Traffic monitoring data analysis method and device under vehicle-road cooperation

Abstract

The application discloses a traffic kiosk monitoring data analysis method and device under vehicle-road cooperation, and relates to the technical field of traffic monitoring.The method comprises the following steps: taking a traffic kiosk as a starting point, deploying a RSU sequence in the extension part of the kiosk road section; obtaining multiple groups of traffic dynamic data through V2X communication with a vehicle-mounted OBU; synchronously collecting road section environment data of the kiosk road section through an environment sensing unit; fusing the multiple groups of traffic dynamic data to obtain a kiosk traffic situation map; positioning multiple collision risk vehicles; matching multiple risk warning instructions; and sending the multiple risk warning instructions to the multiple collision risk vehicles.The technical problems of poor real-time traffic data collection, lack of effective interaction between vehicles and infrastructure, difficulty in comprehensively and accurately grasping traffic dynamics, and inability to effectively respond to traffic congestion and prevent traffic accidents in the prior art are solved, and the technical effects of accurately positioning collision risk vehicles and timely risk warning and improving traffic management efficiency are achieved.

Description

Technical Field

[0001] This application relates to the technical field of traffic monitoring, specifically to a method and device for analyzing traffic checkpoint monitoring data under vehicle-road cooperation. Background Technology

[0002] Traditional traffic checkpoint monitoring mainly relies on fixed cameras, geomagnetic sensors, and other equipment. Although it can acquire some traffic data, it suffers from problems such as limited information collection, insufficient real-time performance, and lack of interaction between vehicles and between vehicles and infrastructure. With the acceleration of urbanization and the continuous increase in the number of motor vehicles, traffic flow is constantly increasing and traffic scenarios are becoming more complex. Traditional monitoring methods are unable to fully and accurately grasp traffic dynamics and cannot effectively cope with problems such as traffic congestion and frequent traffic accidents, thus affecting the efficiency and accuracy of traffic management.

[0003] Therefore, current technologies suffer from technical problems such as poor real-time traffic data collection, lack of effective interaction between vehicles and infrastructure, difficulty in comprehensively and accurately grasping traffic dynamics, and inability to effectively address traffic congestion and prevent traffic accidents. Summary of the Invention

[0004] This application provides a method and device for analyzing traffic checkpoint monitoring data under vehicle-road cooperation, which solves the technical problems existing in the prior art, such as poor real-time traffic data collection, lack of effective interaction between vehicles and infrastructure, difficulty in comprehensively and accurately grasping traffic dynamics, and inability to effectively deal with traffic congestion and prevent traffic accidents. It achieves the technical effect of accurately locating vehicles at risk of collision and providing timely risk warnings, thereby improving traffic management efficiency.

[0005] This application provides a method for analyzing traffic checkpoint monitoring data under vehicle-road cooperation. The method includes: deploying a traffic checkpoint sequence extending along the checkpoint road segment; obtaining multiple sets of traffic dynamic data through V2X communication between the RSU sequence and the on-board units (OBUs) of vehicles passing through the checkpoint road segment; synchronously collecting road segment environmental data of the checkpoint road segment through an environmental sensing unit; fusing the multiple sets of traffic dynamic data to obtain a checkpoint traffic situation map; performing trajectory prediction on the checkpoint traffic situation map based on the road segment environmental data to locate multiple collision-risk vehicles; matching multiple risk warning commands based on multiple traffic risk characteristics of the multiple collision-risk vehicles; and sending the multiple risk warning commands to the multiple collision-risk vehicles through the V2X communication link between the RSU sequence and the on-board units (OBUs).

[0006] This application also provides a traffic checkpoint monitoring data analysis device under vehicle-road cooperation, the device comprising: an RSU sequence deployment module for deploying an RSU sequence extending along the checkpoint road segment from the traffic checkpoint as the starting point; a traffic dynamic data acquisition module for obtaining multiple sets of traffic dynamic data by the RSU sequence through V2X communication with the on-board units (OBUs) of vehicles passing through the checkpoint road segment; an environmental data acquisition module for synchronously acquiring road segment environmental data of the checkpoint road segment through an environmental sensing unit; a traffic dynamic data fusion module for fusing the multiple sets of traffic dynamic data to obtain a checkpoint traffic situation map; a trajectory prediction module for performing trajectory prediction on the checkpoint traffic situation map based on the road segment environmental data to locate multiple collision-risk vehicles; a risk warning instruction matching module for matching multiple risk warning instructions based on multiple traffic risk characteristics of the multiple collision-risk vehicles; and a risk warning instruction sending module for sending the multiple risk warning instructions to the multiple collision-risk vehicles through the V2X communication link between the RSU sequence and the on-board units (OBUs).

[0007] This application proposes a traffic checkpoint monitoring data analysis method and device under vehicle-road cooperative systems. Starting from a traffic checkpoint, a series of Remote Units (RSUs) are deployed along the checkpoint road segment. Multiple sets of dynamic traffic data are obtained through V2X communication with the vehicle-mounted On-Board Unit (OBU). Environmental data of the checkpoint road segment is simultaneously collected via an environmental sensing unit. Multiple sets of dynamic traffic data are fused to obtain a traffic situation map of the checkpoint. Multiple collision-risk vehicles are located; multiple risk warning commands are matched; and these commands are sent to the vehicles at risk of collision. This solves the technical problems of poor real-time traffic data acquisition, lack of effective interaction between vehicles and infrastructure, difficulty in comprehensively and accurately grasping traffic dynamics, and inability to effectively address traffic congestion and prevent traffic accidents in existing technologies. It achieves the technical effect of accurately locating collision-risk vehicles and providing timely risk warnings, thereby improving traffic management efficiency. Attached Figure Description

[0008] To more clearly illustrate the technical solutions of the embodiments of this disclosure, the accompanying drawings of the embodiments of this disclosure will be briefly described below. Flowcharts are used in this application to illustrate the operations performed by the apparatus according to the embodiments of this application. It should be understood that the preceding or following operations are not necessarily performed precisely in sequence. Instead, various steps can be processed in reverse order or simultaneously as needed. Furthermore, other operations can be added to these processes, or one or more steps can be removed from these processes.

[0009] Figure 1 A schematic diagram of the traffic checkpoint monitoring data analysis method under vehicle-road cooperation provided in the embodiments of this application.

[0010] Figure 2A schematic diagram of the traffic checkpoint monitoring data analysis device under vehicle-road cooperation provided in this application embodiment.

[0011] Figure labeling: RSU sequence deployment module 10, traffic dynamic data acquisition module 20, environmental data acquisition module 30, traffic dynamic data fusion module 40, trajectory prediction module 50, risk warning instruction matching module 60, risk warning instruction sending module 70. Detailed Implementation

[0012] The above description is merely an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, specific embodiments of this application are given below.

[0013] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description of this application will be provided in conjunction with the accompanying drawings. The described embodiments should not be considered as limitations on this application. All other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0014] In the following description, references to "some embodiments" describe a subset of all possible embodiments. However, it is understood that "some embodiments" can be the same or different subsets of all possible embodiments and can be combined with each other without conflict. The terms "first" and "second" are used merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, apparatus, product, or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules not explicitly listed or inherent to these processes, methods, products, or apparatuses. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only.

[0015] This application provides a method for analyzing traffic checkpoint monitoring data under vehicle-road cooperation, such as... Figure 1 As shown, the method includes:

[0016] Step S100: Starting from the traffic checkpoint, deploy RSU sequences along the checkpoint road section.

[0017] Step S100 further includes step S110, interactively obtaining the speed limit threshold and terrain features of the traffic checkpoint; step S120, calculating and outputting the baseline deployment interval based on the speed limit threshold; step S130, after quantifying the terrain complexity based on the terrain features, matching the length of the monitoring road segment based on the terrain complexity; step S140, locating the checkpoint road segment with the traffic checkpoint as the center and based on the length of the monitoring road segment; and step S150, extending and deploying the RSU sequence on the checkpoint road segment according to the baseline deployment interval.

[0018] Preferably, by interacting with traffic management systems, geographic information systems, etc., the legal speed limit (i.e., speed limit threshold) of the road segment where the traffic checkpoint is located is obtained, as well as the terrain conditions of the road segment (such as straight road segments, curves, slopes, or terrain features such as mountain roads and urban roads). Based on the obtained speed limit threshold, the deployment interval of RSU (roadside unit) under ideal conditions is obtained through a specific calculation formula. Generally speaking, the higher the speed limit, the faster the vehicle travels. In order to ensure stable V2X communication between RSU and on-board OBU (on-board unit), the deployment interval of RSU may need to be relatively shorter to ensure that the vehicle can exchange information with RSU in a timely manner during high-speed travel. Next, the terrain features are analyzed, and the complexity of the terrain is quantified. For example, road sections with many curves and steep slopes are quantified as high complexity, while straight and open road sections are quantified as low complexity. Based on the quantified terrain complexity, combined with historical traffic data and communication requirements, an appropriate monitoring segment length is determined. Road sections with complex terrain may require longer monitoring segments to more comprehensively understand vehicle operation status and traffic conditions. Then, using traffic checkpoints as the baseline, the monitoring segment length is extended upstream and downstream of the checkpoint to delineate the specific checkpoint segment range. This segment is the target area for deploying the RSU sequence. Finally, according to the baseline deployment interval, RSUs are sequentially installed and deployed on the checkpoint segment, ensuring that the RSUs are evenly distributed throughout the segment, thus forming an RSU sequence. This ensures that vehicles can continuously and stably communicate with the RSUs for V2X while traveling in the checkpoint segment, acquiring and uploading traffic information.

[0019] Furthermore, step S150 also includes step S151, updating the regional road segment deployment based on the terrain features to obtain multiple regional deployment intervals; step S152, interactively obtaining the traffic flow characteristics of the traffic checkpoint; step S153, compensating the baseline deployment interval based on the traffic flow characteristics to obtain the updated deployment interval; and step S154, extending the deployment of the RSU sequence on the checkpoint road segment based on the updated deployment interval and the multiple regional deployment intervals.

[0020] Preferably, the deployment of RSUs in different road sections is updated based on terrain features. This includes a detailed analysis of the terrain of the road sections where traffic checkpoints are located, identifying different terrain areas such as curves, slopes, tunnels, bridges, and ordinary straight roads. Then, based on the characteristics and communication requirements of each terrain type, the deployment interval of RSUs in different terrain areas is adjusted and updated to obtain multiple regional deployment intervals. For example, at curves, because vehicles need to slow down and visibility may be obstructed, the deployment interval of RSUs may be relatively short to ensure communication quality and vehicle safety; while on straight and open road sections, the deployment interval can be relatively long. Then, by interacting with traffic monitoring systems or related sensors, traffic flow characteristic information of traffic checkpoints is obtained, including vehicle volume, vehicle type distribution, peak and off-peak times, etc. The baseline deployment interval is adjusted and compensated based on traffic flow characteristics. For example, if the traffic flow is high, the deployment interval is shortened to ensure that each vehicle can communicate with the RSU in a timely manner and avoid communication congestion; conversely, if the traffic flow is low, the deployment interval is appropriately increased to obtain an updated deployment interval that better reflects the actual traffic conditions. Finally, the updated deployment interval and multiple regional deployment intervals are integrated to deploy RSU sequences. Specifically, at checkpoint sections, RSUs are deployed in an extended manner according to the integrated interval requirements. For areas with complex terrain and high traffic volume, a shorter deployment interval is used; while for areas with flat terrain and low traffic volume, a relatively longer deployment interval is used. This ensures the effectiveness of vehicle-road cooperative communication while making reasonable use of resources to optimize the deployment of RSU sequences, so as to better meet the needs of traffic checkpoint monitoring and management.

[0021] In step S200, the RSU sequence obtains multiple sets of traffic dynamic data by communicating with the on-board OBU of vehicles passing through the checkpoint section via V2X.

[0022] Preferably, after the Roadside Unit (RSU) sequence is deployed along the traffic checkpoint section, it continuously transmits signals. When a vehicle enters the signal coverage area of ​​the RSU, the Onboard Unit (OBU) on the vehicle receives the signal and establishes a Vehicle-to-Everything (V2X) communication connection with the RSU. The V2X connection is bidirectional, allowing information to be sent from the OBU to the RSU, and vice versa. Multiple sets of traffic dynamic data are obtained through communication, which may include basic vehicle information, driving status data, driving behavior data, and information about surrounding vehicles.

[0023] Preferably, the OBU sends basic vehicle information, such as vehicle model, license plate number, and vehicle color, to the RSU, which helps to uniquely identify and classify the vehicle. It acquires real-time speed, acceleration, direction of travel, and location information of the vehicle through onboard sensors (such as speed sensors, acceleration sensors, and GPS positioning modules), and packages this information before sending it to the RSU. It also acquires driver actions, such as the braking and accelerator pedal positions and steering angle, from the vehicle's electronic control unit (ECU), and sends this information to the RSU. Finally, it obtains information about surrounding vehicles, such as the distance, relative speed, and direction of travel of surrounding vehicles, through vehicle-to-vehicle (V2V) communication, and sends this information to the RSU as well.

[0024] Step S300: The environmental sensing unit synchronously collects the road environment data of the checkpoint section.

[0025] Preferably, the environmental sensing unit works collaboratively with various sensors to monitor and collect environmental data at the checkpoint section, obtaining road environment data that may include meteorological conditions, road conditions, and surrounding environment data. Specifically, a temperature sensor measures the air temperature at the checkpoint section to understand road conditions (such as the possibility of icing) and vehicle performance (such as tire wear and engine cooling). A humidity sensor acquires air humidity data, which affects the road's coefficient of friction and the propagation effect of vehicle lights. Wind speed and direction sensors monitor wind speed and direction at the checkpoint section. A road surface condition sensor detects the road surface's slipperiness by measuring parameters such as capacitance and resistance to determine whether the road surface is dry, wet, or has water accumulation or icing. A laser smoothness meter detects the smoothness of the road surface, and image recognition is used to determine whether there are cracks, potholes, or other damage on the road. By using image sensors to capture traffic signs and markings at checkpoints, and using image recognition to detect whether they are clear, complete, and need maintenance or updates, the system can also use LiDAR or cameras to perceive the location and shape of obstacles such as buildings, trees, and billboards around the checkpoints. This will improve the efficiency and safety of traffic management and provide vehicles with more accurate information about their driving environment.

[0026] Step S400: Integrate the multiple sets of traffic dynamic data to obtain a traffic situation map of the checkpoint.

[0027] Step S400 further includes step S410, aggregating the multiple sets of traffic dynamic data based on vehicle IDs to obtain P time-series vehicle dynamic data for P passing vehicles; step S420, after unifying the spatiotemporal reference of the P time-series vehicle dynamic data through the NTP protocol, fitting and outputting the driving status of P vehicles; step S430, aligning the driving status of the P vehicles in the checkpoint section through coordinate system transformation space, and outputting the checkpoint traffic status map.

[0028] Preferably, each onboard unit (OBU) carries a unique vehicle ID during communication. This ID is used to associate multiple sets of traffic dynamic data (such as location, speed, acceleration, etc.) generated by the same vehicle at different times and in different RSU coverage areas. All data points for the same vehicle are arranged chronologically, forming an independent time-series data stream for each vehicle, i.e., P time-series vehicle dynamic data (P being the total number of passing vehicles). For example, vehicle A's position at time t1 is (x1, y1) and speed is v1; its position at time t2 is (x2, y2) and speed is v2, and so on, forming the vehicle's time-series data. Since the clocks of different RSUs and OBUs may deviate, NTP (Network Time Protocol) is used to unify the time-series data of all vehicles to the same time base, eliminating time errors. For example, the time of all devices is synchronized to Coordinated Universal Time (UTC), and then the vehicle position data undergoes coordinate system transformation to ensure that the position coordinates of all vehicles are based on the same geographic coordinate system (such as WGS84 or the local projected coordinate system), solving the coordinate deviation problem between different sensors or positioning systems.

[0029] Preferably, based on time-series location data with a unified spatiotemporal reference, continuous and smooth vehicle trajectory curves are fitted using interpolation or smoothing algorithms (such as Kalman filtering). Based on time-series speed data, a speed-time curve for each vehicle is plotted, visually demonstrating the vehicle's acceleration and deceleration process. This generates a complete driving status for each vehicle, including its trajectory and speed change curve. Then, the driving status of all vehicles is mapped onto a digital map of the checkpoint section. Coordinate transformation aligns the vehicle trajectories with the actual road geometry. Specifically, the current position and historical trajectory of all vehicles are displayed in real-time on the map, using different colors or line thicknesses to distinguish vehicle types or driving states. Road condition data (such as waterlogged areas and construction zones) collected by environmental sensing units are dynamically labeled on the map. Key relative parameters between vehicles are calculated and displayed, such as following distance (the longitudinal distance between the vehicle in front and behind) and lateral offset (the lateral distance between vehicles in adjacent lanes), visually represented by arrows or numbers. The final result is a traffic situation map of the checkpoint, which visually displays the driving status and positional relationship of all vehicles within the checkpoint section, including the overall traffic flow, density and direction of the checkpoint section, as well as potential dangers such as insufficient vehicle spacing and abnormal lane changes.

[0030] Furthermore, step S400 also includes the traffic dynamic data including vehicle ID, GNSS positioning coordinates, speed, acceleration, braking signal and steering status.

[0031] Preferably, the Vehicle ID is a unique identifier for each vehicle, similar to a person's ID number, such as the Vehicle Identification Number (VIN). GNSS positioning coordinates refer to global navigation satellite systems, such as the common GPS (Global Positioning System) and BeiDou Navigation Satellite System, indicating the vehicle's specific location on the Earth's surface, usually presented in the form of latitude and longitude. Speed ​​refers to the instantaneous speed of the vehicle during travel, usually measured in kilometers per hour (km / h) or meters per second (m / s), used to determine if the vehicle is speeding and to analyze the traffic flow of a road segment. Acceleration is a physical quantity describing how quickly the vehicle's speed changes, measured in meters per second² (m / s²). 2 The system indicates whether a vehicle is accelerating or decelerating; the braking signal is the operating status signal of the vehicle's braking system, indicating whether the vehicle is braking; the steering status describes the vehicle's steering operation, including whether the vehicle is turning, the direction of steering (left or right), and the steering angle.

[0032] Step S500: Based on the road segment environmental data, perform trajectory prediction on the traffic situation map at the checkpoint to locate multiple vehicles at risk of collision.

[0033] Step S500 further includes step S510, constructing a trajectory prediction model based on an LSTM model; step S520, inputting the road segment environmental data and P vehicle driving situations into the trajectory prediction model to obtain P extended driving situations; step S530, connecting the P vehicle driving situations and P extended driving situations in the checkpoint traffic situation map to locate multiple collision risk nodes; step S540, extracting vehicle IDs from the multiple collision risk nodes to obtain the multiple collision risk vehicles.

[0034] Preferably, LSTM (Long Short-Term Memory) is a special type of recurrent neural network (RNN) that can effectively handle long-term dependencies in sequential data. Then, using historical traffic dynamic data (including vehicle position, speed, acceleration, etc.) and the corresponding time series as input, the LSTM model learns its patterns and rules to build a model that can predict the future trajectory of vehicles, i.e., to build a trajectory prediction model. For example, the model learns the speed variation of vehicles under different road sections and traffic conditions, as well as the turning probability at intersections, and thus predicts the vehicle's trajectory in the future based on the current vehicle status and environmental information.

[0035] Preferably, the collected checkpoint road segment environmental data (such as road conditions, traffic signal status, weather conditions, etc.) and the fitted P vehicle driving states (including driving trajectories, speed change curves, etc.) are provided as input to the trajectory prediction model. Among them, the road segment environmental data helps to understand the external environmental conditions of vehicle driving, while the vehicle driving states reflect the current motion state and historical trajectory information of the vehicle. Then, based on the input information, the trajectory prediction model uses the predictive capability of the LSTM model to predict the future driving trajectory of each vehicle, and obtains P extended driving states, which are used to represent the possible driving path and state changes of the vehicle in the future, such as the possible driving direction, speed change trend, and expected destination.

[0036] Preferably, the predicted P extended driving situations are connected with the existing P vehicle driving situations in the checkpoint traffic situation map. On the traffic situation map, the current driving trajectory of the vehicle and the predicted future trajectory are connected in a visual way to form a continuous trajectory display, so that traffic management personnel can intuitively see the current position of the vehicle and the possible future driving direction. Then, by analyzing the connected vehicle driving trajectory, nodes with potential collision risks are found. This includes comparing the trajectories of different vehicles based on vehicle speed, driving direction, distance, etc., to determine whether they will intersect or approach each other at some point in the future, thus creating a possibility of collision. For example, if the extended driving situations of two vehicles show that they will arrive at the same position at a certain intersection, this position may be a collision risk node.

[0037] Preferably, the IDs of relevant vehicles are extracted from the vehicle trajectories corresponding to multiple collision risk nodes, that is, vehicles with potential collision risks are identified, and finally a list of multiple collision risk vehicles is obtained, clearly indicating which vehicles are at risk of collision, so that corresponding measures can be taken in a timely manner, such as issuing an alarm to remind the driver to pay attention to safety, adjusting traffic signals to avoid collisions, or automatically taking braking or avoidance measures in autonomous vehicles, so as to reduce the probability of traffic accidents and ensure traffic safety.

[0038] Step S600: Match multiple risk warning instructions based on multiple traffic risk characteristics of the multiple collision risk vehicles.

[0039] Step S600 further includes step S610, performing driving status backtracking on the multiple collision risk vehicles along the multiple collision risk nodes to obtain multiple instantaneous risk driving statuses; step S620, matching and outputting multiple risk avoidance driving operations based on the driving characteristics of the multiple instantaneous risk driving statuses; step S630, matching warning instructions for the multiple risk avoidance driving operations and outputting the multiple risk warning instructions.

[0040] Preferably, starting from multiple identified collision risk nodes, the driving process of the collision risk vehicle is traced backward along the timeline before reaching the node. This involves examining the changes in the vehicle's state as it approaches the collision risk node, including changes in speed, acceleration, steering angle, and driving trajectory. By tracing back, the specific driving state information of each collision risk vehicle at the moment of approaching the collision risk node is obtained, thereby forming multiple instantaneous risk driving states. For example, a vehicle may be traveling at high speed and making a sharp turn when approaching a collision risk node, which is the instantaneous risk driving state of the vehicle, reflecting the actual driving condition of the vehicle before the moment of potential collision.

[0041] Preferably, each instantaneous risk driving situation is analyzed in depth to extract key driving characteristics, which may include whether the vehicle speed is too high, whether the steering is too abrupt, and whether the distance to the vehicle in front or surrounding vehicles is too close. For example, if a vehicle's instantaneous risk driving situation shows that its speed significantly exceeds the safe speed limit for that road segment and the distance to the vehicle in front is less than the safe braking distance, excessive speed and insufficient distance are two important driving characteristics. Then, based on the analyzed driving characteristics, combined with traffic rules and safe driving experience, corresponding risk avoidance driving operations are matched for each collision-risk vehicle. For example, if the vehicle speed is too high, the matched operation may be to immediately take braking measures to reduce the speed; if the steering is too abrupt, it may be necessary to appropriately straighten the steering wheel and adjust the steering angle to maintain vehicle stability; if the distance to the vehicle in front is too close, it may be necessary to simultaneously take braking and lane-changing operations to increase the safe distance; thereby correcting the vehicle's current dangerous driving state and reducing the risk of collision.

[0042] Preferably, for each risk-avoidance driving operation, it is converted into a specific warning instruction, which is used to issue clear instructions to the driver or relevant systems, informing them what measures need to be taken to avoid the risk. For example, for an operation that requires braking, the warning instruction may be "Brake immediately and reduce the speed to a safe range"; for a lane change operation, the warning instruction may be "Please observe the surrounding traffic conditions as soon as possible and safely change lanes to the right lane"; so that the driver or autonomous driving system can quickly understand and execute, and finally output multiple matched risk warning instructions.

[0043] In step S700, the multiple risk warning commands are sent to the multiple collision risk vehicles through the V2X communication link between the RSU sequence and the on-board OBU.

[0044] Step S700 further includes step S710, quantifying the multiple operational complexities of the multiple risk avoidance driving operations; step S720, invoking multiple collision prediction delays of the multiple instantaneous risk driving situations; step S730, evaluating the risk level of the multiple risk warning commands based on the weighted result of the multiple operational complexities and multiple collision prediction delays, and outputting multiple risk warning levels; step S740, sending the multiple risk warning commands to the multiple collision risk vehicles in a graded manner according to the multiple risk warning levels.

[0045] Preferably, multiple risk warning commands are sent to multiple vehicles at risk of collision via a V2X communication link between the RSU sequence and the on-board unit (OBU). These commands are then displayed on the vehicle's dashboard screen and through voice prompts, helping the driver take timely measures to avoid collisions and ensure driving safety. Specifically, operational complexity refers to the ease or difficulty of performing risk avoidance driving maneuvers and the level of skill required of the driver. For example, emergency braking is relatively simple and direct, with low operational complexity; however, continuous lane changing in complex traffic environments requires the driver to simultaneously observe vehicle dynamics in multiple directions and judge the appropriate timing for lane changes, thus increasing operational complexity. By considering the time, effort, and skill requirements of each operation, the complexity of each risk avoidance driving maneuver is assessed and quantified to more accurately understand its difficulty.

[0046] Preferably, collision prediction delay refers to the remaining time from the current moment to the possible collision. By analyzing and predicting information such as the vehicle's trajectory, speed, acceleration, and the state of surrounding vehicles, the time from which each collision-risk vehicle is likely to collide under its current driving situation is calculated. For example, if a vehicle is constantly decreasing in distance from the vehicle in front, and based on its current speed and acceleration, a rear-end collision is likely to occur within the next few seconds, this "few seconds" is the collision prediction delay for that vehicle. Then, the collision prediction delay corresponding to each instantaneous risk driving situation is obtained to understand the urgency faced by each collision-risk vehicle. The shorter the collision prediction delay, the closer the vehicle is to the possible collision time, and the more urgent the situation.

[0047] Preferably, different weights are assigned to operational complexity and collision prediction latency, and a weighted calculation is performed to obtain a weighted result that reflects the risk level corresponding to each risk warning instruction. Then, each risk warning instruction is evaluated to determine its risk level, which can be divided into different levels, such as high risk, medium risk, and low risk. For example, if the weighted result value corresponding to a risk warning instruction is large, it indicates that the operational complexity is high and the collision prediction latency is short, and the risk level of the risk warning instruction is high; conversely, if the weighted result value is small, the risk level is low. In this way, the risk level of multiple risk warning instructions is accurately evaluated, and the corresponding multiple risk warning levels are output.

[0048] Preferably, risk warning instructions are categorized according to the determined risk warning level. High-risk warning instructions are prioritized for the corresponding collision-risk vehicles and may employ stronger alerts, such as emergency voice prompts or flashing warning lights. Medium-risk warning instructions can be sent using standard voice or text prompts. Low-risk warning instructions can use milder alerts, such as displaying simple information on the dashboard. By sending risk warning instructions in a tiered manner, collision-risk vehicles can take appropriate measures based on their varying levels of risk, effectively reducing the probability of traffic accidents and improving traffic safety.

[0049] In the above text, refer to Figure 1 This paper describes in detail a method for analyzing traffic checkpoint monitoring data under vehicle-road cooperation according to an embodiment of the present invention. Next, we will refer to... Figure 2 A traffic checkpoint monitoring data analysis device under vehicle-road cooperation according to an embodiment of the present invention is described.

[0050] The traffic checkpoint monitoring data analysis device under vehicle-road cooperation according to embodiments of the present invention is used to solve the technical problems existing in the prior art, such as the detection scenarios not being able to match the actual driving conditions of users, the difficulty in dynamically monitoring the performance changes of sealing strips throughout their entire life cycle, resulting in the inability to provide early warning of potential failure risks and poor accuracy of sealing detection. It achieves the technical effect of improving detection accuracy and realizing early warning of sealing strip failure risks. Figure 2 As shown, the traffic checkpoint monitoring data analysis device under vehicle-road cooperation includes: RSU sequence deployment module 10, traffic dynamic data acquisition module 20, environmental data acquisition module 30, traffic dynamic data fusion module 40, trajectory prediction module 50, risk warning instruction matching module 60, and risk warning instruction sending module 70.

[0051] RSU sequence deployment module 10 is used to deploy RSU sequences extending along the checkpoint road segment, starting from the traffic checkpoint; traffic dynamic data acquisition module 20 is used to obtain multiple sets of traffic dynamic data by having the RSU sequences communicate with the on-board units (OBUs) of vehicles passing through the checkpoint road segment via V2X; environmental data acquisition module 30 is used to synchronously collect road segment environmental data of the checkpoint road segment through an environmental sensing unit; traffic dynamic data fusion module 40 is used to fuse the multiple sets of traffic dynamic data to obtain a checkpoint traffic situation map; trajectory prediction module 50 is used to perform trajectory prediction on the checkpoint traffic situation map based on the road segment environmental data to locate multiple collision risk vehicles; risk warning instruction matching module 60 is used to match multiple risk warning instructions based on multiple traffic risk characteristics of the multiple collision risk vehicles; risk warning instruction sending module 70 is used to send the multiple risk warning instructions to the multiple collision risk vehicles through the V2X communication link between the RSU sequences and the on-board units (OBUs).

[0052] The specific configuration of the RSU sequence deployment module 10 will be described in detail below. The RSU sequence deployment module 10 further includes: interactively obtaining the speed limit threshold and terrain features of the traffic checkpoint, calculating and outputting a baseline deployment interval based on the speed limit threshold; quantifying the terrain complexity based on the terrain features, and matching the length of the monitored road segment based on the terrain complexity; locating the checkpoint road segment centered on the traffic checkpoint and based on the length of the monitored road segment; and extending and deploying the RSU sequence on the checkpoint road segment according to the baseline deployment interval.

[0053] The specific configuration of the RSU sequence deployment module 10 will be described in detail below. The RSU sequence deployment module 10 further includes: updating the regional road segment deployment based on the terrain features to obtain multiple regional deployment intervals; interactively obtaining the traffic flow characteristics of the traffic checkpoint; compensating the baseline deployment interval based on the traffic flow characteristics to obtain an updated deployment interval; and extending the RSU sequence to the checkpoint road segment based on the updated deployment interval and the multiple regional deployment intervals.

[0054] The specific configuration of the traffic dynamic data fusion module 40 will be described in detail below. The traffic dynamic data fusion module 40 further includes: aggregating the multiple sets of traffic dynamic data based on vehicle IDs to obtain P time-series vehicle dynamic data for P passing vehicles; unifying the spatiotemporal reference of the P time-series vehicle dynamic data using the NTP protocol, and then fitting and outputting P vehicle driving situations; aligning the P vehicle driving situations in the checkpoint section through coordinate system transformation, and outputting the checkpoint traffic situation map.

[0055] The specific configuration of the traffic dynamic data fusion module 40 will be described in detail below. The traffic dynamic data fusion module 40 further includes: the traffic dynamic data includes vehicle ID, GNSS positioning coordinates, speed, acceleration, braking signal, and steering status.

[0056] The specific configuration of the trajectory prediction module 50 will be described in detail below. The trajectory prediction module 50 further includes: constructing a trajectory prediction model based on an LSTM model; inputting the road segment environmental data and P vehicle driving states into the trajectory prediction model to obtain P extended driving states; connecting the P vehicle driving states and the P extended driving states in the checkpoint traffic situation map to locate multiple collision risk nodes; and extracting vehicle IDs from the multiple collision risk nodes to obtain the multiple collision risk vehicles.

[0057] The specific configuration of the risk warning instruction matching module 60 will be described in detail below. The risk warning instruction matching module 60 further includes: tracing the driving status of the multiple collision risk vehicles along the multiple collision risk nodes to obtain multiple instantaneous risk driving statuses; matching and outputting multiple risk avoidance driving operations based on the driving characteristics of the multiple instantaneous risk driving statuses; matching warning instructions to the multiple risk avoidance driving operations, and outputting the multiple risk warning instructions.

[0058] The specific configuration of the risk warning instruction sending module 70 will be described in detail below. The risk warning instruction sending module 70 further includes: quantifying the operational complexity of the multiple risk avoidance driving operations; invoking multiple collision prediction delays of the multiple instantaneous risk driving situations; evaluating the risk level of the multiple risk warning instructions based on the weighted result of the multiple operational complexities and multiple collision prediction delays, and outputting multiple risk warning levels; and sending the multiple risk warning instructions to the multiple collision risk vehicles according to the multiple risk warning levels.

[0059] The traffic checkpoint monitoring data analysis device under vehicle-road cooperation provided in this embodiment of the invention can execute the traffic checkpoint monitoring data analysis method under vehicle-road cooperation provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method.

[0060] Although this application makes various references to certain modules in the apparatus according to the embodiments of this application, any number of different modules can be used and run on user terminals and / or servers. The various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of each functional unit are only for easy distinction between each other and are not intended to limit the scope of protection of this invention.

[0061] The specific embodiments described above do not constitute a limitation on the scope of protection of this application. Those skilled in the art should understand that various modifications, combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A method for analyzing traffic checkpoint monitoring data under vehicle-road cooperation, characterized in that, The method includes: Starting from traffic checkpoints, RSU sequences are deployed extending along the checkpoint road sections; The RSU sequence obtains multiple sets of traffic dynamic data by communicating with the on-board OBU of vehicles passing through the checkpoint section via V2X. The environmental sensing unit synchronously collects road environment data of the checkpoint section; By integrating the multiple sets of traffic dynamic data, a traffic situation map of the checkpoint is obtained; Based on the road segment environmental data, trajectory prediction is performed on the traffic situation map at the checkpoint to locate multiple vehicles at risk of collision, including: Constructing a trajectory prediction model based on the LSTM model; The road segment environmental data and P vehicle driving patterns are input into the trajectory prediction model to obtain P extended driving patterns. By connecting the P vehicle driving situations and P extended driving situations in the traffic situation map at the checkpoint, multiple collision risk nodes are located; Vehicle IDs are extracted from the multiple collision risk nodes to obtain the multiple collision risk vehicles; Multiple risk warning instructions are matched based on multiple traffic risk characteristics of the multiple vehicles at risk of collision. The multiple risk warning commands are sent to the multiple collision-risk vehicles via the V2X communication link between the RSU sequence and the on-board OBU. The method of matching multiple risk warning instructions based on multiple traffic risk characteristics of the multiple collision-risk vehicles includes: By backtracking the driving status of the multiple collision risk vehicles along the multiple collision risk nodes, multiple instantaneous risk driving statuses are obtained. Based on the driving characteristics of the multiple instantaneous risk driving situations, multiple risk avoidance driving operations are matched and output; Match the multiple risk avoidance driving operations with warning commands and output the multiple risk warning commands; The method of sending the multiple risk warning commands to the multiple collision-risk vehicles via the V2X communication link between the RSU sequence and the on-board unit (OBU) includes: Quantify the operational complexity of the various risk avoidance driving operations; Multiple collision prediction delays are invoked for the aforementioned multiple instantaneous risk driving situations; Based on the weighted results of the multiple operational complexities and multiple collision prediction delays, the risk levels of the multiple risk warning commands are evaluated, and multiple risk warning levels are output. Based on the multiple risk warning levels, the multiple risk warning instructions are sent to the multiple collision risk vehicles in a tiered manner.

2. The traffic checkpoint monitoring data analysis method under vehicle-road cooperation as described in claim 1, characterized in that, Starting from a traffic checkpoint, a series of RSUs are deployed extending along the checkpoint road segment. The method includes: The speed limit threshold and terrain features of the traffic checkpoint are obtained interactively. The baseline deployment interval is calculated and output based on the speed limit threshold. After quantifying the terrain complexity based on the terrain features, the length of the monitored road segment is matched according to the terrain complexity. Using the traffic checkpoint as the center, the checkpoint road segment is located based on the length of the monitored road segment; The RSU sequence is deployed at the checkpoint section according to the baseline deployment interval.

3. The traffic checkpoint monitoring data analysis method under vehicle-road cooperation as described in claim 2, characterized in that, The method includes: Deploying the RSU sequence at the checkpoint section according to the baseline deployment interval. Based on the terrain features, regional road segment deployment is updated to obtain multiple regional deployment intervals; The traffic flow characteristics of the traffic checkpoint are obtained interactively; The updated deployment interval is obtained by compensating the baseline deployment interval based on the traffic flow characteristics. Based on the update deployment interval and multiple regional deployment intervals, the RSU sequence is extended and deployed on the checkpoint section.

4. The traffic checkpoint monitoring data analysis method under vehicle-road cooperation as described in claim 1, characterized in that, By integrating the multiple sets of traffic dynamic data, a traffic situation map at the checkpoint is obtained. The method includes: Based on the vehicle ID, the multiple sets of traffic dynamic data are aggregated to obtain P time-series vehicle dynamic data for P passing vehicles. After unifying the spatiotemporal reference of the P time-series vehicle dynamic data using the NTP protocol, the driving status of the P vehicles is fitted and output. The traffic situation of the P vehicles is spatially aligned by coordinate system transformation at the checkpoint section, and the traffic situation map of the checkpoint is output.

5. The traffic checkpoint monitoring data analysis method under vehicle-road cooperation as described in claim 4, characterized in that, The traffic dynamic data includes vehicle ID, GNSS positioning coordinates, speed, acceleration, braking signal, and steering status.

6. A traffic checkpoint monitoring data analysis device under vehicle-road cooperation, characterized in that, The device is used to implement the traffic checkpoint monitoring data analysis method under vehicle-road cooperation as described in any one of claims 1 to 5, and the device comprises: The RSU sequence deployment module is used to deploy RSU sequences starting from traffic checkpoints and extending to the checkpoint road sections. The traffic dynamic data acquisition module is used to obtain multiple sets of traffic dynamic data by having the RSU sequence communicate with the on-board OBU of vehicles passing through the checkpoint section via V2X. The environmental data acquisition module is used to synchronously collect road environmental data of the checkpoint section through the environmental sensing unit; The traffic dynamic data fusion module is used to fuse the multiple sets of traffic dynamic data to obtain a traffic situation map at the checkpoint. The trajectory prediction module is used to combine the road segment environmental data with the traffic situation map at the checkpoint to predict trajectories and locate multiple vehicles at risk of collision. The risk warning instruction matching module is used to match multiple risk warning instructions based on multiple traffic risk characteristics of the multiple collision risk vehicles; The risk warning instruction sending module is used to send the multiple risk warning instructions to the multiple collision risk vehicles through the V2X communication link between the RSU sequence and the on-board OBU.

Images