System and method for discovering and tracking unmanned aerial vehicle based on longitude and latitude by pan-tilt camera

Abstract

The invention provides a system and a method for discovering and tracking an unmanned aerial vehicle based on longitude and latitude by a pan-tilt camera, and relates to the technical field of image tracking. According to the invention, relation mapping is carried out on the actual control quantity corresponding to each control parameter of the PTZ camera, so that the actual control quantity can be accurately adjusted by adjusting the control parameters; position information of a pan-tilt camera is calibrated, a calibration point is set, and a correction angle is obtained, so that angle control deviation is corrected, and error superposition is avoided; a complex unmanned aerial vehicle position positioning algorithm is not needed, efficient scanning is directly carried out through the radar to find the unmanned aerial vehicle, the pan-tilt camera only needs to collect the image of the corresponding area, the unmanned aerial vehicle target can be autonomously recognized and tracked, and the method has the advantages that the monocular cost is low, and the monocular algorithm is simple and efficient; in addition, control parameters are adjusted directly according to image conditions; therefore, the system regulates and controls the parameters directly according to the image state instead of a secondary algorithm control result, so that the image stability is ensured.

Description

Technical Field

[0001] The present invention relates to the field of image tracking technology, and in particular to a system and method for a pan-tilt camera to discover and track a drone based on longitude and latitude. Background Art

[0002] 2024 is known as the "first year of low-altitude economy", and the high-quality development of low-altitude economy has become the focus of social attention. In this context, effective identification and supervision of low-altitude aircraft has become one of the key factors in achieving high-quality development of low-altitude economy; currently, the detection, identification and tracking of low-altitude drones face the challenge of low automation.

[0003] Most of the existing low-altitude UAV identification and tracking systems rely on manual operations, such as manual frame tracking, which is not only inefficient but also difficult to adapt to the complex and changeable low-altitude environment.

[0004] In addition, the autonomous positioning technology of low-altitude drones is not yet mature, and the display ratio and position of the drone in the picture cannot be guaranteed, which brings additional difficulties to the tracking and supervision of drones.

[0005] Therefore, there is an urgent need for a system and method for a gimbal camera to discover and track drones based on longitude and latitude to solve the problems of low automation and insufficient autonomous positioning in the current low-altitude drone identification and tracking system. Summary of the invention

[0006] The purpose of the present invention is to overcome the shortcomings of the prior art and provide a system and method for a gimbal camera to discover and track drones based on longitude and latitude, mainly to solve the problems of manual frame tracking in the prior art, which cannot guarantee the display ratio and position of the drone in the picture, and the high cost of tracking hardware and complex software implementation.

[0007] The purpose of the present invention is achieved through the following technical solutions: In a first aspect, a method for a gimbal camera to discover and track a drone based on longitude and latitude is provided, wherein the drone is discovered and tracked by the following steps: Step 1: Install the PTZ camera; and determine the mapping relationship of each control parameter of the PTZ camera; Step 2: gimbal camera calibration, including gimbal camera position information calibration, calibration point setting and correction angle acquisition; Step 3: The radar detects the drone target; the radar monitoring unit detects and collects the drone target location information; Step 4: PTZ camera adjustment: adjust various control parameters according to the UAV target position information collected by the radar monitoring unit, so that the UAV target appears in the picture of the PTZ camera output video stream in a preset state; Step 5: Autonomously identify drone targets; the gimbal camera uses the locally set drone detection model to detect drones in the output video stream and identify drone targets appearing in the screen; if a drone target is identified, execute step 6; otherwise, return to step 3 and wait for the radar monitoring unit to discover and collect the drone target location information; Step 6: Autonomously track the drone target; the gimbal camera continuously adjusts various control parameters so that the drone target remains in the picture of the gimbal camera output video stream in a preset state.

[0008] As a further solution, the gimbal camera can be rotated and zoomed through various control parameters. The control parameter pan is used to adjust the horizontal rotation of the gimbal, the control parameter tilt is used to adjust the pitch rotation of the gimbal, and the control parameter zoom is used to adjust the zoom of the gimbal camera.

[0009] As a further solution, in step 1, the control parameter mapping relationship determined includes: Determine the mapping relationship between the horizontal angle of the gimbal camera and the control parameter pan, and obtain the mapping relationship of the horizontal control parameter; Determine the mapping relationship between the pitch angle of the gimbal camera and the control parameter tilt, and obtain the mapping relationship of the pitch control parameter; The mapping relationship between the pan / tilt camera magnification and the control parameter zoom is determined to obtain the mapping relationship of the zoom control parameter.

[0010] As a further solution, the gimbal camera position information and the drone target position information are both represented by longitude information, latitude information and altitude information.

[0011] As a further solution, the correction angle is obtained by the following steps: Get the set calibration point; Control the pan / tilt camera to rotate and zoom so that the center of the output video stream is aligned with the calibration point; Get the aligned control parameters pan and tilt; Calculate the angle between the origin position where the control parameter pan and the control parameter tilt are both 0 and the calibration point; Set the angle between the origin and the calibration point as the correction angle.

[0012] As a further solution, in step 4, adjust the control parameters as follows: Obtain the target location information of the UAV through the radar monitoring unit; Calculate the target azimuth according to the gimbal camera position information and the drone target position information; Correct the target azimuth by the correction angle to obtain the actual adjustment angle; Convert the actual adjustment angle into a horizontal angle adjustment value and a pitch angle adjustment value; The control parameter pan adjustment value is obtained through the horizontal control parameter mapping relationship and the horizontal angle adjustment value; The control parameter tilt adjustment value is obtained through the pitch control parameter mapping relationship and the pitch angle adjustment value; The focal length adjustment value is calculated based on the gimbal camera position information and the drone target position information; Calculate the magnification adjustment value through the focal length adjustment value; The control parameter zoom adjustment value is obtained through the zoom control parameter mapping relationship and the magnification adjustment value.

[0013] As a further solution, the focal length adjustment value is calculated by the following formula; ; ; Among them, focal_length represents the focal length adjustment value; fram_width represents the screen width of the video stream output by the gimbal camera; obj_ratio is the setting value of the ratio of the drone target in the screen; pixel_size is the pixel size; d_uav_2_o represents the target distance value between the drone target and the gimbal camera; obj_width is the width value of the drone target in the screen; m is the magnification adjustment value; focal_length_min is the minimum focal length adjustment value.

[0014] As a further solution, when autonomously tracking a drone target, adjust the control parameter pan as follows: Obtain the horizontal change of the drone target obj_center_x_change through the center position of the drone target in the previous frame and the center position of the current frame; Get the horizontal field of view h_fov of the gimbal camera and the frame width frame_width of the gimbal camera output video stream at the current magnification; Calculate the horizontal offset ratio ratio_x_offset of the drone target in the horizontal direction of the video stream through obj_center_x_change / frame_width; The horizontal field of view adjustment degree x_fov is calculated by multiplying ratio_x_offset by h_fov; Get the parameter adjustment range value range_pan of the control parameter pan and the pan / tilt horizontal rotation angle adjustment range value range_horizonta langle; The resolution_pan is adjusted by calculating the control parameter pan through range_pan / range_horizontal langle; By multiplying x_fov by resolution_pan, we can calculate the control parameter adjustment change_pan for the horizontal rotation of the gimbal. If the x value of the current drone target center position is greater than the x value of the screen center position: final_pan = original_pan + change_pan; If the x value of the current drone target center position is smaller than the x value of the screen center position: final_pan = original_pan - change_pan; Among them, original_pan is the current control parameter pan; final_pan is the adjusted control parameter pan.

[0015] As a further solution, when autonomously tracking a drone target, adjust the control parameter tilt by following the steps below: Obtain the vertical angle change of the drone target obj_center_y_change through the center position of the drone target in the previous frame and the center position of the current frame; Get the vertical field of view v_fov of the gimbal camera at the current magnification and the frame height value frame_height of the video stream output by the gimbal camera; Calculate the horizontal offset ratio ratio_y_offset of the drone target in the vertical direction of the video stream through obj_center_y_change / frame_height; The vertical field of view adjustment degree y_fov is calculated by multiplying ratio_y_offset by v_fov; Get the parameter adjustment range value range_tilt of the control parameter tilt, the minimum vertical rotation angle value vertical_angle_min of the gimbal, and the maximum vertical rotation angle value veritcal_angle_max of the gimbal; The parameter adjustment resolution_tilt of the control parameter tilt is calculated by range_tilt / [abs(vertical_angle_min)+abs(vertical_angle_max)]; By multiplying y_fov by resolution_tilt, we can calculate the control parameter adjustment change_tilt of the vertical rotation of the gimbal. If the y value of the current drone target center position is greater than the y value of the screen center position: final_tilt = original_tilt - change_tilt; If the y value of the current drone target center position is smaller than the y value of the screen center position: final_tilt = original_tilt + change_tilt; Among them, original_tilt is the current control parameter tilt; final_tilt is the adjusted control parameter tilt.

[0016] In a second aspect, a system for a gimbal camera to detect and track drones based on longitude and latitude is provided, using a method for a gimbal camera to detect and track drones based on longitude and latitude as described in any of the above items.

[0017] Compared with the related art, the system and method for detecting and tracking drones based on longitude and latitude provided by the present invention has the following advantages: The present invention does not require a complex UAV positioning algorithm, but directly uses radar to efficiently scan and discover UAVs. The gimbal camera only needs to collect images of the corresponding area to autonomously identify and track the UAV target. It has the advantages of low monocular cost, no need to set up local radar, and simple and efficient monocular algorithm. In addition, since the control parameters are adjusted directly according to the image conditions, the system can directly ensure the image status rather than the secondary algorithm control result. The early mapping relationship, calibration point setting and correction angle further ensure the accuracy of control. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 A schematic diagram of a method for a pan-tilt camera to discover and track a drone based on longitude and latitude provided by the present invention; Figure 2 This is a schematic diagram of the similar triangle principle provided by the present invention. DETAILED DESCRIPTION

[0019] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0020] See also Figure 1 The present invention provides a method for a pan-tilt camera to discover and track a UAV based on longitude and latitude, and the method discovers and tracks a UAV through the following steps: Step 1: Install the PTZ camera; and determine the mapping relationship of each control parameter of the PTZ camera; Step 2: gimbal camera calibration, including gimbal camera position information calibration, calibration point setting and correction angle acquisition; Step 3: The radar detects the drone target; the radar monitoring unit detects and collects the drone target location information; Step 4: PTZ camera adjustment: adjust various control parameters according to the UAV target position information collected by the radar monitoring unit, so that the UAV target appears in the picture of the PTZ camera output video stream in a preset state; Step 5: Autonomously identify drone targets; the gimbal camera uses the locally set drone detection model to detect drones in the output video stream and identify drone targets appearing in the screen; if a drone target is identified, execute step 6; otherwise, return to step 3 and wait for the radar monitoring unit to discover and collect the drone target location information; Step 6: Autonomously track the drone target; the gimbal camera continuously adjusts various control parameters so that the drone target remains in the picture of the gimbal camera output video stream in a preset state.

[0021] It should be noted that most of the existing low-altitude UAV identification and tracking systems rely on manual operation, and cannot guarantee the display ratio and position of the UAV in the picture. In addition, many of them are based on binocular positioning and require complex identification and tracking algorithms, which have the problems of high cost, low degree of automation, identification accuracy and tracking stability.

[0022] First, this embodiment maps the relationship between each control parameter of the gimbal camera and the actual control amount, so as to ensure that the actual control amount can be accurately adjusted by adjusting the control parameters; by calibrating the position information of the gimbal camera, setting the calibration point and obtaining the correction angle, the angle control deviation is corrected and error superposition is avoided.

[0023] Then, this embodiment scans and monitors an area through the radar monitoring unit, collects the drone target position information after discovering the low-altitude drone target, and sends it to the gimbal camera corresponding to the current area; the gimbal camera adjusts the camera angle and focal length according to the drone target position information to aim at the corresponding drone target.

[0024] Finally, the gimbal camera uses the locally set drone detection model to detect drones in the output video stream, identify drone targets appearing in the picture, and after discovering the drone target, continuously adjust the control parameters of the gimbal camera based on pure visual image analysis, so that the drone target remains in the picture of the gimbal camera output video stream in a preset state.

[0025] This method does not require a complex UAV positioning algorithm, but directly detects the UAV through efficient scanning through radar. The gimbal camera only needs to collect images of the corresponding area to autonomously identify and track the UAV target. It has the advantages of low monocular cost, no need to set up local radar, and simple and efficient monocular algorithm. In addition, since the control parameters are adjusted directly according to the image conditions, this system can directly guarantee the image status rather than the secondary algorithm control result (with greater error). The early mapping relationship, calibration point setting and correction angle further guarantee the accuracy of control.

[0026] The control parameters used in this embodiment mainly include: the control parameter pan is used to adjust the horizontal rotation of the gimbal, the control parameter tilt is used to adjust the pitch rotation of the gimbal, and the control parameter zoom is used to adjust the magnification of the gimbal camera; through these three control parameters we can efficiently adjust the angle and focal length.

[0027] As a further solution, in step 1, the control parameter mapping relationship determined includes: Determine the mapping relationship between the horizontal angle of the gimbal camera and the control parameter pan, and obtain the mapping relationship of the horizontal control parameter; Determine the mapping relationship between the pitch angle of the gimbal camera and the control parameter tilt, and obtain the mapping relationship of the pitch control parameter; The mapping relationship between the pan / tilt camera magnification and the control parameter zoom is determined to obtain the mapping relationship of the zoom control parameter.

[0028] Through the gimbal camera position information and the longitude, latitude and altitude information of the drone's target location, we can preliminarily calculate the target azimuth, so that the gimbal camera can quickly aim at the corresponding area.

[0029] As a further solution, the correction angle is obtained by the following steps: Get the set calibration point; Control the pan / tilt camera to rotate and zoom so that the center of the output video stream is aligned with the calibration point; Get the aligned control parameters pan and tilt; Calculate the angle between the origin position where the control parameter pan and the control parameter tilt are both 0 and the calibration point; Set the angle between the origin and the calibration point as the correction angle.

[0030] As a further solution, in step 4, adjust the control parameters as follows: Obtain the target location information of the UAV through the radar monitoring unit; Calculate the target azimuth according to the gimbal camera position information and the drone target position information; Correct the target azimuth by the correction angle to obtain the actual adjustment angle; Convert the actual adjustment angle into a horizontal angle adjustment value and a pitch angle adjustment value; The control parameter pan adjustment value is obtained through the horizontal control parameter mapping relationship and the horizontal angle adjustment value; The control parameter tilt adjustment value is obtained through the pitch control parameter mapping relationship and the pitch angle adjustment value; The focal length adjustment value is calculated based on the gimbal camera position information and the drone target position information; Calculate the magnification adjustment value through the focal length adjustment value; The control parameter zoom adjustment value is obtained through the zoom control parameter mapping relationship and the magnification adjustment value.

[0031] As a further solution, the focal length adjustment value is calculated by the following formula; ; ; Among them, focal_length represents the focal length adjustment value; fram_width represents the screen width of the video stream output by the gimbal camera; obj_ratio is the setting value of the ratio of the drone target in the screen; pixel_size is the pixel size; d_uav_2_o represents the target distance value between the drone target and the gimbal camera; obj_width is the width value of the drone target in the screen; m is the magnification adjustment value; focal_length_min is the minimum focal length adjustment value.

[0032] It should be noted that: this embodiment mainly uses the principle of similar triangles, such as Figure 2 In: L is the target width, d is the target distance value, o is the camera center point, and f is the focal length; according to the principle of similar triangles, the target width mapped on the camera screen is Ld / f; similarly, in order to display the drone target in the screen with the set ratio setting value, it is necessary to adjust the focal length, that is, it is necessary to calculate the focal length adjustment value and consider the influence of the pixel size. In addition, since this embodiment is based on the control parameter zoom for zoom adjustment, it is also necessary to convert the focal length adjustment value into a magnification adjustment value; wherein the magnification is the ratio of the current focal length to the minimum focal length.

[0033] As a further solution, when autonomously tracking a drone target, adjust the control parameter pan as follows: Obtain the horizontal change of the drone target obj_center_x_change through the center position of the drone target in the previous frame and the center position of the current frame; Get the horizontal field of view h_fov of the gimbal camera and the frame width frame_width of the gimbal camera output video stream at the current magnification; Calculate the horizontal offset ratio ratio_x_offset of the drone target in the horizontal direction of the video stream through obj_center_x_change / frame_width; The horizontal field of view adjustment degree x_fov is calculated by multiplying ratio_x_offset by h_fov; Get the parameter adjustment range value range_pan of the control parameter pan and the pan / tilt horizontal rotation angle adjustment range value range_horizonta langle; The resolution_pan is adjusted by calculating the control parameter pan through range_pan / range_horizontal langle; By multiplying x_fov by resolution_pan, we can calculate the control parameter adjustment change_pan for the horizontal rotation of the gimbal. If the x value of the current drone target center position is greater than the x value of the screen center position: final_pan = original_pan + change_pan; If the x value of the current drone target center position is smaller than the x value of the screen center position: final_pan = original_pan - change_pan; Among them, original_pan is the current control parameter pan; final_pan is the adjusted control parameter pan.

[0034] It should be noted that we first need to obtain the change in the horizontal direction of the drone target; then, based on the horizontal field of view angle of the gimbal camera at the current magnification (there is a corresponding relationship between the field of view angle and the magnification) and the ratio of the change in the horizontal direction, we can obtain the horizontal offset ratio of the drone target in the horizontal direction of the video stream, and calculate the adjustment degree of the horizontal field of view angle; Consider the parameter adjustment resolution of the control parameter pan (that is, how much rotation corresponds to each unit of control), and then calculate the control parameter adjustment amount of the horizontal rotation of the gimbal by dividing it by the horizontal field of view angle adjustment degree, and adjust the control parameter pan according to the actual positive and negative situation.

[0035] In a specific embodiment, the gimbal camera can rotate 360°, that is, the gimbal horizontal rotation angle adjustment range value range_horizontal langle=360; no matter what magnification the gimbal camera lens is at, the range of the control parameter pan is -1~1, so range_pan is 2, and the parameter adjustment resolution resolution_pan=2 / 360.

[0036] As a further solution, when autonomously tracking a drone target, adjust the control parameter tilt by following the steps below: Obtain the vertical angle change of the drone target obj_center_y_change through the center position of the drone target in the previous frame and the center position of the current frame; Get the vertical field of view v_fov of the gimbal camera at the current magnification and the frame height value frame_height of the video stream output by the gimbal camera; Calculate the horizontal offset ratio ratio_y_offset of the drone target in the vertical direction of the video stream through obj_center_y_change / frame_height; The vertical field of view adjustment degree y_fov is calculated by multiplying ratio_y_offset by v_fov; Get the parameter adjustment range value range_tilt of the control parameter tilt, the minimum vertical rotation angle value vertical_angle_min of the gimbal, and the maximum vertical rotation angle value veritcal_angle_max of the gimbal; The parameter adjustment resolution_tilt of the control parameter tilt is calculated by range_tilt / [abs(vertical_angle_min)+abs(vertical_angle_max)]; By multiplying y_fov by resolution_tilt, we can calculate the control parameter adjustment change_tilt of the vertical rotation of the gimbal. If the y value of the current drone target center position is greater than the y value of the screen center position: final_tilt = original_tilt - change_tilt; If the y value of the current drone target center position is smaller than the y value of the screen center position: final_tilt = original_tilt + change_tilt; Among them, original_tilt is the current control parameter tilt; final_tilt is the adjusted control parameter tilt.

[0037] It should be noted that the calculation principle is similar to the adjustment in the horizontal direction. The difference is that the vertical direction of the gimbal (i.e. the pitch angle direction) has a range. For example, it can only pitch up to 60° and can only pitch down to 60°. In the gimbal system, there will be positive and negative values, so the absolute value is used to calculate the tilt value corresponding to each degree in the tilt direction: abs(vertical_angle_min (minimum pitch angle)) and abs(vertical_angle_max (maximum pitch angle)).

[0038] The above embodiments only express preferred implementation modes, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present invention. It should be pointed out that, for ordinary technicians in this field, several modifications and improvements can be made without departing from the concept of the present invention, and these all belong to the protection scope of the present invention.

Claims

1. A method for detecting and tracking a drone using a pan-tilt camera based on longitude and latitude, characterized in that: Follow these steps to find and track a drone: Step 1: Install the PTZ camera; and determine the mapping relationship of each control parameter of the PTZ camera; Step 2: gimbal camera calibration, including gimbal camera position information calibration, calibration point setting and correction angle acquisition; Step 3: The radar detects the drone target; the radar monitoring unit detects and collects the drone target location information; Step 4: PTZ camera adjustment: adjust various control parameters according to the UAV target position information collected by the radar monitoring unit, so that the UAV target appears in the picture of the PTZ camera output video stream in a preset state; Step 5: Autonomously identify drone targets; the gimbal camera uses the locally set drone detection model to detect drones in the output video stream and identify drone targets appearing in the screen; if a drone target is identified, execute step 6; otherwise, return to step 3 and wait for the radar monitoring unit to discover and collect the drone target location information; Step 6: Autonomously track the drone target; the gimbal camera continuously adjusts various control parameters so that the drone target remains in the picture of the gimbal camera output video stream in a preset state.

2. The method for detecting and tracking a UAV by a PTZ camera based on longitude and latitude according to claim 1, characterized in that: The pan / tilt camera is rotated and zoomed through various control parameters. The pan control parameter is used to adjust the horizontal rotation of the pan / tilt, the tilt control parameter is used to adjust the pitch rotation of the pan / tilt, and the zoom control parameter is used to adjust the zoom of the pan / tilt camera.

3. The method for detecting and tracking a UAV based on latitude and longitude by a PTZ camera according to claim 2, characterized in that: In step 1, the measured control parameter mapping relationship includes: Determine the mapping relationship between the horizontal angle of the gimbal camera and the control parameter pan, and obtain the mapping relationship of the horizontal control parameter; Determine the mapping relationship between the pitch angle of the gimbal camera and the control parameter tilt, and obtain the mapping relationship of the pitch control parameter; The mapping relationship between the pan / tilt camera magnification and the control parameter zoom is determined to obtain the mapping relationship of the zoom control parameter.

4. The method for detecting and tracking a UAV based on latitude and longitude by a PTZ camera according to claim 1, characterized in that: The gimbal camera position information and the drone target position information are both represented by longitude information, latitude information, and altitude information.

5. The method for detecting and tracking a UAV based on latitude and longitude by a PTZ camera according to claim 2, characterized in that: Obtain the correction angle by following the steps below: Get the set calibration point; Control the pan / tilt camera to rotate and zoom so that the center of the output video stream is aligned with the calibration point; Get the aligned control parameters pan and tilt; Calculate the angle between the origin position where the control parameter pan and the control parameter tilt are both 0 and the calibration point; Set the angle between the origin and the calibration point as the correction angle.

6. A method for detecting and tracking a UAV based on latitude and longitude using a PTZ camera according to any one of claim 3 or claim 5, characterized in that: In step 4, adjust the control parameters as follows: Obtain the target location information of the UAV through the radar monitoring unit; Calculate the target azimuth according to the gimbal camera position information and the drone target position information; Correct the target azimuth by the correction angle to obtain the actual adjustment angle; Convert the actual adjustment angle into a horizontal angle adjustment value and a pitch angle adjustment value; The control parameter pan adjustment value is obtained through the horizontal control parameter mapping relationship and the horizontal angle adjustment value; The control parameter tilt adjustment value is obtained through the pitch control parameter mapping relationship and the pitch angle adjustment value; The focal length adjustment value is calculated based on the gimbal camera position information and the drone target position information; Calculate the magnification adjustment value through the focal length adjustment value; The control parameter zoom adjustment value is obtained through the zoom control parameter mapping relationship and the magnification adjustment value.

7. The method for detecting and tracking a UAV based on latitude and longitude by a PTZ camera according to claim 6, characterized in that: The focal length adjustment value is calculated using the following formula; ； ； Among them, focal_length represents the focal length adjustment value; fram_width represents the screen width of the video stream output by the gimbal camera; obj_ratio is the setting value of the ratio of the drone target in the screen; pixel_size is the pixel size; d_uav_2_o represents the target distance value between the drone target and the gimbal camera; obj_width is the width value of the drone target in the screen; m is the magnification adjustment value; focal_length_min is the minimum focal length adjustment value.

8. The method for detecting and tracking a UAV based on latitude and longitude by a PTZ camera according to claim 2, characterized in that: When autonomously tracking a drone target, adjust the control parameter pan by following the steps below: Obtain the horizontal change of the drone target obj_center_x_change through the center position of the drone target in the previous frame and the center position of the current frame; Get the horizontal field of view h_fov of the gimbal camera and the frame width frame_width of the gimbal camera output video stream at the current magnification; Calculate the horizontal offset ratio ratio_x_offset of the drone target in the horizontal direction of the video stream through obj_center_x_change / frame_width; The horizontal field of view adjustment degree x_fov is calculated by multiplying ratio_x_offset by h_fov; Get the parameter adjustment range value range_pan of the control parameter pan and the pan / tilt horizontal rotation angle adjustment range value range_horizonta langle; The resolution_pan is adjusted by calculating the control parameter pan through range_pan / range_horizontal langle; By multiplying x_fov by resolution_pan, we can calculate the control parameter adjustment change_pan for the horizontal rotation of the gimbal. If the x value of the current drone target center position is greater than the x value of the screen center position: final_pan = original_pan + change_pan; If the x value of the current drone target center position is smaller than the x value of the screen center position: final_pan = original_pan - change_pan; Among them, original_pan is the current control parameter pan; final_pan is the adjusted control parameter pan.

9. The method for detecting and tracking a UAV based on latitude and longitude by a PTZ camera according to claim 2, characterized in that: When autonomously tracking a drone target, adjust the control parameter tilt by following the steps below: Obtain the vertical angle change of the drone target obj_center_y_change through the center position of the drone target in the previous frame and the center position of the current frame; Get the vertical field of view v_fov of the gimbal camera at the current magnification and the frame height value frame_height of the video stream output by the gimbal camera; Calculate the horizontal offset ratio ratio_y_offset of the drone target in the vertical direction of the video stream through obj_center_y_change / frame_height; The vertical field of view adjustment degree y_fov is calculated by multiplying ratio_y_offset by v_fov; Get the parameter adjustment range value range_tilt of the control parameter tilt, the minimum vertical rotation angle value vertical_angle_min of the gimbal, and the maximum vertical rotation angle value veritcal_angle_max of the gimbal; The parameter adjustment resolution_tilt of the control parameter tilt is calculated by range_tilt / [abs(vertical_angle_min)+abs(vertical_angle_max)]; By multiplying y_fov by resolution_tilt, we can calculate the control parameter adjustment change_tilt of the vertical rotation of the gimbal. If the y value of the current drone target center position is greater than the y value of the screen center position: final_tilt = original_tilt - change_tilt; If the y value of the current drone target center position is smaller than the y value of the screen center position: final_tilt = original_tilt + change_tilt; Among them, original_tilt is the current control parameter tilt; final_tilt is the adjusted control parameter tilt.

10. A system for detecting and tracking drones based on longitude and latitude using a PTZ camera, characterized in that: A method for discovering and tracking a drone based on longitude and latitude using a pan-tilt camera as described in any one of claims 1 to 9.

Images