Road traffic information monitoring system and method

Abstract

The invention discloses a road traffic information monitoring system and method, and the method comprises the steps: deploying a video monitor, a sensor, an unmanned plane and a satellite device to collect real-time road traffic data, and protecting the data safety through encryption transmission and multilayer identity authentication; the flow is monitored in real time by combining image recognition and sensor data, congestion is analyzed, traffic violation is recognized, and an alarm is given; future flow is predicted through machine learning and big data analysis, and the signal lamp period is intelligently adjusted; through combination of real-time and historical data, accident risk points are identified and early warning is carried out, and early warning is automatically issued and adjustment and control are carried out for severe weather. The AI technology automatically identifies accidents and notifies a management center, dispatches emergency resources, optimizes signal lamps and lane traffic, and dynamically adjusts surrounding flow; according to the road traffic information monitoring system and method, an automatic emergency processing system is established, accidents are automatically detected and alarms are triggered under the conditions of traffic accidents and emergencies, and emergency resources are quickly dispatched.

Description

Technical Field

[0001] The present invention belongs to the field of road traffic information monitoring, and in particular relates to a road traffic information monitoring system and method. Background Art

[0002] A road traffic signal monitoring system is a system that uses various technical means and equipment to monitor, collect and analyze road traffic conditions, traffic flow, traffic violations, traffic safety and other aspects in real time. Its purpose is to improve the level of road traffic management, ensure traffic safety, optimize traffic smoothness, and reduce traffic accidents and congestion; through cameras, sensors, radars and other equipment installed on the road, real-time monitoring of traffic conditions such as vehicle flow, speed, lane usage, etc., to help traffic management departments respond in a timely manner; traffic violation monitoring includes monitoring of traffic violations such as running red lights, speeding, driving in the wrong direction, and driving out of lane. Common equipment includes traffic cameras, Automatic speedometer, traffic light control system, etc.; when abnormal situations such as traffic accidents and road failures are detected through monitoring equipment, the system can automatically alarm and notify relevant departments to take prompt measures; for example, monitoring of street lights, traffic signs, and road conditions (such as potholes, landslides, etc.) to ensure the normal operation of road facilities; intelligent traffic management integrates a variety of monitoring data, and through big data analysis, artificial intelligence and other technologies, predicts traffic flow, optimizes signal control, and diverts traffic to improve road use efficiency; collects real-time video and data through cameras, sensors and other equipment, and uses image recognition and video analysis technology to automatically identify and record traffic conditions.

[0003] However, although the existing road traffic information monitoring system has achieved remarkable results in improving traffic management efficiency, enhancing traffic safety, and optimizing traffic flow, it also has some defects and shortcomings and is unable to handle complex scenarios. Most of the existing monitoring systems focus on basic traffic flow monitoring and violation detection, and have weak response and processing capabilities for complex traffic events (such as large-scale traffic accidents, emergencies, etc.). Summary of the invention

[0004] In view of the deficiencies in the prior art, the purpose of the present invention is to provide a road traffic information monitoring system and method, to establish an automated emergency response system, to automatically detect accidents and trigger alarms in the event of traffic accidents or emergencies, and to quickly dispatch emergency resources.

[0005] The technical solution adopted by the present invention to solve its technical problem is:

[0006] A road traffic information monitoring system, comprising:

[0007] The data acquisition module is used to collect real-time traffic flow, vehicle speed, lane occupancy, and traffic density data through installed geomagnetic sensors, radar sensors, infrared sensors, lidar, and road surface temperature and humidity sensors;

[0008] The data processing and data storage module is used to transmit data to the central server, conduct real-time traffic analysis, anomaly detection, and traffic trend prediction through the big data platform, and store the collected data and video surveillance content in the cloud and encrypt them;

[0009] Intelligent image recognition and traffic violation detection module, which uses AI image recognition technology to automatically recognize license plates, perform vehicle registration, fee management, and detect violations. It uses image recognition technology to detect traffic violations such as running red lights, driving in the wrong direction, and occupying bus lanes, and automatically records and alarms.

[0010] Intelligent traffic signal control module, used for traffic lights to automatically adjust cycles according to real-time traffic flow data. For buses and emergency vehicles, the system automatically identifies and prioritizes traffic signals;

[0011] Traffic accident automatic identification and alarm module, which is used to automatically identify collision and rollover traffic accidents through video surveillance, sensors and AI algorithms. After the accident is identified, the alarm information is immediately sent to the traffic management center, and the nearest police car and ambulance emergency resources are automatically dispatched, and the traffic signals of surrounding roads are adjusted according to the traffic conditions;

[0012] Dynamic traffic flow prediction and guidance module, which uses machine learning algorithms to predict future traffic flow based on historical data and real-time data, and takes measures such as adjusting traffic lights and issuing traffic reminders in advance. Through intelligent navigation and traffic information release systems, it guides drivers to avoid congested sections, divert traffic, and optimize travel routes;

[0013] Intelligent decision support system module, which uses big data and AI to analyze historical data, identify high-incidence points of traffic accidents, set warning signs in advance and take control measures, and automatically optimize traffic control measures according to traffic conditions, emergencies, and weather factors;

[0014] The traffic management control platform module allows administrators to view road traffic flow, accident information, and camera videos in real time through the platform, and adopts automatic and manual dispatch functions. Administrators can adjust traffic signals, release traffic control information, and dispatch emergency resources based on real-time data.

[0015] A road traffic information monitoring method, comprising:

[0016] Obtain real-time road traffic information data through deployed video surveillance, sensors, drones and satellite equipment, and transmit and process the acquired data;

[0017] Real-time data analysis is performed based on the real-time road information data obtained. The data analysis includes flow monitoring and congestion analysis. Through image recognition and sensor data, traffic violations can be automatically monitored and identified, and real-time alarms can be issued.

[0018] Using machine learning and big data analysis methods, based on historical traffic data, weather conditions, and holiday factors, traffic flow in the next few hours or days is predicted, and traffic light cycles are intelligently adjusted based on real-time traffic data and prediction results;

[0019] By combining real-time data with historical data, potential accident risk points can be identified, warnings can be issued in advance and intervention can be carried out. Sensors can be used to monitor road temperature, humidity, weather conditions and environmental factors in real time. When severe weather occurs, the system can automatically issue warnings and adjust traffic control measures.

[0020] Using AI automatic recognition technology, when an accident is detected through video surveillance or sensor equipment, the system automatically alarms and notifies the traffic management center, and dispatches the nearest emergency resources. Based on the accident, the system automatically adjusts the traffic lights, optimizes lane traffic, and adjusts the traffic flow of surrounding roads based on the predicted data;

[0021] The traffic road information data collected by the equipment is encrypted and transmitted, and a multi-layer identity authentication mechanism is adopted to set control functions for authorized personnel to access sensitive data and operating systems.

[0022] As a preferred method, the real-time road traffic information data is obtained through the deployed video surveillance, sensors, drones and satellite equipment, and the method for transmitting and processing the obtained data is:

[0023] Deploy video surveillance cameras, ground sensors, drones and satellite equipment at key locations on the road:

[0024] Video surveillance cameras capture real-time image information of vehicles, traffic flow, and traffic signals on the road;

[0025] Geomagnetic sensors, infrared sensors, radar sensors, and lidar collect information on vehicle speed, lane occupancy, and traffic density;

[0026] Drones and satellite equipment to obtain traffic data on remote areas of roads;

[0027] The data collected by each device is transmitted to the data processing center through wireless communication technology or wired network. After being transmitted to the central server, the data will undergo preliminary preprocessing, which includes noise filtering, data format conversion, and video image decoding. Data from different sources are comprehensively analyzed through data fusion algorithms. A big data analysis platform is used to dynamically evaluate traffic conditions through flow analysis, trend prediction, and anomaly detection algorithms.

[0028] As a preferred method, the traffic road information data collected by the equipment is encrypted for transmission, and a multi-layer identity authentication mechanism is adopted to set control functions for authorized personnel to access sensitive data and the operating system:

[0029] Establish an encrypted channel between the data acquisition device and the receiving end. The encrypted channel includes TLS / SSL, AES, and RSA, and uses a hash function to perform hash verification on the transmitted data.

[0030] Use username and password, two-factor authentication, biometric authentication, and identity authentication mechanisms to limit access to sensitive data and system control functions;

[0031] A log management system is used for centralized management and real-time analysis. Access behaviors, system operations, and data operations are recorded in logs. Access control lists are set for different data and functions. Fine-grained access control ensures that only authenticated and authorized users can access sensitive data or perform system setting operations. Transparent data encryption and column-level encryption are used to encrypt and store sensitive data, and a key rotation strategy is implemented.

[0032] Preferably, real-time data analysis is performed based on the acquired real-time road information data, the data analysis includes flow monitoring and congestion analysis, and the method of automatically monitoring and identifying traffic violations and making real-time alarms by combining image recognition with sensor data is as follows:

[0033] Based on the real-time data obtained from video surveillance, sensors, and drone equipment, pre-process the raw data, clean invalid data, and convert it into a unified format;

[0034] Use geomagnetic sensors, radar or lidar sensors to obtain vehicle speed and lane occupancy information for traffic analysis. Based on the traffic data and historical traffic data, make real-time congestion predictions. Use traffic density models or machine learning models to analyze traffic conditions and automatically detect possible congested areas and time periods.

[0035] Through real-time images or video traffic in video surveillance, computer vision technology is used for target detection and image recognition. Deep learning models are used to identify vehicles, lanes, and signal light status. Sensor data is combined with video images to evaluate traffic flow and congestion status.

[0036] Through image recognition technology, surveillance cameras detect the status of traffic light signals and combine them with the position of the vehicle to identify whether the vehicle passes through the intersection under the red light state and determine whether there is red light running. Combined with the vehicle's movement trajectory, lane detection and image recognition, it can determine whether there are traffic violations such as driving in the wrong direction, occupying the bus lane, and illegal parking.

[0037] Based on the above, when a traffic violation or traffic congestion is identified, the system immediately sends an alarm signal, and the traffic management center or intelligent transportation system generates an event report through images and sensor data, and sends notifications to relevant traffic management personnel, law enforcement personnel or emergency response teams through the alarm system.

[0038] As a preferred method, machine learning and big data analysis methods are used to predict traffic flow in the next few hours or days based on historical traffic data, weather conditions, and holiday factors, and the method for intelligently adjusting the traffic light cycle based on real-time traffic data and prediction results is as follows:

[0039] Based on big data features, we use machine learning algorithms such as regression models, time series models, ensemble learning models, and deep learning models to predict traffic flow;

[0040] Based on historical traffic, weather conditions and holiday factors, the trained machine learning model is used to predict traffic flow in the next few hours or days. For predicting traffic flow in the next few days, the model integrates more historical data, holiday patterns, weather patterns and seasonal changes to make long-term predictions;

[0041] Through sensors and video surveillance equipment, the traffic flow, vehicle speed, and lane occupancy rate of the road are obtained in real time to supplement and verify the prediction results, compare the real-time traffic data with the prediction results, and detect the deviation of traffic prediction;

[0042] Based on the predicted traffic flow data, the intelligent traffic management system makes the following adjustments to the traffic light cycle:

[0043] Extend green light time and shorten red light time during periods when high traffic is predicted;

[0044] Shorten green light time during low traffic hours;

[0045] Based on real-time traffic data and forecast data, when there is a sudden increase in traffic flow, the system adjusts the traffic light cycle in real time and adjusts the cycle and timing of traffic lights.

[0046] As a preferred method, the signal lights at multiple intersections are controlled in linkage through a communication network and a regional traffic control algorithm, and the red light duration of the branch intersection is dynamically adjusted according to the traffic flow conditions of the main road:

[0047] Through the Internet of Vehicles and the dedicated traffic management communication system communication network, the traffic flow data of the signal lights at each intersection is obtained in real time, and the traffic flow of the main roads is monitored in real time through sensors, cameras, and geomagnetic equipment;

[0048] By monitoring the traffic conditions at branch intersections, the traffic volume, waiting time, and queue length of each branch road can be obtained, and traffic lights can be coordinated and adjusted through real-time data transmission and sharing;

[0049] By calculating the green light time of multiple intersections, a green wave band is formed. During peak hours, the system adjusts the signal cycle to extend the signal cycle of the main road and shorten the signal cycle of the branch road, and vice versa, to balance the flow and waiting time between the intersections;

[0050] Continuously optimize signal control strategies through interaction with traffic flow.

[0051] As a preferred method, by combining real-time data with historical data, potential accident risk points can be identified, warnings can be issued in advance and intervention can be carried out. The road surface temperature, humidity, weather conditions and environmental factors can be monitored in real time through sensors. When bad weather occurs, the system automatically issues warnings and adjusts traffic control measures.

[0052] Based on real-time data and historical data, use machine learning or deep learning methods to identify potential accident risk points, and use regression models, classification models or deep learning models based on historical data to predict the risk of accidents in the next few hours or days;

[0053] Based on meteorological data, when it is detected that ice and snow, heavy rain, and haze weather conditions reach a predetermined threshold, the system automatically triggers an early warning;

[0054] When a road section or intersection is identified as having a high accident risk, a risk warning is issued to notify traffic management departments and drivers based on historical data and real-time analysis. The warning information is released through multiple channels, including traffic lights, traffic signs, mobile applications, and broadcasts.

[0055] Based on the prediction of bad weather and accident risks, the system automatically adjusts the cycle of traffic lights, controls traffic flow, and limits vehicle speeds;

[0056] Based on the traffic flow and accident prediction results, measures such as closing some road sections or implementing temporary detours are taken in advance. Combined with the real-time traffic monitoring and early warning system, when a traffic accident occurs or a traffic accident caused by bad weather occurs, the intelligent transportation system automatically intervenes by dispatching emergency vehicles, optimizing traffic lights, and adjusting the direction of traffic through the road control system.

[0057] As a preferred method, AI automatic recognition technology is used. When an accident is detected by video surveillance or sensor equipment, the system automatically alarms and notifies the traffic management center, and dispatches the nearest emergency resources. After the accident occurs, the system automatically adjusts the traffic lights, optimizes lane traffic, and adjusts the traffic flow of surrounding roads according to the predicted data. The method is as follows:

[0058] Through cameras deployed on the road surface, intersections, and tunnel areas, computer vision technology is used to analyze video streams in real time, automatically identify traffic accidents or abnormal situations, and combine lane sensors to monitor vehicle speed, lane occupancy, and vehicle driving trajectory;

[0059] Identify accidents through data changes, combine multi-source data from video surveillance, radar sensors, and traffic flow sensors, and perform fusion processing through AI models;

[0060] Based on the AI ​​model, the system automatically identifies traffic accidents and immediately sends out automatic alarm signals to notify the traffic management center and relevant departments through SMS, phone calls, emails, and internal communications;

[0061] By integrating with the emergency resource management system, the AI ​​system automatically dispatches the nearest emergency resources based on the accident type, accident location, traffic conditions, and the nearest emergency resource location;

[0062] The system uses intelligent traffic signal control algorithms to adjust traffic lights in the accident area and surrounding roads in real time to optimize lane traffic. Through real-time traffic monitoring of the accident site and surrounding roads, the AI ​​system automatically adjusts the use of the following lanes:

[0063] In the event of a multi-vehicle collision, the system will prioritize the use of emergency lanes or set up dedicated lanes to divert non-accident vehicles;

[0064] Automatically adjust lanes when traffic jams are severe;

[0065] Based on the changes in traffic flow after the accident, the AI ​​system predicts the traffic flow on surrounding roads through historical data and real-time monitoring, and guides the flow by controlling traffic lights and dispatching traffic control.

[0066] Another technical problem to be solved by the present invention is to provide an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, a road traffic information monitoring system and method as described above is implemented.

[0067] Another technical problem to be solved by the present invention is to provide a computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, a road traffic information monitoring system and method are implemented.

[0068] The beneficial effects of the present invention are:

[0069] By acquiring traffic data in real time through video surveillance, sensors, drones and satellite equipment, and transmitting and processing data, it is possible to monitor road traffic conditions in real time, including flow, congestion, traffic violations, etc. Compared with traditional methods, it can provide higher real-time and accuracy, helping traffic management personnel make decisions immediately; through the combination of image recognition and sensor data, the system can automatically monitor and identify traffic violations (such as running red lights, driving in the wrong direction, etc.), and issue real-time alarms, greatly improving the efficiency and accuracy of traffic law enforcement; based on historical flow data, weather conditions, holiday factors, etc., using machine learning and big data analysis methods, it can accurately predict traffic flow in the next few hours or days. This prediction capability can enable the traffic system to make adjustments in advance, intelligently adjust the traffic light cycle, and alleviate traffic congestion; by combining real-time data with historical data, the system can identify potential events and problems. Therefore, risk points can be identified, and warning signals can be issued in advance, and intervention measures can be taken to reduce the probability of accidents and avoid congestion and casualties caused by traffic accidents; sensors can monitor environmental factors such as road temperature and humidity in real time. When there is severe weather (such as heavy rain, ice and snow, haze, etc.), the system can automatically issue warnings and adjust traffic control measures, such as optimizing traffic light cycles, closing some roads or changing lane allocations, thereby enhancing the protection of traffic safety under special weather conditions; AI automatic recognition technology can detect when a traffic accident occurs through video surveillance and sensor equipment. The system will automatically alarm and notify the traffic management center immediately. At the same time, the system can also quickly dispatch the nearest emergency resources, such as fire and emergency vehicles, to ensure timely handling of the accident scene; after the accident, the system can adjust traffic lights according to real-time data, optimize lane capacity, and reduce the impact of the accident on other roads.At the same time, through predictive analysis, the system can adjust the traffic flow of surrounding roads to avoid serious congestion in other areas; traffic information involves a large amount of sensitive data (such as traffic flow, illegal behavior, accident information, etc.). This method ensures the security of data through encrypted transmission, and adopts a multi-layer identity authentication mechanism to ensure that only authorized personnel can access sensitive data and perform system settings, which greatly enhances the security of the system and prevents data leakage or tampering; through strong identity authentication and permission management measures, it is ensured that only authorized personnel can access key data and execute control commands, effectively reducing the risk of system abuse and data leakage; the system comprehensively processes data from different sources (such as video surveillance, sensors, drones, satellites, etc.) to form a complete view of traffic conditions, which can more comprehensively understand and analyze road traffic conditions, so as to formulate more appropriate traffic management plans; by introducing advanced technologies such as machine learning and big data analysis, traffic management is not only more intelligent and automated, but also data-driven decision support makes traffic management more scientific, predictable and efficient; through timely warning, rapid response to accidents, intelligent adjustment of traffic lights and other measures, it can effectively reduce the occurrence of traffic accidents, alleviate congestion and improve road traffic efficiency. This directly improves the travel safety and experience of citizens; especially when the weather changes and emergencies occur, it can intelligently adjust traffic flow, ensure the safe operation of public transportation, and prevent traffic accidents caused by accidents or bad weather from affecting public transportation. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] Figure 1 The present invention is a road traffic information monitoring system flow chart. DETAILED DESCRIPTION

[0071] The principles and features of the present invention are described below, and the examples are only used to explain the present invention and are not used to limit the scope of the present invention. The present invention is described more specifically by way of example in the following paragraphs. According to the following description and claims, the advantages and features of the present invention will become clearer.

[0072] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used herein in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more related listed items.

[0073] Example

[0074] A road traffic information monitoring system, comprising:

[0075] The data acquisition module is used to collect real-time traffic flow, vehicle speed, lane occupancy, and traffic density data through installed geomagnetic sensors, radar sensors, infrared sensors, lidar, and road surface temperature and humidity sensors;

[0076] The data processing and data storage module is used to transmit data to the central server, conduct real-time traffic analysis, anomaly detection, and traffic trend prediction through the big data platform, and store the collected data and video surveillance content in the cloud and encrypt them;

[0077] Intelligent image recognition and traffic violation detection module, which uses AI image recognition technology to automatically recognize license plates, perform vehicle registration, fee management, and detect violations. It uses image recognition technology to detect traffic violations such as running red lights, driving in the wrong direction, and occupying bus lanes, and automatically records and alarms.

[0078] Intelligent traffic signal control module, used for traffic lights to automatically adjust cycles according to real-time traffic flow data. For buses and emergency vehicles, the system automatically identifies and prioritizes traffic signals;

[0079] Traffic accident automatic identification and alarm module, which is used to automatically identify collision and rollover traffic accidents through video surveillance, sensors and AI algorithms. After the accident is identified, the alarm information is immediately sent to the traffic management center, and the nearest police car and ambulance emergency resources are automatically dispatched, and the traffic signals of surrounding roads are adjusted according to the traffic conditions;

[0080] Dynamic traffic flow prediction and guidance module, which uses machine learning algorithms to predict future traffic flow based on historical data and real-time data, and takes measures such as adjusting traffic lights and issuing traffic reminders in advance. Through intelligent navigation and traffic information release systems, it guides drivers to avoid congested sections, divert traffic, and optimize travel routes;

[0081] Intelligent decision support system module, which uses big data and AI to analyze historical data, identify high-incidence points of traffic accidents, set warning signs in advance and take control measures, and automatically optimize traffic control measures according to traffic conditions, emergencies, and weather factors;

[0082] The traffic management control platform module allows administrators to view road traffic flow, accident information, and camera videos in real time through the platform, and adopts automatic and manual dispatch functions. Administrators can adjust traffic signals, release traffic control information, and dispatch emergency resources based on real-time data.

[0083] Utilize sensors and video technology to collect comprehensive traffic data, monitor traffic conditions in real time, and achieve dynamic management; use AI to identify traffic violations and traffic accidents and quickly report them, effectively reducing the occurrence and processing time of accidents and improving road safety; intelligent traffic signal control, traffic flow prediction and guidance, reduce congestion, improve travel efficiency, reduce energy consumption and pollution; AI image recognition technology improves the accuracy of violation detection and reduces loopholes and disputes in manual law enforcement; intelligent decision support system based on big data analysis, identifies hidden dangers in advance, optimizes traffic control measures, and improves management effectiveness; accident identification and alarm module quickly locates the accident site, automatically allocates resources, and shortens rescue time; the system has a high degree of automation, reduces the error rate of manual operation, and improves management efficiency; Traffic flow, speed, density, occupancy rate and other data are acquired in real time through sensors and cameras to ensure the comprehensiveness and real-time nature of the data. Big data technology is used to analyze real-time data and extract valuable information, while cloud storage encryption is used to ensure data security. AI algorithms are used for image recognition and data analysis to achieve functions such as vehicle identification, violation detection, and accident judgment. The traffic light system dynamically adjusts the cycle to ensure that emergency vehicles have priority. Machine learning algorithms combine historical and real-time data to predict traffic flow and guide vehicle diversion through navigation and reminder systems. Based on AI and big data analysis, managers are supported to make quick decisions and optimize resource allocation and traffic control measures. The management and control platform uniformly displays and dispatches traffic information, combines automation functions with manual intervention to improve management flexibility.

[0084] A road traffic information monitoring method, comprising:

[0085] Obtain real-time road traffic information data through deployed video surveillance, sensors, drones and satellite equipment, and transmit and process the acquired data;

[0086] Real-time data analysis is performed based on the real-time road information data obtained. The data analysis includes flow monitoring and congestion analysis. Through image recognition and sensor data, traffic violations can be automatically monitored and identified, and real-time alarms can be issued.

[0087] Using machine learning and big data analysis methods, based on historical traffic data, weather conditions, and holiday factors, traffic flow in the next few hours or days is predicted, and traffic light cycles are intelligently adjusted based on real-time traffic data and prediction results;

[0088] By combining real-time data with historical data, potential accident risk points can be identified, warnings can be issued in advance and intervention can be carried out. Sensors can be used to monitor road temperature, humidity, weather conditions and environmental factors in real time. When severe weather occurs, the system can automatically issue warnings and adjust traffic control measures.

[0089] Using AI automatic recognition technology, when an accident is detected through video surveillance or sensor equipment, the system automatically alarms and notifies the traffic management center, and dispatches the nearest emergency resources. Based on the accident, the system automatically adjusts the traffic lights, optimizes lane traffic, and adjusts the traffic flow of surrounding roads based on the predicted data;

[0090] The traffic road information data collected by the equipment is encrypted and transmitted, and a multi-layer identity authentication mechanism is adopted to set control functions for authorized personnel to access sensitive data and operating systems.

[0091] Using video surveillance, sensors, drones and satellite equipment, the coverage is wide, traffic dynamics are obtained in real time, and information is more comprehensive; through flow monitoring and congestion analysis, the signal light cycle is intelligently adjusted to reduce traffic jams and improve road traffic efficiency; based on machine learning and big data, combined with weather and holiday factors, future traffic conditions are accurately predicted to provide optimization solutions for management departments and drivers; high-risk accident points are identified in advance, active warnings are issued, and accident rates are reduced; severe weather warnings and adjustment of control measures are carried out to ensure driving safety; AI technology automatically identifies accidents and alarms, quickly dispatches emergency resources, optimizes traffic lights, and reduces the scope of accident impact; data encryption and multi-layer identity authentication mechanisms ensure the secure transmission and access of traffic information and prevent information leakage; based on accidents and environmental dynamics, signal lights and lane traffic plans are adjusted to improve emergency response efficiency; through flow optimization and signal adjustment, vehicle idling time is reduced and fuel consumption is reduced consumption and carbon emissions; deploy a variety of collection equipment (such as video surveillance, sensors, drones, satellites) to obtain traffic information in real time and transmit data to the central processing system through high-speed networks; use AI and image recognition technology to analyze video images and sensor data in real time to detect traffic flow, violations and accidents; use machine learning models, combined with historical traffic data and environmental factors, to predict future traffic trends and provide decision support; the system dynamically adjusts the traffic light cycle according to real-time traffic data and prediction results to improve traffic efficiency; AI automatically alarms after identifying an accident, notifies the traffic management center, and dispatches the nearest emergency resources (such as police cars and ambulances) according to the location; sensors detect weather conditions in real time, and the system automatically issues warnings in severe weather and adjusts traffic measures (such as reducing vehicle speeds and increasing patrols); use data encryption and identity authentication technology to ensure that the collected traffic information can only be accessed and operated by authorized personnel.

[0092] The method of acquiring real-time road traffic information data through deployed video surveillance, sensors, drones and satellite equipment, and transmitting and processing the acquired data is as follows:

[0093] Deploy video surveillance cameras, ground sensors, drones and satellite equipment at key locations on the road:

[0094] Video surveillance cameras capture real-time image information of vehicles, traffic flow, and traffic signals on the road;

[0095] Geomagnetic sensors, infrared sensors, radar sensors, and lidar collect information on vehicle speed, lane occupancy, and traffic density;

[0096] Drones and satellite equipment to obtain traffic data on remote areas of roads;

[0097] The data collected by each device is transmitted to the data processing center through wireless communication technology or wired network. After being transmitted to the central server, the data will undergo preliminary preprocessing, which includes noise filtering, data format conversion, and video image decoding. Data from different sources are comprehensively analyzed through data fusion algorithms. A big data analysis platform is used to dynamically evaluate traffic conditions through flow analysis, trend prediction, and anomaly detection algorithms.

[0098] Through the combined use of video surveillance, sensors, drones and satellites, traffic monitoring from the ground to the air, from local to global is achieved, with a wide coverage and comprehensive data; road traffic data is obtained in real time through a variety of devices to ensure the immediacy of information and provide support for dynamic traffic management; multi-sensor data fusion is used to eliminate the limitations of a single data source and improve the accuracy and reliability of data analysis; data preprocessing steps (such as noise filtering and format conversion) improve data quality; traffic analysis, trend prediction and anomaly detection are quickly completed through big data platforms and advanced algorithms; drones and satellite equipment can quickly cover areas where ground equipment is difficult to install, reducing manpower and equipment deployment costs; integrated data from multiple devices can quickly detect traffic anomalies (such as accidents, congestion) and assist in the formulation of intelligent traffic management plans; the system is based on a big data analysis platform, which is convenient for subsequent expansion of new equipment or the addition of more functional modules (such as automatic adjustment of traffic lights and optimization of emergency response); dynamic assessment of traffic conditions and prediction of trends provide a basis for management departments to optimize resource allocation and divert traffic, reducing congestion and delays.

[0099] According to the traffic road information data collected by the equipment, encrypted transmission is carried out, and a multi-layer identity authentication mechanism is adopted to set control functions for authorized personnel to access sensitive data and operating systems:

[0100] Establish an encrypted channel between the data acquisition device and the receiving end. The encrypted channel includes TLS / SSL, AES, and RSA, and uses a hash function to perform hash verification on the transmitted data.

[0101] Use username and password, two-factor authentication, biometric authentication, and identity authentication mechanisms to limit access to sensitive data and system control functions;

[0102] A log management system is used for centralized management and real-time analysis. Access behaviors, system operations, and data operations are recorded in logs. Access control lists are set for different data and functions. Fine-grained access control ensures that only authenticated and authorized users can access sensitive data or perform system setting operations. Transparent data encryption and column-level encryption are used to encrypt and store sensitive data, and a key rotation strategy is implemented.

[0103] Use encrypted channels (TLS / SSL, AES, RSA) to ensure that data in transmission will not be intercepted or tampered with. Hash verification ensures data integrity and prevents data from being forged or damaged. Multi-layer identity authentication (user name and password, two-factor authentication, biometrics) effectively prevents unauthorized personnel from accessing sensitive data or operating systems. Fine-grained access control lists (ACLs) further restrict permissions to ensure that sensitive functions can only be operated by specific personnel. Transparent data encryption and column-level encryption protect sensitive data. Even if the storage medium is stolen, the data is still safe. The key rotation strategy prevents security risks caused by the long-term use of the same key. The log management system centrally records access behavior and operation history, supports real-time monitoring and post-audit, and abnormal behavior can be quickly located to facilitate accident investigation and responsibility tracking. The solution complies with common data protection and privacy regulations (such as GDPR, CCPA, etc.) and enhances system compliance. Strengthen the sensitive data protection mechanism and improve the trust of users and organizations in the system.

[0104] Real-time data analysis is performed based on the acquired real-time road information data. The data analysis includes flow monitoring and congestion analysis. By combining image recognition with sensor data, traffic violations can be automatically monitored and identified. The method for real-time alarm is as follows:

[0105] Based on the real-time data obtained from video surveillance, sensors, and drone equipment, pre-process the raw data, clean invalid data, and convert it into a unified format;

[0106] Use geomagnetic sensors, radar or lidar sensors to obtain vehicle speed and lane occupancy information for traffic analysis. Based on the traffic data and historical traffic data, make real-time congestion predictions. Use traffic density models or machine learning models to analyze traffic conditions and automatically detect possible congested areas and time periods.

[0107] Through real-time images or video traffic in video surveillance, computer vision technology is used for target detection and image recognition. Deep learning models are used to identify vehicles, lanes, and signal light status. Sensor data is combined with video images to evaluate traffic flow and congestion status.

[0108] Through image recognition technology, surveillance cameras detect the status of traffic light signals and combine them with the position of the vehicle to identify whether the vehicle passes through the intersection under the red light state and determine whether there is red light running. Combined with the vehicle's movement trajectory, lane detection and image recognition, it can determine whether there are traffic violations such as driving in the wrong direction, occupying the bus lane, and illegal parking.

[0109] Based on the above, when a traffic violation or traffic congestion is identified, the system immediately sends an alarm signal, and the traffic management center or intelligent transportation system generates an event report through images and sensor data, and sends notifications to relevant traffic management personnel, law enforcement personnel or emergency response teams through the alarm system.

[0110] Through real-time data collection and analysis, traffic violations and congestion can be quickly identified, and timely alarms and countermeasures can be taken; integrated sensor data and image recognition technology can provide accurate traffic status assessments to reduce false alarms and missed alarms; based on data fusion from multiple devices, the monitoring range is wide, covering ground traffic, traffic light status and road violations; using deep learning models and computer vision technology, data analysis, violation identification and alarm generation are automatically completed, reducing manual intervention and improving efficiency; combining historical data and real-time data, using machine learning models to predict congestion, providing a basis for traffic management to formulate response plans in advance; quickly identifying traffic problems and notifying relevant personnel, reducing congestion duration, optimizing traffic flow, and improving urban traffic operation efficiency; automatically identifying violations (such as running red lights, driving in the wrong direction, illegal parking, etc.) and generating event reports, providing accurate evidence for traffic law enforcement and improving road safety; replacing traditional manual monitoring methods with technical means, saving human resources, and reducing social and economic losses caused by traffic accidents and congestion.

[0111] Using machine learning and big data analysis methods, based on historical traffic data, weather conditions, and holiday factors, the traffic flow in the next few hours or days is predicted. Based on real-time traffic data and prediction results, the method of intelligently adjusting the traffic light cycle is as follows:

[0112] Based on big data features, we use machine learning algorithms such as regression models, time series models, ensemble learning models, and deep learning models to predict traffic flow;

[0113] Based on historical traffic, weather conditions and holiday factors, the trained machine learning model is used to predict traffic flow in the next few hours or days. For predicting traffic flow in the next few days, the model integrates more historical data, holiday patterns, weather patterns and seasonal changes to make long-term predictions;

[0114] Through sensors and video surveillance equipment, the traffic flow, vehicle speed, and lane occupancy rate of the road are obtained in real time to supplement and verify the prediction results, compare the real-time traffic data with the prediction results, and detect the deviation of traffic prediction;

[0115] Based on the predicted traffic flow data, the intelligent traffic management system makes the following adjustments to the traffic light cycle:

[0116] Extend green light time and shorten red light time during periods when high traffic is predicted;

[0117] Shorten green light time during low traffic hours;

[0118] Based on real-time traffic data and forecast data, when there is a sudden increase in traffic flow, the system adjusts the traffic light cycle in real time and adjusts the cycle and timing of traffic lights.

[0119] Dynamically adjust the traffic light cycle to reduce vehicle waiting time, optimize traffic flow, and reduce the probability of congestion; combine historical traffic data, weather, holidays and other factors, use advanced machine learning models to make short-term and long-term predictions of traffic flow to improve prediction accuracy; the system can quickly adjust the traffic light cycle according to real-time traffic data to respond to sudden traffic changes and improve the flexibility of traffic management; reduce vehicle idling waiting time, reduce fuel consumption and exhaust emissions, and promote environmental protection; intelligent traffic light control reduces dependence on manual traffic management, improves management efficiency, and optimizes traffic law enforcement and dispatch resource allocation; considers multi-dimensional factors such as weather and holidays, and is suitable for traffic management needs in complex scenarios such as cities, festivals, and disasters; vehicle drivers experience a smoother traffic environment, reduce commuting time, and improve travel satisfaction.

[0120] Through the communication network and regional traffic control algorithm, the traffic lights at multiple intersections are controlled in a linked manner. According to the traffic flow conditions of the main road, the method for dynamically adjusting the red light duration at the branch intersection is as follows:

[0121] Through the Internet of Vehicles and the dedicated traffic management communication system communication network, the traffic flow data of the signal lights at each intersection is obtained in real time, and the traffic flow of the main roads is monitored in real time through sensors, cameras, and geomagnetic equipment;

[0122] By monitoring the traffic conditions at branch intersections, the traffic volume, waiting time, and queue length of each branch road can be obtained, and traffic lights can be coordinated and adjusted through real-time data transmission and sharing;

[0123] By calculating the green light time of multiple intersections, a green wave band is formed. During peak hours, the system adjusts the signal cycle to extend the signal cycle of the main road and shorten the signal cycle of the branch road, and vice versa, to balance the flow and waiting time between the intersections;

[0124] Continuously optimize signal control strategies through interaction with traffic flow.

[0125] The formation of green wave belts on the main roads enables vehicles to pass through multiple intersections continuously, reducing the number of stops and waiting time, and optimizing traffic efficiency; achieving dynamic balance control of main roads and branch roads, reducing congestion pressure during peak hours, and balancing traffic flow distribution; using real-time data and communication networks, signal light linkage control can quickly respond to traffic changes and ensure the effectiveness of control strategies; reducing fuel consumption and exhaust emissions caused by frequent vehicle starts and stops, promoting green travel and low-carbon city development; multi-intersection linkage control optimizes traffic flow distribution within the region through communication network and algorithm coordination, reducing the limitations of single-point optimization; drivers can enjoy a smoother driving experience, reduce psychological pressure and travel time, and improve travel satisfaction.

[0126] By combining real-time data with historical data, potential accident risk points can be identified, early warnings can be issued and intervention can be carried out. Sensors can be used to monitor road temperature, humidity, weather conditions and environmental factors in real time. When severe weather occurs, the system can automatically issue warnings and adjust traffic control measures.

[0127] Based on real-time data and historical data, use machine learning or deep learning methods to identify potential accident risk points, and use regression models, classification models or deep learning models based on historical data to predict the risk of accidents in the next few hours or days;

[0128] Based on meteorological data, when it is detected that ice and snow, heavy rain, and haze weather conditions reach a predetermined threshold, the system automatically triggers an early warning;

[0129] When a road section or intersection is identified as having a high accident risk, a risk warning is issued to notify traffic management departments and drivers based on historical data and real-time analysis. The warning information is released through multiple channels, including traffic lights, traffic signs, mobile applications, and broadcasts.

[0130] Based on the prediction of bad weather and accident risks, the system automatically adjusts the cycle of traffic lights, controls traffic flow, and limits vehicle speeds;

[0131] Based on the traffic flow and accident prediction results, measures such as closing some road sections or implementing temporary detours are taken in advance. Combined with the real-time traffic monitoring and early warning system, when a traffic accident occurs or a traffic accident caused by bad weather occurs, the intelligent transportation system automatically intervenes by dispatching emergency vehicles, optimizing traffic lights, and adjusting the direction of traffic through the road control system.

[0132] Through real-time warning and intervention, traffic accidents caused by severe weather or potential accident risks can be reduced, and the safety of people and vehicles can be guaranteed. By combining historical data and real-time monitoring, machine learning algorithms can be used to accurately predict accident risk points and improve the reliability and timeliness of warnings. The system automatically adjusts traffic lights and optimizes traffic directions to quickly respond to traffic accidents or risks and reduce the impact on overall traffic. By intelligently dispatching emergency vehicles and resources, accident handling time can be shortened and emergency response efficiency can be improved. Weather changes can be automatically identified and traffic control measures can be adjusted to ensure smooth and safe traffic under severe weather conditions. Warning information can be released through multiple channels to promptly notify drivers and management departments, thereby improving information transmission efficiency and user response speed. Economic losses caused by traffic congestion and delays caused by accidents or weather can be reduced, and travel efficiency can be improved.

[0133] Using AI automatic recognition technology, when an accident is detected through video surveillance or sensor equipment, the system automatically alarms and notifies the traffic management center, and dispatches the nearest emergency resources. After the accident occurs, the system automatically adjusts the traffic lights, optimizes lane traffic, and adjusts the traffic flow of surrounding roads based on the predicted data. The method is as follows:

[0134] Through cameras deployed on the road surface, intersections, and tunnel areas, computer vision technology is used to analyze video streams in real time, automatically identify traffic accidents or abnormal situations, and combine lane sensors to monitor vehicle speed, lane occupancy, and vehicle driving trajectory;

[0135] Identify accidents through data changes, combine multi-source data from video surveillance, radar sensors, and traffic flow sensors, and perform fusion processing through AI models;

[0136] Based on the AI ​​model, the system automatically identifies traffic accidents and immediately sends out automatic alarm signals to notify the traffic management center and relevant departments through SMS, phone calls, emails, and internal communications;

[0137] By integrating with the emergency resource management system, the AI ​​system automatically dispatches the nearest emergency resources based on the accident type, accident location, traffic conditions, and the nearest emergency resource location;

[0138] The system uses intelligent traffic signal control algorithms to adjust traffic lights in the accident area and surrounding roads in real time to optimize lane traffic. Through real-time traffic monitoring of the accident site and surrounding roads, the AI ​​system automatically adjusts the use of the following lanes:

[0139] In the event of a multi-vehicle collision, the system will prioritize the use of emergency lanes or set up dedicated lanes to divert non-accident vehicles;

[0140] Automatically adjust lanes when traffic jams are severe;

[0141] Based on the changes in traffic flow after the accident, the AI ​​system predicts the traffic flow on surrounding roads through historical data and real-time monitoring, and guides the flow by controlling traffic lights and dispatching traffic control.

[0142] Automatically detect accidents and promptly notify the traffic management center and relevant departments to shorten accident response time and reduce the impact of accidents. The AI ​​system automatically selects the nearest and most appropriate emergency resources based on real-time positioning and accident conditions to improve resource utilization efficiency. Through signal light optimization and lane adjustment, traffic congestion caused by accidents is reduced to ensure smooth passage of non-accident vehicles. Based on real-time and historical data, changes in traffic flow in and around the accident area are predicted, and diversion and traffic control are dynamically implemented. Integrate video surveillance and multi-source data, conduct in-depth analysis through AI models, improve the accuracy of accident identification, and reduce false alarms. Automatically notify relevant parties through multiple channels such as SMS, phone calls, and emails to achieve rapid information transmission and synchronization, reduce traffic risks in accident areas, protect the safety of road users, and improve public satisfaction with traffic management.

[0143] This embodiment also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, a road traffic information monitoring system and method as described above is implemented.

[0144] This embodiment also provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, a road traffic information monitoring system and method as described above are implemented.

[0145] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0146] Those skilled in the art will clearly understand that for the sake of convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the system can be divided into different functional units or modules to complete all or part of the functions described above.

[0147] The above embodiments of the present invention are not intended to limit the protection scope of the present invention, and the implementation modes of the present invention are not limited thereto. All other modifications, replacements or changes made to the above structures of the present invention based on the above contents of the present invention, in accordance with common technical knowledge and customary means in the art, without departing from the above basic technical ideas of the present invention, should fall within the protection scope of the present invention.

Claims

1. A road traffic information monitoring system, characterized in that: Included are: The data acquisition module is used to collect real-time traffic flow, vehicle speed, lane occupancy, and traffic density data through installed geomagnetic sensors, radar sensors, infrared sensors, lidar, and road surface temperature and humidity sensors; The data processing and data storage module is used to transmit data to the central server, conduct real-time traffic analysis, anomaly detection, and traffic trend prediction through the big data platform, and store the collected data and video surveillance content in the cloud and encrypt them; Intelligent image recognition and traffic violation detection module, which uses AI image recognition technology to automatically recognize license plates, perform vehicle registration, fee management, and detect violations. It uses image recognition technology to detect traffic violations such as running red lights, driving in the wrong direction, and occupying bus lanes, and automatically records and alarms. Intelligent traffic signal control module, used for traffic lights to automatically adjust cycles according to real-time traffic flow data. For buses and emergency vehicles, the system automatically identifies and prioritizes traffic signals; Traffic accident automatic identification and alarm module, which is used to automatically identify collision and rollover traffic accidents through video surveillance, sensors and AI algorithms. After the accident is identified, the alarm information is immediately sent to the traffic management center, and the nearest police car and ambulance emergency resources are automatically dispatched, and the traffic signals of surrounding roads are adjusted according to the traffic conditions; Dynamic traffic flow prediction and guidance module, which uses machine learning algorithms to predict future traffic flow based on historical data and real-time data, and takes measures such as adjusting traffic lights and issuing traffic reminders in advance. Through intelligent navigation and traffic information release systems, it guides drivers to avoid congested sections, divert traffic, and optimize travel routes; Intelligent decision support system module, which uses big data and AI to analyze historical data, identify high-incidence points of traffic accidents, set warning signs in advance and take control measures, and automatically optimize traffic control measures according to traffic conditions, emergencies, and weather factors; The traffic management control platform module allows administrators to view road traffic flow, accident information, and camera videos in real time through the platform, and adopts automatic and manual dispatch functions. Administrators can adjust traffic signals, release traffic control information, and dispatch emergency resources based on real-time data.

2. A road traffic information monitoring method, characterized in that: Included are: Obtain real-time road traffic information data through deployed video surveillance, sensors, drones and satellite equipment, and transmit and process the acquired data; Traffic road information data collected by the equipment is encrypted for transmission, and a multi-layer identity authentication mechanism is used to set control functions for authorized personnel to access sensitive data and operating systems; Real-time data analysis is performed based on the real-time road information data obtained. The data analysis includes flow monitoring and congestion analysis. Through image recognition and sensor data, traffic violations can be automatically monitored and identified, and real-time alarms can be issued. Using machine learning and big data analysis methods, based on historical traffic data, weather conditions, and holiday factors, traffic flow in the next few hours or days is predicted, and traffic light cycles are intelligently adjusted based on real-time traffic data and prediction results; By combining real-time data with historical data, potential accident risk points can be identified, warnings can be issued in advance and intervention can be carried out. Sensors can be used to monitor road temperature, humidity, weather conditions and environmental factors in real time. When severe weather occurs, the system can automatically issue warnings and adjust traffic control measures. Using AI automatic recognition technology, when an accident is detected through video surveillance or sensor equipment, the system automatically alarms and notifies the traffic management center, and dispatches the nearest emergency resources. After the accident occurs, the system automatically adjusts traffic lights, optimizes lane traffic, and adjusts traffic flow on surrounding roads based on predicted data.

3. The road traffic information monitoring method according to claim 2, characterized in that: The method of acquiring real-time road traffic information data through deployed video surveillance, sensors, drones and satellite equipment, and transmitting and processing the acquired data is as follows: Deploy video surveillance cameras, ground sensors, drones and satellite equipment at key locations on the road: Video surveillance cameras capture real-time image information of vehicles, traffic flow, and traffic signals on the road; Geomagnetic sensors, infrared sensors, radar sensors, and lidar collect information on vehicle speed, lane occupancy, and traffic density; Drones and satellite equipment to obtain traffic data on remote areas of roads; The data collected by each device is transmitted to the data processing center through wireless communication technology or wired network. After being transmitted to the central server, the data will undergo preliminary preprocessing, which includes noise filtering, data format conversion, and video image decoding. Data from different sources are comprehensively analyzed through data fusion algorithms. A big data analysis platform is used to dynamically evaluate traffic conditions through flow analysis, trend prediction, and anomaly detection algorithms.

4. The road traffic information monitoring method according to claim 3, characterized in that: According to the traffic road information data collected by the equipment, encrypted transmission is carried out, and a multi-layer identity authentication mechanism is adopted to set control functions for authorized personnel to access sensitive data and operating systems: Establish an encrypted channel between the data acquisition device and the receiving end. The encrypted channel includes TLS / SSL, AES, and RSA, and uses a hash function to perform hash verification on the transmitted data. Use username and password, two-factor authentication, biometric authentication, and identity authentication mechanisms to limit access to sensitive data and system control functions; A log management system is used for centralized management and real-time analysis. Access behaviors, system operations, and data operations are recorded in logs. Access control lists are set for different data and functions. Fine-grained access control ensures that only authenticated and authorized users can access sensitive data or perform system setting operations. Transparent data encryption and column-level encryption are used to encrypt and store sensitive data, and a key rotation strategy is implemented.

5. The road traffic information monitoring method according to claim 4, characterized in that: Real-time data analysis is performed based on the acquired real-time road information data. The data analysis includes flow monitoring and congestion analysis. By combining image recognition with sensor data, traffic violations can be automatically monitored and identified. The method for real-time alarm is as follows: Based on the real-time data obtained from video surveillance, sensors, and drone equipment, pre-process the raw data, clean invalid data, and convert it into a unified format; Use geomagnetic sensors, radar or lidar sensors to obtain vehicle speed and lane occupancy information for traffic analysis. Based on the traffic data and historical traffic data, make real-time congestion predictions. Use traffic density models or machine learning models to analyze traffic conditions and automatically detect possible congested areas and time periods. Through real-time images or video traffic in video surveillance, computer vision technology is used for target detection and image recognition. Deep learning models are used to identify vehicles, lanes, and signal light status. Sensor data is combined with video images to evaluate traffic flow and congestion status. Through image recognition technology, surveillance cameras detect the status of traffic light signals and combine them with the position of the vehicle to identify whether the vehicle passes through the intersection under the red light state and determine whether there is red light running. Combined with the vehicle's movement trajectory, lane detection and image recognition, it can determine whether there are traffic violations such as driving in the wrong direction, occupying the bus lane, and illegal parking. Based on the above, when a traffic violation or traffic congestion is identified, the system immediately sends out an alarm signal, and the traffic management center or intelligent transportation system generates an event report through images and sensor data, and sends notifications to relevant traffic management personnel, law enforcement personnel or emergency response teams through the alarm system.

6. The road traffic information monitoring method according to claim 5, characterized in that: Using machine learning and big data analysis methods, based on historical traffic data, weather conditions, and holiday factors, the traffic flow in the next few hours or days is predicted. Based on real-time traffic data and prediction results, the method of intelligently adjusting the traffic light cycle is as follows: Based on big data features, we use machine learning algorithms such as regression models, time series models, ensemble learning models, and deep learning models to predict traffic flow; Based on historical traffic, weather conditions and holiday factors, the trained machine learning model is used to predict traffic flow in the next few hours or days. For predicting traffic flow in the next few days, the model integrates more historical data, holiday patterns, weather patterns and seasonal changes to make long-term predictions; Through sensors and video surveillance equipment, the traffic flow, vehicle speed, and lane occupancy rate of the road are obtained in real time to supplement and verify the prediction results, compare the real-time traffic data with the prediction results, and detect the deviation of traffic prediction; Based on the predicted traffic flow data, the intelligent traffic management system makes the following adjustments to the traffic light cycle: Extend green light time and shorten red light time during periods of predicted high traffic volume; Shorten green light time during low traffic hours; Based on real-time traffic data and forecast data, when there is a sudden increase in traffic flow, the system adjusts the traffic light cycle in real time and adjusts the cycle and timing of traffic lights.

7. The road traffic information monitoring method according to claim 6, characterized in that: Through the communication network and regional traffic control algorithm, the traffic lights at multiple intersections are linked and controlled. According to the traffic flow conditions of the main road, the method for dynamically adjusting the red light duration at the branch intersection is as follows: Through the Internet of Vehicles and the dedicated traffic management communication system communication network, the traffic flow data of the signal lights at each intersection is obtained in real time, and the traffic flow of the main roads is monitored in real time through sensors, cameras, and geomagnetic equipment; By monitoring the traffic conditions at branch intersections, the traffic volume, waiting time, and queue length of each branch road can be obtained, and traffic lights can be coordinated and adjusted through real-time data transmission and sharing; By calculating the green light time of multiple intersections, a green wave band is formed. During peak hours, the system adjusts the signal cycle to extend the signal cycle of the main road and shorten the signal cycle of the branch road, and vice versa, to balance the flow and waiting time between the intersections; Continuously optimize signal control strategies through interaction with traffic flow.

8. The road traffic information monitoring method according to claim 7, characterized in that: By combining real-time data with historical data, potential accident risk points can be identified, early warnings can be issued and intervention can be carried out. Sensors can be used to monitor road temperature, humidity, weather conditions and environmental factors in real time. When severe weather occurs, the system can automatically issue warnings and adjust traffic control measures. Based on real-time data and historical data, use machine learning or deep learning methods to identify potential accident risk points, and use regression models, classification models or deep learning models based on historical data to predict the risk of accidents in the next few hours or days; Based on meteorological data, when it is detected that ice and snow, heavy rain, and haze weather conditions reach a predetermined threshold, the system automatically triggers an early warning; When a road section or intersection is identified as having a high accident risk, a risk warning is issued to notify traffic management departments and drivers based on historical data and real-time analysis. The warning information is released through multiple channels, including traffic lights, traffic signs, mobile applications, and broadcasts. Based on the prediction of bad weather and accident risks, the system automatically adjusts the cycle of traffic lights, controls traffic flow, and limits vehicle speeds; Based on the traffic flow and accident prediction results, measures such as closing some road sections or implementing temporary detours are taken in advance. Combined with the real-time traffic monitoring and early warning system, when a traffic accident occurs or a traffic accident caused by bad weather occurs, the intelligent transportation system automatically intervenes by dispatching emergency vehicles, optimizing traffic lights, and adjusting the direction of traffic through the road control system.

9. The road traffic information monitoring method according to claim 8, characterized in that: Using AI automatic recognition technology, when an accident is detected through video surveillance or sensor equipment, the system automatically alarms and notifies the traffic management center, and dispatches the nearest emergency resources. After the accident occurs, the system automatically adjusts the traffic lights, optimizes lane traffic, and adjusts the traffic flow of surrounding roads based on the predicted data. The method is as follows: Through cameras deployed on the road surface, intersections, and tunnel areas, computer vision technology is used to analyze video streams in real time, automatically identify traffic accidents or abnormal situations, and combine lane sensors to monitor vehicle speed, lane occupancy, and vehicle driving trajectory; Identify accidents through data changes, combine multi-source data from video surveillance, radar sensors, and traffic flow sensors, and perform fusion processing through AI models; Based on the AI ​​model, the system automatically identifies traffic accidents and immediately sends out automatic alarm signals to notify the traffic management center and relevant departments through SMS, phone calls, emails, and internal communications; By integrating with the emergency resource management system, the AI ​​system automatically dispatches the nearest emergency resources based on the accident type, accident location, traffic conditions, and the nearest emergency resource location; The system uses intelligent traffic signal control algorithms to adjust traffic lights in the accident area and surrounding roads in real time to optimize lane traffic. Through real-time traffic monitoring of the accident site and surrounding roads, the AI ​​system automatically adjusts the use of the following lanes: In the event of a multi-vehicle collision, the system will prioritize the use of emergency lanes or set up dedicated lanes to divert non-accident vehicles; Automatically adjust lanes when traffic jams are severe; Based on the changes in traffic flow after the accident, the AI ​​system predicts the traffic flow on surrounding roads through historical data and real-time monitoring, and guides the flow by controlling traffic lights and dispatching traffic control.

10. An electronic device, characterized in that: The method comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method for monitoring road traffic information as claimed in any one of claims 2 to 9 is implemented; A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the road traffic information monitoring method as described in any one of claims 2-9 is implemented.

Images