Urban and rural planning road safety monitoring method and system

Abstract

The invention discloses an urban and rural planning road safety monitoring method and system in the technical field of road safety. The system comprises a plurality of cameras used for collecting image data; a plurality of rain gauges used for collecting real-time rainfall information; and the road analysis module is used for analyzing the probability of fatigue driving and dangerous driving of the driver caused by straight roads and curved roads with different length distances on the road. And the ponding analysis module is used for analyzing the probability of congestion and accidents of the road caused by the road ponding amount and the road ponding dissipation speed. And the obstacle analysis module is used for analyzing the probability that obstacles appear on the road cause congestion and accidents on the monitored road. And the traffic flow analysis module is used for analyzing the probability of congestion and accidents of the monitored road caused by different traffic flows of the road. The method is scientific and reasonable, data integrity and accuracy are improved by optimizing data acquisition, processing and transmission mechanisms, road safety risks are evaluated more accurately, early warning information is sent out in time, and road traffic safety is guaranteed.

Description

Technical Field

[0001] The present invention belongs to the technical field of road safety, and specifically relates to a method and system for monitoring road safety in urban and rural planning. Background Art

[0002] With the acceleration of urbanization, roads, as an important part of urban infrastructure, are directly related to the overall operation quality of the city and the quality of life of residents due to their safety and traffic efficiency. In order to cope with the increasingly complex traffic environment and the increasing demand for road safety management, the urban and rural planning road safety monitoring system came into being. The system integrates a variety of sensor devices, analysis modules and communication technologies to achieve real-time monitoring, analysis and early warning of road safety conditions.

[0003] Although the urban and rural planning road safety monitoring methods and systems have achieved remarkable results, there are still some problems in practical applications. Due to the complex and changeable road environment, sensor equipment may be subject to various interferences and influences when collecting data, resulting in insufficient data integrity and accuracy, which will affect subsequent data analysis and risk assessment results.

[0004] In summary, the lack of data integrity and accuracy collected by traditional urban and rural planning road safety monitoring methods and systems has become a problem that technicians in this field need to solve urgently. Therefore, it is necessary to propose a method and system for urban and rural planning road safety monitoring. Summary of the invention

[0005] In order to solve the above problems, the purpose of the present invention is to provide a method and system for urban and rural planning road safety monitoring, which improves data integrity and accuracy by optimizing data collection, processing and transmission mechanisms, thereby more accurately assessing road safety risks and issuing early warning information in a timely manner to ensure road safety.

[0006] In order to achieve the above-mentioned purpose, the technical solution of the present invention is as follows: a road safety monitoring system for urban and rural planning, including cameras for collecting image data of vehicles and drivers on the monitoring road, and the cameras are deployed in sections according to preset distances.

[0007] Rain gauges are used to collect real-time rainfall information on monitored roads. Rain gauges are deployed in preset areas.

[0008] The road analysis module is used to analyze and monitor the probability of driver fatigue and dangerous driving caused by straight roads and curves of different lengths on the road. Big data analysis is combined with wind speed, temperature, humidity, road type, drainage efficiency, and straight and curved road distribution factors to establish a water dissipation speed prediction model. The water dissipation speed prediction model predicts the time required for the natural dissipation of water in the waterlogged area and whether human intervention is required.

[0009] The water accumulation analysis module is used to analyze the amount of water accumulated on the monitored roads and the speed at which water accumulates on the roads to determine the probability of congestion and accidents on the monitored roads.

[0010] The obstacle analysis module is used to monitor the occurrence of road obstacles and the frequency of obstacle occurrence, and is also used to analyze the probability of congestion and accidents on the monitored roads caused by the occurrence of obstacles.

[0011] The traffic flow analysis module is used to analyze the probability of congestion and accidents on the monitored roads caused by different traffic flows on the monitored roads.

[0012] The communication and collaboration module is used for real-time communication and collaboration with the traffic police department, road maintenance department and emergency center.

[0013] Furthermore, the road analysis module combines historical accident data, road design parameters, driver real-time status and vehicle speed information to establish a fatigue driving and dangerous driving risk prediction model. The road analysis module provides the driver with warning information and recommends safe driving routes based on the fatigue driving and dangerous driving risk prediction model.

[0014] Furthermore, the obstacle analysis module automatically detects obstacles on the road through camera image processing and machine learning algorithms, including accident vehicles, fallen rocks and fallen trees, and immediately generates a warning that is transmitted to the communication collaboration module.

[0015] Furthermore, the traffic flow analysis module integrates the intelligent traffic unit, and based on the real-time collected traffic flow data and the number of congestion occurrences, it dynamically notifies the relevant departments through the communication and collaboration module to adjust the timing of traffic lights and optimize traffic flow.

[0016] Furthermore, the waterlogging analysis module integrates a GIS technology unit, combines real-time rainfall data, road topography information, road waterlogging volume, and road water dissipation rate, predicts and displays road waterlogging areas, and sends cleanup instructions to relevant departments or issues early warning information to the public through the communication and collaboration module.

[0017] Furthermore, cameras and rain gauges are customized for development and deployment by dynamically adjusting the needs of the cameras and rain gauges based on the climate characteristics, traffic flow patterns, road aging, and future development plans of the installation area.

[0018] Furthermore, the fatigue driving and dangerous driving risk prediction model in the road analysis module has self-learning capabilities. The self-learning capabilities dynamically adjust the parameters of the dangerous driving risk prediction model based on multi-source data such as historical data, social media, weather forecasts, and news reports.

[0019] Furthermore, the communication and collaboration module adopts a redundant design and a failover mechanism, which allows it to continue to operate and provide communication services when some modules and networks fail. At the same time, through big data analysis and machine learning algorithms, it assesses the scope, severity and response strategies of emergencies, and automatically sends task instruction suggestions and coordination recommendations to relevant departments.

[0020] Furthermore, the communication and collaboration module will archive and store monitoring data and assessment results, regularly analyze data trends, build a comprehensive data visualization and analysis platform, and integrate and display monitoring data, analysis results, warning information, and emergency response record data.

[0021] A method for monitoring road safety in urban and rural planning, comprising the following steps:

[0022] Step 1: Data collection: using several cameras and rain gauges to collect road images, rainfall, obstacles and traffic flow data in real time;

[0023] Step 2: Data analysis: the data collected in step 1 is transmitted for image recognition, rainfall analysis, road condition assessment, obstacle detection and traffic flow statistics;

[0024] Step 3: Warning generation: Based on the analysis results of step 2, road safety risks are assessed, including fatigue driving, dangerous driving, water accumulation, obstacles and congestion risks, and corresponding warning information is generated;

[0025] Step 4: Auxiliary adjustment. According to the warning information in step 3, the emergency response mechanism is triggered. The emergency response mechanism includes adjusting traffic signals, notifying relevant departments to clear accumulated water or obstacles, and issuing safety tips to the public. The collected data and the emergency response mechanism assist planners in specifying road design and traffic management strategies.

[0026] The following principles and beneficial effects are achieved by adopting the above scheme:

[0027] 1. The present invention uses high-definition cameras, rain gauges and other sensor equipment to collect key data such as road images, rainfall, obstacles and traffic flow in real time and comprehensively, providing a basis for subsequent accurate analysis. The road analysis module, water accumulation analysis module, obstacle analysis module and traffic flow analysis module use advanced algorithms and models to conduct in-depth mining and analysis of the collected data. Through multi-source data collection and intelligent data analysis, the integrity and accuracy of road safety monitoring data are significantly improved, providing more reliable data support for risk assessment and early warning.

[0028] 2. The system of the present invention can evaluate road safety risks in real time and generate early warning information. The communication and collaboration module ensures that the early warning information can be transmitted to the traffic police department, road maintenance department and emergency center in a timely manner, and triggers the emergency response mechanism, such as adjusting traffic signals, clearing accumulated water or obstacles, issuing safety tips, etc. The real-time early warning and emergency response mechanism can quickly respond to road safety incidents, reduce the possibility and scope of accidents, and ensure road safety.

[0029] 3. The fatigue driving and dangerous driving risk prediction model in the present invention has self-learning and optimization capabilities, and can continuously adjust the algorithm model according to the actual operation situation to improve the accuracy of prediction and evaluation. The redundant design and failover mechanism of the communication cooperation module ensure the stability and reliability of the system

[0030] 4. The data collected by the system and the emergency response mechanism of the present invention provide valuable reference information for planners, which helps to formulate more scientific and reasonable road design and traffic management strategies and improve the overall efficiency of the urban transportation system.

[0031] 5. The present invention enhances the public's road safety awareness by issuing safety tips and warning information to the public, prompting drivers and pedestrians to pay more attention to traffic safety and form good traffic habits. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 4 is a system flow chart of an embodiment of the present invention.

[0033] Figure 2 The figure is a flow chart of a method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0034] The following is further described in detail through specific implementation methods:

[0035] Example 1

[0036] Basically as attached Figure 1 As shown: A road safety monitoring system for urban and rural planning includes several cameras, several rain gauges and the following modules:

[0037] Cameras are used to collect image data of vehicles and drivers on the monitored roads, and are deployed in sections according to preset distances. Rain gauges are used to collect real-time rainfall information on monitored roads, and are deployed in preset areas. Cameras and rain gauges are customized for development and deployment based on the climate characteristics, traffic flow patterns, road aging, and future development plans of the installation area, and the needs of cameras and rain gauges are dynamically adjusted.

[0038] Road analysis module: used to analyze and monitor the probability of drivers driving fatigued and driving dangerously due to straight roads and curves of different lengths on the road; combined with historical accident data, road design parameters, driver's real-time status and vehicle speed information, a fatigue driving and dangerous driving risk prediction model is established. The road analysis module provides drivers with warning information and recommends safe driving routes based on the fatigue driving and dangerous driving risk prediction model. The fatigue driving and dangerous driving risk prediction model has self-learning capabilities. The self-learning capability is based on historical data, social media, weather forecasts, and news reports. Multi-source data dynamically adjusts the parameters of the dangerous driving risk prediction model. The logical relationship of the road analysis module is as follows:

[0039] Data collection and integration

[0040] Road characteristic data: including road length, ratio of straight roads to curves, road design parameters such as slope, curvature, number of lanes, and lighting conditions.

[0041] Historical accident data: Analyze the types and frequency of accidents that occurred on specific roads and under specific conditions such as weather and time, especially those related to fatigue and dangerous driving.

[0042] Real-time driver status: The camera monitors the driver's blinking frequency, facial expressions, and head posture to assess their fatigue level; at the same time, the vehicle status data such as steering wheel operation frequency and brake / accelerator usage are used to analyze whether the driving behavior is abnormal.

[0043] Vehicle speed information: Obtain vehicle speed in real time, and combine road speed limits and traffic flow to assess the possibility of dangerous driving behaviors such as speeding.

[0044] External data sources: For example, social media sentiment analysis may affect driver emotions, weather forecasts may affect driving conditions, and news reports may mention traffic conditions or accidents on specific roads.

[0045] Feature extraction and modeling

[0046] Feature engineering: Extract key features from the above data, such as road complexity index, driver fatigue index, and driving behavior abnormality index.

[0047] Model construction: Use deep learning algorithms such as logistic regression, random forest, and neural network, combined with historical data to build a fatigue driving and dangerous driving risk prediction model. The fatigue driving and dangerous driving risk prediction model predicts the probability of fatigue driving and dangerous driving based on input features.

[0048] Risk assessment and early warning

[0049] Real-time assessment: During vehicle driving, relevant data is collected and processed in real time, input into the fatigue driving and dangerous driving risk prediction model, and the probability of fatigue driving and dangerous driving under current conditions is calculated.

[0050] Threshold judgment: Set a risk threshold. When the predicted risk exceeds the threshold, the early warning mechanism is triggered.

[0051] Warning information generation: Generate specific warning information based on risk assessment results, such as "Please take a rest and avoid driving while fatigued" or "The current road section is dangerous, please slow down."

[0052] Safe driving suggestions: Combined with the data from the road analysis module, it provides drivers with safe driving route suggestions to avoid high-risk sections.

[0053] Waterlogging analysis module: used to analyze the probability of congestion and accidents on monitored roads caused by the amount of waterlogging on the monitored roads and the speed at which waterlogging dissipates; it also integrates a GIS technology unit, combines real-time rainfall data, road terrain information, the amount of waterlogging on the roads and the speed at which waterlogging dissipates on the roads, predicts and displays road waterlogging areas, and then uses big data analysis to combine wind speed, temperature, humidity, road type, drainage efficiency, and the distribution of straight and curved roads to establish a waterlogging dissipation speed prediction model. The waterlogging dissipation speed prediction model predicts the time required for the natural dissipation of waterlogging in the waterlogged area and whether human intervention is required, providing a scientific basis for road cleaning and restoring traffic, and sending cleaning instructions to relevant departments or issuing early warning information to the public through the communication collaboration module. The logical relationship of the waterlogging analysis module is as follows:

[0054] Data collection and integration

[0055] Real-time rainfall data: Get real-time rainfall data from weather stations or sensor networks.

[0056] Road terrain information: Use GIS technology units to obtain road elevation models, slopes, curvatures and other terrain data.

[0057] Road water accumulation: The amount of water accumulation is monitored in real time through water level sensors installed on the road.

[0058] Speed ​​of water dissipation: In the initial stage, it may be estimated through historical data or empirical values, and then adjusted based on real-time data.

[0059] Other environmental factors: including wind speed, temperature, humidity, etc., which have an important impact on the speed at which accumulated water dissipates.

[0060] Road type and drainage efficiency: Different road types such as asphalt roads, cement roads, permeable brick roads and drainage systems such as drainage ditches and sewers have different drainage efficiencies.

[0061] Distribution of straight and curved roads: The distribution of straight and curved roads may affect the accumulation and dissipation of water.

[0062] Flooding area prediction

[0063] Application of GIS technology: Combine real-time rainfall data and road terrain information, and use GIS's raster calculation, overlay analysis and other functions to predict and display road waterlogging areas.

[0064] Analysis of waterlogging scope and depth: Through GIS spatial analysis tools, low-lying areas are extracted and the scope and depth of waterlogging are calculated.

[0065] Prediction model of water dissipation rate

[0066] Model construction: Using big data analysis technology, combined with factors such as wind speed, temperature, humidity, road type, drainage efficiency, and distribution of straight and curved roads, a water dissipation speed prediction model is established.

[0067] Parameter setting: The initial parameters of the model are set through historical data and experimental data, including the influence coefficient of different environmental factors on the speed of water dissipation.

[0068] Real-time adjustment: Dynamically adjust model parameters based on real-time monitored water accumulation and dissipation rate to improve prediction accuracy.

[0069] Congestion and accident probability calculation

[0070] Analysis of the impact of waterlogging: Based on the scope, depth and dissipation speed of the waterlogged area, analyze the impact of waterlogging on road traffic, including reduced vehicle speed and decreased road capacity.

[0071] Congestion and accident risk assessment: Combine historical accident data and road traffic flow data to assess road congestion and accident risks caused by waterlogging.

[0072] Probability calculation: Based on the above analysis, statistical or machine learning algorithms are used to calculate the probability of congestion and accidents on the monitored roads.

[0073] Early warning and decision support

[0074] Warning information release: When it is predicted that a waterlogged area may cause road congestion or accidents, cleanup instructions are sent to relevant departments or warning information is released to the public through the communication collaboration module.

[0075] Obstacle analysis module: used to monitor the occurrence and frequency of obstacles on the road, and also used to analyze the probability of congestion and accidents on the monitored road caused by the occurrence of obstacles; through camera image processing and machine learning algorithms, it automatically detects obstacles on the road, including accident vehicles, fallen rocks and fallen trees, and immediately generates an early warning and transmits it to the communication collaboration module. The logical relationship of the obstacle analysis module is as follows:

[0076] Obstacle Detection

[0077] Camera image processing: Real-time images are captured by cameras on the road and pre-processed, such as grayscale, denoising, edge detection, etc., to improve image quality.

[0078] Machine learning models: Apply trained machine learning models such as convolutional neural networks (CNNs) to the processed images for obstacle recognition. These models can automatically identify obstacles such as accident vehicles, fallen rocks, and fallen trees.

[0079] Real-time detection: The system runs in real time, constantly detecting obstacles on the road and recording their location, size, type and other information.

[0080] Obstacle frequency analysis

[0081] Data collection: Collect obstacle data detected over a period of time, including the time, location, and type of obstacles.

[0082] Frequency statistics: Statistical analysis is performed on the collected data to calculate the frequency of occurrence of different types of obstacles in different time periods and on different road sections.

[0083] Congestion and accident risk assessment

[0084] Analysis of influencing factors: Analyze the impact of obstacles on road traffic, including vehicle speed, road capacity, driver reaction time, etc. At the same time, other factors such as road type, traffic flow, weather conditions, etc. are considered.

[0085] Parameter adjustment: Based on new test data and accident records, parameters are continuously adjusted and optimized to improve prediction accuracy.

[0086] Probability calculation

[0087] Real-time prediction: After an obstacle is detected, relevant information about the obstacle is immediately input into the machine prediction algorithm to calculate the probability of the obstacle causing road congestion and accidents under the current circumstances.

[0088] Threshold judgment: Set a risk threshold. When the predicted risk probability exceeds the threshold, the system considers that there is a high risk of congestion and accidents.

[0089] Warning transmission

[0090] Warning generation: Once a higher risk probability is predicted, the system immediately generates warning information, including the type of obstacle, location, predicted risk level, etc.

[0091] Communication and collaboration: The warning information is transmitted to the communication and collaboration module so that relevant departments and drivers can be notified in time to take necessary measures to deal with potential congestion and accident risks.

[0092] Traffic flow analysis module: used to analyze the probability of congestion and accidents on the monitored roads due to different traffic flows; at the same time, it integrates the intelligent traffic unit, and dynamically notifies the relevant departments to adjust the traffic light timing and optimize the traffic flow through the communication and collaboration module based on the real-time collected traffic flow data and the number of congestion occurrences. The logical relationship of the traffic flow analysis module is as follows:

[0093] Data Collection

[0094] Real-time traffic flow data: Through cameras installed on the road combined with image processing technology, traffic flow data is collected in real time, including the number of vehicles, speed, type, etc.

[0095] Congestion Occurrences: Record the number of congestion events that occurred on the monitored roads and their duration. These data can be obtained through traffic monitoring systems or manual reports.

[0096] Other relevant data: such as road type, number of lanes, intersection layout, weather conditions, etc., which may affect the relationship between traffic flow and congestion.

[0097] Data preprocessing

[0098] Data cleaning: remove outliers, duplicate data, etc. to ensure data accuracy and reliability.

[0099] Data integration: Integrate data from different sources into a unified dataset for subsequent analysis.

[0100] Congestion and accident risk analysis

[0101] Correlation analysis: Use statistical methods to analyze the correlation between traffic flow and the number of congestion occurrences to determine the degree of association between them.

[0102] Historical data analysis: Review historical data to identify the relationship patterns between traffic flow and congestion and accidents in different time periods, such as morning and evening peaks and holidays.

[0103] Modeling and forecasting

[0104] Model selection: Select an appropriate model based on data characteristics and analysis requirements, such as time series analysis, regression analysis, random forest, neural network, etc.

[0105] Model training: Use historical data to train the model and let the model learn the relationship between traffic flow, congestion and accidents.

[0106] Parameter adjustment: The model parameters are adjusted through the cross-validation method to improve the prediction accuracy of the model.

[0107] Real-time prediction: The traffic flow data collected in real time is input into the model to predict the probability of congestion and accidents on the monitored roads in the current or future period.

[0108] Decision support

[0109] Threshold setting: Set the thresholds for congestion and accident risks based on actual needs.

[0110] Warning generation: When the predicted risk probability exceeds the set threshold, a warning message is generated.

[0111] Dynamic adjustment: The warning information is sent to relevant departments through the communication and collaboration module, and measures such as adjusting the timing of traffic lights and increasing police patrols are recommended to optimize traffic flow and reduce congestion and accident risks.

[0112] Communication and collaboration module: used for real-time communication and collaboration with the traffic police department, road maintenance department and emergency center to ensure response and coordination in the event of an emergency. With redundant design and failover mechanism, some modules and networks continue to operate and provide communication services when failures occur. At the same time, through big data analysis and machine learning algorithms, the scope, severity and response strategies of emergencies are evaluated, and task instruction suggestions and coordination suggestions are automatically sent to relevant departments. After the communication and collaboration is completed, the communication and collaboration module will archive and store the monitoring data and evaluation results, regularly analyze data trends, build a comprehensive data visualization and analysis platform, and integrate and display monitoring data, analysis results, warning information and emergency response record data. The logical relationship of the communication and collaboration module is as follows:

[0113] Emergency Identification and Assessment

[0114] Real-time communication: Through real-time communication with traffic police departments, road maintenance departments and emergency centers, emergency situations such as traffic accidents, road congestion, natural disasters, etc. can be quickly identified.

[0115] Data analysis: Use big data analysis and machine learning algorithms to conduct preliminary assessments of emergencies. This includes analyzing the location, scope, severity, and possible development trends of the emergency.

[0116] Impact Scope and Severity Assessment

[0117] Geospatial analysis: Using GIS technology, the location of the emergency is combined with geospatial information such as road networks, population density, and distribution of medical resources to assess the scope of impact.

[0118] Dynamic simulation: Through simulation algorithms, predict the possible development trajectory and spread of emergencies, as well as the secondary disasters or impacts that may be caused.

[0119] Comprehensive assessment: Combined with the above information, comprehensively assess the severity of the emergency, including casualties, property losses, traffic impacts, etc.

[0120] Response strategy formulation

[0121] Knowledge base and case library: The communication and collaboration module maintains a knowledge base and case library, which stores historical emergency response strategies, successful cases and best practices.

[0122] Intelligent recommendation: Based on the assessment results of the emergency situation, similar cases are retrieved from the knowledge base and case base, and corresponding response strategies are intelligently recommended.

[0123] Expert system: Combine built-in expert system or remote expert consultation to further review and optimize recommended strategies.

[0124] Mission instructions and coordination proposal generation.

[0125] Task allocation: Based on the assessment results and response strategies, task instructions are automatically generated to clarify the responsibilities and tasks of each department. For example, the traffic police department is responsible for traffic diversion, the road maintenance department is responsible for clearing road obstacles, and the emergency center is responsible for treating the wounded.

[0126] Coordination Recommendations: Make cross-departmental coordination recommendations to ensure seamless collaboration among departments to jointly respond to emergencies.

[0127] Automatic sending: Through the communication and collaboration module, task instructions and coordination suggestions are automatically sent to relevant departments to ensure timely delivery and response of information.

[0128] Monitoring and feedback

[0129] Continuous monitoring: During the emergency response process, continuously monitor the on-site situation and collect the latest data and information.

[0130] Effect evaluation: Based on the monitoring results, evaluate the implementation effect of the response strategy and adjust and optimize the strategy in a timely manner.

[0131] Feedback loop: Feedback the experience and lessons learned from the processing process to the communication and collaboration module to optimize the algorithm and improve future response capabilities.

[0132] Data Archiving and Visualization

[0133] Data archiving: Archive and store monitoring data, assessment results, warning information and emergency response record data to ensure data integrity and traceability.

[0134] Data Visualization: Build a comprehensive data visualization and analysis platform to transform complex data into intuitive charts and graphs for easy understanding and analysis.

[0135] Regular analysis: Regularly analyze data trends to identify potential problems and patterns, and provide a scientific basis for future emergency responses.

[0136] Specific implementation steps:

[0137] Consider a major traffic artery in a large city. This road contains multiple straight roads, curves, and intersections and is often affected by seasonal rainfall, posing a risk of waterlogging.

[0138] Several cameras on both sides of the road began to capture the movement of vehicles, driver behavior, and obstacles on the road in real time. For example, the camera captured several vehicles slowing down and igniting their hazard lights, which may be the initial signs of water accumulation or obstacles ahead. Several rain gauges installed along the road began to record real-time rainfall and transmit data to the water accumulation analysis module.

[0139] Road analysis module: Based on camera and vehicle sensor data, combined with historical accident data and road design parameters, the road analysis module found that vehicle speeds generally dropped at a certain bend and drivers showed signs of fatigue. It then issued a fatigue driving warning to drivers in the area and advised them to take a rest or choose other safe routes.

[0140] The road analysis module found that the speed of vehicles on a straight road increased generally, and the driver's status showed signs of dangerous driving. Due to the long-term driving on the straight road, the driver lacked sensory stimulation and the reduced difficulty of driving on the straight road, which led to inattention, which eventually led to slow driving reaction or dangerous driving behavior. Therefore, a long straight road warning or dangerous driving warning was issued to the drivers in the area, and they were advised to pay more attention and avoid dangerous driving behavior.

[0141] Waterlogging analysis module: Combining rain gauge data, waterlogging dissipation rate prediction model and GIS terrain information, the waterlogging analysis module predicts that several low-lying areas will soon form waterlogging areas, and immediately sends cleanup instructions to the road maintenance department through the communication collaboration module. At the same time, it issues waterlogging warning information to the public and guides vehicles to detour.

[0142] Obstacle analysis module: The camera captured a rear-end collision, and the accident vehicle occupied part of the lane, forming an obstacle. The obstacle analysis module quickly identified and generated warning information, and notified the traffic police and emergency center to handle it through the communication collaboration module. The obstacle analysis module also recorded the time and location of the obstacle to obtain the frequency of obstacles at the preset time and preset road section. The frequency of obstacles is fed back to the planner for subsequent road safety optimization.

[0143] Traffic flow analysis module: The intelligent traffic unit analyzes that due to waterlogging and accidents, the traffic volume on this road section has increased sharply and serious congestion is about to occur. Therefore, the traffic flow analysis module notifies the traffic police department through the communication collaboration module to adjust the timing of traffic lights and give priority to vehicles on this road section to alleviate congestion.

[0144] Communication and collaboration module: Throughout the entire process, the communication and collaboration module serves as the hub to ensure data flow and command transmission between modules. At the same time, through big data analysis and machine learning algorithms, it assesses the impact, severity and response strategies of emergencies, and automatically sends task instruction suggestions and coordination suggestions to relevant departments. The communication and collaboration module maintains real-time communication with the traffic police department, road maintenance department and emergency center to ensure rapid response and coordinated handling of emergencies.

[0145] After the incident is handled, the communication and collaboration module archives and stores the monitoring data and evaluation results. Build a comprehensive data visualization and analysis platform to display monitoring data, analysis results, warning information and emergency response records. Provide intuitive decision support for traffic managers, including road design optimization, traffic signal layout adjustment, public transportation route planning, etc. Regularly analyzing these data and assisting planners in optimizing the design direction of the road can help optimize the accuracy of fatigue driving and dangerous driving risk prediction models and improve the overall efficiency of the system.

[0146] Example 2

[0147] Basically as attached Figure 2 As shown in the figure, different from the above-mentioned embodiment, a method for monitoring road safety in urban and rural planning includes the following steps:

[0148] Step 1: Data collection: using several cameras and rain gauges to collect road images, rainfall, obstacles and traffic flow data in real time;

[0149] Step 2: Data analysis: the data collected in step 1 is transmitted for image recognition, rainfall analysis, road condition assessment, obstacle detection and traffic flow statistics;

[0150] Step 3: Warning generation: Based on the analysis results of step 2, road safety risks are assessed, including fatigue driving, dangerous driving, water accumulation, obstacles and congestion risks, and corresponding warning information is generated;

[0151] Step 4: Auxiliary adjustment. According to the warning information in step 3, the emergency response mechanism is triggered. The emergency response mechanism includes adjusting traffic signals, notifying relevant departments to clear accumulated water or obstacles, and issuing safety tips to the public. The collected data and the emergency response mechanism assist planners in specifying road design and traffic management strategies.

[0152] Specific implementation steps:

[0153] Suppose a busy traffic artery in a city is often affected by rainy and snowy weather changes and traffic accidents, resulting in increased road safety risks. In order to improve road safety, the city decided to adopt this urban and rural planning road safety monitoring method.

[0154] Step 1: Data Collection

[0155] Multiple high-definition cameras installed along the road capture real-time road images, including vehicle driving status, driver behavior, road obstacles, etc. Several rain gauges deployed at key locations record rainfall in real time, providing data support for subsequent waterlogging analysis.

[0156] Step 2: Data Analysis

[0157] Using advanced image processing technology, the images captured by the camera are automatically analyzed to identify the driver's fatigue and dangerous driving behavior, including speeding and illegal lane changes. According to the data from the rain gauge, the water accumulation on the road is analyzed to predict the water accumulation area and the speed of water dissipation. Combining the results of image recognition and rainfall analysis, the overall condition of the road is evaluated, including the driving safety of straight roads and curves. Through image recognition technology, obstacles on the road are automatically detected, such as accident vehicles, fallen rocks, fallen trees, etc. The number of vehicles on the road and the driving speed are counted to evaluate the risk of congestion.

[0158] Step 3: Generate warning

[0159] When the driver is detected to be fatigued or engaging in dangerous driving behaviors such as speeding or illegal lane changes, an early warning message is generated to remind the driver to take a rest or sound an alarm through a mobile device. When water is predicted to accumulate on the road, a water accumulation early warning message is issued to the public, and the road maintenance department is notified to prepare for cleanup. When an obstacle is detected on the road, an early warning message is immediately generated, and the traffic police are notified to deal with it. When the traffic volume reaches a certain level and congestion is predicted, congestion early warning information is issued to the public through traffic broadcasts, navigation software and other channels.

[0160] Step 4: Auxiliary adjustment

[0161] According to the traffic statistics and congestion prediction results, the timing of traffic lights is dynamically adjusted to relieve congestion. Instructions are sent to the road maintenance department to clear water or obstacles, and traffic accidents are reported to the traffic police department. Road safety tips are issued to the public through social media, traffic broadcasts and other channels to guide drivers to drive safely. The collected data and the results of the emergency response mechanism provide important references for the formulation of road design and traffic management strategies, and assist planners in optimizing road layout and traffic management plans.

[0162] The above is only an embodiment of the present invention. The common sense such as the known specific structure and characteristics in the scheme is not described in detail here. The ordinary technicians in the relevant field know all the common technical knowledge in the technical field of the invention before the application date or priority date, can obtain all the existing technologies in the field, and have the ability to apply the conventional experimental means before that date. The ordinary technicians in the relevant field can improve and implement this scheme in combination with their own abilities under the enlightenment given by this application. Some typical known structures or known methods should not become obstacles for ordinary technicians in the relevant field to implement this application. It should be pointed out that for those skilled in the art, without departing from the structure of the present invention, several deformations and improvements can be made, which should also be regarded as the protection scope of the present invention, which will not affect the effect of the implementation of the present invention and the practicality of the patent. The protection scope required by this application shall be based on the content of its claims, and the specific implementation methods and other records in the specification can be used to interpret the content of the claims.

Claims

1. A road safety monitoring system for urban and rural planning, characterized in that: include: Cameras are used to collect image data of vehicles and drivers on the road. The cameras are deployed in sections at preset distances. Rain gauges are used to collect real-time rainfall information on monitored roads. Rain gauges are deployed according to preset areas. The road analysis module is used to analyze and monitor the probability of driver fatigue and dangerous driving caused by straight roads and curves of different lengths on the road; The water accumulation analysis module is used to analyze the probability of congestion and accidents on the monitored roads due to the amount of water accumulated on the monitored roads and the speed at which water accumulates and dissipates. A water accumulation dissipation speed prediction model is established by combining big data analysis with factors such as wind speed, temperature, humidity, road type, drainage efficiency, and the distribution of straight roads and curves. The water accumulation dissipation speed prediction model predicts the time required for the water in the waterlogged area to dissipate naturally and whether manual intervention is required. The obstacle analysis module is used to monitor the occurrence and frequency of obstacles on the road, and is also used to analyze the probability of congestion and accidents on the monitored road caused by the occurrence of obstacles; Traffic flow analysis module, used to analyze the probability of congestion and accidents on the monitored roads caused by different traffic flows; The communication and collaboration module is used for real-time communication and collaboration with the traffic police department, road maintenance department and emergency center.

2. According to claim 1, it is characterized in that: The road analysis module combines historical accident data, road design parameters, driver real-time status and vehicle speed information to establish a fatigue driving and dangerous driving risk prediction model. The road analysis module provides drivers with warning information and recommends safe driving routes based on the fatigue driving and dangerous driving risk prediction model.

3. According to claim 2, it is characterized in that: The obstacle analysis module automatically detects obstacles on the road through camera image processing and machine learning algorithms, including accident vehicles, fallen rocks and fallen trees, and immediately generates an early warning and transmits it to the communication collaboration module.

4. The method according to claim 3, characterized in that: The traffic flow analysis module integrates an intelligent traffic unit. Based on the real-time collected traffic flow data and congestion occurrence frequency, it dynamically notifies relevant departments through the communication collaboration module to adjust the timing of traffic lights and optimize traffic flow.

5. The method according to claim 4, characterized in that: The waterlogging analysis module integrates GIS technology units, combines real-time rainfall data, road terrain information, road waterlogging volume and road water dissipation speed, predicts and displays road waterlogging areas, and sends cleanup instructions to relevant departments or issues early warning information to the public through the communication collaboration module.

6. The method according to claim 5, characterized in that: Cameras and rain gauges are customized for development and deployment based on the climate characteristics, traffic flow patterns, road aging and future development plans of the installation area, with dynamic adjustments to the needs of cameras and rain gauges.

7. The method according to claim 6, characterized in that: The fatigue driving and dangerous driving risk prediction model in the road analysis module has self-learning capabilities. The self-learning capabilities are based on historical data, social media, weather forecasts, and news reports, and dynamically adjust the parameters of the dangerous driving risk prediction model.

8. The method according to claim 7, characterized in that: The communication and collaboration module adopts a redundant design and failover mechanism. It continues to operate and provide communication services when some modules and networks fail. At the same time, it uses big data analysis and machine learning algorithms to assess the scope, severity and response strategies of emergencies, and automatically sends task instruction suggestions and coordination suggestions to relevant departments.

9. The method according to claim 8, characterized in that: The communication and collaboration module archives and stores monitoring data and assessment results, regularly analyzes data trends, builds a comprehensive data visualization and analysis platform, and integrates and displays monitoring data, analysis results, warning information, and emergency response record data.

10. A method for monitoring road safety in urban and rural planning, characterized by: The steps include: Step 1: Data collection: using several cameras and rain gauges to collect road images, rainfall, obstacles and traffic flow data in real time; Step 2: Data analysis: the data collected in step 1 is transmitted for image recognition, rainfall analysis, road condition assessment, obstacle detection and traffic flow statistics; Step 3: Warning generation: Based on the analysis results of step 2, road safety risks are assessed, including fatigue driving, dangerous driving, water accumulation, obstacles and congestion risks, and corresponding warning information is generated; Step 4: Auxiliary adjustment. According to the warning information in step 3, the emergency response mechanism is triggered. The emergency response mechanism includes adjusting traffic signals, notifying relevant departments to clear accumulated water or obstacles, and issuing safety tips to the public. The collected data and the emergency response mechanism assist planners in specifying road design and traffic management strategies.

Images