UAV state detection method, UAV control device and UAV

The camera device collects the drone arm images and recognizes the detection position and calibration area, solving the unreliability problem of drone status detection when signal quality is poor, achieving more accurate judgment of the arm expansion state, and improving detection reliability and task security.

CN117975313BActive Publication Date: 2024-12-06ZHEJIANG HUASHI INTELLIGENT INSPECTION TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410361942.6
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-03-28
Publication Date
2024-12-06
Estimated Expiration
2044-03-28

AI Technical Summary

Technical Problem

Existing drone status detection methods are unreliable when positioning signal quality is poor, which may lead to mission delays or drone damage.

Method used

The image camera is used to collect images of the drone arm, and by identifying the detection position and calibration area in the image, we can determine whether the drone arm has reached the unfolded state, and use visual features to accurately calibrate and detect the detection results. The impact of

Benefits of technology

It improves the reliability of drone status detection, ensures the accuracy of arm expansion status detection, reduces misjudgment caused by signal quality, and enhances the safety of task execution.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN117975313B_ABST
    Figure CN117975313B_ABST
Patent Text Reader

Abstract

The present application discloses a method for detecting the state of a drone, a drone control device, and a drone. The drone is provided with a camera device capable of collecting images at the drone arm. The method for detecting the state of a drone comprises: obtaining an image to be identified collected by the camera device, and determining the detection position of the drone arm in the image to be identified; obtaining a calibration area of ​​the drone arm in a calibration image, and determining whether the drone arm has reached an unfolded state based on the calibration area and the detection position; wherein the calibration image is an image collected when the drone arm reaches an unfolded state. In the above manner, the present application can improve the reliability of drone state detection.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

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

[0002] In order to save storage space for drones, conventional drone arms are foldable arms, which are adjusted to an unfolded state when the drone is needed to perform a task. In the prior art, sensors are usually used to obtain positioning signals to locate the position of the drone arms, and then the distance between the drone arms is calculated based on the positioning information to determine whether the unfolded state has been reached. However, when the positioning signal quality is poor, the detection result will be unreliable. If the drone arms are put into use before reaching the unfolded state, it is very likely to cause mission delays or even damage to the drone. In view of this, how to improve the reliability of drone status detection has become an urgent problem to be solved. Summary of the invention

[0003] The main technical problem solved by the present application is to provide a drone status detection method, a drone control device and a drone, which can improve the reliability of drone status detection.

[0004] To solve the above technical problems, the first aspect of the present application provides a method for detecting the status of a drone, wherein the drone is provided with a camera device capable of capturing images at the drone arm, and the method comprises: obtaining an image to be identified captured by the camera device, and determining a detection position of the drone arm in the image to be identified; obtaining a calibration area of ​​the drone arm in a calibration image, and determining whether the drone arm has reached an unfolded state based on the calibration area and the detection position; wherein the calibration image is an image captured when the drone arm reaches the unfolded state.

[0005] In order to solve the above-mentioned technical problems, the second aspect of the present application provides a drone control device, which includes: a memory and a processor coupled to each other, wherein the memory stores program data, and the processor calls the program data to execute the method described in the first aspect above.

[0006] In order to solve the above technical problem, the third aspect of the present application provides a computer-readable storage medium on which program data is stored. When the program data is executed by a processor, the method described in the first aspect is implemented.

[0007] In order to solve the above technical problems, the fourth aspect of the present application provides a drone, which is provided with a camera device capable of collecting images at the drone arm and a drone control device as described in the second aspect above.

[0008] The above scheme obtains the image to be identified captured by the camera device on the drone, determines the position of the drone arm from the image to be identified, obtains the detection position of the drone arm, obtains the position of the drone arm in the calibration image, and determines the calibration area of ​​the drone arm, wherein the calibration image is an image captured when the drone arm reaches the unfolded state, so that the calibration area corresponding to the drone arm that reaches the unfolded state can be accurately obtained in the calibration image, and based on the positional relationship between the calibration area and the detection position, it is judged whether the drone arm reaches the unfolded state, and the detection result of the drone state is obtained, so as to use the visual features on the image to calibrate and detect the precise position of the drone arm, and thereby analyze whether the drone arm is fully unfolded, reduce the influence of signal quality on the detection result, and improve the reliability of drone state detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. 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 creative work. Among them:

[0010] Figure 1 It is a flow chart of an implementation method of a drone status detection method of the present application;

[0011] Figure 2 It is a flowchart of another implementation method of the drone status detection method of the present application;

[0012] Figure 3 This is a schematic structural diagram of an implementation method of the drone control device of the present application;

[0013] Figure 4 It is a schematic diagram of the structure of an embodiment of a computer-readable storage medium of the present application;

[0014] Figure 5 It is a structural schematic diagram of an implementation method of the drone of the present application. DETAILED DESCRIPTION

[0015] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments, and different implementation methods can be adaptively combined. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0016] The terms "system" and "network" are often used interchangeably in this article. The term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship. In addition, "many" in this article means two or more than two.

[0017] The drone status detection method provided in the present application is used to detect whether the drone arm has reached the unfolded state. The drone is provided with a camera device capable of capturing images at the drone arm, and its corresponding execution subject is a processing unit capable of calling and processing the data collected by the drone.

[0018] See also Figure 1 , Figure 1 : is a flow chart of an implementation method of a drone status detection method of the present application, the method comprising:

[0019] S101: Acquire an image to be identified captured by a camera device, and determine a detection position of an arm of a drone in the image to be identified.

[0020] Specifically, an image to be identified captured by a camera device on the drone is obtained, the position of the drone arm is determined from the image to be identified, and the detection position of the drone arm is obtained.

[0021] In one application, an image to be identified captured by a camera device is obtained, the outline of the drone arm in the image to be identified is identified, the position corresponding to the outline of the drone arm in the image to be identified is determined, and the detection position of the drone arm is obtained.

[0022] In another application mode, an image to be identified captured by a camera device is obtained, a positioning area on the drone arm in the image to be identified is identified, a position corresponding to the positioning area on the drone arm in the image to be identified is determined, and the detection position of the drone arm is obtained. The positioning area is a selected point or a divided range on the drone arm.

[0023] Optionally, the images to be identified have the same image size and a preconfigured image coordinate system, and the detected position of the drone arm corresponds to the coordinates of at least a partial area on the drone arm in the image coordinate system.

[0024] In some implementation scenarios, the background area in the image to be identified is determined, the image area outside the background area is extracted from the image to be identified to obtain an image area with higher accuracy, image features are obtained from the extracted image area, the outline of the drone arm is determined based on the image features, and the coordinates of the outline of the drone arm in the image to be identified are obtained.

[0025] In some implementation scenarios, the positioning area on the drone arm is set with a color that is different from other areas, and the image area with obvious color distinction is extracted from the image to be identified, and the positioning area is determined from the extracted image area to obtain the coordinates of the positioning area in the image to be identified.

[0026] It should be noted that there is an image acquisition trigger condition corresponding to the image to be identified being collected by the camera device. When the image acquisition trigger condition is triggered, the camera device collects the image to be identified toward the drone arm.

[0027] In some implementation scenarios, the image acquisition trigger condition is triggered by the user, the position of the drone arm is adjusted by the user, and the image acquisition trigger condition is triggered after the adjustment is completed, so that the image acquisition trigger condition is triggered when the user needs to detect the deployment state of the drone arm.

[0028] In some implementation scenarios, the image acquisition trigger condition is automatically triggered, the position of the UAV arm is adjusted by the driving device, and the image acquisition trigger condition is triggered after the driving device stops working, so as to realize the automation of the detection of the deployment status of the UAV arm and ensure that the UAV performs at least one status detection before performing a mission.

[0029] It is understandable that the camera device has a higher resolution to ensure detection accuracy, and the camera device can have the function of collecting infrared images and thermal imaging images, thereby improving applicability in different environments.

[0030] Furthermore, the number of the camera device is at least one. When there is one camera device, the camera device uses a wide-angle camera, so that the image to be identified includes all drone arms. When there are multiple camera devices, the image to be identified captured by the camera device includes at least one drone arm. When each drone arm corresponds to one camera device, the camera device faces the corresponding drone arm and captures the image to be identified.

[0031] S102: Obtain a calibration area of ​​the drone arm in the calibration image, and determine whether the drone arm has reached an unfolded state based on the calibration area and the detection position; wherein the calibration image is an image captured when the drone arm reaches an unfolded state.

[0032] Specifically, the position of the drone arm in the calibration image is obtained, and the calibration area of ​​the drone arm is determined, wherein the calibration image is an image captured when the drone arm reaches the unfolded state, so that the calibration area corresponding to the drone arm that reaches the unfolded state can be accurately obtained in the calibration image, and based on the positional relationship between the calibration area and the detection position, it is judged whether the drone arm has reached the unfolded state to obtain the detection result of the drone state.

[0033] It can be understood that the calibration image is an image captured by the camera device of the corresponding drone arm in the unfolded state. The calibration area is predetermined and the process of determining the calibration area is similar to the process of determining the detection position. However, taking into account the acquisition error and environmental changes, the calibration area is determined based on multiple calibration images. The calibration area represents the theoretical range of at least part of the area on the drone arm in the calibration image. That is to say, when the calibration area is set in any calibration image, the drone arm in the unfolded state is located in the calibration area.

[0034] In one application, the detection position and the calibration area are determined based on the contour of the drone arm, the overlap between the detection position and the calibration area is obtained, and whether the drone arm has reached the deployed state is determined based on the overlap. When the detection position is completely located in the calibration area, it is determined that the drone arm has reached the deployed state, and when the detection position is not completely located in the calibration area, it is determined that the drone arm has not reached the deployed state.

[0035] In another application mode, the detection position and the calibration area correspond to the positioning area on the drone arm. For each positioning area, the distance difference between the detection position and the center point of the calibration area is obtained, and whether the drone arm has reached the deployed state is determined based on the distance difference. When the distance difference is less than the distance threshold, it is determined that the drone arm has reached the deployed state, and when the distance difference is greater than or equal to the distance threshold, it is determined that the drone arm has not reached the deployed state.

[0036] It is understandable that the precise position of the drone arm is calibrated and detected by using the visual features on the image, and this is used to analyze whether the drone arm is fully deployed, reduce the impact of signal quality on the detection results, and improve the reliability of drone status detection. When multiple camera devices respectively capture at least one drone arm corresponding to each of them, the drone arm in the image to be identified captured by each camera device is detected based on the above steps.

[0037] Optionally, after determining the detection result of whether the drone arm has reached the unfolded state, if the drone arm has not reached the unfolded state, a prompt message is generated and displayed to the user, so as to prompt the user to adjust the drone arm to the unfolded state, and perform the test again after the user adjusts. The prompt message can be voice broadcast or sent to an application bound to the drone.

[0038] The above scheme obtains the image to be identified captured by the camera device on the drone, determines the position of the drone arm from the image to be identified, obtains the detection position of the drone arm, obtains the position of the drone arm in the calibration image, and determines the calibration area of ​​the drone arm, wherein the calibration image is an image captured when the drone arm reaches the unfolded state, so that the calibration area corresponding to the drone arm that reaches the unfolded state can be accurately obtained in the calibration image, and based on the positional relationship between the calibration area and the detection position, it is judged whether the drone arm reaches the unfolded state, and the detection result of the drone state is obtained, so as to use the visual features on the image to calibrate and detect the precise position of the drone arm, and thereby analyze whether the drone arm is fully unfolded, reduce the influence of signal quality on the detection result, and improve the reliability of drone state detection.

[0039] See also Figure 2 , Figure 2 It is a flow chart of another embodiment of the method for detecting the state of a drone of the present application. A driving motor is connected to one end of the drone arm away from the drone base, and a locking mechanism is provided on the drone arm. The method includes:

[0040] S201: Acquire an image to be identified captured by a camera device, and determine a detection position of an arm of a drone in the image to be identified.

[0041] Specifically, an image to be identified captured by a camera device is acquired, a detection position of a locking mechanism on an arm of the drone in the image to be identified is determined, and a detection position of a driving motor connected to the arm of the drone is determined.

[0042] In one application mode, an image to be identified captured by a camera device is acquired, and detection coordinates of the drive motor and the locking mechanism in the image to be identified are determined.

[0043] Specifically, the image to be identified captured by the camera device is obtained, the driving motor and the locking mechanism in the image to be identified are detected, the detection frame where the driving motor and the locking mechanism are located is obtained, and the detection coordinates corresponding to the detection frame where the driving motor and the locking mechanism are located are determined in the image to be identified. The image to be identified and the calibration image have the same image size, the image to be identified and the calibration image have the same image coordinate system, the detection coordinates of the driving motor are the coordinates of the detection frame of the driving motor in the image coordinate system, and the detection coordinates of the locking mechanism are the coordinates of the detection frame of the locking mechanism in the image coordinate system.

[0044] It is understandable that the drive motor and the locking mechanism are smaller in size than the entire drone arm. By detecting the drive motor and the locking mechanism in the image to be identified, the detection of the entire drone arm can be broken down into the detection of the drive motor and the locking mechanism, and smaller areas can be extracted from the drone arm and from the area to which the drone arm is connected, making the detection process more refined and thus improving the detection accuracy.

[0045] It should be noted that in addition to the drive motor and locking mechanism mentioned in this application, other areas related to the drone arm can also be used as detected areas, and this application does not impose any specific restrictions on this.

[0046] In some implementation scenarios, each drone arm of the drone also includes a sensor connected to the locking mechanism. When the locking mechanism is locked, the corresponding sensor triggers a locking signal.

[0047] It should be noted that before obtaining the image to be identified captured by the camera device and determining the detection position of the drone arm in the image to be identified, it also includes: in response to obtaining a locking signal triggered by a sensor on at least one drone arm, sending an image acquisition instruction to the camera device.

[0048] Specifically, when it is detected that a locking signal is triggered by a sensor on at least one arm of the drone, an image acquisition instruction is sent to the camera device so that the camera device acquires the image to be identified.

[0049] It can be understood that after the locking mechanism locks the drone arm, the drone arm cannot continue to be adjusted. The corresponding sensor triggers a locking signal after detecting that the locking mechanism is locked. When a locking signal is triggered by a sensor on at least one drone arm, an image acquisition instruction is sent to the corresponding camera device to realize the automation of the acquisition of the image to be identified. The image to be identified is acquired after the drone arm can no longer be adjusted, which improves the accuracy of the acquisition time node of the image to be identified.

[0050] In a specific implementation scenario, each camera device corresponds to a drone arm. When the locking mechanism on the drone arm is locked, an image acquisition instruction is sent to the corresponding camera device, so as to accurately control the time node of each drone arm collecting the image to be identified, and detect whether each drone arm has reached the unfolded state.

[0051] In a specific implementation scenario, each camera device corresponds to a drone arm. When the locking mechanism on any drone arm is locked, an image acquisition instruction is sent to all camera devices, thereby acquiring images to be identified at all drone arms, and timely detecting whether all drone arms captured by the camera device have reached the unfolded state. When some drone arms have not reached the unfolded state, prompt information is generated to adjust the drone arms that have not reached the unfolded state, thereby improving the real-time nature of the prompt information.

[0052] In a specific implementation scenario, each camera device corresponds to multiple drone arms. When one of the locking mechanisms of the multiple drone arms corresponding to the camera device is locked, an image acquisition instruction is sent to the corresponding camera device, so as to timely detect whether all drone arms captured by the camera device have reached the unfolded state. When some drone arms have not reached the unfolded state, prompt information is generated to adjust the drone arms that have not reached the unfolded state, thereby improving the real-time nature of the prompt information.

[0053] Optionally, the driving motor and the locking mechanism each include at least one calibration range, and the calibration range is provided with a color different from other areas.

[0054] Specifically, at least one calibration range is pre-set on each of the driving motor and the locking mechanism, and a color different from other areas is set within the calibration range, thereby reducing the difficulty of locating the calibration range in the image to be identified and saving processing resource consumption during image processing.

[0055] In a specific implementation scenario, the drive motor includes a motor base and a motor body, and the drive motor is pre-divided into corresponding calibration ranges according to the motor base and the motor body, and the locking mechanism has a corresponding calibration range. The shape corresponding to the calibration range can be any custom shape, and this application does not make specific restrictions on this.

[0056] S202: Obtain a calibration area of ​​the drone arm in the calibration image, and determine whether the drone arm has reached an unfolded state based on the calibration area and the detection position; wherein the calibration image is an image captured when the drone arm reaches an unfolded state.

[0057] Specifically, a calibration area of ​​the drone arm in the calibration image is obtained, and based on the positional relationship between the calibration area and the detection position, it is judged whether the drone arm has reached the deployed state, and a detection result of the drone state is obtained.

[0058] It can be understood that the calibration area corresponds to the calibration coordinate range of the drive motor and the locking mechanism. Based on the calibration area and the detection position, it is determined whether the UAV arm has reached the deployed state, including: based on the calibration coordinate range of the drive motor and the detection coordinates of the drive motor, as well as the calibration coordinate range of the locking mechanism and the detection coordinates of the locking mechanism, it is determined whether the UAV arm has reached the deployed state.

[0059] Specifically, based on the positional relationship between the calibrated coordinate range of the drive motor and the detected coordinates of the drive motor, as well as the positional relationship between the calibrated coordinate range of the locking mechanism and the detected coordinates of the locking mechanism, it is determined whether the drone arm has reached the deployed state, thereby improving the accuracy of state detection through a more sophisticated coordinate matching method in a small area.

[0060] In a specific implementation scenario, a first degree of overlap between the calibrated coordinate range of the drive motor and the detected coordinates of the drive motor, and a second degree of overlap between the calibrated coordinate range of the locking mechanism and the detected coordinates of the locking mechanism are obtained, and whether the drone arm has reached the deployed state is determined based on the first degree of overlap and the second degree of overlap. Only when the detected coordinates of the drive motor and the locking mechanism are both within the corresponding calibrated coordinate ranges, is it determined that the drone arm has reached the deployed state.

[0061] In a specific implementation scenario, a first distance difference between the center point of the calibrated coordinate range of the drive motor and the detected coordinate of the drive motor, and a second distance difference between the center point of the calibrated coordinate range of the locking mechanism and the detected coordinate of the locking mechanism are obtained, and whether the drone arm has reached the deployed state is determined based on the first distance difference and the second distance difference. Only when both the first distance difference and the second distance difference are less than the distance threshold, it is determined that the drone arm has reached the deployed state.

[0062] It should be noted that the calibration process of the calibration coordinate range includes: obtaining multiple calibration images of the same size and determining the center coordinates in the calibration images; determining the calibration coordinate range of the drive motor based on the calibration range and center coordinates of the drive motor in the multiple calibration images, and determining the calibration coordinate range of the locking mechanism based on the calibration range and center coordinates of the locking mechanism in the multiple calibration images.

[0063] Specifically, multiple calibration images are acquired and preprocessed to obtain calibration images of the same size, and the center coordinates are determined in the calibration images of the same size, wherein the center coordinates may be a specified position in the calibration image.

[0064] Furthermore, based on the distance of the calibration range of the drive motor relative to the center coordinate in multiple calibration images, the calibration coordinate range theoretically corresponding to the drive motor is circled from the calibration image, thereby reducing the impact of the acquisition angle and environmental changes on the calibration coordinate range of the drive motor. Similarly, based on the distance of the calibration range of the locking mechanism relative to the center coordinate in multiple calibration images, the calibration coordinate range theoretically corresponding to the locking mechanism is circled from the calibration image, thereby reducing the impact of the acquisition angle and environmental changes on the calibration coordinate range of the locking mechanism.

[0065] S203: In response to any drone arm not reaching the unfolded state, obtaining the mission state of the drone.

[0066] Specifically, when it is detected that the arm of any drone has not reached the unfolded state, the current mission state of the drone is obtained to confirm whether the drone is currently performing a mission.

[0067] S204: Based on the mission status, generate prompt information related to the drone arm that has not reached the unfolded state.

[0068] Specifically, when the mission status is not taken off, the prompt information is used to prompt the user to check the drone arms that have not reached the unfolded state. When the mission status is taken off, the prompt information is used to prompt the user to control the drone to land and check the drone arms that have not reached the unfolded state. Therefore, prompt information is used to send prompts to users in a timely manner to improve the safety of drone mission execution.

[0069] It is understandable that when the drone has not taken off to perform a mission, a prompt message is generated to prompt the user to check the drone arms that have not reached the unfolded state. When the drone has taken off to perform a mission, a prompt message is generated to prompt the user to control the drone to land as soon as possible and check the drone arms that have not reached the unfolded state after landing.

[0070] Optionally, the prompt information includes the position of the drone arm that has not reached the unfolded state, so that the user can quickly locate the drone arm that needs to be adjusted. In addition, when the mission state is the take-off state, the output power of the drive motor is limited, thereby reducing the probability of the drone arm folding back during flight due to the drone arm not reaching the unfolded state.

[0071] In this embodiment, a driving motor is connected to one end of the drone arm away from the drone base, and a locking mechanism is provided on the drone arm. By detecting the driving motor and the locking mechanism in the image to be identified, the detection of the entire drone arm can be disassembled into the detection of the driving motor and the locking mechanism, and a smaller area is extracted from the drone arm and from the area to which the drone arm is connected, so that the detection process is more refined. Based on the positional relationship between the calibrated coordinate range of the driving motor and the detection coordinates of the driving motor, and the positional relationship between the calibrated coordinate range of the locking mechanism and the detection coordinates of the locking mechanism, it is determined whether the drone arm has reached the deployed state, thereby improving the accuracy of state detection in a small-sized area through a more refined coordinate matching method. When it is detected that any drone arm has not reached the deployed state, a prompt message is used to promptly remind the user, thereby improving the safety of the drone in performing tasks.

[0072] See also Figure 3 , Figure 3 30 is a schematic diagram of the structure of an implementation method of a drone control device of the present application. The drone control device 30 includes a memory 301 and a processor 302 coupled to each other, wherein the memory 301 stores program data (not shown), and the processor 302 calls the program data to implement the drone state detection method in the above embodiment. For the description of the relevant content, please refer to the detailed description of the above method embodiment, which will not be repeated here.

[0073] See also Figure 4 , Figure 4 It is a structural diagram of an embodiment of a computer-readable storage medium of the present application. The computer-readable storage medium 40 stores program data 400. When the program data 400 is executed by the processor, the drone status detection method in the above embodiment is implemented. For the description of the relevant content, please refer to the detailed description of the above method embodiment, which will not be repeated here.

[0074] See also Figure 3 and Figure 5 , Figure 5 It is a schematic structural diagram of an embodiment of a drone of the present application. The drone 50 is provided with a camera device 500 capable of collecting images at the drone arm and a drone control device 30 as described in the above embodiment.

[0075] It should be noted that the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present implementation scheme.

[0076] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0077] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or 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 to enable a computer device (which can be a personal computer, server, or network device, etc.) or a processor to execute all or part of the steps of each implementation method of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program code.

[0078] The above description is only an implementation method of the present application, and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly used in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A method for detecting the state of a drone, characterized in that: The drone is provided with a camera device capable of collecting images at the drone arm, and the method comprises: Acquire the image to be identified captured by the camera device, and determine the detection position of the drone arm in the image to be identified; wherein the image to be identified includes at least one drone arm; Acquire a calibration area of ​​the drone arm in a calibration image, and determine whether the drone arm reaches an unfolded state based on the calibration area and the detection position; wherein the calibration image is an image captured when the drone arm reaches the unfolded state; A drive motor is connected to one end of the drone arm away from the drone base, and a locking mechanism is provided on the drone arm; the drive motor and the locking mechanism each include at least one calibration range, and a color different from other areas is provided in the calibration range, the drive motor includes a motor base and a motor body, and the drive motor is pre-divided into respective corresponding calibration ranges according to the motor base and the motor body, and the locking mechanism corresponds to one calibration range; The step of acquiring the image to be identified captured by the camera device and determining the detection position of the drone arm in the image to be identified includes: Acquire the image to be identified captured by the camera device, and determine the detection coordinates of the drive motor and the locking mechanism in the image to be identified; wherein the calibration area corresponds to the calibration coordinate range of the drive motor and the locking mechanism, and the calibration coordinate range is obtained based on multiple calibration images; the calibration process of the calibration coordinate range includes: acquiring multiple calibration images of the same size, and determining the center coordinates in the calibration images; determining the calibration coordinate range of the drive motor based on the calibration range and the center coordinates of the drive motor in the multiple calibration images, and determining the calibration coordinate range of the locking mechanism based on the calibration range and the center coordinates of the locking mechanism in the multiple calibration images; The determining whether the drone arm reaches the deployed state based on the calibration area and the detection position includes: Based on the calibrated coordinate range of the drive motor and the detected coordinates of the drive motor, as well as the calibrated coordinate range of the locking mechanism and the detected coordinates of the locking mechanism, determining whether the drone arm has reached the deployed state; a first distance difference corresponds to a center point of the calibrated coordinate range of the drive motor and the detected coordinates of the drive motor, and a second distance difference corresponds to a center point of the calibrated coordinate range of the locking mechanism and the detected coordinates of the locking mechanism; when both the first distance difference and the second distance difference are less than a distance threshold, it is determined that the drone arm has reached the deployed state; Wherein, each of the camera devices corresponds to at least one of the drone arms, and when one of the locking mechanisms in the drone arms corresponding to the camera device has been locked, at least an image acquisition instruction is sent to the corresponding camera device.

2. The drone status detection method according to claim 1, characterized in that: Each of the drone arms of the drone also includes a sensor connected to the locking mechanism, and when the locking mechanism is locked, the corresponding sensor triggers a locking signal; Before acquiring the image to be identified captured by the camera device and determining the detection position of the drone arm in the image to be identified, the method further includes: In response to obtaining the locking signal triggered by at least one sensor on the drone arm, an image acquisition instruction is sent to the camera device.

3. The method for detecting the state of a drone according to claim 1, characterized in that: After obtaining the calibration area of ​​the drone arm in the calibration image and determining whether the drone arm has reached the deployed state based on the calibration area and the detection position, the method further includes: In response to any of the drone arms not reaching the deployed state, obtaining the mission state of the drone; Based on the mission status, prompt information related to the drone arm that has not reached the deployed state is generated; wherein, when the mission status is a non-take-off state, the prompt information is used to prompt the user to check the drone arm that has not reached the deployed state, and when the mission status is a take-off state, the prompt information is used to prompt the user to control the drone to land and check the drone arm that has not reached the deployed state.

4. A drone control device, characterized in that: include: A memory and a processor coupled to each other, wherein the memory stores program data, and the processor calls the program data to execute the method according to any one of claims 1 to 3.

5. A computer-readable storage medium having program data stored thereon, characterized in that: When the program data is executed by a processor, the method according to any one of claims 1 to 3 is implemented.

6. A drone, characterized in that: The drone is provided with a camera device capable of collecting images at the drone arm and the drone control device as claimed in claim 4.