Road surface traffic condition monitoring method and equipment based on intelligent guardrail, and medium

Abstract

The embodiment of the invention discloses a road surface traffic condition monitoring method and equipment based on an intelligent guardrail and a medium, belongs to the technical field of intelligent traffic, and solves the problem that a guardrail on a current road is difficult to quickly deal with when encountering severe weather. Comprising the steps that meteorological data and road image data corresponding to a to-be-measured road surface are acquired based on a plurality of data acquisition devices on guardrails on the two sides of the to-be-measured road surface, and the meteorological data and the road image data are uploaded to a traffic management center; carrying out hidden danger element data extraction on the meteorological data through a preset combined data extraction model; determining a road surface traffic condition risk prediction value based on the road image data and the hidden danger element data corresponding to different target road sections; performing target area identification on the road image data through an edge detection algorithm, and determining an actual risk value of the road surface based on a target area; and based on the road surface traffic condition risk prediction value and the road surface actual risk value, controlling the change of the guardrails on the two sides so as to carry out road traffic adjustment.

Description

Technical Field

[0001] The present application relates to the field of intelligent transportation technology, and in particular to a method, device and medium for monitoring road traffic conditions based on intelligent guardrails. Background Art

[0002] With the acceleration of urbanization and the continuous increase in traffic volume, road traffic safety issues have become increasingly prominent. In order to effectively monitor and warn road traffic conditions and improve road traffic efficiency and safety, modern traffic management systems are gradually developing in the direction of intelligence and refinement.

[0003] In bad weather conditions, such as rain and snow, severe cold and freezing, roads often face severe challenges such as ice and water accumulation. In the existing technology, although surveillance cameras have been installed to monitor road traffic conditions, this method only stays at the level of surface observation and is highly dependent on manual real-time monitoring of surveillance images, which increases labor costs and is prone to omissions and delays in actual operations.

[0004] Guardrails are the most basic traffic protection facilities on highways and urban roads, and play a very important role in traffic protection. At present, the design of guardrails on roads is mostly still at the traditional level, which only blocks vehicles from colliding with each other. Its intelligence level is low, and it is difficult to respond quickly in bad weather conditions, thus it is difficult to reduce the incidence of traffic accidents. Summary of the invention

[0005] The embodiments of the present application provide a road traffic condition monitoring method, device and medium based on intelligent guardrails, which are used to solve the following technical problems: the current guardrail design on the road only blocks vehicle collisions and the like, and its intelligence level is low. When encountering severe weather conditions, it is difficult to respond quickly, thereby making it difficult to reduce the incidence of traffic accidents.

[0006] The present application embodiment adopts the following technical solutions:

[0007] The embodiment of the present application provides a method for monitoring road traffic conditions based on intelligent guardrails. The method comprises: obtaining meteorological data and road image data corresponding to the road to be tested based on multiple data acquisition devices on the guardrails on both sides of the road to be tested, and uploading the meteorological data and road image data to the traffic management center; wherein the multiple data acquisition devices are respectively arranged on different target sections of the road to be tested; at the traffic management center, extracting hidden danger element data from meteorological data through a preset combined data extraction model; determining the road traffic condition risk prediction value corresponding to the road to be tested based on the road image data and hidden danger element data corresponding to different target sections; identifying the target area of ​​the road image data through an edge detection algorithm to determine the actual risk value of the road based on the target area; performing graded warning on the road traffic condition based on the road traffic condition risk prediction value and the actual risk value of the road, and controlling the change of the guardrails on both sides based on the graded warning to adjust the road traffic.

[0008] The embodiment of the present application realizes the automatic collection of road meteorological data and image data by installing multiple data acquisition devices on the guardrail, reducing the reliance on manual monitoring and improving the efficiency and accuracy of data acquisition. The traffic management center uses the preset combined data extraction model and edge detection algorithm to automatically analyze the data and predict the risk of road traffic conditions, thus realizing intelligent traffic management. Secondly, the data acquisition devices are respectively set in different target sections, which can obtain more detailed and comprehensive road information, making risk prediction more accurate. Through the graded warning mechanism, corresponding warning measures can be taken according to different risk levels, and drivers and traffic managers can be reminded to pay attention to road conditions in time to reduce the risk of traffic accidents. According to the warning results, the guardrail changes are controlled and road traffic adjustments are made, such as adjusting the lane width, limiting the speed, etc., which further improves the safety and efficiency of road traffic.

[0009] In one implementation of the present application, before extracting hidden danger element data from meteorological data through a preset combined data extraction model, the method also includes: taking historical meteorological data samples as a training set, inputting the preset deep learning model to train the preset deep learning model; based on a preset feature interaction table, determining the interactive influence relationship between different initial element data output by the preset deep learning model; wherein the preset feature interaction table includes multiple different initial element data, and also includes the interactive influence relationship between multiple initial element data; based on the interactive influence relationship, weighted averaging the different initial element data to generate a fused training set; inputting the fused training set into a preset gradient boosting tree model to train the preset gradient boosting tree model; and obtaining a preset combined data extraction model based on the trained preset deep learning model and the trained preset gradient boosting tree model.

[0010] In one implementation of the present application, based on the interactive influence relationship, different initial element data are weighted averaged to generate a fusion training set, which specifically includes:

[0011] Interaction functions based on preset data:

[0012]

[0013] Perform weighted averaging on different initial factor data to generate a fusion training set;

[0014] Among them, X fused is the fused data; w ij represents the interaction weight between the i-th initial feature data and the j-th initial feature data, x i represents the characteristic value of the i-th initial element data; x j Represents the eigenvalue of the jth initial feature data.

[0015] In one implementation of the present application, based on the road image data and hidden danger element data corresponding to different target road sections, the road traffic condition risk prediction value corresponding to the road surface to be tested is determined, specifically including: based on the road image data, determining the road condition types corresponding to different target road sections; wherein the road condition types include road icing and road waterlogging; when the road condition type is road icing, the hidden danger air pressure data and hidden danger temperature data of the road are determined through the hidden danger element data, and the road freezing and melting time and the road freezing and melting speed are generated based on the hidden danger air pressure data and the hidden danger temperature data, so as to generate road warning information based on the road freezing and melting time and the road freezing and melting speed; when the road condition type is road waterlogging, the hidden danger precipitation, hidden danger humidity and hidden danger temperature of the road are determined through the hidden danger element data, and the water dissipation time and water dissipation speed are determined based on the hidden danger precipitation, hidden danger humidity, hidden danger temperature and the drainage system data corresponding to the road surface to be tested, so as to generate road warning information based on the water dissipation time and water dissipation speed; based on the road warning information corresponding to different target road sections, the road traffic condition risk prediction value corresponding to the road surface to be tested is determined.

[0016] In one implementation of the present application, based on the road warning information corresponding to different target sections, the road traffic condition risk prediction value corresponding to the road surface to be tested is determined, specifically including: based on the installation position of the guardrail, determining the position information corresponding to the different target sections; based on the position information, determining the historical traffic accident data corresponding to each target section in the historical traffic database, and assigning a first weight to each target section based on the historical traffic accident data; based on the position information, determining the road structure data corresponding to each target section in the traffic network map corresponding to the road surface to be tested, and assigning a second weight to each target section based on the road structure data; the first weight assignment, the second weight assignment and the road warning information corresponding to the different target sections are weighted to obtain the road traffic condition risk prediction value corresponding to the road surface to be tested.

[0017] In one implementation of the present application, target area identification is performed on road image data through an edge detection algorithm to determine the actual risk value of the road surface based on the target area, specifically including: target area detection is performed on road image data; wherein the target area includes at least an ice area and a water accumulation area; based on the edge detection algorithm, the boundary between the target area and the road surface is determined to determine the area information of the target area based on the boundary; according to the difference in image grayscale values ​​between the target area and the road surface image, the water level is determined to obtain the depth of water accumulation based on the water level; based on the area information and the depth of water accumulation, a reference risk value corresponding to the road surface is obtained; and based on a preset time length and the corresponding number of vehicles passing within the preset time length, a road vehicle traffic rate is obtained; based on the road vehicle flow traffic rate, the reference risk value is adjusted to obtain the actual risk value of the road surface.

[0018] In one implementation of the present application, a graded warning is given for the road traffic condition based on the road traffic condition risk prediction value and the road actual risk value, and the guardrail changes on both sides of the road are controlled based on the graded warning to adjust the road traffic, specifically including: obtaining the risk value for the road to be tested in the future time period based on the road traffic condition risk prediction value and the road actual risk value; determining the risk thresholds corresponding to different preset risk levels, dividing the risk values ​​in the future time period based on the risk thresholds to obtain multiple risk time periods; matching the corresponding guardrail adjustment strategies based on different risk levels, and associating the guardrail adjustment strategies with multiple risk time periods; and controlling the guardrail changes on both sides of the road in the corresponding risk time periods based on the association relationship to adjust the road traffic.

[0019] In one implementation of the present application, based on the road traffic condition risk prediction value and the road actual risk value, the risk value of the road to be tested in the future time period is obtained, specifically including: inputting the road traffic condition risk prediction value and the road actual risk value into a time series prediction model to obtain a reference risk value corresponding to the road to be tested; constructing a risk value change line graph based on the reference risk value, so as to determine the risk value of the road to be tested in the future time period based on the risk value change line graph.

[0020] The embodiment of the present application provides a road traffic condition monitoring device based on intelligent guardrails, comprising: at least one processor; and a memory connected to the at least one processor in communication; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can: based on multiple data acquisition devices on the guardrails on both sides of the road to be tested, obtain meteorological data and road image data corresponding to the road to be tested, and upload the meteorological data and road image data to a traffic management center; wherein the multiple data acquisition devices are respectively arranged at different target sections of the road to be tested; at the traffic management center, extract hidden danger element data from the meteorological data through a preset combined data extraction model; based on the road image data and hidden danger element data corresponding to different target sections, determine the road traffic condition risk prediction value corresponding to the road to be tested; identify the target area of ​​the road image data through an edge detection algorithm to determine the actual risk value of the road based on the target area; based on the road traffic condition risk prediction value and the actual risk value of the road, perform graded warning on the road traffic condition, and control the change of the guardrails on both sides based on the graded warning to adjust the road traffic.

[0021] A non-volatile computer storage medium provided in an embodiment of the present application stores computer executable instructions, wherein the computer executable instructions are configured to: based on multiple data acquisition devices on guardrails on both sides of a road surface to be tested, obtain meteorological data and road image data corresponding to the road surface to be tested, and upload the meteorological data and road image data to a traffic management center; wherein the multiple data acquisition devices are respectively arranged at different target sections of the road surface to be tested; at the traffic management center, extract hidden danger element data from the meteorological data through a preset combined data extraction model; determine a road surface traffic condition risk prediction value corresponding to the road surface to be tested based on the road image data and hidden danger element data corresponding to different target sections; identify a target area of ​​the road image data through an edge detection algorithm to determine an actual road surface risk value based on the target area; perform graded warnings on the road surface traffic condition based on the road surface traffic condition risk prediction value and the actual road surface risk value, and control the changes of guardrails on both sides based on the graded warnings to adjust the road traffic.

[0022] At least one of the above technical solutions adopted in the embodiments of the present application can achieve the following beneficial effects: The embodiments of the present application realize automatic collection of road meteorological data and image data by installing multiple data acquisition devices on the guardrail, reduce the reliance on manual monitoring, and improve the efficiency and accuracy of data acquisition. The traffic management center can automatically analyze data and predict the risk of road traffic conditions by using the preset combined data extraction model and edge detection algorithm, realizing intelligent traffic management. Secondly, the data acquisition devices are respectively set in different target sections, which can obtain more detailed and comprehensive road information, making risk prediction more accurate. Through the graded warning mechanism, corresponding warning measures can be taken according to different risk levels, timely reminding drivers and traffic managers to pay attention to road conditions and reduce the risk of traffic accidents. According to the warning results, the guardrail changes are controlled, and road traffic adjustments are made, such as adjusting the lane width, limiting the speed, etc., which further improves the safety and efficiency of road traffic. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. In the drawings:

[0024] Figure 1 A flow chart of a method for monitoring road traffic conditions based on intelligent guardrails provided in an embodiment of the present application;

[0025] Figure 2 A schematic diagram of the structure of a road traffic condition monitoring device based on a smart guardrail provided in an embodiment of the present application.

[0026] Reference numerals:

[0027] 200: road traffic condition monitoring equipment based on intelligent guardrail, 201: processor, 202: memory. DETAILED DESCRIPTION

[0028] The embodiments of the present application provide a method, device and medium for monitoring road traffic conditions based on smart guardrails.

[0029] In order to enable those skilled in the art to better understand the technical solutions in this application, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are only part of the embodiments of this application, not all of them. Based on the embodiments of this specification, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this application.

[0030] The technical solution proposed in the embodiment of the present invention is described in detail below with reference to the accompanying drawings.

[0031] Smart guardrails use precise sensing technology and Internet of Things technology to perceive the tilt, displacement, vibration and other parameters of traffic guardrails in real time, and transmit the data to the traffic management center in real time through the NB-IOT network, thereby realizing real-time intelligent monitoring of guardrails and automatic warning of abnormal conditions. The traffic management center supports one-stop alarm, alarm reception, and operation and maintenance management. It can automatically decide on the fault handling process, automatically dispatch orders and workers, and automatically confirm maintenance. It can establish and improve an integrated, standardized, and automated rapid response mechanism, thereby realizing real-time and reliable intelligent monitoring of guardrails, predicting dangers in advance, preventing secondary traffic accidents caused by guardrail abnormalities, reducing safety accidents, and improving operational management capabilities.

[0032] The parameters of the smart guardrail in the embodiment of the present application are:

[0033] Wireless communication: Using NB-IoT / 4G Internet of Things technology, built-in SIM card.

[0034] Tilt monitoring: uses a low-power six-axis acceleration sensor, tilts 0-180 degrees to alarm, supports remote setting of thresholds, and has a built-in anti-shake processing algorithm.

[0035] Vibration monitoring: Adopt high-precision vibration sensor, support remote acceleration setting, and real-time vibration monitoring.

[0036] Displacement monitoring: Using GPS+Beidou positioning, with high positioning accuracy.

[0037] Standby current: Adopting micro-power consumption technology and ARM architecture processor, the sleep current is small.

[0038] Power supply mode: solar power supply.

[0039] Data upload frequency: Quick response, when the fence is detected to be tilted, vibrated, or displaced, data will be uploaded within 15 seconds.

[0040] Working temperature: -40~85℃.

[0041] Waterproof grade: IP68.

[0042] The open protocol connects to third-party platforms for easy integration and unified management.

[0043] Figure 1 A flow chart of a road traffic condition monitoring method based on intelligent guardrails provided in an embodiment of the present application is as follows: Figure 1 As shown, the road traffic condition monitoring method based on the intelligent guardrail includes the following steps:

[0044] S101, based on multiple data acquisition devices on the guardrails on both sides of the road to be tested, obtain meteorological data and road image data corresponding to the road to be tested, and upload the meteorological data and road image data to the traffic management center.

[0045] In one embodiment of the present application, multiple data acquisition devices are installed on the guardrails on both sides of the road to be tested. The multiple data acquisition devices are respectively set at different target sections of the road to be tested. These devices include meteorological sensors, such as temperature sensors, humidity sensors, anemometers, etc., and image acquisition devices, such as high-definition cameras, and ensure that they can cover different areas of the road.

[0046] Furthermore, meteorological sensors are responsible for real-time monitoring and recording of meteorological data on and around the road surface, such as temperature, humidity, wind speed, wind direction, precipitation, etc., while image acquisition equipment is responsible for capturing road image data, including vehicle flow, pedestrian activity, and road conditions (such as water accumulation, ice, cracks, etc.). The collected meteorological data and road image data are uploaded to the traffic management center in real time through wired or wireless methods, such as 4G / 5G networks, Wi-Fi, dedicated communication networks, etc.

[0047] S102. At the traffic management center, hidden danger element data is extracted from the meteorological data using a preset combined data extraction model.

[0048] In one embodiment of the present application, historical meteorological data samples are used as training sets and input into a preset deep learning model to train the preset deep learning model. Based on a preset feature interaction table, the interactive influence relationship between different initial element data output by the preset deep learning model is determined; wherein the preset feature interaction table includes multiple different initial element data, and also includes the interactive influence relationship between multiple initial element data. Based on the interactive influence relationship, the different initial element data are weighted averaged to generate a fused training set. The fused training set is input into a preset gradient boosting tree model to train the preset gradient boosting tree model. Based on the trained preset deep learning model and the trained preset gradient boosting tree model, a preset combined data extraction model is obtained.

[0049] Specifically, historical meteorological data samples are collected and sorted, and these data samples include data of meteorological elements such as temperature, humidity, wind speed, and precipitation. These historical meteorological data samples are input into a preset deep learning model as a training set to train the preset deep learning model. Among them, the deep learning model in the embodiment of the present application can be a convolutional neural network.

[0050] Furthermore, the interactive influence relationship between different initial element data output by the deep learning model is determined by a preset feature interaction table. The feature interaction table in the embodiment of the present application is a priori knowledge base, which lists multiple initial element data (such as temperature, humidity, etc.) and the interactive influence relationship between them (such as increased temperature may lead to decreased humidity). Based on the determined interactive influence relationship, the different initial element data are weighted averaged. Through weighted averaging, a fusion training set is generated, which contains the initial element data adjusted by the interactive influence relationship.

[0051] Furthermore, the generated fusion training set is input into the preset gradient boosting tree model. It should be noted that the gradient boosting tree is a powerful ensemble learning method that improves prediction performance by building multiple weak learners and combining their results. Through training, the gradient boosting tree model learns the relationships and patterns between the data in the fusion training set. The trained deep learning model and the trained gradient boosting tree model are combined to construct a preset combined data extraction model. The preset combined data extraction model can take advantage of the advantages of the deep learning model in capturing complex relationships and the ability of the gradient boosting tree model in handling nonlinear relationships and feature interactions. By combining these two models, more accurate and comprehensive data extraction results can be obtained.

[0052] In one embodiment of the present application, based on the preset data interaction function:

[0053]

[0054] Perform weighted averaging on different initial factor data to generate a fusion training set;

[0055] Among them, X fused is the fused data; w ij represents the interaction weight between the i-th initial feature data and the j-th initial feature data, x i represents the characteristic value of the i-th initial element data; x j Represents the eigenvalue of the jth initial feature data.

[0056] S103: Based on the road image data and hidden danger element data corresponding to different target road sections, determine the road traffic condition risk prediction value corresponding to the road to be tested.

[0057] In one embodiment of the present application, based on the road image data, the road condition types corresponding to different target road sections are determined; wherein the road condition types include road icing and road waterlogging; when the road condition type is road icing, the road hidden danger pressure data and hidden danger temperature data are determined through the hidden danger element data, and the road freezing and melting time and road freezing and melting speed are generated based on the hidden danger pressure data and hidden danger temperature data, so as to generate road warning information based on the road freezing and melting time and road freezing and melting speed. When the road condition type is road waterlogging, the road hidden danger precipitation, hidden danger humidity and hidden danger temperature are determined through the hidden danger element data, and the water dissipation time and water dissipation speed are determined based on the hidden danger precipitation, hidden danger humidity, hidden danger temperature and the drainage system data corresponding to the road to be tested, so as to generate road warning information based on the water dissipation time and water dissipation speed. Based on the road warning information corresponding to different target road sections, the road traffic condition risk prediction value corresponding to the road to be tested is determined.

[0058] Specifically, the road image data is used to determine the road condition types corresponding to different target road sections through image recognition technology, wherein the road condition types in the embodiment of the present application mainly include road icing and road surface water. When the road condition type is road icing, the hidden danger air pressure data and hidden danger temperature data of the road are determined through hidden danger element data, such as air pressure and temperature in meteorological data, and the road freezing and melting time and road freezing and melting speed are obtained based on the hidden danger air pressure data and hidden danger temperature data using a preset calculation model. Among them, the training process of the preset calculation model is: taking the hidden danger element data sample as input, taking the road freezing and melting time and road freezing and melting speed sample data corresponding to the input sample as output, and training the preset neural network model to obtain the preset calculation model. These parameters reflect the melting rate and required time of the ice layer under specific meteorological conditions. According to the road freezing and melting time and road freezing and melting speed, the road warning information is generated. The warning information may include the degree of icing, and the expected recovery time.

[0059] Furthermore, when the road surface condition type is road waterlogging, the water dissipation time and water dissipation speed are obtained through the preset calculation model through the hidden danger factor data, such as precipitation, humidity, temperature, etc., and the drainage system data corresponding to the road surface to be tested. The training process of the preset calculation model is: taking the hidden danger factor data sample as input, and the water dissipation time and water dissipation speed sample data corresponding to the input sample as output, and training the preset neural network model to obtain the preset calculation model. Among them, the drainage system data may include information such as the capacity of the drainage pipe and the drainage efficiency. According to the water dissipation time and water dissipation speed, the road surface warning information is generated. The warning information may include the degree of waterlogging, and the expected recovery time, etc.

[0060] Furthermore, based on the road surface warning information corresponding to different target road sections, a road surface traffic condition risk prediction value corresponding to the road surface to be tested is determined.

[0061] In one embodiment of the present application, based on the installation position of the guardrail, the position information corresponding to different target sections is determined. Based on the position information, the historical traffic accident data corresponding to each target section is determined in the historical traffic database, and the first weight is assigned to each target section based on the historical traffic accident data. Based on the position information, the road structure data corresponding to each target section is determined in the traffic network map corresponding to the road surface to be tested, and the second weight is assigned to each target section based on the road structure data. The first weight assignment, the second weight assignment, and the road warning information corresponding to different target sections are weighted to obtain the road traffic condition risk prediction value corresponding to the road surface to be tested.

[0062] Specifically, guardrails are usually installed at key locations on the road, such as bridges, tunnels, sharp bends, steep slopes, etc. These locations are often more prone to traffic accidents. By measuring the installation location of the guardrail, the specific location information of different target sections in the traffic network map can be determined, such as the starting point, end point, length, direction, etc. Using the established historical traffic database, according to the location information of the target section, the traffic accident data that occurred in each section in the past period of time can be retrieved, including the type of accident, cause of the accident, number of casualties, vehicle damage, etc. According to the severity and frequency of historical traffic accident data, each target section is weighted. In the traffic network map of the road to be tested, according to the location information of the target section, the road structure data of each section can be obtained. These data include road grade, number of lanes, pavement material, design speed, traffic signs and markings, etc. According to the quality and complexity of the road structure data, each target section is weighted.

[0063] Furthermore, the first weight assignment, the second weight assignment and the road warning information corresponding to different target road sections are weighted, and the result of the weighted processing is the road traffic condition risk prediction value corresponding to the road to be tested, which reflects the traffic risks that each road section may face in the current and future period of time.

[0064] S104: identifying a target area of ​​the road image data by using an edge detection algorithm to determine an actual risk value of the road surface based on the target area.

[0065] In one embodiment of the present application, target area detection is performed on road image data; wherein the target area includes at least an ice area and a water accumulation area. Based on an edge detection algorithm, the boundary between the target area and the road surface is determined to determine the area information of the target area based on the boundary. According to the difference in image grayscale values ​​between the target area and the road surface image, a water level is determined to obtain the depth of water accumulation based on the water level. Based on the area information and the depth of water accumulation, a reference risk value corresponding to the road surface is obtained. And, based on a preset time length and the number of vehicles passing through the preset time length, a road vehicle traffic rate is obtained. The reference risk value is adjusted based on the road vehicle flow rate to obtain an actual road risk value.

[0066] Specifically, image processing technology is used to process road image data to identify and mark target areas. These target areas include at least ice areas and water areas. Edge detection algorithms (such as Canny edge detection, Sobel operator, etc.) are applied to identify the boundary between the target area and the road surface. The area information of the target area is obtained by calculating the area enclosed by the boundary.

[0067] Furthermore, the grayscale value difference between the target area, especially the waterlogged area and the road surface image is analyzed. According to the trend of grayscale value changes, the water level position is determined, and the water depth is calculated through the relationship between the water level position and the road surface height. Water depth is an important indicator for assessing waterlogging risk. Combining the area information of the target area and the water depth, the reference risk value corresponding to the road surface is determined. This value reflects the risk level that the road may face under the current conditions. For example, the larger the target area and the deeper the water depth, the greater the reference risk value.

[0068] Furthermore, a preset time period is set, such as the past ten minutes, and the number of vehicles passing through the road surface during this time period is counted. The road vehicle traffic rate is obtained by calculating the ratio of the number of vehicles to the preset time period. This value reflects the traffic flow of the road. Considering the impact of traffic flow on road risk, the road vehicle traffic rate is used to adjust the reference risk value. If the traffic flow is large, the road risk may increase accordingly, so the risk value needs to be increased; conversely, if the traffic flow is small, the road risk may decrease, so the risk value can be appropriately reduced. The adjusted risk value is the actual risk value of the road surface, which more accurately reflects the risk level of road traffic under the current traffic flow conditions.

[0069] S105. Based on the predicted risk value of the road condition and the actual risk value of the road condition, a graded warning is given to the road condition, and the guardrails on both sides are controlled based on the graded warning to adjust the road condition.

[0070] In one embodiment of the present application, based on the predicted risk value of the road traffic condition and the actual risk value of the road, the risk value in the future time period corresponding to the road to be tested is obtained. The risk thresholds corresponding to different preset risk levels are determined, and the risk values ​​in the future time period are divided based on the risk thresholds to obtain multiple risk time periods. Based on different risk levels, the corresponding guardrail adjustment strategy is matched, and the guardrail adjustment strategy is associated with multiple risk time periods. Based on the association relationship, the guardrail changes on both sides of the road are controlled in the corresponding risk time period to adjust the road traffic.

[0071] Specifically, the calculated road traffic condition risk prediction value is combined with the actual road risk value to obtain a comprehensive risk assessment value. This value represents the risk level that the road to be tested may face in a certain period of time in the future. In one embodiment of the present application, the road traffic condition risk prediction value and the actual road risk value are input into a time series prediction model to obtain a reference risk value corresponding to the road to be tested; a risk value change line graph is constructed based on the reference risk value to determine the risk value of the road to be tested in the future period based on the risk value change line graph.

[0072] Specifically, first, the risk prediction value of the road traffic condition is used as input and input into the time series prediction model. Through the calculation of the time series prediction model, a reference risk value of the road to be tested in a certain period of time in the future can be obtained. This value is a prediction result that combines historical data and real-time data, so it is more accurate and reliable than using any data alone. Use the reference risk value to construct a risk value change line graph. This line graph shows the trend of risk value changes over time, and can intuitively understand the changes in the risk level of the road to be tested in the future period. The risk value change line graph can contain risk values ​​at multiple time points, which can be continuous (such as every hour, every day, etc.) or specific time points (such as peak traffic hours, bad weather periods, etc.). Determine the risk value of the road to be tested in the future period based on the risk value change line graph.

[0073] Furthermore, different preset risk levels are set, and corresponding risk thresholds are determined for each level. These thresholds are used to divide the risk assessment values ​​in the future time period, thereby obtaining multiple time periods with different risk levels. For example, the risk level can be divided into three levels: low, medium, and high, and corresponding thresholds can be set for them respectively. According to different risk levels, corresponding guardrail adjustment strategies are formulated. These strategies may include increasing the height and density of guardrails or changing the type of guardrails to meet the road traffic needs under different risk levels. These guardrail adjustment strategies are associated with the risk time periods obtained by the previous division to ensure that more stringent guardrail adjustment measures are implemented in time periods with higher risks.

[0074] Furthermore, based on the above association, the guardrails on both sides of the road are automatically controlled to change during the corresponding risk time period. These changes are intended to improve road safety and reduce the risk of traffic accidents. For example, during a period of high risk, the height or density of the guardrails can be increased to better protect pedestrians and vehicles; while during a period of low risk, the density or height of the guardrails can be appropriately reduced to improve the traffic efficiency of the road.

[0075] Figure 2 The schematic diagram of the structure of a road traffic condition monitoring device based on a smart guardrail provided in an embodiment of the present application. Figure 2 As shown, a road traffic condition monitoring device 200 based on an intelligent guardrail comprises: at least one processor 201; and a memory 202 in communication with the at least one processor 201; wherein the memory 202 stores instructions executable by the at least one processor 201, and the instructions are executed by the at least one processor 201 so that the at least one processor 201 can: based on multiple data acquisition devices on the guardrails on both sides of the road to be tested, obtain meteorological data and road image data corresponding to the road to be tested, and upload the meteorological data and road image data to a traffic management center; wherein the multiple data acquisition devices are respectively arranged at different target sections of the road to be tested; at the traffic management center, extract hidden danger element data from the meteorological data through a preset combined data extraction model; determine the road traffic condition risk prediction value corresponding to the road to be tested based on the road image data and hidden danger element data corresponding to different target sections; identify the target area of ​​the road image data through an edge detection algorithm to determine the actual risk value of the road based on the target area; perform graded warning on the road traffic condition based on the road traffic condition risk prediction value and the actual risk value of the road, and control the change of the guardrails on both sides based on the graded warning to adjust the road traffic.

[0076] A non-volatile computer storage medium provided in an embodiment of the present application stores computer executable instructions, wherein the computer executable instructions are configured to: based on multiple data acquisition devices on guardrails on both sides of a road surface to be tested, obtain meteorological data and road image data corresponding to the road surface to be tested, and upload the meteorological data and road image data to a traffic management center; wherein the multiple data acquisition devices are respectively arranged at different target sections of the road surface to be tested; at the traffic management center, extract hidden danger element data from the meteorological data through a preset combined data extraction model; determine a road surface traffic condition risk prediction value corresponding to the road surface to be tested based on the road image data and hidden danger element data corresponding to different target sections; identify a target area of ​​the road image data through an edge detection algorithm to determine an actual road surface risk value based on the target area; perform graded warnings on the road surface traffic condition based on the road surface traffic condition risk prediction value and the actual road surface risk value, and control the changes of guardrails on both sides based on the graded warnings to adjust the road traffic.

[0077] Each embodiment in this application is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device, equipment, and non-volatile computer storage medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0078] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the embodiments of the present application may have various changes and variations. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present application.

Claims

1. A road traffic condition monitoring method based on intelligent guardrail, characterized in that: The method comprises: Based on multiple data acquisition devices on the guardrails on both sides of the road to be tested, meteorological data and road image data corresponding to the road to be tested are acquired, and the meteorological data and the road image data are uploaded to the traffic management center; wherein the multiple data acquisition devices are respectively arranged at different target sections of the road to be tested; In the traffic management center, extracting hidden danger element data from the meteorological data by using a preset combined data extraction model; Determining a road traffic condition risk prediction value corresponding to the road to be tested based on the road image data and the hidden danger element data corresponding to the different target road sections respectively; Performing target area recognition on the road image data by using an edge detection algorithm to determine an actual road surface risk value based on the target area; Based on the predicted risk value of the road traffic condition and the actual risk value of the road traffic condition, a graded warning is given to the road traffic condition, and based on the graded warning, changes in the guardrails on both sides are controlled to adjust road traffic.

2. A method for monitoring road traffic conditions based on intelligent guardrails according to claim 1, characterized in that: Before extracting hidden danger element data from the meteorological data by using the preset combined data extraction model, the method further includes: Using historical meteorological data samples as a training set and inputting them into a preset deep learning model to train the preset deep learning model; Based on a preset feature interaction table, determining the interaction relationship between different initial element data output by the preset deep learning model; wherein the preset feature interaction table includes a plurality of different initial element data, and also includes the interaction relationship between the plurality of initial element data; Based on the interactive influence relationship, weighted averaging the different initial element data to generate a fusion training set; Inputting the fused training set into a preset gradient boosting tree model to train the preset gradient boosting tree model; Based on the trained preset deep learning model and the trained preset gradient boosting tree model, the preset combined data extraction model is obtained.

3. A method for monitoring road traffic conditions based on intelligent guardrails according to claim 2, characterized in that: Based on the interactive influence relationship, weighted averaging the different initial element data to generate a fusion training set specifically includes: Interaction functions based on preset data: Performing weighted averaging on the different initial element data to generate the fusion training set; Among them, X fused is the fused data; w ij represents the interaction weight between the i-th initial feature data and the j-th initial feature data, x i represents the characteristic value of the i-th initial element data; x j Represents the eigenvalue of the jth initial feature data.

4. The method for monitoring road traffic conditions based on intelligent guardrail according to claim 1, characterized in that: The determining of the road traffic condition risk prediction value corresponding to the road to be tested based on the road image data and the hidden danger element data respectively corresponding to the different target road sections specifically includes: Based on the road image data, determining the road condition types corresponding to the different target road sections respectively; wherein the road condition types include road icing and road surface water; In the case where the road condition type is the road icing, determining the road hidden danger air pressure data and the road hidden danger temperature data through the hidden danger element data, generating the road ice melting time and the road ice melting speed based on the hidden danger air pressure data and the hidden danger temperature data, and generating the road early warning information based on the road ice melting time and the road ice melting speed; In the case where the road condition type is the road waterlogging, the potential danger precipitation, potential danger humidity and potential danger temperature of the road are determined through the potential danger element data, and the water accumulation dissipation time and water accumulation dissipation speed are determined based on the potential danger precipitation, potential danger humidity, potential danger temperature and the drainage system data corresponding to the road surface to be tested, so as to generate the road surface warning information based on the water accumulation dissipation time and water accumulation dissipation speed; Based on the road surface warning information corresponding to the different target road sections, the road surface traffic condition risk prediction value corresponding to the road surface to be tested is determined.

5. A method for monitoring road traffic conditions based on intelligent guardrails according to claim 4, characterized in that: The determining of the road traffic condition risk prediction value corresponding to the road to be tested based on the road warning information corresponding to the different target road sections specifically includes: Based on the installation position of the guardrail, determining the position information corresponding to the different target road sections respectively; Based on the location information, determine the historical traffic accident data corresponding to each of the target road sections in a historical traffic database, and assign a first weight to each of the target road sections based on the historical traffic accident data; Based on the location information, determining the road structure data corresponding to each of the target road sections in the traffic network map corresponding to the road surface to be tested, and assigning a second weight to each of the target road sections based on the road structure data; The first weight assignment, the second weight assignment and the road surface warning information corresponding to the different target road sections are weighted to obtain a road surface traffic condition risk prediction value corresponding to the road surface to be tested.

6. The method for monitoring road traffic conditions based on intelligent guardrails according to claim 1 is characterized in that: The step of identifying a target area of ​​the road image data by using an edge detection algorithm to determine an actual road surface risk value based on the target area specifically includes: Performing target area detection on the road image data; wherein the target area at least includes an ice area and a water accumulation area; Based on an edge detection algorithm, determining a boundary between the target area and a road surface, so as to determine area information of the target area based on the boundary; Determine a water level line according to the difference in image grayscale values ​​between the target area and the road surface image, so as to obtain the depth of water accumulation based on the water level line; Based on the area information and the water depth, obtaining a reference risk value corresponding to the road surface; And, based on a preset time length and the number of vehicles passing through the preset time length, a vehicle traffic rate on the road surface is obtained; The reference risk value is adjusted based on the road traffic flow rate to obtain an actual road risk value.

7. The method for monitoring road traffic conditions based on intelligent guardrails according to claim 1 is characterized in that: The step of providing a graded warning for the road traffic condition based on the road traffic condition risk prediction value and the road actual risk value, and controlling the change of the guardrails on both sides of the road based on the graded warning to adjust the road traffic, specifically includes: Based on the road traffic condition risk prediction value and the road actual risk value, obtaining a risk value in a future time period corresponding to the road to be tested; Determine risk thresholds corresponding to different preset risk levels, and divide the risk value in the future period based on the risk thresholds to obtain multiple risk time periods; Based on the different risk levels, matching corresponding guardrail adjustment strategies, and associating the guardrail adjustment strategies with a plurality of risk time periods; Based on the association relationship, the guardrails on both sides of the road are controlled during the corresponding risk time period to adjust the road traffic.

8. The method for monitoring road traffic conditions based on intelligent guardrails according to claim 1 is characterized in that: The step of obtaining the risk value of the road surface to be tested corresponding to the road surface in the future time period based on the road surface traffic condition risk prediction value and the road surface actual risk value specifically includes: Input the road traffic condition risk prediction value and the road actual risk value into a time series prediction model to obtain a reference risk value corresponding to the road to be tested; A risk value variation line graph is constructed based on the reference risk value, so as to determine the risk value in the future time period corresponding to the road surface to be tested based on the risk value variation line graph.

9. A road traffic condition monitoring device based on intelligent guardrail, characterized in that: The device comprises a memory for storing computer program instructions and a processor for executing the program instructions, wherein when the computer program instructions are executed by the processor, the device is triggered to execute the method according to any one of claims 1 to 8.

10. A non-volatile computer storage medium storing computer executable instructions, characterized in that: The computer executable instructions can execute the method according to any one of claims 1 to 8.

Images