Anti-occlusion automatic tracking system for flying vehicle, flying vehicle with Anti-occlusion automatic tracking system and Anti-occlusion automatic tracking method for flying vehicle

Abstract

An automatic tracking system and method for anti-obstruction of aircraft is disclosed, applicable to aircraft. The system includes a position sensor, an inertial sensor, an image acquisition device, and a computing device. The position sensor is used to detect the real-time position information of the aircraft. The inertial sensor is used to detect the real-time inertial information of the aircraft. The image acquisition device is used to capture real-time images. The computing device is used to detect targets in the real-time images to obtain target areas, then obtain a position vector of the target based on a set of pre-stored size information of the target and an image size of the target area, and obtain target positioning information of the target based on the real-time position information, real-time inertial information, and position vector, and track the target area in the real-time images based on the target positioning information, real-time position information, and real-time inertial information.

Description

[Technical Field]

[0001] This invention relates to an automatic tracking system and method for preventing obstruction of flight vehicles. [Previous Technology]

[0002] Currently, drones equipped with automated systems are increasingly being used in various high-risk work environments to reduce traditional manpower requirements. In some applications, drones equipped with image acquisition devices can perform target detection based on machine vision and then perform further interactive operations based on accurate target detection. However, when the target detection results are unreliable, traditional tracking processes face challenges or even fail. [Summary of the Invention]

[0003] In view of the above, the present invention provides an automatic tracking system for anti-obstruction of flight vehicles, a flight vehicle having the automatic tracking system for anti-obstruction of flight vehicles, and an automatic tracking method for anti-obstruction of flight vehicles.

[0004] An automatic tracking system for anti-obstruction of an aircraft according to an embodiment of the present invention is applicable to an aircraft and includes a first position sensor, an inertial sensor, an image capturing device, and a computing device. The first position sensor is used to detect the real-time position information of the aircraft, wherein the real-time position information is based on position information of a satellite positioning system. The inertial sensor is used to detect the real-time inertial information of the aircraft. The image capturing device is used to capture a real-time image. The computing device is connected to the first position sensor, the inertial sensor, and the image capturing device, and is used to detect a target area in the real-time image, obtain a position vector of the target area based on a set of pre-stored size information of the target area and an image size of the target area, and obtain target positioning information of the target area based on the real-time position information, the real-time inertial information, and the position vector. When the real-time position information, the real-time inertial information, or the real-time image is updated, the computing device is further used to track the target area in the real-time image based on the target positioning information, the real-time position information, and the real-time inertial information.

[0005] An airborne vehicle with an anti-obstruction automatic tracking system according to an embodiment of the present invention includes a base, a first position sensor, an inertial sensor, an image capturing device, and a computing device. The first position sensor is disposed on the base and is used to detect the real-time position information of the airborne vehicle, wherein the real-time position information is based on position information of a satellite positioning system. The inertial sensor is disposed on the base and is used to detect the real-time inertial information of the airborne vehicle. The image capturing device is disposed on the base and is used to capture a real-time image. The computing device is connected to the first position sensor, the inertial sensor, and the image capturing device, and is used to perform target object detection on the real-time image to obtain a target area, then obtain a position vector of the target object according to a set of pre-stored size information of the target object and an image size of the target area, and obtain target positioning information of the target object according to the real-time position information, the real-time inertial information, and the position vector. When the real-time location information, the real-time inertial information, or the real-time image is updated, the computing device is further configured to track the target area in the real-time image based on the target positioning information, the real-time location information, and the real-time inertial information.

[0006] An automatic tracking method for anti-obstruction of an aircraft according to an embodiment of the present invention includes the following steps performed by a computing device: obtaining real-time position information of the aircraft through a first position sensor, wherein the real-time position information is based on position information of a satellite positioning system; obtaining real-time inertial information of the aircraft through an inertial sensor; obtaining a real-time image through an image capturing device; detecting a target area in the real-time image; obtaining a position vector of the target based on a set of pre-stored size information of the target and an image size of the target area; obtaining target positioning information of the target based on the real-time position information, the real-time inertial information and the position vector; and tracking the target area in the real-time image based on the target positioning information, the real-time position information and the real-time inertial information when the real-time position information, the real-time inertial information or the real-time image is updated.

[0007] Through the above structure, the anti-obstruction automatic tracking system for aircraft, the aircraft equipped with the anti-obstruction automatic tracking system, and the anti-obstruction automatic tracking method for aircraft disclosed in this case can obtain target positioning information in the first stage based on the real-time position information, real-time inertial information, and position vector between the aircraft and the target object; and in the second stage, it can track the target area in the real-time image based on the target positioning information, real-time position information, and real-time inertial information. This avoids the problem in this case where the aircraft cannot continuously track the target object when interacting with it due to changes in the captured image or obstruction of the target object, thus realizing an anti-obstruction automatic tracking system and method suitable for aircraft.

[0008] The above description of the disclosure and the following description of the embodiments are intended to demonstrate and explain the spirit and principles of the present invention, and to provide a further explanation of the scope of the patent application of the present invention.

Implementation Method

[0010] The detailed features and advantages of the present invention are described below in the embodiments. The content is sufficient to enable anyone skilled in the art to understand the technical content of the present invention and implement it accordingly. Based on the disclosure, patent claims, and drawings in this specification, anyone skilled in the art can easily understand the relevant objectives and advantages of the present invention. The following embodiments further illustrate the viewpoints of the present invention, but are not intended to limit the scope of the present invention in any way.

[0011] Please refer to Figure 1, which is a functional block diagram illustrating an aircraft and its anti-obstruction automatic tracking system according to an embodiment of the present invention. As shown in Figure 1, the aircraft FV may include an anti-obstruction automatic tracking system 1 and a base 2. The anti-obstruction automatic tracking system 1 may include a position sensor 12, an inertial sensor 13, an image capturing device 14, and a computing device 15. The position sensor 12 may be disposed on the base 2 for detecting the real-time position information of the aircraft FV, wherein the real-time position information is based on position information from a Global Navigation Satellite System (GNSS). The inertial sensor 13 may be disposed on the base 2 for detecting the real-time inertial information of the aircraft FV. The image capturing device 14 may be disposed on the base 2 for capturing a real-time image. The computing device 15 is connected to the position sensor 12, the inertial sensor 13, and the image capturing device 14. It is used to detect a target area in the real-time image, obtain a position vector of the target area based on a set of pre-stored size information of the target area, and obtain target positioning information of the target area based on the real-time position information, the real-time inertial information, and the position vector. When the real-time position information, the real-time inertial information, or the real-time image is updated, the computing device 15 is further used to track the target area in the real-time image based on the target positioning information, the real-time position information, and the real-time inertial information.

[0012] In this example, the flight vehicle FV can be an aircraft, such as a drone with automatic or semi-automatic flight control functions. The base 2 on which the position sensor 12, inertial sensor 13, and image capturing device 14 are mounted can include the body (fuselage) and / or extensions (extend arms) of the flight vehicle FV. The position sensor 12 can generate real-time position information of the flight vehicle FV based on a satellite positioning system (GNSS). Specifically, the real-time position information can include the three-dimensional coordinate information of the flight vehicle FV in the world. The inertial sensor 13 (inertial measurement unit, IMU) can be used to measure the attitude angles (angular rates) and accelerations of the flight vehicle FV along three axes, that is, information on the acceleration, rotation angle, and tilt angle of the flight vehicle FV. For example, the inertial sensor 13 can be equipped with a three-axis gyroscope and three-direction accelerometers to measure the angular velocity and acceleration of the flight vehicle FV in three-dimensional space, and thereby calculate the attitude of the flight vehicle FV. In addition, to improve measurement accuracy, multiple inertial sensors 13 can be equipped for each axis of the flight vehicle FV.

[0013] The image capturing device 14 can be used to capture images of a specific axis of the flight vehicle FV to obtain real-time images. Specifically, the inertial sensor 13 can be used to measure the attitude angle of the flight vehicle FV at a specific time point, and this attitude angle can be used to determine the shooting direction of the image capturing device 14 at that specific time point. The computing device 15 can be disposed on the base 2 and electrically connected to the position sensor 12, the inertial sensor 13 and the image capturing device 14, or it can be disposed at a remote end and communicatively connected to the position sensor 12, the inertial sensor 13 and the image capturing device 14. The computing device 15 may include one or more processing / control units with data receiving, recording, computing, storage and output functions, such as a microcontroller, a central processing unit, a graphics processor, a programmable logic controller or any combination thereof.

[0014] Please refer to Figure 2 in conjunction with Figure 1. Figure 2 is a flowchart illustrating an automatic tracking method for anti-obstruction of an aircraft according to an embodiment of the present invention. As shown in Figure 2, the automatic tracking method for anti-obstruction of an aircraft includes the following steps executed by a computing device: Step S1: Obtaining real-time position information of an aircraft through a position sensor; Step S2: Obtaining real-time inertial information of the aircraft through an inertial sensor; Step S3: Obtaining a real-time image through an image capturing device; Step S4: Detecting a target object in the real-time image to obtain a target area; Step S5: Obtaining a position vector of the target object based on a set of pre-stored size information of the target object and an image size of the target area; Step S6: Obtaining target positioning information of the target object based on the real-time position information, the real-time inertial information, and the position vector; and Step S7: When the real-time position information, the real-time inertial information, or the real-time image is updated, tracking the target area in the real-time image based on the target positioning information, the real-time position information, and the real-time inertial information.

[0015] In step S1, the computing device 15 can obtain the real-time position information of the UAV through the position sensor 11. The real-time position information can be based on the position information of a satellite positioning system (GNSS). Based on practical accuracy requirements, different types of position sensors can be selected or multiple position sensors can be used for auxiliary positioning. Please refer to FIG3, which is a schematic diagram illustrating the precise positioning of an air vehicle according to another embodiment of the present invention. As shown in FIG3, the air vehicle FV in this example can include the devices and components shown in FIG1, wherein the position sensor 12 can be regarded as the first position sensor and can be operated in conjunction with a second position sensor 16. The first position sensor of the air vehicle FV and the second position sensor 16 set in the environment can generate accurate real-time position information based on real-time kinematic (RTK) technology, thereby improving the positioning accuracy, which can reach the centimeter (cm) level. In one embodiment, the second position sensor 16 can be regarded as one of the devices included in the anti-obstruction automatic tracking system. In addition, the computing device 15 can set the takeoff position R of the flight vehicle FV to (0,0,0) as the origin coordinate for subsequent calculations.

[0016] In addition to the aforementioned Real-Time Kinematic (RTK) positioning technology for precise positioning, other positioning alternatives may also be employed. For example, satellite-based positioning systems such as the Global Positioning System (GPS), Galileo, and BeiDou Navigation Satellite System; image-based positioning systems such as visual odometry, optical flow, event cameras, ground control points, and simultaneous localization and mapping (SLAM); and sensor-based positioning systems such as LiDAR, radar, and inertial navigation systems (INS) can all be used as auxiliary positioning technologies to provide accurate real-time position information for the flight vehicle (FV). This application does not limit the aforementioned positioning methods.

[0017] In step S2, the computing device 15 can obtain real-time inertial information, including the attitude angles (angular rates) and accelerations of the three axes of the flight vehicle FV, through the inertial sensor 12 installed on the base 2 of the flight vehicle FV. In step S3, the computing device 15 can obtain real-time images through the image capturing device 14 installed on the base 2 of the flight vehicle FV. The "real-time information" can represent the real-time measurement information generated by the continuous operation of the sensors and the transmission of data to the computing device. That is, in steps S1 to S3, the computing device 15 can continuously obtain the position information measured by the position sensor 12, the inertial information measured by the inertial sensor 13, and the images obtained by the image capturing device 14. The order of steps S1 to S3 can be arbitrarily interchanged or executed simultaneously.

[0018] In steps S4 and S5, the computing device 15 can perform target detection on the real-time image to obtain a target region of the selected target, and obtain a position vector of the target based on a set of pre-stored size information of the target and the image size of the target region. Please refer to Figures 4 and 5, which are schematic diagrams illustrating a flight vehicle performing target detection and obtaining the position vector of the target according to an embodiment of the present invention. As shown in Figures 4 and 5, when the flight vehicle FV faces the target T, the image capturing device can obtain a real-time image containing the image of the target and transmit the real-time image to the computing device. The computing device can select the target in the real-time image to generate a target region TA, wherein the boundary of the target region TA is a bounding box. For example, the computing device can train a target recognition model using multiple pre-stored images of the target T, and perform target detection on the real-time image based on the target recognition model to obtain the target region. The target recognition model may be a convolutional neural network used to perform image segmentation, such as a customized U-Net generative adversarial network (U-Net GAN), but this case is not limited to this.

[0019] Next, the computing device can obtain the distance between the flight vehicle FV and the target object T based on a set of pre-stored size information (e.g., length and width) of the target object and the image size of the target area (e.g., the number of pixels in the length and width directions), and obtain the position vector V0 of the target object T in the reference coordinate system of the image capturing device. For example, when the computing device selects the target area TA, it can lock the midpoint P of the target area TA and obtain the length L1 and width W1 of the target area TA in the real-time image. The computing device can further determine the current distance between the flight vehicle FV and the target object T based on the pre-stored length and width of the target object. Specifically, the distance can be determined based on the ratio between the image size and the actual size of the target object. For example, the computing device can obtain the distance between the flight vehicle FV and the target object T based on the focal length of the image capturing device, the pre-stored size information, and the image size. Please refer to the following relationship (1), where d is the distance between the flying vehicle FV and the target object T, f is the focal length of the image capturing device, M is the actual size of the target object (e.g., length or width), and m is the size of the target object in the image (e.g., length L1 or width W1).

[0020] Relation (1):

[0021] After obtaining the distance between the aircraft FV and the target object T through the image, the computing device can calculate the position vector V0 of the target object T relative to the reference coordinate system of the image capturing device. Then, in step S6, the computing device can obtain target positioning information of the target object T based on the real-time position information, real-time inertial information, and position vector V0. For example, the real-time position information can correspond to the coordinate position of the aircraft FV in space, the real-time inertial information can correspond to the shooting direction of the image capturing device, and the position vector V0 can correspond to the vector of the target object T relative to the reference coordinate system of the image capturing device. Therefore, by adding the above three geometric information in vector form, the coordinate position of the target object T in space (target positioning information) can be obtained. That is, the computing device can use the coordinate position of the aircraft FV as a reference to locate the target object T through the captured image. The calculation method for this positioning information can be based on coordinate transformation operations between vectors and matrices (e.g., rotation matrices), which will not be described in detail here.

[0022] Further, the computing device can store vector information about the setting position of the image capturing device relative to the first position sensor, and obtain the target positioning information of the target object T based on the vector information, the real-time position information, the real-time inertial information, and the position vector V0. Please refer to FIG6, which is a schematic diagram of a flight vehicle tracking and locking a target object for spraying operation according to an embodiment of the present invention. As shown in FIG6, in this example, the first position sensor can be set on the body of the flight vehicle FV, the image capturing device 14 can be set on an extension, the vector V1 can correspond to the relative position between the image capturing device 14 and the first position sensor, and the vector V2 can correspond to the relative position between the image capturing device 14 and the target object. In this way, the computing device can obtain the position of the image capturing device based on the position of the flight vehicle FV, and obtain the target positioning information of the target object by identifying the target area TA in the image Img. Thus, the operation of obtaining the target positioning information of the target object can be called a pose back propagation operation, which can obtain the absolute position coordinates of the target object relative to the ground.

[0023] In step S7, when the real-time position information, the real-time inertial information, or the real-time image is updated—that is, when the flight vehicle FV undergoes displacement, attitude shift, or the image changes due to external factors—the computing device can track the target area in the real-time image based on the target positioning information, the real-time position information, and the real-time inertial information. For example, when the target object is obstructed by a foreign object, preventing the image capturing device from obtaining a complete image of the target object and causing the target object detection to fail, the computing device can continuously track the target area TA in the image based on the previously obtained target positioning information of the target object and the position and inertial information of the flight vehicle FV. Thus, the operation of continuously tracking the target area TA in the image based on the previously obtained target positioning information of the target object and the position and inertial information of the flight vehicle FV can be called a pose forward propagation operation, which can obtain the relative position coordinates of the target object relative to the flight vehicle FV based on the absolute position coordinates of the target object relative to the ground. In this way, the problem that the flight-mounted FV in this case could not continuously track the target when interacting with the target due to changes in the captured image or the target being obscured can be avoided.

[0024] In one embodiment, the flight vehicle anti-obstruction automatic tracking system may further include an end effector 17, disposed on an extension of the flight vehicle FV and connected to the computing device. The computing device may further be used to store vector information of the extension relative to the first position sensor, and control the end effector to perform a specified operation on the target object based on the vector information, the target positioning information, the real-time position information, and the real-time inertial information. As shown in FIG6, in this example, the first position sensor may be disposed on the body of the flight vehicle FV, the end effector 17 may be disposed on an extension, vector V3 may correspond to the relative position between the end effector 17 and the first position sensor, and vector V4 may correspond to the relative position between the end effector 17 and the target object. The end effector 17 may be a spraying device, a laser device, or a robotic arm, etc., and is not limited thereto in this embodiment. In this example, the end effector 17 is a spraying device, and the end effector 17 may have at least one rotating axis. The computing device can control the end effector 17 to rotate along an operating trajectory of the target area to perform the specified operation on the target object. That is, after obtaining the target positioning information of the target object, the computing device can calculate the required spraying angle of the spraying device based on the vector information, the target positioning information, the real-time position information, and the real-time inertial information to perform the spraying operation on the target object. The calculation method of the rotation angle of the end effector 17 can be referred to inverse kinematics of robot manipulators, and will not be elaborated here.

[0025] Furthermore, since the target positioning information of the target object is obtained in step S6, even if the position or attitude of the flight vehicle FV shifts or the target object in the image is obscured, the computing device can still continuously track the target area TA in the image (step S7). Accordingly, the computing device can further control the spraying device (end effector 17) to continuously track the target area TA and perform spraying operations. Please refer to Figure 7, which is a statistical chart of the tracking error of the flight vehicle anti-obstruction automatic tracking system and method according to an embodiment of the present invention. As shown in Figure 7, according to the aforementioned embodiment of the flight vehicle anti-obstruction automatic tracking system and method of this case, it has been experimentally verified that the error range between the aiming point of the end effector in the target area and the actual center point of the target object is within the centimeter range, and most of them fall within the range of about 2 centimeters. For detailed experimental data, please refer to the following table (A).

[0026] Table (A): X error (cm) Y error (cm) Distance (cm) average value 0.47 -0.27 2.227 Maximum value 7.79 6.71 8.572 Standard deviation 1.27 2.17 1.289

[0027] As shown in Figure 7 and Table (A), the automatic tracking system and method for anti-obstruction of aircraft in this invention can reduce the average tracking and aiming offset error caused by translational or rotational motion of the aircraft to 2.27 cm. In the field of UAV control technology, this offset error already meets the 10 cm error standard required by Taiwan Power Company. Compared with algorithms that rely solely on vision, the offset error is prone to accumulate and gradually increase during the process. The system and method of this invention are less susceptible to environmental interference and are more robust. The system and method of this invention ensure reliable tracking in critical stages (such as when the visual reference is lost due to water spraying from the spraying device), and can still track the target position with centimeter-level accuracy even under significant visual interference.

[0028] Please refer to Figure 8, which is a functional block diagram of an aircraft and its anti-obstruction automatic tracking system according to another embodiment of the present invention. Compared with the embodiment in Figure 1, the anti-obstruction automatic tracking system 1' included in the aircraft FV' in this example may further include a remote control device 16. The remote control device 16 is connected to the computing device 15, and when the remote control device 16 determines that the target area has an error, it can control the computing device 15 to re-detect the target object. For example, the remote control device 16 can determine whether the tracking has an error based on the center point of the target area, and re-detect the target object when the tracking has an error. The above-mentioned operation and judgment of the remote control device 16 can be implemented based on manual operation or automatic control. Specifically, the remote control device 16 may include one or more processing / control units with data receiving, recording, computing, storage and output functions, such as a microcontroller, a central processing unit, a graphics processor, a programmable logic controller or any combination thereof.

[0029] Through the above structure, the anti-obstruction automatic tracking system for aircraft, the aircraft with the anti-obstruction automatic tracking system, and the anti-obstruction automatic tracking method for aircraft disclosed in this case can obtain target positioning information in the first stage based on the real-time position information, real-time inertial information, and position vector between the aircraft and the target object; and in the second stage, it can track the target area in the real-time image based on the target positioning information, real-time position information, and real-time inertial information. In this way, the problem that the aircraft of this case cannot continuously track the target object when interacting with the target object due to changes in the captured image or the target object being obstructed can be avoided, realizing an anti-obstruction automatic tracking system and method suitable for aircraft. In addition, through the positioning method of real-time dynamic positioning technology, the anti-obstruction automatic tracking system for aircraft, the aircraft with the anti-obstruction automatic tracking system, and the anti-obstruction automatic tracking method for aircraft disclosed in this case can still track the target position with centimeter-level accuracy in critical stages (such as when the visual reference is lost due to water spraying by the spraying device), even under significant visual interference.

[0030] Although the present invention has been disclosed above with reference to the foregoing embodiments, it is not intended to limit the present invention. Any modifications and refinements made without departing from the spirit and scope of the present invention are within the scope of patent protection of the present invention. For the scope of protection defined by the present invention, please refer to the appended claims. [Simplified Explanation of the Diagram]

[0009] Figure 1 is a functional block diagram of an aircraft and its anti-obstruction automatic tracking system according to an embodiment of the present invention. Figure 2 is a flowchart of an anti-obstruction automatic tracking method for an aircraft according to an embodiment of the present invention. Figure 3 is a schematic diagram of precise positioning of an aircraft according to another embodiment of the present invention. Figures 4 and 5 are schematic diagrams of an aircraft detecting a target and obtaining the position vector of the target object according to an embodiment of the present invention. Figure 6 is a schematic diagram of an aircraft tracking a target area and locking onto the target object for spraying operation according to an embodiment of the present invention. Figure 7 is a statistical chart of the tracking error of the anti-obstruction automatic tracking system and method for an aircraft according to an embodiment of the present invention. Figure 8 is a functional block diagram of an aircraft and its anti-obstruction automatic tracking system according to yet another embodiment of the present invention.

Claims

1. An automatic tracking system for anti-obstruction of an aircraft, applicable to an aircraft, and comprising: a first position sensor for detecting real-time position information of the aircraft, wherein the real-time position information is based on position information from a satellite positioning system; an inertial sensor for detecting real-time inertial information of the aircraft; an image capturing device for capturing a real-time image; a computing device connected to the first position sensor, the inertial sensor, and the image capturing device, for performing target detection on the real-time image to obtain a target area, then obtaining a position vector of the target based on a set of pre-stored size information of the target and an image size of the target area, and obtaining target positioning information of the target based on the real-time position information, the real-time inertial information, and the position vector; and an end effector connected to the computing device, wherein... When the real-time location information, the real-time inertial information, or the real-time image is updated, the computing device is further used to track the target area in the real-time image based on the target positioning information, the real-time location information, and the real-time inertial information. The computing device is further used to store vector information of an extension of the flight vehicle relative to the first position sensor, and to control the end effector to perform a specified operation on the target object based on the vector information, the target positioning information, the real-time location information, and the real-time inertial information.

2. The automatic tracking system for anti-obstruction of aircraft as described in claim 1 further includes a second position sensor, wherein, The real-time location information is obtained by the first location sensor and the second location sensor based on real-time dynamic positioning technology.

3. The automatic tracking system for anti-obstruction of an aircraft as described in claim 1, wherein the real-time inertial information includes information on the acceleration, rotation angle and tilt angle of the aircraft.

4. The automatic tracking system for anti-obstruction of an aircraft as claimed in claim 1, wherein the computing device is used to obtain the position vector of the target object based on the focal length of the image capturing device, the set of pre-stored size information, the image size, and the reference coordinate system of the image capturing device.

5. The automatic tracking system for anti-obstruction of flight vehicles as claimed in claim 1, wherein the computing device is used to store vector information of the setting position of the image capturing device relative to the first position sensor, and to obtain the target positioning information of the target object based on the vector information, the real-time position information, the real-time inertial information and the position vector.

6. The automatic tracking system for anti-obstruction of aircraft as claimed in claim 1, wherein the end effector is a spraying device.

7. The automatic tracking system for anti-obstruction of an aircraft as claimed in claim 1, wherein the end effector has at least one pivot, and the computing device is used to control the end effector to rotate along an operating trajectory of the target area to perform the specified operation on the target object.

8. The automatic tracking system for anti-obstruction of aircraft as described in claim 1 further includes a remote control device connected to the computing device, wherein, When the remote control device determines that the target area has an error, it controls the computing device to re-detect the target object.

9. The automatic tracking system for anti-obstruction of an aircraft as claimed in claim 1, wherein the computing device is used to train a target recognition model with multiple pre-stored images of the target, and to detect the target in the real-time image according to the target recognition model to obtain the target area.

10. An aircraft with an anti-obstruction automatic tracking system, comprising: a base; a first position sensor disposed on the base for detecting real-time position information of the aircraft, wherein the real-time position information is based on position information from a satellite positioning system; an inertial sensor disposed on the base for detecting real-time inertial information of the aircraft; an image capturing device disposed on the base for capturing a real-time image; a computing device connected to the first position sensor, the inertial sensor, and the image capturing device, for detecting a target area in the real-time image, obtaining a position vector of the target area based on a set of pre-stored size information of the target area and an image size of the target area, and obtaining target positioning information of the target area based on the real-time position information, the real-time inertial information, and the position vector; and an extension and an end effector, the end effector being disposed on the extension and connected to the computing device, wherein... When the real-time location information, the real-time inertial information, or the real-time image is updated, the computing device is further used to track the target area in the real-time image based on the target positioning information, the real-time location information, and the real-time inertial information. The computing device is further used to store a vector information of the extension of the flight vehicle relative to the first position sensor, and to control the end effector to perform a specified operation on the target object based on the vector information, the target positioning information, the real-time location information, and the real-time inertial information.

11. The flight vehicle with an anti-obstruction automatic tracking system as described in claim 10 further includes a second position sensor, wherein, The real-time location information is obtained by the first location sensor and the second location sensor based on real-time dynamic positioning technology.

12. The flight vehicle with an anti-obstruction automatic tracking system as described in claim 10, wherein the real-time inertial information includes information on the acceleration, rotation angle and tilt angle of the flight vehicle.

13. The flight vehicle with an anti-obstruction automatic tracking system as claimed in claim 10, wherein the computing device is used to obtain the position vector of the target object based on the focal length of the image capturing device, the set of pre-stored size information and the image size.

14. The flight vehicle with an anti-obstruction automatic tracking system as described in claim 10, wherein the computing device is configured to store a vector information of the setting position of the image capturing device relative to the first position sensor, and to obtain the target positioning information of the target object based on the vector information, the real-time position information, the real-time inertial information and the position vector.

15. The flight vehicle with an anti-obstruction automatic tracking system as described in claim 10, wherein the end effector is a spraying device.

16. The flight vehicle with an anti-obstruction automatic tracking system as claimed in claim 10, wherein the end effector has at least one pivot, and the computing device is used to control the end effector to rotate along an operating trajectory of the target area to perform the specified operation on the target object.

17. The flight vehicle with an anti-obstruction automatic tracking system as described in claim 10 further includes a remote control device connected to the computing device, wherein, When the remote control device determines that the target area has an error, it controls the computing device to re-detect the target object.

18. The flight vehicle with an anti-obstruction automatic tracking system as claimed in claim 10, wherein the computing device is used to train a target recognition model with multiple pre-stored images of the target, and to perform target detection on the real-time image according to the target recognition model to obtain the target area.

19. An automatic tracking method for anti-obstruction of an aircraft, comprising the following steps performed by a computing device: acquiring real-time position information of an aircraft via a first position sensor, wherein the real-time position information is based on position information from a satellite positioning system; acquiring real-time inertial information of the aircraft via an inertial sensor; acquiring a real-time image via an image capturing device; performing target detection on the real-time image to obtain a target region; obtaining a position vector of the target based on a set of pre-stored size information of the target and an image size of the target region; obtaining target positioning information of the target based on the real-time position information, the real-time inertial information, and the position vector; and tracking the target region in the real-time image based on the target positioning information, the real-time position information, and the real-time inertial information when the real-time position information, the real-time inertial information, or the real-time image is updated. Obtain vector information of an extension of the flight vehicle, wherein an end effector is disposed on the extension; and control the end effector to perform a specified operation on the target object based on the vector information, the target positioning information, the real-time position information and the real-time inertial information.

20. The automatic tracking method for anti-obstruction of an aircraft as described in claim 19, wherein obtaining the real-time position information of the aircraft comprises: obtaining the real-time position information based on real-time dynamic positioning technology through the first position sensor and a second position sensor.

21. The automatic tracking method for anti-obstruction of an aircraft as described in claim 19, wherein the real-time inertial information includes information on the acceleration, rotation angle and tilt angle of the aircraft.

22. The automatic tracking method for anti-obstruction of an aircraft as described in claim 19, wherein obtaining the position vector of the target object comprises: obtaining the position vector of the target object based on the focal length of the image capturing device, the set of pre-stored size information, the image size, and the reference coordinate system of the image capturing device.

23. The automatic tracking method for anti-obstruction of an aircraft as described in claim 19, wherein obtaining the target positioning information of the target object comprises: obtaining a vector information of the setting position of the image capturing device relative to the first position sensor; and obtaining the target positioning information of the target object based on the vector information, the real-time position information, the real-time inertial information and the position vector.

24. The automatic tracking method for anti-obstruction of an aircraft as described in claim 19, wherein the end effector is a spraying device.

25. The automatic tracking method for anti-obstruction of an aircraft as claimed in claim 19, wherein the end effector has at least one pivot, and controlling the end effector to perform the specified operation on the target object comprises: controlling the end effector to rotate along an operating trajectory of the target area to perform the specified operation on the target object.

26. The automatic tracking method for anti-obstruction of flight vehicles as described in claim 19 further includes, when performed by a remote control device: when it is determined that the target area has an error, controlling the computing device to re-detect the target object.

27. The automatic tracking method for anti-obstruction of a flight vehicle as described in claim 19, wherein detecting a target area in the real-time image comprises: training a target recognition model with multiple pre-stored images of the target, and detecting a target area in the real-time image based on the target recognition model to obtain the target area.

Images