Method and device for detecting external parameters of unmanned aerial vehicle

Abstract

The present application relates to the technical field of unmanned aerial vehicle, and especially relates to a detection method and device for external parameters of unmanned aerial vehicle. The method comprises the following steps: determining a first description value of a bearing surface according to attitude data of the unmanned aerial vehicle when the unmanned aerial vehicle is static on the bearing surface; determining a second description value of the bearing surface according to camera data of the bearing surface shot by the unmanned aerial vehicle in a flight state; and determining an external parameter error of the unmanned aerial vehicle according to the first description value and the second description value. The embodiment of the present application can realize online detection of the external parameters of the unmanned aerial vehicle more simply, and the external parameter error is detected depending on fixed environmental information such as the bearing surface, so that the detection result has higher robustness.

Description

Technical Field

[0001] This invention relates to the field of unmanned aerial vehicle (UAV) technology, and in particular to a method and apparatus for detecting external parameters of UAVs. Background Technology

[0002] Cameras, inertial measurement units (IMUs), and odometry are the main sensors used by UAVs to perceive their own state or flight environment. Accurately acquiring the spatial position and attitude transformation relationships between the coordinate systems of each sensor—that is, calibrating the sensor extrinsic parameters—is a necessary prerequisite for fusing data from various sensors. Currently, iterative optimization is mainly used to calibrate UAV extrinsic parameters. This involves constructing an objective function and optimization equations for the UAV extrinsic parameters, and obtaining the optimal solution for the UAV extrinsic parameters through iterative optimization of the objective function and optimization equations. While this method can correct the UAV extrinsic parameters during flight, achieving convergence in state estimation requires the UAV to maintain rotational and translational motion for a certain period, and changes in the flight environment can also affect the accuracy of the UAV extrinsic parameter estimation. Summary of the Invention

[0003] In view of this, embodiments of the present invention provide a method and apparatus for detecting the external parameters of a UAV, which can easily realize online detection of the external parameters of a UAV, and relies on fixed environmental information such as the bearing surface to detect external parameter errors, and the detection results have high robustness.

[0004] In a first aspect, embodiments of the present invention provide a method for detecting the extrinsic parameters of a UAV, comprising:

[0005] Based on the drone attitude data when the drone is stationary on the bearing surface, a first description value of the bearing surface is determined;

[0006] A second descriptive value for the bearing surface is determined based on camera data of the bearing surface captured by the UAV in flight.

[0007] The extrinsic error of the UAV is determined based on the first descriptive value and the second descriptive value.

[0008] Optionally, determining the first descriptive value of the bearing surface based on the drone's attitude data when the drone is stationary on the bearing surface includes:

[0009] Based on the UAV attitude data, determine the rotation matrix of the UAV in the world coordinate system.

[0010] According to the rotation matrix The true value of the normal vector of the bearing surface is determined and used as the first descriptive value.

[0011] Optionally, determining the second descriptive value of the bearing surface based on camera data of the bearing surface captured by the drone in flight includes:

[0012] Based on the camera data, a planar model of the bearing surface is established;

[0013] Based on the bearing surface plane model, the normal vector measurement value of the bearing surface in the world coordinate system is determined and used as the second descriptive value.

[0014] Optionally, determining the normal vector measurement value of the bearing surface in the world coordinate system based on the bearing surface plane model includes:

[0015] Based on the plane model of the bearing surface, determine the normal vector of the bearing surface in the camera coordinate system.

[0016] The normal vector Converted to the measured value of the normal vector.

[0017] Optionally, the bearing surface planar model is determined based on the planar point cloud of the bearing surface captured by the UAV in flight, and the normal vector of the bearing surface in the camera coordinate system is determined based on the bearing surface planar model. include:

[0018] The eigenvector corresponding to the minimum eigenvalue of the bearing surface plane model is determined as the normal vector.

[0019] Optionally, the bearing surface is provided with markers, and the bearing surface planar model is determined based on the marker corner points in the image of the markers taken by the UAV in flight. The normal vector of the bearing surface in the camera coordinate system is determined based on the bearing surface planar model. include:

[0020] Based on the corner points of the marker, determine the rotation matrix of the center coordinate system of the marker's image relative to the camera coordinate system.

[0021] The rotation matrix Convert to the normal vector

[0022] Optionally, the normal vector Converting to the normal vector measurement value includes:

[0023] Based on the rotation matrix of the UAV from the world coordinate system to the sensor coordinate system during flight. And the external parameters of rotation from the sensor coordinate system to the camera coordinate system The normal vector Converted to the measured value of the normal vector.

[0024] Optionally, determining the extrinsic parameter error of the UAV based on the first descriptive value and the second descriptive value includes:

[0025] The extrinsic error of the UAV is determined based on the Euclidean distance between the first descriptive value and the second descriptive value;

[0026] If the Euclidean distance is greater than a set threshold, then the extrinsic parameter error is an abnormal error.

[0027] Optionally, determining the extrinsic error of the UAV based on the Euclidean distance between the first descriptive value and the second descriptive value includes:

[0028] Determine the average of multiple second description values ​​within a preset time period;

[0029] The extrinsic parameter error is determined based on the Euclidean distance between the first descriptive value and the mean.

[0030] Secondly, embodiments of the present invention provide a device for detecting the external parameters of a UAV, comprising:

[0031] The first determining module is used to determine a first description value of the bearing surface based on the drone attitude data when the drone is stationary on the bearing surface;

[0032] The second determining module is used to determine a second description value of the bearing surface based on camera data of the bearing surface captured by the UAV in flight.

[0033] An extrinsic parameter correction module is used to determine the extrinsic parameter error of the UAV based on the first descriptive value and the second descriptive value.

[0034] Thirdly, embodiments of the present invention provide a device for detecting external parameters of an unmanned aerial vehicle (UAV), comprising: at least one processor; and at least one memory communicatively connected to the processor, wherein: the memory stores program instructions executable by the processor, and the processor invokes the program instructions to perform the method as described in the first aspect or any embodiment of the first aspect.

[0035] Fourthly, embodiments of the present invention provide a computer-readable storage medium comprising a stored program, wherein, when the program is executed, it controls the device on which the computer-readable storage medium is located to perform the method described in the first aspect or any embodiment of the first aspect.

[0036] In this embodiment of the invention, descriptive values ​​about the bearing surface are acquired when the UAV is stationary on the bearing surface and when the UAV is in flight, respectively, thereby determining the error of the UAV's extrinsic parameters based on the bearing surface descriptive values. This embodiment of the invention, by detecting extrinsic parameter errors based on fixed environmental information such as the bearing surface, can minimize the impact of atmospheric and lighting conditions on the accuracy of the detection results, thus improving the robustness of the UAV's extrinsic parameter detection results. Furthermore, this embodiment of the invention has a simple implementation process and saves UAV computing resources. Attached Figure Description

[0037] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0038] Figure 1 A flowchart of a method for detecting external parameters of an unmanned aerial vehicle (UAV) provided in an embodiment of the present invention;

[0039] Figure 2 A schematic diagram of a drone stationary on a bearing surface, provided as an embodiment of the present invention;

[0040] Figure 3 This is a schematic diagram of a drone in flight, provided as an embodiment of the present invention.

[0041] Figure 4 A flowchart of another method for detecting external parameters of a UAV provided in an embodiment of the present invention;

[0042] Figure 5 A flowchart of another method for detecting external parameters of a UAV provided in an embodiment of the present invention;

[0043] Figure 6 This is a schematic diagram of a QR code set on a bearing surface according to an embodiment of the present invention;

[0044] Figure 7 This is a schematic diagram of the structure of a device for detecting external parameters of an unmanned aerial vehicle (UAV) according to an embodiment of the present invention;

[0045] Figure 8 This is a schematic diagram of the structure of a device for detecting external parameters of a UAV provided in an embodiment of the present invention. Detailed Implementation

[0046] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0047] See Figure 1 This is a flowchart illustrating a method for detecting extrinsic parameters of a drone according to an embodiment of the present invention. The subject of this method is the drone, specifically a processing device installed on the drone. Figure 1 As shown, the processing steps of this method include:

[0048] 101. Based on the drone attitude data when the drone is stationary on the bearing surface, determine the first descriptive value of the bearing surface.

[0049] See Figure 2 This is a schematic diagram illustrating a drone stationary on a bearing surface, as provided in an embodiment of the present invention. Figure 2 As shown, the above-mentioned bearing surface is a plane with a high degree of parallelism, for example, the above-mentioned bearing surface is a drone landing pad.

[0050] In some embodiments, determining that the drone is stationary on the support surface may include: acquiring the height value of the drone above the support surface, and determining that the drone is stationary on the support surface when the height value is less than a first threshold. Optionally, the first threshold can be set according to actual needs, for example, the first threshold is 0.5 meters. That is, when the height value of the drone above the support surface is less than 0.5 meters, the drone is determined to be stationary on the support surface.

[0051] In some embodiments, when the UAV is stationary on the support surface, UAV attitude data can be acquired via an IMU. Specifically, the UAV attitude data may include UAV pitch angle, acceleration, angular velocity, etc. Optionally, a first descriptive value of the support surface can be determined based on the UAV attitude data acquired by the IMU.

[0052] In some embodiments, determining a first descriptive value of the bearing surface based on the UAV attitude data when the UAV is stationary on the bearing surface may include: determining the rotation matrix of the UAV in the world coordinate system based on the UAV attitude data when the UAV is stationary on the bearing surface. Based on the rotation matrix of the UAV in the world coordinate system Determine the true value of the normal vector of the bearing surface. Used as the first descriptive value of the bearing surface.

[0053] In some embodiments, based on the rotation matrix of the UAV in the world coordinate system Determine the true value of the normal vector of the bearing surface. Includes: according to the formula Calculate the true value of the normal vector of the bearing surface. Where k is the unit vector of the UAV in the Z-axis direction in the world coordinate system, and is a known value.

[0054] It should be noted that the drone's attitude data when stationary on the support surface, or the first descriptive value of the support surface, can be pre-stored in the drone. When the drone needs to perform extrinsic parameter detection during flight, the stored drone attitude data or the first descriptive value of the support surface can be directly retrieved. Alternatively, after the drone activates the extrinsic parameter detection function, the drone's attitude data when stationary on the support surface can be obtained, and the first descriptive value can be calculated.

[0055] 102. Determine the second descriptive value of the bearing surface based on camera data of the bearing surface taken by the UAV in flight.

[0056] In some embodiments, the drone captures camera data of the bearing surface using a downward-looking camera while in flight, and determines a second descriptive value of the bearing surface based on the camera data.

[0057] See Figure 3 This is a schematic diagram of a drone in flight, provided by an embodiment of the present invention. Figure 3 As shown, the timing for the drone to capture camera data of the bearing surface while in flight can include: when the drone's altitude above the bearing surface is greater than or equal to a first threshold and less than a second threshold, the drone captures camera data of the bearing surface using a downward-looking camera. Optionally, the second threshold can be set according to actual needs, and the second threshold is less than the drone's maximum flight altitude; for example, the second threshold is 8 meters. In some embodiments, during the process of the drone changing from a stationary state to a takeoff state, when the takeoff altitude is greater than or equal to the first threshold and less than the second threshold, camera data of the bearing surface is captured using a downward-looking camera. In some embodiments, during the process of the drone changing from a normal flight state to a descent state, when the drone's altitude after descent is greater than or equal to the first threshold and less than the second threshold, camera data of the bearing surface is captured using a downward-looking camera.

[0058] In some embodiments, after acquiring camera data of the bearing surface captured by the UAV in flight, a planar model of the bearing surface can be established based on the camera data. Then, based on the planar model, the measured normal vector value of the bearing surface in the world coordinate system can be determined. The measured normal vector value of the bearing surface in the world coordinate system can then be used as the second descriptive value of the bearing surface.

[0059] In some embodiments, determining the measured value of the normal vector of the bearing surface in the world coordinate system based on the bearing surface plane model includes: determining the normal vector of the bearing surface in the camera coordinate system based on the bearing surface plane model. The normal vector of the bearing surface in the camera coordinate system Convert to the normal vector measurement of the bearing surface in the world coordinate system.

[0060] In some embodiments, the normal vector of the bearing surface in the camera coordinate system is... Convert to the normal vector measurement of the bearing surface in the world coordinate system. This includes: the rotation matrix from the world coordinate system to the sensor coordinate system based on the UAV's flight state. And the external parameter R of rotation from the sensor coordinate system to the camera coordinate system bc The normal vector of the camera coordinate system Normal vector measurement converted to world coordinate system

[0061] 103. Determine the external parameter error of the UAV based on the first and second description values ​​of the bearing surface.

[0062] As a fixed environment for the drone's parking, the description values ​​of the bearing surface, measured using different methods, should theoretically remain consistent. Based on this principle, this embodiment of the invention acquires the description values ​​of the bearing surface when the drone is stationary on the bearing surface and when the drone is in flight. The first and second description values ​​of the bearing surface are determined based on data collected by the drone's IMU and downward-looking camera, respectively. If the extrinsic parameter calibration of the drone's IMU and downward-looking camera is relatively accurate, the first and second description values ​​will be relatively consistent; if the extrinsic parameter error of the drone is large, there will also be a large error between the first and second description values. Based on this, this embodiment of the invention can determine the error of the drone's extrinsic parameters based on the first and second description values.

[0063] In some embodiments, the extrinsic parameter error of the UAV can be determined based on the Euclidean distance between the first and second descriptive values. When the Euclidean distance between the first and second descriptive values ​​is small, the extrinsic parameter error of the UAV is also small; when the Euclidean distance between the first and second descriptive values ​​is large, it indicates that the extrinsic parameters of the UAV have a large error, and the UAV extrinsic parameters need to be recalibrated.

[0064] In some embodiments, when calculating the Euclidean distance between the first description value and the second description value, multiple second description values ​​of the bearing surface can be calculated based on camera data collected within a preset time period. The Euclidean distance between the first description value and the average of these multiple second description values ​​is then calculated.

[0065] In the embodiments of the present invention, external parameter error detection is performed based on fixed environmental information such as the bearing surface, which can minimize the impact of atmospheric and light environments on the accuracy of detection results and improve the robustness of UAV external parameter detection results.

[0066] Furthermore, the embodiments of the present invention perform the detection of external parameters of the UAV during the take-off or landing process of the UAV, which is simple to implement and does not require the use of computing resources when the UAV is operating at high altitude.

[0067] Furthermore, when performing external parameter detection during drone takeoff, the detection of external parameters can be completed within a short period of time after takeoff, and an immediate alarm can be triggered when the external parameters are abnormal.

[0068] See Figure 4 This is a flowchart illustrating another method for detecting extrinsic parameters of a UAV provided in an embodiment of the present invention. In this embodiment, the planar model of the bearing surface is determined based on the planar point cloud of the bearing surface captured by the UAV in flight. Figure 4 As shown, when the drone activates the extrinsic parameter detection function, the following steps are executed:

[0069] 201. Determine the altitude of the UAV above the support surface based on data collected by the altitude sensor. Optionally, the altitude sensor can be a barometer, ultrasonic sensor, GPS, etc. The altitude of the UAV above the support surface can be determined based on the data collected by the altitude sensor.

[0070] 202. When the aforementioned height value is less than the first threshold, the true value of the normal vector of the bearing surface is determined based on the UAV attitude data collected by the IMU.

[0071] The aforementioned first threshold value is relatively small and is used to determine whether the drone is stationary or approximately stationary on the support surface. Optionally, this first threshold can be determined based on the drone's fuselage height; for example, the fuselage height or 0.5 times the fuselage height can be used as the first threshold. If the drone's height from the support surface is less than the first threshold, it is determined that the drone is stationary or approximately stationary on the support surface. In this case, the true value of the normal vector of the support surface can be determined based on the drone's attitude data collected by the IMU.

[0072] 203. When the aforementioned height value is greater than or equal to the first threshold and less than the second threshold, the planar point cloud of the bearing surface is captured by a camera. Optionally, the planar point cloud of the bearing surface can be captured by a binocular camera mounted on a drone.

[0073] 204. Establish a planar model of the bearing surface based on the planar point cloud. Optionally, after obtaining the planar point cloud of the bearing surface, a planar model of the bearing surface can be established based on the RANSAC algorithm.

[0074] 205. The eigenvector corresponding to the smallest eigenvalue of the bearing surface planar model is determined as the normal vector of the bearing surface in the camera coordinate system.

[0075] 206, the normal vector of the bearing surface in the camera coordinate system. Convert to the normal vector measurement of the bearing surface in the world coordinate system.

[0076] in, Let be the rotation matrix of the UAV in the world coordinate system during flight, and k be the unit vector of the UAV in the Z-axis direction in the world coordinate system.

[0077] Optionally, the following formula can be used to... Convert to

[0078] in, Let R be the rotation matrix from the world coordinate system to the sensor coordinate system for the UAV at flight time τ; bc This is the rotational extrinsic parameter from the sensor coordinate system to the camera coordinate system.

[0079] 207, based on the true value of the normal vector of the bearing surface and normal vector measurement value The Euclidean distance d between them is used to determine the external parameter error of the drone. If the Euclidean distance is greater than the set threshold, the external parameter error of the drone is considered an abnormal error.

[0080] In some embodiments,

[0081] In this embodiment of the invention, it is assumed that the UAV attitude data measurement is accurate; therefore, the change in vector distance d mainly originates from R. bc and when When the solution is satisfactory, the UAV extrinsic parameters R can be evaluated using the vector distance d. bc The accuracy of the rotation parameters is such that when d is large, it indicates that there is an error in the external parameters and recalibration is required.

[0082] See Figure 5 This is a flowchart illustrating another method for detecting external parameters of a UAV provided in an embodiment of the present invention. In this embodiment, a marker is provided on the bearing surface. The UAV takes an image of the marker on the bearing surface while in flight, and establishes a planar model of the bearing surface based on the marker corner points in the image taken in flight. Figure 5 As shown, when the UAV enables the extrinsic parameter detection function, the execution steps of this method include:

[0083] 301. Determine the height of the drone from the bearing surface based on the data collected by the altitude sensor.

[0084] 302. When the aforementioned height value is less than the first threshold, the true value of the normal vector of the bearing surface is determined based on the UAV attitude data collected by the IMU.

[0085] 303. When the height value is greater than or equal to the first threshold and less than the second threshold, an image of the marker set on the bearing surface is captured by a camera. For example... Figure 6 As shown, the marker on the bearing surface can be a QR code. When the height value is greater than or equal to the first threshold but less than the second threshold, an image of the QR code can be captured by a monocular camera.

[0086] 304. Identify the corner points of the sign from the captured image of the sign, and establish a planar model of the bearing surface based on the identified corner points. Optionally, when the image of the sign captured by a monocular camera is a QR code image, identify the four corner points of the outermost dimension of the QR code in the QR code image, and establish a planar model of the bearing surface based on the coordinates of these four corner points in the camera coordinate system.

[0087] 305. Based on the corner points of the marker identified from the marker image, determine the rotation matrix of the center coordinate system of the marker image relative to the camera coordinate system. Optionally, after recognizing the four outermost corner points of the QR code image, the rotation matrix of the QR code's center coordinate system relative to the camera frame can be solved using the PNP algorithm.

[0088] 306, based on the rotation matrix Determine the normal vector of the bearing surface in the camera coordinate system. Optional, it can be based on the formula Will Convert to k is the unit vector of the UAV in the Z-axis direction in the world coordinate system.

[0089] 307, the normal vector of the bearing surface in the camera coordinate system. Convert to the normal vector measurement of the bearing surface in the world coordinate system.

[0090] 308, based on the true value of the normal vector of the bearing surface and normal vector measurement value The Euclidean distance d between them is used to determine the external parameter error of the drone. If the Euclidean distance is greater than the set threshold, the external parameter error of the drone is considered an abnormal error.

[0091] Corresponding to the above-described method for detecting UAV extrinsic parameters, this embodiment of the invention also provides a device for detecting UAV extrinsic parameters. Those skilled in the art will understand that these devices can be configured using commercially available hardware components through the steps taught in this solution. Figure 7 This is a schematic diagram of a device for detecting the extrinsic parameters of a drone, provided as an embodiment of the present invention. Figure 7 As shown, the device includes: a first determining module 401, used to determine a first description value of the bearing surface based on the attitude data of the UAV when the UAV is stationary on the bearing surface; a second determining module 402, used to determine a second description value of the bearing surface based on camera data of the bearing surface taken by the UAV in flight; and an extrinsic parameter correction module 403, used to determine the extrinsic parameter error of the UAV based on the first description value and the second description value.

[0092] The UAV extrinsic parameter detection device of this embodiment of the invention can perform... Figures 1 to 6 The illustrated embodiment relates to a method for detecting extrinsic parameters of a UAV. For parts not described in detail in this embodiment, please refer to the [reference needed]. Figures 1 to 6 The relevant descriptions of the illustrated embodiments are provided below. For the execution process and technical effects of this technical solution, please refer to [link / reference]. Figures 1 to 6 The descriptions in the illustrated embodiments will not be repeated here.

[0093] It should be understood that Figure 7 The division of the various modules in the UAV extrinsic parameter detection device shown is merely a logical functional division. In actual implementation, they can be fully or partially integrated into a single physical entity, or they can be physically separated. Furthermore, these modules can be implemented entirely in software via processing element calls; they can be fully implemented in hardware; or some modules can be implemented in software via processing element calls, while others are implemented in hardware. For example, the first determining module 401 and the second determining module 402 can be separate processing elements, or they can be integrated into a chip in an electronic device. The implementation of other modules is similar. In addition, these modules can be fully or partially integrated together, or they can be implemented independently. During implementation, each step of the above method or each of the above modules can be completed through integrated logic circuits in the hardware of the processor element or through software instructions.

[0094] For example, these modules can be one or more integrated circuits configured to implement the above methods, such as one or more Application Specific Integrated Circuits (ASICs), one or more Digital Signal Processors (DSPs), or one or more Field Programmable Gate Arrays (FPGAs). Alternatively, these modules can be integrated together as a System-On-a-Chip (SOC).

[0095] Figure 8 This is a schematic diagram of a device for detecting the extrinsic parameters of a drone, provided as an embodiment of the present invention. The detection device is deployed on a drone. Figure 8 As shown, the drone is represented in the form of a general-purpose computing device. The components of the drone may include, but are not limited to: one or more processors 510, a communication interface 520, a memory 530, and a communication bus 540 connecting different system components (including the memory 530, the communication interface 520, and the processing unit 510).

[0096] The communication bus 540 represents one or more of several bus architectures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any of the various bus architectures. Examples of these architectures include, but are not limited to, the Industry Standard Architecture (ISA) bus, the Micro Channel Architecture (MAC) bus, the Enhanced ISA bus, the Video Electronics Standards Association (VESA) local bus, and the Peripheral Component Interconnect (PCI) bus.

[0097] Electronic devices typically include a variety of computer-readable media. These media can be any available media that can be accessed by the electronic device, including volatile and non-volatile media, and removable and non-removable media.

[0098] Memory 530 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) and / or cache memory. The electronic device may further include other removable / non-removable, volatile / non-volatile computer system storage media. Memory 530 may include at least one program product having a set (e.g., at least one) of program modules configured to execute embodiments of the present invention. Figures 1 to 6 The embodiment shown relates to a method for detecting external parameters of unmanned aerial vehicles.

[0099] A program / utility having a set (at least one) of program modules can be stored in memory 530. Such program modules include—but are not limited to—an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include an implementation of a network environment. The program modules typically execute embodiments of the present invention. Figures 1 to 6 The embodiment shown relates to a method for detecting external parameters of unmanned aerial vehicles.

[0100] Processor 510 executes various functional applications and data processing by running programs stored in memory 530, such as implementing the functions described in this specification. Figures 1-6 The embodiment shown relates to a method for detecting external parameters of unmanned aerial vehicles.

[0101] In a specific implementation, this application also provides a computer storage medium, wherein the computer storage medium may store a program, and the program, when executed, may include some or all of the steps provided in the various embodiments of this application. The storage medium may be a magnetic disk, optical disk, read-only memory (ROM), or random access memory (RAM), etc.

[0102] In a specific implementation, the present invention also provides a computer program product, which includes executable instructions that, when executed on a computer, cause the computer to perform some or all of the steps in the above method embodiments.

[0103] In this embodiment of the invention, "at least one" refers to one or more, and "more than one" refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent the existence of A alone, the simultaneous existence of A and B, or the existence of B alone. A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one of the following" and similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, and c can represent: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0104] Those skilled in the art will recognize that the units and algorithm steps described in the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of electronic hardware and software. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0105] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0106] In several embodiments provided by this invention, any function, if implemented as a software functional unit and sold or used as an independent product, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0107] The above description is merely a specific embodiment of the present invention. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this invention should be included within the protection scope of this invention. The protection scope of this invention should be determined by the scope of the claims.

Claims

1. A method for detecting extrinsic parameters of an unmanned aerial vehicle (UAV), characterized in that, include: Based on the drone attitude data when the drone is stationary on the bearing surface, a first description value of the bearing surface is determined; A second descriptive value for the bearing surface is determined based on camera data of the bearing surface captured by the UAV in flight. The external parameter error of the UAV is determined based on the first description value and the second description value; The step of determining the first descriptive value of the bearing surface based on the drone's attitude data when the drone is stationary on the bearing surface includes: Based on the UAV attitude data, determine the rotation matrix of the UAV in the world coordinate system. ; According to the rotation matrix The true value of the normal vector of the bearing surface is determined and used as the first descriptive value; The step of determining the second descriptive value of the bearing surface based on camera data of the bearing surface captured by the drone in flight includes: Based on the camera data, a planar model of the bearing surface is established; Based on the bearing surface plane model, the normal vector measurement value of the bearing surface in the world coordinate system is determined and used as the second descriptive value.

2. The method according to claim 1, characterized in that, The step of determining the normal vector measurement value of the bearing surface in the world coordinate system based on the bearing surface plane model includes: Based on the plane model of the bearing surface, determine the normal vector of the bearing surface in the camera coordinate system. ; The normal vector This is converted into the measured value of the normal vector.

3. The method according to claim 2, characterized in that, The bearing surface planar model is determined based on the planar point cloud of the bearing surface captured by the UAV in flight. The normal vector of the bearing surface in the camera coordinate system is then determined based on the bearing surface planar model. ,include: The eigenvector corresponding to the minimum eigenvalue of the bearing surface plane model is determined as the normal vector. .

4. The method according to claim 2, characterized in that, The bearing surface is provided with markers, and the bearing surface planar model is determined based on the marker corner points in the image of the markers taken by the UAV in flight. The normal vector of the bearing surface in the camera coordinate system is determined based on the bearing surface planar model. ,include: Based on the corner points of the marker, determine the rotation matrix of the center coordinate system of the marker's image relative to the camera coordinate system. ; The rotation matrix Converted into the normal vector .

5. The method according to any one of claims 2 to 4, characterized in that, The normal vector The conversion to the normal vector measurement value includes: Based on the rotation matrix of the UAV from the world coordinate system to the sensor coordinate system during flight. And the external parameters of rotation from the sensor coordinate system to the camera coordinate system , the normal vector Converted to the measured value of the normal vector.

6. The method according to claim 1, characterized in that, The step of determining the external parameter error of the UAV based on the first descriptive value and the second descriptive value includes: The extrinsic error of the UAV is determined based on the Euclidean distance between the first descriptive value and the second descriptive value; If the Euclidean distance is greater than a set threshold, then the extrinsic parameter error is an abnormal error.

7. The method according to claim 6, characterized in that, The step of determining the extrinsic parameter error of the UAV based on the Euclidean distance between the first descriptive value and the second descriptive value includes: Determine the average of multiple second description values ​​within a preset time period; The extrinsic parameter error is determined based on the Euclidean distance between the first descriptive value and the mean.

8. A device for detecting the external parameters of an unmanned aerial vehicle (UAV), characterized in that, include: At least one processor; as well as At least one memory communicatively connected to the processor, wherein: The memory stores program instructions that can be executed by the processor, which invokes the program instructions to perform the method as described in any one of claims 1 to 7.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein, when the program is executed, it controls the device on which the computer-readable storage medium is located to perform the method of any one of claims 1 to 7.

Images