Traffic risk early warning system and method for traffic separation zone

Abstract

This invention discloses a traffic risk early warning system and method for traffic medians; it relates to the field of traffic risk technology; the invention collects traffic median data from major traffic arteries; sets up a simplified model generation mechanism to generate a simplified median state model based on the traffic median data; acquires real-time vehicle traffic data from major traffic arteries, and then forms an AR traffic risk prediction model of the simplified median state model based on the relative motion of the vehicle traffic data; simulates the changing position data of the corresponding key points of the simplified median state model under the current environmental data in the AR risk prediction model; analyzes the changing position data to obtain traffic risk data; processes the traffic risk data to obtain processed data; effectively improving the timeliness of traffic median risk early warning under different environments.

Description

Technical Field

[0001] This invention relates to the field of traffic risk technology, and more specifically to a traffic risk early warning system and method for traffic medians. Background Technology

[0002] Traffic barriers are strip-shaped facilities or railings on roads used to separate traffic flows and maintain traffic order; they are not only physical barriers but also important tools for traffic management. Generally, traffic barriers are mainly divided into the following categories according to their location, the objects they isolate, and their physical form: central median, non-motorized vehicle barriers, pedestrian barriers, etc. With the continuous expansion of urban road traffic, traffic isolation facilities such as median strips and guardrails have become key infrastructure for regulating traffic flow, preventing wrong-way driving, and reducing road traffic accidents. Due to natural environmental factors, they are prone to tilting and shifting abnormally. If even minor shifts in the median strip are not detected and addressed in time, they will gradually increase in deformation, compress traffic space, increase the probability of vehicle scrapes and collisions, and seriously threaten road safety. Therefore, the object of this invention is to provide a traffic risk warning system and method for traffic medians. Summary of the Invention

[0003] The purpose of this invention is to provide a traffic risk warning system and method for traffic medians, in order to address the shortcomings in the prior art.

[0004] To achieve the above objectives, the present invention provides the following technical solution: a traffic risk early warning method for traffic medians, the method comprising the following steps: Step S1: Collect data on traffic median strips along major traffic routes; Step S2: Set up a simplified model generation mechanism, and generate a simplified model of the traffic median strip status based on the simplified model generation mechanism; Step S3: Real-time acquisition of vehicle traffic data on major traffic arteries, and then AR traffic risk prediction model based on the relative motion of vehicles based on the traffic data to form a simplified model of the median strip state. Step S4: Simulate the changes in the location data of the key points corresponding to the simplified model of the isolation zone status under the current environmental data in the AR risk prediction model; Step S5: Analyze the location change data to obtain traffic risk data; Step S6: Process traffic risk data and obtain processed data.

[0005] Furthermore, the process of collecting data on traffic medians along major transportation routes includes: The system identifies the major traffic arteries with existing traffic barriers, and then obtains the isolation data of the corresponding traffic barriers for these arteries. The isolation data includes the location of the standard traffic barriers, the type of traffic barriers, and the physical form of the traffic barriers. The location points of the traffic isolation strip are set by the physical shape of the isolation strip, and the horizontal line of the location points is set; the location data of the location points are collected according to the horizontal line of the location points, and the location data includes the intersection point, the intersection angle, the offset angle, the offset start time point, and the offset displacement; Then, the location data is connected with the type of median strip to generate traffic median strip data.

[0006] Furthermore, a simplified model generation mechanism is established. The process of generating a simplified model of the traffic median strip status based on the simplified model generation mechanism includes: The edge nodes of the traffic barrier are obtained based on the physical shape of the barrier, and then the spatial edge lines of the traffic barrier are obtained based on the edge nodes; the spatial edge lines include spatial length edge lines, spatial width edge lines, and spatial height edge lines. The spatial structure is established by using the spatial length edge line, spatial width edge line, and spatial height edge line as the basis for building the length, width, and height of the cuboid, thereby generating a simplified morphological model of the traffic divider. Based on the intersection points and the included angle between the intersection points, the offset points of the corresponding key points in the simplified morphological model are determined; the offset angle, offset start time, and offset displacement of the key points are presented at the offset points to construct a simplified model of the isolation zone state corresponding to the traffic isolation zone position data, and then a simplified model generation mechanism is constructed.

[0007] Furthermore, the process of acquiring real-time vehicle traffic data for key transportation routes includes: Set the relative position driving lines of key locations and map them to the corresponding key locations; display the relative position driving lines on GPS to generate vehicle driving prediction models for each traffic artery. The vehicle driving prediction model sets the vehicle driving acquisition parameters; the driving acquisition parameters include basic vehicle parameters and relative parameters; the basic vehicle parameters include vehicle license plate number and vehicle size; the relative parameters include relative position point, relative speed, relative time, relative displacement and relative distance; the relative position driving line level driving line area is set, and then the acquisition frequency of different level driving line areas is set. Based on GPS, vehicle traffic data is collected in real time from the relative position driving line to collect the corresponding parameters of all vehicles in the driving line area of ​​different levels.

[0008] Furthermore, the process of creating an AR traffic risk prediction model based on relative motion data to form a simplified model of the median strip state includes: The simplified model of the median strip status is mapped to each traffic median strip of the corresponding traffic artery in GPS; and a traffic risk prediction model is formed with the vehicle driving prediction model; according to the vehicle shape and size, the shape model of each vehicle is constructed and mapped to each traffic artery corresponding to the traffic risk prediction model. The traffic risk prediction data for each vehicle on the main traffic artery is generated by mapping the relative parameters of each collection time point to the location data of the corresponding key points based on the collection frequency; and then an AR traffic risk prediction model with a simplified model of the median strip state is constructed.

[0009] Furthermore, the process of simulating changes in the location data of key points corresponding to the current environmental data in the AR risk prediction model to simulate the state of the isolation zone includes: Based on big data, several environmental data combinations are set for different seasons; the environmental data combinations include at least wind speed, rainfall, road surface humidity, and snow thickness; the environmental data combinations are mapped to the AR risk prediction model to perform environmental simulation of the environmental data combinations and obtain the change location data of each key point in the simplified model of the isolation zone status; Based on the change location data, the corresponding offset location points are obtained, and then the offset location points are connected sequentially by straight lines in time order to generate the change location movement trajectory of the key location points; the change location movement trajectory is vertically mapped onto the ground, with the change direction of the offset location points as the vertical axis and the corresponding change location data as the vertical axis; the horizontal axis corresponding to the combination of environmental data is perpendicular to the vertical axis, thereby constructing the change location movement trajectory model; The system collects current environmental data in real time and sends the data to the trajectory model at the changing location to obtain the corresponding location change data.

[0010] Furthermore, the process of analyzing change location data to obtain traffic risk data includes: Determine whether the offset angle and offset displacement of the changed position data meet the preset threshold range; If any point does not meet the corresponding threshold range, the corresponding location point will be marked as an abnormal location point. If the corresponding threshold range is met, then obtain the vehicle traffic data corresponding to the vehicle parameters of the location key point; determine whether the corresponding relative displacement and relative distance meet the preset threshold. If both conditions are met, no action is taken. Conversely, the corresponding location key points will be marked as abnormal location key points; Mark the changed location data corresponding to the abnormal location key points as traffic risk data.

[0011] Furthermore, the process of processing traffic risk data includes: The system obtains the traffic risk data and sends the offset location points and corresponding traffic risk data to the processing personnel in the processing departments via communication for early warning. Traffic risk data is processed and marked as processed data, thereby repositioning the abnormal locations of traffic barriers.

[0012] Furthermore, it includes the following modules: Data acquisition module: Used to collect data on traffic medians along major roads; Model Simplification Module: Used to set up a simplified model generation mechanism, which generates a simplified model of the traffic median strip status from the traffic median strip data. AR Model Generation Module: Used to acquire vehicle traffic data of major traffic arteries in real time, and then form an AR traffic risk prediction model based on the relative motion of the vehicle traffic data to form a simplified model of the median strip state. Monitoring module: Used in the AR risk prediction model to simulate the change of location data of key points corresponding to the isolation zone status under the current environmental data; Analysis module: Used to analyze change location data to obtain traffic risk data.

[0013] Processing module: Used to process traffic risk data and obtain processed data.

[0014] Compared with existing technologies, the beneficial effects of this invention are as follows: This invention collects traffic median strip data from major traffic arteries; sets up a simplified model generation mechanism to generate a simplified median strip state model based on the traffic median strip data; acquires real-time vehicle traffic data from major traffic arteries, and then forms an AR traffic risk prediction model of the simplified median strip state model based on the relative motion of the vehicle traffic data; simulates the changing position data of the corresponding key points of the simplified median strip state model under the current environmental data in the AR risk prediction model; analyzes the changing position data to obtain traffic risk data; processes the traffic risk data to obtain processed data; and effectively improves the timeliness of traffic median strip risk warnings under different environments. Attached Figure Description

[0015] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this invention. For those skilled in the art, other drawings can be obtained based on these drawings.

[0016] Figure 1 This is a flowchart of the traffic risk early warning method for traffic medians according to the present invention.

[0017] Figure 2 This is a schematic diagram of the traffic risk data of the present invention.

[0018] Figure 3 This is a schematic diagram of the traffic risk early warning system for traffic medians according to the present invention. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0020] Please see Figure 1 As shown, a traffic risk warning method for traffic medians includes the following steps: Step S1: Collect data on traffic median strips along major traffic routes; Step S2: Set up a simplified model generation mechanism, and generate a simplified model of the traffic median strip status based on the simplified model generation mechanism; Step S3: Real-time acquisition of vehicle traffic data on major traffic arteries, and then AR traffic risk prediction model based on the relative motion of vehicles based on the traffic data to form a simplified model of the median strip state. Step S4: Simulate the changes in the location data of the key points corresponding to the simplified model of the isolation zone status under the current environmental data in the AR risk prediction model; Step S5: Analyze the location change data to obtain traffic risk data; Step S6: Process traffic risk data and obtain processed data.

[0021] Step S1 needs further clarification. The process of collecting traffic median strip data for major traffic arteries includes: The system identifies the major traffic arteries with existing traffic barriers, and then obtains the isolation data of the corresponding traffic barriers for these arteries. The isolation data includes the location of the standard traffic barriers, the type of traffic barriers, and the physical form of the traffic barriers. The location points of the traffic isolation strip are set by the physical shape of the isolation strip, and the horizontal line of the location points is set; the location data of the location points are collected according to the horizontal line of the location points, and the location data includes the intersection point, the intersection angle, the offset angle, the offset start time point, and the offset displacement; Then, the location data is connected with the type of median strip to generate traffic median strip data.

[0022] In the above embodiments, it is further necessary to define that the standard isolation zone includes a number of standard locations; the physical shape of the isolation zone is used to represent the physical shape of the traffic isolation zone; the location points are used to represent the locations of the main monitored risks, and corresponding sensors or acquisition devices are set at the location points to collect corresponding location data; wherein, if the traffic isolation zone has a wavy arc, each arc node is marked as a location point; the location horizontal line is used to represent the horizontal line passing through the location points; further, the intersecting location point is used to represent the intersection point of the extension line of the location point on the isolation zone and the extension line of the corresponding standard location on the isolation zone, and the corresponding included angle is recorded as the intersection angle; the offset angle is used to represent the angle between the location point and the location horizontal line; the offset start time is used to represent the time point at which the location point is offset from the standard isolation zone position; the offset displacement is used to represent the sine data of the displacement point corresponding to the intersection angle.

[0023] Step S2 requires further clarification. A simplified model generation mechanism needs to be established. The process of generating a simplified model of the traffic median strip status based on the simplified model generation mechanism includes: The edge nodes of the traffic barrier are obtained based on the physical shape of the barrier, and then the spatial edge lines of the traffic barrier are obtained based on the edge nodes; the spatial edge lines include spatial length edge lines, spatial width edge lines, and spatial height edge lines. The spatial structure is established by using the spatial length edge line, spatial width edge line, and spatial height edge line as the basis for building the length, width, and height of the cuboid, thereby generating a simplified morphological model of the traffic divider. Based on the intersection points and the included angle between the intersection points, the offset points of the corresponding key points in the simplified morphological model are determined; the offset angle, offset start time, and offset displacement of the key points are presented at the offset points to construct a simplified model of the isolation zone state corresponding to the traffic isolation zone position data, and then a simplified model generation mechanism is constructed.

[0024] In the above embodiments, it is further defined that the edge node is used to represent the outermost edge node in the length, width, and height directions of the traffic barrier obtained according to the physical shape of the barrier; and the spatial edge line is used to represent the spatial length edge line, spatial width edge line, and spatial height edge line obtained by the edge node based on the length, height, and width of the traffic barrier; and the cuboid obtained based on the spatial length edge line, spatial width edge line, and spatial height edge line as the length, width, and height reference of the cuboid contains all the physical shapes of the traffic barrier; thus, the speed of construction is improved. Specifically, if the barrier has a wavy arc, the highest and lowest points of each arc are first extracted as edge nodes, and these nodes are connected to form physical length edge lines. Then, edge nodes and lines in the width and height directions are extracted, and finally, a simplified cuboid model that can wrap around the entire wave-shaped guardrail is built based on these three lines. By extracting edge nodes and constructing a simplified cuboid model, the modeling complexity is significantly reduced and the modeling efficiency is improved while retaining the core spatial dimensions of the barrier. After superimposing the position data, the offset state of the barrier can be intuitively presented, facilitating accurate monitoring of risk points. This effectively solves the problems of low data modeling efficiency and high computational load caused by the complex shape of traffic medians.

[0025] Please see Figure 2 As shown, step S3 needs further clarification. The process of acquiring real-time vehicle traffic data for major traffic arteries includes: Set the relative position driving lines of key locations and map them to the corresponding key locations; display the relative position driving lines on GPS to generate vehicle driving prediction models for each traffic artery. The vehicle driving prediction model sets the vehicle driving acquisition parameters; the driving acquisition parameters include basic vehicle parameters and relative parameters; the basic vehicle parameters include vehicle license plate number and vehicle size; the relative parameters include relative position point, relative speed, relative time, relative displacement and relative distance; the relative position driving line level driving line area is set, and then the acquisition frequency of different level driving line areas is set. Based on GPS, vehicle traffic data is collected in real time from the relative position driving line to collect the corresponding parameters of all vehicles in the driving line area of ​​different levels.

[0026] In the above embodiments, it is further necessary to define that the vehicle shape and size are used to represent the vehicle's external shape and size; the relative position driving line is used to represent the relative position driving line that best influences vehicle driving based on the key position point; therefore, the vehicle driving route that needs to be monitored is delineated around the risk point of the median strip. The relative position point is used to represent the center position point of the vehicle relative to the key position point from the starting point of the relative driving line; the relative speed is used to represent the driving speed of the vehicle relative to the key position point; the relative displacement is used to represent the displacement of the vehicle relative to the key position point in the driving direction, obtained through relative speed and relative time; the relative time is used to represent the driving time of the vehicle relative to the key position point from the starting point of the relative position driving line in the direction of relative displacement; and the relative distance is used to represent the distance between the key position point and the relative position point.

[0027] It should be further explained that the process of using AR traffic risk prediction models to form simplified models of median strip states based on relative motion from vehicle traffic data includes: The simplified model of the median strip status is mapped to each traffic median strip of the corresponding traffic artery in GPS; and a traffic risk prediction model is formed with the vehicle driving prediction model; according to the vehicle shape and size, the shape model of each vehicle is constructed and mapped to each traffic artery corresponding to the traffic risk prediction model. The traffic risk prediction data for each vehicle on the main traffic artery is generated by mapping the relative parameters of each collection time point to the location data of the corresponding key points based on the collection frequency; and then an AR traffic risk prediction model with a simplified model of the median strip state is constructed.

[0028] In the above embodiments, it should be further explained that the simplified state model of the median strip is the shape model of the traffic median strip. Mapping the simplified state model of the median strip to each traffic median strip of the traffic artery corresponding to the GPS can better realize the prediction of traffic risks of the traffic median strip. Based on the vehicle shape model, the relative parameter motion is used to construct an AR traffic risk prediction model to improve the traffic safety prediction of the traffic median strip.

[0029] Further clarification is needed for step S4, which involves simulating changes in the location data of key points corresponding to the current environmental data in the AR risk prediction model, including: Based on big data, several environmental data combinations are set for different seasons; the environmental data combinations include at least wind speed, rainfall, road surface humidity, and snow thickness; the environmental data combinations are mapped to the AR risk prediction model to perform environmental simulation of the environmental data combinations and obtain the change location data of each key point in the simplified model of the isolation zone status; Based on the change location data, the corresponding offset location points are obtained, and then the offset location points are connected sequentially by straight lines in time order to generate the change location movement trajectory of the key location points; the change location movement trajectory is vertically mapped onto the ground, with the change direction of the offset location points as the vertical axis and the corresponding change location data as the vertical axis; the horizontal axis corresponding to the combination of environmental data is perpendicular to the vertical axis, thereby constructing the change location movement trajectory model; The system collects current environmental data in real time and sends the data to the trajectory model at the changing location to obtain the corresponding location change data.

[0030] In the above embodiments, it should be further explained that the environmental data combination is used to represent the offset of the key points corresponding to the traffic median strip that will mainly affect the straight line; firstly, the change position movement trajectory of the offset position point of the environmental data combination under historical conditions is obtained; then, the change position movement trajectory model is generated based on AI intelligence; and then the change position data of the key points is obtained in real time by collecting the current environmental data combination.

[0031] Further clarification is needed for step S5, which includes the process of analyzing change location data to obtain traffic risk data, including: Determine whether the offset angle and offset displacement of the changed position data meet the preset threshold range; If any point does not meet the corresponding threshold range, the corresponding location point will be marked as an abnormal location point. If the corresponding threshold range is met, then obtain the vehicle traffic data corresponding to the vehicle parameters of the location key point; determine whether the corresponding relative displacement and relative distance meet the preset threshold. If both conditions are met, no action is taken. Conversely, the corresponding location key points will be marked as abnormal location key points; Mark the changed location data corresponding to the abnormal location key points as traffic risk data.

[0032] In the above embodiments, it is necessary to further define that the threshold range includes the offset angle threshold range and the offset displacement threshold range corresponding to the offset angle and the offset displacement, respectively; it is mainly set according to the different traffic isolation strips; the threshold includes the relative displacement threshold and the relative distance threshold corresponding to the relative displacement and the relative distance, respectively.

[0033] Further clarification is needed for step S6, which includes the process of processing traffic risk data to obtain processed data, including: The system obtains the traffic risk data and sends the offset location points and corresponding traffic risk data to the processing personnel in the processing departments via communication for early warning. Traffic risk data is processed and marked as processed data, thereby repositioning the abnormal locations of traffic barriers.

[0034] Please see Figure 3 As shown, the present invention also provides a traffic risk early warning system for traffic medians, comprising the following modules: Data acquisition module: Used to collect data on traffic medians along major roads; Model Simplification Module: Used to set up a simplified model generation mechanism, which generates a simplified model of the traffic median strip status from the traffic median strip data. AR Model Generation Module: Used to acquire vehicle traffic data of major traffic arteries in real time, and then form an AR traffic risk prediction model based on the relative motion of the vehicle traffic data to form a simplified model of the median strip state. Monitoring module: Used in the AR risk prediction model to simulate the change of location data of key points corresponding to the isolation zone status under the current environmental data; Analysis module: Used to analyze change location data to obtain traffic risk data.

[0035] Processing module: Used to process traffic risk data and obtain processed data.

[0036] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A traffic risk early warning method for traffic medians, characterized in that, The method includes the following steps: Step S1: Collect data on traffic median strips along major traffic routes; Step S2: Set up a simplified model generation mechanism, and generate a simplified model of the traffic median strip status based on the simplified model generation mechanism; Step S3: Real-time acquisition of vehicle traffic data on major traffic arteries, and then AR traffic risk prediction model based on the relative motion of vehicles based on the traffic data to form a simplified model of the median strip state. Step S4: Simulate the changes in the location data of the key points corresponding to the simplified model of the isolation zone status under the current environmental data in the AR risk prediction model; Step S5: Analyze the location change data to obtain traffic risk data; Step S6: Process traffic risk data and obtain processed data.

2. The traffic risk early warning method for traffic medians according to claim 1, characterized in that, The process of collecting data on traffic dividers along major roads includes: The system identifies the major traffic arteries with existing traffic barriers, and then obtains the isolation data of the corresponding traffic barriers for these arteries. The isolation data includes the location of the standard traffic barriers, the type of traffic barriers, and the physical form of the traffic barriers. The location points of the traffic isolation strip are set by the physical shape of the isolation strip, and the horizontal line of the location points is set; the location data of the location points are collected according to the horizontal line of the location points, and the location data includes the intersection point, the intersection angle, the offset angle, the offset start time point, and the offset displacement. Then, the location data is connected with the type of median strip to generate traffic median strip data.

3. The traffic risk early warning method for traffic medians according to claim 2, characterized in that, Setting up a simplified model generation mechanism, the process of generating a simplified model of the traffic median strip status from the traffic median strip data based on the simplified model generation mechanism includes: The edge nodes of the traffic barrier are obtained based on the physical shape of the barrier, and then the spatial edge lines of the traffic barrier are obtained based on the edge nodes; the spatial edge lines include spatial length edge lines, spatial width edge lines, and spatial height edge lines. The spatial structure is established by using the spatial length edge line, spatial width edge line, and spatial height edge line as the basis for building the length, width, and height of the cuboid, thereby generating a simplified morphological model of the traffic divider. The offset position points of the corresponding key points in the simplified morphological model are determined based on the intersection points and the included angle between the intersection points. The offset angle, offset start time point, and offset displacement of the key points are presented at the offset position points to construct a simplified state model of the traffic median strip corresponding to the position data, and then a simplified model generation mechanism is constructed.

4. The traffic risk early warning method for traffic medians according to claim 3, characterized in that, The process of acquiring real-time vehicle traffic data for major transportation routes includes: Set the relative position driving lines of key locations and map them to the corresponding key locations; display the relative position driving lines on GPS to generate vehicle driving prediction models for each traffic artery. The vehicle driving prediction model is configured with driving acquisition parameters, including basic vehicle parameters and relative parameters. The basic vehicle parameters include the vehicle license plate number and vehicle size. The relative parameters include relative position point, relative speed, relative time, relative displacement, and relative distance. The relative position driving line levels and driving line regions are set, and the acquisition frequency of different levels and driving line regions is set. Based on GPS, vehicle traffic data is collected in real time from the relative position driving line to collect the corresponding parameters of all vehicles in the driving line area of ​​different levels.

5. The traffic risk early warning method for traffic medians according to claim 4, characterized in that, The process of using AR traffic risk prediction models to form simplified models of median strip states based on relative motion data of vehicle traffic data includes: The simplified model of the median strip status is mapped to each traffic median strip of the corresponding traffic artery in GPS; and a traffic risk prediction model is formed with the vehicle driving prediction model; according to the vehicle shape and size, the shape model of each vehicle is constructed and mapped to each traffic artery corresponding to the traffic risk prediction model. The traffic risk prediction data for each vehicle on the main traffic artery is generated by mapping the relative parameters of each collection time point to the location data of the corresponding key points based on the collection frequency; and then an AR traffic risk prediction model with a simplified model of the median strip state is constructed.

6. The traffic risk early warning method for traffic medians according to claim 5, characterized in that, The process of simulating changes in key locations of the isolation zone under current environmental data in an AR risk prediction model includes: Based on big data, several environmental data combinations are set for different seasons; the environmental data combinations include at least wind speed, rainfall, road surface humidity, and snow thickness; the environmental data combinations are mapped to the AR risk prediction model to perform environmental simulation of the environmental data combinations and obtain the change location data of each key point in the simplified model of the isolation zone status; Based on the change location data, the corresponding offset location points are obtained, and then the offset location points are connected sequentially by straight lines in time order to generate the change location movement trajectory of the key location points; the change location movement trajectory is vertically mapped onto the ground, with the change direction of the offset location points as the vertical axis and the corresponding change location data as the vertical axis; the horizontal axis corresponding to the combination of environmental data is perpendicular to the vertical axis, thereby constructing the change location movement trajectory model; The system collects current environmental data in real time and sends the data to the trajectory model at the changing location to obtain the corresponding location change data.

7. The traffic risk early warning method for traffic medians according to claim 6, characterized in that, The process of analyzing change location data to obtain traffic risk data includes: Determine whether the offset angle and offset displacement of the changed position data meet the preset threshold range; If any point does not meet the corresponding threshold range, the corresponding location point will be marked as an abnormal location point. If the corresponding threshold range is met, then obtain the vehicle traffic data corresponding to the vehicle parameters of the location key point; determine whether the corresponding relative displacement and relative distance meet the preset threshold. If both conditions are met, no action is taken. Conversely, the corresponding location key points will be marked as abnormal location key points; Mark the changed location data corresponding to the abnormal location key points as traffic risk data.

8. The traffic risk early warning method for traffic medians according to claim 7, characterized in that, The process of processing traffic risk data includes: The system obtains the traffic risk data and sends the offset location points and corresponding traffic risk data to the processing personnel in the processing departments via communication for early warning. Traffic risk data is processed and marked as processed data, thereby repositioning the abnormal locations of traffic barriers.

9. A traffic risk warning system for traffic medians, comprising implementing the traffic risk warning method for traffic medians according to any one of claims 1 to 8, characterized in that, Includes the following modules: Data acquisition module: Used to collect data on traffic medians along major roads; Model Simplification Module: Used to set up a simplified model generation mechanism, which generates a simplified model of the traffic median strip status from the traffic median strip data. AR Model Generation Module: Used to acquire vehicle traffic data of major traffic arteries in real time, and then form an AR traffic risk prediction model based on the relative motion of the vehicle traffic data to form a simplified model of the median strip state. Monitoring module: Used in the AR risk prediction model to simulate the change of location data of key points corresponding to the isolation zone status under the current environmental data; Analysis module: Used to analyze change location data to obtain traffic risk data; Processing module: Used to process traffic risk data and obtain processed data.

Images