Unmanned aerial vehicle group coordination control system and method based on data analysis

Abstract

The invention discloses an unmanned aerial vehicle group coordination control system and method based on data analysis, and belongs to the technical field of unmanned aerial vehicle tracking control. The system comprises a task planning control module, a data acquisition module, a three-dimensional model management module, an intelligent judgment module, an intelligent analysis and calculation module and an intelligent tracking control module. The task planning control module is used for determining a tracked target and controlling a plurality of unmanned aerial vehicles to track each target in real time; the data acquisition module is used for acquiring image data and point cloud data; the three-dimensional model management module is used for determining the flight path of each unmanned aerial vehicle and determining the moving path of each target; the intelligent judgment module is used for judging whether the targets corresponding to the unmanned aerial vehicles are dynamically distributed again or not; the intelligent analysis and calculation module is used for re-determining a target set of each unmanned aerial vehicle and a region corresponding to the maximum tracking range of each unmanned aerial vehicle; and the intelligent tracking control module is used for controlling each unmanned aerial vehicle to go to the corresponding tracking position.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned aerial vehicle tracking control, and in particular to a coordinated control system and method for an unmanned aerial vehicle group based on data analysis. Background Art

[0002] Drone tracking control is a comprehensive technology that integrates computer vision, automatic control, artificial intelligence and drone technology. It is mainly used to achieve accurate tracking and dynamic following of specific targets by drones, and is widely used in many fields of life. In drone tracking control systems, three-dimensional models play a vital role. Through the fine construction of their grids and textures, they can realistically simulate the shape and surface characteristics of real or fictional objects, providing rich visual information and precise spatial positioning basis for drone tracking. It is not only used for target recognition and positioning, but also provides prediction and decision support for tracking algorithms by simulating the motion trajectory and posture of target objects.

[0003] When a drone group performs a multi-target tracking task, if there are too many targets to track and the number of drones is insufficient, one drone is needed to track multiple targets; and due to the uncertainty of target movement, the targets often go beyond the monitoring range during the tracking process. In the existing technology, the coordination ability between drone groups is insufficient, resulting in low tracking efficiency; and in the tracking control of drone groups, there is a lack of effective fault-tolerant mechanism, which easily leads to target loss. Summary of the invention

[0004] The purpose of the present invention is to provide a coordinated control system and method for a drone group based on data analysis to solve the problems raised in the above-mentioned background technology.

[0005] In order to solve the above technical problems, the present invention provides the following technical solution: a coordinated control method of a drone group based on data analysis, the method comprising the following steps:

[0006] S10, establishing a three-dimensional space model, determining the target to be tracked and the target set of the drone, controlling several drones to respectively track the targets of their respective target sets in real time; collecting image data and point cloud data of each drone during the tracking process;

[0007] S20, determining the maximum field of view coverage of the drone according to the clarity of the collected image data; determining the maximum tracking range of the drone according to the moving speed of the target and the response time of the drone; wherein the maximum tracking range is within the maximum field of view coverage; determining the change of the flight path of each drone over time according to the positioning of the drone, analyzing the collected image data and point cloud data, and determining the change of the moving path of each target over time;

[0008] S30, according to the moving paths of the targets, respectively determine the current position information of the targets; according to the current position information of the targets, the target sets corresponding to the current drones and the maximum tracking range corresponding to the image data collected by the current drones, determine whether it is necessary to dynamically reallocate the target sets corresponding to the drones; if necessary, execute step S40; if not, execute step S50;

[0009] S40, based on the current position information of each target and the maximum field of view coverage corresponding to the image data collected by each drone, re-determine the target set of each drone and the image position area corresponding to the maximum tracking range of each drone, and re-determine the number of drones. When the current number of drones is insufficient, increase the number of drones; when the current number of drones is too large, reduce the number of drones; determine the current position information of each drone according to the flight path of each drone; control each drone to go to the corresponding tracking position according to the re-determined image position area corresponding to the maximum tracking range of each drone and the current position information of each drone, and execute step S60;

[0010] S50, control each drone to be in a hovering state, and execute step S60;

[0011] S60, repeating steps S30-S50 until the target tracking is completed and each UAV is controlled to return.

[0012] A coordinated control system for drone groups based on data analysis, the system includes a mission planning control module, a data acquisition module, a three-dimensional model management module, an intelligent judgment module, an intelligent analysis and calculation module, and an intelligent tracking control module;

[0013] The mission planning control module is used to determine the target to be tracked, determine the target to be tracked and the target set of the drone, control several drones to respectively track the targets of their respective target sets in real time, and send data acquisition signals to the data acquisition module;

[0014] The data acquisition module is used to collect image data and point cloud data during the UAV tracking process, and send the collected data to the three-dimensional model management module;

[0015] The three-dimensional model management module is used to establish a three-dimensional space model, determine the maximum field of view coverage of the drone according to the clarity of the collected image data; determine the maximum tracking range of the drone according to the moving speed of the target and the response time of the drone; wherein the maximum tracking range is within the maximum field of view coverage; determine the change of the flight path of each drone over time according to the positioning of the drone, analyze the collected image data and point cloud data, and determine the change of the moving path of each target over time;

[0016] The intelligent judgment module is used to determine the current position information of each target according to the moving path of each target; determine whether it is necessary to dynamically reallocate the target set corresponding to each drone according to the current position information of each target, the target set corresponding to each drone and the maximum tracking range corresponding to the current image data collected by each drone; if it is necessary to dynamically reallocate the targets corresponding to each drone, send the dynamic reallocation signal to the intelligent analysis and calculation module; if it is not necessary to dynamically reallocate the targets corresponding to each drone, send the signal that does not need to be dynamically reallocated to the intelligent tracking control module;

[0017] The intelligent analysis and calculation module is used to re-determine the target set of each drone and the image position area corresponding to the maximum tracking range of each drone according to the current position information of each target and the maximum field of view coverage corresponding to the image data collected by each drone, and re-determine the number of drones. When the current number of drones is insufficient, the number of drones is increased; when the current number of drones is too large, the number of drones is reduced and sent to the intelligent tracking control module;

[0018] The intelligent tracking control module is used to determine the current position information of each drone according to the flight path of each drone when it is necessary to dynamically redistribute the target set corresponding to each drone; control each drone to go to the corresponding tracking position according to the image position area corresponding to the redetermined maximum tracking range of each drone and the current position information of each drone; and control each drone to be in a hovering state when it is not necessary to dynamically redistribute the target set corresponding to each drone.

[0019] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: by establishing a three-dimensional space model, determining the maximum field of view coverage and the maximum tracking range corresponding to the image data collected by the drone, analyzing the moving path of the tracking target, determining the location information that the drone needs to go to in the three-dimensional space model, and dynamically coordinating the drone group based on the analysis results, thereby avoiding the loss of the target caused by the uncertainty of the target movement changes and improving the robustness of the drone tracking system; by determining the tracking target corresponding to each drone and allocating the drone tracking tasks, the collaborative operation capability of the drone group is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 is the pixel resolution of the image data collected in the embodiment of the coordinated control method of the drone group based on data analysis of the present invention;

[0021] Figure 2 It is a structural schematic diagram of the coordinated control system of the UAV group based on data analysis of the present invention. DETAILED DESCRIPTION

[0022] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0023] See also Figure 1-2 , the present invention provides a technical solution:

[0024] See also Figure 1 In the first embodiment of the present invention, a coordinated control method for a drone group based on data analysis is provided. The method is based on the existing drone tracking technology. When a drone corresponds to multiple tracking targets, when a target exceeds the tracking range, the target and tracking range corresponding to the drone are automatically allocated. Through the three-dimensional space model, the position information of each target and each drone is determined respectively. Through the image data clarity, the moving speed of the target and the response time of the drone, the maximum field of view coverage and the maximum tracking range are introduced. According to the position information of each target in the three-dimensional space model, the target corresponding to each drone is dynamically allocated, and the drone group is dynamically coordinated according to the dynamic allocation result. Fewer drones are used to track the target. At the same time, when the number of drones to be tracked is insufficient, the number of drones is increased, so as to avoid the loss of the target caused by the uncertainty of the target movement change and improve the robustness of the drone tracking system. The method comprises the following steps:

[0025] S10, establishing a three-dimensional space model, determining the target to be tracked and the target set of the UAV, controlling several UAVs to respectively track the targets of their respective target sets in real time; and collecting image data and point cloud data of each UAV during the tracking process.

[0026] In this embodiment, the target of tracking is wild animals. Initially, the wild animals gather together and the number of targets is m. The target of tracking includes several targets. At this time, two drones are controlled to monitor the targets. Initially, the two drones correspond to each target respectively, and the management personnel manually determine the target set corresponding to each drone. As time changes, the movement of the target causes it to exceed the monitoring range of the drone. At this time, the tracking range of the drone and the target to be tracked need to be dynamically allocated.

[0027] Furthermore, the number of targets is m; the number of drones in the tracking process is n; wherein m>n≥2; the drone is equipped with a high-definition camera, a lidar and a positioning system; the high-definition camera is used to collect image data during the drone tracking process; the lidar is used to collect point cloud data during the drone tracking process; the positioning system is used to determine the location information of the drone; wherein the image data and point cloud data include the tracked target and the scenery around the target.

[0028] In this embodiment, the UAV captures image data of different bands and resolutions through a high-definition camera, emits a laser beam and receives the reflected signal through a lidar, and determines the distance and position of the target object by calculating the round-trip time of the signal, thereby generating point cloud data; based on the collected image data, the tracked target and the surrounding scenery of the target are extracted, and the extracted features are classified and identified using a CNN neural network to distinguish the tracked target and the surrounding scenery of the target, thereby tracking the target in real time; wherein, m>n≥2, that is, the method considers the situation where a single UAV corresponds to multiple targets.

[0029] S20. Determine the maximum field of view coverage of the UAV according to the clarity of the collected image data; determine the maximum tracking range of the UAV according to the moving speed of the target and the response time of the UAV; wherein the maximum tracking range is within the maximum field of view coverage; determine the change of the flight path of each UAV over time according to the positioning of the UAV, analyze the collected image data and point cloud data, and determine the change of the moving path of each target over time.

[0030] Specifically, the method steps are:

[0031] According to the clarity of the collected image data, determine the maximum field of view coverage S of the drone max , according to the target's moving speed and the drone's response time, determine the drone's maximum tracking range s max ; Among them, s max max ; v max Indicates the maximum moving speed of the target; T indicates the response time of the drone; Indicates the maximum field of view coverage length; Indicates the maximum tracking range length; Maximum field of view coverage width; Maximum tracking range width;

[0032] According to the positioning system of the UAV, the flight path of each UAV is determined as a function of time t, and the obtained ​The collected image data and point cloud data are analyzed to determine the change of the moving path of each target over time t, and the in, and The change of is expressed as the change of the spatial coordinate point in the three-dimensional space model over time t; t represents the timestamp.

[0033] It should be noted that when the number of targets is too large and some targets are offset, the UAV needs to be controlled so that all targets are within the tracking range. Therefore, the three-dimensional space model established by the UAV positioning system is used to determine the position information of each target and each UAV, thereby providing data support for the dynamic coordination of the UAV group and improving the accuracy of data analysis.

[0034] It should be noted that the maximum field of view covers a range S max In order to ensure the clarity of the collected target image, the maximum range that the high-definition camera on the drone can capture; by determining the minimum image clarity of the target, the farthest image data collection distance between the drone and the target is determined, and according to the farthest image data collection distance, the maximum field of view coverage S of the image collected by the drone is obtained. max ; In which, in the embodiment, the influence of other variable conditions such as changes in high-definition camera parameters and obstructions is not considered; the image clarity is judged based on whether the CNN neural network can recognize the target, and the maximum field of view coverage is determined based on the maximum image data acquisition distance threshold at which the CNN neural network can recognize the target.

[0035] It should be noted that the maximum tracking range s max It is used as a trigger condition to determine whether the UAV group needs to be dynamically adjusted. It is determined according to the maximum moving speed of the target. For example, if the target is a wild animal, the maximum moving speed of the wild animal is 10m / s. At this time, the maximum field of view coverage of the UAV is 30m×18m. The process of a dynamic allocation of the UAV is 0.2s. Therefore, the maximum tracking range of the UAV is determined to be 26m×14m. Since the moving path of the target is often difficult to predict, the maximum tracking range s is added. max , when there is a target beyond the tracking range, in order to ensure the clarity of the target image, it is necessary to assign other drones to track the target in real time, so the drone group is triggered to dynamically re-assign the conditions and dynamically assign the targets corresponding to each drone; the maximum tracking range s max It can be manually determined by the administrator or automatically changed by adding a training model. When the target moves too fast, it can reduce the maximum tracking range. max , preventing the target from being lost, thereby improving the robustness of the UAV tracking system.

[0036] S30. Determine the current position information of each target according to the moving path of each target; determine whether it is necessary to dynamically reallocate the target set corresponding to each drone according to the current position information of each target, the target set corresponding to each drone and the maximum tracking range corresponding to the image data collected by each drone; if necessary, execute step S40; if not, execute step S50.

[0037] Specifically, the method steps are:

[0038] according to Determine the current location information of each target Determine the current target set P1, P2, ..., P of each drone n ; Each target has a corresponding drone; according to s max , respectively determine the image location area corresponding to the maximum tracking range of each drone

[0039] Determine the set P i After the spatial coordinate points corresponding to the target position information are connected to each other, the outer edge lines form the image position area corresponding to the graphic according to and Determine whether it is necessary to dynamically redistribute the target sets corresponding to each drone: When , the target set corresponding to each UAV needs to be dynamically reallocated; when there is no When P i represents the target set of the current i-th UAV; Indicates the image location area corresponding to the maximum tracking range of the current i-th drone.

[0040] S40. Based on the current position information of each target and the maximum field of view coverage corresponding to the image data collected by each drone, redetermine the target set of each drone and the image position area corresponding to the maximum tracking range of each drone, and redetermine the number of drones. When the current number of drones is insufficient, increase the number of drones; when the current number of drones is too many, reduce the number of drones; determine the current position information of each drone based on its flight path; control each drone to go to the corresponding tracking position based on the redetermined image position area corresponding to the maximum tracking range of each drone and the current position information of each drone, and execute step S60.

[0041] Specifically, the method steps are:

[0042] According to s max 、smax and Determine the image location area corresponding to the maximum field of view coverage of each drone according to and Re-determine the target set P'1, P'2, ..., P' of each drone h The image location area corresponding to the maximum tracking range of each drone satisfies the following conditions:

[0043]

[0044] Wherein, h represents the number of drones that meet the conditions after redetermination; They respectively represent the number of targets in the target set corresponding to different UAVs after re-determination; represents the empty set; Indicates the current location information of the ath target; represents the current position information of the bth target; a=1, 2, ..., m, b=1, 2, ..., m, and a≠b. When calculating When a and b are in the same target set; L max Indicates the maximum image data distance of the maximum tracking range of the drone in the corresponding image location area; P' i represents the target set corresponding to the i-th UAV after redetermination; Re-determine the set P' i After the spatial coordinate points corresponding to the target position information are connected to each other, the outer edge lines form the image position area corresponding to the graphic; represents the image position area corresponding to the maximum tracking range of the i-th drone after re-determination; i = 1, 2, ..., n;

[0045] Among them, the number of drones is re-determined: when the current number of drones cannot meet the conditions, it is determined that the number of drones is insufficient, and h+1 is set to determine whether the conditions are met again. If not, the number of drones is continuously increased until the conditions are met; when the current number of drones meets the conditions, h-1 is set to determine whether the conditions are met again. If so, the number of drones is continuously reduced until the conditions are not met; thereby, the number of drones that meet the conditions after re-determination is minimized;

[0046] according to Determine the image location area corresponding to the maximum tracking range of each drone after redefinition According to P'1, P'2, ..., P' h , respectively determine the targets corresponding to each UAV after redetermination;

[0047] Determine the location information that each drone needs to go to based on the image position area corresponding to the re-determined maximum tracking range of each drone; control each drone to go to the corresponding tracking position based on the location information that each drone needs to go to and the current location information of each drone: calculate the moving distance of each drone from the current location information to the location information that it needs to go to based on the location information that each drone needs to go to and the current location information of each drone and make Satisfying the condition formula: Among them, L z Represents the total moving distance of n drones from their current location to the desired location; It represents the moving distance of the i-th UAV from its current position to the desired position.

[0048] It should be noted that the states of drones are divided into mission drones that are performing tracking tasks and idle drones that have no tracking tasks. All drones mentioned in this method are mission drones. Through h, the target set of each drone that meets the conditions and the corresponding area of ​​the maximum tracking range of each drone are continuously calculated. When h does not meet the conditions, let h+1, that is, change the state of an idle drone to a mission drone, and judge again whether the conditions are met, so that the image position area corresponding to the re-determined graphic is within the maximum tracking range; when h meets the conditions, let h-1, that is, change the state of a mission drone to an idle drone, and judge again whether the conditions are met, so that the image position area corresponding to the re-determined graphic is within the maximum tracking range; until the minimum number of mission drones that meet the conditions is found, the corresponding h is determined at this time, and the target set of each drone and the corresponding area of ​​the maximum tracking range of each drone are obtained.

[0049] It should be noted that and L max When making comparison, a and b need to be in the same target set. The area corresponding to the maximum field of view coverage of the drone is determined, and the maximum image data distance is determined based on the area; the maximum image data distance represents the distance between the two farthest spatial coordinate points within the maximum tracking range.

[0050] It should be noted that, through the above conditions, fewer drones are used to track the target in real time. When the number of drones in the current tracking state is insufficient, the number of drones is added one by one, and the targets corresponding to each drone are dynamically allocated. Fewer drones are used to track the target, thereby improving the efficiency of drone tracking management.

[0051] In this embodiment, when each drone tracks the target in real time, the collected image data always remains within the maximum field of view coverage; the maximum field of view coverage of the image data collected by each drone is the same and fixed; the maximum tracking range of each drone in the three-dimensional space model is the same and fixed; Figure 1 As shown, the corresponding maximum field of view coverage S max The image pixel size is 1920×1080 pixels, corresponding to the maximum tracking range s max The image pixel size is 1620×780 pixels; at this time L max The distance is s max The image diagonal connection distance corresponds to the distance in the maximum tracking range of the three-dimensional space model.

[0052] It should be noted that since this method takes into account the image clarity of the UAV, that is, the image data collected by the UAV within the maximum field of view coverage, when the maximum field of view coverage and the maximum tracking range of the UAV are determined, each UAV’s maximum tracking range has corresponding three-dimensional space model position information, that is, the spatial coordinate point corresponding to the position. At this time, according to the determined position information that the UAV needs to go to, combined with the current UAV position information, the UAV is controlled to go to the corresponding position.

[0053] It should be noted that by determining the target set of each drone and the corresponding area of ​​the maximum tracking range of each drone, the tracking movement of each drone is dynamically allocated according to the location information of each drone to be reached and the current location information of each drone, so that the total moving distance of each drone from the current position to the required position is shortest, thereby improving the tracking efficiency.

[0054] S50, control each drone to be in a hovering state, and execute step S60.

[0055] S60, repeating steps S30-S50 until the target tracking is completed and each UAV is controlled to return.

[0056] In this embodiment, if there is no The drone is always in hovering state. When the UAV group is triggered to dynamically reassign the conditions, The collected image data is re-analyzed, and each drone is controlled to go to the corresponding tracking area until the management personnel determines that the drone tracking task is completed. At this time, each drone is controlled to return and the status of each drone is changed to an idle drone.

[0057] It should be noted that when the target is beyond the range of the image data collected by the drone, it is easy to cause the target to be lost. It is difficult to plan the drone tracking in advance in the existing technology. max , when the target exceeds s maxWhen the target is within the range of S, the conditions for the dynamic redistribution of the drone group are triggered. max The corresponding image range can therefore be used to track and control the drone group in advance based on the target’s location information, thereby improving the robustness of the system.

[0058] See also Figure 2 , in this implementation 2: a coordinated control system for a drone group based on data analysis is provided, the system comprising a task planning control module, a data acquisition module, a three-dimensional model management module, an intelligent judgment module, an intelligent analysis and calculation module, and an intelligent tracking control module;

[0059] The mission planning control module is used to determine the target to be tracked, determine the target to be tracked and the target set of the drone, control several drones to respectively track the targets of their respective target sets in real time, and send data acquisition signals to the data acquisition module;

[0060] The data acquisition module is used to collect image data and point cloud data during the UAV tracking process, and send the collected data to the three-dimensional model management module;

[0061] The three-dimensional model management module is used to establish a three-dimensional space model, determine the maximum field of view coverage of the drone according to the clarity of the collected image data; determine the maximum tracking range of the drone according to the moving speed of the target and the response time of the drone; wherein the maximum tracking range is within the maximum field of view coverage; determine the change of the flight path of each drone over time according to the positioning of the drone, analyze the collected image data and point cloud data, and determine the change of the moving path of each target over time;

[0062] The intelligent judgment module is used to determine the current position information of each target according to the moving path of each target; determine whether it is necessary to dynamically reallocate the target set corresponding to each drone according to the current position information of each target, the target set corresponding to each drone and the maximum tracking range corresponding to the current image data collected by each drone; if it is necessary to dynamically reallocate the targets corresponding to each drone, send the dynamic reallocation signal to the intelligent analysis and calculation module; if it is not necessary to dynamically reallocate the targets corresponding to each drone, send the signal that does not need to be dynamically reallocated to the intelligent tracking control module;

[0063] The intelligent analysis and calculation module is used to re-determine the target set of each drone and the image position area corresponding to the maximum tracking range of each drone according to the current position information of each target and the maximum field of view coverage corresponding to the image data collected by each drone, and re-determine the number of drones. When the current number of drones is insufficient, the number of drones is increased; when the current number of drones is too large, the number of drones is reduced and sent to the intelligent tracking control module;

[0064] The intelligent tracking control module is used to determine the current position information of each drone according to the flight path of each drone when it is necessary to dynamically redistribute the target set corresponding to each drone; control each drone to go to the corresponding tracking position according to the image position area corresponding to the redetermined maximum tracking range of each drone and the current position information of each drone; and control each drone to be in a hovering state when it is not necessary to dynamically redistribute the target set corresponding to each drone.

[0065] In this embodiment:

[0066] The task planning control module is interconnected with the data acquisition module; the data acquisition module is interconnected with the three-dimensional model management module; the three-dimensional model management module is interconnected with the intelligent judgment module; the intelligent judgment module is interconnected with the intelligent analysis and calculation module; the intelligent judgment module is interconnected with the intelligent tracking control module; the intelligent analysis and calculation module is interconnected with the intelligent tracking control module.

[0067] Finally, it should be noted that the above is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A coordinated control method for a drone group based on data analysis, characterized in that: The method comprises the following steps: S10, establishing a three-dimensional space model, determining the target to be tracked and the target set of the drone, controlling several drones to respectively track the targets of their respective target sets in real time; collecting image data and point cloud data of each drone during the tracking process; S20, determining the maximum field of view coverage of the drone according to the clarity of the collected image data; determining the maximum tracking range of the drone according to the moving speed of the target and the response time of the drone; wherein the maximum tracking range is within the maximum field of view coverage; determining the change of the flight path of each drone over time according to the positioning of the drone, analyzing the collected image data and point cloud data, and determining the change of the moving path of each target over time; S30, according to the moving paths of the targets, respectively determine the current position information of the targets; according to the current position information of the targets, the target sets corresponding to the current drones and the maximum tracking range corresponding to the image data collected by the current drones, determine whether it is necessary to dynamically reallocate the target sets corresponding to the drones; if necessary, execute step S40; if not, execute step S50; S40, based on the current position information of each target and the maximum field of view coverage corresponding to the image data collected by each drone, re-determine the target set of each drone and the image position area corresponding to the maximum tracking range of each drone, and re-determine the number of drones. When the current number of drones is insufficient, increase the number of drones; when the current number of drones is too large, reduce the number of drones; determine the current position information of each drone according to the flight path of each drone; control each drone to go to the corresponding tracking position according to the re-determined image position area corresponding to the maximum tracking range of each drone and the current position information of each drone, and execute step S60; S50, control each drone to be in a hovering state, and execute step S60; S60, repeating steps S30-S50 until the target tracking is completed and each UAV is controlled to return.

2. The coordinated control method of a drone group based on data analysis according to claim 1 is characterized in that: The number of targets is m; the number of drones in the tracking process is n; wherein m>n≥2; the drone is equipped with a high-definition camera, a laser radar and a positioning system; the high-definition camera is used to collect image data during the drone tracking process; the laser radar is used to collect point cloud data during the drone tracking process; the positioning system is used to determine the location information of the drone; wherein the image data and point cloud data contain the tracked target and the scenery around the target.

3. The coordinated control method of a drone group based on data analysis according to claim 2 is characterized in that: The method steps of step S20 are: S201. Determine the maximum field of view coverage of the drone based on the clarity of the collected image data S max , according to the target's moving speed and the drone's response time, determine the drone's maximum tracking range s max ; Among them, s max <S max ; v max Indicates the maximum moving speed of the target; T indicates the response time of the drone; Indicates the maximum field of view coverage length; Indicates the maximum tracking range length; Maximum field of view coverage width; Maximum tracking range width; S202: According to the positioning system of the UAV, the flight path of each UAV is determined at any time, and the change of t is obtained. The collected image data and point cloud data are analyzed to determine the change of the moving path of each target over time t, and the in, and The change of is expressed as the change of the spatial coordinate point in the three-dimensional space model over time t; t represents the timestamp.

4. The coordinated control method of a drone group based on data analysis according to claim 3 is characterized in that: The method steps of step S30 are: S301, according to Determine the current location information of each target Determine the current target set P1, P2, ..., P of each drone n ; Each target has a corresponding drone; according to s max , respectively determine the image location area corresponding to the maximum tracking range of each drone S302, determine the set P i After the spatial coordinate points corresponding to the target position information are connected to each other, the outer edge lines form the image position area corresponding to the graphic according to and Determine whether it is necessary to dynamically redistribute the target sets corresponding to each drone: When , the target set corresponding to each UAV needs to be dynamically reallocated; when there is no When P i represents the target set of the current i-th UAV; Indicates the image location area corresponding to the maximum tracking range of the current i-th drone.

5. The coordinated control method of a drone group based on data analysis according to claim 4 is characterized in that: The method steps of step S40 are: S401, according to S max 、s max and Determine the image location area corresponding to the maximum field of view coverage of each drone according to and Re-determine the target set P'1, P'2, ..., P' of each drone h The image location area corresponding to the maximum tracking range of each drone satisfies the following conditions: Wherein, h represents the number of drones that meet the conditions after redetermination; They respectively represent the number of targets in the target set corresponding to different UAVs after re-determination; represents the empty set; Indicates the current location information of the ath target; represents the current position information of the bth target; a=1, 2, ..., m, b=1, 2, ..., m, and a≠b. When calculating When a and b are in the same target set; L max Indicates the maximum image data distance of the maximum tracking range of the drone in the corresponding image location area; P' i represents the target set corresponding to the i-th UAV after redetermination; Re-determine the set P' i After the spatial coordinate points corresponding to the target position information are connected to each other, the outer edge lines form the image position area corresponding to the graphic; represents the image position area corresponding to the maximum tracking range of the i-th drone after re-determination; i = 1, 2, ..., n; Among them, the number of drones is re-determined: when the current number of drones cannot meet the conditions, it is determined that the number of drones is insufficient, and h+1 is set to determine whether the conditions are met again. If not, the number of drones is continuously increased until the conditions are met; when the current number of drones meets the conditions, h-1 is set to determine whether the conditions are met again. If so, the number of drones is continuously reduced until the conditions are not met; thereby, the number of drones that meet the conditions after re-determination is minimized; S402, according to Determine the image location area corresponding to the maximum tracking range of each drone after redefinition According to P'1, P'2, ..., P h , respectively determine the targets corresponding to each UAV after redetermination; S403, determine the location information that each drone needs to go to based on the image position area corresponding to the re-determined maximum tracking range of each drone; control each drone to go to the corresponding tracking position based on the location information that each drone needs to go to and the current location information of each drone; calculate the moving distance of each drone from the current location information to the location information that it needs to go to based on the location information that each drone needs to go to and the current location information of each drone and make Satisfying the condition formula: Among them, L z It represents the total moving distance of n drones from their current location to the desired location; It represents the moving distance of the i-th UAV from its current position to the desired position.

6. A coordinated control system for drone groups based on data analysis, characterized by: The system includes a task planning control module, a data acquisition module, a three-dimensional model management module, an intelligent judgment module, an intelligent analysis and calculation module, and an intelligent tracking control module; The mission planning control module is used to determine the target to be tracked, determine the target to be tracked and the target set of the drone, control several drones to respectively track the targets of their respective target sets in real time, and send data acquisition signals to the data acquisition module; The data acquisition module is used to collect image data and point cloud data during the UAV tracking process, and send the collected data to the three-dimensional model management module; The three-dimensional model management module is used to establish a three-dimensional space model, determine the maximum field of view coverage of the drone according to the clarity of the collected image data; determine the maximum tracking range of the drone according to the moving speed of the target and the response time of the drone; wherein the maximum tracking range is within the maximum field of view coverage; determine the change of the flight path of each drone over time according to the positioning of the drone, analyze the collected image data and point cloud data, and determine the change of the moving path of each target over time; The intelligent judgment module is used to determine the current position information of each target according to the moving path of each target; determine whether it is necessary to dynamically reallocate the target set corresponding to each drone according to the current position information of each target, the target set corresponding to each drone and the maximum tracking range corresponding to the current image data collected by each drone; if it is necessary to dynamically reallocate the targets corresponding to each drone, send the dynamic reallocation signal to the intelligent analysis and calculation module; if it is not necessary to dynamically reallocate the targets corresponding to each drone, send the signal that does not need to be dynamically reallocated to the intelligent tracking control module; The intelligent analysis and calculation module is used to re-determine the target set of each drone and the image position area corresponding to the maximum tracking range of each drone according to the current position information of each target and the maximum field of view coverage corresponding to the image data collected by each drone, and re-determine the number of drones. When the current number of drones is insufficient, the number of drones is increased; when the current number of drones is too large, the number of drones is reduced and sent to the intelligent tracking control module; The intelligent tracking control module is used to determine the current position information of each drone according to the flight path of each drone when it is necessary to dynamically redistribute the target set corresponding to each drone; control each drone to go to the corresponding tracking position according to the image position area corresponding to the redetermined maximum tracking range of each drone and the current position information of each drone; and control each drone to be in a hovering state when it is not necessary to dynamically redistribute the target set corresponding to each drone.

Images