprehensively through optical fiber sensing technology, which solves the problems of low efficiency and limited coverage of traditional manual inspection and video monitoring. The system integrates multi-dimensional information such as road surface flatness, weather influence and traffic behavior, and can more accurately evaluate the status of road markings and their influencing factors, thereby improving the comprehensiveness and accuracy of monitoring. By using deep learning models or support vector machine technology, the wear of road markings can be predicted in advance, and primary warning instructions can be issued in time when the marking wear index Msz exceeds the wear threshold A, thereby avoiding the safety hazards caused by marking failure. The system provides personalized repair strategies based on the repair index Xfzs of different monitoring areas, which not only improves the pertinence and effectiveness of repair, but also reduces unnecessary maintenance costs and waste of resources. Through accurate marking wear monitoring and timely and effective repair, the clarity and integrity of road markings are ensured, the safety and traffic efficiency of roads are improved, and the incidence of traffic accidents is reduced.

[0023] Example 2, please refer to Figure 1 , the traffic intersection acquisition module includes a region segmentation unit and a deployment unit; The area segmentation unit is used for traffic facility management needs, determining the intersections and street ranges of traffic infrastructure that need to be monitored; and dividing the streets around each traffic intersection into monitoring areas, setting the streets within a radius of 50 meters with the intersection as the center as the monitoring area; The deployment unit is used to deploy monitoring points in each monitoring area, specifically including: setting distributed optical fiber sensors along the markings and road surfaces to monitor changes in marking temperature and road surface height; Rainfall sensors are deployed in the monitoring area, and the optical fiber network transmits rainfall data; Temperature sensors and optical fiber ice detection sensors are laid on the road surface to monitor the thickness of the ice layer; Temperature sensors are laid on the road surface to transmit temperature data via optical fiber; Pressure sensors and traffic flow sensors are laid on the road surface, and optical fibers transmit traffic density data; Distributed fiber optic sensors are deployed along the lane lines to detect vehicle lane-changing behavior; Deploy weight sensors on the road surface to transmit heavy vehicle data via optical fiber; Acceleration sensors are placed on the road surface and emergency braking frequency data is transmitted via a fiber optic network.

[0024] The first data set includes: marking deformation Bxd, marking thickness reduction , Marking color brightness attenuation value and the number of broken segments of the marking line ; The second data set includes: road surface roughness Ccd, road surface crack density lfmd, pothole density kwmd, average change value of vehicle vertical acceleration Jsdb, rainfall Jyl, ice thickness Bchd, road surface temperature PT, traffic density Jtmd, lane change frequency Bdpc, heavy vehicle flow Zxcl and lane emergency braking frequency Jspc.

[0025] In this embodiment, based on distributed fiber optic sensor technology, the temperature change of road markings and the height change of the road surface can be obtained in real time, and the road condition data can be fully collected. Through the deployment of rain sensors, temperature sensors, ice detection sensors, pressure sensors, traffic sensors, weight sensors and acceleration sensors, the impact of environmental and traffic factors on road markings can be fully and real-time monitored. Integrate multiple sensor data, perform data cleaning, data synchronization and data dimensionless processing to ensure data accuracy and consistency. Provide a wealth of environmental and traffic parameters, such as temperature, rainfall, ice thickness, traffic density, lane change behavior, heavy vehicle traffic and emergency braking frequency, etc., to provide a scientific basis for the comprehensive evaluation of road marking wear.

[0026] Example 3, please refer to Figure 1, the prediction module includes a model building unit and a first calculation unit; The model building unit is used to select a deep learning model or a support vector machine (SVM) technology to build a road surface prediction model, and divide the first data set and the second data set into a 70% training set and a 30% validation set to train and evaluate the road surface prediction model; The first calculation unit is used to extract the road marking deformation characteristics in the corresponding monitoring area according to the first data set, calculate and obtain the road marking deformation degree Bxd, and use the road marking deformation degree in the i-th monitoring area as the Take this as an example, and obtain it as follows: S11. First, the original marking shape area is obtained through CAD drawings or original construction data, and the actual shape data of the current marking is obtained using image processing technology and sensors to obtain the actual marking contour point set and the original marking contour point set: Assume that the actual line contour point set is , represents n discrete points extracted from the actual marking contour; Assume that the original line contour point set is , represents m discrete points extracted from the original design marking contour; S12, and calculate the maximum value of the minimum distances from all actual marking points to the original marking points : ; S13, and calculate the average value of the minimum distances from all actual marking points to the original marking points : ; In the formula, It means to sum the minimum value of the distance from each actual marking point p to all original marking points q. It means averaging the sum and calculating the average value of the minimum distance from each actual marking point to the original marking point; S14. The maximum value of the minimum distances from all actual marking points to the original marking points And the average value of the minimum distance from all actual marking points to the original marking points The deformation degree of the marking line in the i-th monitoring area is calculated by the following formula: : ; In the formula, and is the weight coefficient, and .

[0027] The prediction module also includes a second calculation unit and a first early warning unit; The second calculation unit is used to extract the road marking wear characteristics in the corresponding monitoring area based on the first data set, associate the road marking deformation Bxd in the corresponding monitoring area, calculate and obtain the road marking wear index Msz, and use the light marking wear index in the i-th monitoring area as the Take this as an example, and obtain it as follows: ; In the formula, It is expressed as the reduction of the marking thickness in the i-th monitoring area, It is expressed as the brightness attenuation value of the marking color in the i-th monitoring area, represents the deformation degree of the marking line in the i-th monitoring area, It is expressed as the number of broken segments of the marking line in the i-th monitoring area, and are weight coefficients, Expressed as the first correction constant.

[0028] The first warning unit is used to compare and analyze the wear threshold A with the road marking wear index Msz in the corresponding monitoring area, and preliminarily determine whether the road marking wear in the current monitoring area is in an abnormal state. The specific contents are as follows: If the marking wear index in the i-th monitoring area When the wear threshold A is exceeded, it indicates that the road marking wear in the current monitoring area is in an abnormal state, and a primary warning instruction is issued; If the marking wear index in the i-th monitoring area When the wear threshold value A is not exceeded, it indicates that the road marking wear in the current monitoring area is in a normal wear state.

[0029] In this embodiment, the prediction module includes a model building unit, a first calculation unit, a second calculation unit and a first warning unit. Through a deep learning model or SVM technology, a high-precision road surface prediction model is established using rich training data and verification data to accurately predict the wear of road markings. According to the first data set, the deformation characteristics of the road markings in the corresponding monitoring area are extracted, and the deformation degree of the markings Bxd is calculated. By accurately extracting and calculating the deformation characteristics of the road markings, combined with CAD drawings and image processing technology, the deformation degree of the markings Bxd is monitored in real time, providing important parameters for the calculation of the marking wear index Msz. The calculation of the marking wear index Msz combines multi-dimensional parameters such as the reduction in marking thickness, color brightness attenuation value, deformation degree and number of broken segments to comprehensively evaluate the wear of the road markings and ensure the comprehensiveness and accuracy of the evaluation results. Based on the comparative analysis of the wear threshold A and the marking wear index Msz, abnormal wear conditions are discovered and warned in a timely manner to ensure the timely repair of road markings and ensure traffic safety.

[0030] Example 4, please refer to Figure 1 , the prediction module also includes a road surface smoothness calculation unit; The road surface smoothness calculation unit is used to extract features based on the road surface smoothness information after receiving the primary warning instruction, so as to obtain the road surface roughness Ccd, road surface crack density lfmd, pothole density kwmd, and average change value of vehicle vertical acceleration Jsdb in the corresponding monitoring area, perform dimensionless processing, and calculate and obtain the road surface smoothness influence factor L in the corresponding monitoring area, and use the road surface smoothness influence factor L in the i-th monitoring area as the road surface smoothness influence factor L. Take this as an example, and obtain it as follows: ; ; In the formula, is the road surface height in the ith monitoring area, represents the average height of k sampling points, where k represents the number of sampling points; It is expressed as the road surface roughness in the i-th monitoring area, It is expressed as the pavement crack density in the i-th monitoring area, represents the pothole density in the i-th monitoring area, It is expressed as the average change value of the vertical acceleration of the traffic flow in the i-th monitoring area, and They are all weight coefficients, which are adjusted and set by the user, and the sum of the weight coefficients is 1. Expressed as the second correction constant.

[0031] In this embodiment, the uneven road surface will cause the vehicle to vibrate and bump violently during driving, thereby aggravating the wear of the road markings and shortening the service life of the markings. Problems such as road cracks and potholes will cause the markings to deform and break at these locations, affecting the overall effect and recognition of the markings. Frequent maintenance and redrawing of markings not only increase maintenance costs, but also have a certain impact on traffic operations. The road surface flatness calculation unit is used to extract features based on the road flatness information after receiving the primary warning instruction, so as to obtain the road surface roughness Ccd, road surface crack density lfmd, pothole density kwmd, and average change value of vehicle vertical acceleration Jsdb in the corresponding monitoring area, and perform dimensionless processing to calculate and obtain the road surface flatness influence factor L in the corresponding monitoring area. The road surface flatness influence factor L can monitor and evaluate the flatness of the road surface in real time, discover and repair problems in time, reduce the negative impact on road markings, and ensure the good operation of transportation infrastructure.

[0032] Example 5, please refer to Figure 1The prediction module also includes a thermal expansion and contraction influence calculation unit; the thermal expansion and contraction influence calculation unit is used to calculate the thermal expansion and contraction influence factor Rs of the corresponding monitoring area after dimensionless processing based on the rainfall Jyl, ice thickness Bchd and road surface temperature PT, and to obtain the thermal expansion and contraction influence factor Rs of the corresponding monitoring area. Take this as an example, and obtain it as follows: ; In the formula, It is expressed as the rainfall in the i-th monitoring area, It is represented by the ice thickness of the road surface in the i-th monitoring area, PT is the road surface temperature in the i-th monitoring area, Indicates the maximum temperature that the road surface can withstand. and They are all weight coefficients, which are adjusted and set by the user, and the sum of the weight coefficients is 1. Expressed as the third correction constant.

[0033] In this embodiment, temperature changes will cause thermal expansion and contraction of the marking material, which may cause deformation, cracks or falling of the marking, affecting the function and visibility of the marking. Ice and high temperature will affect the adhesion of the marking, making it easier for the marking to fall off during driving, increasing the difficulty of maintaining the road marking. Calculating the thermal expansion and contraction factor Rs can comprehensively evaluate the combined impact of temperature changes, rainfall and ice on road markings, and help understand the actual impact of these factors on the marking materials and functions. Based on the calculation results of the thermal expansion and contraction factor, a maintenance plan can be formulated more accurately, and the markings can be repaired or repainted in time to reduce the failure of the markings caused by temperature changes. Determining the thermal expansion and contraction factor Rs can adjust the maintenance and repair plan, taking into account the impact of seasonal changes and extreme weather conditions on the markings, and ensuring that the road markings are always in good condition.

[0034] Example 6, please refer to Figure 1 , the prediction module also includes a vehicle flow behavior impact calculation unit and associated units; The vehicle flow behavior impact calculation unit is used to calculate and obtain the vehicle flow behavior impact factor Xw based on the traffic density Jtmd, the lane change frequency Bdpc, the heavy vehicle flow Zxcl and the lane emergency braking frequency Jspc after dimensionless processing; the vehicle flow behavior impact factor Xw in the i-th monitoring area Take this as an example, and obtain it as follows: ; In the formula, It is expressed as the traffic density in the i-th monitoring area, It is represented as the frequency of lane changes in the i-th monitoring area, represents the heavy vehicle flow in the i-th monitoring area, represents the frequency of emergency braking in the lane within the i-th monitoring area, and They are all weight coefficients, which are adjusted and set by the user, and the sum of the weight coefficients is 1. Expressed as the fourth correction constant; High traffic density and frequent lane changes accelerate the wear of road markings, especially in areas with heavy traffic and frequent lane changes, where the markings will be compressed and worn faster. Heavy traffic may cause greater physical pressure on the markings, affecting the clarity and visibility of the markings. Frequent sudden braking will cause additional friction and pressure on the markings, further affecting the effectiveness of the markings. Frequent sudden braking and high lane change frequency will cause local deformation or detachment of the markings, affecting their guiding function. By calculating the traffic behavior impact factor Xw, it is possible to more accurately determine traffic-dense areas and high-risk areas, thereby optimizing the marking maintenance and repair strategy. Identifying high-impact areas helps to reasonably allocate maintenance resources and priorities, reducing unnecessary maintenance costs and time waste.

[0035] The association unit is used to associate the road surface flatness influence factor L, the thermal expansion and contraction influence factor Rs, the traffic behavior influence factor Xw and the road marking wear index Msz of the corresponding monitoring area, and calculate the repair index Xfzs of the corresponding monitoring area. i Take this as an example, and obtain it as follows: ; In the formula, They are all weight coefficients, e is the base of natural numbers, and its value is 2.71828.

[0036] In this embodiment, the repair index Xfzs takes multiple influencing factors into consideration and can provide a comprehensive assessment of the road marking repair needs. This comprehensive calculation can more accurately reflect the actual repair needs of each monitored area. By calculating the repair index Xfzs, those areas that need priority repair can be identified. An area with a high repair index Xfzs means that the markings in this area are more severely worn and are affected by more factors, so priority treatment is required. In a large range of road marking maintenance work, the repair index Xfzs helps to optimize the allocation and scheduling of resources, ensuring that limited maintenance resources are used most effectively, thereby reducing overall maintenance costs.

[0037] Example 7, please refer to Figure 1 , the management module includes a first level assessment unit and a second repair unit; The first level evaluation unit compares the restoration index Xfzs in the corresponding monitoring area with the first restoration threshold Q 1 and the second repair threshold Q 2Comparative analysis is performed to determine the corresponding level of road marking wear in the current monitoring area. The specific contents are as follows: If the repair index Xfzs < the first repair threshold Q 1 , generating the first level assessment result; indicating that the road marking wear is low and the damaged area needs to be repaired; If the first repair threshold Q 1 ≤Repair index Xfzs≤Second repair threshold Q 2 , generating the second level assessment result; indicating that the road marking wear is moderate and the damaged area needs to be repainted on the original basis; If the repair index Xfzs> the second repair threshold Q 2 , generating the third level assessment result. It means that the road marking wear is serious, which may cause the lane separation effect to fail, increase the risk of lane confusion and traffic congestion, especially at night or in low visibility conditions, it is difficult to identify, and the damaged area needs to be repainted; The second repair unit is used to generate a corresponding repair strategy according to the first level evaluation result, the second level evaluation result and the third level evaluation result, including: The first level assessment results generate the first repair strategy, including: dispatching a maintenance team to clean and dry the road surface within 36 hours, clean the damaged area of ​​the marking, remove the loose part of the marking, and repair the damaged area to make the connection between the repaired part and the original marking smooth and avoid unevenness. Then, use cold spray paint to add a layer of paint on the original surface and spray a layer of anti-skid granule protective layer; The second level assessment results generate the second repair strategy, including: dispatching maintenance teams to clean and dry the road surface, fill potholes and uneven areas, and repaint the road markings in the corresponding monitoring area within 48 hours using thermal spray paint; using thermal spray paint to add one layer of paint on the original surface and spray two layers of anti-skid granule protective layer; The third level assessment results generate the third repair strategy, including: immediately start the emergency maintenance procedure, dispatch an emergency maintenance team to use heating equipment to melt and remove the old markings within 24 hours, remove the old markings, including grinding or high-pressure water washing; and re-draw new markings, including at least 1 layer of primer, 1 layer of hot-melt mid-coat, 1 layer of reflective ceramic particle surface layer and 1 layer of anti-skid particle protection layer. Add a layer of reflective ceramic particle surface layer to improve the visibility of the markings, especially at night or in low light conditions. Anti-skid particle protection layer: Finally, spray a layer of anti-skid particle protection layer to enhance the anti-skid performance of the markings and ensure safe driving.

[0038] In this embodiment, through graded assessment and targeted repair strategies, it is ensured that different levels of road marking wear problems are properly handled and accurately meet road maintenance needs. Different levels of repair strategies can extend the service life of road markings, reduce frequent maintenance and replacement, and thus reduce maintenance costs. Through detailed repair strategies and graded assessments, the transparency and traceability of road maintenance work are improved, making it easier for relevant departments and the public to understand the maintenance situation. Emergency repair strategies can quickly respond to serious road marking damage problems, ensure the restoration and use of road markings, and reduce the impact on traffic.

[0039] The threshold is set to facilitate comparison. The size of the threshold depends on the amount of sample data and the number of bases set by technicians in this field for each group of sample data; as long as it does not affect the proportional relationship between the parameter and the quantized value.

[0040] The above formulas are obtained by collecting a large amount of data for software simulation and selecting a formula that is close to the actual value. The coefficients in the formula are set by technical personnel in this field according to actual conditions. The above is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited to this. Any technical personnel familiar with the technical field within the technical scope disclosed by the present invention, according to the technical solution and the inventive concept of the present invention, make equivalent replacement or change, which should be covered within the protection scope of the present invention.

Claims

1. An optical fiber-based traffic and infrastructure monitoring system, characterized in that: include, The traffic intersection acquisition module is used to pre-select the monitoring traffic street range according to the traffic facility management requirements, collect the intersection latitude and longitude coordinates and structural information, and divide each intersection into independent monitoring areas; A real-time monitoring module, used to monitor the wear information of the road markings and establish a first data set; And monitor the road leveling information, weather impact information and traffic behavior information in the corresponding monitoring area to establish a second data set; A processing module, used for performing data preprocessing on the first data set and the second data set, wherein the preprocessing includes data cleaning, data synchronization and dimensionless data processing, and then transmitting and storing the data to a facility management data set; A prediction module is used to extract the road marking wear characteristics in the corresponding monitoring area based on the first data set by using the trained road surface prediction model, and construct a road marking wear index Msz. When the road marking wear index Msz exceeds the wear threshold A, a preliminary warning instruction is issued externally; and the road flatness information, weather impact information and vehicle flow behavior information are feature extracted to respectively obtain the road surface roughness Ccd, road surface crack density lfmd, pothole density kwmd, average change value of vehicle vertical acceleration Jsdb, rainfall Jyl, ice thickness Bchd, road surface temperature PT, traffic density Jtmd, lane change frequency Bdpc, heavy vehicle flow Zxcl and lane emergency braking frequency Jspc in the corresponding monitoring area, and calculate and obtain the road surface flatness influence factor L, thermal expansion and contraction influence factor Rs and vehicle flow behavior influence factor Xw; the road marking wear index Msz, road surface flatness influence factor L, thermal expansion and contraction influence factor Rs and vehicle flow behavior influence factor Xw in the corresponding monitoring area are associated, and the repair index Xfzs of the corresponding monitoring area is calculated; A management module is used to pre-set a first repair threshold Q 1 and the second repair threshold Q 2 and the restoration index Xfzs in the corresponding monitoring area is compared with the first restoration threshold Q 1 and the second repair threshold Q 2 Conduct comparative analysis and adopt management measures within the corresponding monitoring area based on the results of the comparative analysis.

2. The optical fiber-based traffic and infrastructure monitoring system according to claim 1, characterized in that: The traffic intersection acquisition module includes a region segmentation unit and a deployment unit; The area segmentation unit is used for traffic facility management needs, determining the intersections and street ranges of traffic infrastructure that need to be monitored; and dividing the streets around each traffic intersection into monitoring areas, setting the streets within a radius of 50 meters with the intersection as the center as the monitoring area; The deployment unit is used to deploy monitoring points in each monitoring area, specifically including: setting distributed optical fiber sensors along the markings and road surfaces to monitor changes in marking temperature and road surface height; Rainfall sensors are deployed in the monitoring area, and the optical fiber network transmits rainfall data; Temperature sensors and optical fiber ice detection sensors are laid on the road surface to monitor the thickness of the ice layer; Temperature sensors are laid on the road surface to transmit temperature data via optical fiber; Pressure sensors and traffic flow sensors are laid on the road surface, and optical fibers transmit traffic density data; Distributed fiber optic sensors are deployed along the lane lines to detect vehicle lane-changing behavior; Deploy weight sensors on the road surface to transmit heavy vehicle data via optical fiber; Acceleration sensors are placed on the road surface and emergency braking frequency data is transmitted via a fiber optic network.

3. The optical fiber-based traffic and infrastructure monitoring system according to claim 1, characterized in that: The prediction module includes a model building unit and a first calculation unit; The model building unit is used to select a deep learning model or a support vector machine (SVM) technology to build a road surface prediction model, and divide the first data set and the second data set into a 70% training set and a 30% validation set to train and evaluate the road surface prediction model; The first calculation unit is used to extract the road marking deformation characteristics in the corresponding monitoring area according to the first data set, calculate and obtain the road marking deformation degree Bxd, and use the road marking deformation degree in the i-th monitoring area as the For example, the specific method is as follows: S11. First, the original marking shape area is obtained through CAD drawings or original construction data, and the actual shape data of the current marking is obtained using image processing technology and sensors to obtain the actual marking contour point set and the original marking contour point set: Assume that the actual line contour point set is , represents n discrete points extracted from the actual marking contour; Assume that the original line contour point set is , represents m discrete points extracted from the original design marking contour; S12, and calculate the maximum value of the minimum distances from all actual marking points to the original marking points : ； S13, and calculate the average value of the minimum distances from all actual marking points to the original marking points : ； In the formula, It means to sum the minimum value of the distance from each actual marking point p to all original marking points q. It means averaging the sum and calculating the average value of the minimum distance from each actual marking point to the original marking point; S14. The maximum value of the minimum distances from all actual marking points to the original marking points And the average value of the minimum distance from all actual marking points to the original marking points The deformation degree of the marking line in the i-th monitoring area is calculated by the following formula: : ； In the formula, and is the weight coefficient, and .

4. The optical fiber-based traffic and infrastructure monitoring system according to claim 3, characterized in that: The prediction module also includes a second calculation unit and a first early warning unit; The second calculation unit is used to extract the road marking wear characteristics in the corresponding monitoring area based on the first data set, associate the road marking deformation Bxd in the corresponding monitoring area, calculate and obtain the road marking wear index Msz, and use the light marking wear index in the i-th monitoring area as the Take this as an example, and obtain it as follows: ； In the formula, It is expressed as the reduction in the thickness of the marking line in the i-th monitoring area, It is expressed as the brightness attenuation value of the marking color in the i-th monitoring area, represents the deformation degree of the marking line in the i-th monitoring area, It is expressed as the number of broken segments of the marking line in the i-th monitoring area, and are weight coefficients, Expressed as the first correction constant.

5. The optical fiber-based traffic and infrastructure monitoring system according to claim 4, characterized in that: The first warning unit is used to compare and analyze the wear threshold A with the road marking wear index Msz in the corresponding monitoring area, and preliminarily determine whether the road marking wear in the current monitoring area is in an abnormal state. The specific contents are as follows: If the marking wear index in the i-th monitoring area When the wear threshold A is exceeded, it indicates that the road marking wear in the current monitoring area is in an abnormal state, and a primary warning instruction is issued; If the marking wear index in the i-th monitoring area When the wear threshold value A is not exceeded, it indicates that the road marking wear in the current monitoring area is in a normal wear state.

6. The optical fiber-based traffic and infrastructure monitoring system according to claim 5, characterized in that: The prediction module also includes a road surface smoothness calculation unit; The road surface smoothness calculation unit is used to extract features based on the road surface smoothness information after receiving the primary warning instruction, so as to obtain the road surface roughness Ccd, road surface crack density lfmd, pothole density kwmd, and average change value of vehicle vertical acceleration Jsdb in the corresponding monitoring area, perform dimensionless processing, and calculate and obtain the road surface smoothness influence factor L in the corresponding monitoring area, and use the road surface smoothness influence factor L in the i-th monitoring area as the road surface smoothness influence factor L. For example, the specific method is as follows: ； ； In the formula, is the road surface height in the ith monitoring area, represents the average height of k sampling points, where k represents the number of sampling points; It is expressed as the road surface roughness in the i-th monitoring area, It is expressed as the pavement crack density in the i-th monitoring area, represents the pothole density in the ith monitoring area, It is expressed as the average change value of the vertical acceleration of the traffic flow in the i-th monitoring area, and are weight coefficients, Expressed as the second correction constant.

7. The optical fiber-based traffic and infrastructure monitoring system according to claim 6, characterized in that: The prediction module also includes a thermal expansion and contraction influence calculation unit; the thermal expansion and contraction influence calculation unit is used to calculate the thermal expansion and contraction influence factor Rs of the corresponding monitoring area after dimensionless processing based on the rainfall Jyl, ice thickness Bchd and road surface temperature PT, and to obtain the thermal expansion and contraction influence factor Rs of the corresponding monitoring area. Take this as an example, and obtain it as follows: ； In the formula, It is expressed as the rainfall in the ith monitoring area, It is represented by the ice thickness of the road surface in the i-th monitoring area, PT is the road surface temperature in the i-th monitoring area, Indicates the maximum temperature that the road surface can withstand. and are weight coefficients, Expressed as the third correction constant.

8. The optical fiber-based traffic and infrastructure monitoring system according to claim 7, characterized in that: The prediction module also includes a vehicle flow behavior impact calculation unit and an associated unit; The vehicle flow behavior impact calculation unit is used to calculate and obtain the vehicle flow behavior impact factor Xw after dimensionless processing based on the traffic density Jtmd, the lane change frequency Bdpc, the heavy vehicle flow Zxcl and the lane emergency braking frequency Jspc; The influencing factors of vehicle flow behavior in the i-th monitoring area are Take this as an example, and obtain it as follows: ； In the formula, It is expressed as the traffic density in the i-th monitoring area, It is represented as the frequency of lane changes in the i-th monitoring area, represents the heavy vehicle flow in the i-th monitoring area, represents the frequency of emergency braking in the lane within the i-th monitoring area, and are weight coefficients, Expressed as the fourth correction constant; The association unit is used to associate the road surface flatness influence factor L, the thermal expansion and contraction influence factor Rs, the traffic behavior influence factor Xw and the road marking wear index Msz of the corresponding monitoring area, and calculate the repair index Xfzs of the corresponding monitoring area. i Take this as an example, and obtain it as follows: ； In the formula, They are all weight coefficients, e is the base of natural numbers, and its value is 2.71828.

9. The optical fiber-based traffic and infrastructure monitoring system according to claim 8, characterized in that: The management module includes a first level assessment unit and a second repair unit; The first level evaluation unit compares the restoration index Xfzs in the corresponding monitoring area with the first restoration threshold Q 1 and the second repair threshold Q 2 Comparative analysis is performed to determine the corresponding level of road marking wear in the current monitoring area. The specific contents are as follows: If the repair index Xfzs < the first repair threshold Q 1 , generate the first level evaluation results; If the first repair threshold Q 1 ≤Repair index Xfzs≤Second repair threshold Q 2 , generate the second level evaluation results; If the repair index Xfzs> the second repair threshold Q 2 , generate the third level evaluation results.

10. The optical fiber-based traffic and infrastructure monitoring system according to claim 9, characterized in that: The second repair unit is used to generate a corresponding repair strategy according to the first level evaluation result, the second level evaluation result and the third level evaluation result, including: The first level assessment results generate the first repair strategy, including: dispatching a maintenance team to clean and dry the road surface within 36 hours, clean the damaged area of ​​the marking, remove the loose part of the marking, and repair the damaged area to make the connection between the repaired part and the original marking smooth and avoid unevenness. Then, use cold spray paint to add a layer of paint on the original surface and spray a layer of anti-skid granule protective layer; The second level assessment results generate the second repair strategy, including: dispatching maintenance teams to clean and dry the road surface, fill potholes and uneven areas, and repaint the road markings in the corresponding monitoring area within 48 hours using thermal spray paint; using thermal spray paint to add one layer of paint on the original surface and spray two layers of anti-skid granule protective layer; The third-level assessment results generate the third repair strategy, including: immediately starting the emergency maintenance procedure, dispatching an emergency maintenance team to use heating equipment to melt and remove the old markings within 24 hours, and then removing the old markings, including grinding or high-pressure water washing; and redrawing new markings, including at least 1 layer of primer, 1 layer of hot-melt mid-coat, 1 layer of reflective ceramic particle surface layer and 1 layer of anti-skid particle protective layer.

Images