Unmanned aerial vehicle ground target tracking method and system

Abstract

The invention belongs to the related technical field of robot tracking, and provides an unmanned aerial vehicle ground target tracking method and system, and the method comprises the steps: determining the distance from a ground mobile robot to four preset sound wave capturing positions in a mobile robot according to a sound wave signal and the sound wave receiving time; the coordinates of the ground mobile robot in the camera coordinate system are obtained according to the determined distance, and the coordinates of the ground mobile robot in the pixel coordinate system are determined according to the conversion relation from the camera coordinate system to the pixel coordinate system; according to the coordinates of the ground mobile robot in the pixel coordinate system, the relative orientation of the ground mobile robot in the unmanned aerial vehicle is determined, and image deviation is obtained; the unmanned aerial vehicle is controlled according to the relative orientation of the ground mobile machine in the unmanned aerial vehicle and the image deviation, tracking of the ground mobile machine is achieved, and the problem that accurate tracking cannot be achieved due to the fact that the unmanned aerial vehicle cannot obtain the precise position information of the unmanned aerial vehicle due to GPS signal loss is avoided on the basis of guaranteeing positioning and tracking precision.

Description

Technical Field

[0001] The present invention belongs to the technical field related to robot tracking, and in particular relates to a method and system for tracking ground targets by unmanned aerial vehicles. Background Art

[0002] UAV target tracking technology is one of the hot spots in the current UAV application field. It has broad application prospects by identifying and tracking specific targets in real time through the vision or other sensors on the UAV. The current UAV target tracking technology mainly relies on GPS signals and visual sensors. In an environment with good GPS signals, the UAV can obtain its own precise location information through the GPS receiver, and then accurately track the target; at the same time, the visual sensor monitors and tracks the moving target by capturing real-time images; and some advanced tracking algorithms and frameworks are also applied to UAV target tracking.

[0003] However, the current UAV target tracking methods will significantly reduce the tracking accuracy or even lose the target when facing low light conditions, especially extremely low brightness night scenes. Specifically, the lack of GPS signals will cause the UAV to be unable to obtain its own precise location information, and thus unable to accurately track the target; the light conditions at night are weak, and the camera needs to set a higher sensitivity and use a longer exposure time to obtain sufficient light, which may lead to a decrease in image quality and increase the difficulty of target tracking; at the same time, noise and interference in the night environment may also have a negative impact on the accuracy of target tracking, which limits the application of UAVs at night or in areas with limited GPS signals. Summary of the invention

[0004] In order to solve the above problems, the present invention proposes a method and system for tracking ground targets by unmanned aerial vehicles. The present invention determines the distance from a ground mobile robot to four preset sound wave capture positions in the mobile robot according to the sound wave signal and the time of receiving the sound wave; and obtains the coordinates of the ground mobile robot in the camera coordinate system according to the determined distance, and determines the coordinates of the ground mobile robot in the pixel coordinate system according to the transformation relationship from the camera coordinate system to the pixel coordinate system; determines the relative position of the ground mobile machine to the unmanned aerial vehicle according to the coordinates of the ground mobile robot in the pixel coordinate system, and obtains the image deviation; finally, controls the unmanned aerial vehicle according to the image deviation, realizes the tracking of the ground mobile machine, and avoids the problem that the unmanned aerial vehicle cannot obtain its own precise position information due to the lack of GPS signal, thereby failing to realize accurate tracking, on the basis of ensuring the positioning and tracking accuracy.

[0005] In order to achieve the above object, the present invention is implemented through the following technical solutions:

[0006] In a first aspect, the present invention provides a method for tracking a ground target by a UAV, comprising:

[0007] Acquire the acoustic wave signal of the ground mobile robot to be tracked, as well as the camera coordinate system and pixel coordinate system of the preset camera on the drone;

[0008] According to the sound wave signal and the time of receiving the sound wave, the distance from the ground mobile robot to four preset sound wave capture positions in the mobile robot is determined; and the coordinates of the ground mobile robot in the camera coordinate system are obtained according to the determined distance, and the coordinates of the ground mobile robot in the pixel coordinate system are determined according to the transformation relationship from the camera coordinate system to the pixel coordinate system;

[0009] According to the coordinates of the ground mobile robot in the pixel coordinate system, the relative position of the ground mobile machine to the UAV is determined, and the image deviation is obtained;

[0010] The UAV is controlled according to the relative position of the ground mobile machine to the UAV and the image deviation to track the ground mobile machine.

[0011] Furthermore, the optical center of the preset camera on the drone is used as the origin of the coordinate system, the Z axis coincides with the optical axis of the camera and points to the ground. The camera coordinate system is determined according to the right-hand rule, and the Y axis passes through the two acoustic wave catchers at the head and tail of the drone and points in the direction of the drone head; the pixel coordinate system represents the image on the camera imaging plane, expressed in pixels, with the origin located in the upper left corner of the image, the u axis parallel to the right, and the v axis vertically downward.

[0012] Furthermore, let the camera coordinate system X C The two acoustic wave catchers on the axis are A and B, Y C The two acoustic wave catchers on the axis are C and D, and the position of the ground mobile robot is P; the installation distance AB of the acoustic wave catcher, and the distance to the position of the ground mobile robot is S A and S B It is known that according to the triangle cosine theorem:

[0013]

[0014] The angle of ∠ABP can be obtained. According to the triangle cosine theorem, O C P length and ∠BO C The angle P is:

[0015]

[0016] Make plane Y through point P C O C Z C The normal QP intersects the plane Y C O C Z C At point Q, due to O CP length and ∠BO C If the angle P is known, then QP is:

[0017] QP=O C P*cos∠BO C P;

[0018] QP is the X-axis coordinate of the target point P; the X-axis coordinate of the target point P, the Y-axis coordinate of the target point P, and the Z-axis coordinate of the punctuation point P are:

[0019]

[0020] Furthermore, the coordinates (u, v) of the target ground mobile robot in the pixel coordinate system are

[0021]

[0022] Where (X, Y, Z) is the position coordinate of the ground mobile robot in the camera coordinate system; f is the focal length of the camera; (c x , c y ) is the coordinate of the camera optical center projected in the pixel coordinate system.

[0023] Furthermore, the image is biased as follows:

[0024]

[0025] Furthermore, the UAV is controlled to adjust its posture so that it moves in the direction where the deviation is reduced, and the ground mobile robot always stays in the center of the image to complete the tracking.

[0026] In a second aspect, the present invention further provides a UAV ground target tracking system, comprising:

[0027] The data acquisition module is configured to: obtain the acoustic wave signal of the ground mobile robot to be tracked, and the camera coordinate system and pixel coordinate system of the preset camera on the drone;

[0028] The coordinate system determination module is configured to: determine the distance from the ground mobile robot to four preset sound wave capture positions in the mobile robot according to the sound wave signal and the time of receiving the sound wave; obtain the coordinates of the ground mobile robot in the camera coordinate system according to the determined distance, and determine the coordinates of the ground mobile robot in the pixel coordinate system according to the conversion relationship from the camera coordinate system to the pixel coordinate system;

[0029] The deviation determination module is configured to: determine the relative position of the ground mobile machine to the UAV according to the coordinates of the ground mobile robot in the pixel coordinate system, and obtain the image deviation;

[0030] The tracking control module is configured to control the UAV according to the relative position of the ground mobile machine to the UAV and the image deviation to track the ground mobile machine.

[0031] In a third aspect, the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the UAV ground target tracking method described in the first aspect.

[0032] In a fourth aspect, the present invention further provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and capable of running on the processor, wherein when the processor executes the program, the steps of the UAV ground target tracking method described in the first aspect are implemented.

[0033] In a fifth aspect, the present invention further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the steps of the UAV ground target tracking method described in the first aspect are implemented.

[0034] Compared with the prior art, the present invention has the following beneficial effects:

[0035] The present invention determines the distance from the ground mobile robot to four preset sound wave capturing positions in the mobile robot according to the sound wave signal and the time of receiving the sound wave; obtains the coordinates of the ground mobile robot in the camera coordinate system according to the determined distance, and determines the coordinates of the ground mobile robot in the pixel coordinate system according to the transformation relationship from the camera coordinate system to the pixel coordinate system; determines the relative position of the ground mobile machine to the unmanned aerial vehicle according to the coordinates of the ground mobile robot in the pixel coordinate system, and obtains the image deviation; finally, controls the unmanned aerial vehicle according to the relative position of the ground mobile machine to the unmanned aerial vehicle and the image deviation, and realizes the tracking of the ground mobile machine. On the basis of ensuring the positioning and tracking accuracy, it avoids the problem that the unmanned aerial vehicle cannot obtain its own precise position information due to the lack of GPS signal, thereby being unable to realize accurate tracking, and reduces the tracking difficulty in the weak light environment at night. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] The drawings in the specification that constitute a part of this embodiment are used to provide a further understanding of this embodiment. The schematic embodiments of this embodiment and their descriptions are used to explain this embodiment and do not constitute improper limitations on this embodiment.

[0037] Figure 1 This is a schematic diagram of a tracking system according to Embodiment 1 of the present invention;

[0038] Figure 2 This is a schematic diagram of the installation positions of the acoustic wave capturer and the monocular camera on the drone according to Example 1 of the present invention;

[0039] Figure 3 This is a schematic diagram of the installation position of the sound wave generator and the radio on the ground mobile robot according to Example 1 of the present invention;

[0040] Figure 4 This is a schematic diagram of the imaging position solution of the target in the system composed of a monocular camera and an acoustic wave capturer in Example 1 of the present invention;

[0041] Among them, 1. Quad-rotor drone; 2. Ground mobile robot; 3. Sound wave capture system; 4. Vision system; 5. Wireless communication system; 6. Sound wave generation system. DETAILED DESCRIPTION

[0042] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0043] It should be noted that the following detailed descriptions are exemplary and are intended to provide further explanation of the present application. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present application belongs.

[0044] Embodiment 1:

[0045] UAV target tracking technology is one of the hot spots in the current UAV application field. This technology generally uses the visual or other sensors on the UAV to identify and track specific targets in real time, and has a wide range of application prospects, such as military patrols, security surveillance, disaster relief, agricultural monitoring, environmental tracking, and entertainment and media. In the daytime and in an environment with good GPS signals, UAV target tracking technology has made significant progress, but in the night environment without GPS signals, the application of this technology still faces many challenges.

[0046] The current drone target tracking technology mainly relies on GPS signals and visual sensors. In an environment with good GPS signals, drones can obtain their own precise location information through GPS receivers, thereby accurately tracking the target. At the same time, visual sensors (such as cameras) also play an important role by capturing real-time images to monitor and track moving targets. Some advanced tracking algorithms and frameworks have also been applied to drone target tracking. For example, tracking methods based on correlation filtering and tracking methods based on deep learning have achieved good tracking effects in real-world scenes with good lighting conditions. However, these tracking methods will have a significant drop in tracking accuracy and may even lose the target when facing low-light conditions, especially extremely low-brightness night scenes.

[0047] Specifically, as described in the background technology, the lack of GPS signals makes it impossible for drones to obtain their own precise location information, and thus cannot accurately track targets. Light conditions are weak at night, and cameras need to set higher sensitivity and use longer exposure times to obtain sufficient light. This may lead to a decrease in image quality and increase the difficulty of target tracking. At the same time, noise and interference in the night environment may also have a negative impact on the accuracy of target tracking, which limits the application of drones at night or in areas where GPS signals are limited.

[0048] In order to solve at least one of the above problems, this embodiment provides a method for tracking a ground target by a UAV. Corresponding to the solution, this embodiment also provides a tracking system, such as Figure 1 As shown, the system includes a multi-rotor drone 1 and a plurality of ground mobile robots 2; Figure 2 and Figure 3 As shown, the multi-rotor UAV 1 is equipped with a sound wave capture system 3, a visual system 4 and a distance measurement and obstacle avoidance system, and the ground mobile robot 2 is equipped with a wireless communication system 5 and a sound wave generation system 6. The wireless communication system 5 uses radio for data communication and is used to receive control instructions from the host computer; the sound wave generation system 6 and the sound wave capture system 3 are respectively a sound wave generator and a sound wave capturer, which can emit or receive sound waves of a specific frequency, and determine the relative position of the robot and the UAV through sound wave positioning; the visual system 4 uses a monocular camera to obtain image information, and displays the tracking target position according to the information located by the sound wave system; the distance measurement and obstacle avoidance system uses an ultrasonic radar to obtain information about the surrounding environment of the UAV, which is used to ensure the safe flight of the UAV. Among them, a radio device and a sound wave generator are installed above the ground mobile robot body; a monocular camera is installed vertically downward at the center position below the UAV body, and four sound wave catchers are installed in a diamond-shaped central symmetric manner with the monocular camera as the center point. The difference between two adjacent sound wave catchers is 90°. The installation direction of the sound wave catcher is vertically downward, and the monocular camera lens and the sound wave catcher are in the same plane.

[0049] The method in this example includes three parts: human-machine interaction, the ground mobile robot receives the control command and sends out a sound wave signal; the relative position information between the ground mobile robot and the UAV is calculated through the sound wave signal, the target position information is marked with a camera to realize the visualization of the tracked target; and the tracking is realized through the target position information. Specifically:

[0050] S1. Human-computer interaction:

[0051] S1.1. The user determines which ground mobile robot needs to follow through the host computer, and sends a control command to the target ground mobile robot via radio.

[0052] S1.2. The target ground mobile robot receives the control command and sends out a sound wave signal.

[0053] S2. Calculate the relative position between the target ground mobile robot and the UAV:

[0054] S2.1. Given the propagation speed V of a specific sound wave in the air, the distance S from the target ground mobile robot to the four sound wave catchers is calculated based on the time T when the sound wave catcher receives the specific sound wave. The following relationship exists:

[0055] S=VT

[0056] S2.2. Establish the camera coordinate system, image coordinate system and pixel coordinate system, and determine the relationship between them. The transformation relationship from the camera coordinate system to the pixel coordinate system is:

[0057]

[0058] Wherein, (X, Y, Z) is the position coordinate of the target ground mobile robot in the camera coordinate system; (u, v) is the coordinate of the target ground mobile robot in the pixel coordinate system; f is the focal length of the camera; (c x , c y ) is the coordinate of the camera optical center projected in the pixel coordinate system.

[0059] S2.3, such as Figure 4 As shown, according to the distance from the target P to the four acoustic wave capturers (A, B, C and D) obtained in step S2.1, the coordinates of the target ground mobile robot in the camera coordinate system can be obtained, and the coordinates are represented by (X, Y, Z).

[0060] S2.4. According to the relationship between the coordinate systems in step S2.2, the coordinates of the target ground mobile robot in the pixel coordinate system can be obtained. The coordinates (u, v) are expressed as follows:

[0061]

[0062] The target position information can then be highlighted on the image plane for visual display.

[0063] In step S2.2, a coordinate system is established, with the optical center of the camera as the origin of the coordinate system, the Z axis coincides with the optical axis of the camera and points to the ground, and the camera coordinate system O is determined according to the right-hand rule. C -X C Y C Z C, where the Y axis passes through the two acoustic wave catchers at the nose and tail of the drone and points to the direction of the drone nose. The image coordinate system is a coordinate system used on the imaging plane, with its origin located at the center of the imaging plane (or the intersection of the optical axis and the image plane), and the X-axis and Y-axis point in the same direction as the camera coordinate system. The coordinates are represented by (x, y). The pixel coordinate system represents the image on the camera imaging plane, expressed in pixels, with its origin located in the upper left corner of the image, the u axis parallel to the right, and the v axis vertically downward.

[0064] In step S2.3, the steps for solving the target in the camera coordinate system are as follows:

[0065] Step S2.3.1, set the camera coordinate system X C The two acoustic wave catchers on the axis are A and B, Y C The two acoustic wave catchers on the axis are C and D, and the target point position is P.

[0066] Step S2.3.2: Due to the installation distance AB of the acoustic wave catcher and the distance S to the target position A and S B It is known that according to the triangle cosine theorem:

[0067]

[0068] The angle of ∠ABP can be obtained. According to the triangle cosine theorem, O C P length and ∠BO C The angle P can be expressed as:

[0069]

[0070] Step S2.3.3: Make plane Y through point P C O C Z C The normal QP intersects the plane Y C O C Z C At point Q, due to O C P length and ∠BO C If the angle P is known, QP can be expressed as:

[0071] QP=O C P*cos∠BO C P

[0072] QP is the X-axis coordinate of the target point P. The X-coordinate of the target point P can be expressed as:

[0073]

[0074] Step S2.3.4: Using the catchers C and D according to the method in step S2.3.2 and step S2.3.2, the Y-axis coordinate of the position of the target point P can be obtained. The Y-coordinate of the target point P can be expressed as:

[0075]

[0076] According to the spatial relationship, the Z coordinate of the target point P can be expressed as:

[0077]

[0078] At this point, the X, Y, and Z coordinates of the target point are known.

[0079] S3, target tracking by target position includes the following steps:

[0080] S3.1. According to the coordinates of the target in the pixel coordinate system, determine the relative position of the target to the drone, with the center point of the image (c x , c y ) is the expected position, and the image deviation is obtained as follows:

[0081]

[0082] S3.2, the image deviation is input into the UAV MPC-BPPID tracking controller, and the tracking controller calculates the control signal.

[0083] S3.3, the UAV adjusts its posture so that the UAV moves in the direction where the deviation decreases, and repeats step S3.2 so that the target always remains in the center of the image to complete the tracking.

[0084] In step S3.2, the MPC-BPPID tracking controller is used to adjust the position and attitude information of the quadrotor, and the algorithm is as follows:

[0085] Quadrotor UAV mathematical model:

[0086]

[0087] Among them, x, y, z represent the horizontal and vertical positions of the quadrotor in the earth coordinate system; θ, ψ represent the rotation angle of the quadrotor around the coordinate axis in the body coordinate system; m represents the total mass of the quadrotor; g represents the acceleration of gravity; l represents the distance from the center of the quadrotor to the center of the propeller; J x , J y , J z represents the moment of inertia; J r Represents the moment of inertia; Ω r Indicates the propeller speed difference; for ψ.G iIndicates the air resistance coefficient; d i Indicates the external disturbance of the quadrotor; u1 indicates the total thrust; u2, u3, u4 are the attitude angles The control inputs of θ, ψ.

[0088] For the position subsystem, the error of position information is converted into virtual force through the MPC controller:

[0089]

[0090] The virtual force cannot be directly applied to the drone, but needs to be converted into the total lift u1 of the drone and the desired attitude angle. θ d The conversion formula is as follows:

[0091]

[0092]

[0093] For the attitude subsystem, the attitude information error is converted into attitude control input u2, u3, u4 through the BPPID controller:

[0094] The selected PID controller form is as follows:

[0095]

[0096] Among them, u(t) is the PID output value; e(t) is the attitude deviation; is the integral amount; is the differential quantity; k p , k i , k d are proportional, integral, and differential coefficients.

[0097] In order to facilitate the design of BPPID controller, the above PID is converted into discrete incremental form:

[0098] u(k)=u(k-1)+k p (e(k)-e(k-1))+k i e(k)

[0099] +k d (e(k)-2e(k-1)+e(k-2))

[0100] In order to facilitate the adjustment of PID parameters, the BP neural network algorithm is introduced. The input layer of the BP neural network is The corresponding output layers are: [Δk pθ , Δk iθ , Δk dθ ],[Δkpψ , Δk iψ , Δk dψ ].

[0101] At this point, the four input forces u1, u2, u3, and u4 required by the quadrotor have been designed. The corresponding relationship between them and the forces generated by the four propellers is:

[0102]

[0103] Therefore, F1, F2, F3, and F4 can be solved and mapped to PWM output to ensure the tracking stability of the quadrotor.

[0104] Embodiment 2:

[0105] This embodiment provides a UAV ground target tracking system, including:

[0106] The data acquisition module is configured to: obtain the acoustic wave signal of the ground mobile robot to be tracked, and the camera coordinate system and pixel coordinate system of the preset camera on the drone;

[0107] The coordinate system determination module is configured to: determine the distance from the ground mobile robot to four preset sound wave capture positions in the mobile robot according to the sound wave signal and the time of receiving the sound wave; obtain the coordinates of the ground mobile robot in the camera coordinate system according to the determined distance, and determine the coordinates of the ground mobile robot in the pixel coordinate system according to the conversion relationship from the camera coordinate system to the pixel coordinate system;

[0108] The deviation determination module is configured to: determine the relative position of the ground mobile machine to the UAV according to the coordinates of the ground mobile robot in the pixel coordinate system, and obtain the image deviation;

[0109] The tracking control module is configured to control the UAV according to the relative position of the ground mobile machine to the UAV and the image deviation to track the ground mobile machine.

[0110] The working method of the system is the same as the UAV ground target tracking method in Example 1, and will not be repeated here.

[0111] Embodiment 3:

[0112] This embodiment provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the steps of the method for tracking a ground target by a drone described in Embodiment 1 are implemented.

[0113] Embodiment 4:

[0114] This embodiment provides an electronic device, including a memory, a processor, and a computer program stored in the memory and capable of running on the processor. When the processor executes the program, the steps of the drone ground target tracking method described in Example 1 are implemented.

[0115] Embodiment 5:

[0116] This embodiment provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the steps of the drone ground target tracking method described in Example 1 are implemented.

[0117] The above description is only a preferred embodiment of the present embodiment and is not intended to limit the present embodiment. For those skilled in the art, the present embodiment may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present embodiment shall be included in the protection scope of the present embodiment.

Claims

1. A method for tracking a ground target by an unmanned aerial vehicle, characterized in that: include: Acquire the acoustic wave signal of the ground mobile robot to be tracked, as well as the camera coordinate system and pixel coordinate system of the preset camera on the drone; According to the sound wave signal and the time of receiving the sound wave, the distance from the ground mobile robot to four preset sound wave capture positions in the mobile robot is determined; and the coordinates of the ground mobile robot in the camera coordinate system are obtained according to the determined distance, and the coordinates of the ground mobile robot in the pixel coordinate system are determined according to the transformation relationship from the camera coordinate system to the pixel coordinate system; According to the coordinates of the ground mobile robot in the pixel coordinate system, the relative position of the ground mobile machine to the UAV is determined, and the image deviation is obtained; The UAV is controlled according to the relative position of the ground mobile machine to the UAV and the image deviation to track the ground mobile machine.

2. A method for tracking a ground target by an unmanned aerial vehicle according to claim 1, characterized in that: The optical center of the preset camera on the drone is used as the origin of the coordinate system. The Z axis coincides with the optical axis of the camera and points to the ground. The camera coordinate system is determined according to the right-hand rule. The Y axis passes through the two acoustic wave catchers at the head and tail of the drone and points to the direction of the drone head. The pixel coordinate system represents the image on the camera imaging plane, expressed in pixels, with the origin located in the upper left corner of the image, the u axis parallel to the right, and the v axis vertically downward.

3. A method for tracking a ground target by an unmanned aerial vehicle according to claim 2, characterized in that: Camera coordinate system X C The two acoustic wave catchers on the axis are A and B, Y C The two acoustic wave catchers on the axis are C and D, and the position of the ground mobile robot is P; the installation distance AB of the acoustic wave catcher, and the distance to the position of the ground mobile robot is S A and S B It is known that according to the triangle cosine theorem: The angle of ∠ABP can be obtained. According to the triangle cosine theorem, O C P length and ∠BO C The angle P is: Make plane Y through point P C O C Z C The normal QP intersects the plane Y C O C Z C At point Q, due to O C P length and ∠BO C If the angle P is known, then QP is: QP=O C P*cos∠BO C P; QP is the X-axis coordinate of the target point P; the X-axis coordinate of the target point P, the Y-axis coordinate of the target point P and the Z-axis coordinate of the punctuation point P are:

4. A method for tracking a ground target by an unmanned aerial vehicle according to claim 3, characterized in that: The coordinates (u, v) of the target ground mobile robot in the pixel coordinate system are: Where (X, Y, Z) is the position coordinate of the ground mobile robot in the camera coordinate system; f is the focal length of the camera; (c x , c y ) is the coordinate of the camera optical center projected in the pixel coordinate system.

5. A method for tracking a ground target by an unmanned aerial vehicle according to claim 4, characterized in that: The image is biased towards:

6. A method for tracking a ground target by an unmanned aerial vehicle according to claim 1, characterized in that: The drone is controlled to adjust its posture so that it moves in the direction where the deviation is reduced, and the ground mobile robot is always kept in the center of the image to complete the tracking.

7. A UAV ground target tracking system, characterized in that: include: The data acquisition module is configured to: obtain the acoustic wave signal of the ground mobile robot to be tracked, and the camera coordinate system and pixel coordinate system of the preset camera on the drone; The coordinate system determination module is configured to: determine the distance from the ground mobile robot to four preset sound wave capture positions in the mobile robot according to the sound wave signal and the time of receiving the sound wave; obtain the coordinates of the ground mobile robot in the camera coordinate system according to the determined distance, and determine the coordinates of the ground mobile robot in the pixel coordinate system according to the conversion relationship from the camera coordinate system to the pixel coordinate system; The deviation determination module is configured to: determine the relative position of the ground mobile machine to the UAV according to the coordinates of the ground mobile robot in the pixel coordinate system, and obtain the image deviation; The tracking control module is configured to control the UAV according to the relative position of the ground mobile machine to the UAV and the image deviation to track the ground mobile machine.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the UAV ground target tracking method as described in any one of claims 1 to 6 are implemented.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and capable of running on the processor, characterized in that: When the processor executes the program, the steps of the UAV ground target tracking method as described in any one of claims 1-6 are implemented.

10. A computer program product, characterized in that The computer program product includes a computer program, and when the computer program is executed by a processor, the steps of the UAV ground target tracking method as described in any one of claims 1 to 6 are implemented.

Images