Intelligent traffic management optimization method and device based on target detection and medium

Abstract

The invention discloses an intelligent traffic management optimization method and device based on target detection, and a medium, relates to the technical field of traffic management optimization, and solves the problems that a current transfer vehicle usually needs to be guided by a worker during driving, and the traffic flow condition in a transfer path cannot be mastered in real time. The method comprises the steps that the unmanned aerial vehicle group identifies a to-be-transferred vehicle after arriving at a predetermined waiting point; detecting a road congestion condition in a predetermined driving path corresponding to the to-be-transferred vehicle, and detecting to obtain a path congestion index of the predetermined driving path; analyzing the lighting duration of the traffic signal lamp in the predetermined driving path to obtain the passing condition of the to-be-transferred vehicle at the current signal intersection; according to the method, intelligent guidance of the to-be-transferred vehicle is realized through target detection of the unmanned aerial vehicle, and path adjustment of the to-be-transferred vehicle is realized based on a road congestion condition analysis result.

Description

Technical Field

[0001] The present invention belongs to the technical field of traffic management optimization, and specifically relates to an intelligent traffic management optimization method, device and medium based on target detection. Background Art

[0002] Intelligent traffic management is a comprehensive system that leverages advanced information perception, communication networks, and data analysis technologies to monitor and coordinate the real-time control of traffic elements such as roads, vehicles, and traffic lights, in order to improve traffic efficiency, ensure driving safety, and reduce environmental costs. Its core system involves collecting multi-source data such as traffic flow, vehicle speed, congestion, and accidents through video surveillance, sensors, and the Internet of Vehicles. It leverages big data analysis, artificial intelligence, and cloud platforms to dynamically optimize signal timing, route planning, and emergency dispatch. Furthermore, it provides real-time services such as diversion navigation, green wave control, and accident warnings to drivers or autonomous vehicles through visual interfaces and on-board terminals, achieving intelligent scheduling and closed-loop optimization management of traffic flows.

[0003] In existing technologies, when patients need to be transported by vehicle, staff are required to guide the vehicle, wasting manpower and resources. Furthermore, it is impossible to monitor the traffic flow along the transport route in real time. Furthermore, existing target vehicle guidance relies on manual guidance, and route planning relies on a command center using static maps. This makes it impossible to select appropriate roads based on real-time traffic conditions, and it is difficult to create green wave sections for target vehicles. To this end, the present invention proposes an intelligent traffic management optimization method, device and medium based on target detection. Summary of the Invention

[0004] In view of the shortcomings of the existing technology, the purpose of the present invention is to provide an intelligent traffic management optimization method, equipment and medium based on target detection.

[0005] The technical problems to be solved by the present invention are: How to efficiently use drones for target identification and path optimization.

[0006] In order to achieve the above object, the present invention adopts the following technical solutions: Intelligent traffic management optimization method based on target detection, including: Step S100: Acquire alarm information of the vehicle to be transferred, and the drone group arrives at the designated location according to the alarm information and identifies the vehicle to be transferred; Step S200: detecting the road congestion situation within the predetermined driving route of the vehicle to be transferred, and obtaining a path congestion index of the predetermined driving route; Step S300: analyzing the traffic lights in the predetermined driving route to obtain the passing status of the vehicle to be transferred at the current signal intersection; Step S400: Obtain intersection data of all signalized intersections, and construct green wave sections for vehicles to be transferred based on the intersection data.

[0007] Furthermore, the alarm information is the license plate information, vehicle color and vehicle coordinates of the vehicle to be transferred. The drone group includes a first drone and a second drone. The first drone is used to guide the vehicle to be transferred, and the second drone is used to determine the road congestion within the predetermined driving path of the vehicle to be transferred.

[0008] Furthermore, the step S100 includes the following sub-steps: Step S101, when the drone group receives the alarm information, the first drone obtains the vehicle coordinates of the vehicle to be transferred and simultaneously obtains the destination coordinates of all destinations in the city; Step S102: Calculate the straight-line distances between the destination coordinates of all destinations and the vehicle coordinates of the vehicle to be transferred, traverse the calculated results and arrange them in ascending order to obtain a path travel table between the destination coordinates and the vehicle coordinates, and use the first position in the path travel table as the predetermined travel path between the destination coordinates and the vehicle coordinates; Step S103: Obtain the flight speed interval of the drone group and the average speed of the vehicle to be transferred, and analyze to obtain the predetermined waiting point of the first drone; wherein the maximum endpoint value of the flight speed interval is the maximum flight speed of the drone group, and the minimum endpoint value is the minimum flight speed of the drone group; Step S104: When the drone group arrives at the predetermined waiting point, the first drone identifies the vehicle to be transferred; In step S105, the first UAV flies above the vehicle to be transferred, and at the same time, the second UAV flies in front of the vehicle to be transferred and maintains a fixed distance from the first UAV.

[0009] Furthermore, the analysis process of the predetermined waiting point is as follows: Step S1031: Draw a perpendicular line from the coordinates of the drone group to the predetermined driving path. The intersection of the perpendicular line and the predetermined driving path is used as the flight target point of the first drone. A flight target point of the second drone is set to the side of the corresponding flight target point of the first drone and in the direction of travel of the to-be-transferred vehicle. The flight target point of the second drone is separated from the flight target point of the first drone by a fixed distance. Step S1032: Obtain the straight-line distance between the drone group coordinates and the flight target point, divide the straight-line distance by the minimum flight speed of the first drone, calculate the maximum flight time of the first drone, add the maximum flight time to the delay time, and obtain the first required arrival time of the first drone; the delay time is the time required for the first drone to detect and identify the vehicle to be transferred; Step S1033: Obtain the vehicle coordinates of the vehicle to be transferred, calculate the path length between the vehicle to be transferred and the flight destination using the distance formula, and then divide the path length by the average speed to obtain the required vehicle arrival time required for the vehicle to be transferred to reach the flight destination. Step S1034, comparing the first required arrival time of the first UAV with the vehicle required arrival time of the vehicle to be transferred; If the first required arrival time is less than or equal to the vehicle's required arrival time, the flight target point is used as the scheduled waiting point for the first UAV; If the first demand arrival time is longer than the vehicle demand arrival time, proceed to the next step; Step S1035: Divide the straight-line distance by the maximum flight speed of the first UAV, and add the calculated result to the delay time to obtain the second required arrival time of the first UAV; Among them, the arrival time of the first demand is greater than the arrival time of the second demand, and the arrival time of the second demand is greater than zero; Step S1036: If the second required arrival time is less than or equal to the vehicle required arrival time, the flight target point is used as the predetermined waiting point for the first UAV; If the second demand arrival time is still longer than the vehicle demand arrival time, proceed to the next step; Step S1037: Use the original second drone as the first drone, and use the original first drone as the second drone; Step S1038: Acquire the original flight target point of the second UAV as the predetermined waiting point of the first UAV.

[0010] Furthermore, the process of identifying the vehicle to be transferred is as follows: Step S1041, obtaining a past road image of the predetermined driving route, identifying the vehicle frames of all vehicles in the past road image, and cropping the vehicles according to the vehicle frames to obtain a vehicle image in the past road image; Step S1042: Obtain the R value, G value, and B value of any pixel in the vehicle image, obtain the maximum value TZD and the minimum value among the R value, G value, and B value, subtract the maximum value from the minimum value to obtain the brightness of the corresponding pixel; Step S1043: when the maximum value among the R value, the G value, and the B value is zero, the saturation of the corresponding pixel is zero; when the maximum value among the R value, the G value, and the B value is not zero, the saturation of the pixel is calculated; Step S1044: if the brightness of the pixel is zero, the hue corresponding to the pixel is zero; If the brightness of the pixel is not equal to zero, the hue of the pixel is calculated; Step S1045: When the hue of the pixel point falls within the hue threshold range, the saturation is greater than or equal to the saturation threshold, and the brightness falls within the brightness threshold range, it is determined that the corresponding pixel point is the same color as the vehicle to be transferred, and the process proceeds to the next step; When the hue of a pixel does not fall within the hue threshold range, or the saturation is greater than or equal to the saturation threshold, or the brightness falls within the brightness threshold range, it is determined that the corresponding pixel is different from the vehicle color of the vehicle to be transferred, and no operation is performed; Step S1046: Repeat the above steps to determine whether all pixels in the vehicle image have the same color as the vehicle to be transferred, count the number of pixels that have the same color as the vehicle to be transferred, and simultaneously obtain the total number of pixels in the vehicle image. Divide the number of pixels that have the same color as the vehicle to be transferred to obtain the same ratio. If the same ratio is greater than or equal to the ratio threshold, the corresponding vehicle will be recorded as a suspected transfer vehicle and proceed to the next step; If the same ratio is less than the ratio threshold, it is determined that the vehicle color of the corresponding vehicle is different from the vehicle color of the vehicle to be transferred, and no operation is performed; Step S1047, obtaining the license plate information of the suspected transfer vehicle, and comparing the license plate information of the suspected transfer vehicle with the license plate information of the vehicle to be transferred; If the license plate information of the suspected transfer vehicle is identical to the license plate information of the vehicle to be transferred, the suspected transfer vehicle is determined to be the vehicle to be transferred. If the license plate information of the suspected transfer vehicle obtained through comparative detection is different from the license plate information of the vehicle to be transferred, the vehicle in the next passing road image will be detected.

[0011] Furthermore, the step S200 includes the following sub-steps: Step S201: The second drone takes pictures of a first driving direction image and a second driving direction image of a predetermined driving path at intervals of a preset duration. Step S202: Setting a maximum detection distance, detecting vehicles within the maximum detection distance in the first driving direction image using a target detection algorithm, obtaining vehicle images in the first driving direction image, and then obtaining images of all vehicles in the first driving direction image and their corresponding vehicle coordinates. Step S203, repeat the above steps to obtain the vehicle coordinates of all vehicles in the second driving direction image; Step S204, matching the vehicle images in the first driving direction image with the vehicle images in the second driving direction image one by one; Step S205: Calculate the travel distance of the corresponding vehicle within the preset shooting time using the Euclidean distance formula, and divide the travel distance by the preset shooting time to obtain the real-time speed of the corresponding vehicle; Step S206: Obtain the number of vehicles in the first driving direction image, the maximum speed of the predetermined driving path, and the real-time speeds of all vehicles. When the real-time speed of a vehicle is equal to the maximum speed of the predetermined driving path, the speed delay value of the corresponding vehicle is zero; when the real-time speed of a vehicle is less than the maximum speed of the predetermined driving path, calculate the speed delay value of the predetermined driving path. Step S207, obtaining the maximum detection distance and the number of vehicles, and calculating the vehicle density within the maximum detection distance; Step S208, calculating the path congestion index of the scheduled driving path; Step S209: When the path congestion index is less than or equal to the congestion index threshold, it is determined that the congestion situation of the scheduled driving path is not congested, and the process proceeds to step S300; In step S210, when the path congestion index is greater than the congestion index threshold, the congestion condition of the predetermined driving path is determined to be congested. The second UAV obtains the second position in the path driving table as the secondary driving path between the destination coordinates and the vehicle coordinates, and then repeats the above steps to obtain the secondary driving path corresponding to the minimum path congestion index. In step S211, the second UAV sends a route change instruction to the first UAV, and the first UAV guides the vehicle to be transferred to the secondary driving route and proceeds to the next step.

[0012] Furthermore, the step S300 includes the following sub-steps: Step S301, taking any time point after the vehicle to be transferred passes the current signal intersection as a monitoring time point; Step S302: At the monitoring time node, the second drone obtains the remaining distance between the vehicle to be transferred and the next signalized intersection, as well as the real-time speed of the vehicle to be transferred; the current signalized intersection is the signalized intersection that the vehicle to be transferred has already passed, and the next signalized intersection is the signalized intersection that the vehicle to be transferred is about to pass; Step S303: When the next signalized intersection turns green, the remaining green light duration is obtained, and then the remaining distance is divided by the remaining green light duration to obtain the required speed of the vehicle to be transferred to just pass the next signalized intersection; If the required speed is less than or equal to the real-time speed, the real-time speed of the vehicle to be transferred is determined to meet the speed requirement, and the process proceeds to the next step; If the required vehicle speed is greater than the real-time vehicle speed and less than or equal to the maximum speed of the predetermined driving path, the second UAV sends an acceleration signal to the first UAV, and then the first UAV sends an acceleration command to the vehicle to be transferred, so that the real-time speed of the vehicle to be transferred is accelerated to the maximum speed of the predetermined driving path, and then the process proceeds to the next step; Step S304: When the next signalized intersection turns red, obtain the remaining red light duration, divide the remaining distance by the real-time speed of the vehicle to be transferred, and obtain the travel time of the vehicle to be transferred when it reaches the next signalized intersection; Step S305: If the driving time is greater than or equal to the remaining time of the red light, it is determined that the real-time speed of the vehicle to be transferred meets the speed requirement, and no operation is performed; If the driving time is less than the remaining time of the red light, the remaining time of the red light at the next signalized intersection will be changed to the driving time; Step S306: Monitor the traffic lights corresponding to the adjacent signalized intersections adjacent to the next signalized intersection. If the vehicle to be transferred can pass through the adjacent signalized intersection at the real-time speed, continue monitoring until the vehicle to be transferred cannot pass through any signalized intersection at the maximum speed, and then enter step S400.

[0013] Furthermore, the intersection data includes the intersection coordinates of all signalized intersections and the green light start time nodes of the traffic lights corresponding to the travel directions of the vehicles to be transferred at the signalized intersections; The step S400 includes the following sub-steps: Step S401: number all signalized intersections. When the vehicle to be transferred is traveling at the maximum speed, the signalized intersection that cannot be passed is regarded as the first signalized intersection. Step S402, taking the first signalized intersection as a reference, calculating the intersection distances from all subsequent signalized intersections to the first signalized intersection; Step S403: Obtain the maximum speed of the vehicle to be transferred, and calculate the estimated travel time of the vehicle to be transferred from the first signalized intersection to any other signalized intersection at the maximum speed using a distance formula; Step S404: Obtain the current time node, add the estimated travel time to the current time node, and obtain the ideal green light time node at the corresponding signalized intersection when the vehicle to be transferred passes through any signalized intersection; Step S405: Obtain the green light start time node of the signalized intersection, subtract the ideal green light time node from the green light start time node, and obtain a duration deviation value; Step S406: If the duration deviation value is less than zero, it is determined that the green light start time node of the corresponding signalized intersection needs to be delayed; If the duration deviation value is greater than zero, it is determined that the green light start time node of the corresponding signal intersection needs to be advanced; If the duration deviation value is zero, the green light start time node of the corresponding signal intersection is determined to be normal, and no operation is performed; Step S407, adding the green light start time node of the corresponding signalized intersection to the duration deviation value to obtain the standard green light start time node; Step S408: Repeat the above steps to change the traffic lights at all signalized intersections to construct a green wave section.

[0014] The present invention further provides a computer device, comprising: a memory storing a computer program; A processor is communicatively connected to the memory, and when the computer program is executed by the processor, any one of the target detection-based intelligent traffic management optimization methods is implemented.

[0015] The present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any one of the target detection-based intelligent traffic management optimization methods.

[0016] Compared with the prior art, the present invention has the following beneficial effects: 1. The present invention first obtains the alarm information of the vehicle to be transferred. After the drone group arrives at the predetermined waiting point based on the alarm information, it identifies the vehicle to be transferred. The present invention realizes the accurate identification of the vehicle to be transferred; 2. The present invention uses the driving direction image to detect the road congestion situation within the predetermined driving path of the transfer vehicle, and combines the speed delay value and vehicle density detection to obtain the path congestion index of the predetermined driving path. The present invention realizes the early analysis of the congestion situation of the driving path of the transfer vehicle, so that the transfer vehicle can make timely adjustments; 2. The present invention determines whether the real-time speed of the vehicle to be transferred meets the speed requirement based on the relationship between the real-time speed and the required speed. If the real-time speed meets the speed requirement, the present invention analyzes the duration of traffic lights on the predetermined driving path to obtain the passing status of the vehicle to be transferred at the current signalized intersection. The present invention combines the duration of different traffic lights and the real-time speed of the vehicle to be transferred to achieve intelligent adjustment of the speed of the vehicle to be transferred, ensuring that the vehicle to be transferred can efficiently pass through different signalized intersections. 4. When the vehicle to be transferred cannot pass through any signal intersection at the maximum speed, the present invention obtains the intersection data of all signal intersections, and obtains the duration deviation value of the signal intersection based on the intersection data, and then adjusts the green light start time node corresponding to the signal intersection according to the duration deviation value, thereby constructing a green wave section for the vehicle to be transferred. The present invention adjusts the light-on duration of the signal intersection so that the vehicle to be transferred can reach the destination unimpeded and realize efficient transfer. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] To facilitate understanding by those skilled in the art, the present invention is further described below with reference to the accompanying drawings.

[0018] Figure 1 is a flow chart of the method of the present invention; Figure 2 This is an example diagram of the positions of the vehicle to be transported and the drone group in the present invention; Figure 3 Schematic diagram of the flight target point in the present invention; Figure 4 It is a structural diagram of the computer device in the present invention. DETAILED DESCRIPTION

[0019] The technical solutions of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0020] Example 1, please refer to Figure 1-Figure 3 As shown, the technical solution provided by the present invention is: an intelligent traffic management optimization method based on target detection, which is used to identify the vehicles to be transferred through a drone group and optimize the traffic flow for the vehicles to be transferred based on the road conditions. The method is as follows: Step S100: Acquire the alarm information of the vehicle to be transferred, and the drone group will identify the vehicle to be transferred after arriving at the predetermined waiting point based on the alarm information; The alarm information specifically includes the license plate information, vehicle color and vehicle coordinates of the vehicle to be transferred; Specifically, the drone group includes a first drone and a second drone, the first drone is used to guide the vehicle to be transferred, and the second drone is used to determine the road congestion within the predetermined driving path of the vehicle to be transferred; In this embodiment, step S100 includes the following sub-steps: Step S101, when the drone group receives the alarm information, the first drone obtains the vehicle coordinates of the vehicle to be transferred and simultaneously obtains the destination coordinates of all destinations in the city; In specific implementation, the destination is specifically the hospital; Step S102: Calculate the straight-line distances between the destination coordinates of all destinations and the vehicle coordinates of the vehicle to be transferred, traverse the calculated results and arrange them in ascending order to obtain a path travel table between the destination coordinates and the vehicle coordinates, and use the first position in the path travel table as the predetermined travel path between the destination coordinates and the vehicle coordinates; In specific implementation, the A-star algorithm can be used to construct a predetermined driving path between the transfer vehicle and the corresponding destination. The A-star algorithm is an existing technology for constructing a predetermined driving path. Step S103: Obtain the flight speed range of the drone group and the average speed of the vehicle to be transferred, and analyze to obtain the predetermined waiting point of the first drone; Among them, the maximum endpoint value of the flight speed range is the maximum flight speed of the drone group, and the minimum endpoint value is the minimum flight speed of the drone group; like Figure 3 As shown in the figure, the analysis process of the scheduled waiting point is as follows: Step S1031: Draw a perpendicular line from the coordinates of the drone group to the planned driving path. The intersection of the perpendicular line and the planned driving path is used as the flight target point of the first drone. The flight target point of the second drone is set to the side of the corresponding flight target point of the first drone and in the direction of travel of the vehicle to be transferred. The flight target point of the second UAV is spaced a fixed distance from the flight target point of the first UAV; Step S1032: Obtain the straight-line distance between the coordinates of the drone group and the flight target point, divide the straight-line distance by the minimum flight speed of the first drone, calculate the maximum flight time of the first drone, add the maximum flight time to the delay time, and obtain the first required arrival time of the first drone; The delay time specifically refers to the time required for the first drone to detect and identify the vehicle to be transferred; Step S1033: Obtain the vehicle coordinates of the vehicle to be transferred, calculate the path length between the vehicle to be transferred and the flight destination using the distance formula, and then divide the path length by the average speed to obtain the required vehicle arrival time required for the vehicle to be transferred to reach the flight destination. Step S1034, comparing the first required arrival time of the first UAV with the vehicle required arrival time of the vehicle to be transferred; If the first required arrival time is less than or equal to the vehicle's required arrival time, the flight target point is used as the scheduled waiting point for the first UAV; If the first demand arrival time is longer than the vehicle demand arrival time, proceed to step S1035; Step S1035: Divide the straight-line distance by the maximum flight speed of the first UAV, and add the calculated result to the delay time to obtain the second required arrival time of the first UAV; Among them, the arrival time of the first demand is greater than the arrival time of the second demand, and the arrival time of the second demand is greater than zero; Step S1036: If the second required arrival time is less than or equal to the vehicle required arrival time, the flight target point is used as the predetermined waiting point for the first UAV; If the second demand arrival time is still greater than the vehicle demand arrival time, proceed to step S1037; Step S1037: Use the original second drone as the first drone, and use the original first drone as the second drone; Step S1038: Obtain the original flight target point of the second UAV as the predetermined waiting point for the first UAV; Step S104: When the drone group arrives at the predetermined waiting point, the first drone identifies the vehicle to be transferred. The identification process is as follows: Step S1041: Obtain a past road image of the predetermined driving route, identify the vehicle bounding boxes of all vehicles in the past road image using a target detection algorithm, and crop the vehicles based on the vehicle bounding boxes to obtain a vehicle image in the past road image; Among them, the target detection algorithm for detecting the vehicle border in the image is an existing technology. The target detection algorithm includes YOLOv5-Nano and YOLOX-Tiny. In this embodiment, YOLOX-Tiny is preferably used as the target recognition algorithm. YOLOX-Tiny is suitable for detecting the vehicle border in the image; Specifically, a camera deployed on the first UAV is used to obtain images of the passing road, with the shooting direction being specifically the direction of the vehicle to be transferred along the predetermined driving path; Step S1042: Obtain the R value, G value, and B value of any pixel in the vehicle image, obtain the maximum value TZD and the minimum value among the R value, G value, and B value, subtract the maximum value from the minimum value to obtain the brightness XMD of the corresponding pixel; Among them, brightness is specifically the brightness of the RGB value of the pixel relative to black; In step S1043, when the maximum value among the R value, the G value, and the B value is zero, the saturation of the corresponding pixel is zero; when the maximum value among the R value, the G value, and the B value is not zero, the saturation of the pixel BHD is calculated using the formula, which is as follows: BHD=XMD / TZD; Step S1044: if the brightness of the pixel is zero, the hue corresponding to the pixel is zero; If the lightness of the pixel is not equal to zero, the hue TSX of the pixel is calculated using the formula. The formula is as follows: TSX=60°×(GB) / XMD, TZD=R; TSX=60°×(BR) / XMD+120°, TZD=G; TSX=60°×(RG) / XMD+240°, TZD=B; Step S1045: When the hue of the pixel point falls within the hue threshold range, the saturation is greater than or equal to the saturation threshold, and the brightness falls within the brightness threshold range, it is determined that the corresponding pixel point is the same color as the vehicle to be transferred, and the process proceeds to step S1046; When the hue of a pixel does not fall within the hue threshold range, or the saturation is less than the saturation threshold, or the brightness does not fall within the brightness threshold range, it is determined that the corresponding pixel is different from the vehicle color of the vehicle to be transferred, and no operation is performed; Among them, the corresponding hue threshold interval, saturation threshold interval and brightness threshold interval are obtained according to the vehicle color of the vehicle to be transferred; Step S1046, repeating steps S1041 to S1045, determining whether all pixels in the vehicle image have the same color as the vehicle to be transferred, counting the number of pixels that have the same color as the vehicle to be transferred, and obtaining the total number of pixels in the vehicle image, dividing the number of pixels that have the same color as the vehicle to be transferred to obtain the same ratio; If the same ratio is greater than or equal to the ratio threshold, the corresponding vehicle is recorded as a suspected transfer vehicle and the process proceeds to step S1047; If the same ratio is less than the ratio threshold, it is determined that the vehicle color of the corresponding vehicle is different from the vehicle color of the vehicle to be transferred, and no operation is performed; Step S1047: obtaining the license plate information of the suspected transfer vehicle through a license plate detection and recognition algorithm, and comparing the license plate information of the suspected transfer vehicle with the license plate information of the vehicle to be transferred; If the license plate information of the suspected transfer vehicle is identical to the license plate information of the vehicle to be transferred, the suspected transfer vehicle is determined to be the vehicle to be transferred. If the license plate information of the suspected transfer vehicle is different from the license plate information of the vehicle to be transferred, the vehicle in the next passing road image corresponding to the predetermined driving path is detected; Among them, the license plate detection and recognition algorithms include the EasyOCR algorithm, the HyperLPR algorithm, and the MMOCR algorithm, which are existing technologies. At the same time, the reason for detecting the vehicle in the next past road image is that the current past road image of the planned driving route does not contain the vehicle to be transferred, so it is necessary to detect other past road images of the planned driving route; In step S105, the first drone flies above the vehicle to be transferred, and at the same time, the second drone flies in front of the vehicle to be transferred and maintains a fixed distance from the first drone.

[0021] In step S200, the second drone detects the road congestion situation within the predetermined driving path corresponding to the transfer vehicle using the driving direction image, and obtains the path congestion index of the predetermined driving path by combining the speed delay value and the vehicle density detection; In this embodiment, step S200 includes the following sub-steps: Step S201: The second drone takes pictures of a first driving direction image and a second driving direction image of a predetermined driving path at intervals of a preset duration. wherein, a first driving direction image and a second driving direction image of the predetermined driving path are captured by a camera deployed on the second UAV, wherein the capturing direction is specifically the direction of the destination of the predetermined driving path; Specifically, the first driving direction image is an image of the predetermined driving path taken by the second UAV at a first shooting time node; the second driving direction image is an image of the predetermined driving path taken by the second UAV at a second shooting time node; and a preset shooting time length is set between the second shooting time node and the first shooting time node. In specific implementation, the preset shooting time can be 0.5 seconds; Step S202: Setting a maximum detection distance, detecting vehicles within the maximum detection distance in the first driving direction image using a target detection algorithm, and obtaining images of all vehicles in the first driving direction image and corresponding vehicle coordinates; Step S203, repeating steps S201 to S202 to obtain the vehicle coordinates of all vehicles in the second driving direction image; Step S204, matching the vehicle images in the first driving direction image with the vehicle images in the second driving direction image one by one; Step S205: Calculate the travel distance of the corresponding vehicle within the preset shooting time using the Euclidean distance formula, and divide the travel distance by the preset shooting time to obtain the real-time speed of the corresponding vehicle; Actually, in this embodiment, the unit of all vehicle speeds is meter per second; Step S206: Obtain the number of vehicles CSL in the first driving direction image, the maximum speed DCS of the predetermined driving path, and the real-time speeds SCSi of all vehicles, where i is the vehicle number in the first driving direction image, i=1, 2, ..., n, and n is the maximum value of the vehicle number. When the real-time speed of a vehicle is equal to the maximum speed of the predetermined driving path, the speed delay value of the corresponding vehicle is zero; when the real-time speed of a vehicle is less than the maximum speed of the predetermined driving path, the speed delay value SYL of the predetermined driving path is calculated using the formula, which is as follows: ; It should be specifically noted that, since the preset shooting time is short, the number of vehicles in the first driving direction image and the second driving direction image is the same within the preset shooting time; Step S207: Obtain the maximum detection distance ZDJ and the number of vehicles n, and calculate the vehicle density CLM within the maximum detection distance using the formula. The formula is as follows: CLM=n / ZDJ; Step S208: Calculate the path congestion index YDZ of the scheduled driving path using the following formula: YDZ=w1×(SYL / BSYL)+w2×(CLM / BCLM), where w1 and w2 are fixed weight coefficients, BSYL is the standard value corresponding to the speed delay value, and BCLM is the standard value corresponding to the vehicle density. In specific implementation, BSYL=1, BCLM=1, w1=0.6, and w2=0.4; Step S209: When the path congestion index is less than or equal to the congestion index threshold, it is determined that the congestion situation of the scheduled driving path is not congested, and the process proceeds to step S300; In step S210, when the path congestion index is greater than the congestion index threshold, the congestion condition of the predetermined driving path is determined to be congested. The second UAV uses the second position in the path driving table as the secondary driving path between the destination coordinates and the vehicle coordinates, and then repeats steps S201 to S208 to obtain the secondary driving path corresponding to the minimum path congestion index. It should be specifically noted that, in the subsequent methods, the secondary driving paths are referred to as predetermined driving paths; In step S211, the second UAV sends a route change instruction to the first UAV, and the first UAV guides the vehicle to be transferred to the secondary driving route and enters step S300.

[0022] Step S300: Based on the relationship between the real-time speed and the required speed, it is determined whether the real-time speed of the vehicle to be transferred meets the speed requirement. If the real-time speed meets the speed requirement, the second drone analyzes the duration of the traffic lights in the predetermined driving path to obtain the passing status of the vehicle to be transferred at the current signalized intersection. In this embodiment, step S300 includes the following sub-steps: Step S301, taking any time point after the vehicle to be transferred passes the current signal intersection as a monitoring time point; Step S302: The second UAV obtains the remaining distance between the vehicle to be transferred and the next signalized intersection, as well as the real-time speed of the vehicle to be transferred, at the monitoring time node. The current signalized intersection is the signalized intersection that the vehicle to be transferred has passed, and the next signalized intersection is the signalized intersection that the vehicle to be transferred is about to pass; Step S303: When the next signalized intersection turns green, the remaining green light duration is obtained, and then the remaining distance is divided by the remaining green light duration to obtain the required speed of the vehicle to be transferred to just pass the next signalized intersection; If the required speed is less than or equal to the real-time speed, it is determined that the real-time speed of the vehicle to be transferred meets the speed requirement, and the process proceeds to step S304; If the required speed is greater than the real-time speed and less than or equal to the maximum speed of the predetermined driving path, the second UAV sends an acceleration signal to the first UAV, and then the first UAV sends an acceleration command to the transfer vehicle to accelerate the real-time speed of the transfer vehicle to the maximum speed of the predetermined driving path, and then enters step S304; The purpose of accelerating the real-time speed of the vehicle to be transferred to the maximum speed of the predetermined driving route is to ensure that the vehicle to be transferred can pass through the corresponding intersection 100% of the time and to ensure that the vehicle to be transferred can reach the destination earlier. In practice, the real-time speed can be increased to a value between the required speed and the maximum speed. The first drone sends a corresponding instruction to the vehicle to be transferred through the loudspeaker. Step S304: When the next signalized intersection turns red, obtain the remaining red light duration, divide the remaining distance by the real-time speed of the vehicle to be transferred, and obtain the travel time of the vehicle to be transferred when it reaches the next signalized intersection; Step S305: If the driving time is greater than or equal to the remaining time of the red light, it is determined that the real-time speed of the vehicle to be transferred meets the speed requirement, and no operation is performed; If the driving time is less than the remaining time of the red light, the remaining time of the red light at the next signalized intersection will be changed to the driving time; In specific implementation, when the traffic light is yellow, the yellow light will be recorded as red; Step S306, monitor the traffic lights corresponding to the adjacent signal intersections adjacent to the next signal intersection. If the vehicle to be transferred can pass through the adjacent signal intersection at the real-time speed, continue to monitor the passage of the vehicle to be transferred through the signal intersection until the vehicle to be transferred cannot pass through any signal intersection at the maximum speed, and then enter step S400.

[0023] Step S400: obtaining a duration deviation value of a signalized intersection based on the intersection data, and adjusting the green light start time node corresponding to the signalized intersection according to the duration deviation value, thereby constructing a green wave section for the vehicle to be transferred; The intersection data specifically includes the intersection coordinates of all signalized intersections and the green light start time node of the traffic light corresponding to the direction of the vehicle to be transferred at the signalized intersection; In this embodiment, step S400 includes the following sub-steps: Step S401: number all signalized intersections. When the vehicle to be transferred is traveling at the maximum speed, the signalized intersection that cannot be passed is regarded as the first signalized intersection. Step S402, taking the first signalized intersection as a reference, calculating the intersection distances between all signalized intersections and the first signalized intersection; Step S403: Obtain the maximum speed of the vehicle to be transferred, and calculate the estimated travel time of the vehicle to be transferred from the first signalized intersection to any other signalized intersection at the maximum speed using the distance formula between two points; Step S404: Obtain the current time node, add the estimated travel time to the current time node, and obtain the ideal green light time node at the corresponding signalized intersection when the vehicle to be transferred passes through any signalized intersection; Step S405: Obtain the green light start time node of the signalized intersection, subtract the ideal green light time node from the green light start time node, and obtain a duration deviation value; The green light start time node of the signalized intersection is specifically a time node adjacent to the ideal green light time node and earlier than the ideal green light time node; Step S406: If the duration deviation value is less than zero, it is determined that the green light start time node of the corresponding signalized intersection needs to be delayed; If the duration deviation value is greater than zero, it is determined that the green light start time node of the corresponding signal intersection needs to be advanced; If the duration deviation value is zero, the green light start time node of the corresponding signal intersection is determined to be normal, and no operation is performed; Step S407, adding the green light start time node of the corresponding signalized intersection to the duration deviation value to obtain the standard green light start time node; Step S408, repeating steps S401 to S407, changing the traffic lights at all signalized intersections, and constructing a green wave section.

[0024] Example 2: This embodiment of the present invention further provides a computer device for running the intelligent traffic management optimization method based on target detection; see Figure 4 The structure diagram of a computer device provided by an embodiment of the present invention is shown, wherein the computer device includes a memory and a processor, wherein the memory is used to store one or more computer instructions, and the one or more computer instructions are executed by the processor to implement the above-mentioned intelligent traffic management optimization method based on target detection; Further, Figure 4 The computer device shown further includes a system bus and a communication interface, and the processor, the communication interface and the memory are connected via the communication bus; Among them, the memory may include high-speed random access memory (RAM), and may also include non-volatile memory (non-volatile memory), such as at least one disk storage. The communication connection between the system network element and at least one other network element is realized through at least one communication interface (which can be wired or wireless), and the Internet, wide area network, local area network, metropolitan area network, etc. can be used. The system bus can be an ISA bus, PCI bus or EISA bus, etc. The system bus can be divided into an address bus, a data bus, a control bus, etc. For the convenience of representation, Figure 4 Only one bidirectional arrow is used, but it does not mean that there is only one communication bus or one type of system bus; The processor may be an integrated circuit chip with signal processing capabilities. During implementation, the steps of the above-mentioned method may be completed by hardware integrated logic circuits within the processor or by software instructions. The above-mentioned processor may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. The methods, steps, and logic block diagrams disclosed in the embodiments of the present invention may be implemented or executed. The general-purpose processor may be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of the present invention may be directly executed by a hardware decoding processor or by a combination of hardware and software modules within the decoding processor. The software modules may be located in storage media well-known in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other such storage media. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the method of the above embodiment in combination with its hardware.

[0025] In Example 3, an embodiment of the present invention further provides a computer storage medium storing computer-executable instructions. When the computer-executable instructions are called and executed by a processor, the computer-executable instructions cause the processor to implement the above-mentioned intelligent traffic management optimization method based on target detection. For specific implementation, please refer to the method embodiment and will not be repeated here. The computer program product of the target detection-based intelligent traffic management optimization method provided in the embodiment of the present invention includes a computer storage medium storing program code. The instructions included in the program code can be used to execute the method in the previous method embodiment. The specific implementation can be found in the method embodiment and will not be repeated here.

[0026] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working process of the system and / or device described above can refer to the corresponding process in the aforementioned method embodiment and will not be repeated here.

[0027] In addition, in the description of the embodiments of the present invention, unless otherwise expressly specified or limited, the terms "mounted," "connected," and "connected" should be understood in a broad sense. For example, they may refer to fixed connections, detachable connections, or integral connections; they may refer to mechanical connections or electrical connections; they may refer to direct connections or indirect connections through an intermediate medium; and they may refer to internal communication between two components. Those skilled in the art will understand the specific meanings of the above terms in the present invention based on the specific circumstances.

[0028] If the functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage media include various media capable of storing program code, such as USB flash drives, mobile hard drives, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical disks.

[0029] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. An intelligent traffic management optimization method based on target detection, characterized in that: Methods include: Step S100: Acquire the alarm information of the vehicle to be transferred, and the drone group will identify the vehicle to be transferred after arriving at the predetermined waiting point based on the alarm information; Step S200: detecting the road congestion situation within the predetermined driving path corresponding to the transfer vehicle using the driving direction image, and obtaining the path congestion index of the predetermined driving path by combining the speed delay value and the vehicle density detection; Step S300: Determine whether the real-time speed of the vehicle to be transferred meets the speed requirement based on the relationship between the real-time speed and the required speed. If the real-time speed meets the speed requirement, analyze the duration of traffic lights on the planned driving path to determine the passing status of the vehicle to be transferred at the current signalized intersection. Step S400: Obtain the duration deviation value of the signalized intersection based on the intersection data, and adjust the green light start time node corresponding to the signalized intersection according to the duration deviation value, thereby constructing a green wave section for the vehicle to be transferred.

2. The intelligent traffic management optimization method based on target detection according to claim 1 is characterized in that: The alarm information includes the license plate information, vehicle color and vehicle coordinates of the vehicle to be transferred. The drone group includes a first drone and a second drone. The first drone is used to guide the vehicle to be transferred, and the second drone is used to determine the road congestion within the predetermined driving path of the vehicle to be transferred.

3. The intelligent traffic management optimization method based on target detection according to claim 2 is characterized in that: The step S100 includes the following sub-steps: Step S101, when the drone group receives the alarm information, the first drone obtains the vehicle coordinates of the vehicle to be transferred and simultaneously obtains the destination coordinates of all destinations in the city; Step S102: Calculate the straight-line distances between the destination coordinates of all destinations and the vehicle coordinates of the vehicle to be transferred, traverse the calculated results and arrange them in ascending order to obtain a path travel table between the destination coordinates and the vehicle coordinates, and use the first position in the path travel table as the predetermined travel path between the destination coordinates and the vehicle coordinates; Step S103: Obtain the flight speed interval of the drone group and the average speed of the vehicle to be transferred, and analyze to obtain the predetermined waiting point of the first drone; wherein the maximum endpoint value of the flight speed interval is the maximum flight speed of the drone group, and the minimum endpoint value is the minimum flight speed of the drone group; Step S104: When the drone group arrives at the predetermined waiting point, the first drone identifies the vehicle to be transferred; In step S105, the first drone flies above the vehicle to be transferred, and at the same time, the second drone flies in front of the vehicle to be transferred and maintains a fixed distance from the first drone.

4. The intelligent traffic management optimization method based on target detection according to claim 3 is characterized in that: The analysis process of the predetermined waiting point is as follows: Step S1031: Draw a perpendicular line from the coordinates of the drone group to the predetermined driving path. The intersection of the perpendicular line and the predetermined driving path is used as the flight target point of the first drone. A flight target point of the second drone is set to the side of the corresponding flight target point of the first drone and in the direction of travel of the to-be-transferred vehicle. The flight target point of the second drone is separated from the flight target point of the first drone by a fixed distance. Step S1032: Obtain the straight-line distance between the drone group coordinates and the flight target point, divide the straight-line distance by the minimum flight speed of the first drone, calculate the maximum flight time of the first drone, add the maximum flight time to the delay time, and obtain the first required arrival time of the first drone; the delay time is the time required for the first drone to detect and identify the vehicle to be transferred; Step S1033: Obtain the vehicle coordinates of the vehicle to be transferred, calculate the path length between the vehicle to be transferred and the flight destination using the distance formula, and then divide the path length by the average speed to obtain the required vehicle arrival time required for the vehicle to be transferred to reach the flight destination. Step S1034, comparing the first required arrival time of the first UAV with the vehicle required arrival time of the vehicle to be transferred; If the first required arrival time is less than or equal to the vehicle's required arrival time, the flight target point is used as the scheduled waiting point for the first UAV; If the first demand arrival time is longer than the vehicle demand arrival time, proceed to step S1035; Step S1035: Divide the straight-line distance by the maximum flight speed of the first UAV, and add the calculated result to the delay time to obtain the second required arrival time of the first UAV; Among them, the arrival time of the first demand is greater than the arrival time of the second demand, and the arrival time of the second demand is greater than zero; Step S1036: If the second required arrival time is less than or equal to the vehicle required arrival time, the flight target point is used as the predetermined waiting point for the first UAV; If the second demand arrival time is still greater than the vehicle demand arrival time, proceed to step S1037; Step S1037: Use the original second drone as the first drone, and use the original first drone as the second drone; Step S1038: Acquire the original flight target point of the second UAV as the predetermined waiting point of the first UAV.

5. The intelligent traffic management optimization method based on target detection according to claim 3 is characterized in that: The specific process of identifying the vehicle to be transferred is as follows: Step S1041, obtaining a past road image of the predetermined driving route, identifying the vehicle frames of all vehicles in the past road image, and cropping the vehicles according to the vehicle frames to obtain a vehicle image in the past road image; Step S1042: Obtain the R value, G value, and B value of any pixel in the vehicle image, obtain the maximum value TZD and the minimum value among the R value, G value, and B value, subtract the maximum value from the minimum value to obtain the brightness of the corresponding pixel; Step S1043: when the maximum value among the R value, the G value, and the B value is zero, the saturation of the corresponding pixel is zero; when the maximum value among the R value, the G value, and the B value is not zero, the saturation of the pixel is calculated; Step S1044: if the brightness of the pixel is zero, the hue corresponding to the pixel is zero; If the brightness of the pixel is not equal to zero, the hue of the pixel is calculated; Step S1045: When the hue of the pixel point falls within the hue threshold range, the saturation is greater than or equal to the saturation threshold, and the brightness falls within the brightness threshold range, it is determined that the corresponding pixel point is the same color as the vehicle to be transferred, and the process proceeds to step S1046; When the hue of a pixel does not fall within the hue threshold range, or the saturation is less than the saturation threshold, or the brightness does not fall within the brightness threshold range, it is determined that the corresponding pixel is different from the vehicle color of the vehicle to be transferred, and no operation is performed; Step S1046, repeating steps S1041 to S1045, determining whether all pixels in the vehicle image have the same color as the vehicle to be transferred, counting the number of pixels that have the same color as the vehicle to be transferred, and obtaining the total number of pixels in the vehicle image, dividing the number of pixels that have the same color as the vehicle to be transferred to obtain the same ratio; If the same ratio is greater than or equal to the ratio threshold, the corresponding vehicle is recorded as a suspected transfer vehicle and the process proceeds to step S1047; If the same ratio is less than the ratio threshold, it is determined that the vehicle color of the corresponding vehicle is different from the vehicle color of the vehicle to be transferred, and no operation is performed; Step S1047, obtaining the license plate information of the suspected transfer vehicle, and comparing the license plate information of the suspected transfer vehicle with the license plate information of the vehicle to be transferred; If the license plate information of the suspected transfer vehicle is identical to the license plate information of the vehicle to be transferred, the suspected transfer vehicle is determined to be the vehicle to be transferred. If the license plate information of the suspected transfer vehicle obtained through comparison detection is different from the license plate information of the vehicle to be transferred, the vehicle in the next passing road image corresponding to the predetermined driving path is detected.

6. The target detection-based intelligent traffic management optimization method according to claim 3 is characterized in that: The step S200 includes the following sub-steps: Step S201: The second drone takes pictures of a first driving direction image and a second driving direction image of a predetermined driving path at intervals of a preset duration. Step S202: Setting a maximum detection distance, detecting vehicles within the maximum detection distance in the first driving direction image using a target detection algorithm, and obtaining images of all vehicles in the first driving direction image and corresponding vehicle coordinates; Step S203, repeating steps S201 to S202 to obtain the vehicle coordinates of all vehicles in the second driving direction image; Step S204, matching the vehicle images in the first driving direction image with the vehicle images in the second driving direction image one by one; Step S205: Calculate the travel distance of the corresponding vehicle within the preset shooting time using the Euclidean distance formula, and divide the travel distance by the preset shooting time to obtain the real-time speed of the corresponding vehicle; Step S206: Obtain the number of vehicles in the first driving direction image, the maximum speed of the predetermined driving path, and the real-time speeds of all vehicles. When the real-time speed of a vehicle is equal to the maximum speed of the predetermined driving path, the speed delay value of the corresponding vehicle is zero; when the real-time speed of a vehicle is less than the maximum speed of the predetermined driving path, calculate the speed delay value of the predetermined driving path. Step S207, obtaining the maximum detection distance and the number of vehicles, and calculating the vehicle density within the maximum detection distance; Step S208, calculating the path congestion index of the scheduled driving path; Step S209: When the path congestion index is less than or equal to the congestion index threshold, it is determined that the congestion situation of the scheduled driving path is not congested, and the process proceeds to step S300; In step S210, when the path congestion index is greater than the congestion index threshold, the congestion condition of the predetermined driving path is determined to be congested. The second UAV uses the second position in the path driving table as the secondary driving path between the destination coordinates and the vehicle coordinates, and then repeats steps S201 to S208 to obtain the secondary driving path corresponding to the minimum path congestion index. In step S211, the second UAV sends a route change instruction to the first UAV, and the first UAV guides the vehicle to be transferred to the secondary driving route and enters step S300.

7. The intelligent traffic management optimization method based on target detection according to claim 6 is characterized in that: The step S300 includes the following sub-steps: Step S301, taking any time point after the vehicle to be transferred passes the current signal intersection as a monitoring time point; Step S302: At the monitoring time node, the second drone obtains the remaining distance between the vehicle to be transferred and the next signalized intersection, as well as the real-time speed of the vehicle to be transferred; the current signalized intersection is the signalized intersection that the vehicle to be transferred has already passed, and the next signalized intersection is the signalized intersection that the vehicle to be transferred is about to pass; Step S303: When the next signalized intersection turns green, the remaining green light duration is obtained, and then the remaining distance is divided by the remaining green light duration to obtain the required speed of the vehicle to be transferred to just pass the next signalized intersection; If the required speed is less than or equal to the real-time speed, it is determined that the real-time speed of the vehicle to be transferred meets the speed requirement, and the process proceeds to step S304; If the required speed is greater than the real-time speed and less than or equal to the maximum speed of the predetermined driving path, the second UAV sends an acceleration signal to the first UAV, and then the first UAV sends an acceleration command to the transfer vehicle to accelerate the real-time speed of the transfer vehicle to the maximum speed of the predetermined driving path, and then enters step S304; Step S304: When the next signalized intersection turns red, obtain the remaining red light duration, divide the remaining distance by the real-time speed of the vehicle to be transferred, and obtain the travel time of the vehicle to be transferred when it reaches the next signalized intersection; Step S305: If the driving time is greater than or equal to the remaining time of the red light, it is determined that the real-time speed of the vehicle to be transferred meets the speed requirement, and no operation is performed; If the driving time is less than the remaining time of the red light, the remaining time of the red light at the next signalized intersection will be changed to the driving time; Step S306, monitor the traffic lights corresponding to the adjacent signal intersections adjacent to the next signal intersection. If the vehicle to be transferred passes through the adjacent signal intersection at the real-time speed, continue to monitor the passage of the vehicle to be transferred through the signal intersection until the vehicle to be transferred cannot pass through any signal intersection at the maximum speed, and then enter step S400.

8. The target detection-based intelligent traffic management optimization method according to claim 7 is characterized in that: The intersection data includes the intersection coordinates of all signalized intersections and the green light start time node of the traffic light corresponding to the direction of the vehicle to be transferred at the signalized intersection; The step S400 includes the following sub-steps: Step S401: number all signalized intersections. When the vehicle to be transferred is traveling at the maximum speed, the signalized intersection that cannot be passed is regarded as the first signalized intersection. Step S402, taking the first signalized intersection as a reference, calculating the intersection distances between all signalized intersections and the first signalized intersection; Step S403, obtaining the maximum speed of the vehicle to be transferred, and calculating the estimated travel time of the vehicle to be transferred from the first signalized intersection to any signalized intersection at the maximum speed; Step S404: Obtain the current time node, add the estimated travel time to the current time node, and obtain the ideal green light time node at the corresponding signalized intersection when the vehicle to be transferred passes through any signalized intersection; Step S405: Obtain the green light start time node of the signalized intersection, subtract the ideal green light time node from the green light start time node, and obtain a duration deviation value; Step S406: If the duration deviation value is less than zero, it is determined that the green light start time node of the corresponding signalized intersection needs to be delayed; If the duration deviation value is greater than zero, it is determined that the green light start time node of the corresponding signal intersection needs to be advanced; If the duration deviation value is zero, the green light start time node of the corresponding signal intersection is determined to be normal, and no operation is performed; Step S407, adding the green light start time node of the corresponding signalized intersection to the duration deviation value to obtain the standard green light start time node; Step S408, repeating steps S401 to S407, changing the traffic lights at all signalized intersections, and constructing a green wave section.

9. A computer device, characterized in that: The computer device comprises: a memory storing a computer program; A processor is communicatively connected to the memory, and when the computer program is executed by the processor, the method according to any one of claims 1 to 8 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 8 is implemented.

Images