An Emergency Traffic Dispatching and Management Method and System Based on UAV Surveillance

Abstract

The present invention discloses an emergency traffic dispatching management method and system based on drone surveillance, which relates to the technical field of traffic management control. It includes determining the emergency traffic location within the urban arterial road area based on traffic image data, and planning the driving data of the target object within the urban arterial road area according to the emergency traffic location. By collecting the image data of the target object at different positions within the urban arterial road area by the drone and combining the time intervals between the image data at different positions, the drone can locate the position of the target object and enable the communication device of the public transportation interacting with the target object to connect to the command channel with the drone, so that the drone can send regulation commands to the public transportation communication device in stages based on the position of the target object and the position of the drones, thereby realizing a rapid response and precise dispatching to the emergency traffic situation and ensuring the efficiency of traffic dispatching.

Description

Technical Field

[0001] The present invention relates to the technical field of traffic management and control, and specifically provides an emergency traffic dispatching management method and system based on drone surveillance. Background Art

[0002] In the field of traffic management and control, using drones to conduct real-time surveillance and recording of traffic conditions can quickly reach the airspace above the accident or congestion site, providing first-hand on-site information for the dispatching center. At the same time, it can help managers accurately judge the traffic conditions and formulate more precise dispatching plans.

[0003] After retrieval, the Chinese invention patent with the publication number "CN118486198A" discloses "a drone traffic control method, device, and medium based on area division". This application can confirm which positions are working areas where the work objectives can be achieved through the analysis of the point cloud data of the target building, and set warning areas around the working areas. Thus, through reasonable area division, the flight range of the working drones is restricted, facilitating traffic control within each area for the drones. Compared with the manual control method, it does not depend on the operator's operation level, making the traffic control more efficient and accurate, and increasing the automation control level of the device.

[0004] In addition, the Chinese invention patent with the publication number "CN119207087A" discloses "a method, device, electronic device, and storage medium for identifying highway traffic jam events". This application uses the real-time video of the drone as the data source, identifies and analyzes the vehicles in the data source, and calculates the distance relationship between adjacent vehicles to determine whether a traffic jam occurs. Compared with the traditional method that only relies on traffic flow or average vehicle speed, this method is closer to the physical characteristics of actual traffic jams, so it can more accurately detect actual traffic jam events and reduce the occurrence of false alarms and missed reports.

[0005] When sudden traffic events occur in the urban arterial road area, in view of the above two publicly disclosed patents and similar patent methods in practical applications, they usually can only identify relatively stationary targets, resulting in traffic control instructions based on these stationary targets being unable to respond in a timely manner to the real-time changes in traffic conditions, thus affecting the efficiency of traffic control. Summary of the Invention

[0006] The purpose of the present invention is to provide an emergency traffic dispatching management method and system based on drone surveillance to solve the problems raised in the above background art.

[0007] To achieve the above purpose, the present invention provides the following technical solutions:

[0008] In a first aspect, an emergency traffic dispatching and management method based on drone surveillance is proposed, including: a number of drones arranged over the urban arterial road area, where the drones are used to obtain traffic image data and transmit control instructions to public transportation communication devices within the urban arterial road area;

[0009] Determine the emergency traffic locations within the urban arterial road area based on the traffic image data;

[0010] According to the emergency traffic locations, plan the driving data of the target object within the urban arterial road area;

[0011] Select the marked drones corresponding to the driving data from among the multiple drones;

[0012] Collect primary traffic image data, which is obtained by the marked drone located at the starting node within the driving data, for recording the traffic conditions when the target object is at the starting node within the driving data;

[0013] Collect secondary traffic image data, which is obtained by the marked drone located at any node within the driving data, for recording the traffic conditions when the target object is at any node within the driving data;

[0014] Calculate the time interval between the primary traffic image data and the secondary traffic image data;

[0015] The marked drones send control instructions to the corresponding public transportation communication devices based on the time interval, the primary traffic image data, and the secondary traffic image data;

[0016] The public transportation communication devices adjust the traffic flow in the urban arterial road area according to the control instructions.

[0017] As a further preferred embodiment of this technical solution, the method for determining the emergency traffic locations includes;

[0018] Select an initial image segment, where the initial image segment is any static image frame in the traffic image data collected by a single drone;

[0019] Mark the moving feature points in the initial image segment, where the moving feature points include: vehicles and pedestrians;

[0020] Taking the initial image segment as a reference, extract multiple static image segments of the traffic image data at the same position but different time points;

[0021] Taking the initial image segment as a template, overlay the multiple static image segments to form a discriminant image;

[0022] Determine a discriminant target within the discriminant image, where the discriminant target is any continuously moving feature point within the discriminant image;

[0023] Compare and determine the positions of the discrimination target at different time points within the discrimination image to obtain the movement attribute data of the discrimination target;

[0024] Based on the movement attribute data of the discrimination target and combined with traffic rules, evaluate whether there is an emergency traffic situation in the traffic image data collected by a single drone;

[0025] Based on the evaluation result, mark the movement range of the discrimination target as an emergency traffic position.

[0026] As a further optimization of this technical solution, the method for evaluating whether there is an emergency traffic situation in the traffic image data collected by a single drone includes:

[0027] Extract the threshold data within the urban arterial road area according to traffic rules;

[0028] Map the movement attribute data of the discrimination target and the threshold data into a two-dimensional coordinate system, where the horizontal axis of the two-dimensional coordinate system represents the movement speed of the discrimination target, and the vertical axis of the two-dimensional coordinate system represents the movement direction of the discrimination target;

[0029] In the two-dimensional coordinate system, with the threshold data as the benchmark, define normal moving objects and emergency moving objects;

[0030] Evaluate whether there is an emergency traffic situation for the discrimination target based on the position of the movement attribute data of the discrimination target within the two-dimensional coordinate system.

[0031] As a further optimization of this technical solution, the planning method for driving data includes:

[0032] The drone retrieves the area covering the emergency traffic position within the traffic image data and uploads it to the map system of the urban arterial road;

[0033] The map system of the urban arterial road forms a termination node based on the area of the emergency traffic position, and the termination node is used to identify the end point of the driving data;

[0034] The drone retrieves the starting node of the target object within the urban arterial road area based on the type of target object attributes, and the starting node is used to identify the starting point of the driving data;

[0035] Based on the starting node, the termination node, and the road attributes of the urban arterial road, construct a series of basic data sequences;

[0036] A series of basic data sequences filter out the corresponding driving data according to the attributes of the emergency traffic position;

[0037] The drone transmits the filtered driving data to the target object to guide the target object to navigate according to the driving data.

[0038] As a further preference of this technical solution, the attributes of the emergency traffic location include: dynamic attributes and static attributes;

[0039] A method for a series of basic data sequences to filter driving data based on the dynamic attributes of the emergency traffic location includes:

[0040] Taking the dynamic attributes of the emergency traffic location in the urban arterial road area as a benchmark, obtain the moving trend of the emergency traffic location in the traffic image data;

[0041] According to the moving trend, filter out the subset of driving data that matches it in the basic data sequence. The subset of driving data is used to represent the driving data that is consistent with the driving direction of the target object;

[0042] The drone identifies the driving data that is consistent with the driving direction of the target object in the subset of driving data as the optimal driving data.

[0043] As a further preference of this technical solution, a method for a series of basic data sequences to filter driving data based on the static attributes of the emergency traffic location includes:

[0044] Taking the static attributes of the emergency traffic location in the urban arterial road area as a benchmark, obtain the distribution locations of public transportation communication devices of the emergency traffic location in the urban arterial road area in the traffic image data;

[0045] Based on the distribution locations of the public transportation communication devices, select the subset of driving data that matches the distribution locations of the public transportation communication devices in the basic data sequence. The subset of driving data is the driving data corresponding to the public transportation communication device closest to the target object;

[0046] The drone takes the driving data closest to the target object in the subset of driving data as the optimal driving data.

[0047] As a further preference of this technical solution, the method for selecting a marked drone includes:

[0048] Based on the driving data of the target object in the urban arterial road area, select several drones as candidate drones;

[0049] Calculate the relative distance between the candidate drone and the target object and the included angle between the candidate drone and the driving direction of the target object, and conduct quantitative analysis;

[0050] Based on the quantitative analysis results, construct a priority evaluation rule for the candidate drones. The numerical value given by the priority evaluation rule has a negative correlation with the priority level;

[0051] Select the candidate drone with the highest priority as the marked drone.

[0052] As a further preference of this technical solution, the method for a marked drone to send a regulation instruction to a public transportation communication device includes:

[0053] According to the position information of the target object in the primary traffic image data and the secondary image data, extract the corresponding serial numbers of two marked drones;

[0054] Match the extracted serial numbers of the two marked drones with the position information of the target object in the driving data, and construct a position matching relationship;

[0055] Based on the position matching relationship, locate the target position of the target object in the driving data set;

[0056] According to the distance between the target position and the two marked drones, activate the instruction channels between the marked drones and the public transportation communication devices that have interacted with the target object in the driving data in the order from near to far;

[0057] According to the time interval, the two marked drones send regulation instructions to the public transportation communication device in stages.

[0058] In a second aspect, to improve the above technical solution, an emergency traffic dispatching management system based on drone surveillance is also proposed. An emergency traffic dispatching management system based on drone surveillance uses the above-mentioned emergency traffic dispatching management method based on drone surveillance and includes:

[0059] A drone monitoring module, responsible for collecting traffic image data;

[0060] A traffic image data processing module, which undertakes the tasks of extracting static image segments, marking feature points, and image overlay for the obtained traffic image data;

[0061] A drone cooperation module, aiming to realize the mutual association and cooperative operation between drones;

[0062] An emergency traffic position recognition and evaluation module, responsible for analyzing traffic image data, and identifying and evaluating emergency traffic positions;

[0063] A target object driving data planning module, used to plan the driving data of the target object in the urban arterial road area according to the emergency traffic position and traffic rules;

[0064] A drone instruction sending module, based on the position, driving data, and image data of the target object, sends regulation instructions to the public transportation communication device;

[0065] A public transportation communication device module, responsible for receiving the regulation instructions from the marked drones and adjusting the traffic flow in the urban arterial road area according to the instructions;

[0066] The data interaction module realizes the data interaction function among the unmanned aerial vehicle (UAV), the public transportation communication device, and the map system.

[0067] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0068] The emergency traffic dispatching management method and system based on UAV surveillance collect image data of a target object at different positions in the urban arterial road area through the UAV, and combine the time intervals between the image data at different positions. While the UAV locates the position of the target object, it enables the connection of an instruction channel between the public transportation communication device interacting with the target object and the UAV, so that the UAV can send control instructions to the public transportation communication device in stages based on the position of the target object and the position of the UAVs, thereby realizing a rapid response and precise dispatching of the emergency traffic situation, not only ensuring the efficiency of traffic dispatching, but also ensuring the timeliness and accuracy of the dispatching instructions. BRIEF DESCRIPTION OF THE DRAWINGS

[0069] Figure 1 It is the flowchart of the steps of the method disclosed in the present invention;

[0070] Figure 2 It is the block diagram of the modules of the system disclosed in the present invention;

[0071] Figure 3 It is the auxiliary explanatory diagram of step S107.1 of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0072] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0073] Before understanding the technical solutions proposed in this application, it should be clear that the specific use of the UAV in the present invention is aerial surveillance and dispatching command in case of an emergency traffic event in the urban arterial road area, and the UAV monitors the traffic conditions in the air in real time.

[0074] It should be noted that in the present invention, several UAVs are set over the urban arterial road area, and the UAVs are used to obtain traffic image data and transmit control instructions to the public transportation communication devices in the urban arterial road area.

[0075] Specifically, in the present invention, the drone captures traffic image data by carrying a high-definition camera, and the traffic image data is then transmitted to the ground control center. Therefore, the emergency traffic dispatching management system based on drone surveillance proposed in the present invention further includes a ground control center module, where the ground control center module is used to receive, analyze, and process the traffic image data transmitted by the drone. In addition, during actual use, the ground control center module can also monitor the flight status of the drone to ensure that it performs the surveillance task safely and stably.

[0076] It should be added that, referring to Figure 2 it can be seen that an emergency traffic dispatching management system based on drone surveillance proposed in the present invention, in addition to the ground control center module, further includes:

[0077] A drone monitoring module, which is responsible for collecting traffic image data. It should be clear that the drone monitoring module is specifically a high-definition camera externally mounted on the drone in the present invention.

[0078] A traffic image data processing module, which undertakes the tasks of extracting static image segments, marking feature points, and image overlay for the acquired traffic image data. It should be clear that the traffic image data processing module is the image processing unit inside the high-definition camera in the present invention. The image processing unit can perform preliminary processing on the real-time traffic images captured by the high-definition camera to extract key information. It should be added that since the image processing unit is a common technical component at the present stage, the applicant will not elaborate too much on its specific structure and working principle here.

[0079] A drone cooperation module, which aims to achieve the mutual association and cooperative operation among drones. It should be clear that the drone cooperation module is specifically a communication component installed inside the drone in the present invention. Through the communication component, drones can share position information, flight status, and captured traffic image data in real time, ensuring that multiple drones can perform cooperative surveillance efficiently and orderly during emergency traffic events. In addition, during actual use, the drone cooperation module can also receive instructions from the ground control center module to adjust the flight trajectory or surveillance object.

[0080] An emergency traffic location identification and evaluation module, which is responsible for analyzing traffic image data and identifying and evaluating emergency traffic locations.

[0081] A target object travel data planning module, which is used to plan the travel data of the target object in the urban main road area according to the emergency traffic location and traffic rules.

[0082] A drone instruction sending module, which sends control instructions to public transportation communication devices based on the position, travel data, and image data of the target object.

[0083] The public transportation communication device module is responsible for receiving the control instructions from the marked drones and adjusting the traffic flow in the urban arterial road area according to the instructions.

[0084] The data interaction module realizes the data interaction function among the drones, the public transportation communication device, and the map system.

[0085] It should be noted that in the present invention, the emergency traffic location identification and evaluation module, the target object travel data planning module, the drone instruction sending module, the public transportation communication device module, and the data interaction module are all specifically classified into the technical category of the integrated processing chip. The integrated processing chip is installed in the drones, the public transportation communication device, and the ground control center in the present invention.

[0086] In addition, it should also be explained that for an emergency traffic dispatching management system based on drone surveillance provided by the present invention, during actual operation, the drones continuously capture traffic image data in the air. The traffic image data is transmitted to the ground control center in real time through the drone monitoring module. After the ground control center module receives this data, it starts the traffic image data processing module to perform preliminary processing such as static image segment extraction, feature point marking, and image overlay on the captured real-time traffic images to quickly extract key traffic information.

[0087] Subsequently, the emergency traffic location identification and evaluation module works to analyze the processed traffic image data, identify the location of the emergency traffic event, and evaluate the traffic conditions at that location. Based on the evaluation results, the target object travel data planning module quickly plans the optimal travel data for the target objects in the urban arterial road area according to the emergency traffic location and traffic rules.

[0088] The drone instruction sending module then intelligently generates control instructions according to the location, travel data, and real-time image data of the target objects, and sends these instructions to the public transportation communication device through the data interaction module. After receiving the instructions, the public transportation communication device module immediately adjusts the traffic flow in the urban arterial road area according to the instructions to ensure smooth and safe traffic.

[0089] Based on the emergency traffic dispatching management system based on drone surveillance proposed by the present invention, as Figure 1 shown, the present invention provides a technical solution: an emergency traffic dispatching management method based on drone surveillance, and includes: step S100 - step S800.

[0090] Step S100: Determine the emergency traffic location in the urban arterial road area based on the traffic image data.

[0091] It should be understood that the method for determining the emergency traffic position in step S400 includes: steps S101 to S108.

[0092] Step S101: Select an initial image segment.

[0093] It should be noted that the initial image segment in step S101 is any frame of static image in the traffic image data collected by a single drone.

[0094] Step S102: marking moving feature points in the initial image segment.

[0095] It should be noted that the moving feature points in step S102 include vehicles and pedestrians.

[0096] Step S103: Taking the initial image segment as a reference, extracting multiple static image segments of the traffic image data at the same location but at different time points.

[0097] It should be clear that step S103 in the present invention is used to compare static image segments at different time points and analyze the position changes of moving feature points, so as to determine the state of traffic flow and whether there are emergency traffic conditions such as abnormal congestion or accidents.

[0098] Step S104: using the initial image segment as a template, superimposing multiple frames of static image segments to form a discrimination image.

[0099] Step S105: determining a discrimination target in the discrimination image, where the discrimination target is any continuously moving feature point in the discrimination image.

[0100] Step S106: comparing the positions of the target at different time points in the detection image to obtain movement attribute data of the target.

[0101] It should be clear that step S106 is used in the present invention to analyze the moving speed, moving direction and moving trajectory of the target, and then determine whether the target is in an abnormal state, such as sudden braking, sharp turns and reverse driving to cause traffic accidents.

[0102] Step S107: Based on the movement attribute data of the identified target and in combination with traffic rules, it is evaluated whether there is an emergency traffic situation in the traffic image data collected by a single drone.

[0103] Step S108: Based on the evaluation result, the moving range of the determination target is marked as an emergency traffic location.

[0104] It should be noted that in the present invention, steps S101 to S108 can be automatically executed by the emergency traffic location recognition and evaluation module without manual intervention, thus ensuring the processing efficiency and accuracy of emergency traffic events. After determining the emergency traffic location, the system immediately enters step S200, that is, according to the emergency traffic location and traffic rules, the driving data of the target object within the urban arterial road area is planned.

[0105] In addition, it should be further noted that in step S107 of the present invention, the method for evaluating whether there is an emergency traffic situation in the traffic image data collected by a single unmanned aerial vehicle includes: steps S107.1 - S107.4.

[0106] Step S107.1: Extract the threshold data within the urban arterial road area according to the traffic rules.

[0107] It should be clear that in step S107.1, the threshold data covers any combination of two or more of the maximum and minimum vehicle driving speeds, the safety distance between vehicles, traffic signs, and the indication rules of traffic lights.

[0108] For example: Refer to Figure 3 It can be seen that when the traffic rules are specifically that within the urban arterial road area, the vehicle driving speed shall not exceed 60 kilometers per hour and shall not be lower than 30 kilometers per hour, and at the same time, the vehicles traveling in the same direction shall maintain a safety distance of at least 50 meters, the specific manifestation form of the threshold data at this time is (60 - 30) km / h ± 50 m.

[0109] Step S107.2: Map the movement attribute data of the discrimination target and the threshold data to a two-dimensional coordinate system.

[0110] It should be clear that referring to Figure 3 It can be seen that in step S107.2 of the present invention, the horizontal axis of the two-dimensional coordinate system represents the movement speed of the discrimination target, and the two ends of the horizontal axis respectively represent the movement speed of the discrimination target. The vertical axis of the two-dimensional coordinate system represents the distance between two discrimination targets. Among them, the positive value in the vertical axis within the two-dimensional coordinate system indicates that the two discrimination targets are in the same-direction driving state, while the negative value in the vertical axis within the two-dimensional coordinate system indicates that the two discrimination targets are in the oncoming driving state.

[0111] Step S107.3: In the two-dimensional coordinate system, define normal moving objects and emergency moving objects based on the threshold data.

[0112] Step S107.4: Evaluate whether there is an emergency traffic situation for the discrimination target based on the position of the movement attribute data of the discrimination target within the two-dimensional coordinate system.

[0113] It should be added that in the actual operation of steps S107.1 to S107.4 of the present invention, by comparing and discriminating the movement attribute data of the target with the preset threshold data, those traffic participants deviating from the normal driving state can be quickly and accurately identified, such as speeding, illegal lane changing or abnormal parking. In the scenario of detecting an emergency traffic situation, the evaluation result is fed back to the target object driving data planning module, and the target object driving data planning module then plans a driving path or avoidance plan for vehicles and pedestrians in the urban arterial road area according to the current traffic conditions and traffic rules, reducing to a certain extent the impact of emergency traffic incidents on the overall traffic flow and ensuring the safety and smooth passage of all road users.

[0114] Step S200: Plan the driving data of the target object in the urban arterial road area according to the emergency traffic location.

[0115] It should be clear that the method for planning the driving data in step S200 includes: steps S201 - S206.

[0116] Step S201: The drone retrieves the area covering the emergency traffic location from the traffic image data and uploads it to the map system of the urban arterial road.

[0117] Step S202: The map system of the urban arterial road forms a termination node based on the area of the emergency traffic location.

[0118] It should be clear that in the present invention, the termination node is used to identify the end point of the driving data. In addition, in the present invention, the map system of the urban arterial road is input into the integrated processing chip.

[0119] Step S203: The drone retrieves the starting node of the target object in the urban arterial road area based on the type of the target object attribute.

[0120] It should be clear that in this step S203, the starting node is used to identify the starting point of the driving data.

[0121] Step S204: Based on the starting node, the termination node and the road attributes of the urban arterial road, a series of basic data sequences are constructed.

[0122] It should be clear that in step S204, the road attributes of the urban arterial road cover the specific distribution positions of the public transportation communication equipment in the urban arterial road and the operation logic under normal conditions of the public transportation communication equipment.

[0123] Step S205: A series of basic data sequences screen out the corresponding driving data according to the attributes of the emergency traffic location.

[0124] Step S206: The drone transmits the selected driving data to the target object to guide the target object to navigate based on the driving data.

[0125] It should be noted that in the present invention, steps S201 to S206 are jointly executed by the target object driving data planning module and the drone instruction sending module, ensuring the timeliness and accuracy of driving data planning. Additionally, it should be added that the target object, including but not limited to vehicles and pedestrians, can quickly receive the optimal driving path or avoidance plan, thereby effectively avoiding or approaching the emergency traffic location.

[0126] It should be further added that in step S205, the attributes of the emergency traffic location include: dynamic attributes and static attributes. It should be clear that the dynamic attribute of the emergency traffic location represents the moving state of the emergency traffic location in the actual scenario. Specifically, in the existing emergency traffic scenarios, it can be the vehicle involved in a traffic accident. In this traffic scenario, the dynamic attribute of the emergency traffic location will change as the emergency traffic event moves.

[0127] In contrast, the static attribute of the emergency traffic location represents the stationary state of the emergency traffic location in the actual scenario. Specifically, in the existing emergency traffic events, it can be road construction, obstacles after a traffic accident, and traffic control areas. At this time, the static attribute of the emergency traffic location will remain unchanged until the emergency traffic event is handled. By analyzing the dynamic and static attributes of the emergency traffic location, the target object driving data planning module can more accurately screen out the driving data suitable for the current traffic conditions, thereby further improving the practicality and reliability of the emergency traffic dispatching management system.

[0128] Therefore, the method for screening driving data based on the dynamic attributes of the emergency traffic location for a series of basic data sequences includes: steps S205.1 - S205.3.

[0129] Step S205.1: Taking the dynamic attributes of the emergency traffic location in the urban arterial road area as a benchmark, obtain the moving trend of the emergency traffic location in the traffic image data.

[0130] Step S205.2: According to the moving trend, screen out the subset of driving data that matches it in the basic data sequence.

[0131] It should be clear that in step S205.2, the subset of driving data is used to represent the driving data that is consistent with the driving direction of the target object.

[0132] Step S205.3: The drone identifies the driving data that is consistent with the driving direction of the target object in the subset of driving data as the optimal driving data.

[0133] In contrast, a method for filtering driving data based on the static attributes of an emergency traffic location for a series of basic data sequences includes: step S205.A - step S205.C.

[0134] Step S205.A: Taking the static attributes of the emergency traffic location in the urban arterial road area as a reference, obtain the distribution locations of public transportation communication devices of the emergency traffic location within the urban arterial road area in the traffic image data.

[0135] Step S205.B: Based on the distribution locations of the public transportation communication devices, select a subset of driving data that matches the distribution locations of the public transportation communication devices in the basic data sequence.

[0136] It should be clear that in step S205.B, the subset of driving data is the driving data corresponding to the public transportation communication device closest to the target object.

[0137] Step S206.C: The drone takes the driving data closest to the target object within the subset of driving data as the optimal driving data.

[0138] Step S300: Select a marked drone corresponding to the driving data among multiple drones.

[0139] It should be clear that the method for selecting the marked drone in step S300 includes: step S301 - step S304.

[0140] Step S301: Based on the driving data of the target object within the urban arterial road area, select several drones as candidate drones.

[0141] Step S302: Calculate the relative distance between the candidate drone and the target object and the included angle between the candidate drone and the driving direction of the target object, and conduct quantitative analysis.

[0142] Step S303: Based on the results of the quantitative analysis, construct a priority evaluation rule for the candidate drones. The numerical value given by the priority evaluation rule has a negative correlation with the priority level.

[0143] It should be clear that the meaning represented by the negative correlation in step S300 is that the closer the relative distance between the candidate drone and the target object, and the smaller the included angle between the candidate drone and the driving direction of the target object, the higher the priority of the candidate drone.

[0144] Step S304: Select the candidate drone with the highest priority as the marked drone.

[0145] Step S400: Collect primary traffic image data.

[0146] It should be clear that the primary traffic image data is acquired by the marked drones located at the starting node in the driving data, and is used to record the traffic conditions of the target object at the starting node in the driving data.

[0147] Step S500: Collect secondary traffic image data.

[0148] It should be clear that the secondary traffic image data is acquired by the marked drones located at any node in the driving data, and is used to record the traffic conditions of the target object at any node in the driving data.

[0149] Step S600: Calculate the time interval between the primary traffic image data and the secondary traffic image data.

[0150] It should be clear that in step S600, the time interval between the primary traffic image data and the secondary traffic image data is obtained by comparing the timestamp information of the traffic image data. In the prior art, the traffic impact data contains timestamp information.

[0151] Step S700: The marked drones send control commands to the corresponding public transportation communication devices based on the time interval, the primary traffic image data, and the secondary traffic image data.

[0152] It should be clear that in step S700, the method by which the marked drones send control commands to the public transportation communication devices includes: steps S701 - S705.

[0153] Step S701: According to the position information of the target object in the primary traffic image data and the secondary image data, extract the corresponding two marked drone sequence numbers.

[0154] Step S702: Match the two extracted marked drone sequence numbers with the position information of the target object in the driving data, and construct a position matching relationship.

[0155] Step S703: Based on the position matching relationship, locate the target position of the target object in the driving data set.

[0156] Step S704: According to the distance between the target position and the two marked drones, activate the command channels between the marked drones and the public transportation communication devices that have interacted with the target object in the driving data in the order from near to far.

[0157] Step S705: According to the time interval, the two marked drones send control commands to the public transportation communication devices in stages.

[0158] It should be noted that in step S702, the position matching relationship is determined according to the relative distance of the position information in the marked drone and the driving data. Specifically, when the relative distance between the marked drone and the position information is less than the distance between two marked drones, it is determined that the position matching relationship is established.

[0159] Step S800: The public transportation communication device adjusts the traffic flow in the urban arterial road area according to the regulation instruction.

[0160] It should be clear that in the actual operation of step S800, the specific content of the regulation instruction will be dynamically adjusted according to the traffic conditions in the current urban arterial road area and the driving needs of the target object. For example, if the target object is an ambulance that urgently needs to pass through a congested section, the regulation instruction will instruct the public transportation communication device to adjust the signal timing and open a green channel for the ambulance.

[0161] Although the embodiments of the present invention have been shown and described, for those of ordinary skill in the art, it can be understood that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the appended embodiments and their equivalents.

Claims

1. An emergency traffic dispatching and management method based on drone surveillance, comprising: A number of unmanned aerial vehicles (UAVs) are set over the urban arterial road area. The UAVs are used to obtain traffic image data and transmit control instructions to public transportation communication devices within the urban arterial road area. It is characterized in that: Determine the emergency traffic locations within the urban arterial road area based on the traffic image data; According to the emergency traffic locations, plan the driving data of the target object within the urban arterial road area; Select the marked UAV corresponding to the driving data from among multiple UAVs; Collect primary traffic image data, which is obtained by the marked UAV located at the starting node within the driving data, for recording the traffic conditions when the target object is at the starting node within the driving data; Collect secondary traffic image data, which is obtained by the marked UAV located at any node within the driving data, for recording the traffic conditions when the target object is at any node within the driving data; Calculate the time interval between the primary traffic image data and the secondary traffic image data; The marked UAV sends control instructions to the corresponding public transportation communication devices based on the time interval, the primary traffic image data, and the secondary traffic image data; The public transportation communication device adjusts the traffic flow in the urban arterial road area according to the control instructions; The method for determining the emergency traffic locations includes: Select an initial image segment, which is any frame of static image in the traffic image data collected by a single UAV; Mark the moving feature points in the initial image segment, and the moving feature points cover vehicles and pedestrians; Taking the initial image segment as a reference, extract multiple frames of static image segments of the traffic image data at the same position but different time points; Taking the initial image segment as a template, overlay multiple frames of static image segments to form a discriminant image; Determine a discriminant target within the discriminant image, and the discriminant target is any continuously moving feature point within the discriminant image; Compare the positions of the discriminant target at different time points within the discriminant image to obtain the moving attribute data of the discriminant target; Based on the moving attribute data of the discriminant target and combined with traffic rules, evaluate whether there is an emergency traffic situation in the traffic image data collected by a single UAV; Based on the evaluation result, mark the moving range of the discriminant target as the emergency traffic location; The method for evaluating whether there is an emergency traffic situation in the traffic image data collected by a single UAV includes: According to traffic rules, extract the threshold data within the urban arterial road area; Map the moving attribute data of the discriminant target and the threshold data to a two-dimensional coordinate system, where the horizontal axis of the two-dimensional coordinate system represents the moving speed of the discriminant target, and the vertical axis of the two-dimensional coordinate system represents the moving direction of the discriminant target; In the two-dimensional coordinate system, taking the threshold data as a reference, define normal moving objects and emergency moving objects; Evaluate whether the discriminant target has an emergency traffic situation based on the position of the moving attribute data of the discriminant target within the two-dimensional coordinate system.

2. The emergency traffic dispatching management method based on drone surveillance according to claim 1, characterized in that: The method for planning the driving data includes: The UAV retrieves the area within the traffic image data that covers the emergency traffic location and uploads it to the map system of the urban arterial road; The map system of the urban arterial road forms a termination node based on the area of the emergency traffic location, and the termination node is used to identify the end point of the driving data; Based on the types of target object attributes, the drone retrieves the starting node of the target object within the urban arterial road area, and the starting node is used to identify the starting point of the driving data; Based on the starting node, the ending node, and the road attributes of the urban arterial road, a series of basic data sequences are constructed; A series of basic data sequences filter out corresponding driving data according to the attributes of the emergency traffic location; The drone transmits the filtered driving data to the target object to guide the target object to navigate according to the driving data.

3. The emergency traffic dispatching and management method based on UAV surveillance according to claim 2, characterized in that: The attributes of the emergency traffic location include: dynamic attributes and static attributes; The method for a series of basic data sequences to filter driving data based on the dynamic attributes of the emergency traffic location includes: Taking the dynamic attributes of the emergency traffic location in the urban arterial road area as a benchmark, obtaining the moving trend of the emergency traffic location in the traffic image data; According to the moving trend, filtering out a subset of driving data that matches it in the basic data sequence, and the subset of driving data is used to represent the driving data consistent with the driving direction of the target object; The drone identifies the driving data consistent with the driving direction of the target object within the subset of driving data as the optimal driving data.

4. The emergency traffic dispatching and management method based on UAV surveillance according to claim 3, characterized in that: The method for a series of basic data sequences to filter driving data based on the static attributes of the emergency traffic location includes: Taking the static attributes of the emergency traffic location in the urban arterial road area as a benchmark, obtaining the distribution locations of public transportation communication devices of the emergency traffic location within the urban arterial road area in the traffic image data; Based on the distribution locations of public transportation communication devices, selecting a subset of driving data that matches the distribution locations of public transportation communication devices in the basic data sequence, and the subset of driving data is the driving data corresponding to the public transportation communication device closest to the target object; The drone takes the driving data closest to the target object within the subset of driving data as the optimal driving data.

5. The emergency traffic dispatching management method based on UAV surveillance according to claim 1, wherein: The method for marking the drone includes: Based on the driving data of the target object within the urban arterial road area, several drones are selected as candidate drones; Calculating the relative distance between the candidate drone and the target object and the included angle between the candidate drone and the driving direction of the target object, and conducting quantitative analysis; Based on the results of the quantitative analysis, constructing a priority evaluation rule for the candidate drones, and the numerical value given by the priority evaluation rule is negatively correlated with the priority level; Selecting the candidate drone with the highest priority as the marked drone.

6. The emergency traffic dispatching management method based on UAV surveillance according to claim 1, characterized in that: The method for the marked drone to send a control instruction to the public transportation communication device includes: According to the position information of the target object in the primary traffic image data and the secondary image data, extracting the corresponding two marked drone sequence numbers; Matching the two extracted marked drone sequence numbers with the position information of the target object in the driving data, and constructing a position matching relationship; Based on the position matching relationship, positioning the target position of the target object in the driving data set; According to the distance between the target position and the two marked drones, activating the instruction channels between the marked drones and the public transportation communication devices that have interacted with the target object in the driving data in the order from near to far; According to the time interval, the two marked drones send control instructions to the public transportation communication device in stages.

7. An emergency traffic dispatching and management system based on UAV surveillance, which uses an emergency traffic dispatching and management method according to any one of claims 1-6, is characterized in that, Including: The UAV monitoring module is responsible for collecting traffic image data; The traffic image data processing module undertakes the tasks of extracting static image segments, marking feature points, and image overlay on the obtained traffic image data; The UAV collaboration module aims to achieve the interconnection and collaborative operation among UAVs; The emergency traffic location recognition and evaluation module is responsible for analyzing traffic image data and identifying and evaluating emergency traffic locations; The target object travel data planning module is used to plan the travel data of the target object in the urban arterial road area according to the emergency traffic location and traffic rules; The UAV instruction sending module sends control instructions to the public transportation communication device based on the location, travel data, and image data of the target object; The public transportation communication device module is responsible for receiving the control instructions from the marked UAVs and adjusting the traffic flow in the urban arterial road area according to the instructions; The data interaction module realizes the data interaction function among UAVs, public transportation communication devices, and the map system.

Images