Traffic jam monitoring method and device for cruising of four-axis unmanned aerial vehicle and storage medium

Abstract

According to the traffic jam monitoring method and device for cruising of the four-axis unmanned aerial vehicle and the storage medium, the four-axis unmanned aerial vehicle is provided with a high-definition camera, a sensor and other devices, and the cruising track and the cruising period which conform to traffic track operation are set for the four-axis unmanned aerial vehicle based on the fixed point and automatic cruising functions of the four-axis unmanned aerial vehicle. A road section vehicle target is obtained through real-time video returning and an image recognition technology target tracking algorithm, the vehicle advancing track and speed are accurately tracked and analyzed, whether the road section is in a congestion state or not is analyzed, and intelligent traffic monitoring of multiple different road section point positions can be achieved. The problems that an original video probe and an original sensor can only monitor a fixed range and are prone to missing detection and false detection are solved, flexible and accurate monitoring on a traffic road section is achieved, traffic jam signals are efficiently transmitted back in real time, and a traffic control department is assisted in studying and judging traffic operation conditions and scientifically conducting traffic dispersion work.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned aerial vehicles, and in particular to a traffic congestion monitoring method, equipment and storage medium for a four-axis unmanned aerial vehicle cruise. Background Art

[0002] With the development of social economy and the advancement of science and technology, my country's urbanization process is accelerating, and the challenges faced by urban traffic are becoming increasingly severe. The current intelligent traffic monitoring methods mainly rely on the deployment of cameras and sensors on the road, and with the development of image recognition technology, traffic detection technology based on video images has achieved certain results, but its limitations are becoming increasingly prominent in the face of increasingly complex traffic conditions. Fixed monitoring has limited coverage and inflexible monitoring scope. Since fixed traffic monitoring data is derived from front-end cameras and sensors, only sections where cameras and sensors have been built can be monitored. On sections where the corresponding front-end equipment is not installed or where the equipment installation density is low, it is difficult to obtain corresponding traffic data. At the same time, traffic road management often faces the cycle of equipment addition and maintenance replacement. During this stage, the lack of monitoring and perception data will directly lead to the inability to obtain traffic monitoring data in some areas, resulting in a window period for supervision. It is difficult to achieve corresponding coordination and scheduling. The monitoring cost is high. The current traffic road monitoring system based on image processing, the installation density and total number of cameras and sensors determine the accuracy and reliability of traffic data. If you want to increase the value of traffic monitoring data, you must increase the number of front-end cameras and sensor points. Installing cameras in each lane will inevitably increase the cost of supervision and the difficulty of maintenance. Summary of the invention

[0003] The present invention proposes a traffic congestion monitoring method, device and storage medium for a quad-axis unmanned aerial vehicle cruise, which can at least solve one of the technical problems in the background technology.

[0004] To achieve the above object, the present invention adopts the following technical solutions: A traffic congestion monitoring method for a quadcopter drone cruise includes the following steps: Flying camera equipped with: A remote camera device is installed on the UAV, the dynamic camera is controlled to be parallel to the road, and the orthographic projection of the road in the road section is obtained.

[0005] Cruise trajectory planning: Obtain the urban road trajectory and the corresponding road speed limit data, plan the quadcopter's cruise nodes and edges (lines), and take the road centerline as the cruise path. Determine whether it is a traffic signal controlled intersection, classify the road type according to the road speed limit standard, and set the corresponding action direction and speed limit.

[0006] Cruise cycle setting: The daily traffic monitoring cruise cycle is set according to the length of the monitored road section, the monitoring time point, and the performance parameters of the quadcopter drone, such as the maximum cruising speed and the maximum cruising time. The cruise frequency is increased according to the traffic peak conditions on weekdays and holidays, such as during the morning rush hour from 7 to 9 o'clock on weekdays and the evening rush hour from 7 to 19 o'clock.

[0007] Quadcopter drone video input: Drone real-time streaming uses RTMP protocol, RTSP protocol, or GB / T28181 protocol. Therefore, a streaming media service that can receive RTMP, RTSP, and GB / T28181 is required. The streaming media service can be deployed in an Internet computer room or cloud host with a fixed IP, or in a local network within the drone flight area.

[0008] Frame extraction optimization module: The direction and speed of the drone, the speed limit of the road and other factors will cause the relative speed between the vehicle and the drone to change. Different frame extraction frequencies are divided according to the relative speed range.

[0009] Multi-target tracking module: Using a multi-target tracking algorithm, multiple car targets in the video are detected and assigned IDs for trajectory tracking without knowing the number of targets in advance. Different targets have different IDs, and the tracking target is determined based on the ID.

[0010] Speed ​​calculation module: According to the frame extraction and target tracking results, the vehicle position difference between the previous and next frames is compared, and the speed of the tracked target vehicle is calculated according to the flight direction and speed of the drone. The speed calculation within 200m near the intersection controlled by traffic signals is excluded.

[0011] Traffic congestion classification model: Design road congestion classification indicators, calculate the overall operating speed of the traffic road in the section according to the speed of multiple target vehicles in the non-traffic signal-controlled intersection section, and determine the traffic congestion classification of the cruising section at this time.

[0012] Traffic congestion warning information push: Real-time push of traffic congestion monitoring data, based on the five-level congestion classification, push 0 represents unimpeded traffic, push 1 represents basically unimpeded traffic, push 2 represents light congestion, push 3 represents moderate congestion, and push 4 represents severe congestion.

[0013] On the other hand, the present invention further discloses a computer-readable storage medium storing a computer program, wherein when the computer program is executed by a processor, the processor executes the steps of the above method.

[0014] On the other hand, the present invention further discloses a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the above method.

[0015] It can be seen from the above technical scheme that the purpose of the present invention is to provide a traffic monitoring system based on quadcopter drone cruising and its implementation method. Quadcopter drones have the advantages of flexible mobility, high autonomy, and high cost performance. On the basis of the high cost performance of quadcopter drones, setting reasonable cruising routes and cycles for them can improve the utilization rate of quadcopter drones, and large-scale traffic monitoring can be achieved with less equipment, greatly reducing the cost of traffic monitoring.

[0016] By equipping the quadcopter with high-definition cameras and sensors and other equipment, and based on the quadcopter's fixed-point and automatic cruising functions, the cruise trajectory and cruise cycle that conform to the traffic track operation can be set for it. Through real-time video feedback, combined with the image recognition technology target tracking algorithm to obtain the vehicle target on the road section, accurate tracking and analysis of the vehicle's trajectory and speed can be achieved, and whether the road section is in a congested state can be analyzed, so as to realize intelligent traffic monitoring of multiple different road sections. It solves the problems that the original video probes and sensors can only monitor a fixed range and are prone to missed detection and false detection, and realizes flexible and accurate monitoring of traffic sections, real-time and efficient return of traffic congestion signals, assisting traffic management departments in analyzing and judging traffic operation conditions, and scientifically conducting traffic diversion work.

[0017] Specifically, the present invention utilizes drones to transmit road traffic video, monitors the driving status of road vehicles based on target tracking, designs five-level indicators for traffic congestion, and realizes the push of traffic monitoring information.

[0018] 1) By using drones to reduce the cost of traffic congestion monitoring, the scope of traffic monitoring can be expanded to sections of roads where cameras and sensors are not installed, thus achieving flexible and efficient traffic congestion signal transmission.

[0019] 2) By optimizing frame extraction, the efficiency of frame extraction in different travel directions and on roads with different speed limits is improved, thereby improving the accuracy of traffic congestion monitoring and reducing the call for feature matching in the tracking stage, thereby reducing computing pressure. 3) Through comprehensive analysis of road vehicle operation conditions based on multi-target tracking and corresponding five-level traffic congestion indicators, it provides traffic management departments with clearer, more comprehensive and accurate traffic congestion conditions, helping them to achieve smart traffic congestion control. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 It is a flowchart of the present invention; Figure 2 Schematic diagram of multi-target tracking of the present invention. DETAILED DESCRIPTION

[0021] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments.

[0022] In order to solve the above problems, realize intelligent traffic analysis, timely discover congested sections, and assist traffic management departments in achieving traffic diversion. The embodiment of the present invention discloses a traffic congestion monitoring method based on quadcopter drone cruising, comprising the following steps: Flying camera equipped with: ① Install a remote camera device on the drone, control the dynamic camera to be parallel to the road, and obtain the orthographic projection of the road in the section.

[0023] ② Through the attitude analysis of the quadcopter, the quadcopter attitude adjustment algorithm is implemented to enhance the stability of the quadcopter video acquisition.

[0024] Cruise trajectory planning: Obtain the urban road trajectory and the corresponding road speed limit data, plan the quadcopter's cruise nodes and edges (lines), and take the road centerline as the cruise path. Determine whether it is a traffic signal controlled intersection, classify the road type according to the road speed limit standard, and set the corresponding action direction and speed limit.

[0025] Cruise cycle setting: The daily traffic monitoring cruise cycle is set according to the length of the monitored road section, the monitoring time point, and the performance parameters of the quadcopter drone, such as the maximum cruising speed and the maximum cruising time. The cruise frequency is increased according to the traffic peak conditions on weekdays and holidays, such as during the morning rush hour from 7 to 9 o'clock on weekdays and the evening rush hour from 7 to 19 o'clock.

[0026] Quadcopter drone video input: Drone real-time streaming uses RTMP protocol, RTSP protocol, or GB / T28181 protocol. Therefore, a streaming media service that can receive RTMP, RTSP, and GB / T28181 is required. The streaming media service can be deployed in an Internet computer room or cloud host with a fixed IP, or in a local network within the drone flight area.

[0027] Frame extraction optimization module: ① When optimizing the default frame rate control method for drone video shooting, the direction of the road needs to be marked. When the directions of travel on both sides of the road are different, it is necessary to mark which side is the same direction and which side is the opposite direction.

[0028] ② When the direction of the vehicle on the monitored road is the same as that of the drone, since the vehicle and the drone are moving in the same direction, the relative movement speed is relatively slow, so a lower frame extraction frequency is used. After the frame extraction is completed, the frame extraction images are input into the same direction respectively. ③ When the direction of the vehicle on the monitored road is the same as that of the drone, the vehicle and the drone move in opposite directions, making the moving speed relatively fast, so a higher frame extraction frequency is used. After the frame extraction is completed, the frame extraction images are input to the reverse direction respectively.

[0029] ④ When the target returned by the target detection result includes vehicles moving forward and backward at the same time, a higher frame extraction frequency is used. After the frame extraction is completed, the frame extraction image is input into the same direction / reverse two major target detection modules respectively. Among them, when input into the same direction target tracking module, appropriate frame loss processing is performed according to certain rules; ⑤ Control the frame rate according to the forward and reverse results output by the target tracking module to achieve frame extraction optimization.

[0030] Multi-target tracking module: Figure 2 As shown; ① Target detection: Use the target detection algorithm to identify the current frame, track one or more vehicles as tracking targets, and locate the bounding box positions of multiple target vehicles through the monitoring model.

[0031] ② Feature extraction: Calculate visual features such as color, boundary, and shape for each detected vehicle in the current frame of the video. Use deep learning-based feature extraction and hybrid feature extraction to distinguish multiple target vehicles.

[0032] ③ Similarity calculation: Calculate the matching degree between the previous frame and multiple targets in the current frame, extract the target features of the vehicle to be tracked for similarity calculation and comparison. When the similarity is greater than the set threshold, the target is tracked successfully; when the similarity is less than the threshold, the tracked target is lost; ④ Data association: Based on the similarity data, the trajectory data of multiple tracking targets are obtained. Using the trajectory data of the tracking target, the trajectory route of the target vehicle is retrieved in the video structured data.

[0033] Speed ​​calculation module: ① Eliminate target data whose endpoint of the action trajectory is within 200m of the traffic signal-controlled intersection.

[0034] ② The same-direction and reverse-direction vehicles are respectively tracked by the multi-target tracking module to obtain the vehicle trajectory information, and the front-to-back running distance S (m) of the two needles of the vehicle is calculated in combination with the geographic feature information.

[0035] ③ The time interval between the two frames before and after the frame rate is T (s), and the vehicle running speed between the previous and next frames is calculated as V (km / h) = S*1000 / (T*3600).

[0036] ④ According to the target tracking results, the running speeds of one to n successfully tracked target vehicles on the same road section are calculated to form a set {V 1 , V 2 , V 3 , ... V n}.

[0037] Traffic congestion classification model: ① Obtain a set of speed data of multiple target vehicles at a certain time and on a certain road section through speed calculation. Considering the abnormal situation of traffic vehicles, it is necessary to eliminate the speed values ​​with large deviations.

[0038] ② Set the speed limit v' of the road section, mark the average speed difference of the moving vehicles as S', and successfully track n target vehicles. According to the normal traffic speed, the reasonable threshold of the variance is S'^2=100*n / (n-1), which is calculated by floating 10km / h above and below the speed limit.

[0039] ③ Calculate the speed V of vehicles in the same direction on this road section {V 1 , V 2 , V 3 , ... V n The average value V 平 , then the variance of the V value of the multi-target vehicle travel data at this moment is ^2=∑ (V n -V 平 ) / (n-1).

[0040] ④ When When S'^2≤S'^2, it is considered that the driving conditions of multiple vehicles in the same driving direction are relatively consistent and no abnormal driving conditions occur. At this time, the comprehensive driving speed v=V 平 ⑤ When When ^2>S'^2, it is considered that the current collection of driving speed data of multiple vehicles in the same direction has a large deviation or abnormal data, so the maximum value V in the speed data set is eliminated. max and minimum value V min Then calculate the average value V 平 , comprehensive travel speed v=V 平 .

[0041] ⑥ Design five-level classification standard indicators, the speed limit of the cruising section is v': Smooth: Traffic conditions are good, there is basically no road congestion, and you can drive according to the road speed limit standard, that is, the corresponding standard is that the comprehensive travel speed is 1 times the road speed limit, and the comprehensive travel speed v=v'; Basically smooth: traffic conditions are good, and it takes 0.2 to 0.5 times longer than when it is smooth. The corresponding standard is that the comprehensive speed is (0.67, 0.83] times the road speed limit, 0.67v' <v≤0.83v'; Mild congestion: Traffic conditions are poor, and it takes 0.5 to 0.8 times longer than when the traffic is smooth. The corresponding standard is that the comprehensive speed is (0.56, 0.67] times the road speed limit, 0.56v' <v≤0.67v'; Moderate congestion: Traffic conditions are poor, and it takes 0.8 to 1.1 times longer than when the traffic is smooth. The corresponding travel standard is a comprehensive speed of (0.48, 0.56] times the road speed limit, 0.48v' <v≤0.56v'; Severe congestion: Traffic conditions are very poor, and the travel time is 1.1 times or more longer than when traffic is unblocked. The corresponding comprehensive travel speed is less than or equal to 0.48 times the road speed limit, and the comprehensive travel speed v≤0.48v'.

[0042] Traffic congestion warning information push: Real-time push of traffic congestion monitoring data. According to the five-level congestion classification, push 0 represents unobstructed traffic, push 1 represents basically unobstructed traffic, push 2 represents light congestion, push 3 represents moderate congestion, and push 4 represents severe congestion.

[0043] In summary, the present invention has the following specific features: (1) Based on the vehicle speed calculation and congestion monitoring model of multi-target tracking, a five-level assessment of road traffic congestion can be achieved, which can more accurately assess the traffic congestion situation on the road section.

[0044] (2) Optimize the frame extraction method, calculate the difference between the speed limit of different roads and the speed in the direction of the UAV's flight, change the frame extraction efficiency, improve the frame extraction efficiency, and reduce the occupation of computing resources.

[0045] On the other hand, the present invention further discloses a computer-readable storage medium storing a computer program, wherein when the computer program is executed by a processor, the processor executes the steps of the above method.

[0046] On the other hand, the present invention further discloses a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the above method.

[0047] In another embodiment provided in the present application, a computer program product comprising instructions is also provided, which, when executed on a computer, enables the computer to execute any of the traffic congestion monitoring methods for quadcopter cruise in the above-mentioned embodiments.

[0048] It is understandable that the system, device and storage medium provided in the embodiments of the present invention correspond to the method provided in the embodiments of the present invention, and the explanation, examples and beneficial effects of the relevant contents can refer to the corresponding parts in the above methods.

[0049] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from a website site, a computer, a server or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or a data center that includes one or more available media integrated. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive Solid State Disk (SSD)), etc.

[0050] It should be noted that, in this article, relational terms such as first and second, etc. are only used 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.

[0051] Each embodiment in this specification is described in a related manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0052] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A traffic congestion monitoring method for a quadcopter drone cruise, characterized in that: The following steps are included: Install a remote camera device on the drone, control the dynamic camera to be parallel to the road, and obtain the road orthographic projection in the road section; Obtain the urban road trajectory and the corresponding road section speed limit data, plan the quadcopter's cruise nodes and edges or lines, and take the road centerline as the cruise path; Determine whether it is a traffic signal controlled intersection, classify the road type according to the road speed limit standard, and set the corresponding direction of action and speed limit; According to the monitoring section length, monitoring time point, and the performance parameters of the quadcopter UAV's maximum cruising speed and maximum cruising time, the daily traffic monitoring cruise cycle is set; Get the video of the quadcopter drone; divide the frame extraction frequencies into different ranges according to the relative speed; Using a multi-target tracking algorithm, multiple car targets in the video are detected and assigned IDs for trajectory tracking without knowing the number of targets in advance; According to the frame extraction and target tracking results, the vehicle position difference between the previous and next frames is compared, and the speed of the tracked target vehicle is calculated according to the flight direction and speed of the drone; Design road congestion classification indicators, calculate the overall operating speed of the traffic road in the section according to the speed of multiple target vehicles in the non-traffic signal-controlled intersection section, and determine the traffic congestion classification of the cruising section at this time.

2. The traffic congestion monitoring method for quadcopter drone cruising according to claim 1 is characterized by: It also includes real-time push of traffic congestion monitoring data. According to the five-level congestion classification, push 0 represents unobstructed traffic, push 1 represents basically unobstructed traffic, push 2 represents light congestion, push 3 represents moderate congestion, and push 4 represents severe congestion.

3. The traffic congestion monitoring method for quadcopter cruise according to claim 1 is characterized in that: By setting up a streaming media service that can receive RTMP, RTSP, and GB / T28181, the streaming media service is deployed in an Internet computer room with a fixed IP, a cloud host, or in a local network within the drone flight area to obtain quadcopter drone videos.

4. The traffic congestion monitoring method for quadcopter drone cruising according to claim 1 is characterized by: According to the relative speed range, different frame extraction frequencies are divided, including The default frame rate control method is optimized for drone video, and the direction of the road is marked. When the directions of the two sides of the road are different, mark which side is the same direction and which side is the opposite direction; When the direction of the vehicle on the monitored road is the same as that of the UAV, since the vehicle and the UAV are moving in the same direction, the relative movement speed is relatively slow, and a lower frame extraction frequency is used; after the frame extraction is completed, the frame extraction images are input into the same direction respectively; When the direction of the vehicle on the monitored road is the same as that of the drone, since the vehicle and the drone are moving in opposite directions at this time, the moving speed is relatively fast, and a higher frame extraction frequency is used; after the frame extraction is completed, the frame extraction images are input to the opposite direction respectively; When the target returned by the target detection result includes vehicles moving forward and backward in both directions, a higher frame extraction frequency is used. After the frame extraction is completed, the frame extraction image is input into the same-direction / reverse target detection modules respectively. Among them, when input into the same-direction target tracking module, frame dropping processing is performed according to the set rules. The frame rate is controlled according to the forward and reverse results output by the target tracking module to achieve frame extraction optimization.

5. The traffic congestion monitoring method for quadcopter drone cruising according to claim 1 is characterized by: Using a multi-target tracking algorithm, multiple car targets in the video are detected and assigned IDs for trajectory tracking without knowing the number of targets in advance. Specifically, Target detection: Use the target detection algorithm to identify the current frame, track one or more vehicles as tracking targets, and locate the bounding box positions of multiple target vehicles through the monitoring model; Feature extraction: Calculate different visual features for each detected vehicle in the current frame of the video, and use deep learning-based feature extraction and hybrid feature extraction to distinguish multiple target vehicles; Similarity calculation: Calculate the matching degree between the previous frame and multiple targets in the current frame, extract the target features of the vehicle to be tracked for similarity calculation and comparison. When the similarity is greater than the set threshold, the target tracking is successful; When the similarity is less than the threshold, the tracking target is lost; Data association: Based on the similarity data, the trajectory data of multiple tracking targets are obtained. Using the trajectory data of the tracking targets, the trajectory route of the target vehicle is retrieved in the video structured data.

6. The traffic congestion monitoring method for quadcopter drone cruising according to claim 1 is characterized by: According to the frame extraction and target tracking results, the vehicle position difference between the previous and next frames is compared, and the speed of the tracked target vehicle is calculated according to the flight direction and speed of the drone, including: Eliminate target data whose endpoint of the action trajectory is within 200m of the traffic signal-controlled intersection; The same-direction and reverse-direction vehicles are respectively tracked by the multi-target tracking module to obtain the vehicle trajectory information, and the front-to-back running distance S (m) of the two needles of the vehicle is calculated in combination with the geographical feature information; The time interval between the two frames before and after the frame rate is T (s), and the vehicle running speed between the previous and next frames is calculated as V (km / h) = S*1000 / (T*3600); According to the target tracking results, the running speeds of one to n successfully tracked target vehicles on the same road section are calculated to form a set of vehicles with the same speed V in the same direction on a certain road section at a certain time {V1, V2, V3, ... V n }.

7. The traffic congestion monitoring method for quadcopter drone cruising according to claim 1 is characterized by: Design road congestion classification indicators include: Through speed calculation, multiple target vehicle speed sets of a certain road section at a certain time are obtained; considering the abnormal situation of traffic vehicles, the speed values ​​with large deviations need to be eliminated; Set the speed limit v' of the road section, the average speed difference of the moving vehicles is marked as S', n target vehicles are successfully tracked, and the variance reasonable threshold is S'^2=100*n / (n-1) according to the normal traffic speed fluctuation of 10km / h above and below the speed limit; Calculate the speed V set {V1, V2, V3, ... V n The average value V 平 , then the variance of the V value of the multi-target vehicle travel data at this moment is ^2=∑ (V n -V 平 ) / (n-1); when When S^2≤S'^2, it is considered that the driving conditions of multiple vehicles in the same driving direction are relatively consistent and no abnormal driving conditions occur. At this time, the comprehensive driving speed v=V 平 when When ^2>S'^2, it is considered that the current collection of driving speed data of multiple vehicles in the same direction has a large deviation or abnormal data, so the maximum value V in the speed data set is eliminated. max and minimum value V min Then calculate the average value V 平 , comprehensive travel speed v=V 平 ; Design a five-level classification standard index, the speed limit of the cruising section is v': Smooth: Traffic conditions are good, there is basically no road congestion, and you can drive according to the road speed limit standard, that is, the corresponding standard is that the comprehensive travel speed is 1 times the road speed limit, and the comprehensive travel speed v=v'; Basically smooth: traffic conditions are good, and it takes 0.2 to 0.5 times longer than when it is smooth. The corresponding standard is that the comprehensive speed is (0.67, 0.83] times the road speed limit, 0.67v' <v≤0.83v'; Mild congestion: Traffic conditions are poor, and it takes 0.5 to 0.8 times longer than when the traffic is smooth. The corresponding standard is that the comprehensive speed is (0.56, 0.67] times the road speed limit, 0.56v' <v≤0.67v'; Moderate congestion: Traffic conditions are poor, and it takes 0.8 to 1.1 times longer than when the traffic is smooth. The corresponding travel standard is a comprehensive speed of (0.48, 0.56] times the road speed limit, 0.48v' <v≤0.56v'; Severe congestion: The traffic condition is very bad, and it takes 1.1 times or more time than when it is unblocked. The corresponding comprehensive travel speed is less than or equal to 0.48 times the road speed limit, and the comprehensive travel speed v≤0.48v'; Traffic congestion warning information push: real-time push of traffic congestion monitoring data, according to the five-level congestion classification, push 0 represents smooth traffic, push 1 represents basically smooth traffic, push 2 represents light congestion, push 3 represents moderate congestion, push 4 represents severe congestion.

8. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the processor is caused to perform the steps of the method according to any one of claims 1 to 6.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the computer program is executed by the processor, the processor is caused to perform the steps of the method according to any one of claims 1 to 6.

Images