UAV landing control method, control device and storage medium

By setting up vision sensors on the apron and using morphological image processing technology, the problem of light and GPS signal quality limitation in drone landing technology is solved, and precise landing in complex environments is achieved.

CN115202395BActive Publication Date: 2024-11-26QINGDAO CLOUD CENTURY INFORMATION TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202210864021.2
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-07-21
Publication Date
2024-11-26
Estimated Expiration
2042-07-21

AI Technical Summary

Technical Problem

The existing drone landing technology is susceptible to external light and limited GPS signal quality, resulting in a decrease in landing accuracy, especially in complex environments, which is difficult to achieve accurate landing.

Method used

Set up a vision sensor on the tarmac, obtain the target morphology image of the drone through the vision sensor, determine the deviation between the shape center and the visual center, control the drone to fly to the vision center of the vision sensor, and ensure the shape through filtering and body judgment algorithms Integrity ultimately achieves accurate landing.

Benefits of technology

It improves the landing accuracy of drones on the apron, reduces the impact of light and GPS signal quality on landing, and ensures accurate landing effect in various environments.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN115202395B_ABST
    Figure CN115202395B_ABST
Patent Text Reader

Abstract

The embodiments of the present invention provide a drone landing control method, a control device and a storage medium related to the field of drone technology, which are applied to a controller in a drone landing system. The drone landing system also includes a visual sensor, which is arranged on a helipad, and the controller is respectively connected to the visual sensor and the drone for communication. The method includes: controlling the drone to fly to the visual center of the visual sensor, and obtaining a target shape image of the drone based on the visual sensor, and then determining the body center of the drone based on the target shape image, and judging whether the deviation between the body center and the visual center in the vertical direction is within a preset deviation threshold range. If so, controlling the drone to land on the helipad. The present invention can effectively improve the accuracy of drone landing.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned aerial vehicles, and in particular to a landing control method, a control device and a storage medium for an unmanned aerial vehicle. Background Art

[0002] With the development of drone technology, drones are being used more and more widely in various fields. In some fields, drones need to be accurately landed in a designated area.

[0003] The existing technology mainly uses image recognition and positioning based on the downward-looking lens of the drone, and uses RTK (Real-Time Kinematic, carrier phase difference technology) to accurately land the drone.

[0004] However, the visual recognition image is easily affected by external light, resulting in a decrease in recognition rate, which in turn affects the landing accuracy of the drone. The RTK's precise landing method is limited by the GPS (Global Positioning System) signal quality of the on-site environment. Summary of the invention

[0005] The objectives of the present invention include, for example, providing a drone landing control method, a control device and a storage medium, which can at least partially solve the above-mentioned technical problems.

[0006] The embodiments of the present invention can be implemented as follows:

[0007] In a first aspect, an embodiment of the present invention provides a method for controlling a landing of a drone, which is applied to a controller in a landing system of a drone, wherein the landing system of the drone further includes a visual sensor, wherein the visual sensor is disposed on a helipad, and the controller is respectively connected to the visual sensor and the drone for communication; the method includes:

[0008] Controlling the UAV to fly to the visual center of the visual sensor;

[0009] Acquire a target morphological image of the UAV based on the visual sensor;

[0010] Determining the shape center of the UAV according to the target shape image;

[0011] Determine whether the deviation between the body center and the visual center in the vertical direction is within a preset deviation threshold range; if so, control the UAV to land on the apron.

[0012] Optionally, acquiring the target morphology image of the drone based on the visual sensor includes:

[0013] Controlling the visual sensor to capture a morphological image of the drone;

[0014] Acquire the morphological image captured by the visual sensor;

[0015] The morphological image is filtered to obtain the target morphological image.

[0016] Optionally, after obtaining the target morphological image and before determining the body center of the drone, the method further includes:

[0017] Based on a shape judgment algorithm, judging whether the target shape image is a complete shape of the UAV;

[0018] If not, the drone is controlled to fly back to the visual center of the visual sensor to obtain the complete form of the drone.

[0019] Optionally, judging whether the target shape image is a complete shape of the drone based on a shape judgment algorithm includes:

[0020] Based on the minimum outer rectangle algorithm, obtaining the aspect ratio of the minimum outer rectangle of the target morphological image;

[0021] Determining whether the aspect ratio of the minimum circumscribed rectangle is less than a preset aspect ratio threshold;

[0022] If so, it is determined that the target shape image is the complete shape of the drone.

[0023] Optionally, the method further comprises:

[0024] If the aspect ratio of the minimum circumscribed rectangle is greater than or equal to the preset aspect ratio threshold, the drone is controlled to fly back to the visual center of the visual sensor and the target shape image of the drone is reacquired until the aspect ratio of the minimum circumscribed rectangle of the reacquired target shape image is less than the preset aspect ratio threshold.

[0025] Optionally, determining the shape center of the drone according to the target shape image includes:

[0026] Based on the spatial moment calculation formula:

[0027]

[0028] Calculate the spatial moment parameters of the target morphological image, where x and y represent the coordinates in the target morphological image, M and N represent the length and width of each frame of the target morphological image, f(x, y) represents the pixel value of the target morphological image at the coordinate (x, y), and p and q are 0 or 1 respectively;

[0029] Based on the center of gravity calculation formula:

[0030]

[0031] According to the spatial moment parameters, the shape center of the UAV is determined, where are the coordinates of the center of the shape in the target morphological image.

[0032] Optionally, the method further comprises:

[0033] If the deviation between the body center and the visual center in the vertical direction is outside the preset deviation threshold range, the drone is controlled to fly back to the visual center of the visual sensor so that the deviation between the body center and the visual center in the vertical direction is within the preset deviation threshold range.

[0034] Optionally, controlling the UAV to land on the helipad includes:

[0035] Controlling the drone to descend and monitoring the height of the drone from the helipad;

[0036] When the drone descends to a preset landing height, the drone is controlled to stop propellers and land on the helipad.

[0037] In a second aspect, an embodiment of the present invention provides a control device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of any one of the above-mentioned UAV landing control methods are implemented.

[0038] In a third aspect, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium includes a computer program, and when the computer program is executed, the server where the computer-readable storage medium is located is controlled to implement the steps of any one of the above-mentioned UAV landing control methods.

[0039] The beneficial effects of the embodiments of the present invention include, for example:

[0040] The present invention sets a visual sensor on the apron, controls the UAV to fly to the visual center of the visual sensor, obtains the target shape image of the UAV through the visual sensor, further determines the body center of the UAV, and makes the visual center correspond to the body center in the vertical direction, finally realizing the precise landing of the UAV on the apron. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0042] Figure 1 An architectural diagram of a drone landing system provided in an embodiment of this specification;

[0043] Figure 2 An architectural diagram of a control device provided in an embodiment of this specification;

[0044] Figure 3 A flowchart of a method for controlling the landing of a drone provided in an embodiment of this specification;

[0045] Figure 4 A diagram showing the relationship between the positions of the visual sensor and the apron provided in the embodiments of this specification;

[0046] Figure 5 A diagram showing the position relationship between the visual sensor and the drone provided in the embodiments of this specification;

[0047] Figure 6 A drone morphology diagram before filtering provided in the embodiment of this specification;

[0048] Figure 7 The filtered drone morphology diagram provided in the embodiments of this specification;

[0049] Figure 8 A schematic diagram of a partial structure of a drone provided in an embodiment of this specification entering the field of view of a visual sensor;

[0050] Fig. 9 A schematic diagram of a circumscribed rectangle of a contour provided in an embodiment of this specification;

[0051] Fig.10 A schematic diagram of a drone landing control device provided in an embodiment of this specification.

[0052] Icon: 100-control device; 110-memory; 120-processor; 130-communication module; 300-UAV landing control device; 301-flight control unit; 302-target morphological image acquisition unit; 303-body center determination unit; 304-landing control unit; 400-UAV landing system; 401-controller; 402-visual sensor. DETAILED DESCRIPTION

[0053] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0054] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention claimed for protection, but merely represents selected embodiments of the present invention. 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.

[0055] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0056] In addition, the terms “first”, “second”, etc., if used, are merely used to distinguish between the descriptions and should not be understood as indicating or implying relative importance.

[0057] It should be noted that, in the absence of conflict, the features in the embodiments of the present invention may be combined with each other.

[0058] In the drone landing control scheme in the prior art, image recognition and positioning based on the drone's downward-looking lens is based on downward visual recognition images, which are easily affected by external light, thereby resulting in a decrease in recognition rate. Moreover, in this scheme, the drone's downward-looking lens will also be limited by the number of landing patterns during the last meter of landing, resulting in recognition blank areas. Therefore, its image landing efficiency is not high. In an environment with relatively strong winds, this scheme also cannot achieve a good landing effect.

[0059] However, precise landing based on RTK is limited by the quality of GPS signals in the on-site environment. In complex deployment environments, RTK may fail to converge to a fixed mode, resulting in failure of precise landing.

[0060] In order to improve the above problems, an embodiment of the present invention provides a UAV landing control solution, which improves the landing accuracy of the UAV by setting up a UAV landing system and adopting a UAV landing control method suitable for the UAV landing system. Figure 1As shown, a drone landing system 400 provided by the present invention includes a controller 401 and a visual sensor 402. The visual sensor 402 is arranged on the apron, and the controller 401 is respectively connected to the visual sensor 402 and the drone for communication. In the process of controlling the drone to land, the controller 401 controls the visual sensor 402 and the flight state of the drone to achieve the purpose of making the drone land accurately.

[0061] The controller in the drone landing system can be as follows Figure 2 The control device 100 shown includes a memory 110, a processor 120 and a communication module 130. The memory 110, the processor 120 and the communication module 130. Each component is directly or indirectly electrically connected to each other to achieve data transmission or interaction. For example, these components can be electrically connected to each other through one or more communication buses or signal lines.

[0062] The memory 110 is used to store programs or data. The memory 110 may be, but is not limited to, a random access memory (RAM), a read only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), etc.

[0063] The processor 120 is used to read / write data or programs stored in the memory and execute corresponding functions.

[0064] The communication module 130 is used to establish a communication connection between the server and other communication terminals through the network, and to send and receive data through the network.

[0065] It should be understood that Figure 2 The structure shown is only a schematic diagram of the structure of the control device 100. The control device 100 may also include Figure 2 More or fewer components as shown, or with Figure 2 Different configurations shown. Figure 2 Each component shown in the figure can be implemented by hardware, software or a combination thereof.

[0066] The control device 100 may be a physical device of the controller 401, and various logics and programs carried thereon may be used to implement the following Figure 3The drone landing control method shown is applied to a controller in a drone landing system, wherein the drone landing system further includes a visual sensor, the visual sensor is disposed on a helipad, and the controller is respectively connected to the visual sensor and the drone for communication. The method includes the following steps:

[0067] Step S110: Control the drone to fly to the visual center of the visual sensor.

[0068] Step S120: Acquire a target shape image of the UAV based on the visual sensor.

[0069] Step S130: determining the shape center of the drone according to the target shape image.

[0070] Step S140: Determine whether the deviation between the body center and the visual center in the vertical direction is within a preset deviation threshold range; if so, control the UAV to land on the apron.

[0071] After the UAV completes the flight mission, the UAV can be controlled to land on the helipad by a controller in the UAV landing system. The controller executes step S110: controlling the UAV to fly to the visual center of the visual sensor.

[0072] The visual sensor is a sensor that can acquire images of the drone's shape in the drone landing system, such as a 3D TOF (Time of flight) sensor module. In order to increase the environmental adaptability of the visual sensor, the camera of the visual sensor can be a 3D TOF depth camera based on a 940nm VCSEL light source. The camera can actively detect. The depth camera in this band can be used in all environments such as strong light, backlight, and darkness. Its detection presents an elliptical outward radiation detection.

[0073] The visual center can be a position where the visual sensor can capture the complete image of the drone, such as the center point of the visual sensor camera. The visual sensor can be set at any position on the apron where the drone can land. As an optional embodiment, Figure 4 As shown, the visual sensor can be set at the center of the apron. The controller can send a control signal to the drone through the communication module set on the drone to control the drone to fly to the visual center of the visual sensor so that the visual sensor can capture the image of the drone.

[0074] After the UAV reaches the visual center of the visual sensor, step S120 is executed to obtain a target shape image of the UAV based on the visual sensor.

[0075] like Figure 5As shown, after the UAV reaches the visual center, the controller controls the visual sensor to obtain the UAV's morphological image (i.e., the target morphological image). The target morphological image obtained can be one or multiple morphological images, and the user or the preset program of the controller selects the best one as the target morphological image.

[0076] Optionally, the acquiring the target morphological image of the drone based on the visual sensor comprises: controlling the visual sensor to capture the morphological image of the drone, acquiring the morphological image captured by the visual sensor, and performing filtering processing on the morphological image to obtain the target morphological image.

[0077] like Figure 6 As shown in the figure, since the visual sensor may be affected by sunlight or other floating objects in the air when acquiring images, these interference items have obvious mismatches in height characteristics and continuous characteristics with the actual UAV to be detected. Therefore, the first layer of filtering can be performed based on the height information, and then the laser data in the morphological image is converted into grayscale data. Then, the second layer of linear filtering is performed to filter out the interference data except the UAV morphological image data, and a binary image is obtained as the target morphological image, thereby ensuring data reliability.

[0078] As an optional embodiment, after the UAV reaches the visual center, it sends an arrival signal to the controller. After receiving the arrival signal, the controller sends a control signal to the visual sensor to control the visual sensor to capture one or more morphological images of the UAV. When there are multiple morphological images captured, one morphological image is selected, and then the morphological image is filtered to obtain the following image: Figure 7 The target morphology image is shown.

[0079] Optionally, after obtaining the target shape image, the method further comprises: judging whether the target shape image is the complete shape of the drone based on a shape judgment algorithm. If not, controlling the drone to fly back to the visual center of the visual sensor to obtain the complete shape of the drone.

[0080] During the guided detection process, it often happens that part of the drone enters the field of view of the visual sensor (such as Figure 8 The figure shows the situation where the drone's wings enter the field of view), especially when the drone is flying at a low altitude, this situation will be more common. In this case, although a shape center can still be calculated by the algorithm, in fact, this shape center is not the real shape center of the drone, that is, this situation does not meet the landing conditions.

[0081] Therefore, after obtaining the target shape image, it is necessary to determine the shape information of the drone to determine whether the drone has entered the shooting range of the visual sensor as a whole (i.e., whether the complete shape of the drone has been captured) to determine whether the center point calculated later is the shape center of the drone. If the drone has not entered the shooting range of the visual sensor as a whole, the controller can be used to control the drone to fly back to the visual center of the visual sensor to obtain the complete shape of the drone.

[0082] Optionally, judging whether the target shape image is the complete shape of the drone based on the shape judgment algorithm includes: obtaining the aspect ratio of the minimum circumscribed rectangle of the target shape image based on the minimum external rectangle algorithm. Judging whether the aspect ratio of the minimum circumscribed rectangle is less than a preset aspect ratio threshold. If so, judging that the target shape image is the complete shape of the drone.

[0083] There are two types of circumscribed rectangles of contours, such as Fig. 9 As shown in the figure, the white one is called boundingRect(), which means the rectangle that does not consider rotation and can contain the entire outline. The black one is called the minimum bounding rectangle minAreaRect(), which takes rotation into consideration. Since the drone will inevitably rotate during the descent process, the minimum bounding rectangle algorithm can be applied to calculate the aspect ratio of the outer frame. The aspect ratio of the minimum bounding rectangle detected by a normal drone is small. If only a part of the drone enters the shooting range of the visual sensor, the aspect ratio will be large. Therefore, a preset length and width threshold can be set to determine whether it is the complete form of the drone. If so, the drone form in the target form image is the complete form of the drone.

[0084] Optionally, the method further includes: if the aspect ratio of the minimum circumscribed rectangle is greater than or equal to the preset aspect ratio threshold, controlling the drone to fly back to the visual center of the visual sensor so that the aspect ratio of the minimum circumscribed rectangle is less than the preset aspect ratio threshold.

[0085] When the aspect ratio of the minimum circumscribed rectangle is greater than or equal to the preset aspect ratio threshold, it means that the target shape image is not the complete shape of the drone, and the drone needs to be controlled by the controller to fly back to the visual center so that the visual sensor can re-acquire the target shape image of the drone.

[0086] In step S130, the shape center of the UAV is determined according to the target shape image.

[0087] After the target shape image of the UAV is determined, and the target shape image is the complete shape of the UAV, the shape center of the UAV, that is, the position of the center point of the UAV, can be determined according to the target shape image based on various image algorithms.

[0088] As an optional implementation scheme, determining the shape center of the drone according to the target shape image may include:

[0089] Based on the spatial moment calculation formula:

[0090]

[0091] Calculate the spatial moment parameters of the target morphological image, where x and y represent the coordinates in the target morphological image, M and N represent the length and width of each frame of the target morphological image, f(x, y) represents the pixel value of the target morphological image at the coordinate (x, y), and p and q are 0 or 1 respectively;

[0092] Based on the center of gravity calculation formula:

[0093]

[0094] According to the spatial moment parameters, the shape center of the UAV is determined, where are the coordinates of the center of the shape in the target morphological image.

[0095] After acquiring the target morphological image, the controller can obtain the length and width of each frame in the target morphological image, as well as the coordinates of each point according to the built-in program or preset algorithm. In order to save resources, the second-order moment can be used to calculate the spatial moment parameters of the target morphological image, that is, p and q are 0 or 1 respectively. The spatial moment calculation formula can be used to obtain four spatial moment parameters, and then the four spatial moment parameters are substituted into the center of gravity calculation formula to determine the shape center of the drone.

[0096] After the body center is determined, step S140 is executed to determine whether the deviation between the body center and the visual center in the vertical direction is within a preset deviation threshold range. If so, the UAV is controlled to land on the apron.

[0097] When the body center and the visual center are in the same straight line in the vertical direction, it means that the drone can directly land vertically on the visual center. In real life, due to various factors, the body center and the visual center may not be completely in the same straight line in the vertical direction. Therefore, a preset deviation threshold range can be set in the controller. If the deviation between the body center and the visual center of the drone in the vertical direction is within the preset deviation threshold range, the drone can be controlled to land on the helipad. The preset deviation threshold range can be set by the user according to actual needs, and the present invention does not specifically limit this.

[0098] Optionally, the method also includes: if the deviation between the body center and the visual center in the vertical direction is outside a preset deviation threshold range, controlling the drone to fly again to the visual center of the visual sensor so that the deviation between the body center and the visual center in the vertical direction is within a preset deviation threshold range.

[0099] If it is outside the preset deviation threshold range, it means that if the drone lands from the current position, it cannot meet the accuracy requirement required by the user. Therefore, the drone can be controlled to fly back to the visual center so that the vertical deviation between the body center and the visual center is within the preset deviation threshold range.

[0100] Optionally, controlling the drone to land on the helipad includes: controlling the drone to descend, and monitoring the height of the drone from the helipad. When the drone descends to a preset landing height, controlling the drone to stop propellers and land on the helipad.

[0101] When the deviation between the body center and the visual center in the vertical direction is within the preset deviation threshold range, the controller controls the drone to start descending, and monitors the height of the drone from the ground (i.e., the helipad) in real time during the descent. When the drone descends to a preset height, such as 15 cm, the controller controls the drone to stop propellers and complete the landing on the helipad.

[0102] Based on the same inventive concept, Fig.10 As shown, the embodiment of the specification of the present invention provides a drone landing control device 300, which is applied to a controller in a drone landing system. The drone landing system also includes a visual sensor, which is arranged on a helipad, and the controller is respectively connected to the visual sensor and the drone for communication; the drone landing control device 300 includes:

[0103] A flight control unit 301 is used to control the UAV to fly to the visual center of the visual sensor;

[0104] A target morphology image acquisition unit 302 is used to acquire a target morphology image of the UAV based on the visual sensor;

[0105] A body center determination unit 303, configured to determine the body center of the drone according to the target morphological image;

[0106] The landing control unit 304 is used to determine whether the deviation between the body center and the visual center in the vertical direction is within a preset deviation threshold range. If so, control the UAV to land on the apron.

[0107] Regarding the above-mentioned drone landing control device 300, the specific functions of each unit therein have been described in detail in the embodiment of the drone landing control method provided in this specification, and will not be elaborated here.

[0108] Based on the same inventive concept, Figure 1 As shown, the embodiment of the specification of the present invention provides a drone landing system 400, including a controller 401 and a visual sensor 402, the visual sensor 402 is arranged on the apron, and the controller 401 is respectively communicated with the visual sensor 402 and the drone.

[0109] The visual sensor 402 receives the control instruction sent by the controller 401; and captures the morphological image of the UAV according to the control instruction, or monitors the height of the UAV from the landing pad.

[0110] The controller 401 controls the UAV to fly to the visual center of the visual sensor 402; obtains the target shape image of the UAV; determines the body center of the UAV based on the target shape image; determines whether the deviation between the body center and the visual center in the vertical direction is within a preset deviation threshold range, and if so, controls the UAV to land on the apron.

[0111] Regarding the above-mentioned drone landing system 400, the specific functions of each unit therein have been described in detail in the embodiment of the drone landing control method provided in this specification, and will not be elaborated here.

[0112] Based on the same inventive concept, an embodiment of the present invention specification provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the steps of any method of the welding machine focal length correction method described above are implemented.

[0113] The present invention has at least the following beneficial effects:

[0114] By setting up a visual sensor on the apron and controlling the drone to fly to the visual center of the visual sensor, the target shape image of the drone is obtained through the visual sensor, the body center of the drone is further determined, and the visual center and the body center are matched in the vertical direction, finally achieving the precise landing of the drone on the apron.

[0115] In several embodiments provided by the present invention, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely schematic. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the devices, methods and computer program products according to multiple embodiments of the present invention. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the module, a program segment or a part of a code contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0116] In addition, the functional modules in the various embodiments of the present invention may be integrated together to form an independent part, or each module may exist independently, or two or more modules may be integrated to form an independent part.

[0117] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0118] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed by the present invention should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A method for controlling the landing of an unmanned aerial vehicle, characterized in that: A controller used in a drone landing system, wherein the drone landing system further comprises a visual sensor, wherein the visual sensor is disposed on a helipad, and wherein the controller is respectively connected to the visual sensor and the drone for communication; and the method comprises: Controlling the UAV to fly to the visual center of the visual sensor; Acquire a target morphological image of the UAV based on the visual sensor; Based on the shape judgment algorithm, judging whether the target shape image is the complete shape of the drone, including: based on the minimum bounding rectangle algorithm, obtaining the aspect ratio of the minimum bounding rectangle of the target shape image; judging whether the aspect ratio of the minimum bounding rectangle is less than a preset aspect ratio threshold; if so, judging that the target shape image is the complete shape of the drone; If not, the drone is controlled to fly back to the visual center of the visual sensor, and the target shape image of the drone is reacquired until the aspect ratio of the minimum circumscribed rectangle of the reacquired target shape image is less than the preset aspect ratio threshold; Determining the shape center of the UAV according to the target shape image; Determine whether the deviation between the body center and the visual center in the vertical direction is within a preset deviation threshold range; if so, control the UAV to land on the apron.

2. The UAV landing control method according to claim 1, characterized in that: The step of acquiring the target morphological image of the drone based on the visual sensor includes: Controlling the visual sensor to capture a morphological image of the drone; Acquire the morphological image captured by the visual sensor; The morphological image is filtered to obtain the target morphological image.

3. The UAV landing control method according to claim 1, characterized in that: Determining the shape center of the drone according to the target shape image includes: Based on the spatial moment calculation formula: Calculate the spatial moment parameters of the target morphological image, where x and y represent the coordinates in the target morphological image, M and N represent the length and width of each frame of the target morphological image, f(x, y) represents the pixel value of the target morphological image at the coordinate (x, y), and p and q are 0 or 1 respectively; Based on the center of gravity calculation formula: According to the spatial moment parameters, the shape center of the UAV is determined, where are the coordinates of the center of the shape in the target morphological image.

4. The UAV landing control method according to claim 1, characterized in that: The method further comprises: If the deviation between the body center and the visual center in the vertical direction is outside the preset deviation threshold range, the drone is controlled to fly back to the visual center of the visual sensor so that the deviation between the body center and the visual center in the vertical direction is within the preset deviation threshold range.

5. The UAV landing control method according to claim 1, characterized in that: The controlling the UAV to land on the helipad comprises: Controlling the drone to descend and monitoring the height of the drone from the helipad; When the drone descends to a preset landing height, the drone is controlled to stop propellers and land on the helipad.

6. A control device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method according to any one of claims 1 to 5 when executing the program.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a computer program, and when the computer program is executed, the server where the computer-readable storage medium is located is controlled to implement the steps of the method according to any one of claims 1 to 5.