Road traffic accident monitoring and alarming method and system

Abstract

The invention discloses a road traffic accident monitoring and alarming method and system, and relates to the technical field of data processing. The method comprises the following steps: acquiring vehicle speed values, vehicle distance values and driving tracks of a plurality of vehicles on a road to be monitored; calculating a speed change rate according to the vehicle speed value of each vehicle, calculating a distance change rate according to the vehicle distance value of each vehicle, and calculating a vehicle transverse offset according to each driving track; when the speed change rate, the distance change rate or the vehicle lateral offset exceeds the corresponding standard threshold value, determining that a traffic accident occurs on the road to be monitored; receiving the lane occupancy rate, the traffic flow density and the average passing speed of the road to be monitored; and determining an accident grade corresponding to the traffic accident based on the lane occupancy rate, the traffic flow density and the average passing speed, and generating alarm information of the accident grade corresponding to the traffic accident. By implementing the technical scheme provided by the invention, the effect of improving the road traffic accident monitoring and alarming efficiency is achieved.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a road traffic accident monitoring and alarm method, system, electronic equipment and storage medium. Background Art

[0002] With the acceleration of urbanization and the continuous growth of motor vehicle ownership, frequent road traffic accidents have become an important factor affecting urban traffic safety and operation efficiency. Timely detection and handling of traffic accidents is of great significance to reducing traffic congestion and reducing the risk of secondary accidents.

[0003] At present, the existing road traffic accident monitoring and alarm methods mainly rely on manual real-time monitoring through traffic cameras, and the staff observes and determines whether a traffic accident has occurred and issues an alarm. However, in actual applications, the real-time monitoring method by staff consumes a lot of human resources. When there are multiple traffic accidents, the manual monitoring and alarm method alone often has a time lag, which is not conducive to the timely handling of accidents, resulting in low efficiency of road traffic accident monitoring and alarm. Summary of the invention

[0004] The present application provides a road traffic accident monitoring and alarm method and system, which has the effect of improving the efficiency of road traffic accident monitoring and alarm.

[0005] In a first aspect, the present application provides a road traffic accident monitoring and alarm method, comprising: Acquire vehicle running status data of the road to be monitored, wherein the vehicle running status data includes speed values, vehicle distance values, and driving trajectories of multiple vehicles; Calculating the speed change rate between any two adjacent vehicles according to the vehicle speed value of each vehicle, calculating the distance change rate between any two adjacent vehicles according to the vehicle distance value of each vehicle, and calculating the vehicle lateral offset of each vehicle according to each driving trajectory; When the speed change rate, the distance change rate or the vehicle lateral offset exceeds the corresponding standard threshold, it is determined that a traffic accident occurs on the road to be monitored; Receiving road status data of the road to be monitored, wherein the road status data includes lane occupancy rate, traffic flow density and average travel speed; Based on the lane occupancy rate, the traffic flow density and the average travel speed, the accident level corresponding to the traffic accident is determined, and alarm information of the accident level corresponding to the traffic accident is generated.

[0006] In a second aspect of the present application, a road traffic accident monitoring and alarm system is provided, the system comprising: A data acquisition module, used to acquire vehicle running status data of the road to be monitored, wherein the vehicle running status data includes vehicle speed values, vehicle distance values ​​and driving trajectories of multiple vehicles; A data processing module, used to calculate the speed change rate between any two adjacent vehicles according to the speed value of each vehicle, calculate the distance change rate between any two adjacent vehicles according to the vehicle distance value of each vehicle, and calculate the vehicle lateral offset of each vehicle according to each driving trajectory; An accident monitoring module, configured to determine that a traffic accident occurs on the road to be monitored when the speed change rate, the distance change rate or the vehicle lateral offset exceeds a corresponding standard threshold; The accident alarm module is used to receive the road status data of the road to be monitored, the road status data including lane occupancy, traffic flow density and average travel speed; based on the lane occupancy, traffic flow density and average travel speed, determine the accident level corresponding to the traffic accident, and generate alarm information of the accident level corresponding to the traffic accident.

[0007] In a third aspect of the present application, an electronic device is provided, comprising a memory, a processor, and a program stored in the memory and executable on the processor, wherein the program can implement a road traffic accident monitoring and alarm method when loaded and executed by the processor.

[0008] In a fourth aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor implements a road traffic accident monitoring and alarm method.

[0009] In summary, one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: By adopting the above technical solution, the vehicle operation status data is collected and analyzed, including multi-dimensional information such as vehicle speed, vehicle distance and driving trajectory. By calculating the speed change rate, distance change rate and lateral offset of adjacent vehicles, the system can capture the abnormal behavior characteristics of the vehicle during operation. When these characteristic indicators exceed the preset standard threshold, the system can quickly determine the occurrence of a traffic accident, which reduces the delay time of accident discovery compared to manual data analysis by staff. Secondly, after determining that a traffic accident has occurred, the impact assessment mechanism based on road status data is immediately started. By analyzing key indicators such as lane occupancy, traffic flow density and average speed, the system can comprehensively assess the impact of the accident on the road's traffic capacity. This multi-dimensional assessment method not only considers the direct impact of the accident on the current traffic flow, but also predicts the chain reaction it may cause, providing a basis for the accurate determination of the accident level. Finally, by generating alarm information corresponding to the accident level, a closed-loop management from accident discovery to impact assessment to warning issuance is realized. This hierarchical warning mechanism based on the actual impact level realizes timely monitoring and alarm of road traffic through comprehensive analysis of vehicle status data and road status data, and improves the efficiency of emergency response to traffic accidents. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 It is a flow chart of a road traffic accident monitoring and alarm method provided in an embodiment of the present application; Figure 2 It is a structural diagram of a road traffic accident monitoring and alarm system provided in an embodiment of the present application; Figure 3 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application.

[0011] Description of reference numerals: 300, electronic device; 301, processor; 302, communication bus; 303, user interface; 304, network interface; 305, memory. DETAILED DESCRIPTION

[0012] In order to enable technicians in this field to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments.

[0013] In the description of the embodiments of the present application, words such as "for example" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "for example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "for example" or "for example" is intended to present related concepts in a specific way.

[0014] In the description of the embodiments of the present application, the meaning of the term "multiple" refers to two or more. For example, multiple systems refer to two or more systems, and multiple screen terminals refer to two or more screen terminals. In addition, the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. The terms "include", "comprise", "have" and their variations all mean "including but not limited to", unless otherwise specifically emphasized.

[0015] The present application embodiment provides a road traffic accident monitoring and alarm method. In one embodiment, please refer to Figure 1 , Figure 1 The present invention provides a road traffic accident monitoring and alarm method provided by the embodiment of the present invention. The method can be implemented by a computer program, which can be integrated into an application or run as an independent tool application. The method can also be implemented by a single-chip microcomputer or run on a road traffic accident monitoring and alarm system based on the von Neumann system. Specifically, the method can include the following steps: Step 101: Acquire vehicle operation status data of a road to be monitored, where the vehicle operation status data includes speed values, vehicle distance values, and driving trajectories of multiple vehicles.

[0016] Among them, vehicle operation status data refers to a set of key parameters that can reflect the real-time operation status of vehicles on the road, specifically including the speed values, vehicle distance values ​​and driving trajectories of multiple vehicles.

[0017] The speed value indicates the instantaneous speed of the vehicle on the road. The distance value indicates the relative distance between any two adjacent vehicles. The driving trajectory records the movement path of the vehicle on the road plane in the form of a coordinate sequence.

[0018] Specifically, multiple sensors deployed on the road to be monitored collect vehicle operation status data in real time. Specifically, the vehicle speed and distance values ​​can be obtained through radar sensors, and the vehicle driving trajectory data can be collected through video sensors. Among them, the speed value reflects the driving speed of the vehicle on the road, which helps to determine whether the vehicle has abnormal situations such as sudden braking or rear-end collision; the distance value represents the distance between adjacent vehicles, which can be used to identify whether the vehicle maintains a safe driving distance; the driving trajectory records the movement path of the vehicle on the road, which can detect whether the vehicle has abnormal lane changes or deviates from the driving route. These sensors continuously collect data at a preset sampling frequency, such as 10 times per second, to ensure that changes in the vehicle's operating status can be captured in a timely manner. The collected data is transmitted in real time to the data processing server of the traffic monitoring center through the road communication network. The server pre-processes the received data, including data cleaning, format unification and other operations, to form a standardized vehicle operation status data set. By acquiring these vehicle operating status data, an accurate data basis is provided for the subsequent calculation of key indicators such as speed change rate, distance change rate and vehicle lateral offset, thereby enabling rapid and automatic identification of traffic accidents, overcoming the problems of delayed response and high misjudgment rate in traditional manual monitoring methods, and significantly improving the efficiency and accuracy of road traffic accident monitoring.

[0019] Step 102: Calculate the speed change rate between any two adjacent vehicles based on the speed value of each vehicle, calculate the distance change rate between any two adjacent vehicles based on the vehicle distance value of each vehicle, and calculate the vehicle lateral offset of each vehicle based on each driving trajectory.

[0020] The speed change rate refers to the ratio of the speed difference between any two adjacent vehicles to their relative distance within a preset time period. For two adjacent vehicles, the speed change rate is equal to the speed of the rear vehicle minus the speed of the front vehicle divided by the distance between the two vehicles. This indicator reflects the relative speed difference between adjacent vehicles.

[0021] The distance change rate refers to the ratio of the distance change value between any two adjacent vehicles within a preset time period to the time period. The distance change rate is calculated by subtracting the distance value at the preset end time from the distance value at the preset start time, and then dividing it by the time interval between the two times. This indicator directly reflects the dynamic change speed of the distance between adjacent vehicles.

[0022] The lateral deviation of a vehicle can be understood as a quantitative indicator of the degree to which the vehicle deviates from its normal driving path. The average driving direction angle represents the expected driving direction of the vehicle over a longer time scale and reflects the basic direction of the road; while the actual driving direction angle represents the current instantaneous direction of movement of the vehicle. The greater the difference between the two, the more unstable the vehicle's driving trajectory is, and there may be dangerous situations such as abnormal lane changes, loss of control or rollover.

[0023] Specifically, the speed change rate between any two adjacent vehicles is calculated based on the vehicle speed value. The system divides a preset time period, such as 5 seconds, into multiple time sampling points, obtains the instantaneous speed of adjacent vehicles at each sampling point, calculates the speed difference, and divides the difference by the relative distance between the two vehicles to obtain the speed change rate. This indicator can effectively reflect the relative motion state between vehicles. When an accident such as a rear-end collision occurs, the speed change rate usually fluctuates significantly. Secondly, the system calculates the distance change rate between any two adjacent vehicles. Specifically, by comparing the distance values ​​between the two vehicles at the preset start time and the preset end time, the distance change value is calculated, and then the value is divided by the corresponding time interval to obtain the distance change rate. This indicator can reflect the dynamic change trend of the distance between vehicles. When a rapid approach or collision occurs, the distance change rate will show abnormal change characteristics. Finally, the system calculates the lateral offset of the vehicle according to the vehicle's driving trajectory. Specifically, by analyzing the angle between the average driving direction angle of the vehicle and the actual driving direction angle, combined with the driving distance, the lateral offset degree of the vehicle is calculated. This indicator can effectively identify whether the vehicle has an accident type such as rollover, loss of control or abnormal lane change. The calculation process of these three indicators is independent of each other, but the results confirm each other, forming a comprehensive accident identification system. For example, when a vehicle is involved in a rear-end collision, it will not only be reflected in the sharp change in the speed change rate, but may also be accompanied by an abnormal distance change rate and an increase in lateral offset. This multi-indicator collaborative judgment method improves the accuracy of accident identification.

[0024] Based on the above embodiment, as an optional embodiment, in step 102: calculating the speed change rate between any two adjacent vehicles according to the speed value of each vehicle, this step may also include the following steps: Step 201: Based on the speed value of each vehicle, determine the speed values ​​of any two adjacent vehicles within a preset time period.

[0025] Specifically, a preset time period is first set, for example, 5 seconds. The selection of this time period needs to balance the requirements of data validity and real-time performance: a time period that is too short may not fully reflect the changing trend of the vehicle's motion state, while a time period that is too long will reduce the timeliness of the system response. After determining the preset time period, the system divides the time period into multiple uniform sampling moments, for example, one sampling point every 0.5 seconds, so as to obtain data from 10 sampling points in each preset time period. For each pair of adjacent vehicles on the road, the system records their instantaneous vehicle speed values ​​at these sampling moments. Among them, the determination of adjacent vehicles is based on the front and rear position relationship of the vehicle in the same lane, which is determined by the vehicle's position coordinates and driving direction. To ensure the accuracy of the data, the system will pre-process the collected vehicle speed values. First, outlier detection is performed to eliminate speed data that obviously deviates from the reasonable range; then interpolation processing is performed on possible data missing to ensure data continuity within the preset time period. For changes in the relationship between adjacent vehicles caused by lane changes, the system dynamically updates the pairing relationship of adjacent vehicles by tracking the movement trajectory of the vehicle. This method of determining vehicle speed values ​​based on a time window can not only accurately capture the dynamic changes in vehicle speed, but also provide a reliable data basis for the subsequent calculation of the speed change rate.

[0026] Step 202: Divide the preset time period into a plurality of time sampling points; calculate the speed difference between any two adjacent vehicles at each time sampling point.

[0027] The multiple time sampling points refer to a series of discrete time points obtained by evenly dividing the preset time period. Within the preset time period, sampling is performed at fixed time intervals to form a time series containing multiple time points. Each sampling point corresponds to a specific timestamp, which is used to record and identify the collection time of the vehicle motion state data.

[0028] Specifically, a preset time period, such as 5 seconds, is evenly divided into several time sampling points, and the sampling interval is usually set to 0.5 seconds, so that 10 time sampling points can be obtained in each preset time period. Selecting a suitable sampling interval is crucial to accurately capture speed changes: too dense sampling may introduce redundant data and noise, while too sparse sampling may miss important speed change information. At each time sampling point, the system obtains the instantaneous speed of two adjacent vehicles and calculates the speed difference between them. The specific calculation method is to subtract the instantaneous speed of the front vehicle from the instantaneous speed of the rear vehicle to obtain a signed difference. The sign of this difference has a clear physical meaning: a positive value indicates that the speed of the rear vehicle is greater than that of the front vehicle, and there is a trend of catching up; a negative value indicates that the speed of the rear vehicle is less than that of the front vehicle, and the relative distance is increasing. In order to improve the accuracy of speed difference calculation, the system adopts data smoothing technology. First, the speed data of each sampling point is filtered by moving average to reduce the influence of random noise; then the interpolation algorithm is used to handle possible data missing or outliers to ensure the continuity of speed difference calculation. For lane change scenarios, the system uses a trajectory prediction algorithm to maintain accurate tracking of adjacent relationships during the vehicle lane change process, ensuring the effectiveness of speed difference calculation.

[0029] Step 203: Divide the speed difference by the relative distance between any two adjacent vehicles to obtain the speed change rate between any two adjacent vehicles.

[0030] Specifically, the relative distance between any two adjacent vehicles is obtained at each time sampling point. The relative distance is calculated by the vehicle's GPS positioning data or other positioning sensor data, specifically the straight-line distance between the rear vehicle and the front vehicle. Then, the speed difference calculated at the time sampling point is divided by the relative distance to obtain the speed change rate of the sampling point. The calculation formula is: speed change rate = speed difference / relative distance. Among them, the unit of the speed difference is meter per second, the unit of the relative distance is meter, and the unit of the speed change rate is per second. In order to improve the reliability of the calculation results, the system verifies the validity of the relative distance. When the relative distance is less than the safety threshold, such as 2 meters, the system will regard it as a potential collision risk; when the relative distance is particularly large, such as more than 100 meters, it may indicate that the interaction between the two vehicles is weak. For these special cases, the system will make special marks and give extra attention in the subsequent accident identification process. At the same time, the system will also perform a rationality check on the calculated speed change rate and filter out abnormal values ​​that obviously do not conform to the laws of physics. This speed change rate calculation method based on relative distance normalization has obvious advantages. First, it can more accurately reflect the degree of danger between vehicles. For example, the same speed difference has different danger levels at different vehicle distances: the danger level is higher when the vehicle distance is smaller, and this characteristic is naturally reflected in the speed change rate. Secondly, as a normalized indicator, the speed change rate is convenient for horizontal comparison and threshold setting in different scenarios. Finally, by continuously calculating the speed change rate of multiple sampling points, the system can construct a time series of the speed change rate, which is used to analyze the dynamic change characteristics of the vehicle's motion state.

[0031] Based on the above embodiment, as an optional embodiment, in step 102: calculating the distance change rate between any two adjacent vehicles according to the vehicle distance value of each vehicle, this step may also include the following steps: Step 204: Based on the vehicle distance value of each vehicle, determine a first distance value between any two adjacent vehicles at a preset start time and a second distance value between any two adjacent vehicles at a preset end time.

[0032] The first distance value can be understood as a quantitative representation of the initial spacing between adjacent vehicles, which is a numerical description of the relative position relationship of the vehicles at the beginning of the preset time period. This distance value reflects the spatial distribution state of the vehicles at the beginning of the observation and provides a benchmark reference value for evaluating the distance change during the vehicle movement process.

[0033] The second distance value can be understood as a quantitative representation of the end spacing between adjacent vehicles, and is a numerical description of the relative position relationship of the vehicles at the end of the preset time period. This distance value reflects the spatial distribution state of the vehicles at the end of the observation.

[0034] Specifically, first, the first distance value between any two adjacent vehicles is obtained at the preset start time. The distance value is calculated by the precise positioning data of the vehicle, specifically the straight-line distance between the front bumper of the rear vehicle and the rear bumper of the front vehicle. Similarly, the second distance value between the pair of adjacent vehicles is obtained at the preset end time. In order to ensure the accuracy of distance measurement, the system adopts multi-source sensor data fusion technology, comprehensively utilizes the data of various sensor devices such as GPS positioning, laser radar, millimeter wave radar, and optimizes the original data through the Kalman filter algorithm. In the process of obtaining the distance value, the system needs to pay special attention to the lane change. When the vehicle changes lanes, the system dynamically updates the pairing relationship of adjacent vehicles by tracking the vehicle trajectory in real time to ensure that the first distance value and the second distance value correspond to the same pair of adjacent vehicles. For possible data anomalies, the system adopts a data validity verification mechanism. When the measured distance value exceeds the reasonable range or a mutation occurs, the data correction process will be triggered. This distance value determination method based on the start and end time can reflect the changing trend of the vehicle spacing by simultaneously recording the distance values ​​at the preset start time and the preset end time.

[0035] Step 205: The difference between the first distance value and the second distance value is taken as the distance change value, and the distance change value is divided by the time between the preset start time and the preset end time to obtain the distance change rate between any two adjacent vehicles.

[0036] Specifically, the distance change value is first calculated, that is, the first distance value is subtracted from the second distance value. The positive and negative of this difference have clear physical meanings: a positive value indicates that the distance between the two vehicles is increasing, and a negative value indicates that the distance between the two vehicles is decreasing. Subsequently, the system divides the distance change value by the time between the preset start time and the preset end time (for example, 5 seconds) to obtain the distance change rate. The calculation formula is: distance change rate = (second distance value-first distance value) / time interval. Among them, the unit of distance is meter, and the unit of time is second, so the unit of distance change rate is meter / second. In order to improve the accuracy of calculation, the system verifies the validity of the distance change value. When the distance change value exceeds the reasonable range, it may be due to sensor error or data anomaly, and the system will start the data correction mechanism. At the same time, considering that the vehicle may change lanes, the system uses the vehicle trajectory tracking algorithm to ensure that the calculation of the distance change value is always for the same pair of adjacent vehicles. For the calculated distance change rate, the system will also perform a rationality check to eliminate abnormal values ​​that do not conform to physical laws. This distance change rate calculation method based on time normalization has significant advantages. First, it converts the absolute distance change into the rate of change per unit time, making the data at different time scales comparable; second, the distance change rate intuitively reflects the speed at which vehicles approach or move away, making it easier to set the warning threshold; finally, by continuously monitoring the changing trend of the distance change rate, the system can promptly detect abnormal vehicle motion status.

[0037] Based on the above embodiment, as an optional embodiment, in step 102: calculating the vehicle lateral offset of each vehicle according to each driving trajectory, this step may also include the following steps: Step 206: Based on the driving trajectory of each vehicle, determine the average driving direction angle and driving distance of each vehicle.

[0038] The average driving direction angle refers to the angle between the main movement direction of the vehicle's driving trajectory and the true north direction within a preset time period. Specifically, the angle is calculated by weighted average of the instantaneous direction angles at all sampling moments within the preset time period. The average driving direction angle can be understood as an indication of the direction of the vehicle's overall movement trend within the observation time period.

[0039] Driving distance refers to the cumulative distance traveled by the vehicle along its actual driving trajectory within a preset time period. This distance is obtained by calculating the sum of the distances between all adjacent trajectory sampling points within the preset time period. The system calculates this precise distance value through the continuous position coordinates collected by the vehicle positioning device and the trajectory smoothing algorithm.

[0040] Specifically, the vehicle's position coordinate sequence is first collected continuously within a preset time period through the on-board positioning device (such as GPS, inertial navigation system, etc.) to form the vehicle's driving trajectory. For each sampling point, the system records its latitude and longitude coordinates and timestamp. Based on these trajectory point data, the system uses a vector calculation method to determine the direction angle between adjacent trajectory points, and calculates the average driving direction angle within the entire preset time period by weighted average. Among them, the direction angle is defined as the angle between the vehicle's moving direction and the true north direction, and the value range is 0° to 360°. At the same time, the system calculates the total driving distance of the vehicle within the preset time period by accumulating the distance between adjacent trajectory points. In order to improve the calculation accuracy, the system adopts a multi-level data processing strategy. First, the original trajectory data is noise filtered to eliminate the trajectory jitter caused by positioning error; then the trajectory smoothing algorithm is used to optimize the processed data to obtain a more continuous and smooth motion trajectory. When calculating the average driving direction angle, the system takes into account the nonlinear characteristics of the vehicle's steering process and adopts a speed-weighted average method to make the calculation result more accurately reflect the main direction of movement of the vehicle. For the calculation of the driving distance, the influence of the earth's curvature is considered to ensure the accuracy of the distance calculation. This trajectory analysis-based method has several advantages. First, the average driving direction angle can reflect the overall movement trend of the vehicle, which helps to identify abnormal steering behavior of the vehicle. Second, the driving distance provides a quantitative indicator of vehicle displacement, which can be used to assess the intensity of vehicle movement. The combination of these two parameters can effectively describe the movement characteristics of the vehicle and provide a multi-dimensional judgment basis for accident identification.

[0041] Step 207: Obtain the current actual driving direction angle of each vehicle; calculate the angle between the actual driving direction angle of each vehicle and the average driving direction angle.

[0042] Specifically, the vehicle's current heading data is first collected in real time through the on-board sensor network (including electronic compass, gyroscope, etc.), and the actual driving direction angle of the vehicle is calculated by combining with GPS positioning information. The actual driving direction angle is also expressed as the angle with the true north direction, with a value range of 0° to 360°. Subsequently, the system compares the actual driving direction angle obtained in real time with the average driving direction angle calculated previously, and calculates the angle between the two angles. Considering the periodic characteristics of the angle, the system adopts the minimum angle principle for calculation to ensure that the calculated angle does not exceed 180°. In order to improve the reliability of the calculation, the system performs multiple verifications on the sensor data. First, the direction information provided by different sensors is comprehensively processed through the data fusion algorithm to reduce the error influence of a single sensor; secondly, the actual driving direction angle calculated is rationally checked to eliminate abnormal values ​​caused by sensor failure or signal interference; finally, when calculating the angle, the system considers the continuity characteristics of the vehicle's steering and reduces the influence of instantaneous fluctuations through smoothing. This analysis method based on the direction angle has significant advantages. First, the steering angle intuitively reflects the degree of deviation between the vehicle's current direction of movement and the recent main movement trend, which is convenient for setting the warning threshold; second, this method has little dependence on vehicle speed and is suitable for various driving conditions; finally, by continuously monitoring the changing trend of the steering angle, the system can promptly detect abnormal steering behavior.

[0043] Step 208: For each vehicle, determine the lateral offset of the vehicle according to the angle and the travel distance.

[0044] Specifically, the trigonometric function calculation method is used to decompose the vehicle's motion into a longitudinal component along the average driving direction and a lateral component perpendicular to the average driving direction. The calculation formula for the lateral offset is: lateral offset = driving distance × sin (angle), where the angle is the angle difference between the actual driving direction angle and the average driving direction angle. This calculation method takes into account the curve characteristics of the actual motion trajectory of the vehicle and can accurately reflect the degree of lateral deviation of the vehicle. In order to improve the calculation accuracy, the system adopts a number of optimization measures. First, the angle is normalized to ensure that the minimum angle value is used in the calculation; second, the physical parameters such as the vehicle's wheelbase and turning radius are considered in the calculation process to make the calculation results more in line with the actual situation; finally, the system also establishes a data smoothing mechanism to reduce the impact of instantaneous fluctuations on the calculation of lateral offset. This method of calculating lateral offset based on geometric relationships has significant advantages. First, it simplifies complex vehicle movements into quantifiable lateral offset indicators, which is convenient for threshold judgment; second, by combining the two parameters of angle and travel distance, it takes into account both the steering amplitude and the distance of movement, making the calculation result more comprehensive and accurate; the lateral offset is a scalar indicator, which facilitates the system to conduct real-time monitoring and early warning.

[0045] Step 103: When the speed change rate, the distance change rate or the lateral offset of the vehicle exceeds the corresponding standard threshold, it is determined that a traffic accident occurs on the road to be monitored.

[0046] Specifically, according to the analysis of historical data, corresponding standard thresholds are set for each monitoring indicator. The standard threshold of speed change rate is used to identify sharp acceleration or deceleration behavior, the standard threshold of distance change rate is used to detect abnormal changes in vehicle spacing, and the standard threshold of vehicle lateral offset is used to detect dangerous steering or deviation behavior. The setting of these thresholds takes into account environmental factors such as road type, weather conditions, and traffic density, and adopts a hierarchical threshold system to ensure the scientificity and applicability of the judgment criteria. During the real-time monitoring process, the system continuously calculates and updates the values ​​of these three indicators, and compares them with the corresponding standard thresholds in real time. When any indicator exceeds its standard threshold, the system triggers the accident judgment mechanism. In order to improve the accuracy of the judgment, the system adopts a composite judgment strategy: for the case where a single indicator exceeds the threshold, the system will further analyze its duration and change trend; for the case where multiple indicators exceed the threshold at the same time, the system will comprehensively evaluate the degree of exceeding the limit and correlation of each indicator, so as to make a more reliable accident judgment. This accident detection method based on multi-parameter thresholds has significant advantages. First, by simultaneously monitoring multiple motion characteristic parameters, the system can fully grasp the vehicle's motion status and avoid misjudgment due to accidental fluctuations in a single indicator; second, different types of traffic accidents usually exhibit different combinations of parameter characteristics, and multi-parameter monitoring helps to accurately identify the type of accident; finally, by setting a reasonable threshold system, the system can not only detect emergencies in a timely manner, but also avoid false warnings caused by excessive sensitivity.

[0047] Step 104: Receive road status data of the road to be monitored, where the road status data includes lane occupancy, traffic flow density, and average travel speed.

[0048] Among them, road status data refers to a real-time data set that reflects the current traffic operation status of the road to be monitored, mainly including three indicators: lane occupancy rate, traffic flow density and average travel speed. Lane occupancy rate represents the proportion of time that a lane is occupied by motor vehicles per unit time, traffic flow density represents the number of vehicles in a unit section, and average travel speed represents the actual driving speed of vehicles in the section.

[0049] Specifically, the system collects road status data through a multi-source sensing device network deployed on the road. The lane occupancy rate is obtained through the coil detector or video image analysis on the lane line, reflecting the proportion of time that the lane is occupied by motor vehicles per unit time; the traffic flow density is calculated by the roadside radar or video monitoring system to measure the number of vehicles in a unit section; the average speed is calculated by multi-point speed measurement equipment or vehicle-mounted GPS data fusion. These data are collected and updated at fixed time intervals (usually 1 minute) to ensure the real-time and continuity of monitoring. To improve the reliability of the data, the system adopts a multiple verification mechanism. First, the information from different sensing devices is integrated through the data fusion algorithm to reduce the impact of single device failure or error; secondly, a data quality assessment model is established to verify the rationality of the collected data in real time and eliminate outliers; finally, the validity of the current collected data is verified through historical data comparison and spatial correlation analysis. This multi-dimensional road status monitoring method has significant advantages. First, the lane occupancy rate can directly reflect the degree of road congestion. When the occupancy rate is too high, it indicates that the vehicle driving space is limited and the risk of collision increases. Secondly, the traffic flow density reflects the degree of vehicle aggregation. When the density is abnormal, it may indicate an unstable state of traffic flow. Finally, the average speed reflects the overall traffic efficiency. Significant fluctuations in speed are often closely related to the risk of traffic accidents. In practical applications, this monitoring method has shown excellent early warning effects. The system can detect potential dangerous conditions in a timely manner by analyzing the combined characteristics of these three indicators in real time.

[0050] Step 105: Based on the lane occupancy rate, traffic flow density and average travel speed, determine the accident level corresponding to the traffic accident, and generate alarm information of the accident level corresponding to the traffic accident.

[0051] Among them, the accident level refers to the classification standard divided according to the impact of traffic accidents on the operation status of road traffic, which is mainly quantitatively evaluated through the combined characteristics of road status data such as lane occupancy rate, traffic flow density and average travel speed.

[0052] Alarm information refers to the notification data packet automatically generated by the system after confirming the occurrence of a traffic accident and determining its level, which contains key information about the accident. It mainly includes the time, location, level, scope of impact, key road status parameters, etc. of the accident, as well as emergency response suggestions generated based on this information.

[0053] Specifically, the system first divides the accident level into several intervals. Based on the lane occupancy rate, traffic flow density and average speed, a weighted calculation is performed to obtain an accident level score, and then the interval in which the accident level score is located is determined to determine the accident level corresponding to the interval. After determining the accident level, the system generates corresponding alarm information according to different levels. For minor levels, basic information including the accident location and brief impact is generated; for general levels, surrounding road status data is added; for severe levels, traffic control suggestions are supplemented; for particularly severe levels, a complete emergency response plan is provided. These alarm messages are sent to relevant personnel through text messages, application push, etc. Through this accident level determination and alarm mechanism, the system can help traffic management departments quickly understand the impact of the accident and allocate emergency resources in a timely manner.

[0054] Based on the above embodiment, as an optional embodiment, in step 105: determining the accident level corresponding to the traffic accident based on the lane occupancy rate, traffic flow density and average traffic speed, this step may also include the following steps: Step 301: Based on the lane occupancy rate, determine the number of affected lanes, based on the traffic flow density value, calculate the length of the affected road section, and based on the average travel speed, calculate the traffic flow interruption coefficient.

[0055] The number of affected lanes refers to the number of lanes whose lane occupancy rate increases abnormally due to the impact of the accident after the traffic accident occurs. It is an important indicator to measure the impact of the traffic accident on the lateral traffic capacity of the road. This abnormality is mainly manifested in the lane occupancy rate exceeding the preset threshold, reflecting that the traffic capacity of the lane is significantly restricted or interrupted.

[0056] The length of the affected road section refers to the total length of the continuous road section where the traffic flow density value increases abnormally due to the impact of the traffic accident after the traffic accident occurs. It is an important indicator to measure the impact of the traffic accident on the longitudinal traffic capacity of the road, and reflects the obvious vehicle backlog or traffic obstruction in the section.

[0057] Traffic flow interruption coefficient refers to a dimensionless indicator that reflects the extent of decline in road traffic efficiency by comparing the difference between the current average speed and the normal speed after a traffic accident. This coefficient reflects the degree of damage to the continuity of traffic flow caused by the accident, and is expressed as a value between 0 and 1. The larger the value, the more serious the traffic interruption.

[0058] Specifically, the number of affected lanes is determined based on the lane occupancy rate. The system analyzes the occupancy rate data of each lane, and when the occupancy rate of a lane exceeds a preset threshold (such as 85%), it determines it as an affected lane. For example, in a three-lane road section, if the occupancy rates of two lanes are 90% and 87% respectively, and the other is 50%, the number of affected lanes is 2. This determination method can accurately reflect the lateral impact range of the accident on the road capacity. Secondly, the length of the affected section is calculated based on the traffic flow density value. The system divides the upstream and downstream sections of the accident point into several detection units and analyzes the traffic flow density value of each unit. When the density value of a detection unit exceeds 1.5 times the normal value, it is included in the impact range. The total length of the affected section is obtained by accumulating the lengths of all affected detection units. For example, if each detection unit is 100 meters long, and the density values ​​of 5 units upstream and 3 units downstream exceed the threshold, the total length of the affected section is 800 meters. This calculation method can accurately quantify the longitudinal impact range of the accident.

[0059] Finally, the traffic flow interruption coefficient is calculated based on the average speed. This coefficient reflects the impact of the accident on traffic operation efficiency, and the calculation formula is: interruption coefficient = current average speed / benchmark speed. For example, if the normal speed of the road section is 60 km / h and the current average speed drops to 20 km / h, the interruption coefficient is 0.67, indicating that the traffic operation efficiency has decreased by 67%. This calculation method can quantify the impact of the accident on traffic operation efficiency. Through this multi-dimensional impact assessment method, the system can fully grasp the impact characteristics of the accident. The number of affected lanes reflects the lateral impact range and helps determine the traffic diversion plan; the length of the affected road section reflects the longitudinal impact range and helps plan the detour route; the traffic flow interruption coefficient reflects the loss of operation efficiency and provides a basis for the recovery time estimation. These evaluation results provide a reference for subsequent traffic organization and emergency response.

[0060] Based on the above embodiment, as an optional embodiment, in step 301: determining the number of affected lanes based on the lane occupancy rate, calculating the length of the affected road section based on the traffic flow density value, and calculating the traffic flow interruption coefficient based on the average travel speed, this step may also include the following steps: Step 311: Determine the sub-occupancies corresponding to the multiple lanes in the lane occupancy rate; in each lane, select the lane whose sub-occupancy rate is greater than or equal to the occupancy rate threshold as the affected lane, and count the number of each affected lane as the number of affected lanes.

[0061] Specifically, the system first obtains the real-time lane occupancy data of all lanes on the road, and uses the occupancy corresponding to each lane as the sub-occupancy. For example, in a four-lane road section, the system collects the occupancy data of the four lanes respectively and obtains four sub-occupancy values. These sub-occupancy data directly reflect the actual use status of each lane and can objectively reflect the impact of the accident on different lanes. Subsequently, the system compares the sub-occupancy of each lane with the preset occupancy threshold (such as 85%). When the sub-occupancy of a lane is greater than or equal to the occupancy threshold, it indicates that the traffic capacity of the lane is significantly affected, and it is determined to be an affected lane. For example, if the sub-occupancy of the four lanes is 90%, 87%, 45% and 40% respectively, and the occupancy threshold is 85%, then two lanes (lanes with sub-occupancy of 90% and 87%) are determined to be affected lanes. This determination method can accurately identify the lanes where traffic is blocked and avoid errors caused by subjective judgment. Finally, the system counts the number of affected lanes to obtain the number of affected lanes. In the above example, the number of affected lanes is 2. This value directly reflects the impact of the accident on the lateral capacity of the road, and provides an important reference for the formulation of traffic organization plans. This method of identifying affected lanes based on sub-occupancy has significant advantages. First, by collecting real-time occupancy data of each lane, lanes with abnormal capacity can be discovered in a timely manner; second, the threshold judgment method is adopted to ensure the objectivity and consistency of the identification results; finally, the number of affected lanes is directly counted, providing a clear quantitative indicator for subsequent decision-making.

[0062] Step 321: Based on the traffic flow density value, determine the sub-traffic flow density of multiple road sections; in each road section, calculate the sum of the section distances of the sections whose sub-traffic flow density is greater than or equal to the density threshold to obtain the affected section length.

[0063] Specifically, the system first divides the roads upstream and downstream of the accident point into several equal-length sections (such as 100 meters per section), and obtains the real-time traffic flow density value of each section as the sub-traffic flow density. For example, density data of 5 sections upstream of the accident point and density data of 4 sections downstream are collected to obtain 9 sub-traffic flow density values. This fine-grained density data collection method can accurately reflect the distribution of traffic congestion caused by the accident. Subsequently, the system compares the sub-traffic flow density of each section with the preset density threshold (such as 1.5 times the normal traffic flow density). When the sub-traffic flow density of a section is greater than or equal to the density threshold, it indicates that there is a significant backlog of vehicles on the section, and it is determined to be an affected section. For example, if the normal traffic flow density is 30 vehicles / km, the density threshold is 45 vehicles / km. When the sub-traffic flow density of a section reaches 50 vehicles / km, the section is determined to be an affected section. This determination method can objectively identify the range of sections with vehicle backlogs. Finally, the system calculates the sum of the distances of all affected sections to obtain the length of the affected section. For example, if the sub-traffic flow density of the three upstream sections and the two downstream sections exceeds the threshold, the length of the affected section is (3+2)×100=500 meters. This cumulative length directly reflects the longitudinal impact range caused by the accident and provides a reference for the formulation of traffic diversion plans.

[0064] Step 331: The ratio of the average traffic speed to the reference traffic speed of the road to be monitored is used as the traffic flow interruption coefficient.

[0065] Specifically, the system first obtains the real-time average speed of the road and the pre-set benchmark speed data. Among them, the average speed is obtained by collecting the speeds of all vehicles within the accident impact range in real time and calculating the average value, and the benchmark speed is determined based on historical data statistics, reflecting the typical operating speed of the road section under normal traffic conditions. For example, the benchmark speed of a certain section is 60 kilometers per hour, and the average speed after the accident drops to 15 kilometers per hour. Subsequently, the system calculates the ratio of the average speed to the benchmark speed to obtain the traffic flow interruption coefficient, that is: traffic flow interruption coefficient = average speed / benchmark speed. In the above example, the traffic flow interruption coefficient is 15 / 60=0.25, indicating that the traffic efficiency of the section is reduced to 25% of the normal level. This ratio calculation method converts speed changes into standardized evaluation indicators, which facilitates horizontal comparison of the impact of accidents on different sections and different time periods. This method of calculating the traffic flow interruption coefficient based on speed ratio has significant advantages. First, by introducing the benchmark speed as a reference standard, the loss of traffic efficiency caused by accidents can be objectively reflected; secondly, by using a ratio for calculation, the obtained indicator has good comparability and is not affected by differences in road grade and design speed, providing a clear quantitative basis for traffic management decisions.

[0066] Step 302: Determine the accident level corresponding to the traffic accident based on the number of affected lanes, the length of the affected road section, and the traffic flow interruption coefficient.

[0067] Specifically, after obtaining the three indicators of the number of affected lanes, the length of the affected road sections and the traffic flow interruption coefficient, the traffic flow interruption coefficient is first used to adjust the number of affected lanes and the length of the affected road sections to make the indicators more in line with the current actual traffic environment. Then, the adjusted number of affected lanes and the length of the affected road sections are weighted and summed to obtain the accident level.

[0068] Based on the above embodiment, as an optional embodiment, in step 302: determining the accident level corresponding to the traffic accident in combination with the number of affected lanes, the length of the affected road section and the traffic flow interruption coefficient, this step may also include the following steps: Step 312: Obtain a first weight of the number of affected lanes and a second weight of the length of the affected road section.

[0069] The first weight refers to the weight coefficient assigned to the evaluation indicator of the number of affected lanes in the accident impact assessment model. In the embodiment of the present application, it can be understood as a value between 0 and 1, which is used to quantify the relative importance of the number of affected lanes in the overall accident level assessment.

[0070] The second weight refers to the weight coefficient assigned to the evaluation index of the length of the affected section in the accident impact assessment model. In the embodiment of the present application, it can be understood as a value between 0 and 1, which is used to quantify the relative importance of the length of the affected section in the overall accident level assessment, and the sum of the first weight and the second weight is 1.

[0071] Specifically, the system first sets the basic weight value according to the road grade and functional characteristics. For roads with large traffic volume and high traffic requirements such as urban trunk roads, the first weight of the number of affected lanes is set to 0.6, and the second weight of the length of the affected section is set to 0.4. This is because the lateral traffic capacity of the trunk road has a more critical impact on the overall traffic operation; for roads such as secondary trunk roads, the first weight and the second weight are both set to 0.5, reflecting the balance of lateral and longitudinal influences; for roads such as branch roads, the first weight is set to 0.4 and the second weight is set to 0.6, highlighting the importance of longitudinal influence. Subsequently, the system dynamically adjusts the basic weight according to the real-time road network operation status. For example, during peak hours in the morning and evening, due to the large overall traffic pressure on the road and the increased importance of lateral traffic capacity, the system will appropriately increase the value of the first weight; during off-peak hours, due to the relatively dispersed traffic demand, the system maintains the original weight ratio. This dynamic adjustment mechanism ensures the matching of weight allocation with actual traffic operation characteristics. This dynamic weight allocation method has significant advantages. First, through differentiated weight settings, more targeted evaluation can be carried out for the characteristics of roads of different grades.

[0072] Step 322: According to the traffic flow interruption coefficient, the number of affected lanes and the length of the affected road section are adjusted to obtain the target number of affected lanes and the target length of the affected road section; based on the first weight and the second weight, the target number of affected lanes and the target length of the affected road section are weighted and summed to obtain the accident level corresponding to the traffic accident.

[0073] Specifically, the system first uses the traffic flow interruption coefficient to correct the two basic evaluation indicators. The correction calculation adopts the product form of the basic indicator value and the traffic flow interruption coefficient, that is: the corrected number of affected lanes = the original number of affected lanes × (1 + traffic flow interruption coefficient), the corrected length of the affected section = the original length of the affected section × (1 + traffic flow interruption coefficient). For example, when an accident occurs on a certain section of road, the original number of affected lanes is 3, the original length of the affected section is 800 meters, and the traffic flow interruption coefficient is 0.7. Then the corrected number of affected lanes is 3 × (1 + 0.7) = 5.1, and the corrected length of the affected section is 800 × (1 + 0.7) = 1360 meters. This correction method takes into account the amplification effect of the decline in traffic operation efficiency on the actual impact range, making the evaluation results more in line with the actual situation. After obtaining the corrected evaluation index value, the system assigns weight coefficients to the two indicators for weighted calculation: the corrected weight of the number of affected lanes is 0.5, that is, the first weight, and the corrected weight of the affected section length is 0.5, that is, the second weight. The corrected index value is normalized, multiplied by the corresponding weight coefficient and summed to obtain the comprehensive impact value of the accident. For example, the above corrected values ​​are normalized (assuming that the maximum reference values ​​are 6 and 1500 meters respectively), and the normalized values ​​are 0.85 and 0.91 respectively, then the comprehensive impact value is 0.85×0.5+0.91×0.5=0.88. According to the calculated comprehensive impact value, the system divides the accident level into four levels: when the comprehensive impact value is less than 0.6, it is judged as a minor level, between 0.6-0.7 is judged as a general level, between 0.7-0.85 is judged as a serious level, and when it is greater than 0.85, it is judged as a particularly serious level. In the above example, the comprehensive impact value is 0.88, so it is judged as a particularly serious level accident.

[0074] Reference Figure 2 , is a road traffic accident monitoring and alarm system provided by an embodiment of the present application, the system comprises: a data acquisition module, a data processing module, an accident monitoring module, and an accident alarm module, wherein: A data acquisition module is used to acquire vehicle operation status data of the road to be monitored, wherein the vehicle operation status data includes vehicle speed values, vehicle distance values ​​and driving trajectories of multiple vehicles; A data processing module, used to calculate the speed change rate between any two adjacent vehicles according to the speed value of each vehicle, calculate the distance change rate between any two adjacent vehicles according to the vehicle distance value of each vehicle, and calculate the vehicle lateral offset of each vehicle according to each driving trajectory; An accident monitoring module is used to determine that a traffic accident has occurred on the monitored road when the speed change rate, distance change rate or vehicle lateral offset exceeds the corresponding standard threshold; The accident alarm module is used to receive road status data of the road to be monitored, the road status data including lane occupancy rate, traffic flow density and average travel speed; based on the lane occupancy rate, traffic flow density and average travel speed, determine the accident level corresponding to the traffic accident, and generate alarm information of the accident level corresponding to the traffic accident.

[0075] On the basis of the above embodiment, the data processing module is also used to determine the speed values ​​of any two adjacent vehicles within a preset time period based on the speed value of each vehicle; divide the preset time period into multiple time sampling points; calculate the speed difference between any two adjacent vehicles at each time sampling point; divide the speed difference by the relative distance between any two adjacent vehicles to obtain the speed change rate between any two adjacent vehicles.

[0076] On the basis of the above embodiment, the data processing module is also used to determine a first distance value between any two adjacent vehicles at a preset start time and a second distance value between any two adjacent vehicles at a preset end time based on the vehicle distance value of each vehicle; the difference between the first distance value and the second distance value is used as the distance change value, and the distance change value is divided by the time length between the preset start time and the preset end time to obtain the distance change rate between any two adjacent vehicles.

[0077] Based on the above embodiments, the data processing module is also used to determine the average driving direction angle and driving distance of each vehicle based on the driving trajectory of each vehicle; obtain the current actual driving direction angle of each vehicle; calculate the angle between the actual driving direction angle of each vehicle and the average driving direction angle; for each vehicle, determine the vehicle's lateral offset based on the angle and the driving distance.

[0078] Based on the above embodiment, the accident alarm module is also used to determine the number of affected lanes based on lane occupancy rate, calculate the length of the affected road section based on the traffic flow density value, and calculate the traffic flow interruption coefficient based on the average travel speed; the accident level corresponding to the traffic accident is determined by combining the number of affected lanes, the length of the affected road section and the traffic flow interruption coefficient.

[0079] On the basis of the above embodiment, the accident alarm module is also used to determine the sub-occupancy rates corresponding to multiple lanes in the lane occupancy rate; in each lane, the lanes with sub-occupancy rates greater than or equal to the occupancy rate threshold are screened out as affected lanes, and the number of affected lanes is counted as the number of affected lanes; based on the traffic flow density value, the sub-traffic flow density of multiple road sections is determined; in each road section, the sum of the section distances of the sections with sub-traffic flow density greater than or equal to the density threshold is calculated to obtain the affected section length; the ratio of the average traffic speed to the benchmark traffic speed of the road to be monitored is used as the traffic flow interruption coefficient.

[0080] Based on the above embodiment, the accident alarm module is also used to obtain a first weight for the number of affected lanes and a second weight for the length of the affected road section; according to the traffic flow interruption coefficient, the number of affected lanes and the length of the affected road section are adjusted to obtain the target number of affected lanes and the target affected road section length; based on the first weight and the second weight, the target number of affected lanes and the target affected road section length are weighted and summed to obtain the accident level corresponding to the traffic accident.

[0081] It should be noted that: when the device provided in the above embodiment realizes its function, only the division of the above functional modules is used as an example. In actual application, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the device and method embodiments provided in the above embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0082] The present application also discloses an electronic device. Figure 3 , Figure 3 The electronic device 300 may include: at least one processor 301 , at least one network interface 304 , a user interface 303 , a memory 305 , and at least one communication bus 302 .

[0083] The communication bus 302 is used to realize the connection and communication between these components.

[0084] The user interface 303 may include a display interface and a camera interface. Optionally, the user interface 303 may also include a standard wired interface and a wireless interface.

[0085] The network interface 304 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0086] Among them, the processor 301 may include one or more processing cores. The processor 301 uses various interfaces and lines to connect various parts in the entire server, and executes various functions of the server and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 305, and calling data stored in the memory 305. Optionally, the processor 301 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 301 can integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface diagrams and applications, etc.; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 301, and it can be implemented separately through a chip.

[0087] Among them, the memory 305 may include a random access memory (Random Access Memory, RAM) and may also include a read-only memory (Read-Only Memory). Optionally, the memory 305 includes a non-transitory computer-readable storage medium. The memory 305 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 305 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 305 may optionally also be at least one storage device located away from the aforementioned processor 301. Refer to Figure 3 , the memory 305 as a computer storage medium may include an operating system, a network communication module, a user interface module and an application program of a road traffic accident monitoring and alarm method.

[0088] exist Figure 3In the electronic device 300 shown, the user interface 303 is mainly used to provide an input interface for the user and obtain the data input by the user; and the processor 301 can be used to call the application program storing a road traffic accident monitoring and alarm method in the memory 305, and when executed by one or more processors 301, the electronic device 300 executes one or more methods in the above-mentioned embodiments. It should be noted that for the aforementioned method embodiments, for the sake of simple description, they are all expressed as a series of action combinations, but those skilled in the art should know that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required for the present application.

[0089] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0090] In the several embodiments provided in this application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0091] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0092] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0093] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a memory and includes several instructions for a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the various embodiments of the present application. The aforementioned memory includes: various media that can store program codes, such as USB flash drives, mobile hard drives, magnetic disks or optical disks.

[0094] The above are only exemplary embodiments of the present disclosure and cannot be used to limit the scope of the present disclosure. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the disclosure of the specification and practice, those skilled in the art will easily think of other embodiments of the present disclosure.

[0095] This application is intended to cover any variation, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary technical means in the art not recorded in the present disclosure. The description and examples are to be regarded as exemplary only.

Claims

1. A road traffic accident monitoring and alarm method, characterized in that: include: Acquire vehicle running status data of the road to be monitored, wherein the vehicle running status data includes speed values, vehicle distance values, and driving trajectories of multiple vehicles; Calculating the speed change rate between any two adjacent vehicles according to the vehicle speed value of each vehicle, calculating the distance change rate between any two adjacent vehicles according to the vehicle distance value of each vehicle, and calculating the vehicle lateral offset of each vehicle according to each driving trajectory; When the speed change rate, the distance change rate or the vehicle lateral offset exceeds the corresponding standard threshold, it is determined that a traffic accident occurs on the road to be monitored; Receiving road status data of the road to be monitored, wherein the road status data includes lane occupancy rate, traffic flow density and average travel speed; Based on the lane occupancy rate, the traffic flow density and the average travel speed, the accident level corresponding to the traffic accident is determined, and alarm information of the accident level corresponding to the traffic accident is generated.

2. The road traffic accident monitoring and alarm method according to claim 1, characterized in that: The step of calculating the speed change rate between any two adjacent vehicles according to the speed values ​​of the vehicles comprises: Based on the speed values ​​of each of the vehicles, determining the speed values ​​of any two adjacent vehicles within a preset time period; Dividing the preset time period into a plurality of time sampling points; Calculating the speed difference between any two adjacent vehicles at each of the time sampling points; The speed difference is divided by the relative distance between any two adjacent vehicles to obtain the speed change rate between the any two adjacent vehicles.

3. The road traffic accident monitoring and alarm method according to claim 1, characterized in that: The calculating the distance change rate between any two adjacent vehicles according to the vehicle distance value of each vehicle includes: Based on the vehicle distance values ​​of the vehicles, determining a first distance value between any two adjacent vehicles at a preset start time and a second distance value between any two adjacent vehicles at a preset end time; The difference between the first distance value and the second distance value is taken as a distance change value, and the distance change value is divided by the duration between the preset start time and the preset end time to obtain a distance change rate between any two adjacent vehicles.

4. The road traffic accident monitoring and alarm method according to claim 1, characterized in that: The calculating the lateral displacement of each vehicle according to each of the driving trajectories includes: Determining the average driving direction angle and driving distance of each of the vehicles based on the driving trajectory of each of the vehicles; Obtaining the actual current driving direction angle of each of the vehicles; Calculating the angle between the actual driving direction angle of each of the vehicles and the average driving direction angle; For each of the vehicles, a lateral offset of the vehicle is determined according to the angle and the travel distance.

5. The road traffic accident monitoring and alarm method according to claim 1, characterized in that: The determining the accident level corresponding to the traffic accident based on the lane occupancy rate, the traffic flow density and the average traffic speed includes: Based on the lane occupancy rate, determine the number of affected lanes, based on the traffic flow density value, calculate the length of the affected road section, and based on the average travel speed, calculate the traffic flow interruption coefficient; The accident level corresponding to the traffic accident is determined based on the number of affected lanes, the length of the affected road section, and the traffic flow interruption coefficient.

6. The road traffic accident monitoring and alarm method according to claim 5, characterized in that: The determining of the number of affected lanes based on the lane occupancy rate, the calculating of the length of the affected road section based on the traffic flow density value, and the calculating of the traffic flow interruption coefficient based on the average travel speed include: Determine sub-occupancy rates corresponding to a plurality of lanes in the lane occupancy rate; In each lane, the lanes whose sub-occupancy rates are greater than or equal to the occupancy rate threshold are selected as affected lanes, and the number of the affected lanes is counted as the number of affected lanes; Determining sub-traffic flow densities of a plurality of road sections based on the traffic flow density values; In each of the road sections, the sum of the road section distances of the road sections where the sub-traffic flow density is greater than or equal to the density threshold is calculated to obtain the length of the affected road section; The ratio of the average traffic speed to the reference traffic speed of the road to be monitored is used as the traffic flow interruption coefficient.

7. The road traffic accident monitoring and alarm method according to claim 5, characterized in that: The determining the accident level corresponding to the traffic accident by combining the number of affected lanes, the length of the affected road section and the traffic flow interruption coefficient includes: Obtaining a first weight of the number of affected lanes and a second weight of the affected road section length; According to the traffic flow interruption coefficient, the number of affected lanes and the length of the affected road section are adjusted to obtain a target number of affected lanes and a target length of affected road section; Based on the first weight and the second weight, a weighted sum is performed on the target number of affected lanes and the target affected road section length to obtain an accident level corresponding to the traffic accident.

8. A road traffic accident monitoring and alarm system, characterized in that: The system comprises: A data acquisition module, used to acquire vehicle running status data of the road to be monitored, wherein the vehicle running status data includes vehicle speed values, vehicle distance values ​​and driving trajectories of multiple vehicles; A data processing module, used to calculate the speed change rate between any two adjacent vehicles according to the speed value of each vehicle, calculate the distance change rate between any two adjacent vehicles according to the vehicle distance value of each vehicle, and calculate the vehicle lateral offset of each vehicle according to each driving trajectory; An accident monitoring module, configured to determine that a traffic accident occurs on the road to be monitored when the speed change rate, the distance change rate or the vehicle lateral offset exceeds a corresponding standard threshold; The accident alarm module is used to receive the road status data of the road to be monitored, the road status data including lane occupancy, traffic flow density and average travel speed; based on the lane occupancy, traffic flow density and average travel speed, determine the accident level corresponding to the traffic accident, and generate alarm information of the accident level corresponding to the traffic accident.

9. An electronic device, characterized in that: It includes a processor, a memory, a user interface and a network interface, the memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device executes the road traffic accident monitoring and alarm method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions, and when the instructions are executed, the road traffic accident monitoring and alarm method as described in any one of claims 1-7 is executed.

Images