Early warning method and system based on highway road condition monitoring

Abstract

The present invention provides an early warning method and system based on highway road condition monitoring, which relates to the field of radio detection technology. The method integrates multi-dimensional data collected by vehicle-mounted terminals, laser radars, acoustic wave sensors and video monitoring, calculates congestion coefficients, average delay values ​​and differences, and generates a traffic condition model; based on real-time data and historical data, a traffic state prediction model is constructed, and the indicators generated by the traffic state model are used as input to generate traffic state prediction results for future time periods; an early warning threshold is set, and when the traffic state prediction results are abnormal, an early warning signal is automatically issued. The present invention monitors the traffic conditions of highways through electromagnetic wave reflection technology, and issues early warning signals in a timely manner, thereby reducing the incidence of traffic accidents and improving road safety. The early warning method and system based on highway road condition monitoring will greatly improve the intelligent level of traffic management and contribute to the construction of a safe and smooth highway network.

Description

Technical Field

[0001] The invention relates to the technical field of radio detection, and in particular to an early warning method and system based on highway road condition monitoring. Background Art

[0002] With the acceleration of urbanization and the continuous increase in the number of motor vehicles, traffic congestion and frequent accidents have become urgent problems that need to be solved worldwide. Although traditional traffic monitoring methods, such as closed-circuit television (CCTV) and ground sensors, provide road condition information to a certain extent, in high-speed environments such as highways, the field of view of traditional cameras is limited and cannot fully monitor the complex road conditions of highways, resulting in limited coverage of monitoring methods, especially the long data processing and feedback time, which cannot achieve rapid response, resulting in handling after the accident occurs.

[0003] Therefore, traditional traffic monitoring systems rely heavily on cameras and ground sensors, which make it difficult to accurately obtain highway road condition information in real time. There is an urgent need for an early warning method for highway road condition monitoring that uses lidar or satellite radio beacons as electromagnetic wave reflections to effectively monitor traffic flow, speed and vehicle status, so as to achieve intelligent early warning and meet the traffic monitoring needs of highway road conditions. Summary of the invention

[0004] In view of this, in order to solve the above problems, the present invention proposes an early warning method and system based on highway road condition monitoring, which monitors the traffic conditions of the highway through electromagnetic wave reflection technology and issues early warning signals in time, thereby reducing the incidence of traffic accidents and improving road safety.

[0005] The present invention is implemented by the following technical solutions:

[0006] In a first aspect, the present invention provides an early warning method based on highway road condition monitoring, the method comprising the following steps:

[0007] Based on the vehicle terminal installed on the vehicle, the vehicle speed, location coordinates, vehicle distance and driving record information are collected in real time and transmitted through the wireless network;

[0008] Through the LiDAR and acoustic wave sensors deployed along the highway, laser pulse scanning and acoustic wave detection are used to obtain real-time distance, speed and noise data of the surrounding environment;

[0009] The configured video surveillance system is used to capture traffic flow and vehicle behavior data in real time, and the precise location of the vehicle is obtained through satellite signals and electromagnetic wave communications, and real-time road condition information is transmitted;

[0010] The multi-dimensional data collected by the vehicle terminal, laser radar, acoustic sensor and video surveillance are integrated to calculate the congestion coefficient, average delay value and difference, and generate a traffic condition model;

[0011] Based on real-time data and historical data, a traffic status prediction model is constructed, and the indicators generated by the traffic status model are used as input to generate traffic status prediction results for future periods;

[0012] Set the warning threshold and automatically issue a warning signal when the traffic status prediction results are abnormal.

[0013] As a further solution of the present invention, the vehicle-mounted terminal installed on the vehicle includes a GPS module, an inertial measurement unit, a millimeter-wave radar, a vehicle CAN bus interface and a 5G wireless communication module; the inertial measurement unit includes an accelerometer and a gyroscope, which are used to obtain the acceleration and angular velocity of the vehicle in real time, and perform dynamic positioning in combination with GPS data; the millimeter-wave radar is used to measure the distance between the vehicle and the obstacle ahead.

[0014] As a further solution of the present invention, when a vehicle terminal is installed on the vehicle to collect the vehicle's speed, position coordinates, vehicle distance and driving record information in real time, the GPS module is combined with the inertial measurement unit to provide the vehicle's real-time position and motion state; wherein the position coordinates of the real-time position are ( ),in, is the longitude coordinate of the vehicle, is the latitude coordinate of the vehicle; Longitude correction value provided by the GPS module; The latitude correction value provided by the GPS module; Longitude correction provided to the inertial measurement unit; Latitude correction provided by the inertial measurement unit.

[0015] As a further solution of the present invention, when the vehicle speed, position coordinates, vehicle distance and driving record information are collected in real time based on the vehicle terminal installed on the vehicle, the current vehicle speed is obtained through the vehicle CAN bus interface, the distance to the obstacle in front is measured in real time using the millimeter wave radar, and the data from the GPS, IMU, CAN bus and laser radar are processed to summarize the vehicle speed, position coordinates, vehicle distance and other information to generate a data packet; the data packet is uploaded to the central monitoring system using the 5G wireless communication module; wherein the vehicle speed measurement formula is:

[0016]

[0017] In the formula, is the speed of the vehicle, in meters per second; For vehicles in the time period Distance traveled within, in meters; It is the time period, unit: second;

[0018] When using millimeter-wave radar to measure the distance to the obstacle in front in real time, the distance measurement formula to the vehicle in front is:

[0019]

[0020] In the formula, is the distance to the obstacle in front, in meters; is the propagation speed of millimeter waves in the air, unit: meter / second; It is the round-trip time of millimeter wave signal from transmission to reception, in seconds.

[0021] As a further solution of the present invention, when using laser pulse scanning and acoustic wave detection, the laser radar sends laser pulses, calculates the distance to the object through reflection ranging, records the pulse emission and reception time, and calculates the speed of the target object using multiple measurements; the acoustic wave sensor sends acoustic wave signals, measures the echo and time difference of the acoustic wave signals, and obtains the environmental noise level and the speed of the object.

[0022] As a further solution of the present invention, when the multi-dimensional data collected by the vehicle-mounted terminal, laser radar, acoustic wave sensor and video surveillance are fused, the Kalman filtering technology is used to fuse the multi-dimensional data from the vehicle-mounted terminal, laser radar, acoustic wave sensor and video surveillance to obtain the state vector, state transfer equation and observation equation of the multi-dimensional data, and predict the current state, and calculate the Kalman gain in the update phase.

[0023] As a further solution of the present invention, when calculating the congestion coefficient, the calculation formula for calculating the congestion coefficient is:

[0024]

[0025] In the formula, is the congestion coefficient, which indicates the degree of traffic congestion, 0 indicates smooth traffic, and 1 indicates complete congestion; is the free flow speed, which means the maximum flow speed of the road under ideal conditions, that is, the maximum flow speed in an uncongested state; is the actual flow speed, which indicates the vehicle speed under the current traffic conditions.

[0026] As a further solution of the present invention, when calculating the average delay value, the calculation formula for calculating the average delay value is:

[0027]

[0028] In the formula, is the average delay value; For the The actual driving time of the vehicle, is the driving time of the vehicle in the absence of congestion; is the number of vehicles passing through the measurement section.

[0029] As a further solution of the present invention, when calculating the difference, the calculation formula for calculating the difference is:

[0030]

[0031] In the formula, is the degree of difference, which indicates the degree of fluctuation of traffic flow speed; is the sample size, i.e., the number of vehicles passing through the measurement section; For the The speed of the vehicle; is the average speed of the vehicle.

[0032] As a further solution of the present invention, when generating a traffic condition model, the calculated congestion coefficient, average delay value and difference are weighted and integrated to obtain the traffic condition model.

[0033] As a further solution of the present invention, when constructing a traffic status prediction model, real-time data of the current traffic status is obtained, and historical traffic data is collected. After data cleaning and integration, features are extracted from the indicators generated by the traffic status model, including congestion coefficient, average delay value and difference. ARIMA based on time series is constructed as a prediction model, and historical data is divided into a training set and a test set. The model is trained using the training set, and hyperparameters are adjusted. The model is evaluated on the test set to obtain a trained traffic status prediction model, and the indicators generated by the traffic status model for the future time period are input to generate prediction results.

[0034] In a second aspect, the present invention also includes an early warning system based on highway road condition monitoring, the system comprising:

[0035] Data acquisition module, used to collect data from vehicle terminals, laser radar, acoustic wave sensors and video surveillance;

[0036] The data fusion module is used to integrate data from vehicle terminals, lidar, acoustic sensors and video surveillance, perform multi-source data fusion, and generate a unified data set;

[0037] Traffic condition analysis module, used to calculate key traffic indicators, generate traffic condition models, and reflect the current traffic status;

[0038] Traffic status prediction module, which is used to build a traffic status prediction model based on real-time data and historical data using machine learning or time series analysis methods, and use the generated traffic status model indicators as input to predict the traffic status in the future period;

[0039] The warning module is used to set the traffic status warning threshold and automatically issue a warning signal when the prediction result is abnormal.

[0040] As a further solution of the present invention, the data acquisition module includes:

[0041] On-board terminal: installed on each vehicle, responsible for collecting and transmitting the vehicle's speed, location coordinates, distance between vehicles and driving record information in real time.

[0042] LiDAR module: deployed along highways, it uses laser pulses to scan the environment and obtain distance and speed data of surrounding vehicles.

[0043] Acoustic wave sensor: detects environmental noise and vehicle status in real time, and provides data support for traffic flow analysis.

[0044] Video surveillance system: capture traffic flow and vehicle behavior in real time, and analyze traffic density and direction.

[0045] Satellite positioning module: obtains the precise location of the vehicle through satellite signals and transmits real-time traffic information;

[0046] Satellite signal and electromagnetic wave module: obtain the precise location of the vehicle and transmit real-time traffic information.

[0047] As a further solution of the present invention, the key traffic indicators calculated include congestion coefficient, average delay value and difference.

[0048] The present invention also includes a computer device, comprising: at least one processor, and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor executes the early warning method based on highway road condition monitoring.

[0049] The present invention also includes a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the early warning method based on highway road condition monitoring.

[0050] Compared with the prior art, the early warning method and system based on highway road condition monitoring provided by the present invention has the following beneficial effects:

[0051] 1. Real-time traffic monitoring and safety improvement. The system of the present invention can continuously monitor the traffic status of the highway to ensure that any changes can be captured in time, thereby providing accurate data support for the management department. Through real-time data analysis and early warning mechanisms, potential dangerous situations can be quickly identified, accidents can be reduced, and the safety of drivers and passengers can be guaranteed.

[0052] 2. Effective traffic flow management and rapid emergency response are achieved. The method of the present invention can analyze traffic flow in real time and identify congestion, thereby achieving more efficient traffic flow scheduling and optimizing traffic flow. When a traffic accident or emergency occurs, the system can immediately issue an early warning to help relevant departments respond quickly and reduce the consequences of the accident.

[0053] 3. Reduced traffic delays and improved travel efficiency. By predicting traffic conditions, the present invention allows drivers to obtain more accurate travel information and choose the best travel time and route, thereby effectively reducing travel delays. Drivers and passengers can adjust their itineraries based on real-time traffic information, reduce waiting time, improve overall travel efficiency, and provide traffic information and early warning notifications in a timely manner, making the public's travel experience more convenient and comfortable, and enhancing travel satisfaction.

[0054] In summary, the early warning method and system based on highway road condition monitoring of the present invention will greatly improve the intelligent level of traffic management and contribute to building a safe and smooth highway network.

[0055] These and other aspects of the present invention will be more clearly understood in the following description of the embodiments. It should be understood that the above general description and the following detailed description are only exemplary and explanatory and cannot limit the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or related technologies, the following briefly introduces the drawings required for use in the exemplary embodiments or related technical descriptions. The drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation to the present invention. In the drawings:

[0057] Figure 1 The figure is a flow chart of an early warning method based on highway road condition monitoring according to an embodiment of the present invention.

[0058] Figure 2 The figure is a structural block diagram of an early warning system based on highway road condition monitoring according to an embodiment of the present invention. DETAILED DESCRIPTION

[0059] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0060] In some of the processes described in the specification and claims of the present invention and the above-mentioned figures, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this article or executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., do not represent the order of precedence, and do not limit the "first" and "second" to be different types.

[0061] The following will be combined with the drawings in the exemplary embodiments of the present invention to clearly and completely describe the technical solutions in the exemplary embodiments of the present invention. Obviously, the exemplary embodiments described are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0062] In high-speed environments such as highways, the field of view of traditional cameras is limited and they are unable to fully monitor the complex road conditions of highways, resulting in limited coverage of monitoring methods. In particular, data processing and feedback time is long, and rapid response cannot be achieved, resulting in accidents being handled only after they occur. The present invention provides an early warning method and system based on highway road condition monitoring, which monitors the traffic conditions of highways through electromagnetic wave reflection technology and sends out early warning signals in a timely manner, thereby reducing the incidence of traffic accidents and improving road safety.

[0063] The technical solution of the present invention is further described below in conjunction with specific embodiments:

[0064] See also Figure 1 As shown, Figure 1 A flowchart of an early warning method based on highway road condition monitoring provided by the present invention. An early warning method based on highway road condition monitoring provided in one embodiment of the present invention comprises the following steps:

[0065] Step S10: Based on the vehicle-mounted terminal installed on the vehicle, the vehicle's speed, position coordinates, vehicle distance and driving record information are collected in real time and transmitted through the wireless network.

[0066] In this step, the vehicle terminal installed on the vehicle includes a GPS module, an inertial measurement unit, a millimeter-wave radar, a vehicle CAN bus interface and a 5G wireless communication module; the inertial measurement unit includes an accelerometer and a gyroscope, which are used to obtain the acceleration and angular velocity of the vehicle in real time, and perform dynamic positioning in combination with GPS data; the millimeter-wave radar is used to measure the distance between the vehicle and the obstacle in front.

[0067] Wherein, when the vehicle terminal installed on the vehicle collects the vehicle's speed, position coordinates, vehicle distance and driving record information in real time, the GPS module is combined with the inertial measurement unit to provide the vehicle's real-time position and motion status; wherein the position coordinates of the real-time position are ( ),in, is the longitude coordinate of the vehicle, is the latitude coordinate of the vehicle; Longitude correction value provided by the GPS module; The latitude correction value provided by the GPS module; Longitude correction provided to the inertial measurement unit; Latitude correction provided by the inertial measurement unit.

[0068] When the vehicle terminal installed on the vehicle collects the vehicle's speed, position coordinates, vehicle distance and driving record information in real time, the current vehicle speed is obtained through the vehicle CAN bus interface, and the distance to the obstacle in front is measured in real time using the millimeter-wave radar. The data from GPS, IMU, CAN bus and millimeter-wave radar are processed, and the vehicle's speed, position coordinates, vehicle distance and other information are summarized to generate a data packet; the 5G wireless communication module is used to upload the data packet to the central monitoring system; the vehicle speed measurement formula is:

[0069]

[0070] In the formula, is the speed of the vehicle, in meters per second; For vehicles in the time period Distance traveled within, in meters; It is the time period, unit: second;

[0071] When using millimeter-wave radar to measure the distance to the obstacle in front in real time, the distance measurement formula to the vehicle in front is:

[0072]

[0073] In the formula, is the distance to the obstacle in front, in meters; is the propagation speed of millimeter waves in the air, unit: meter / second; It is the round-trip time of millimeter wave signal from transmission to reception, in seconds.

[0074] When data is transmitted, the wireless communication module is used to upload the data packet to the central monitoring system through the 4G / 5G network. The transmission protocol can use the MQTT or HTTP protocol to ensure the real-time and reliability of the data. Therefore, when collecting data, the vehicle terminal receives the data from the GPS, speed and vehicle distance sensors every second during the vehicle's driving process. The data processing unit aggregates the sensor data, generates a data packet, and uploads the data packet to the central monitoring system through the wireless network.

[0075] For example, when monitoring and warning are performed by the early warning method based on highway road condition monitoring of this embodiment, when the vehicle-mounted terminal of a selected target vehicle is driving, the data collection process is as follows:

[0076] 1. Timestamp: 2024-09-18 12:00:00;

[0077] 2. Vehicle speed sensor: updated every second, current value is 80 km / h;

[0078] 3.GPS module: longitude 34.0522, latitude -118.2437;

[0079] 4. Radar sensor: The current distance to the vehicle in front is 15 meters;

[0080] The final generated data packet is as follows:

[0081] {

[0082] "timestamp": "2024-09-18T12:00:00Z",

[0083] "vehicle_id": "XYZ789",

[0084] "speed": 80.0,

[0085] "location": {

[0086] "latitude": 34.0522,

[0087] "longitude": -118.2437

[0088] },

[0089] "distance_to_front": 15.0

[0090] }

[0091] The data packet is sent to the central monitoring system via the 4G / 5G network for real-time monitoring and analysis, thereby providing accurate data support for highway road condition monitoring.

[0092] Step S20: Using laser radar and acoustic wave sensors deployed along the highway, laser pulse scanning and acoustic wave detection are used to obtain real-time distance, speed and noise data of the surrounding environment.

[0093] In this step, when using laser pulse scanning and acoustic wave detection, the laser radar sends laser pulses, calculates the distance to the object through reflection ranging, records the pulse emission and reception time, and calculates the speed of the target object using multiple measurements; the acoustic wave sensor sends acoustic wave signals, measures the echo and time difference of the acoustic wave signals, and obtains the environmental noise level and the speed of the object.

[0094] The calculation formula for the ambient noise level is:

[0095]

[0096] In the formula, is the noise level (dB); is the measured sound power (Watt); is the reference sound power.

[0097] When performing laser pulse scanning and acoustic wave detection, the lidar emits pulses at regular intervals to capture reflected signals. The system calculates distance, speed, and noise level, and updates data in real time; the data is uploaded to the central monitoring system via a wireless network.

[0098] For example, suppose that a LiDAR and an acoustic wave sensor are deployed on a certain section of a highway. When the LiDAR measures distance, the round-trip time of the reflected signal is measured to be 2 microseconds. Therefore: Meters; when calculating speed, if the vehicle in front moves 25 meters in 1 second, the speed is: m / s = 90 km / h; when measuring noise, the sound wave sensor measures the sound power as Watt, the noise level is: dB.

[0099] With the above data, the monitoring system can analyze traffic conditions and environmental noise in real time and respond to potential problems in a timely manner.

[0100] Step S30: Use the configured video surveillance system to capture traffic flow and vehicle behavior data in real time, and obtain the precise location of the vehicle through satellite signals and electromagnetic wave communications, and transmit real-time road condition information.

[0101] In this step, the video surveillance system includes high-definition cameras installed along the highway to capture traffic flow and vehicle behavior; GPS modules are used to obtain the precise location of vehicles, and electromagnetic wave communication equipment is used to transmit real-time data to the central monitoring system. During data collection, after the video surveillance data is captured, the video stream is analyzed through image processing to obtain traffic flow, including the number, speed, and type of vehicles; then the real-time location of the vehicle is obtained through GPS, and the video data and GPS information are transmitted to the central monitoring system through electromagnetic wave communication equipment. The central system processes the received data, generates real-time road condition information, and transmits it to the driver and traffic management department.

[0102] For example, assuming that 10 cameras and multiple GPS devices are deployed on a highway section, the system can monitor the number, speed and location of vehicles in real time. Within 10 seconds, 100 vehicles with an average speed of 80 km / h (about 22.2 m / s) are captured, and the location of all vehicles is obtained through GPS, and a real-time traffic report is generated and released to users and traffic management departments in a timely manner, which not only improves the accuracy of traffic monitoring, but also lays the foundation for the development of intelligent transportation systems.

[0103] Step S40: Fuse the multi-dimensional data collected by the vehicle terminal, laser radar, acoustic sensor and video surveillance, calculate the congestion coefficient, average delay value and difference, and generate a traffic condition model.

[0104] In this step, when the multi-dimensional data collected by the vehicle terminal, laser radar, acoustic wave sensor and video surveillance are integrated, the Kalman filtering technology is used to integrate the multi-dimensional data from the vehicle terminal, laser radar, acoustic wave sensor and video surveillance to obtain the state vector, state transfer equation and observation equation of the multi-dimensional data, and predict the current state. The Kalman gain is calculated in the update stage.

[0105] Among them, the state transfer equation is:

[0106]

[0107] In the formula, is the current state vector; is the state transfer matrix; is the control input matrix; is the control input; is the process noise.

[0108] The observation equation is: , where is the observation vector; is the observation matrix; is the observation noise.

[0109] Among them, when calculating the congestion coefficient, the calculation formula for calculating the congestion coefficient is:

[0110]

[0111] In the formula, is the congestion coefficient, which indicates the degree of traffic congestion, 0 indicates smooth traffic, and 1 indicates complete congestion; is the free flow speed, which means the maximum flow speed of the road under ideal conditions, that is, the maximum flow speed in an uncongested state; is the actual flow speed, which indicates the vehicle speed under the current traffic conditions.

[0112] When calculating the average delay value, the calculation formula for the average delay value is:

[0113]

[0114] In the formula, is the average delay value; For the The actual driving time of the vehicle, is the driving time of the vehicle in the absence of congestion; is the number of vehicles passing through the measurement section.

[0115] When calculating the difference, the calculation formula for calculating the difference is:

[0116]

[0117] In the formula, is the degree of difference, which indicates the degree of fluctuation of traffic flow speed; is the sample size, i.e., the number of vehicles passing through the measurement section; For the The speed of the vehicle; is the average speed of the vehicle.

[0118] When generating a traffic condition model, the calculated congestion coefficient, average delay value and difference are weighted and integrated to obtain the traffic condition model.

[0119] For example, assume that multiple sensors are deployed on a highway section and the following data is collected:

[0120] Vehicle terminal: The average speed data of 30 vehicles is 60 km / h (about 16.67 m / s).

[0121] LiDAR: The average distance is 10 meters, and the traffic flow is calculated to be 100 vehicles per hour.

[0122] Acoustic sensor: Noise levels of 80 dB indicate possible congestion.

[0123] Video surveillance: The number of vehicles detected is 50.

[0124] Based on these data, the congestion coefficient, average delay value and difference are calculated in turn. Among them:

[0125] (1) Calculation of congestion coefficient:

[0126]

[0127] (2) Calculate the average delay value: Assume that the travel time is 120 seconds without congestion and the actual travel time is 150 seconds:

[0128]

[0129] (3) Calculate the difference, assuming the speed is: .

[0130] The above data will eventually be integrated to generate a traffic condition model, which will ensure smooth and safe traffic flow through continuous monitoring and adjustment.

[0131] Among them, when the traffic condition model is obtained by combining the calculated congestion coefficient, average delay value and difference through weighted synthesis, ;in, is the traffic condition model indicator; , , is the weight of each indicator, assuming the weight , , ; Then the traffic condition model is:

[0132] .

[0133] Through this model, traffic conditions can be evaluated in real time and decision support can be provided for traffic management.

[0134] Step S50: construct a traffic status prediction model based on real-time data and historical data, and use the indicators generated by the traffic status model as input to generate traffic status prediction results for future time periods.

[0135] In this step, when building a traffic status prediction model, real-time data of the current traffic status is obtained, and historical traffic data is collected. After data cleaning and integration, features are extracted from the indicators generated by the traffic status model, including congestion coefficient, average delay value and difference. A time series-based ARIMA is built as a prediction model, and historical data is divided into a training set and a test set. The model is trained using the training set, and the hyperparameters are adjusted. The model is evaluated on the test set to obtain a trained traffic status prediction model. The indicators generated by the traffic status model for the future period are input to generate prediction results.

[0136] Step S60: Set a warning threshold and automatically issue a warning signal when the traffic status prediction result is abnormal.

[0137] For example, the predicted congestion coefficient for the next hour is 0.7. Through the above steps, a traffic status prediction model can be effectively constructed and utilized to improve the management and scheduling capabilities of highways.

[0138] Suppose a highway detects the following data during a certain period of time:

[0139] Congestion coefficient C = 0.8

[0140] Average delay D = 15 minutes

[0141] Difference Δ=10 km / h

[0142] Based on historical data analysis, the congestion coefficient during this period is usually below 0.5, and the delay value does not exceed 5 minutes. Since the current indicators are beyond the normal range, the system will automatically trigger an early warning and recommend that car owners avoid this section of the road.

[0143] This early warning method improves the safety and traffic efficiency of highways by comprehensively utilizing data from multiple sensors and combining it with intelligent prediction technology, and can respond to potential traffic problems in a timely manner.

[0144] The present invention provides an early warning method based on highway road condition monitoring, which can continuously monitor the traffic status of the highway and ensure that any changes can be captured in time, thereby providing accurate data support for the management department. Through real-time data analysis and early warning mechanisms, potential dangerous situations can be quickly identified, accidents can be reduced, and the safety of drivers and passengers can be guaranteed. Traffic flow can be analyzed in real time, congestion can be identified, so as to achieve more efficient traffic flow scheduling and optimize traffic flow. When a traffic accident or emergency occurs, the system can immediately issue an early warning to help relevant departments respond quickly and reduce the consequences of the accident.

[0145] The early warning method based on highway road condition monitoring of the present invention can also predict traffic conditions, so that drivers can obtain more accurate travel information and choose the best travel time and route, thereby effectively reducing driving delays. Drivers and passengers can adjust their itineraries based on real-time road condition information, reduce waiting time, improve overall travel efficiency, and provide road condition information and early warning notifications in a timely manner, making the public's travel experience more convenient and comfortable, and enhancing travel satisfaction.

[0146] It should be understood that, although described in a certain order, these steps are not necessarily performed in sequence in the above order. Unless there is clear explanation in this article, the execution of these steps does not have strict order restriction, and these steps can be performed in other orders. Moreover, a part of the steps of the present embodiment may include a plurality of steps or a plurality of stages, and these steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with at least a part of the steps or stages in other steps or other steps.

[0147] In one embodiment, see Figure 2 As shown, the present invention provides an early warning system based on highway road condition monitoring, which is used to execute the above-mentioned early warning method based on highway road condition monitoring, and the system includes:

[0148] Data acquisition module 1, used to collect data from vehicle terminals, laser radar, acoustic wave sensors and video surveillance;

[0149] Data fusion module 2 is used to integrate data from vehicle terminals, laser radar, acoustic wave sensors and video surveillance, perform multi-source data fusion, and generate a unified data set;

[0150] Traffic condition analysis module 3 is used to calculate key traffic indicators, generate a traffic condition model, and reflect the current traffic status; wherein the calculated key traffic indicators include congestion coefficient, average delay value, and difference;

[0151] Traffic status prediction module 4, used to construct a traffic status prediction model based on real-time data and historical data by using machine learning or time series analysis methods, and use the generated traffic status model indicators as input to predict the traffic status in the future period;

[0152] The warning module 5 is used to set the traffic status warning threshold and automatically send out a warning signal when the prediction result is abnormal.

[0153] In this embodiment, the data acquisition module includes:

[0154] Vehicle terminal 101: installed on each vehicle, responsible for collecting and transmitting the vehicle's speed, position coordinates, vehicle distance and driving record information in real time.

[0155] LiDAR module 102: deployed along the highway, uses laser pulses to scan the environment and obtain distance and speed data of surrounding vehicles.

[0156] Acoustic wave sensor 103: detects environmental noise and vehicle status in real time, and provides data support for traffic flow analysis.

[0157] Video surveillance system 104: capturing traffic flow and vehicle behavior in real time, and analyzing traffic density and direction;

[0158] Satellite signal and electromagnetic wave module 105: obtains the precise location of the vehicle and transmits real-time traffic information.

[0159] In this embodiment, the early warning system based on highway road condition monitoring adopts the steps of the early warning method based on highway road condition monitoring as mentioned above during execution. Therefore, the operation process of the early warning system based on highway road condition monitoring will not be introduced in detail in this embodiment.

[0160] In summary, the early warning method and system based on highway road condition monitoring of the present invention will greatly enhance the intelligent level of traffic management and contribute to building a safe and smooth highway network.

[0161] In one embodiment, a computer device is also provided in an embodiment of the present invention, comprising at least one processor and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor performs the steps of the early warning method based on highway road condition monitoring.

[0162] In one embodiment, the present invention further provides a computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable the computer to execute the steps of the early warning method based on highway road condition monitoring.

[0163] A person skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be realized by instructing the relevant hardware through a computer program represented by computer instructions, 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 at least one of non-volatile and volatile memory.

[0164] Non-volatile memory may include read-only memory, magnetic tape, floppy disk, flash memory or optical storage, etc. Volatile memory may include random access memory or external cache memory. As an illustration and not limitation, RAM may be in various forms, such as static random access memory or dynamic random access memory, etc.

[0165] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A warning method based on highway road condition monitoring, characterized in that: The method comprises the following steps: Based on the vehicle terminal installed on the vehicle, the vehicle speed, location coordinates, vehicle distance and driving record information are collected in real time and transmitted through the wireless network; Through the LiDAR and acoustic wave sensors deployed along the highway, laser pulse scanning and acoustic wave detection are used to obtain real-time distance, speed and noise data of the surrounding environment; The configured video surveillance system is used to capture traffic flow and vehicle behavior data in real time, and the precise location of the vehicle is obtained through satellite signals and electromagnetic wave communications, and real-time road condition information is transmitted; The multi-dimensional data collected by the vehicle terminal, laser radar, acoustic sensor and video surveillance are integrated to calculate the congestion coefficient, average delay value and difference, and generate a traffic condition model; Based on real-time data and historical data, a traffic status prediction model is constructed, and the indicators generated by the traffic status model are used as input to generate traffic status prediction results for future periods; Set warning thresholds and automatically issue warning signals when traffic status prediction results are abnormal; Among them, when fusing the multi-dimensional data collected by the vehicle terminal, laser radar, acoustic sensor and video surveillance, the Kalman filter technology is used to fuse the multi-dimensional data from the vehicle terminal, laser radar, acoustic sensor and video surveillance to obtain the state vector, state transfer equation and observation equation of the multi-dimensional data, and predict the current state. The Kalman gain is calculated in the update stage; Among them, the state transfer equation is: In the formula, is the current state vector; is the state transfer matrix; is the control input matrix; is the control input; is the process noise; The observation equation is: , where is the observation vector; is the observation matrix; is the observation noise; Among them, when calculating the congestion coefficient, the calculation formula for calculating the congestion coefficient is: In the formula, is the congestion coefficient, which indicates the degree of traffic congestion, 0 indicates smooth traffic, and 1 indicates complete congestion; is the free flow speed, which means the maximum flow speed of the road under ideal conditions, that is, the maximum flow speed in an uncongested state; is the actual flow speed, which indicates the vehicle speed under the current traffic conditions; When calculating the average delay value, the calculation formula for calculating the average delay value is: In the formula, is the average delay value; For the The actual driving time of the vehicle, is the driving time of the vehicle in the absence of congestion; is the number of vehicles passing through the measurement section; When calculating the difference, the calculation formula for calculating the difference is: In the formula, is the degree of difference, which indicates the degree of fluctuation of traffic flow speed; is the sample size, i.e., the number of vehicles passing through the measurement section; For the The speed of the vehicle; is the average speed of the vehicle.

2. The early warning method based on highway road condition monitoring as claimed in claim 1, characterized in that: The vehicle-mounted terminal installed on the vehicle includes a GPS module, an inertial measurement unit, a millimeter-wave radar, a vehicle CAN bus interface and a 5G wireless communication module; the inertial measurement unit includes an accelerometer and a gyroscope, which are used to obtain the acceleration and angular velocity of the vehicle in real time and perform dynamic positioning in combination with GPS data; the millimeter-wave radar is used to measure the distance between the vehicle and the obstacle in front.

3. The early warning method based on highway road condition monitoring as claimed in claim 2, characterized in that: When the vehicle terminal installed on the vehicle collects the vehicle's speed, position coordinates, vehicle distance and driving record information in real time, the GPS module is combined with the inertial measurement unit to provide the vehicle's real-time position and motion status; wherein the position coordinates of the real-time position are ,in, is the longitude coordinate of the vehicle, is the latitude coordinate of the vehicle; Longitude correction value provided by the GPS module; The latitude correction value provided by the GPS module; Longitude correction provided to the inertial measurement unit; Latitude correction provided to the inertial measurement unit.

4. The early warning method based on highway road condition monitoring as claimed in claim 3, characterized in that: Based on the on-board terminal installed on the vehicle, the vehicle's speed, position coordinates, vehicle distance and driving record information are collected in real time. The current vehicle speed is obtained through the vehicle's CAN bus interface, and the millimeter-wave radar is used to measure the distance to the obstacle in front in real time. The data from GPS, IMU, CAN bus and lidar are processed, and the vehicle's speed, position coordinates, and vehicle distance information are summarized to generate a data packet; the 5G wireless communication module is used to upload the data packet to the central monitoring system.

5. The early warning method based on highway road condition monitoring as claimed in claim 4, characterized in that: When using laser pulse scanning and sound wave detection, the laser radar sends laser pulses, measures the distance to the object through reflection, records the pulse emission and reception time, and uses multiple measurements to calculate the speed of the target object; The acoustic wave sensor transmits acoustic wave signals, measures the echo and time difference of the acoustic wave signals, and obtains the ambient noise level and the speed of the object.

6. An early warning system based on highway road condition monitoring, characterized in that: Used to execute the early warning method based on highway road condition monitoring as described in any one of claims 1 to 5, the early warning system based on highway road condition monitoring comprises: Data acquisition module, used to collect data from vehicle terminals, laser radar, acoustic wave sensors and video surveillance; The data fusion module is used to integrate data from vehicle terminals, lidar, acoustic sensors and video surveillance, perform multi-source data fusion, and generate a unified data set; Traffic condition analysis module, used to calculate key traffic indicators, generate traffic condition models, and reflect the current traffic status; Traffic status prediction module, which is used to build a traffic status prediction model based on real-time data and historical data by using machine learning or time series analysis methods, and use the generated traffic status model indicators as input to predict the traffic status in the future period; The warning module is used to set the traffic status warning threshold and automatically issue a warning signal when the prediction result is abnormal.

Images