A method and system for tracking a ground target by a UAV

Abstract

The application belongs to the technical field of robot tracking, and provides a UAV target tracking method and system, wherein the distance from the ground mobile robot to the preset four sound wave capturing positions in the mobile robot is determined according to the sound wave signal and the time of receiving the sound wave; the coordinates of the ground mobile robot in the camera coordinate system are determined according to the determined distance, and the coordinates of the ground mobile robot in the pixel coordinate system are determined according to the conversion relationship from the camera coordinate system to the pixel coordinate system; the relative position of the ground mobile robot to the UAV is determined according to the coordinates of the ground mobile robot in the pixel coordinate system, and the image deviation is obtained; the UAV is controlled according to the relative position of the ground mobile robot to the UAV and the image deviation, so that the tracking of the ground mobile robot is realized, and on the basis of ensuring the positioning and tracking accuracy, the problem that the UAV cannot obtain the accurate position information of itself due to the loss of the GPS signal is avoided, so that the accurate tracking cannot be realized.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of robot tracking, and particularly relates to a UAV target tracking method and system. BACKGROUND

[0002] The UAV target tracking technology is one of the current hotspots in the field of UAV application, which has a wide application prospect by identifying and tracking specific targets in real time through vision or other sensors on the UAV. The current UAV target tracking technology mainly relies on GPS signals and vision sensors. In a good GPS signal environment, the UAV can obtain its accurate position information through the GPS receiver, and then realize accurate tracking of the target. At the same time, the vision sensor monitors and tracks the moving target by capturing real-time images. In addition, some advanced tracking algorithms and frameworks are also applied to UAV target tracking.

[0003] However, the current UAV target tracking method will greatly reduce the tracking accuracy, or even lose the target under low light conditions, especially in the extremely low brightness night scene. Specifically, the absence of GPS signals will cause the UAV to be unable to obtain its accurate position information, thereby failing to achieve accurate tracking of the target. In the night, the light condition is weak, and the camera needs to set a higher sensitivity and use a longer exposure time to obtain sufficient light, which may cause the image quality to decrease and increase the difficulty of target tracking. At the same time, the noise and interference in the night environment may also have a negative impact on the accuracy of target tracking, which limits the application of UAV in the night or GPS signal limited area. SUMMARY

[0004] In order to solve the above problems, the present application provides a UAV target tracking method and system. According to the sound wave signal and the time of receiving the sound wave, the distance from the ground mobile robot to the preset four sound wave capturing positions in the mobile robot is determined. According to the determined distance, the coordinates of the ground mobile robot in the camera coordinate system are obtained, and the coordinates of the ground mobile robot in the pixel coordinate system are determined according to the conversion 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 robot to the UAV is determined, and the image deviation is obtained. Finally, the UAV is controlled according to the image deviation to realize the tracking of the ground mobile robot. On the basis of ensuring the positioning and tracking accuracy, the problem that the UAV cannot obtain its accurate position information due to the absence of GPS signals, thereby failing to achieve accurate tracking, is avoided.

[0005] In order to achieve the above purpose, the present application is realized by the following technical scheme:

[0006] In a first aspect, the present application provides a UAV target tracking method, comprising:

[0007] Obtain the sound 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 unmanned aerial vehicle;

[0008] According to the sound wave signal and the time of receiving the sound wave, the distance from the ground mobile robot to the preset four sound wave capturing positions in the mobile robot is determined; and according to the determined distance, the coordinates of the ground mobile robot in the camera coordinate system are obtained, and the coordinates of the ground mobile robot in the pixel coordinate system are determined according to the conversion 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 robot to the unmanned aerial vehicle is determined, and the image deviation is obtained;

[0010] According to the relative position of the ground mobile robot to the unmanned aerial vehicle and the image deviation, the unmanned aerial vehicle is controlled to track the ground mobile robot.

[0011] Further, the optical center of the preset camera on the unmanned aerial vehicle is taken 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 sound wave capturing devices of the nose and tail of the unmanned aerial vehicle and points to the direction of the nose of the unmanned aerial vehicle; the pixel coordinate system represents the image on the imaging plane of the camera, and is represented in units of pixels, the origin is located at the upper left corner of the image, the u axis is parallel to the right, and the v axis is perpendicular to the downward.

[0012] Further, the camera coordinate system X C The two sound wave capturing devices on the Y C axis are A and B, and the two sound wave capturing devices on the Y A axis are C and D, and the position of the ground mobile robot is P; the installation distance of the sound wave capturing devices AB and the distance S B from the ground mobile robot position are known.

[0013]

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

[0015]

[0016] A plane Y C O C Z C is made through the point P, intersecting the normal QP of the plane Y C O C Z C at point Q, and since O CP length and ∠BO C P angle is known, QP is:

[0017] QP=O C P*cos∠BO C P;

[0018] QP is the X-axis coordinate of the target point P position, and 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 point P are:

[0019]

[0020] Further, 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 camera focal length; (c x , c y ) is the projection of the camera optical center in the pixel coordinate system.

[0023] Further, the image deviation is:

[0024]

[0025] Further, the unmanned aerial vehicle adjusts the attitude, moves in the direction of reducing the deviation, and keeps the ground mobile robot in the image center to complete tracking.

[0026] In a second aspect, the present application also provides an unmanned aerial vehicle ground target tracking system, comprising:

[0027] The data acquisition module is configured to acquire the sound wave signal of the ground mobile robot to be tracked and the camera coordinate system and the pixel coordinate system of the preset camera on the unmanned aerial vehicle;

[0028] The coordinate system determination module is configured to determine the distance from the ground mobile robot to the preset four sound wave capturing positions in the mobile robot according to the sound wave signal and the time of receiving the sound wave, and determine 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 robot in the unmanned aerial vehicle 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 unmanned aerial vehicle to track the ground mobile machine according to the relative position of the ground mobile machine to the unmanned aerial vehicle and the image deviation.

[0031] In a third aspect, the present application also provides a computer readable storage medium, which stores a computer program, and the program is executed by a processor to implement the steps of the unmanned aerial vehicle tracking a ground target method in the first aspect.

[0032] In a fourth aspect, the present application also provides an electronic device, which comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, and the processor implements the steps of the unmanned aerial vehicle tracking a ground target method in the first aspect when executing the program.

[0033] In a fifth aspect, the present application also provides a computer program product, which comprises a computer program, and the computer program is executed by a processor to implement the steps of the unmanned aerial vehicle tracking a ground target method in the first aspect.

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

[0035] In the present application, the distance of the ground mobile robot to the preset four sound wave capturing positions in the mobile robot is determined according to the sound wave signal and the time of receiving the sound wave, the coordinates of the ground mobile robot in the camera coordinate system are determined according to the determined distance, and the coordinates of the ground mobile robot in the pixel coordinate system are determined according to the conversion relationship from the camera coordinate system to the pixel coordinate system; the relative position of the ground mobile machine to the unmanned aerial vehicle is determined according to the coordinates of the ground mobile robot in the pixel coordinate system, and the image deviation is obtained; finally, the unmanned aerial vehicle is controlled according to the relative position of the ground mobile machine to the unmanned aerial vehicle and the image deviation, so as to realize the tracking of the ground mobile machine. On the basis of ensuring the positioning and tracking accuracy, the problem that the unmanned aerial vehicle cannot obtain accurate position information of itself due to the lack of GPS signal, so as to realize accurate tracking, is avoided, and the tracking difficulty in the environment with weak light at night is reduced. BRIEF DESCRIPTION OF DRAWINGS

[0036] The drawings constituting a part of this embodiment are used to provide further understanding of this embodiment, and the schematic embodiment of this embodiment and the description thereof are used to explain this embodiment, and do not constitute improper limitation on this embodiment.

[0037] Figure 1 It is a schematic diagram of the tracking system of embodiment 1 of the present application;

[0038] Figure 2 It is a schematic diagram of the installation position of the sound wave capturing device and the monocular camera on the unmanned aerial vehicle in embodiment 1 of the present application;

[0039] Figure 3 Figure 1 is a schematic diagram of the installation position of the sound wave generator and radio of the embodiment 1 of the present application on a ground mobile robot;

[0040] Figure 4 Figure 2 is a schematic diagram of the position calculation of the target in the system composed of a monocular camera and a sound wave capture device of the embodiment 1 of the present application;

[0041] Wherein, 1, quadcopter; 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 application will be further described below in conjunction with the drawings and embodiments.

[0043] It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the present application. Unless otherwise indicated, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.

[0044] Embodiment 1:

[0045] Unmanned aerial vehicle target tracking technology is one of the current hotspots in the field of unmanned aerial vehicle application. This technology generally identifies and tracks specific targets in real time through vision or other sensors on unmanned aerial vehicles, and has wide application prospects, such as military patrol, security monitoring, disaster rescue, agricultural monitoring, environmental tracking, and entertainment and media fields. In the daytime and in the environment with good GPS signal, the unmanned aerial vehicle target tracking technology has made significant progress, but in the night without GPS signal, the application of this technology still faces many challenges.

[0046] Current unmanned aerial vehicle target tracking technology mainly relies on GPS signals and vision sensors. In the environment with good GPS signal, the unmanned aerial vehicle can obtain its accurate position information through the GPS receiver, and then realize accurate tracking of the target. At the same time, vision sensors (such as cameras) also play an important role, which capture real-time images to monitor and track moving targets. Some advanced tracking algorithms and frameworks are also applied to unmanned aerial vehicle target tracking, such as correlation filtering-based tracking methods and deep learning-based tracking methods, which have good tracking effect in real scenes with good lighting conditions, but these tracking methods will greatly reduce the tracking accuracy in low light conditions, especially in the night scene with extremely low brightness, and even lose the target.

[0047] Specifically, as described in the background, the absence of GPS signals causes the UAV to be unable to obtain accurate position information of itself, thereby failing to achieve accurate tracking of the target. In the weak light conditions at night, the camera needs to set a higher sensitivity and use a longer exposure time to obtain sufficient light. This may cause the image quality to decrease, increasing the difficulty of target tracking. At the same time, noise and interference in the night environment can negatively affect the accuracy of target tracking, which limits the application of UAVs in the night or GPS signal limited areas.

[0048] To solve at least one of the above problems, the present embodiment provides a UAV ground target tracking method, and the present embodiment also provides a tracking system corresponding to the method, as shown in Figure 1 The system includes a multi-rotor UAV 1 and a plurality of ground mobile robots 2, as shown in Figure 2 and Figure 3 The multi-rotor UAV 1 is equipped with a sound wave capturing system 3, a vision system 4, and a ranging and obstacle avoidance system, and the ground mobile robot 2 is equipped with a wireless communication system 5 and a sound wave generating system 6. The wireless communication system 5 uses radio for data communication, for receiving control instructions from the host computer; the sound wave generating system 6 and the sound wave capturing system 3 are sound wave generators and sound wave capturers, respectively, 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 vision system 4 uses a monocular camera to obtain image information, and displays the tracking target position according to the information positioned by the sound wave system; the ranging and obstacle avoidance system uses ultrasonic radar to obtain the surrounding environment information of the UAV, for ensuring the safe flight of the UAV. Among them, a radio device and a sound wave generator are installed above the body of the ground mobile robot; a monocular camera is vertically downwardly installed at the center position below the UAV body, and four sound wave capturers are installed in a rhombus center-symmetric manner with the monocular camera as the center point, the adjacent two sound wave capturers are 90° apart, the sound wave capturers are installed vertically downward, and the lens of the monocular camera and the sound wave capturers are in the same plane.

[0049] The method in the present example includes three parts, which are the human-computer interaction link, the ground mobile robot receiving control instructions and emitting sound wave signals; calculating the relative position information between the ground mobile robot and the UAV through the sound wave signals, using the camera to mark the target position information, and realizing the visualization of the tracked target; and realizing tracking through the target position information. Specifically:

[0050] S1, human-computer interaction link:

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

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

[0053] S2, calculate the relative position between the target ground mobile robot and the unmanned aerial vehicle:

[0054] S2.1, the propagation speed V of a specific sound wave in the air is known, and the distances S of the target ground mobile robot to the four sound wave catchers are obtained according to the time T when the specific sound wave is received by the sound wave catcher respectively. There is a relationship as follows:

[0055] S = VT

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

[0057]

[0058] where (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 projection of the camera optical center in the pixel coordinate system.

[0059] S2.3, as shown in Figure 4 , according to the distances of the target P to the four sound wave catchers (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, which 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, which are represented by (u, v) as follows,

[0061]

[0062] Further, the target position information can be highlighted and visually displayed on the image plane.

[0063] In step S2.2, the coordinate system is established, taking the camera optical center 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 C -X C Y C Z CWherein, the Y axis passes through the two sound wave catchers of the head and tail of the unmanned aerial vehicle and points to the direction of the head of the unmanned aerial vehicle. The image coordinate system is a coordinate system used on the imaging plane, the origin of which is located at the center of the imaging plane (or the intersection of the optical axis and the image plane), the X axis and the Y axis are consistent with the direction of the camera coordinate system, and the coordinates are represented by (x, y). The pixel coordinate system represents the image on the camera imaging plane, which is represented in pixels, the origin of which is located at the upper left corner of the image, the u axis is parallel to the right, and the v axis is perpendicular to the down.

[0064] In the step S2.3, the solving step of the target in the camera coordinate system is as follows:

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

[0066] Step S2.3.2, since the sound wave catchers are installed at a distance AB, and the distance S A and S B are known, according to the cosine theorem of triangle, it can be obtained that:

[0067]

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

[0069]

[0070] Step S2.3.3, draw the normal line QP of the plane Y C O C Z C passing through the point P, intersecting the plane Y C O C Z C at point Q, since O C P length and ∠BO C P angle are known, then QP can be represented as:

[0071] QP = O C P*cos∠BO C P

[0072] The QP is the X axis coordinate of the position of the target point P. Then the X coordinate of the target point P can be represented as:

[0073]

[0074] Step S2.3.4, using the traps C and D, according to the method in step S2.3.2 and step S2.3.2, the Y axis coordinate of the target point P position can be obtained, and 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 axis coordinates of the target point position are known.

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

[0080] S3.1, according to the coordinates of the target in the pixel coordinate system, the relative position of the target in the unmanned aerial vehicle is judged, and the image center point (c x , c y ) is taken as the expected position to obtain the image deviation, and the image deviation is as follows:

[0081]

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

[0083] S3.3, the unmanned aerial vehicle adjusts its attitude, so that the unmanned aerial vehicle moves in the direction of reducing the deviation, and repeats step S3.2, so that the target is always kept in the image center, and the tracking is completed.

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

[0085] Mathematical model of quadcopter:

[0086]

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

[0088] For position subsystem, error of position information is converted to virtual force by MPC controller:

[0089]

[0090] Virtual force cannot directly act on UAV, and needs to be converted to total lift u1 and expected attitude angle of UAV θ d Conversion formula is as follows:

[0091]

[0092]

[0093] For attitude subsystem, error of attitude information is converted to attitude control input u2, u3, u4 by BPPID controller:

[0094] Selected PID controller form is as follows:

[0095]

[0096] Wherein, u(t) is PID output value; e(t) is attitude deviation; is integral part; is differential part; k p , k i , k d are proportional, integral, and differential coefficients.

[0097] In order to facilitate design of BPPID controller, the above PID is converted to 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 adjustment of PID parameters, BP neural network algorithm is introduced. Input layer of BP neural network is Corresponding output layer is respectively: [Δk pθ , Δk iθ , Δk dθ ], [Δkpψ , Δk iψ , Δk dψ ].

[0101] So far, the four input forces u1, u2, u3, u4 required by the quadcopter have been designed. The corresponding relationship between them and the forces generated by the four propellers is as follows:

[0102]

[0103] Therefore, F1, F2, F3, F4 can be calculated, and the tracking stability of the quadcopter can be ensured through the mapping relationship to the PWM output.

[0104] Embodiment 2:

[0105] The embodiment provides an unmanned aerial vehicle ground target tracking system, comprising:

[0106] A data acquisition module is configured to acquire sound wave signals of a ground mobile robot to be tracked, and a camera coordinate system and a pixel coordinate system of a preset camera on the unmanned aerial vehicle;

[0107] A coordinate system determination module is configured to determine distances from the ground mobile robot to four preset sound wave capturing positions in the ground mobile robot according to the sound wave signals and the time of receiving the sound waves, and determine coordinates of the ground mobile robot in the camera coordinate system according to the determined distances, and determine coordinates of the ground mobile robot in the pixel coordinate system according to a conversion relationship from the camera coordinate system to the pixel coordinate system;

[0108] A deviation determination module is configured to determine a relative direction of the ground mobile robot to the unmanned aerial vehicle according to the coordinates of the ground mobile robot in the pixel coordinate system, and obtain an image deviation;

[0109] A tracking control module is configured to control the unmanned aerial vehicle to track the ground mobile robot according to the relative direction of the ground mobile robot to the unmanned aerial vehicle and the image deviation.

[0110] The working method of the system is the same as the unmanned aerial vehicle ground target tracking method of embodiment 1, and will not be described here.

[0111] Embodiment 3:

[0112] The embodiment provides a computer readable storage medium, which stores a computer program, and the program is executed by a processor to realize the steps of the unmanned aerial vehicle ground target tracking method of embodiment 1.

[0113] Embodiment 4:

[0114] The embodiment 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 the processor implements the steps of the unmanned aerial vehicle ground target tracking method in the embodiment 1 when executing the program.

[0115] Embodiment 5:

[0116] The embodiment provides a computer program product, the computer program product comprises a computer program, the computer program is executed by a processor, and the steps of the unmanned aerial vehicle ground target tracking method in the embodiment 1 are realized.

[0117] The above merely provides the preferred embodiments of the embodiment, and is not intended to limit the embodiment. The embodiment can have various modifications and changes for those skilled in the art. Any modification, equivalent replacement, improvement and the like within the spirit and principle of the embodiment shall be included in the protection scope of the embodiment.

Claims

1. A method for tracking a ground target by a UAV, the method comprising: The method comprises the following steps: acquiring sound wave signals of a ground mobile robot to be tracked, and a camera coordinate system and a pixel coordinate system of a preset camera on a UAV; determining distances from the ground mobile robot to four preset sound wave capturing positions in the mobile robot according to the sound wave signals and a time of receiving the sound waves, and determining coordinates of the ground mobile robot in the camera coordinate system according to the determined distances, and determining coordinates of the ground mobile robot in the pixel coordinate system according to a conversion relationship from the camera coordinate system to the pixel coordinate system; determining a relative position of the ground mobile robot relative to the UAV according to the coordinates of the ground mobile robot in the pixel coordinate system, and obtaining an image deviation; controlling the UAV to track the ground mobile robot according to the relative position of the ground mobile robot relative to the UAV and the image deviation; the image deviation is: ； wherein, is a position coordinate of the ground mobile robot in the camera coordinate system; is a focal length of the camera; P is a length, is an origin of the camera coordinate system, is a target point position; is a coordinate of the target ground mobile robot in the pixel coordinate system. 2.The UAV ground target tracking method of claim 1, wherein, The optical center of a preset camera on the unmanned aerial vehicle is taken as an origin of a coordinate system, Z The axis coincides with the optical axis of the camera and points to the ground, and the camera coordinate system is determined according to the right-hand rule, Y The axis passes through the two sound wave capture devices at the nose and tail of the unmanned aerial vehicle and points to the nose direction of the unmanned aerial vehicle; the pixel coordinate system represents an image on an imaging plane of the camera and is represented by pixels, and the origin is located at the upper left corner of the image, u The axis is parallel to the right, v The axis is perpendicular to the downward direction. 3.The UAV-to-ground target tracking method of claim 2, wherein, Let the camera coordinate system be The two sound wave catchers on the axis are A and B , The two sound wave catchers on the axis are C and D , the ground mobile robot position is P; the sound wave catcher installation distance AB , and the distance from the ground mobile robot position is known, according to the cosine theorem of a triangle: ； The angle of ∠ABP can be obtained according to the cosine theorem of triangle, that is, P Length and ∠B P The angle is: ； ； pass P plane through point normal to plane QP plane intersects plane at point Q since P length and ∠B P angle is known, then QP is: ； QP i.e. target point P position of X axis coordinates; the target point P of X position, target point P of Y coordinates and the point P of Z coordinates are: ； ； 。 4.The UAV-to-ground target tracking method of claim 3, wherein, Target ground mobile robot coordinates in pixel coordinate system is: wherein, is the position coordinate of the ground mobile robot in the camera coordinate system; is the focal length of the camera; is the coordinate of the camera optical center projected in the pixel coordinate system.

5. The method of claim 1, wherein, controlling the UAV to adjust a posture, and moving the UAV in a direction in which the deviation is reduced, so that the ground mobile robot is always kept in the center of an image, and the tracking is completed.

6. An unmanned aerial vehicle ground target tracking system, comprising: The method comprises the following steps: a data acquisition module configured to acquire sound wave signals of a ground mobile robot to be tracked, and a camera coordinate system and a pixel coordinate system of a preset camera on a UAV; a coordinate system determination module configured to determine distances from the ground mobile robot to four preset sound wave capturing positions in the mobile robot according to the sound wave signals and a time of receiving the sound waves, and determine coordinates of the ground mobile robot in the camera coordinate system according to the determined distances, and determine coordinates of the ground mobile robot in the pixel coordinate system according to a conversion relationship from the camera coordinate system to the pixel coordinate system; a deviation determination module configured to determine a relative position of the ground mobile robot relative to the UAV according to the coordinates of the ground mobile robot in the pixel coordinate system, and obtain an image deviation; a tracking control module configured to control the UAV to track the ground mobile robot according to the relative position of the ground mobile robot relative to the UAV and the image deviation; the image deviation is: ； wherein, is a position coordinate of the ground mobile robot in the camera coordinate system; is a camera focal length; P is a length, is a camera coordinate system origin, is a target point position; is a coordinate of the target ground mobile robot in the pixel coordinate system.

7. A computer readable storage medium having stored thereon a computer program, characterized in that, The program is executed by the processor to implement the steps of the UAV tracking a ground target method according to any one of claims 1-5.

8. An electronic device comprising a memory, a processor, and a computer program stored on the memory and capable of running on the processor, characterized in that, The processor executes the program to implement the steps of the UAV tracking a ground target method according to any one of claims 1-5.

9. A computer program product, characterised in that, The computer program product comprises a computer program, which is executed by the processor to implement the steps of the UAV tracking a ground target method according to any one of claims 1-5.

Images