CN116991180A - Unmanned plane tracking method, system and storage medium based on unmanned plane platform - Google Patents
Unmanned plane tracking method, system and storage medium based on unmanned plane platform Download PDFInfo
- Publication number
- CN116991180A CN116991180A CN202310577695.9A CN202310577695A CN116991180A CN 116991180 A CN116991180 A CN 116991180A CN 202310577695 A CN202310577695 A CN 202310577695A CN 116991180 A CN116991180 A CN 116991180A
- Authority
- CN
- China
- Prior art keywords
- aerial vehicle
- unmanned aerial
- servo turntable
- camera
- servo
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 33
- 230000000007 visual effect Effects 0.000 claims description 33
- 230000033001 locomotion Effects 0.000 claims description 29
- 238000004422 calculation algorithm Methods 0.000 claims description 27
- 206010034719 Personality change Diseases 0.000 claims description 11
- 230000008859 change Effects 0.000 claims description 9
- 230000008878 coupling Effects 0.000 claims description 8
- 238000010168 coupling process Methods 0.000 claims description 8
- 238000005859 coupling reaction Methods 0.000 claims description 8
- 230000003068 static effect Effects 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 4
- 238000012546 transfer Methods 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 2
- 230000006870 function Effects 0.000 description 12
- 238000010586 diagram Methods 0.000 description 9
- 230000036544 posture Effects 0.000 description 7
- 238000013461 design Methods 0.000 description 5
- 238000012360 testing method Methods 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 230000001276 controlling effect Effects 0.000 description 4
- 210000004556 brain Anatomy 0.000 description 3
- 238000013135 deep learning Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 210000003414 extremity Anatomy 0.000 description 3
- 210000001508 eye Anatomy 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000005070 sampling Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 230000005764 inhibitory process Effects 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 230000033228 biological regulation Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 230000001629 suppression Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D3/00—Control of position or direction
- G05D3/12—Control of position or direction using feedback
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The application provides an unmanned aerial vehicle tracking method, system and storage medium based on an unmanned platform. According to the unmanned aerial vehicle tracking method of the unmanned aerial vehicle platform, the tracking speed and the accuracy can be achieved, and experiments prove that stable tracking of a target of the unmanned aerial vehicle at a close range can be guaranteed.
Description
Technical Field
The application relates to the field of low-altitude unmanned aerial vehicle tracking and aiming, in particular to an unmanned aerial vehicle tracking and aiming method, system and storage medium based on an unmanned platform.
Background
In recent years, the use of the low-altitude unmanned aerial vehicle is continuously popularized, the use of the low-altitude unmanned aerial vehicle is more and more under the condition of informatization battle, and the low-altitude unmanned aerial vehicle plays a vital role in information collection, battlefield situation awareness and even the task completion of accurate striking and guiding, and is certainly a newly rising saber in the battlefield.
However, for the low-altitude unmanned aerial vehicle, the characteristics of small volume, low speed and low altitude are realized, the traditional radar detection and fire destroying modes are not efficient any more, and the advantages and the application of the photoelectric equipment are suitable for being applied to the countermeasure of low-altitude low-speed flight targets such as unmanned aerial vehicles, and the unmanned aerial vehicle tracking and aiming system based on a motion platform in a battlefield environment becomes a hot topic of research of various countries.
Currently, unmanned aerial vehicle tracking equipment on motion platforms such as ships, automobiles and planes is more and more used for meeting the requirements of high maneuverability and unmanned aerial vehicle tracking striking without being affected by position, but under the motion platform, high-precision tracking of targets is to be realized, compared with the ground with a static base, external disturbance brought by the motion platform is to be overcome, the vibration and the motion of a carrier can enable the unmanned aerial vehicle tracking equipment to generate the same disturbance, so that the position output precision of the targets is reduced, and even the targets are lost in a view field due to excessive motion, so that the tracking of the targets of the unmanned aerial vehicle cannot be realized. Meanwhile, under the condition that the turntable swings unevenly, friction torque between shafting is increased, and tracking accuracy of an unmanned aerial vehicle tracking system is reduced and tracking error is increased. Therefore, in order to enable the unmanned aerial vehicle tracking and aiming system to track the target with high precision, the unmanned aerial vehicle tracking and aiming control system is required to have strong disturbance inhibition capability, and how to improve the disturbance inhibition capability becomes a difficult problem to be solved urgently.
Disclosure of Invention
In order to solve the problems, the application provides an unmanned aerial vehicle tracking method, an unmanned aerial vehicle tracking system and a storage medium based on an unmanned aerial vehicle platform.
The application discloses a low-altitude unmanned aerial vehicle tracking method based on an unmanned platform, wherein the unmanned platform comprises a camera and a servo turntable comprising a direct current motor, and the method comprises the following steps:
step S1: acquiring video stream images containing the unmanned aerial vehicle through a camera and transmitting the video stream images to a computer;
step S2: performing image recognition on the acquired video stream image by using an unmanned aerial vehicle recognition model stored in a computer to acquire position information of an unmanned aerial vehicle target center in the video stream image;
step S3: controlling the rotating angle value and the rotating instruction of the servo turntable based on the position information acquired in the step S2;
step S4: and the servo turntable controls the visual axis of the camera to point to the target center of the unmanned aerial vehicle based on the angle value and the rotation instruction in the step S3.
According to the method of the first aspect of the application, step S2 further comprises: and selecting a yolo recognition algorithm or a contour recognition algorithm for image recognition aiming at different sky background conditions contained in the acquired video stream image so as to acquire an unmanned aerial vehicle target center, and determining the position of the unmanned aerial vehicle target center in the whole image to acquire the position relation between the unmanned aerial vehicle target center and the camera visual axis.
According to the method of the first aspect of the application, step S3 further comprises: the servo turntable with the direct current motor is controlled by using a position closed loop PID control algorithm, and the servo turntable provides power for the steering of the camera so as to realize the transfer following of the visual axis of the camera to the target center of the unmanned aerial vehicle; the angular velocity of the change of the posture of the servo turntable is set to be omega along three axes on a coordinate system of the servo turntable ztx 、ω zty 、ω ztz The method comprises the steps of carrying out a first treatment on the surface of the When the servo turntable is in a static zero state, the angular velocity of the motion of the posture of the servo turntable converted to an azimuth axis coordinate system through the coupling relation between the motion and the azimuth axis is omega fwx 、ω fwy 、ω fwz The azimuth axis of the servo turntable is changed to be theta fw The pitch axis is changed in angle to theta fy The relationship between the angular velocity of the attitude change of the servo turntable coordinate system and the angular velocity of the attitude change of the azimuth axis coordinate system is as follows:
according to the method of the first aspect of the application, the closed-loop PID control algorithm comprises the calculation of the proportion, the integral and the derivative of the target angle difference value.
The application provides a low-altitude unmanned aerial vehicle tracking and aiming system based on an unmanned platform, which comprises a camera, a servo turntable containing a direct-current motor and an embedded control board, wherein the embedded control board adopts an STM32 main control board; the method comprises the steps that a camera is connected with a computer, the computer is connected with an STM32 main control board, the computer obtains a video stream image containing the unmanned aerial vehicle through the camera and identifies to obtain position information of a target center of the unmanned aerial vehicle in the video stream image, and the position information is transmitted to the STM32 main control board; the STM32 main control board integrates a main system and a servo turntable sub-control system, and transmits a rotation instruction to the servo turntable sub-control system according to the position relation between the video axis of the camera and the unmanned aerial vehicle; the STM32 main control board is connected with the direct current motor, the camera is fixed on the rotating frame of the servo turntable, and the servo turntable sub-control system drives the direct current motor to realize that the visual axis of the camera moves to the target center position of the unmanned aerial vehicle through PWM wave output; the system performs the steps of:
step S1: collecting video stream images through a camera and transmitting the video stream images to a computer;
step S2: performing image recognition on the video stream image by using an unmanned aerial vehicle recognition model stored in a computer to acquire position information of an unmanned aerial vehicle target center in the image;
step S3: outputting an angle value and a rotation instruction for controlling the rotation of the servo turntable based on the position information acquired in the step S2;
step S4: and controlling the visual axis of the camera to point to the target center of the unmanned aerial vehicle by the servo turntable based on the angle value and the rotation instruction in the step S3.
According to the system of the second aspect of the application, the main system on the STM32 main control board performs autonomous real-time control on the whole tracking system, acquires the unmanned aerial vehicle position information of the computer end in real time, and controls the servo turntable in real time to direct the visual axis of the camera to the target center of the unmanned aerial vehicle.
According to the system of the second aspect of the application, the coordinate system of the servo turntable is composed of an inertial coordinate system, a servo turntable coordinate system and an axis coordinate system.
According to the system of the second aspect of the application, the azimuth axis and the pitching axis of the servo turntable are subjected to real-time closed-loop control.
According to the system of the second aspect of the present application, the angular velocity of the change in attitude of the servo turntable is set to ω in the three axes on the servo turntable coordinate system ztx 、ω zty 、ω ztz The method comprises the steps of carrying out a first treatment on the surface of the When the servo turntable is in a static zero state, the angular velocity of the motion of the posture of the servo turntable converted to an azimuth axis coordinate system through the coupling relation between the motion and the azimuth axis is omega fwx 、ω fwy 、ω fwz The azimuth axis of the servo turntable is changed to be theta fw The pitch axis is changed in angle to theta fy The relationship between the angular velocity of the attitude change of the servo turntable coordinate system and the angular velocity of the attitude change of the azimuth axis coordinate system is as follows:
a third aspect of the present application provides a computer storage medium storing computer program instructions which, when executed, implement the unmanned platform-based low-altitude unmanned aerial vehicle tracking method of any one of the first aspects.
The low-altitude unmanned aerial vehicle tracking and aiming scheme based on the unmanned platform mainly achieves the following effects:
(1) By utilizing the method, different images are respectively identified according to the image identification algorithm, so that the accuracy of acquiring the position of the unmanned aerial vehicle is improved;
(2) The turntable in the application has high rotation speed towards a set angle and sensitive response, and the stability and reliability of the algorithm and the turntable hardware are embodied. In the overall test of the system, the tracking system can realize stable tracking of an unmanned aerial vehicle target on a distance within 25 meters;
(3) In the control of the servo turntable, the PID control algorithm is adopted, the proportion, the integral and the differential are calculated through the target angle difference value, the visual axis is accurately and rapidly directed to the target center of the unmanned aerial vehicle, the high-precision control of the servo turntable is realized, the tracking speed is improved, the target difference value simulated by the rotation of the motor is enabled to be continuously approximate to a smaller direction, the target can be tracked with high precision, and the high disturbance suppression capability is realized.
Drawings
In order to more clearly illustrate the embodiments of the application or the technical solutions in the prior art, the following description will briefly explain the drawings needed in the embodiments or the prior art description, and it is obvious that the drawings in the following description are some embodiments of the application and that other drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a functional requirement diagram of a tracking system according to an embodiment of the present application;
FIG. 2 is a flowchart of an image recognition module operation according to an embodiment of the present application;
FIG. 3 is a servo turret workflow diagram according to an embodiment of the application;
FIG. 4 is a schematic diagram of a system control module according to an embodiment of the application;
FIG. 5 is a schematic diagram of a hardware configuration according to an embodiment of the present application;
FIG. 6 is a block diagram of a software algorithm according to an embodiment of the application;
FIG. 7 is a general design of a hardware architecture according to an embodiment of the application;
FIG. 8 is a diagram of a coordinate system and a relative relationship according to an embodiment of the present application;
fig. 9 is a general design of a software algorithm according to an embodiment of the application.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present application more apparent, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application, and it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments of the present application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
The application provides a low-altitude unmanned aerial vehicle tracking method and method based on an unmanned platform, wherein the unmanned platform comprises an unmanned motion platform, a camera, a computer, a servo turntable containing a direct current motor and an embedded control board, and the tracking system is a functional schematic diagram as shown in fig. 1. For the unmanned aerial vehicle tracking technology, the animal is better than the animal to look at the object all the time. When an animal is always stared at a certain object, the vision of eyes, the reaction of brain and the actions of limbs are combined to realize, and the system has the functions of eyes, brain and limbs in order to realize the tracking of the unmanned aerial vehicle, and mainly completes the following functions in hardware realization: 1. image recognition function: the "eye" of the system is tracked. In order to realize tracking and aiming of the unmanned aerial vehicle, firstly, the position information of the unmanned aerial vehicle needs to be acquired, and for hardware realization, the most convenient imaging is realized by a camera. However, it is far from enough to acquire the image containing the unmanned aerial vehicle, and the unmanned aerial vehicle can be identified and the position of the unmanned aerial vehicle is determined, so that accurate tracking and aiming can be realized. The tracking and aiming system is required to have the capability of acquiring images and intelligently identifying the position information of the unmanned aerial vehicle; 2. servo turntable driving function: the "limb" of the system is tracked. After the position information of the unmanned aerial vehicle is obtained, the tracking and aiming system always places the unmanned aerial vehicle in the center of the own visual field, namely, in order to realize tracking and aiming alignment, and also in order to prevent the unmanned aerial vehicle from leaving the own visual field range, the tracking and aiming system is required to adjust the gesture of a camera according to the relative position relation with the unmanned aerial vehicle, the unmanned aerial vehicle flying in low altitude is always in the upper hemisphere of the visual field, and the function of a servo turntable is just realized, and the camera can be installed on the servo turntable to rotate; 3. central processing unit control function: the "brain" of the system is tracked. The two functions are completed by the coordination control of the central processing unit, so that the proper central processing unit is selected by combining the precision requirement of the tracking system and the parameter performance of the camera and the turntable hardware to realize the coordination control of the whole tracking system.
The application provides a low-altitude unmanned aerial vehicle tracking method based on an unmanned platform, which comprises the following steps:
step S1: collecting video stream images through a camera and transmitting the video stream images to a computer;
step S2: and carrying out image recognition by using the unmanned aerial vehicle recognition model stored in the computer and based on deep learning, and obtaining the position information of the unmanned aerial vehicle target center in the image.
In particular, as shown in fig. 2, in order to realize the function of image recognition, links of image acquisition, image transmission, image recognition and feedback of position information are required. The image acquisition and image transmission links are required to be completed by a camera, the high-resolution camera transmits image information to a computer after acquiring an image, and the computer end completes the links of image recognition and position information feedback. The realization of the partial functions can adopt a high-resolution USB camera, the acquired image is transmitted to a computer, the computer end uses a yolo and other image recognition algorithms to recognize the unmanned aerial vehicle, and the position of the target center of the unmanned aerial vehicle in the whole image is determined to obtain the position relation with the visual axis of the camera.
Step S3: outputting an angle value and a rotation instruction for controlling the rotation of the servo turntable based on the position information acquired in the step S2;
step S4: the servo turntable controls the visual axis of the camera to point to the target center of the unmanned aerial vehicle based on the instruction of the step S3.
As shown in fig. 3, the servo turntable can provide power for the steering of the camera, so that the following effect of the target transfer of the unmanned aerial vehicle in the visual axis direction is realized. The method mainly comprises three links of receiving a driving instruction, driving the motor to rotate and stopping rotating when reaching a target position. The three links all need special sub-control systems, and after the main control board obtains the relative position relation with the unmanned aerial vehicle from the computer end, the rotation condition of the motor is regulated through the sub-control systems, so that the three links are realized. The servo turntable itself can be realized by adopting a combination of a direct current motor, a bearing and a rigid frame, and a sub-control system can be realized by adopting an accurate control algorithm such as PID control.
As shown in fig. 4, a schematic diagram of a system control module is shown. The whole system control module is required to be integrated on a main control board to realize, so that the data acquisition of the current angle position of the motor can be carried out on the direct current motor, the relative position relationship between the communication receiving camera and the unmanned aerial vehicle target can be established between the computer terminal and the computer terminal, and the function of power supply of equipment is required. The realization of the module can be completed by utilizing an embedded main control board on hardware. The module on the software also needs to realize communication with a computer, and can control a driving system of a direct current motor, so that the control of a servo turntable is realized, and the effect of real-time tracking of an unmanned aerial vehicle target is achieved. .
On hardware, the three modules are respectively realized by a camera, a computer, a servo turntable containing a direct current motor and an embedded control board, and the embedded control board adopts a common STM32 main control board. As shown in fig. 5, the overall design concept of the hardware is as follows: the camera is connected with a computer, and the computer is in serial communication with STM 32. The computer acquires an image through the camera and identifies the image, and transmits the position information to the STM32 main control board through the serial port; and integrating a main system and a servo turntable subsystem on the STM32 main control board. The STM32 main control board sends a rotation instruction to the servo turntable sub-control system according to the position relation between the video axis of the camera and the unmanned aerial vehicle; STM32 main control board links to each other with direct current motor, and the camera is fixed on servo revolving stage frame. And the servo rotor control system drives the direct current motor to realize that the video axis of the camera moves to the target center position of the unmanned aerial vehicle through the output of PWM waves.
The tracking and aiming system mainly relates to an image recognition algorithm at a computer end, a main system program at a main control board end and a servo rotor control algorithm. As shown in fig. 6, an image recognition algorithm is included: the image recognition algorithm of the computer end is required to be capable of realizing real-time recognition of the unmanned aerial vehicle target in the input video stream and obtaining the position information of the target center in the image. The unmanned aerial vehicle recognition model is trained by mainly adopting a yolo_v4 image recognition algorithm and using a deep learning method, and the model is loaded to realize accurate recognition of the unmanned aerial vehicle. The position information of the unmanned aerial vehicle can be obtained by calculating the center coordinates of the recognition frame. Servo rotor control algorithm: for the control of a direct current motor of a servo turntable, a PID control algorithm is mainly adopted in the design. And calculating the proportion, the integral and the derivative through the target angle difference value, and accurately and rapidly pointing the visual axis to the target center of the unmanned aerial vehicle. The current position value is obtained by sampling the angle position of the direct current motor and converting the angle position into a visual axis position. Main system program: the main system prestored on the STM32 needs to carry out autonomous real-time control on the whole tracking and aiming system, so that the position information of the unmanned aerial vehicle at the computer end is acquired in real time, and the servo turntable is controlled in real time to point the visual axis to the target center of the unmanned aerial vehicle, so that the system is a core software program of the whole system.
The application discloses a low-altitude unmanned aerial vehicle tracking system based on an unmanned platform, which comprises a camera, a computer, a servo turntable containing a direct current motor and an embedded control board, wherein the embedded control board adopts an STM32 main control board; the camera is connected with the computer, the computer is in serial communication with the STM32, the computer acquires images through the camera and identifies the images, and the position information is transmitted to the STM32 main control board through the serial port; the STM32 main control board integrates a main system and a servo turntable sub-control system, and transmits a rotation instruction to the servo turntable sub-control system according to the position relation between the video axis of the camera and the unmanned aerial vehicle; STM32 main control board links to each other with direct current motor, and the camera is fixed on servo revolving stage frame, and servo revolving stage sub-control system passes through the output of PWM ripples, and the removal to unmanned aerial vehicle target central point position of camera visual axis is realized to drive direct current motor.
As shown in fig. 7, a tracking system diagram is designed for the overall hardware structure. The hardware of the system mainly comprises an image recognition part, a main control part and a servo turntable part. The image recognition part consists of a computer and a camera, the main control part is mainly an STM32 main control board, and the servo turntable part is mainly a direct current motor, a rotating frame, a platform base and the combination of the components and the camera. The hardware of the image recognition part and the main control part directly combines the existing hardware, the servo turntable part is the main work of hardware design, and the selection of hardware modules is further required to be refined.
For the control of the servo turntable, the basic principle of visual axis stability needs to be studied, and as shown in fig. 8, the coordinate system relationship in the servo turntable is first clarified, so that the motion correlation between the coordinate system axes is clarified, and the rotation of the turntable is mainly the relationship of the angle (angular velocity).
1. Turret coordinate system
And analyzing pitching movement and azimuth movement of the turntable, and establishing a rectangular coordinate system. The basic principle of coordinate transformation is utilized to describe the motion coupling relation of the direction and the pitching two axes, so that a kinematic model of the visual axis of the camera relative to the direction and the pitching two axes is established, the correlation of the relative position relation of the unmanned aerial vehicle with the direction and the pitching absolute position is realized, the adjustment mode of the motor can be determined, and the tracking of the unmanned aerial vehicle target is completed. The turntable coordinate system of the vehicle-mounted unmanned aerial vehicle aiming system mainly comprises an inertial coordinate system, a servo turntable coordinate system and an axis coordinate system, and is specifically defined as follows:
(1) Inertial coordinate system
The vehicle-mounted platform and the unmanned aerial vehicle are both in the inertial coordinate system of the earth to move, and the change condition of the movement postures of the vehicle-mounted platform and the unmanned aerial vehicle can be described by using the spatial inertial coordinate system. The origin of the inertial coordinate system is represented by the center of the earth, and the motion change states of the turntable and the tracked unmanned aerial vehicle target can be unified under the coordinate system, so that tracking control is realized.
(2) Servo turntable coordinate system
When the vehicle-mounted platform moves under the inertial coordinate system, the servo turntable coordinate system can be used for describing the movement posture change of the vehicle-mounted platform. The carrier is directly on the earth's surface in an inertial coordinate system, the rotational speed of which changes as the carrier changes relative to the inertial coordinate system, so in this context the home position of the servo turret coordinate system is fixed at the perpendicular intersection of the azimuth axis and the pitch axis, the coordinate system being denoted ox_zt y_zt z_zt.
(3) Axial coordinate system
The vehicle-mounted servo turntable is divided into two degrees of freedom of an azimuth axis and a pitch axis, and an azimuth axis coordinate system OX_fw Y_fw Z_fw and a pitch axis coordinate system OX_fy Y_fy Z_fy are respectively established. The coordinate axis OZ_zw of the azimuth axis coordinate system and the OZ_zt axis of the servo turntable coordinate system are overlapped, and are perpendicular to the same plane, so that the azimuth motion state of the servo turntable can be reflected; coordinate axis OY_fy of the pitching axis coordinate system is coincident with coordinate axis OY_fw of the azimuth axis coordinate system; the pointing axis of the visual axis center is consistent with the coordinate axis OY_fy direction of the pitching axis coordinate system; the coordinate axis ox_fy of the pitch axis coordinate system coincides with the coordinate axis ox_fw of the azimuth axis coordinate system, and as shown in fig. 8, the definition and the correlation of each coordinate system are shown, and when the azimuth axis coordinate system rotates by the angle θ_fw as a whole, the rotation angle coupled to the pitch axis coordinate system is θ_fy.
2. Establishment of visual axis mathematical model
The high-precision camera view field in the pitching frame of the servo turntable can generate state change according to the motion state of the carrier and the rotation state of the servo turntable, namely the condition of visual axis motion change. According to the geometric constraint relation between the axis coordinate system and the servo turntable coordinate system, friction constraint is generated when the carrier moves and the axis rotates, and the visual axis movement condition is also obtained by coupling the constraint relation of the carrier and the servo turntable coordinate system. If the center of the visual axis is always aligned to the target of the unmanned aerial vehicle, real-time closed-loop control is required to be performed on the azimuth axis and the pitching axis of the servo turntable, and therefore a coordinate transformation relation between the motion of the carrier and the motion of the visual axis is required to be obtained.
The angular velocity of the change of the posture of the servo turntable is set to be omega along three axes on a coordinate system of the servo turntable ztx 、ω zty 、ω ztz The method comprises the steps of carrying out a first treatment on the surface of the The angular velocity of the visual axis in the inertial coordinate system is omega respectively gx 、ω gy 、ω gz The method comprises the steps of carrying out a first treatment on the surface of the When the servo turntable is in a static zero state, the motion of the posture of the servo turntable is converted into the angle of the azimuth axis coordinate system through the coupling relation between the servo turntable and the azimuth axisSpeed omega fwx 、ω fwy 、ω fwz Angular velocity converted to a pitch axis coordinate system by a coupling relation with the pitch axis is ω fwx 、ω fyy 、ω fyz . When the azimuth axis of the servo turntable changes by an angle theta fw The pitch axis changes by an angle theta fy From this, the relationship between the angular velocity of the attitude change of the servo turntable coordinate system and the angular velocity of the attitude change of the azimuth axis coordinate system is obtained:
the application relates to a main servo rotor control algorithm, an image recognition algorithm at a computer end and a main system program at a main control board end, as shown in fig. 9, a tracking system designed by the application adopts a position closed-loop PID control algorithm, a yolo_v4 image recognition algorithm based on deep learning and comprehensive control software of the tracking system based on STM32 in the aspect of software algorithm. High-precision control of the servo turntable is realized through a position closed-loop PID control algorithm, so that the difference value between the servo turntable and the target position is reduced to serve as a target function, and the turntable is quickly adjusted to a state that the visual axis coincides with the target center of the unmanned aerial vehicle.
In the embodiment of the application, sampling test is carried out through the test set pictures: and calling the trained Weights file in the Python by utilizing the picture identification function of the yolo algorithm, and carrying out identification detection on the picture of the inspection set. And setting the recognition credibility threshold value to 0.6, considering the recognition target as the unmanned aerial vehicle target when the recognition credibility is larger than 0.6, and displaying the recognition frame. Analysis of data by sampling test: 200 pictures are randomly selected from 400 pictures of the inspection set with the shooting distance of 5-25 meters for recognition, the maximum value of the recognition reliability is 0.988, and the minimum value is 0.776, so that the unmanned aerial vehicle can be successfully recognized and a range box of the unmanned aerial vehicle can be obtained. And respectively storing the identification credibility of the test set pictures into a table, and reading table data by MATLAB for analysis. The identification reliability of the weight file is over 0.75, and the identification rate is 100% (5-25 m distance).
The application also discloses a computer storage medium which stores computer program instructions, and when the computer program instructions are executed, the low-altitude unmanned aerial vehicle tracking method based on the unmanned platform is realized.
In conclusion, training and using of an image recognition model are achieved based on an image recognition algorithm, the unmanned aerial vehicle target is recognized at a high recognition rate, and meanwhile position information of the unmanned aerial vehicle in an image is obtained according to the center coordinates of the target frame. Through tracking system integrated control software based on STM32, tracking system can acquire computer identification information, send the PID control instruction to servo revolving stage, realizes the whole regulation and control to tracking system, fully utilizes the comprehensive properties of STM32, has improved unmanned aerial vehicle tracking speed and precision.
Note that the technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be regarded as the scope of the description. The foregoing examples illustrate only a few embodiments of the application, which are described in detail and are not to be construed as limiting the scope of the application. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the application, which are all within the scope of the application. Accordingly, the scope of protection of the present application is to be determined by the appended claims.
Claims (10)
1. The utility model provides a low altitude unmanned aerial vehicle is aimed at method based on unmanned platform, unmanned platform includes camera and contains direct current motor's servo revolving stage, its characterized in that, the method includes:
step S1: acquiring video stream images containing the unmanned aerial vehicle through a camera and transmitting the video stream images to a computer;
step S2: performing image recognition on the acquired video stream image by using an unmanned aerial vehicle recognition model stored in a computer to acquire position information of an unmanned aerial vehicle target center in the video stream image;
step S3: controlling the rotating angle value and the rotating instruction of the servo turntable based on the position information acquired in the step S2;
step S4: and the servo turntable controls the visual axis of the camera to point to the target center of the unmanned aerial vehicle based on the angle value and the rotation instruction in the step S3.
2. The unmanned aerial vehicle tracking method based on the unmanned platform of claim 1, wherein step S2 further comprises: and selecting a yolo recognition algorithm or a contour recognition algorithm for image recognition aiming at different sky background conditions contained in the acquired video stream image so as to acquire an unmanned aerial vehicle target center, and determining the position of the unmanned aerial vehicle target center in the whole image to acquire the position relation between the unmanned aerial vehicle target center and the camera visual axis.
3. The unmanned aerial vehicle tracking method based on the unmanned platform according to claim 2, wherein step S3 further comprises: the servo turntable with the direct current motor is controlled by using a position closed loop PID control algorithm, and the servo turntable provides power for the steering of the camera so as to realize the transfer following of the visual axis of the camera to the target center of the unmanned aerial vehicle; the angular velocity of the change of the posture of the servo turntable is set to be omega along three axes on a coordinate system of the servo turntable ztx 、ω zty 、ω ztz The method comprises the steps of carrying out a first treatment on the surface of the When the servo turntable is in a static zero state, the angular velocity of the motion of the posture of the servo turntable converted to an azimuth axis coordinate system through the coupling relation between the motion and the azimuth axis is omega fwx 、ω fwy 、ω fwz The azimuth axis of the servo turntable is changed to be theta fw The pitch axis is changed in angle to theta fy The relationship between the angular velocity of the attitude change of the servo turntable coordinate system and the angular velocity of the attitude change of the azimuth axis coordinate system is as follows:
4. the unmanned aerial vehicle tracking method based on the unmanned platform according to claim 2, wherein the closed-loop PID control algorithm comprises the calculation of the ratio, the integral and the derivative of the target angle difference.
5. A low-altitude unmanned aerial vehicle tracking and aiming system based on an unmanned platform is characterized in that: the system comprises a camera, a servo turntable containing a direct current motor and an embedded control board, wherein the embedded control board adopts an STM32 main control board; the method comprises the steps that a camera is connected with a computer, the computer is connected with an STM32 main control board, the computer obtains a video stream image containing the unmanned aerial vehicle through the camera and identifies to obtain position information of a target center of the unmanned aerial vehicle in the video stream image, and the position information is transmitted to the STM32 main control board; the STM32 main control board integrates a main system and a servo turntable sub-control system, and transmits a rotation instruction to the servo turntable sub-control system according to the position relation between the video axis of the camera and the unmanned aerial vehicle; the STM32 main control board is connected with the direct current motor, the camera is fixed on the rotating frame of the servo turntable, and the servo turntable sub-control system drives the direct current motor to realize that the visual axis of the camera moves to the target center position of the unmanned aerial vehicle through PWM wave output; the system performs the steps of:
step S1: collecting video stream images through a camera and transmitting the video stream images to a computer;
step S2: performing image recognition on the video stream image by using an unmanned aerial vehicle recognition model stored in a computer to acquire position information of an unmanned aerial vehicle target center in the image;
step S3: outputting an angle value and a rotation instruction for controlling the rotation of the servo turntable based on the position information acquired in the step S2;
step S4: and controlling the visual axis of the camera to point to the target center of the unmanned aerial vehicle by the servo turntable based on the angle value and the rotation instruction in the step S3.
6. The unmanned aerial vehicle tracking system based on the unmanned platform of claim 5, wherein the main system on the STM32 main control board performs autonomous real-time control on the whole tracking system, acquires unmanned aerial vehicle position information at a computer end in real time, and controls the servo turntable to direct a camera visual axis to an unmanned aerial vehicle target center in real time.
7. The unmanned aerial vehicle tracking system of claim 5, wherein the servo turret coordinate system consists of an inertial coordinate system, a servo turret coordinate system, and an axis coordinate system.
8. The unmanned aerial vehicle tracking system of claim 7, wherein the azimuth axis and the elevation axis of the servo turntable are closed-loop controlled in real time.
9. The unmanned aerial vehicle tracking system of claim 7, wherein the angular velocity along three axes on the servo turret coordinate system is ω for the angular velocity of the servo turret attitude change ztx 、ω zty 、ω ztz The method comprises the steps of carrying out a first treatment on the surface of the When the servo turntable is in a static zero state, the angular velocity of the motion of the posture of the servo turntable converted to an azimuth axis coordinate system through the coupling relation between the motion and the azimuth axis is omega fwx 、ω fwy 、ω fwz The azimuth axis of the servo turntable is changed to be theta fw The pitch axis is changed in angle to theta fy The relationship between the angular velocity of the attitude change of the servo turntable coordinate system and the angular velocity of the attitude change of the azimuth axis coordinate system is as follows:
10. a computer storage medium storing computer program instructions which, when executed, implement the unmanned platform based low-altitude unmanned aerial vehicle tracking method of any of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310577695.9A CN116991180A (en) | 2023-05-22 | 2023-05-22 | Unmanned plane tracking method, system and storage medium based on unmanned plane platform |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310577695.9A CN116991180A (en) | 2023-05-22 | 2023-05-22 | Unmanned plane tracking method, system and storage medium based on unmanned plane platform |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116991180A true CN116991180A (en) | 2023-11-03 |
Family
ID=88529023
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310577695.9A Pending CN116991180A (en) | 2023-05-22 | 2023-05-22 | Unmanned plane tracking method, system and storage medium based on unmanned plane platform |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116991180A (en) |
-
2023
- 2023-05-22 CN CN202310577695.9A patent/CN116991180A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20210223795A1 (en) | System and method for supporting smooth target following | |
| CN109029433A (en) | Join outside the calibration of view-based access control model and inertial navigation fusion SLAM on a kind of mobile platform and the method for timing | |
| US11906983B2 (en) | System and method for tracking targets | |
| Gur fil et al. | Partial aircraft state estimation from visual motion using the subspace constraints approach | |
| CN110498039A (en) | A kind of intelligent monitor system based on bionic flapping-wing flying vehicle | |
| CN107389968A (en) | A kind of unmanned plane fixed-point implementation method and apparatus based on light stream sensor and acceleration transducer | |
| Cunha et al. | Gimbal control for vision-based target tracking | |
| Battiato et al. | A system for autonomous landing of a UAV on a moving vehicle | |
| De Wagter et al. | Towards vision-based uav situation awareness | |
| Miller et al. | UAV navigation based on videosequences captured by the onboard video camera | |
| CN115857520B (en) | Unmanned aerial vehicle landing state monitoring method based on combination of vision and ship state | |
| Amidi et al. | Research on an autonomous vision-guided helicopter | |
| Schell et al. | Autonomous landing of airplanes by dynamic machine vision | |
| CN109521785B (en) | Intelligent rotor craft system capable of being shot with oneself | |
| Høglund | Autonomous inspection of wind turbines and buildings using an UAV | |
| CN116991180A (en) | Unmanned plane tracking method, system and storage medium based on unmanned plane platform | |
| Boucheloukh et al. | UAV navigation based on adaptive fuzzy backstepping controller using visual odometry | |
| Cao et al. | Research on application of computer vision assist technology in high-precision UAV navigation and positioning | |
| CN110986944A (en) | Ship attitude identification method for shipborne reconnaissance and shooting unmanned aerial vehicle | |
| Ibrahim et al. | Vision-based autonomous tracking control of unmanned aerial vehicle | |
| Ma et al. | KCF based 3D Object Tracking via RGB-D Camera of a Quadrotor | |
| LIANG et al. | Moving target tracking of UAV/UGV heterogeneous system based on quick response code | |
| Li et al. | Control system for a light and small pan-tilt based on multirotor UAV for aerial remote sensing applications | |
| Zhao et al. | 2D monocular visual odometry using mobile-phone sensors | |
| Mofid et al. | Navigation of Swarm Quadcopters in GPS-Denied Environment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |