Urgency ranking method for handling abnormal traffic events based on drone monitoring

Abstract

A method for sorting the urgency of handling abnormal traffic events based on drone monitoring belongs to the technical field of drone traffic application. In order to solve the problem of timely handling of abnormal traffic events based on the degree of urgency, the present invention includes image processing of traffic images obtained from traffic videos to obtain updated traffic images; manually selecting images of abnormal traffic events including different types of vehicles, training the YOLOv10 deep learning model, and obtaining a traffic intelligent recognition model for identifying abnormal traffic events; establishing a conversion relationship between the image size and the actual size of the image identified with the abnormal traffic event; constructing an analysis method for the evolution law of the impact of abnormal traffic events on traffic, analyzing the changes in traffic congestion length, traffic flow, average vehicle speed, and delay time; establishing a comprehensive impact index of abnormal traffic events based on the constructed matrix, and sorting the urgency of handling abnormal traffic events based on drone monitoring.

Description

Technical Field

[0001] The present invention belongs to the technical field of unmanned aerial vehicle (UAV) traffic application, and in particular relates to a method for sorting the urgency of handling abnormal traffic events based on UAV monitoring. Background Art

[0002] Traffic anomalies have a profound impact on the operation of cities and the daily lives of residents. First, these events directly affect the smoothness of traffic flow, leading to traffic congestion, increasing travel time, and affecting people's work efficiency and quality of life. For example, a serious car accident may lead to the closure of a major road, forcing a large number of vehicles to detour and increasing the traffic burden on surrounding roads. Second, traffic anomalies may also lead to economic losses, including direct accident losses, increased transportation costs, and business losses caused by delays. In addition, these events may have an impact on the environment. For example, road congestion can increase vehicle emissions and deteriorate air quality. In terms of public safety, traffic anomalies may threaten life safety, especially when it involves serious traffic accidents or emergencies. Finally, these events also have an impact on public mental health. Long-term traffic congestion and constant reports of traffic accidents may cause drivers and passengers to feel anxious and stressed.

[0003] The urgency of handling traffic abnormal events is crucial for effective traffic management and emergency response. First, by correctly assessing the urgency of the event, it can ensure that resources are allocated reasonably and priority is given to those events that have the greatest impact on traffic or the most serious potential harm. For example, a car accident involving a toxic chemical leak requires a more rapid emergency response than an ordinary collision accident. Second, the urgency of the event can help shorten the response time, reduce the damage caused by the accident, and improve the efficiency of rescue, thereby saving lives and reducing property losses. In addition, this method of judgment helps to improve the public's trust and satisfaction with the efficiency of traffic management. When the public sees that the transportation department can handle serious incidents quickly and effectively, they will trust and support the government's traffic safety measures more.

[0004] The lack of an urgency determination method for handling abnormal traffic incidents may lead to multiple negative consequences. First, the lack of an effective determination method will lead to irrational resource allocation. Emergency resources may be allocated to relatively less urgent incidents, while more urgent incidents will not be handled in a timely manner. This error in resource allocation will not only increase the duration of traffic congestion, but may also cause unnecessary casualties in accidents. Second, without urgency determination, the response strategy of the traffic management department may lack pertinence, resulting in inefficient handling, increasing public dissatisfaction and distrust of the traffic management system. In the long run, this lack may affect the sustainable development of the entire transportation system, hinder the improvement of urban traffic safety and management, and ultimately affect the quality of life and economic development of the city. Summary of the invention

[0005] The problem to be solved by the present invention is to promptly handle abnormal traffic events based on their urgency, and a method for sorting the urgency of handling abnormal traffic events based on drone monitoring is proposed.

[0006] To achieve the above object, the present invention is implemented through the following technical solutions:

[0007] A method for sorting the urgency of handling abnormal traffic events based on drone monitoring comprises the following steps:

[0008] S1. Using a drone to collect traffic videos, and then extracting frames from the traffic videos to obtain traffic images;

[0009] S2. performing image processing on the traffic image obtained from the traffic video to obtain an updated traffic image;

[0010] S3. Using the updated traffic image obtained in step S2, manually select images of abnormal traffic events including different types of vehicles, train the YOLOv10 deep learning model, and obtain an intelligent traffic recognition model for identifying abnormal traffic events;

[0011] S4. The updated traffic image obtained in step S2 is input into the intelligent traffic recognition model for identifying abnormal traffic events in step S3, and the image of the abnormal traffic event is recognized to establish a conversion relationship between the image size and the actual size;

[0012] S5. Based on the images and videos of the traffic abnormality events identified in step S3 and the conversion relationship between the image size and the actual size obtained in step S4, a method for analyzing the evolution law of the impact of traffic abnormality events on traffic is constructed to analyze changes in traffic congestion length, traffic flow, average vehicle speed, and delay time;

[0013] S6. Construct a traffic congestion length change matrix corresponding to traffic abnormal events, a traffic flow change matrix corresponding to traffic abnormal events, an average vehicle speed change matrix corresponding to traffic abnormal events, and a delay time change matrix corresponding to traffic abnormal events. Then, based on the constructed matrix, establish a comprehensive impact index of traffic abnormal events and rank the urgency of handling traffic abnormal events based on drone monitoring.

[0014] Furthermore, the specific implementation method of step S2 includes the following steps:

[0015] S2.1. For the traffic image obtained from the traffic video in step S1, collect the image at pixel coordinates ( a , b ) is represented by the pixel value at the position A (a , b ),in, a and b is the horizontal pixel coordinate and the vertical pixel coordinate, and the pixel gradient is calculated Horizontal difference in the image The vertical difference , the expression is:

[0016] ;

[0017] ;

[0018] in, For the image at coordinates ( a +1, b ) pixel value at the position, For the image at coordinates ( a , b +1) pixel value at position;

[0019] Then calculate the pixel gradient , the calculation formula is:

[0020] ;

[0021] Pixel gradient is used to determine the edge strength at image pixels;

[0022] S2.2. Setting the adjustment factor c ( a , b ), used to determine different locations in the image ( a , b ) pixel update degree, adjustment coefficient c ( a , b ) is calculated as:

[0023] ;

[0024] in, is a constant that controls the sensitivity, To control the constant of the gradient component, both constants are determined empirically;

[0025] S2.3. Update the pixels of the image and obtain the updated image at coordinates ( a , b ) pixel value at position , the calculation formula is:

[0026] ;

[0027] in, is the pixel coordinate ( a , b ) The four pixel coordinates that are adjacent in the top, bottom, left, and right directions, Refers to the pixel values ​​of four adjacent pixel coordinates in the four directions of up, down, left, and right.

[0028] Furthermore, the specific implementation method of step S3 includes the following steps:

[0029] S3.1. Manually select images of traffic anomaly events including different types of vehicles, including vehicle collision, vehicle breakdown, road collapse, mudslide, building collapse, tree breakage, fog, road icing, sudden congestion, long-term congestion, illegal parking, vehicle fire, hazardous material leakage, and road construction; different types of vehicles include sedans, SUVs, vans, vans, trucks, buses, long-distance coaches, engineering vehicles, two-wheelers, cement mixers, tank trucks, and tractors;

[0030] S3.2. Use a labeling tool to label the images manually selected in step S3.1, and label the location and category of the vehicle for each image, and the area and type of the abnormal traffic event;

[0031] S3.3. Build a data set, convert the image annotation file obtained in step S3.2 into txt format, and divide the data set into training set, validation set, and test set according to the ratio of 70%, 15%, and 15% for the images and the corresponding image annotation files;

[0032] S3.4. Use the training set obtained in step S3.3 to train the YOLOv10 model. First, configure an environment suitable for running the YOLOv10 model and set the learning rate, batch size, training cycle, and hyperparameters. Use the loss during training and the performance on the validation set to monitor the training progress and adjust the training parameters.

[0033] The precision and recall rate parameters are used to evaluate the effects of vehicle identification and abnormal event detection. When the precision and recall rate reach the set value, the training is stopped. At this time, the corresponding model is a traffic intelligent recognition model for identifying abnormal traffic events.

[0034] Furthermore, the specific implementation method of step S4 includes the following steps:

[0035] S4.1. The updated traffic image obtained in step S2 is input into the traffic intelligent recognition model for identifying abnormal traffic events in step S3 to identify abnormal traffic events and identify the image of abnormal traffic events;

[0036] S4.2. Obtaining the UAV’s flight altitude data from the UAV’s onboard positioning system hw , get the camera focal length from the camera device j , the width of the sensor k sen ,high h sen , and the width of the image of the traffic anomaly event k img ,high h img ; Calculate the actual length of the image unit pixel corresponding to the traffic abnormality event, the calculation formula is:

[0037] ;

[0038] ;

[0039] in, and are the ground distance in the horizontal direction and the ground distance in the vertical direction of the image unit pixel of the traffic abnormality event respectively;

[0040] S4.3. Based on the fact that the ground distance of unit pixels in the image collected by drone is equal in horizontal and vertical directions, that is, , then establish the pixel coordinates ( a , b ) and actual geographic coordinates The conversion relationship between them is expressed as:

[0041] ;

[0042] ;

[0043] in, are the geographic coordinates of the image reference point, is the pixel coordinate of the image reference point in the image.

[0044] Furthermore, the specific implementation method of step S5 includes the following steps:

[0045] S5.1. Calculation of changes in traffic jam length :

[0046] Based on the images of the identified traffic abnormalities, the vehicle type, vehicle center point coordinates ( Q a , Q b ), length of the vehicle C Q and the width of the vehicle k Q , with the coordinates of the center point of the abnormal event ( ya , y b ) is the starting point, and the identified vehicles are sorted in the opposite direction of the driving direction, and are sorted in order of 1, 2, 3, ..., P, where P is the total number of identified vehicles;

[0047] After sorting i The center point coordinates of each vehicle are recorded as ( Q ai , Q bi ), i=1,2,…,P, calculate the distance between two adjacent vehicles in order R i , the calculation formula is:

[0048] ;

[0049] Setting congestion thresholds Rt ,Compare R i and Rt relationship,

[0050] when When , it indicates that the distance between two adjacent vehicles is large, and there is no congestion in the area;

[0051] when When , it indicates that the distance between two adjacent vehicles is small, and congestion occurs in the area;

[0052] Traffic abnormalities are most likely to occur near the area where congestion occurs. of i The value of is recorded as it , the corresponding center point coordinates of the vehicle are ( Q ait , Q bit );

[0053] Combined with the ground distance of the unit pixel of the image of the traffic abnormality event in the horizontal direction , calculate the center point coordinates of the first vehicle ( Q a1 , Q b1 ) and it The coordinates of the center point of the vehicle ( Q ait , Q bit ) is the traffic congestion length x 2. The calculation formula is:

[0054] ;

[0055] use t The image collected at time 0 is calculated t Traffic jam length at time 0 ,use t The image collected at time 1 is calculated t Traffic jam length per moment ;

[0056] On this basis, the change in traffic congestion length is calculated

[0057] ;

[0058] S5.2. Calculation of traffic flow changes :

[0059] Based on the extracted video data, the first section DM1 is manually selected, and the traffic intelligent recognition model for identifying abnormal traffic events is used to identify and count the total number of vehicles that travel to the first section DM1 within 1 minute. U ,based on U Calculate traffic flow x 3. The expression is:

[0060] ;

[0061] use t The image collected at time 0 can be calculated t Traffic flow at time 0 ;use t The image collected at time 1 is calculated t Traffic flow at 1 moment ;

[0062] On this basis, the traffic flow changes are calculated :

[0063] ;

[0064] S5.3. Calculate average vehicle speed change :

[0065] Based on the extracted video data, the first section DM1 and the second section DM2 are manually selected, and the pixel distance between DM1 and DM2 is extracted as V , using the timestamp in the video data, calculate the time required for the vehicle to travel from section DM1 to section DM2 ta , combined with the ground distance of the unit pixel of the image of the traffic abnormality event in the horizontal direction , calculate the average speed x 4. The expression is:

[0066] ;

[0067] use t The image collected at time 0 is calculated t Average speed at time 0 ;use t The image collected at time 1 is calculated t Average speed at 1 moment ;

[0068] On this basis, the average vehicle speed change is calculated :

[0069] ;

[0070] S5.4. Calculation of delay time changes :

[0071] Based on the extracted video data, the first section DM1 and the second section DM2 are manually selected, and the pixel distance between DM1 and DM2 is extracted as V , using the timestamp in the video data, calculate the time required for the vehicle to travel from section DM1 to section DM2 ta , combined with the ground distance of the unit pixel of the image of the traffic abnormality event in the horizontal direction The design speed of the road section is v , calculate the delay time x 5. The expression is:

[0072] ;

[0073] use t The image collected at time 0 is calculated t Delay time at 0 ;use t The image collected at time 1 is calculated t 1 hour delay ;

[0074] On this basis, the average vehicle speed change is calculated :

[0075] .

[0076] Furthermore, the specific implementation method of step S6 includes the following steps:

[0077] S6.1. After the occurrence of an abnormal traffic event, the factors affecting the traffic change include road type CL, number of lanes CS, traffic flow JL, weather conditions TZ, geographical location of the accident DW, number of detours RS, shoulder width LK, abnormal event type YL, and abnormal event occurrence time YS;

[0078] S6.2. Collection dm Traffic abnormality events, each of which includes all factors affecting the change of traffic conditions. dm Traffic abnormality events, build a traffic abnormality event information summary matrix XJ :

[0079] ;

[0080] in, T is the transpose of the matrix, For the di Traffic abnormal event information matrix;

[0081] ;

[0082] in, The first di The road type, number of lanes, traffic flow, weather conditions, geographical location of the accident, number of detours, shoulder width, abnormal event type, and abnormal event occurrence time corresponding to each traffic abnormal event;

[0083] Based on the method in step S5, respectively calculate dm Traffic congestion length change matrix corresponding to traffic abnormal events , Traffic flow change matrix corresponding to traffic abnormal events , the average vehicle speed change matrix corresponding to traffic abnormal events , Delay time change matrix corresponding to traffic abnormal events :

[0084] ;

[0085] ;

[0086] ;

[0087] ;

[0088] in, , , , The first diThe traffic congestion length change value, traffic flow change value, average vehicle speed change value, and delay time change value corresponding to each traffic abnormality event;

[0089] S6.3. Establish the weight matrix corresponding to the change of traffic congestion length :

[0090] ;

[0091] in, The weight coefficients of the change in traffic congestion length are road type, number of lanes, traffic flow, weather conditions, geographical location of the accident, number of detours, shoulder width, abnormal event type, and abnormal event occurrence time;

[0092] Establish a traffic abnormal event information summary matrix XJ , Traffic congestion length change matrix corresponding to traffic abnormal events , and the weight matrix corresponding to the change in traffic congestion length The relationship between the three:

[0093] ;

[0094] Then calculate middle The value of

[0095] S6.4. Establishing the weight matrix corresponding to traffic flow changes :

[0096] ;

[0097] in, The weight coefficients of road type, number of lanes, traffic flow, weather conditions, geographical location of the accident, number of detours, shoulder width, abnormal event type, and abnormal event occurrence time on traffic flow changes are as follows;

[0098] Establish a traffic abnormal event information summary matrix XJ , Traffic flow change matrix corresponding to traffic abnormal events , and the weight matrix corresponding to the traffic flow change The relationship between the three:

[0099] ;

[0100] Then calculate middle The value of

[0101] S6.5. Establish the weight matrix corresponding to the average speed change :

[0102] ;

[0103] in, The weight coefficients of the road type, number of lanes, traffic flow, weather conditions, geographical location of the accident, number of detours, shoulder width, abnormal event type, and abnormal event occurrence time on the average vehicle speed change are as follows;

[0104] Establish a traffic abnormal event information summary matrix XJ , the average vehicle speed change matrix corresponding to traffic abnormal events , and the weight matrix corresponding to the average speed change The relationship between the three:

[0105] ;

[0106] Then calculate middle The value of

[0107] S6.6. Establish a weight matrix corresponding to the change of delay time :

[0108] ;

[0109] in, The weight coefficients of the change in delay time are road type, number of lanes, traffic flow, weather conditions, geographical location of the accident, number of detours, shoulder width, abnormal event type, and abnormal event occurrence time;

[0110] Establish a traffic abnormal event information summary matrix XJ , Delay time change matrix corresponding to traffic abnormal events , and the weight matrix corresponding to the delay time change The relationship between the three:

[0111] ;

[0112] Then calculate middle The value of

[0113] S6.7. Establish a comprehensive impact index ZH :

[0114] ;

[0115] ;

[0116] in, , , , are the weights corresponding to the changes in traffic congestion length, traffic flow, average vehicle speed, and delay time in the comprehensive impact index. is the processing difficulty index; the above values ​​are determined by technicians based on experience;

[0117] The comprehensive impact index corresponding to the traffic abnormality events is calculated, and then arranged in order from large to small to obtain the order of urgency of handling the traffic abnormality events.

[0118] Beneficial effects of the present invention:

[0119] The method for sorting the urgency of handling abnormal traffic events based on drone monitoring described in the present invention improves image quality by dynamically adjusting pixel values ​​in an image, making image enhancement more natural and reducing the risk of over-processing.

[0120] The method for ranking the urgency of handling abnormal traffic events based on drone monitoring described in the present invention can predict traffic changes after abnormal events occur. It is of great significance for deploying traffic management resources in advance, formulating effective response strategies, and reducing traffic congestion and related economic losses. It can improve road use efficiency, ensure public safety, and optimize traffic flow.

[0121] The method for sorting the urgency of handling abnormal traffic events based on drone monitoring described in the present invention can sort the urgency of handling abnormal traffic events. This method can ensure that the most critical events are handled first and reduce the potential harm of accidents. BRIEF DESCRIPTION OF THE DRAWINGS

[0122] Figure 1 The present invention is a flowchart of a method for sorting the urgency of handling abnormal traffic events based on drone monitoring. DETAILED DESCRIPTION

[0123] In order to make the purpose, technical solution and advantages of the present invention more clear, the present invention is further described in detail below in conjunction with the accompanying drawings and specific 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, that is, the specific embodiments described are only part of the embodiments of the present invention, rather than all of the specific embodiments. The components of the specific embodiments of the present invention described and shown in the drawings herein can be arranged and designed in various different configurations, and the present invention can also have other embodiments.

[0124] Therefore, the following detailed description of the specific embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention claimed for protection, but merely represents the selected specific embodiments of the present invention. Based on the specific embodiments of the present invention, all other specific embodiments obtained by those skilled in the art without making creative work are within the scope of protection of the present invention.

[0125] In order to further understand the content, features and effects of the present invention, the following specific implementation methods are given as examples, and the attached Figure 1 The detailed instructions are as follows:

[0126] Embodiment 1:

[0127] A method for sorting the urgency of handling abnormal traffic events based on drone monitoring comprises the following steps:

[0128] S1. Using a drone to collect traffic videos, and then extracting frames from the traffic videos to obtain traffic images;

[0129] S2. performing image processing on the traffic image obtained from the traffic video to obtain an updated traffic image;

[0130] The specific implementation method of step S2 includes the following steps:

[0131] S2.1. For the traffic image obtained from the traffic video in step S1, collect the image at pixel coordinates ( a , b ) is represented by the pixel value at the position A ( a , b ),in, a and b is the pixel coordinate in the horizontal direction and the pixel coordinate in the vertical direction, and the pixel gradient is calculated Horizontal difference in the image The vertical difference , the expression is:

[0132] ;

[0133] ;

[0134] in, For the image at coordinates ( a +1, b ) pixel value at the position, For the image at coordinates ( a , b +1) pixel value at position;

[0135] Then calculate the pixel gradient , the calculation formula is:

[0136] ;

[0137] Pixel gradient is used to determine the edge strength at image pixels;

[0138] S2.2. Setting the adjustment factor c ( a , b ), used to determine different locations in the image ( a , b ) pixel update degree, adjustment coefficient c ( a , b ) is calculated as:

[0139] ;

[0140] in, is a constant that controls the sensitivity, To control the constant of the gradient component, both constants are determined empirically;

[0141] S2.3. Update the pixels of the image and obtain the updated image at coordinates ( a , b ) pixel value at position , the calculation formula is:

[0142] ;

[0143] in, is the pixel coordinate ( a , b ) The four pixel coordinates that are adjacent in the top, bottom, left, and right directions, Refers to the pixel values ​​of four adjacent pixel coordinates in the four directions of up, down, left, and right;

[0144] Furthermore, in order to solve the problems of blur, noise, detail loss, etc. in drone-collected images due to distance, motion, illumination changes, etc., a method for updating image pixels for drone-collected image quality enhancement is proposed. This method can adapt to local features by independently calculating the changes around each pixel, and can make more detailed adjustments to the details in the image. This method dynamically adjusts the weights and final pixel values ​​according to the actual pixel changes, making the image enhancement more natural and reducing the risk of over-processing.

[0145] S3. Using the updated traffic image obtained in step S2, manually select images of abnormal traffic events including different types of vehicles, train the YOLOv10 deep learning model, and obtain an intelligent traffic recognition model for identifying abnormal traffic events;

[0146] Furthermore, the specific implementation method of step S3 includes the following steps:

[0147] S3.1. Manually select images of traffic anomaly events including different types of vehicles, including vehicle collision, vehicle breakdown, road collapse, mudslide, building collapse, tree breakage, fog, road icing, sudden congestion, long-term congestion, illegal parking, vehicle fire, hazardous material leakage, and road construction; different types of vehicles include sedans, SUVs, vans, vans, trucks, buses, long-distance coaches, engineering vehicles, two-wheelers, cement mixers, tank trucks, and tractors;

[0148] S3.2. Use a labeling tool to label the images manually selected in step S3.1, and label the location and category of the vehicle for each image, and the area and type of the abnormal traffic event;

[0149] S3.3. Build a data set, convert the image annotation file obtained in step S3.2 into txt format, and divide the data set into training set, validation set, and test set according to the ratio of 70%, 15%, and 15% for the images and the corresponding image annotation files;

[0150] S3.4. Use the training set obtained in step S3.3 to train the YOLOv10 model. First, configure an environment suitable for running the YOLOv10 model and set the learning rate, batch size, training cycle, and hyperparameters. Use the loss during training and the performance on the validation set to monitor the training progress and adjust the training parameters.

[0151] The precision and recall rate parameters are used to evaluate the effects of vehicle identification and abnormal event detection. When the precision and recall rate reach the set value, the training is stopped. At this time, the corresponding model is a traffic intelligent recognition model for identifying traffic abnormal events.

[0152] S4. The updated traffic image obtained in step S2 is input into the intelligent traffic recognition model for identifying abnormal traffic events in step S3, and the image of the abnormal traffic event is recognized to establish a conversion relationship between the image size and the actual size;

[0153] Furthermore, the specific implementation method of step S4 includes the following steps:

[0154] S4.1. The updated traffic image obtained in step S2 is input into the traffic intelligent recognition model for identifying abnormal traffic events in step S3 to identify abnormal traffic events and identify the image of abnormal traffic events;

[0155] S4.2. Obtaining the UAV’s flight altitude data from the UAV’s onboard positioning system h w , get the camera focal length from the camera device j , the width of the sensor k sen ,high h sen , and the width of the image of the traffic anomaly event k img ,high h img ; Calculate the actual length of the image unit pixel corresponding to the traffic abnormality event, the calculation formula is:

[0156] ;

[0157] ;

[0158] in, and are the ground distance in the horizontal direction and the ground distance in the vertical direction of the image unit pixel of the traffic abnormality event respectively;

[0159] S4.3. Based on the fact that the ground distance of unit pixels in the image collected by drone is equal in horizontal and vertical directions, that is, , then establish the pixel coordinates ( a , b ) and actual geographic coordinates The conversion relationship between them is expressed as:

[0160] ;

[0161] ;

[0162] in, are the geographic coordinates of the image reference point, is the pixel coordinate of the image reference point in the image;

[0163] S5. Based on the images and videos of the traffic abnormality events identified in step S3 and the conversion relationship between the image size and the actual size obtained in step S4, a method for analyzing the evolution law of the impact of traffic abnormality events on traffic is constructed to analyze changes in traffic congestion length, traffic flow, average vehicle speed, and delay time;

[0164] Furthermore, the specific implementation method of step S5 includes the following steps:

[0165] S5.1. Calculation of changes in traffic jam length :

[0166] Based on the images of the identified traffic abnormalities, the vehicle type, vehicle center point coordinates ( Q a , Q b ), length of the vehicle C Q and the width of the vehicle k Q , with the coordinates of the center point of the abnormal event ( y a , y b ) is the starting point, and the identified vehicles are sorted in the opposite direction of the driving direction, and are sorted in order of 1, 2, 3, ..., P, where P is the total number of identified vehicles;

[0167] After sorting i The center point coordinates of each vehicle are recorded as ( Q ai , Q bi ), i=1,2,…,P, calculate the distance between two adjacent vehicles in order R i , the calculation formula is:

[0168] ;

[0169] Setting congestion thresholds Rt ,Compare R i and Rt relationship,

[0170] when When , it indicates that the distance between two adjacent vehicles is large, and there is no congestion in the area;

[0171] when When , it indicates that the distance between two adjacent vehicles is small, and congestion occurs in the area;

[0172] Traffic abnormalities are most likely to occur near the area where congestion occurs. of i The value of is recorded as it , the corresponding center point coordinates of the vehicle are ( Q ait , Q bit );

[0173] Combined with the ground distance of the unit pixel of the image of the traffic abnormality event in the horizontal direction , calculate the center point coordinates of the first vehicle ( Q a1 , Q b1 ) and it The coordinates of the center point of the vehicle ( Q ait , Q bit ) is the traffic congestion length x 2. The calculation formula is:

[0174] ;

[0175] use t The image collected at time 0 is calculated t Traffic jam length at time 0 ,use t The image collected at time 1 is calculated t Traffic jam length per moment ;

[0176] On this basis, the change in traffic congestion length is calculated :

[0177] ;

[0178] S5.2. Calculation of traffic flow changes :

[0179] Based on the extracted video data, the first section DM1 is manually selected, and the traffic intelligent recognition model for identifying abnormal traffic events is used to identify and count the total number of vehicles that travel to the first section DM1 within 1 minute. U ,based on U Calculate traffic flow x 3. The expression is:

[0180] ;

[0181] use t The image collected at time 0 can be calculated t Traffic flow at time 0 ;use t The image collected at time 1 is calculated t Traffic flow at 1 moment ;

[0182] On this basis, the traffic flow changes are calculated :

[0183] ;

[0184] S5.3. Calculate average vehicle speed change :

[0185] Based on the extracted video data, the first section DM1 and the second section DM2 are manually selected, and the pixel distance between DM1 and DM2 is extracted as V , using the timestamp in the video data, calculate the time required for the vehicle to travel from section DM1 to section DM2 ta , combined with the ground distance of the unit pixel of the image of the traffic abnormality event in the horizontal direction , calculate the average vehicle speed x 4. The expression is:

[0186] ;

[0187] use t The image collected at time 0 is calculated t Average speed at time 0 ;use t The image collected at time 1 is calculated t Average speed at 1 moment ;

[0188] On this basis, the average vehicle speed change is calculated :

[0189] ;

[0190] S5.4. Calculation of delay time changes :

[0191] Based on the extracted video data, the first section DM1 and the second section DM2 are manually selected, and the pixel distance between DM1 and DM2 is extracted as V , using the timestamp in the video data, calculate the time required for the vehicle to travel from section DM1 to section DM2 ta , combined with the ground distance of the unit pixel of the image of the traffic abnormality event in the horizontal direction The design speed of the road section is v , calculate the delay time x 5. The expression is:

[0192] ;

[0193] use t The image collected at time 0 is calculated t Delay time at 0 ;use t The image collected at time 1 is calculatedt 1 hour delay ;

[0194] On this basis, the average vehicle speed change is calculated :

[0195] .

[0196] S6. Construct a traffic congestion length change matrix corresponding to traffic abnormal events, a traffic flow change matrix corresponding to traffic abnormal events, an average vehicle speed change matrix corresponding to traffic abnormal events, and a delay time change matrix corresponding to traffic abnormal events. Then, based on the constructed matrix, establish a comprehensive impact index of traffic abnormal events and rank the urgency of handling traffic abnormal events based on drone monitoring.

[0197] Furthermore, the specific implementation method of step S6 includes the following steps:

[0198] S6.1. After the occurrence of an abnormal traffic event, the factors affecting the traffic change include road type CL, number of lanes CS, traffic flow JL, weather conditions TZ, geographical location of the accident DW, number of detours RS, shoulder width LK, abnormal event type YL, and abnormal event occurrence time YS;

[0199] Furthermore, the road types considered include urban expressways, main roads, and secondary roads. Urban expressways have a large capacity. Once an abnormal event occurs, it may cause serious traffic congestion due to high vehicle speeds and dense traffic. The capacity of the main road is between that of the expressway and the secondary road, and it has a certain emergency response capacity. Abnormal events may cause significant congestion, but there are usually alternative routes to choose from. The capacity of secondary roads is small, but the network density is high. The impact of abnormal events may be relatively limited, and vehicles can easily find alternative routes. In order to achieve quantitative analysis, urban expressways, main roads, and secondary roads are numbered 1, 2, and 3 respectively.

[0200] Furthermore, the number of lanes directly affects road capacity and traffic recovery capabilities. Multi-lane roads have greater buffering capacity. Even if one lane is closed, other lanes can still remain open, reducing overall traffic disruption. Roads with fewer lanes have lower capacity, abnormal events may cause severe congestion, and it may take longer to restore normal traffic flow. In quantitative analysis, the actual number of lanes is used for analysis.

[0201] Furthermore, traffic flow is directly related to the impact of abnormal events. During high-flow periods, the impact of abnormal events is more serious and may cause large-scale traffic congestion and delays. During low-flow periods, the impact is relatively small and the transportation system has greater flexibility to absorb and respond to abnormal situations. In quantitative analysis, actual traffic flow is used for analysis.

[0202] Furthermore, weather conditions affect driving behavior and road conditions. Sunny days provide good visibility and good road conditions, which are conducive to rapid traffic recovery. Rainy and snowy days reduce visibility and road friction, increase the risk of accidents, and may prolong traffic recovery time. Foggy weather seriously affects vision, which may lead to chain accidents and make traffic conditions more complicated. In order to achieve quantitative analysis, sunny days, rainy days, snowy days, and foggy days are numbered 1, 2, 3, and 4 respectively.

[0203] Furthermore, the geographical location of the accident affects the difficulty of rescue and the complexity of traffic control. In the central area of ​​the city, the congestion is usually high, but the emergency resources are relatively abundant, and it may be handled faster. In the suburban area, the traffic flow is relatively small, but the emergency resources may be less, and the processing time may be longer. In the remote area, the rescue arrival time may be longer, but the traffic flow is small, and the impact on the overall transportation network may be small. In order to achieve quantitative analysis, the central area of ​​the city, the suburban area, and the remote area are numbered 1, 2, and 3 respectively.

[0204] Furthermore, the number of detour routes directly affects the traffic diversion capacity. Multiple detour routes: help to disperse traffic flow and reduce the pressure on the main affected roads. Few or no detour routes: may cause serious traffic accumulation near the accident site, prolonging the recovery time. In the quantitative analysis, the actual number of detour routes is used for analysis.

[0205] Furthermore, the width of the shoulder affects emergency handling and temporary traffic capacity. A wide shoulder can provide space for emergency vehicles to pass, which may allow some traffic to continue to flow and speed up recovery. A narrow shoulder limits the space for emergency operations and may lead to complete road closures, increasing traffic disruption time. In the quantitative analysis, the actual shoulder width is used for analysis.

[0206] Furthermore, different types of abnormal events require different processing time and resources. In the present invention, traffic abnormal events include: vehicle collision, vehicle breakdown, road collapse, mudslide, building collapse, tree breakage, fog, road icing, sudden congestion, long-term congestion, illegal parking, vehicle fire, dangerous goods leakage, and road construction. In order to achieve quantitative analysis, the above abnormal events are numbered 1, 2, 3, ..., 14 in sequence.

[0207] Furthermore, the time when an abnormal event occurs is directly related to its impact scope and duration. Peak hours: The impact is the most serious and may cause large-scale traffic paralysis. Off-peak hours: The impact is relatively small and the traffic system has greater flexibility to absorb the impact. In order to achieve quantitative analysis, peak hours and off-peak hours are numbered 1 and 2 respectively.

[0208] The above data are obtained from public channels.

[0209] S6.2. Collection dm Traffic abnormality events, each of which includes all factors affecting the change of traffic conditions. dm Traffic abnormality events, build a traffic abnormality event information summary matrix XJ :

[0210] ;

[0211] in, T is the transpose of the matrix, For the di Traffic abnormal event information matrix;

[0212] ;

[0213] in, The first di The road type, number of lanes, traffic flow, weather conditions, geographical location of the accident, number of detours, shoulder width, abnormal event type, and abnormal event occurrence time corresponding to each traffic abnormal event;

[0214] Based on the method in step S5, respectively calculate dm Traffic congestion length change matrix corresponding to traffic abnormal events , Traffic flow change matrix corresponding to traffic abnormal events , the average vehicle speed change matrix corresponding to traffic abnormal events , Delay time change matrix corresponding to traffic abnormal events :

[0215] ;

[0216] ;

[0217] ;

[0218] ;

[0219] in, , , , The first di The traffic congestion length change value, traffic flow change value, average vehicle speed change value, and delay time change value corresponding to each traffic abnormality event;

[0220] S6.3. Establish the weight matrix corresponding to the change of traffic congestion length :

[0221] ;

[0222] in, The weight coefficients of the change in traffic congestion length are road type, number of lanes, traffic flow, weather conditions, geographical location of the accident, number of detours, shoulder width, abnormal event type, and abnormal event occurrence time;

[0223] Establish a traffic abnormal event information summary matrix XJ , Traffic congestion length change matrix corresponding to traffic abnormal events , and the weight matrix corresponding to the change in traffic congestion length The relationship between the three:

[0224] ;

[0225] Then calculate middle The value of

[0226] S6.4. Establishing the weight matrix corresponding to traffic flow changes :

[0227] ;

[0228] in, The weight coefficients of road type, number of lanes, traffic flow, weather conditions, geographical location of the accident, number of detours, shoulder width, abnormal event type, and abnormal event occurrence time on traffic flow changes are as follows;

[0229] Establish a traffic abnormal event information summary matrix XJ , Traffic flow change matrix corresponding to traffic abnormal events , and the weight matrix corresponding to the traffic flow change The relationship between the three:

[0230] ;

[0231] Then calculate middle The value of

[0232] S6.5. Establish the weight matrix corresponding to the average speed change :

[0233] ;

[0234] in, The weight coefficients of the road type, number of lanes, traffic flow, weather conditions, geographical location of the accident, number of detours, shoulder width, abnormal event type, and abnormal event occurrence time on the average vehicle speed change are as follows;

[0235] Establish a traffic abnormal event information summary matrix XJ , the average vehicle speed change matrix corresponding to traffic abnormal events , and the weight matrix corresponding to the average speed change The relationship between the three:

[0236] ;

[0237] Then calculate middle The value of

[0238] S6.6. Establish a weight matrix corresponding to the change of delay time :

[0239] ;

[0240] in, The weight coefficients of the change in delay time are road type, number of lanes, traffic flow, weather conditions, geographical location of the accident, number of detours, shoulder width, abnormal event type, and abnormal event occurrence time;

[0241] Establish a traffic abnormal event information summary matrix XJ , Delay time change matrix corresponding to traffic abnormal events , and the weight matrix corresponding to the delay time change The relationship between the three:

[0242] ;

[0243] Then calculate middle The value of

[0244] S6.7. Establish a comprehensive impact index ZH :

[0245] ;

[0246] ;

[0247] in, , , , are the weights corresponding to the changes in traffic congestion length, traffic flow, average vehicle speed, and delay time in the comprehensive impact index. is the processing difficulty index; the above values ​​are determined by technicians based on experience;

[0248] The comprehensive impact index corresponding to the traffic abnormality events is calculated, and then arranged in order from large to small to obtain the order of urgency of handling the traffic abnormality events.

[0249] Furthermore, when traffic abnormal events AA1, AA2, AA3, ..., AAnm occur simultaneously (nm is the number of traffic abnormal events), the comprehensive impact index ZH corresponding to each traffic event is calculated respectively. AA1 , ZH AA2 、…、ZH AAnm .

[0250] ZH AA1 For example, after the traffic abnormality event AA1 occurs, the road type, number of lanes, traffic flow, weather conditions, geographical location of the accident, number of detours, shoulder width, abnormal event type, and abnormal event occurrence time data are collected to establish the traffic abnormality event information matrix XJ AA1 :

[0251] ;

[0252] in, They are the road type, number of lanes, traffic flow, weather conditions, geographical location of the accident, number of detours, shoulder width, abnormal event type, and abnormal event occurrence time corresponding to the traffic abnormal event AA1.

[0253] At this time, the corresponding traffic congestion length change can be calculated Traffic flow changes , Average vehicle speed change , Delay time changes :

[0254] ;

[0255] ;

[0256] ;

[0257] ;

[0258] On this basis, the comprehensive impact index ZH corresponding to the traffic abnormality event AA1 is calculated AA1 :

[0259] ;

[0260] Similarly, the comprehensive impact index ZH corresponding to traffic abnormal events AA2, AA3, ..., AAnm can be calculated AA2 , ZH AA3 、…、ZH AAnm .

[0261] ZH AA1 , ZH AA2 , ZH AA3 、…、ZH AAnm , and are arranged in order from large to small, which is the order of urgency for handling traffic abnormal events.

[0262] The key points and intended protection points of the present invention are:

[0263] (1) An image pixel updating method for enhancing the quality of images collected by UAVs.

[0264] (2) A method for analyzing the evolution of the impact of abnormal traffic events on traffic.

[0265] (3) A method for ranking the urgency of handling abnormal traffic events.

[0266] It should be noted that relational terms such as "first" and "second" are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0267] Although the present application has been described above with reference to specific embodiments, various modifications may be made thereto and parts thereof may be replaced with equivalents without departing from the scope of the present application. In particular, as long as there is no structural conflict, the various features in the specific embodiments disclosed in the present application may be used in combination with each other in any manner, and the fact that these combinations are not exhaustively described in this specification is only for the sake of omitting space and saving resources. Therefore, the present application is not limited to the specific embodiments disclosed herein, but includes all technical solutions falling within the scope of the claims.

Claims

1. A method for sorting the urgency of handling abnormal traffic events based on drone monitoring, characterized in that: The steps include: S1. Using a drone to collect traffic videos, and then extracting frames from the traffic videos to obtain traffic images; S2. performing image processing on the traffic image obtained from the traffic video to obtain an updated traffic image; The specific implementation method of step S2 includes the following steps: S2.

1. For the traffic image obtained from the traffic video in step S1, the pixel value of the captured image at the pixel coordinate (a, b) is expressed as A(a, b), where a and b are the pixel coordinates in the horizontal direction and the pixel coordinates in the vertical direction, and the pixel gradient is calculated. The horizontal difference A in the image a and the vertical difference A b , the expression is: A a =A(a+1,b)-A(a,b) A b =A(a,b+1)-A(a,b) Among them, A(a+1,b) is the pixel value of the image at the coordinate position (a+1,b), and A(a,b+1) is the pixel value of the image at the coordinate position (a,b+1); Then calculate the pixel gradient The calculation formula is: Pixel gradient is used to determine the edge strength at image pixels; S2.

2. Set the adjustment coefficient c(a,b) to determine the update degree of pixels at different positions (a,b) in the image. The calculation formula of the adjustment coefficient c(a,b) is: Among them, d is a constant for controlling sensitivity, and g is a constant for controlling the gradient component, both constants are determined empirically; S2.

3. Update the pixel of the image and obtain the pixel value A of the updated image at the coordinate position (a, b) e (a,b), the calculation formula is: A e (a,b)=A(a,b)+Σ f c(a,b)(Af-A(a,b)) Wherein, f is the four pixel coordinates adjacent to the pixel coordinate (a, b) in the four directions of up, down, left, and right, and Af refers to the pixel value of the four pixel coordinates adjacent to the pixel coordinate (a, b) in the four directions of up, down, left, and right; S3. Using the updated traffic image obtained in step S2, manually select images of abnormal traffic events including different types of vehicles, train the YOLOv10 deep learning model, and obtain a traffic intelligent recognition model for identifying abnormal traffic events; S4. The updated traffic image obtained in step S2 is input into the intelligent traffic recognition model for identifying abnormal traffic events in step S3 to identify abnormal traffic events, and the image size of the image that identifies the abnormal traffic event is established to establish a conversion relationship between the image size and the actual size; The specific implementation method of step S4 includes the following steps: S4.

1. The updated traffic image obtained in step S2 is input into the traffic intelligent recognition model for identifying abnormal traffic events in step S3 to identify abnormal traffic events and identify the image of abnormal traffic events; S4.

2. Obtain the UAV flight altitude data h from the UAV onboard positioning system w , get the camera focal length j and sensor width k from the camera device sen , height h sen , and the width k of the image of traffic abnormality event img , height h img ; Calculate the actual length of the image unit pixel corresponding to the traffic abnormality event, the calculation formula is: Among them, M a and M b are the ground distance in the horizontal direction and the ground distance in the vertical direction of the image unit pixel of the traffic abnormality event respectively; S4.

3. Based on the fact that the ground distance of unit pixels in the image collected by drone is equal in horizontal and vertical directions, that is, Ma = Mb, the pixel coordinates (a, b) and the actual geographic coordinates (a s ,b s ) is expressed as: a s =a s-ref +(a-a ref )·M a b s =b s-ref +(b-b ref )·M a Among them, (a s-ref ,b s-ref ) is the geographic coordinates of the image reference point, (a ref ,b ref ) is the pixel coordinate of the image reference point in the image S5. Based on the images and videos of the traffic abnormality events identified in step S3 and the conversion relationship between the image size and the actual size obtained in step S4, a method for analyzing the evolution law of the impact of traffic abnormality events on traffic is constructed to analyze the changes in traffic congestion length, traffic flow, average vehicle speed, and delay time; S6. Construct a traffic congestion length change matrix corresponding to traffic abnormal events, a traffic flow change matrix corresponding to traffic abnormal events, an average vehicle speed change matrix corresponding to traffic abnormal events, and a delay time change matrix corresponding to traffic abnormal events. Then, based on the constructed matrix, establish a comprehensive impact index of traffic abnormal events and rank the urgency of handling traffic abnormal events based on drone monitoring.

2. The method for sorting the urgency of handling abnormal traffic events based on drone monitoring according to claim 1 is characterized in that: The specific implementation method of step S3 includes the following steps: S3.

1. Manually select images of traffic anomaly events including different types of vehicles, including vehicle collision, vehicle breakdown, road collapse, mudslide, building collapse, tree breakage, fog, road icing, sudden congestion, long-term congestion, illegal parking, vehicle fire, dangerous goods leakage, and road construction; the different types of vehicles include sedans, SUVs, vans, vans, trucks, buses, long-distance coaches, engineering vehicles, two-wheelers, cement mixers, tank trucks, and tractors; S3.

2. Use annotation tools to annotate the images manually selected in step S3.1, and annotate the location and category of the vehicle for each image, and the area and type of the abnormal traffic event; S3.

3. Build a data set, convert the image annotation file obtained in step S3.2 into txt format, and divide the image and the corresponding image annotation file into a training set, a validation set, and a test set in a ratio of 70%, 15%, and 15%; S3.

4. Train the YOLOv10 model using the training set obtained in step S3.

3. First, configure an environment suitable for running the YOLOv10 model and set the learning rate, batch size, training cycle, and hyperparameters. Use the loss during training and the performance on the validation set to monitor the training progress and adjust the training parameters. The precision and recall rate parameters are used to evaluate the effects of vehicle identification and abnormal event detection. When the precision and recall rate reach the set value, the training is stopped. At this time, the corresponding model is a traffic intelligent recognition model for identifying abnormal traffic events.

3. The method for sorting the urgency of handling abnormal traffic events based on drone monitoring according to claim 2 is characterized in that: The specific implementation method of step S5 includes the following steps: S5.

1. Calculate the change in traffic jam length Δx2: Based on the image of the identified traffic abnormality event, the vehicle type, vehicle center point coordinates (Q a , Q b ), the length of the vehicle C Q and the width of the vehicle k Q , with the coordinates of the center point of the abnormal event (y a ,y b ) is the starting point, and the identified vehicles are sorted in the opposite direction of the driving direction, and are sorted in order of 1, 2, 3, ..., P, where P is the total number of identified vehicles; The coordinates of the center point of the i-th vehicle after sorting are recorded as (Q ai , Q bi ), i = 1, 2, ..., P, and calculate the distance R between two adjacent vehicles in sequence. i , the calculation formula is: Set the congestion threshold Rt and compare R i Relationship with Rt, When R i >Rt, it indicates that the distance between two adjacent vehicles is large and there is no congestion in the area; When R i When ≤Rt, it indicates that the distance between two adjacent vehicles is small and congestion occurs in the area; The area near the traffic abnormality event is the most prone to congestion. The first occurrence of R i The value of i when >Rt is recorded as it, and the corresponding coordinate of the center point of the vehicle is (Q ait , Q bit ); Combined with the obtained ground distance M of the unit pixel of the image of the traffic abnormality event in the horizontal direction a , calculate the center point coordinates of the first vehicle (Q a1 , Q b1 ) and the coordinates of the center point of the it-th vehicle (Q ait , Q bit ) is the traffic congestion length x2, and the calculation formula is: The traffic congestion length x2 at time t0 is calculated using the image collected at time t0 t0 , the image collected at time t1 is used to calculate the traffic congestion length x2 at time t1 t1 ; On this basis, the change in traffic congestion length Δx2 is calculated: S5.

2. Calculate the traffic flow change Δx3: Based on the extracted video data, the first section DM1 is manually selected, and the traffic intelligent recognition model for identifying traffic abnormal events is used to identify and count the total number U of vehicles that travel to the first section DM1 in 1 minute. The traffic flow x3 is converted based on U, and the expression is: x3=60×U; Using the image collected at time t0, the traffic flow x3 at time t0 can be calculated t0 ; Using the image collected at time t1, calculate the traffic flow x3 at time t1 t1 ; On this basis, the traffic flow change Δx3 is calculated: Δx3=x3 t1 -x3 t0 ; S5.

3. Calculate the average vehicle speed change Δx4: Based on the extracted video data, the first section DM1 and the second section DM2 are manually selected, and the pixel distance between DM1 and DM2 is extracted as V. The time stamp in the video data is used to calculate the time ta required for the vehicle to travel from section DM1 to section DM2, combined with the ground distance M of the unit pixel of the image of the traffic abnormality event in the horizontal direction. a , calculate the average speed x4, the expression is: Using the image collected at time t0, the average vehicle speed at time t0 x4 is calculated t0 ; Using the image collected at time t1, calculate the average vehicle speed at time t1 x4 t1 ; On this basis, the average vehicle speed change Δx4 is calculated: Δx4=x4 t1 -x4 t0 ; S5.

4. Calculate the delay time change Δx5: Based on the extracted video data, the first section DM1 and the second section DM2 are manually selected, and the pixel distance between DM1 and DM2 is extracted as V. The time stamp in the video data is used to calculate the time ta required for the vehicle to travel from section DM1 to section DM2, combined with the ground distance M of the unit pixel of the image of the traffic abnormality event in the horizontal direction. a , the design speed of the road section is v, and the delay time x5 is calculated, and the expression is: Using the image collected at time t0, calculate the delay time x5 at time t0 t0 ; Using the image collected at time t1, calculate the delay time x5 at time t1 t1 ; On this basis, the average vehicle speed change Δx5 is calculated: <h2 style=";text-align:left;direction:ltr">Δx5 = x5<h2 style=";text-align:left;direction:ltr"> t1 <h2 style=";text-align:left;direction:ltr"> -x5<h2 style=";text-align:left;direction:ltr"> t0 <h2 style=";text-align:left;direction:ltr"> 。 4. The method for sorting the urgency of handling abnormal traffic events based on drone monitoring according to claim 3 is characterized in that: The specific implementation method of step S6 includes the following steps: S6.

1. After the occurrence of an abnormal traffic event, the factors affecting the traffic change include road type CL, number of lanes CS, traffic flow JL, weather conditions TZ, geographical location of the accident DW, number of detours RS, shoulder width LK, abnormal event type YL, and abnormal event occurrence time YS; S6.

2. Collect dm traffic abnormality events, each of which includes all factors affecting the change of traffic. Based on all dm traffic abnormality events, construct the traffic abnormality event information summary matrix XJ: XJ=[XJ1 XJ2...XJ di ...XJ dm ] T Where T is the transpose of the matrix, XJ di is the information matrix of the d-th traffic abnormality event; XJ di =[CL di CS di JL di TZ di DW di RS di LK di YL di YS di ] Among them, CL di , CS di , JL di , TZ di , DW di , RS di , LK di , YL di , YS di The road type, number of lanes, traffic flow, weather conditions, geographical location of the accident, number of detours, shoulder width, abnormal event type, and abnormal event occurrence time corresponding to the d-th traffic abnormal event are listed in order; Based on the method in step S5, the traffic congestion length change matrix ΔX2 corresponding to the dm traffic abnormal events, the traffic flow change matrix ΔX3 corresponding to the traffic abnormal events, the average vehicle speed change matrix ΔX4 corresponding to the traffic abnormal events, and the delay time change matrix ΔX5 corresponding to the traffic abnormal events are calculated respectively: ΔX2=[Δx 2-1 Δx 2-2 ...Δx 2-di ...Δx 2-dm ] T ΔX3=[Δx 3-1 Δx 3-2 ...Δx 3-di ...Δx 3-dm ] T ΔX4=[Δx 4-1 Δx 4-2 ...Δx 4-di ...Δx 4-dm ] T ΔX5=[Δx 5-1 Δx 5-2 ...Δx 5-di ...Δx 5-dm ] T Where Δx 2-di , Δx 3-di , Δx 4-di , Δx 5-di They are the traffic jam length change value, traffic flow change value, average vehicle speed change value, and delay time change value corresponding to the d-th traffic abnormality event; S6.

3. Establish the weight matrix α2 corresponding to the change of traffic congestion length: α2＝[α 2-1 α 2-2 α 2-3 ...α 2-9 ] T Among them, α 2-1 , α 2-2 , α 2-3 , α 2-4 , α 2-5 , α 2-6 , α 2-7 , α 2-8 , α 2-9 The weight coefficients of the change in traffic congestion length are road type, number of lanes, traffic flow, weather conditions, geographical location of the accident, number of detours, shoulder width, abnormal event type, and abnormal event occurrence time; The relationship between the traffic abnormality event information summary matrix XJ, the traffic congestion length change matrix ΔX2 corresponding to the traffic abnormality event, and the weight matrix α2 corresponding to the traffic congestion length change is established: XJ·α2=ΔX2 Then the values of α in α2, namely α 2-1 , α 2-2 , α 2-3 , α 2-4 , α 2-5 , α 2-6 , α 2-7 , α 2-8 , α 2-9 are calculated; 2-1 α 2-2 α 2-3 α 2-4 α 2-5 α 2-6 α 2-7 α 2-8 α 2-9 ; S6.

4. Establish the weight matrix α3 corresponding to the traffic flow change: α3＝[α 3-1 α 3-2 α 3-3 ...α 3-9 ] T Among them, α 3-1 , α 3-2 , α 3-3 , α 3-4 , α 3-5 , α 3-6 , α 3-7 , α 3-8 , α 3-9 The weight coefficients of road type, number of lanes, traffic flow, weather conditions, geographical location of the accident, number of detours, shoulder width, abnormal event type, and abnormal event occurrence time on traffic flow changes are as follows; Establish the relationship between the traffic abnormality event information summary matrix XJ, the traffic flow change matrix ΔX3 corresponding to the traffic abnormality event, and the weight matrix α3 corresponding to the traffic flow change: XJ·α3=ΔX3 Then calculate the values of α in α3 3-1 , α 3-2 , α 3-3 , α 3-4 , α 3-5 , α 3-6 , α 3-7 , α 3-8 , α 3-9 ; S6.

5. Establish the weight matrix α4 corresponding to the average vehicle speed change: α4＝[α 4-1 α 4-2 α 4-3 ...α 4-9 ] T Among them, α 4-1 , α 4-2 , α 4-3 , α 4-4 , α 4-5 , α 4-6 , α 4-7 , α 4-8 , α 4-9 The weight coefficients of the road type, number of lanes, traffic flow, weather conditions, geographical location of the accident, number of detours, shoulder width, abnormal event type, and abnormal event occurrence time on the average vehicle speed change are as follows; Establish the relationship between the traffic abnormality event information summary matrix XJ, the average vehicle speed change matrix ΔX4 corresponding to the traffic abnormality event, and the weight matrix α4 corresponding to the average vehicle speed change: XJ·α4=ΔX4 Then calculate the values of α in α4 4-1 , α 4-2 , α 4-3 , α 4-4 , α 4-5 , α 4-6 , α 4-7 , α 4-8 , α 4-9 ; S6.

6. Establish the weight matrix α5 corresponding to the delay time change: α5＝[α 5-1 α 5-2 α 5-3 ...α 5-9 ] T Among them, α 5-1 , α 5-2 , α 5-3 , α 5-4 , α 5-5 , α 5-6 , α 5-7 , α 5-8 , α 5-9 The weight coefficients of the change in delay time are road type, number of lanes, traffic flow, weather conditions, geographical location of the accident, number of detours, shoulder width, abnormal event type, and abnormal event occurrence time; Establish the relationship between the traffic abnormality event information summary matrix XJ, the delay time change matrix ΔX5 corresponding to the traffic abnormality event, and the weight matrix α5 corresponding to the delay time change: XJ·α5=ΔX5 Then, the values of α in α5, namely α 5-1 , α 5-2 , α 5-3 , α 5-4 , α 5-5 , α 5-6 , α 5-7 , α 5-8 , α 5-9 are calculated;​​​​​​​​​​​​​​​​​​ S6.

7. Establish a comprehensive impact index ZH: ZH=β2·ΔX2+β3ΔX3+β4·ΔX4+β5·ΔX5+ND β2+β3+β4+β5＝1 Among them, β2, β3, β4, and β5 are the weights corresponding to the changes in traffic congestion length, traffic flow, average vehicle speed, and delay time in the comprehensive impact index, respectively. ND is the processing difficulty index, which is determined by technical personnel based on experience; The comprehensive impact index corresponding to the traffic abnormality events is calculated, and then arranged in order from large to small to obtain the order of urgency of handling the traffic abnormality events.

Images