Third-person unmanned aerial vehicle environment sensing system and unmanned aerial vehicle control method

Abstract

The invention relates to a third-person unmanned aerial vehicle environment perception system and an unmanned aerial vehicle control method, and the method comprises the steps that a data processing module carries out the alignment and feature extraction of flight state data and a preset model, and generates a semantic three-dimensional scene model; obtaining a global three-dimensional map; and the visualization module renders the global three-dimensional map to generate an operation interface of a third-person view angle. The flight state data and a preset model are subjected to alignment and feature extraction through the data processing module, a semantic three-dimensional scene model is obtained, the three-dimensional scene model is converted into a real-time updated global three-dimensional map through the sensing module, and therefore the accuracy of an environment model is improved; the global three-dimensional map is rendered through the visualization module, an operation interface of a third-person view angle is generated, deep interaction between the unmanned aerial vehicle and environment information is achieved, an interaction mode of the third-person view angle is provided, and therefore the control precision of the unmanned aerial vehicle in the dynamic environment is remarkably improved, and wide applicability is achieved.

Description

Technical Field

[0001] The present application relates to the field of drone technology, and in particular to a third-person drone environment perception system and a drone control method. Background Art

[0002] Existing drones mostly rely on a single sensor or limited data source, resulting in an incomplete perception of the surrounding environment in complex environments, and unable to generate accurate environmental models in real time; data fusion and visualization capabilities are weak, affecting the decision-making efficiency of operators. The control methods of drones mostly rely on simple two-dimensional interfaces, which makes it difficult to achieve deep interaction with environmental information and lacks intuitive interaction capabilities for third-person perspectives, resulting in insufficient control accuracy in dynamic environments.

[0003] It should be noted that the above introduction to the technical background is only for the convenience of providing a clear and complete description of the technical solutions of the present application and for the convenience of understanding by those skilled in the art. It cannot be considered that the above technical solutions are well known to those skilled in the art simply because they are described in the background technology section of the present application. Summary of the invention

[0004] The purpose of this application is to provide a third-person UAV environment perception system and a UAV control method to solve the problems in the prior art of inaccurate environmental models, weak data fusion and visualization capabilities, and lack of intuitive interaction capabilities for a third-person perspective in achieving deep interaction with environmental information.

[0005] In order to solve the above problems, a third-person drone environment perception system involved in this application adopts the following technical solutions: The third-person UAV environment perception system includes: a data acquisition module, a data processing module, a perception module, a visualization module and a control module, wherein: The data acquisition module collects the flight status data of the UAV; The data processing module is connected to the data acquisition module to align and extract features of the flight status data with the preset model to generate a semantic three-dimensional scene model; The perception module is connected to the data processing module to convert the three-dimensional scene model into a global three-dimensional map updated in real time; The visualization module is connected to the perception module to render the global three-dimensional map and generate an operation interface from a third-person perspective; The control module is connected with the visualization module and the data acquisition module to perform real-time control on the UAV.

[0006] In order to solve the above problems, a drone control method involved in the present application is applicable to the third-person drone environment perception system involved in the present application. The drone control method adopts the following technical solutions: Get the flight status data of the drone; Determine a semantic three-dimensional scene model according to the preset model and the flight status data; The three-dimensional scene model is converted into a global three-dimensional map that is updated in real time, and the drone is controlled in real time from a third-person perspective based on the global three-dimensional map.

[0007] In order to solve the above problems, an electronic device involved in the present application includes: a processor; a memory for storing instructions executable by the processor; wherein the processor is configured to execute the instructions to implement the drone control method involved in the present application.

[0008] In order to solve the above problems, the present application involves a non-temporary computer-readable storage medium. When the instructions in the storage medium are executed by a processor of an electronic device, the electronic device can execute the drone control method involved in the present application.

[0009] In order to solve the above-mentioned problem, the present application involves a computer program product, including a computer program, which implements the drone control method involved in the present application when executed by a processor in a communication device.

[0010] The beneficial effects of this application are as follows: The flight status data is aligned and features are extracted with the preset model through the data processing module to obtain a semantic three-dimensional scene model, and the three-dimensional scene model is converted into a real-time updated global three-dimensional map through the perception module, thereby improving the accuracy of the environmental model; the global three-dimensional map is rendered through the visualization module to generate a third-person perspective operation interface, realizing deep interaction between the UAV and environmental information, and providing a third-person perspective interaction method, thereby significantly improving the control accuracy of the UAV in a dynamic environment and having wide applicability. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solution of the embodiment of the present application, the following is a brief introduction to the drawings required for use in the embodiment: Figure 1 A schematic diagram of the structure of a third-person drone environment perception system provided in an embodiment of the present application; Figure 2 A schematic diagram of the structure of a data processing module provided according to an embodiment of the present application; Figure 3 A schematic diagram of the structure of a perception module provided according to an embodiment of the present application; Figure 4 A schematic diagram of the structure of a visualization module provided according to an embodiment of the present application; Figure 5 A schematic diagram of the structure of a control module provided according to an embodiment of the present application; Figure 6 A flowchart of a drone control method provided in an embodiment of the present application; Figure 7 The present invention is a schematic diagram of the structure of an electronic device provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0012] In order to make the technical purpose, technical solution and beneficial effects of the present application clearer, the technical solution of the present application is further described below in conjunction with the drawings and specific embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application, that is, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various different configurations.

[0013] The terms used in the embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to limit the embodiments of the present application. The singular forms of "a" and "the" used in the embodiments of the present application and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more associated listed items.

[0014] It should be understood that, although the terms first, second, third, etc. may be used to describe various information in the embodiments of the present application, these information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of the embodiments of the present application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the words "if" and "if" as used herein may be interpreted as "at..." or "when..." or "in response to determination".

[0015] The embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0016] It should be noted that the method provided in any embodiment of the present application can be executed alone, or can be executed in combination with possible implementation methods in other embodiments, or can be executed in combination with any technical solution in the related technology.

[0017] Traditional drones mostly rely on a single sensor or limited data source, resulting in insufficient comprehensiveness and accuracy of data, which is prone to misunderstanding or misjudgment, especially in complex scenarios. Traditional drones are mainly based on two-dimensional interfaces or first-person perspectives (First-Person View, or FPV, is a flight experience that uses video signals transmitted in real time by a high-definition camera on the drone to observe and control the surrounding environment). They lack a comprehensive perception of the relationship between the drone and the surrounding environment, which affects the operator's judgment and reaction ability in complex scenarios. In a dynamic environment, it is difficult for traditional drones to achieve real-time synchronization updates with the scene, which may affect the efficiency and safety of mission execution after the control response; and in a dynamic environment, the operation of drones needs to rely solely on offline processing and professional hardware equipment as support, resulting in high development costs and unable to meet the needs of flexible and rapid deployment.

[0018] The third-person drone environment perception system of an embodiment of the present application is described below with reference to the accompanying drawings.

[0019] Figure 1 A schematic diagram of the structure of a third-person drone environment perception system provided in an embodiment of the present application. It should be noted that a drone with a third-person perspective (3PV) refers to a drone that transmits the captured images to the operator in real time through a camera or sensor mounted on the drone, so that the operator can observe the flight status and surrounding environment of the drone from an external perspective.

[0020] like Figure 1As shown, the third-person UAV environment perception system includes but is not limited to: a data acquisition module, a data processing module, a perception module, a visualization module and a control module, wherein: the data acquisition module collects the flight status data of the UAV, including the obstacle distance, shape, position, terrain height, terrain texture, image data of buildings, maximum pitch angle, yaw angle, roll angle, etc. in the flight environment, to provide data support for the flight decision, control and analysis of the UAV. The data processing module is connected to the data acquisition module, aligns and extracts features of the flight status data with the preset model, and generates a semantic three-dimensional scene model. In the semantic three-dimensional scene model, each object or area is given a clear semantic label, so as to realize the semantic understanding and interpretation of the scene. The perception module is connected to the data processing module. The three-dimensional scene model may include point cloud data, mesh model, texture information, etc. In order to improve the real-time performance of the three-dimensional scene model, the three-dimensional scene model is converted into a real-time updated global three-dimensional map. The global three-dimensional map may include terrain information, building information, road information, obstacle information, etc., which can be represented on the map in different colors, textures, heights, etc. The visualization module is connected to the perception module, and generates a third-person perspective operation interface by rendering the global three-dimensional map, that is, providing an interactive third-person perspective to display the real-time position and status of the drone relative to the environment. The control module is connected to the visualization module and the data acquisition module to control the drone in real time. For example, it can perform flight simulation training on the drone, plan and dynamically control the drone's mission, and realize the release and feedback of drone control instructions.

[0021] Alternatively, if Figure 1 As shown, as an example, the data acquisition module includes a laser radar, a depth camera, a building information model library and a sensor network, wherein the laser radar can sense changes in the surrounding environment, accurately measure the distance and angle of the target object, provide high-precision three-dimensional data, and build a three-dimensional model of the target object; the depth camera can identify and track the position and motion trajectory of the object in three-dimensional space, and provide support for interaction and navigation; the building information model library is a digital building information model, which contains the geometric information, physical information, functional information and management information of the building; the sensor network includes a global positioning system, an inertial measurement unit, etc., which collects the longitude, latitude, altitude, speed, timestamp, acceleration, angular velocity, attitude angle (pitch angle, yaw angle, roll angle), etc. of the drone. At the same time, the sensor network can also fuse all the data through Kalman filtering, complementary filtering, etc., so as to obtain more accurate and reliable flight status data.

[0022] Alternatively, as an example, Figure 2 Schematic diagram of the structure of the data processing module provided according to the embodiment of the present application. Figure 2As shown, the data processing module includes a point cloud registration unit, a semantic mapping unit and a feature extraction unit, wherein the point cloud registration unit is connected to the data acquisition module. In this embodiment, the point cloud registration unit is connected to the laser radar and the depth camera, and the point cloud data (point cloud data refers to a set of vectors in a three-dimensional coordinate system, these vectors are usually recorded in the form of points, and each point contains three-dimensional coordinate data. Point cloud data is usually obtained by various spatial detection and measurement equipment) from different sources or different positions or different times in the flight status data are converted to the same coordinate system through a certain algorithm. For example, the iterative closest point algorithm (Iterative Closest Point, referred to as ICP) can be used to align the point cloud data with the building information model library. The semantic mapping unit is connected to the point cloud registration unit and the data acquisition module to fuse the data in the building information model data (such as building categories, etc.) with the point cloud data. For example, the data in the building information model data and the points or regions in the point cloud data are managed according to information such as spatial position and geometric shape; the semantic information in the building information model data (such as building categories, building functions, etc.) is annotated to the corresponding point cloud data; and then the annotated point cloud data is combined with the original geometric information to form a three-dimensional point cloud model with rich semantic information. The feature extraction unit is connected to the semantic mapping unit to perform data enhancement on the output of the semantic mapping unit (such as a three-dimensional point cloud model). For example, feature extraction can be performed in a video stream enhancement manner to generate a semantic three-dimensional scene model.

[0023] Alternatively, as an example, Figure 3 FIG. 1 is a schematic diagram of the structure of a perception module provided according to an embodiment of the present application. Figure 3 As shown, the perception module includes a 3D map generation unit, a noise filtering unit and an incremental modeling unit, wherein the 3D map generation unit is connected to the data processing module and receives data from the data processing module, which has been preprocessed and integrated; then the 3D map generation unit maps the received data into a 3D space, and in this process, various algorithms and technologies may be required, such as a height map generation algorithm and a texture mapping algorithm, to ensure the accuracy and realism of the generated primary 3D map. The noise filtering unit is connected to the 3D map generation unit, and the incremental modeling unit is connected to the noise filtering unit. By updating the environmental data in real time, noise filtering and incremental modeling are performed in a dynamic environment to ensure the real-time and stability of the acquired global 3D map.

[0024] Alternatively, as an example, Figure 4 FIG. 1 is a schematic diagram of the structure of a visualization module provided according to an embodiment of the present application. Figure 4As shown in FIG. 1 , the visualization module includes an interactive scene construction unit, a three-dimensional earth image generation unit, and an interface generation unit. The interactive scene construction unit is connected to the perception module and is responsible for constructing and understanding the scene based on the data provided by the perception module. For example, data from different sources can be integrated to improve the accuracy and reliability of the data. Machine learning, deep learning, Unreal Engine 5 and other rendering technologies can also be used to process and analyze the integrated data and the reverse process to understand the structure of the scene, the location and attributes of objects, and the relationship between them. Then, based on the results of scene understanding, interactive strategies are formulated. The three-dimensional earth image generation unit is connected to the perception module to render the global three-dimensional map. The rendering process includes operations such as lighting processing, shadow processing, and anti-aliasing processing to improve the rendering effect and user experience. The interface generation unit is connected with the interactive scene construction unit and the three-dimensional earth image generation unit to generate an operation interface from a third-person perspective, wherein the operation interface allows the user to browse the three-dimensional earth image from different angles; provides perspective adjustment tools, such as zooming, panning and rotating, to meet the personalized needs of users; integrates the functions of the interactive scene construction unit to allow the user to perform operations such as annotation, query and analysis on the three-dimensional earth image, and provides feedback mechanisms, such as highlighting, pop-up windows, etc., to enhance the user's interactive experience.

[0025] Alternatively, as an example, Figure 5 Schematic diagram of the structure of the control module provided according to the embodiment of the present application. Figure 5 As shown, the control module includes a simulation unit, an instruction generation unit and a communication unit, wherein the simulation unit is connected to the visualization module to simulate the flight mission, and can interact with the simulation process through the interface, such as adjusting flight parameters, observing different perspectives, etc.; intuitive user interfaces and interaction methods can be designed, such as touch screens, virtual reality helmets, etc. The instruction generation unit is connected to the visualization module to issue drone control instructions in real time, wherein the instruction generation unit generates corresponding drone control instructions based on the output of the visualization module, and these instructions include take-off, landing, hovering, flight path planning, control of the data acquisition module, etc.; the generated instructions are sent to the drone in real time through the data interface and communication protocol, and the drone parses and executes the corresponding actions after receiving the instructions. The communication unit is connected to the instruction generation unit and the data acquisition module to synchronize the flight parameters of the drone with the flight status data, and the remote monitoring and management of the drone is realized by synchronizing the flight parameters and flight status data of the drone in real time. Furthermore, the communication unit uses the MAVLink communication protocol for data synchronization, and can also use the SimpleRTK2B communication protocol for data synchronization. The appropriate communication protocol should be selected according to actual needs.

[0026] It should be noted that the third-person UAV environment perception system can also be set up by using application-specific integrated circuits (the full name of which is Application Specific Integrated Circuit, or ASIC for short. ASIC is an integrated circuit of a proprietary application designed and manufactured for specific user requirements and specific systems. In this embodiment, the integrated circuit is characterized by a stability detection circuit), IP cores (the full name of which is intellectual property core. IP cores are mature designs of circuit modules with independent functions in chip or integrated circuit design. The circuit design can be applied to other chip or integrated circuit design projects containing the circuit module, thereby reducing the design workload, shortening the design cycle, and improving the success rate of chip or integrated circuit design. IP cores are classified into three levels: behavioral level, structural level, and physical level, and thus correspond to three types of IP cores, which have soft cores designed with hardware description language, solid cores that complete structural description, and hard cores based on physical description and process verification. The specific setting forms will not be described one by one here. As long as a semantic three-dimensional scene model can be generated, and an operation interface from a third-person perspective can be generated according to the semantic three-dimensional scene model, and then the UAV can be controlled in real time according to the operation interface from the third-person perspective, any third-person UAV environment perception system is applicable, and is not limited to this embodiment.

[0027] Figure 6 A flowchart of a drone control method provided in an embodiment of the present application.

[0028] like Figure 4 As shown, the drone control method is applicable to the third-person drone environment perception system provided in the application embodiment, and the drone control method includes but is not limited to the following steps: S601, obtaining the flight status data of the UAV.

[0029] For further details of step S601, please refer to the relevant contents in the above embodiment, which will not be repeated here.

[0030] S602: Determine a semantic three-dimensional scene model according to a preset model and flight status data.

[0031] In a feasible implementation manner, the three-dimensional scene model is obtained by geometrically aligning, fusing and enhancing the flight status data with a preset model.

[0032] S403, converting the three-dimensional scene model into a global three-dimensional map that is updated in real time, and controlling the drone in real time from a third-person perspective based on the global three-dimensional map.

[0033] In a feasible implementation, a global three-dimensional map is rendered and an interactive scene is constructed, an operation interface of a third-person perspective is determined, and the drone is controlled in real time based on the operation interface.

[0034] Furthermore, the global three-dimensional map is rendered to determine an operation interface from a third-person perspective; based on the operation interface, the flight mission is simulated, the UAV control instructions are issued in real time, and the flight parameters of the UAV are synchronized with the flight status data.

[0035] Therefore, by generating an operating interface from a third-person perspective, an intuitive and clear environmental visualization interface is provided; the limitations of the traditional first-person or simple overhead perspective are changed; efficient operation of the UAV in a dynamic and complex environment is achieved; and the efficiency of the UAV in performing tasks is significantly improved.

[0036] In summary, the third-person UAV environment perception system and UAV control method of the embodiments of the present application align and extract features of flight status data with a preset model through a data processing module to obtain a semantic three-dimensional scene model, and convert the three-dimensional scene model into a real-time updated global three-dimensional map through a perception module, thereby improving the accuracy of the environmental model; the global three-dimensional map is rendered through a visualization module to generate an operating interface from a third-person perspective, thereby achieving deep interaction between the UAV and environmental information, and providing an interactive method from a third-person perspective, thereby significantly improving the control accuracy of the UAV in a dynamic environment and having wide applicability.

[0037] Figure 7 The present invention is a schematic diagram of the structure of an electronic device provided according to an embodiment of the present application. Figure 7 The electronic device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0038] like Figure 7 As shown, the electronic device 700 includes a processor 701, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 702 or a program loaded from a memory 706 to a random access memory (RAM) 703. Various programs and data required for the operation of the electronic device 700 are also stored in the RAM 703. The processor 701, the ROM 702, and the RAM 703 are connected to each other via a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0039] The following components are connected to the I / O interface 705: a memory 706 including a hard disk, etc.; and a communication part 707 including a network interface card such as a LAN (Local Area Network) card, a modem, etc., and the communication part 707 performs communication processing via a network such as the Internet; a drive 708 is also connected to the I / O interface 705 as needed.

[0040] In particular, according to an embodiment of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 707. When the computer program is executed by the processor 701, the above-mentioned functions defined in the method of the present application are executed.

[0041] In an exemplary embodiment, a storage medium including instructions is also provided, such as a memory including instructions, and the instructions can be executed by the processor 701 of the electronic device 700 to complete the above method. Optionally, the storage medium can be a non-transitory computer-readable storage medium, for example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0042] In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, apparatus, or device. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in combination with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium may be transmitted using any suitable medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0043] Finally, it should be noted that the above embodiments are only used to illustrate but not limit the technical solutions of the present application. Any equivalent substitutions of the present application and any modifications or partial substitutions that do not depart from the spirit and scope of the present application shall be included in the scope of protection of the claims of the present application.

Claims

1. A third-person drone environment perception system, characterized in that: The third-person UAV environment perception system includes: a data acquisition module, a data processing module, a perception module, a visualization module and a control module, wherein: The data acquisition module collects the flight status data of the UAV; The data processing module is connected to the data acquisition module to align and extract features of the flight status data with the preset model to generate a semantic three-dimensional scene model; The perception module is connected to the data processing module to convert the three-dimensional scene model into a global three-dimensional map updated in real time; The visualization module is connected to the perception module to render the global three-dimensional map and generate an operation interface from a third-person perspective; The control module is connected with the visualization module and the data acquisition module to perform real-time control on the UAV.

2. The third-person drone environment perception system according to claim 1, characterized in that: The data acquisition module includes a laser radar, a depth camera, a building information model library and a sensor network.

3. The third-person drone environment perception system according to claim 1, characterized in that: The data processing module includes a point cloud registration unit, a semantic mapping unit and a feature extraction unit, wherein the point cloud registration unit is connected to the data acquisition module to align the flight status data; the semantic mapping unit is connected to the point cloud registration unit and the data acquisition module to fuse the building information model data with the point cloud data; the feature extraction unit and the semantic mapping unit perform data enhancement on the output of the semantic mapping unit to obtain a semantic three-dimensional scene model.

4. The third-person drone environment perception system according to claim 1, characterized in that: The perception module includes a three-dimensional map generation unit, a noise filtering unit and an incremental modeling unit, wherein the three-dimensional map generation unit is connected to the data processing module to generate a primary three-dimensional map; the noise filtering unit is connected to the three-dimensional map generation unit; the incremental modeling unit is connected to the noise filtering unit to perform incremental three-dimensional modeling in a dynamic environment to obtain the global three-dimensional map.

5. The third-person drone environment perception system according to claim 1, characterized in that: The visualization module includes an interactive scene construction unit, a three-dimensional earth image generation unit and an interface generation unit, wherein the interactive scene construction unit is connected to the perception module; the three-dimensional earth image generation unit is connected to the perception module to render the global three-dimensional map; the interface generation unit is connected to the interactive scene construction unit and the three-dimensional earth image generation unit to generate an operation interface from a third-person perspective.

6. The third-person drone environment perception system according to claim 1, characterized in that: The control module includes a simulation unit, an instruction generation unit and a communication unit, wherein the simulation unit is connected to the visualization module to simulate the flight mission; the instruction generation unit is connected to the visualization module to issue UAV control instructions in real time; the communication unit is connected to the instruction generation unit and the data acquisition module to synchronize the flight parameters of the UAV with the flight status data.

7. The third-person drone environment perception system according to claim 1, characterized in that: The communication unit uses the MAVLink communication protocol for data synchronization.

8. A method for controlling a drone, characterized in that: Applicable to the third-person drone environment perception system according to any one of claims 1 to 7, the method comprising: Get the flight status data of the drone; Determine a semantic three-dimensional scene model according to the preset model and the flight status data; The three-dimensional scene model is converted into a global three-dimensional map that is updated in real time, and the drone is controlled in real time from a third-person perspective based on the global three-dimensional map.

9. The method according to claim 8, characterized in that The determining of the semantic three-dimensional scene model according to the preset model and the flight status data includes: The flight status data is geometrically aligned with a preset model, data is fused, and data is enhanced to obtain the three-dimensional scene model.

10. The method according to claim 9, characterized in that The real-time control of the drone from a third-person perspective according to the global three-dimensional map includes: The global three-dimensional map is rendered and an interactive scene is constructed, an operation interface of a third-person perspective is determined, and the drone is controlled in real time according to the operation interface.

Images