An Internet of Things-based intelligent traffic diversion control method and system

Abstract

The present invention relates to the technical field of traffic diversion control. Specifically, it relates to an intelligent traffic diversion control method and system based on the Internet of Things. The control steps for the drone to project the diversion line are calculated in advance and stored in the drone control terminal. Combining with the industry standards for road condition management, the diversion response status of the main road and the confluence lane is formulated, and the diversion response status is reflected by the vehicle flow influence characteristic value. The present invention monitors the vehicle flow density and vehicle flow speed of different lanes in real time to obtain the vehicle flow status of different lanes. At the same time, it identifies the position of the advance lane diversion line to obtain the adjustment direction of the diversion line, and uses the drone with pre-formulated control steps to project the diversion line. Taking the vehicle flow status as the response basis, the diversion line is adjusted in real time through the drone to change the state of the diversion line to adapt to the vehicle flow status of different lanes, making full use of the diversion function of the diversion line in different states and reducing the vehicle flow pressure on the lane.

Description

Technical Field

[0001] The present invention relates to the technical field of traffic diversion control, and specifically, to an intelligent traffic diversion control method and system based on the Internet of Things. Background Art

[0002] Traffic diversion is an important means in traffic management. By using physical facilities or technical means to guide vehicles to drive along a preset route, road safety and traffic efficiency can be improved. Its core lies in reducing traffic conflicts by regulating vehicle behavior, and it is applicable to scenarios such as complex intersections and highway ramps.

[0003] Traffic diversion mainly takes the form of white V-shaped lines or diagonal line areas (i.e., diversion lines), which force vehicles to drive along a fixed path and prohibit pressing the line, crossing the line, or parking. For example, at intersections or overpass ramps, the diversion lines clearly demarcate lanes through geometric design to prevent vehicles from changing lanes or parking randomly.

[0004] Traditional diversion lines are built during road planning, that is, their corresponding positions and shapes are determined at the initial design stage. Although designers design based on lane distribution and traffic flow prediction, due to subsequent urban development and changes in lane matching types, such as the establishment of commercial buildings and the merger or closure with other lanes, the traffic flow of the current lane changes, making the current diversion lines unable to adapt to the corresponding traffic flow. At the same time, large-scale traffic flow generally occurs during peak hours, that is, during commuting hours. Under normal conditions, due to low traffic flow, the corresponding diversion lines can handle the operation of regular traffic flow. If the diversion lines are modified, they can only adapt to the traffic flow state in a single time period and cannot be flexibly planned to adapt to the traffic flow guidance work at different time periods.

[0005] To solve the above problems, there is an urgent need for an intelligent traffic diversion control method that can adjust the diversion lines in real time. Summary of the Invention

[0006] The purpose of the present invention is to provide an intelligent traffic diversion control method and system based on the Internet of Things to solve the problems raised in the above background art.

[0007] To achieve the above purpose, one of the purposes of the present invention is to provide an intelligent traffic diversion control method based on the Internet of Things, including the following steps:

[0008] Step1. Set up camera monitoring devices in the confluence lane area, collect the traffic flow influence characteristics of the main road and the confluence lane, and reflect the traffic flow states of different lanes through the traffic flow influence characteristics;

[0009] Step2. Prematurely calculate the control steps of the drone projection diversion lines and store them in the drone control terminal;

[0010] Step 3. Establish a network channel between the drone and the camera monitoring device through the Internet of Things to share traffic flow monitoring data;

[0011] Step 4. Combine the industry standards of road condition management to formulate the diversion response status of the main road and the confluence lane, and the diversion response status is reflected by the traffic flow impact characteristic values;

[0012] Step 5. According to the camera monitoring device, update the traffic flow impact characteristic values of different lanes in real time, compare the reflected traffic flow status with the diversion response status, and share the feedback results to the drone control terminal;

[0013] When the traffic flow status of the main road conforms to the diversion response status, the current position of the diversion line remains unchanged;

[0014] When the traffic flow status of the main road does not conform to the diversion response status, the traffic flow status of the confluence lane is determined;

[0015] When the traffic flow status of the confluence lane does not conform to the diversion response status, the current position of the diversion line remains unchanged;

[0016] When the traffic flow status of the confluence lane conforms to the diversion response status, the drone responds and starts, projects the diversion line according to the pre-calculated control steps, and re-divides the diversion area between the main road and the confluence lane;

[0017] Step 6. Obtain the traffic flow guiding status of the projected diversion line and perform real-time data storage.

[0018] As a further improvement of this technical solution, the traffic flow impact characteristics in Step 1 include traffic flow density and traffic flow speed.

[0019] As a further improvement of this technical solution, the calculation method of the traffic flow density in Step 1 includes the following steps:

[0020] Step 1.1. According to the pitch angle and height of the camera, calculate the actual coverage length of the virtual coil. The virtual coil includes a first coil and a second coil, where the first coil is used for triggering detection and the second coil is used for counting. The specific algorithm is as follows:

[0021] ;

[0022] Among them, is the actual physical length of the virtual coil on the ground, is the pixel width of the virtual coil in the image, is the installation height of the camera, is the focal length of the camera, is the pitch angle of the camera;

[0023] Step 1.2: After completing the positioning of the virtual coil, capture the vehicle passing through the video screen, track the trajectory of the vehicle in the lane through particle positioning, and obtain the center of mass coordinates of the vehicle in the connected domain. ,in , ,and is the total number of valid pixels in the connected domain, is the coordinate of the i-th pixel in the connected domain;

[0024] Step 1.3, combine the Kalman filter to predict the center of mass position of the vehicle. When the center of mass passes through the first coil for three consecutive frames and disappears in the second coil, the vehicle flow count is increased by 1. By setting the time window to accumulate the number of triggers, the vehicle volume / hour is output.

[0025] As a further improvement of the technical solution, the vehicle flow speed in Step 1 adopts a double virtual coil speed measurement method, and the specific algorithm is as follows:

[0026] ;

[0027] is the speed of vehicles passing in the lane, is the frame rate of the camera, as well as are the frame numbers of the vehicles passing through the first and second coils respectively. By setting a time window, the average speed of the passing vehicles in the lane within the time window is calculated.

[0028] As a further improvement of the technical solution, the method for calculating the control step of the UAV projection guide line in Step 2 includes the following steps:

[0029] Step 2.1. Scan the ground at a specific frequency using the laser radar on the drone to obtain the original guide line position of the current lane.

[0030] Step 2.2: The drone establishes a spatial rectangular coordinate system with the initial point as the origin, obtains the endpoint coordinates of each original guide line, and generates point cloud data ;

[0031] Step 2.3, obtain the associated lanes with the merging lane in the main road, where the associated lane is the lane closest to the merging lane;

[0032] Step 2.4, obtain the endpoint coordinates of the associated lane guide line, and adjust the drone position based on the endpoint coordinates.

[0033] As a further improvement of the technical solution, the method for adjusting the position of the drone based on the endpoint coordinates in Step 2.4 includes the following steps:

[0034] Step2.4.1. Calculate the area of the vacant position of the guiding line of the associated lane in combination with the spatial coordinates of the end points of the diversion line segment;

[0035] Step2.4.2. Control the drone to fly vertically upward from the ground so that the projection image coincides with the vacant position, and complete the position adjustment on the z-axis;

[0036] Step2.4.3. Control the drone to move along the y-axis so that the side of the projection graph coincides with the guiding line, and complete the position adjustment on the y-axis;

[0037] Step2.4.4. Control the drone to move along the x-axis so that each end point of the projection image coincides with each end point of the vacant position respectively, and the projection graph completely fills the vacant position;

[0038] Step2.4.5. Record the distances of the three adjustments, the adjustment sequence, and the final projection points of the drone as the control steps for the projection guiding line of the drone.

[0039] As a further improvement of this technical solution, the method for formulating the guiding response state of the main road and the confluence lane in Step4 includes the following steps:

[0040] Step4.1. Obtain the traffic flow load ranges of the main road and the confluence lane;

[0041] Step4.2. The traffic flow load range is fed back through the traffic flow density and the traffic flow speed, and the lane saturation algorithm is adopted. The algorithm formula is as follows:

[0042] ;

[0043] Among them, is the maximum traffic flow, is the average speed of vehicles driving on the lane, is the safe distance between vehicles, which is related to the average speed and is the vehicle speed length, n is the number of lanes, and the maximum traffic flow is the guiding response state.

[0044] The second object of the present invention is to provide a system for implementing an intelligent traffic guiding control method based on the Internet of Things, including a monitoring device control system, a drone control system, a guiding response state comparison module, and a projection result acquisition module;

[0045] Among them, the monitoring device control system monitors and processes the main road and the confluence lane, and real-time collects the traffic flow influence characteristics on each lane, where the traffic flow influence characteristics include traffic flow density and traffic flow speed;

[0046] The UAV control system is used to regulate the UAV to project the guide line. Data sharing between the UAV control system and the monitoring device control system is carried out through a data sharing channel built by the Internet of Things. The monitoring device control system feeds back the traffic flow influence characteristics to the UAV control system in real time;

[0047] The UAV control system includes an original guide line acquisition module, a projected guide line simulation module, and a simulation step recording module;

[0048] Among them, the original guide line acquisition module is used to collect the original guide lines of each lane, locate the position of the original guide line in combination with the initial position of the UAV, and locate the corresponding vacant positions;

[0049] The projected guide line simulation module projects the projection pattern to the vacant position by adjusting the position of the UAV;

[0050] The simulation step recording module is used to collect the projection steps;

[0051] The guide line response state comparison module compares the collected lane guide line response states in combination with the feedback information of real-time monitoring, as the feedback for responding to the start of UAV control;

[0052] The projection result acquisition module combines the monitoring device to collect the lane guide line information after the guide line is projected.

[0053] Compared with the prior art, the beneficial effects of the present invention:

[0054] In the intelligent traffic guide line control method and system based on the Internet of Things, by monitoring the traffic flow density and traffic flow speed of different lanes in real time, the traffic flow states of different lanes are obtained. At the same time, by identifying the position of the advance lane guide line in advance, the adjustment direction of the guide line is obtained, and the UAV with pre-determined control steps is used to project the guide line. Taking the traffic flow state as the response basis, the guide line is adjusted in real time through the UAV, changing the state of the guide line to adapt to the traffic flow states of different lanes, making full use of the guiding function of the guide line in different states, and reducing the traffic flow pressure on the lane. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 It is the overall method step diagram of the present invention;

[0056] Figure 2 It is the method step diagram of the calculation method of the traffic flow density of the present invention;

[0057] Figure 3 It is the method step diagram of the control step of calculating the projection guide line of the UAV of the present invention;

[0058] Figure 4 The first schematic diagram of the drone projection simulation of the present invention;

[0059] Figure 5 The second schematic diagram of the drone projection simulation of the present invention;

[0060] Figure 6 The method step diagram for adjusting the position of the drone based on the endpoint coordinates of the present invention;

[0061] Figure 7 The method step diagram for formulating the diversion response state of the main road and the confluence lane of the present invention;

[0062] Figure 8 The overall system flow block diagram of the present invention. Detailed implementation manners

[0063] Next, in combination with the accompanying drawings in the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0064] Please refer to Figure 1 As shown, one of the purposes of the present invention is to provide an intelligent traffic diversion control method based on the Internet of Things, including the following steps:

[0065] Step1. Set up camera monitoring devices in the confluence lane area, collect the traffic flow influence characteristics of the main road and the confluence lane, and reflect the traffic flow states of different lanes through the traffic flow influence characteristics;

[0066] Step2. Prematurely calculate the control steps of the drone projection diversion line and store them in the drone control terminal;

[0067] Step3. Build a network channel between the drone and the camera monitoring device through the Internet of Things to share the traffic flow monitoring data;

[0068] Step4. Combine the road condition management industry standards to formulate the diversion response state of the main road and the confluence lane, and the diversion response state is reflected by the traffic flow influence characteristic values;

[0069] Step5. According to the camera monitoring device, update the traffic flow influence characteristic values of different lanes in real time, compare the reflected traffic flow state with the diversion response state, and share the feedback result to the drone control terminal;

[0070] When the traffic flow state of the main road conforms to the diversion response state, the current diversion line position remains unchanged;

[0071] When the traffic flow state of the main road does not conform to the diversion response state, the traffic flow state of the merging lane is determined;

[0072] When the traffic flow state of the merging lane does not conform to the diversion response state, the current position of the diversion line remains unchanged;

[0073] When the traffic flow state of the merging lane conforms to the diversion response state, the drone responds and starts to project the diversion line according to the pre-calculated control steps, and re-divides the diversion area between the main road and the merging lane;

[0074] Step6. Obtain the traffic flow guiding state of the projected diversion line and perform real-time data storage.

[0075] The specific content is as follows:

[0076] For the planning work of the diversion line, it is necessary to predict in combination with the traffic flow state of the current lane as the basis for responding to the diversion line adjustment. Therefore, it is quite crucial to determine the traffic flow in advance. In this solution, camera monitoring devices are installed in the merging lane area, and the camera monitoring devices collect the traffic flow influence characteristics of the main road and the merging lane. The traffic flow influence characteristics include traffic flow density and traffic flow speed. These two influence characteristics are the key to determining the traffic flow. For the traffic flow density, the virtual coil trigger method is used for calculation, and the corresponding calculation method is as follows:

[0077] As shown by Figure 2 , first, according to the pitch angle and height of the camera, calculate the actual coverage length of the virtual coil, that is, generate two virtual coils for vehicle monitoring in the video image, including the first coil and the second coil. The first coil is used for trigger detection, and the second coil is used for counting. The specific algorithm is as follows:

[0078] ;

[0079] Among them, is the actual physical length of the virtual coil on the ground, is the pixel width of the virtual coil in the image, is the installation height of the camera, is the focal length of the camera, is the pitch angle of the camera. After completing the positioning of the virtual coil, capture the vehicles passing through the video image, and track the trajectories of the vehicles in the lane through particle positioning, that is, obtain the centroid coordinates of the vehicles in the connected domain , where , , and is the total number of effective pixels in the connected domain, is the coordinate of the i-th pixel in the connected domain. When the vehicle (centroid coordinate) enters the virtual coil, the traffic flow count is triggered. Combining with the Kalman filter to predict the vehicle centroid position, when the centroid continuously passes through the first coil for three frames and disappears within the second coil, the traffic flow count is incremented by 1. By setting a time window (usually 5 minutes) to accumulate the trigger times, the vehicle volume per hour is output;

[0080] At the same time, it is also an important basis for whether the lane is congested for the traffic flow speed. In this solution, to ensure data consistency and improve detection efficiency, the dual virtual coil speed measurement method is synchronously used to detect the speed of vehicles passing through the lane. The specific detection method is as follows:

[0081] The same algorithm as calculating the traffic flow above is used to detect the speed through the division of the dual virtual coils, where:

[0082] ;

[0083] is the speed of the vehicle passing through the lane, is the frame rate of the camera, and are the frame numbers when the vehicle passes through the first and second coils respectively. By setting a time window (consistent with the traffic flow detection method), the average vehicle speed of the vehicles passing through the lane within the time window is calculated as the speed measurement result for the current time period for subsequent response determination.

[0084] After completing the real-time detection of the traffic flow density and traffic flow speed, real-time determination is required to predict whether the main road and the confluence main road are congested, as the basis for responding to the start of the drone for diversion line intervention. To ensure that the drone can accurately complete the division of the diversion line, it is necessary to pre-calculate the control steps of the drone projection diversion line and store them in the drone control terminal. As shown by Figure 3 The specific steps are as follows:

[0085] First, use the lidar carried on the drone to scan the ground at a specific frequency (usually 10Hz) to obtain the original diversion line position of the current lane and generate point cloud data , obtain the endpoint coordinates of each original diversion line. As shown by Figure 4 , the drone establishes a space rectangular coordinate system with the initial point as the origin, where the initial point is the drone docking position and also the power supply position. In the actual detection process, the drone is equipped with a solar power supply device and is charged through solar power generation in the docking area to maintain its usage endurance. During the diversion line positioning process, the drone captures the endpoint coordinates of the diversion line. As shown by Figure 4 , where the initial point coordinates are , the main road includes four lanes, namely Lane ①, Lane ②, Lane ③, and Lane ④, which are divided by three guide lines Ⅰ, Ⅱ, and Ⅲ. And Lane ④ is connected to the confluence lane. Since Lane ④ is directly connected to the confluence lane, it has the greatest impact on it. As the guide line for the associated lane, this is because for the confluence lane to enter the main road, it first needs to enter Lane ④. During peak hours, if the traffic flow in both Lane ④ and the confluence lane is in an overloaded state, it is very easy to cause congestion. Therefore, to avoid the above problems, it is necessary to change the guide line Ⅲ in advance, that is, to connect the vacant position in the dotted line area through the projected guide line to form a solid line. At this time, vehicles in other lanes will not be able to change lanes into Lane ④, reducing the traffic flow burden on Lane ④. To close the dotted line, it is necessary to locate the guide line segments that need to be connected by the current guide line in advance. As Figure 4 shown, there are two areas that need to be closed in the current area of the guide line Ⅲ, which are formed by three guide line segments. At this time, the endpoints of the three guide line segments are located respectively to obtain the corresponding spatial coordinates, and the spatial coordinates are stored in the point cloud data . That is, to locate the position of the guide line. At this time, it is necessary to adjust the position of the drone so that the projection of the drone can be projected onto the vacant position. To ensure the consistency of the projection, it is necessary to formulate a corresponding projection pattern according to the size of the vacant position. As Figure 5 shown, the main projection pattern in reality is a square. To ensure a single adjustment, the distance of the unit direction axis is adjusted each time. That is, first control the drone to fly vertically upward from the ground so that the projection image coincides with the vacant position. Before the adjustment process, as Figure 6 shown, the area of the projection pattern formed by the drone at different vertical heights is obtained through the adjustment of the unit vertical height. Combining the spatial coordinates of the endpoints of the guide line segments, the area of the vacant position can be calculated. At this time, only the corresponding vertical height needs to be matched according to the current area, and the drone hovers at the vertical height to complete the position adjustment on the z-axis. Control the drone to move along the y-axis so that the side of the projection pattern coincides with the guide line to complete the position adjustment on the y-axis. Finally, control the drone to move along the x-axis so that each endpoint of the projection image coincides with each endpoint of the vacant position. At this time, the projection pattern completely fills the vacant position, and the distances of the three adjustments, the adjustment order, and the final projection points of the drone are recorded , as the control steps for the projection guide line of the drone.

[0086] Furthermore, to respond in a timely manner, a network channel is established between the drone and the camera monitoring equipment through the Internet of Things for sharing traffic flow monitoring data. Combining with the industry standards of road condition management, the guide line response status of the main road and the confluence lane is formulated. The guide line response status is reflected by the traffic flow impact characteristic values, that is, the traffic flow density and the traffic flow speed. Among them, the guide line response status is used as the basis for the drone startup control steps. The specific formulation method is as follows:

[0087] As shown by Figure 7 , obtain the traffic flow load ranges of the main road and the merging lane, that is, no congestion occurs under the current load range, where the traffic flow load range is fed back by traffic density and traffic speed. The lane saturation algorithm is adopted, and its algorithm formula is as follows:

[0088] ;

[0089] Among them, is the maximum traffic flow, is the average speed of vehicles driving on the lane, is the safe vehicle distance, which is related to the average speed ; is the vehicle speed length. Different types of vehicles have different body lengths. When calculating the traffic flow, the body length is an important factor affecting the vehicle spacing. n is the number of lanes, and the maximum traffic flow is the diversion response state.

[0090] It should be noted that the traffic flow of the main road has a higher priority than that of the merging lane. When the traffic flow of the main road exceeds its corresponding maximum traffic flow , that is, the traffic flow state of the main road conforms to the diversion response state at this time, then it is necessary to maintain the traffic flow of the main road to pass through. Therefore, the corresponding diversion line does not change. Only when the traffic flow state of the main road does not conform to the diversion response state and the traffic flow state of the main road is normal without congestion, then it is necessary to consider the traffic flow situation of the merging lane;

[0091] When the traffic flow state of the merging lane does not conform to the diversion response state, then maintain the current position of the diversion line unchanged, that is, the fixed diversion line can already guide the traffic flow;

[0092] When the traffic flow state of the merging lane conforms to the diversion response state, at this time, the drone intervenes in the diversion line, projects the diversion line according to the pre-calculated control steps, and re-divides the diversion area between the main road and the merging lane, that is, adjusts the position to the projection position. By projecting the projection pattern to the vacant position, the state of the diversion line is changed to reduce the traffic flow pressure in the connection area between the current main road and the merging lane.

[0093] Finally, obtain the traffic flow guiding state of the diversion line after projection, that is, store the numerical change of the traffic flow influence characteristics after the diversion line is adjusted as the evaluation basis for evaluating the adjustment of the diversion line.

[0094] The present invention monitors the traffic flow density and traffic flow speed of different lanes in real time to obtain the traffic flow states of different lanes. At the same time, it identifies the position of the advance lane diversion line to obtain the adjustment direction of the diversion line, and uses a drone with pre-established control steps to project the diversion line. Taking the traffic flow state as the response basis, it adjusts the diversion line in real time through the drone, changes the state of the diversion line to adapt to the traffic flow states of different lanes, makes full use of the diversion function of the diversion line in different states, and reduces the traffic flow pressure on the lanes.

[0095] A second object of the present invention is to provide a system for implementing an intelligent traffic diversion control method based on the Internet of Things, including a monitoring device control system, a drone control system, a diversion response state comparison module, and a projection result collection module;

[0096] Among them, the monitoring device control system monitors and processes the main road and the confluence lane, and collects the traffic flow influence characteristics on each lane in real time. The traffic flow influence characteristics include traffic flow density and traffic flow speed;

[0097] The drone control system is used to control the drone to project the diversion line. A data sharing channel established through the Internet of Things is used for data sharing between the drone control system and the monitoring device control system. The monitoring device control system feeds back the traffic flow influence characteristics to the drone control system in real time;

[0098] The drone control system includes an original diversion line collection module, a projected diversion line simulation module, and a simulation step recording module;

[0099] Among them, the original diversion line collection module is used to collect the original diversion lines of each lane, locate the position of the original diversion line in combination with the initial position of the drone, and locate the corresponding vacant positions;

[0100] The projected diversion line simulation module changes the position by adjusting the drone and projects the projection pattern to the vacant position;

[0101] The simulation step recording module is used to collect the projection steps;

[0102] The diversion response state comparison module combines the feedback information of real-time monitoring to compare the collected lane diversion response states, and serves as the feedback for initiating the drone control;

[0103] The projection result collection module combines the monitoring device to collect the lane diversion information after the diversion line is projected.

[0104] The basic principles, main features and advantages of the present invention have been shown and described above. Those skilled in the art should understand that the present invention is not limited by the above embodiments. The above embodiments and the descriptions in the specification are only preferred examples of the present invention and are not used to limit the present invention. Without departing from the spirit and scope of the present invention, the present invention will have various changes and improvements, and these changes and improvements all fall within the scope of the present invention claimed. The scope of protection of the present invention is defined by the appended claims and their equivalents.

Claims

1. An intelligent traffic diversion control method based on the Internet of Things, characterized in that, It includes the following steps: Step 1: Set up camera monitoring equipment in the confluence lane area to collect the traffic flow influence characteristics of the main road and the confluence lane, and reflect the traffic flow status of different lanes through the traffic flow influence characteristics; Step 2: Calculate in advance the control steps for the drone to project the diversion line and store them in the drone control terminal; Step 3: Build a network channel between the drone and the camera monitoring equipment through the Internet of Things to share traffic flow monitoring data; Step 4: Combine the industry standards of road condition management to formulate the diversion response status of the main road and the confluence lane, and the diversion response status is reflected by the traffic flow influence characteristic values; Step 5: According to the camera monitoring equipment, update the traffic flow influence characteristic values of different lanes in real time, compare the reflected traffic flow status with the diversion response status, and share the feedback result to the drone control terminal; When the traffic flow status of the main road conforms to the diversion response status, the current position of the diversion line remains unchanged; When the traffic flow status of the main road does not conform to the diversion response status, the traffic flow status of the confluence lane is determined; When the traffic flow status of the confluence lane does not conform to the diversion response status, the current position of the diversion line remains unchanged; When the traffic flow status of the confluence lane conforms to the diversion response status, the drone responds and starts to project the diversion line according to the pre-calculated control steps, and re-divides the diversion area between the main road and the confluence lane; Step 6: Obtain the traffic flow guiding status of the projected diversion line and perform real-time data storage.

2. The intelligent traffic diversion control method based on the Internet of Things according to claim 1, characterized in that: The traffic flow influence characteristics in Step 1 include traffic flow density and traffic flow speed.

3. The intelligent traffic diversion control method based on the Internet of Things according to claim 1, wherein: The calculation method of the traffic flow density in Step 1 includes the following steps: Step 1.1: Calculate the actual coverage length of the virtual coil according to the pitch angle and height of the camera. The virtual coil includes a first coil and a second coil, where the first coil is used for triggering detection and the second coil is used for counting. The specific algorithm is as follows: ； Among them, is the actual physical length of the virtual coil on the ground, is the pixel width of the virtual coil in the image, is the installation height of the camera, is the focal length of the camera, is the pitch angle of the camera; Step 1.2: After completing the positioning of the virtual coil, capture the vehicle passing through the video screen, track the trajectory of the vehicle in the lane through particle positioning, and obtain the center of mass coordinates of the vehicle in the connected domain. ,in , ,and is the total number of valid pixels in the connected domain, is the coordinate of the i-th pixel in the connected domain; Step 1.3: Combine the Kalman filter to predict the vehicle centroid position. When the centroid continuously passes through the first coil for three frames and disappears within the second coil, the traffic flow count is incremented by 1. The trigger times are accumulated by setting a time window, and the vehicle volume per hour is output.

4. The intelligent traffic diversion control method based on the Internet of Things according to claim 3, characterized in that: The traffic flow speed in Step 1 uses the double virtual coil speed measurement method, and the specific algorithm is as follows: ； is the speed of the passing vehicle in the lane, is the frame rate of the camera, and are the frame numbers of the vehicle passing through the first and second coils respectively. By setting a time window, the average vehicle speed of the passing vehicles in the lane within the time window is calculated.

5. The intelligent traffic diversion control method based on the Internet of Things according to claim 1, characterized in that: The method for calculating the control steps for the drone to project the diversion line in Step 2 includes the following steps: Step 2.1: Use the lidar carried on the drone to scan the ground at a specific frequency to obtain the original position of the diversion line of the current lane; Step 2.2: The drone establishes a spatial rectangular coordinate system with the initial point as the origin, obtains the endpoint coordinates of each original diversion line, and generates point cloud data ; Step 2.3: Obtain the associated lane in the main road and the confluence lane, where the associated lane is the lane closest to the confluence lane; Step 2.4: Obtain the endpoint coordinates of the diversion line of the associated lane and adjust the position of the drone based on the endpoint coordinates.

6. The intelligent traffic diversion control method based on the Internet of Things according to claim 5, characterized in that: The method for adjusting the position of the drone based on the endpoint coordinates in Step 2.4 includes the following steps: Step 2.4.1: Combine the spatial coordinates of the endpoints of the diversion line segment to calculate the area of the vacant position of the diversion line of the associated lane; Step 2.4.2: Control the drone to fly vertically upward from the ground so that the projected image coincides with the vacant position, completing the position adjustment on the z-axis; Step 2.4.3: Control the drone to move along the y-axis so that the side of the projected figure coincides with the diversion line, completing the position adjustment on the y-axis; Step 2.4.4: Control the drone to move along the x-axis so that each endpoint of the projected image coincides with each endpoint of the vacant position, and the projected figure completely fills the vacant position; Step 2.4.5: Record the distances of the three adjustments, the adjustment order, and the final projection points of the drone as the control steps for the projected diversion line of the drone.

7. The intelligent traffic diversion control method based on the Internet of Things according to claim 1, characterized in that: The method for formulating the diversion response status of the main road and the confluence lane in Step 4 includes the following steps: Step 4.1: Obtain the traffic flow load ranges of the main road and the confluence lane; Step 4.2: The traffic flow load ranges are fed back through traffic flow density and traffic flow speed, and the lane saturation algorithm is used. The algorithm formula is as follows: ； Among them, is the maximum traffic flow, is the average speed of vehicles driving on the lane, is the safe distance between vehicles, related to the average speed and is the vehicle speed length, n is the number of lanes, and the maximum traffic flow is the diversion response state.

8. A system for implementing the Internet of Things-based intelligent traffic diversion control method according to claim 1, characterized in that: It includes a monitoring device control system, a drone control system, a diversion response status comparison module, and a projection result collection module; Among them, the monitoring device control system monitors and processes the main road and the confluence lane, and real-time collects the traffic flow impact characteristics on each lane. The traffic flow impact characteristics include traffic flow density and traffic flow speed; The drone control system is used to control the drone to project the diversion line. A data sharing channel established through the Internet of Things is used for data sharing between the drone control system and the monitoring device control system. The monitoring device control system feeds back the traffic flow impact characteristics to the drone control system in real time; The drone control system includes an original diversion line collection module, a projected diversion line simulation module, and a simulation step recording module; Among them, the original diversion line collection module is used to collect the original diversion lines of each lane, combine the initial position of the drone to locate the position of the original diversion line, and locate the corresponding vacant position; The projected diversion line simulation module projects the projected figure onto the vacant position by adjusting the position of the drone; The simulation step recording module is used to collect the projection steps; The diversion response status comparison module combines the feedback information of real-time monitoring to compare the collected lane diversion response status as the feedback for initiating the drone control; The projection result collection module combines the lane diversion information after the diversion line is projected by the monitoring device.

Images