Landing positioning method, device, storage medium and drone nest for unmanned aerial vehicle

Abstract

The embodiment of the present application discloses a landing positioning method, device, storage medium and drone nest of a drone. The method includes: during the landing process of the drone, when the drone enters the scanning range of the laser radar set in the drone nest, the drone is scanned by the laser radar to obtain a point cloud image, the current posture of the drone is estimated according to the point cloud data, and the posture correction parameters between the current posture and the target posture are compared. The drone nest instructs the drone to perform posture correction according to the posture correction parameters, and the drone can be controlled to land smoothly on the drone nest. There is no need to set up an inertial measurement unit inside the drone, which reduces the hardware cost and weight of the drone.

Description

Technical Field

[0001] The present application relates to the field of positioning, and in particular to a method, device, storage medium and drone nest for landing positioning of a drone. Background Art

[0002] With the widespread application of drones in various industries, based on the different needs of different industries, drones also need better performance in terms of flight speed, energy consumption and positioning accuracy to adapt to the needs of various industries.

[0003] The drone nest is the platform for drones to take off and land. In order to accurately land the drone on the drone nest, most drones are integrated with inertial measurement units such as gyroscopes to assist the drone to land accurately and smoothly on the drone nest. However, as drones develop towards miniaturization, the battery capacity and volume of drones are limited. How to improve the endurance of drones and reduce hardware costs is an urgent problem to be solved. Summary of the invention

[0004] The embodiments of the present application provide a method, device, storage medium and drone landing positioning method for drones, which can solve the problems of high hardware cost and complex structure caused by the inertial measurement unit-assisted landing of drones in related technologies. The technical solution is as follows:

[0005] In a first aspect, an embodiment of the present application provides a method for landing and positioning a drone, the method comprising:

[0006] During the landing process of the UAV, detecting whether the UAV enters the scanning range of the laser radar;

[0007] If yes, scan the drone using the laser radar to obtain a point cloud image;

[0008] Determine the current posture of the UAV in the laser radar coordinate system according to the point cloud image, and calculate the posture correction parameter between the current posture and the target posture;

[0009] Sending a posture correction instruction carrying the posture correction parameters to the drone; wherein the posture correction instruction is used to instruct the drone to perform posture correction according to the posture correction parameters.

[0010] In a second aspect, an embodiment of the present application provides a landing positioning device for a drone, comprising:

[0011] A detection unit, used to detect whether the drone enters the scanning range of the laser radar during the landing process of the drone;

[0012] a scanning unit, for, if yes, scanning the drone by the laser radar to obtain a point cloud image;

[0013] A computing unit, configured to determine a current posture of the UAV in a laser radar coordinate system according to the point cloud image, and to calculate a posture correction parameter between the current posture and a target posture;

[0014] A sending unit is used to send a posture correction instruction carrying the posture correction parameters to the drone; wherein the posture correction instruction is used to instruct the drone to perform posture correction according to the posture correction parameters.

[0015] In a third aspect, an embodiment of the present application provides a computer storage medium, wherein the computer storage medium stores a plurality of instructions, wherein the instructions are suitable for being loaded by a processor and executing the above-mentioned method steps.

[0016] In a fourth aspect, an embodiment of the present application provides a drone nest, which may include: a processor and a memory; wherein the memory stores a computer program, and the computer program is suitable for being loaded by the processor and executing the above-mentioned method steps.

[0017] The beneficial effects brought about by the technical solutions provided by some embodiments of the present application include at least:

[0018] During the landing process of the drone, when the drone enters the scanning range of the laser radar set in the drone nest, the drone is scanned by the laser radar to obtain a point cloud image, the current posture of the drone is estimated based on the point cloud data, and the attitude correction parameters between the current posture and the target posture are compared. The drone nest instructs the drone to perform attitude correction according to the attitude correction parameters. In this way, attitude correction can be achieved for the drone without setting up an inertial measurement unit, thereby ensuring that the drone lands smoothly on the drone nest, reducing the space occupied by the inertial measurement unit of the drone, reducing the power consumption of the drone when the inertial measurement unit is working, reducing the weight of the drone, and reducing the hardware cost of the drone. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0020] Figure 1 It is a network structure diagram provided by an embodiment of the present application;

[0021] Figure 2It is a flow chart of a method for landing and positioning a UAV provided in an embodiment of the present application;

[0022] Figure 3 It is a structural schematic diagram of a landing positioning device for a drone provided in an embodiment of the present application;

[0023] Figure 4 It is a structural schematic diagram of a device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0024] In order to make the objectives, technical solutions and advantages of the present application more clear, the embodiments of the present application will be further described in detail below with reference to the accompanying drawings.

[0025] When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Instead, they are only examples of devices and methods consistent with some aspects of the present application as detailed in the attached claims.

[0026] In the description of the present application, it should be understood that the terms "first", "second", etc. are used for descriptive purposes only and should not be understood as indicating or implying relative importance. For those of ordinary skill in the art, the specific meanings of the above terms in the present application can be understood according to the specific circumstances. In addition, in the description of the present application, unless otherwise specified, "multiple" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the previously associated objects are in an "or" relationship.

[0027] See also Figure 1 , which is a network architecture diagram provided for an embodiment of the present application. The network architecture of the present application includes: a mobile terminal 11, a drone nest 12 and a drone 13. The number of drones 13 can be multiple, and multiple drones can form a drone cluster, and the drone cluster collaborates to complete the task.

[0028] The drone nest 12 provides a docking platform for the drone 13. The drone nest 12 can control the take-off and landing of the drone 13. After the drone 13 successfully takes off, the mobile terminal 11 can take over the control of the drone 13 to control the flight speed and flight direction of the drone 13, or the drone 13 can also start the automatic flight mode to self-control its flight speed, flight direction and other parameters.

[0029] The mobile terminal 11 and the drone nest 12 can use WIFI communication, and the drone nest 12 and the drone can also use WIFI communication. The drone nest 12 can also serve as a relay node to forward the image data collected by the drone 13 to the mobile terminal 11 to increase the communication distance. The mobile terminal 11 can be a mobile phone, a platform computer or a laptop computer, etc.

[0030] based on Figure 1 For network architecture, see Figure 2 , is a flow chart of a method for positioning a landing drone provided in an embodiment of the present application. Figure 2 As shown, the method of the embodiment of the present application may include the following steps:

[0031] S201. During the landing process of the UAV, detect whether the UAV enters the scanning range of the laser radar.

[0032] Among them, the mobile terminal can send a landing command to the drone through the drone nest. The drone nest serves as a relay node for communication between the mobile terminal and the drone. The landing command carries the location information of the drone nest. The drone responds to the landing command and moves in the direction close to the drone nest according to the location information of the drone nest. The drone nest is equipped with a laser radar. The laser radar has a certain scanning range, which consists of a horizontal scanning range and a vertical scanning range. For example, the laser radar is set at the landing mark of the drone nest. The laser radar emits a laser beam toward the sky for scanning. The scanning range of the laser radar is conical. When the drone nest detects that the drone nest enters the scanning range of the laser radar, it starts the laser radar for periodic scanning to avoid the laser radar working when the drone is not detected, thereby reducing the power consumption of the laser radar when it is working.

[0033] Among them, the method for the drone nest to detect whether the drone has entered the scanning range of the laser radar includes: the drone nest pre-stores or is provided with a three-dimensional coordinate set representing the scanning range of the laser radar, the drone nest obtains the three-dimensional coordinates of the drone in real time, the drone and the drone nest both use the same laser radar coordinate system to represent the position information, the origin of the laser radar coordinate system can be the position of the landing mark, the xy plane is the horizontal plane, and the z axis is perpendicular to the horizontal plane. When the drone nest detects that the three-dimensional coordinates of the drone are located in the three-dimensional coordinate set of the laser radar, it is determined that the drone has entered the scanning range of the laser radar.

[0034] 202. If yes, scan the drone using a laser radar to obtain a point cloud image.

[0035] Among them, if the detection result of S201 is yes, the drone is scanned by the laser radar, and the scanning time is the length of one frame. The drone nest can scan the drone multiple times in one frame to obtain multiple point cloud images.

[0036] In one or more embodiments, in addition to the drone, the point cloud image may also include other obstacles, such as clouds, flying birds, buildings or trees, etc. The point cloud data collected by the lidar is filtered and processed to segment the drone area from the point cloud image. The segmentation method may use a neural network method to use a pre-trained background segmentation model to identify the drone area from the point cloud image, so as to improve the accuracy of subsequent estimation of the drone's posture.

[0037] S203, determining the current posture of the UAV in the laser radar coordinate system according to the point cloud image, and calculating the posture correction parameters between the current posture and the target posture.

[0038] The attitude of the UAV represents the orientation of the UAV in the laser radar coordinate system, and the methods for estimating the current attitude of the UAV include: a model-based attitude estimation method and a learning-based attitude estimation method.

[0039] In the model-based attitude estimation method, the collective relationship or feature points of the drone are used for estimation. The basic idea is to use a geometric model or structure to represent the structure and shape of the drone, and to establish a correspondence between the model and the image by extracting the object features. Then, the spatial attitude of the object is estimated through geometry or other methods.

[0040] In the learning-based attitude estimation method, the learning-based method uses machine learning methods to learn the correspondence between two-dimensional observations and three-dimensional attitudes from pre-acquired training samples in different attitudes, and applies the learned decision rules or regression functions to the samples. The results are used as attitude classifiers for attitude estimation of the samples. Learning-based methods generally use global observation features, do not need to detect or identify local features of objects, and have good robustness. The drone nest extracts image features of the point cloud image and uses the pre-trained attitude classifier to identify the current attitude of the drone.

[0041] The target attitude is the standard attitude of the drone when it is parked at the landing mark of the drone nest. The attitude offset between the current attitude and the target attitude is compared, and the attitude correction parameters are calculated based on the attitude offset. The attitude correction parameters include translation and rotation, so that the current attitude of the drone is consistent with the target attitude. The attitude of the drone can be represented by a six-degree-of-freedom vector.

[0042] S204: Sending a posture correction instruction carrying the posture correction parameters to the UAV.

[0043] The attitude correction instruction is used to instruct the drone to perform attitude correction according to the attitude correction parameters, and control the current attitude of the drone to be consistent with the target attitude in real time, so that the drone can land smoothly on the drone nest. The drone nest can send attitude correction instructions to the drone through the WIFI link. The drone nest is provided with multiple antennas, and the multiple antennas form an antenna array. During the communication between the drone nest and the drone, the drone nest obtains the angle of the drone relative to the antenna array in real time, and realizes beamforming by adjusting the weighting coefficients of each antenna, and points the transmission direction of the WIFI signal to the drone, thereby improving the communication quality of the WIFI link.

[0044] In this embodiment, during the landing process of the drone, when the drone enters the scanning range of the laser radar set in the drone nest, the drone is scanned by the laser radar to obtain a point cloud image, the current posture of the drone is estimated based on the point cloud data, and the posture correction parameters between the current posture and the target posture are compared. The drone nest instructs the drone to perform posture correction according to the posture correction parameters. In this way, posture correction can be achieved for the drone without setting up an inertial measurement unit, thereby ensuring that the drone lands smoothly on the drone nest, reducing the space occupied by the inertial measurement unit of the drone, reducing the power consumption of the drone when the inertial measurement unit is working, reducing the weight of the drone, and reducing the hardware cost of the drone.

[0045] The following is an embodiment of the device of the present application, which can be used to execute the embodiment of the method of the present application. For details not disclosed in the embodiment of the device of the present application, please refer to the embodiment of the method of the present application.

[0046] See also Figure 3 , which shows a schematic diagram of the structure of a landing positioning device for a drone provided by an exemplary embodiment of the present application. The landing positioning device for the drone can be implemented as all or part of the drone nest through software, hardware or a combination of both. The device 3 includes: a detection unit 31, a scanning unit 32, a calculation unit 33 and a sending unit 34.

[0047] The detection unit 31 is used to detect whether the drone enters the scanning range of the laser radar during the landing process of the drone;

[0048] A scanning unit 32 is used for scanning the UAV by the laser radar to obtain a point cloud image if the answer is yes;

[0049] A calculation unit 33, used to determine the current posture of the UAV in the laser radar coordinate system according to the point cloud image, and calculate a posture correction parameter between the current posture and the target posture;

[0050] The sending unit 34 is used to send a posture correction instruction carrying the posture correction parameters to the drone; wherein the posture correction instruction is used to instruct the drone to perform posture correction according to the posture correction parameters.

[0051] In one or more embodiments, during the landing process of the drone, detecting whether the drone enters the scanning range of the laser radar includes:

[0052] Obtaining the three-dimensional coordinates of the UAV in the laser radar coordinate system;

[0053] Determining whether the three-dimensional coordinates are within a preset three-dimensional coordinate set;

[0054] If yes, it is determined that the UAV has entered the scanning range of the laser radar;

[0055] If not, it is determined that the drone has not entered the scanning range of the laser radar.

[0056] In one or more embodiments, determining the current posture of the drone in the laser radar coordinate system according to the point cloud image includes:

[0057] Performing feature extraction on the point cloud image to obtain image features;

[0058] The image features are processed based on a posture classifier to obtain the current posture of the UAV in the laser radar coordinate system.

[0059] In one or more embodiments, the scanning unit 42 is further configured to:

[0060] The point cloud data is filtered according to a deep learning network.

[0061] In one or more embodiments, the drone nest is provided with a landing mark, the landing mark is located at the origin of the laser radar coordinate system, and the attitude correction parameters include: translation amount and rotation amount.

[0062] In one or more embodiments, sending the attitude correction instruction carrying the attitude correction parameter to the drone includes:

[0063] Sending a posture correction instruction carrying the posture correction parameters to the drone via a WIFI link.

[0064] In one or more embodiments, the drone nest is provided with an antenna array including a plurality of antennas;

[0065] The device 3 further includes: an adjustment unit, configured to obtain the position information of the drone;

[0066] Determining an angle of the drone relative to the antenna array based on the position information;

[0067] The weighting coefficients of the respective antennas in the antenna array are adjusted according to the angle to generate a WIFI signal directed toward the drone.

[0068] It should be noted that the landing positioning device for the drone provided in the above embodiment only uses the division of the above functional modules as an example when executing the landing positioning method for the drone. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the landing positioning device for the drone provided in the above embodiment and the landing positioning method embodiment of the drone belong to the same concept, and the implementation process thereof is detailed in the method embodiment, which will not be repeated here.

[0069] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0070] The present application also provides a computer storage medium, which can store multiple instructions, and the instructions are suitable for being loaded and executed by a processor as described above. Figure 2 The method steps of the embodiment shown in the figure can be found in the specific implementation process. Figure 2 The specific description of the illustrated embodiment will not be repeated here.

[0071] See also Figure 4 , which is a schematic diagram of the structure of a device provided in the embodiment of the present application. Figure 4 As shown, the device can be Figure 1 The drone nest 1000 may include: at least one processor 1001, at least one network interface 1004, a user interface 1003, a memory 1005, and at least one communication bus 1002.

[0072] The communication bus 1002 is used to realize the connection and communication between these components.

[0073] The user interface 1003 may include a display screen (Display) and a camera (Camera), and the optional user interface 1003 may also include a standard wired interface and a wireless interface.

[0074] The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0075] Among them, the processor 1001 may include one or more processing cores. The processor 1001 uses various interfaces and lines to connect the various parts of the entire drone nest 1000, and executes various functions and processes data of the drone nest 1000 by running or executing instructions, programs, code sets or instruction sets stored in the memory 1005, and calling data stored in the memory 1005. Optionally, the processor 1001 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 1001 can integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 1001, and it can be implemented separately through a chip.

[0076] Among them, the memory 1005 may include a random access memory (Random Access Memory, RAM) and may also include a read-only memory (Read-Only Memory). Optionally, the memory 1005 includes a non-transitory computer-readable storage medium. The memory 1005 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 1005 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 1005 may optionally be at least one storage device located away from the aforementioned processor 1001. As Figure 4 As shown, the memory 1005 as a computer storage medium may include an operating system, a network communication module, a user interface module and an application program.

[0077] exist Figure 4In the drone nest 1000 shown, the user interface 1003 is mainly used to provide an input interface for the user and obtain the data input by the user; and the processor 1001 can be used to call the application program interface configuration stored in the memory 1005, and specifically perform the following operations:

[0078] During the landing process of the UAV, detecting whether the UAV enters the scanning range of the laser radar;

[0079] If yes, scan the drone using the laser radar to obtain a point cloud image;

[0080] Determine the current posture of the UAV in the laser radar coordinate system according to the point cloud image, and calculate the posture correction parameter between the current posture and the target posture;

[0081] Sending a posture correction instruction carrying the posture correction parameters to the drone; wherein the posture correction instruction is used to instruct the drone to perform posture correction according to the posture correction parameters.

[0082] In one or more embodiments, the processor 1001 performs the step of detecting whether the drone enters the scanning range of the laser radar during the landing process of the drone, including:

[0083] Obtaining the three-dimensional coordinates of the UAV in the laser radar coordinate system;

[0084] Determining whether the three-dimensional coordinates are within a preset three-dimensional coordinate set;

[0085] If yes, it is determined that the UAV has entered the scanning range of the laser radar;

[0086] If not, it is determined that the drone has not entered the scanning range of the laser radar.

[0087] In one or more embodiments, the processor 1001 performs the step of determining the current posture of the drone in the laser radar coordinate system according to the point cloud image, including:

[0088] Performing feature extraction on the point cloud image to obtain image features;

[0089] The image features are processed based on a posture classifier to obtain the current posture of the UAV in the laser radar coordinate system.

[0090] In one or more embodiments, the processor 1001 executes the step of scanning the drone by the laser radar to obtain a point cloud image, further comprising:

[0091] The point cloud data is filtered according to a deep learning network.

[0092] In one or more embodiments, the drone nest is provided with a landing mark, the landing mark is located at the origin of the laser radar coordinate system, and the attitude correction parameters include: translation amount and rotation amount.

[0093] In one or more embodiments, sending the attitude correction instruction carrying the attitude correction parameter to the drone includes:

[0094] Sending a posture correction instruction carrying the posture correction parameters to the drone via a WIFI link.

[0095] In one or more embodiments, the drone nest is provided with an antenna array including a plurality of antennas;

[0096] The processor 1001 is further configured to execute:

[0097] Obtaining the location information of the drone;

[0098] Determining an angle of the drone relative to the antenna array based on the position information;

[0099] The weighting coefficients of the respective antennas in the antenna array are adjusted according to the angle to generate a WIFI signal directed toward the drone.

[0100] The concept and Figure 2 The method embodiment is the same as that of the embodiment, and the technical effect it brings is also the same. The specific process can be referred to Figure 2 The description of the embodiments will not be repeated here.

[0101] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing related hardware through a computer program, and the program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above-mentioned methods. The storage medium can be a disk, an optical disk, a read-only storage memory, or a random access memory, etc.

[0102] The above disclosure is only the preferred embodiment of the present application, which certainly cannot be used to limit the scope of rights of the present application. Therefore, equivalent changes made according to the claims of the present application are still within the scope covered by the present application.

Claims

1. A landing positioning method for an unmanned aerial vehicle, characterized in that: include: During the landing process of the drone, detecting whether the drone enters the scanning range of the laser radar set in the drone nest; If yes, scan the drone using the laser radar to obtain a point cloud image; Determine the current posture of the UAV in the laser radar coordinate system according to the point cloud image, and calculate the posture correction parameter between the current posture and the target posture; Sending a posture correction instruction carrying the posture correction parameters to the UAV; wherein, The attitude correction instruction is used to instruct the UAV to perform attitude correction according to the attitude correction parameters; wherein, During the landing process of the drone, detecting whether the drone enters the scanning range of the laser radar includes: Obtaining the three-dimensional coordinates of the UAV in the laser radar coordinate system; Determining whether the three-dimensional coordinates are within a preset three-dimensional coordinate set; If yes, it is determined that the UAV has entered the scanning range of the laser radar; If not, it is determined that the UAV has not entered the scanning range of the laser radar; wherein, Determining the current posture of the UAV in the laser radar coordinate system according to the point cloud image includes: Performing feature extraction on the point cloud image to obtain image features; The image features are processed based on a posture classifier to obtain the current posture of the UAV in the lidar coordinate system, wherein the posture classifier learns the correspondence between two-dimensional observations and three-dimensional postures, and uses pre-acquired training samples under different postures to train decision rules or regression functions. The trained posture classifier inputs new samples and applies the learned rules or functions to output the posture estimation result of the sample.

2. The method according to claim 1, characterized in that The step of scanning the drone by the laser radar to obtain a point cloud image further includes: The point cloud image is filtered according to a deep learning network.

3. The method according to claim 1, characterized in that The drone nest is provided with a landing mark, the landing mark is located at the origin of the laser radar coordinate system, and the attitude correction parameters include: translation amount and rotation amount.

4. The method according to claim 1, characterized in that: The sending of the attitude correction instruction carrying the attitude correction parameter to the UAV includes: Sending a posture correction instruction carrying the posture correction parameters to the drone via a WIFI link.

5. The method according to claim 4, characterized in that The drone nest is provided with an antenna array including a plurality of antennas; The method further comprises: Obtaining the location information of the drone; Determining an angle of the drone relative to the antenna array based on the position information; The weighting coefficients of the respective antennas in the antenna array are adjusted according to the angle to generate a WIFI signal directed toward the drone.

6. A landing positioning device for an unmanned aerial vehicle, characterized in that: include: A detection unit, used to detect whether the drone enters the scanning range of the laser radar set in the drone nest during the landing process of the drone; a scanning unit, for, if yes, scanning the drone by the laser radar to obtain a point cloud image; A computing unit, configured to determine a current posture of the UAV in a laser radar coordinate system according to the point cloud image, and to calculate a posture correction parameter between the current posture and a target posture; A sending unit is used to send a posture correction instruction carrying the posture correction parameters to the UAV; wherein the posture correction instruction is used to instruct the UAV to perform posture correction according to the posture correction parameters, wherein, The detection unit specifically: obtains the three-dimensional coordinates of the UAV in the laser radar coordinate system; Determining whether the three-dimensional coordinates are within a preset three-dimensional coordinate set; If yes, it is determined that the UAV has entered the scanning range of the laser radar; If not, it is determined that the UAV has not entered the scanning range of the laser radar; The calculation unit determines the current posture of the UAV in the laser radar coordinate system according to the point cloud image by: extracting features from the point cloud image to obtain image features; The image features are processed based on a posture classifier to obtain the current posture of the UAV in the lidar coordinate system, wherein the posture classifier learns the correspondence between two-dimensional observations and three-dimensional postures, and uses pre-acquired training samples under different postures to train decision rules or regression functions. The trained posture classifier inputs new samples and applies the learned rules or functions to output the posture estimation result of the sample.

7. A computer storage medium, characterized in that: The computer storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor and executing the method steps as claimed in any one of claims 1 to 5.

8. A drone nest, characterized in that: include: A processor and a memory; wherein the memory stores a computer program, and the computer program is suitable for being loaded by the processor and executing the method steps as claimed in any one of claims 1 to 5.

Images