Photoelectric guidance method and system for air-to-air capture unmanned aerial vehicle

Abstract

The application discloses an air-to-air capturing unmanned aerial vehicle photoelectric guidance method and system, which utilizes target angle and position information measured by a third-party radar to guide the unmanned aerial vehicle into the operation range of photoelectric equipment installed thereon, and completes photoelectric guidance shift. Subsequently, the photoelectric equipment collects target images in real time, obtains the miss distance of the target through image small target identification and full-screen detection technology. Based on the miss distance, the target is tracked in real time, and the angle information of the target relative to the unmanned aerial vehicle is calculated to guide the unmanned aerial vehicle to fly close to the target. When the relative distance between the unmanned aerial vehicle and the target enters the operation range of the capturing equipment, the system adjusts the posture of the capturing equipment in real time by using the pitch frame angle information of the photoelectric equipment. Finally, when the capturing condition is met, the capturing equipment captures the target, and accurate guidance and efficient capturing of the aerial target are realized.

Description

Technical Field

[0001] This invention belongs to the field of unmanned aerial vehicle (UAV) technology and relates to an optoelectronic guidance method and system for air-to-air capture of UAVs. Background Technology

[0002] With the rapid development and widespread application of drone technology, low, slow, and small unmanned aerial vehicles (LSS UAVs) have shown great potential in both civilian and military fields. However, the widespread use of these drones has also brought about numerous security, regulatory, and privacy issues, especially in scenarios such as illegal intrusion, terrorist attacks, and intelligence gathering. Therefore, developing efficient and precise drone capture systems has become a current research hotspot.

[0003] In existing drone capture technologies, ground-to-air and ground-to-ground optoelectronic devices are mainly used for target identification, reconnaissance, and measurement. These devices perform well when dealing with static or low-speed dynamic targets, but their guidance accuracy and real-time performance often fall short when facing high-speed, highly maneuverable aerial targets. Traditional optoelectronic guidance technology faces numerous challenges, especially for air-to-air drone capture missions.

[0004] First, as a ground-based device, radar suffers from a low update rate when guiding highly maneuverable UAVs. Radar guidance accuracy is generally greater than 3°, which is clearly insufficient for capture missions requiring precise guidance. Furthermore, radar systems are susceptible to factors such as terrain and weather, further reducing their guidance reliability.

[0005] Secondly, while drones equipped with video sensors can track targets using image recognition technology, the transmission of images and data relies on wireless data links. This transmission method suffers from significant latency, typically exceeding 0.5 seconds. For drone targets flying at speeds exceeding 20 m / s, this latency can cause target position deviations of over 10 meters, severely impacting the accuracy and success rate of capture.

[0006] Furthermore, the capture mechanisms carried by drones are mostly fixed net capture mechanisms. These mechanisms are fixedly connected to the drone and cover the target location by using the net's launch divergence angle. However, due to the limited coverage area of ​​the net and the influence of various factors such as target positioning accuracy, aiming accuracy, and target movement, fixed net capture mechanisms often fail to achieve the expected capture effect in practical applications.

[0007] Therefore, existing UAV capture technologies have significant shortcomings in terms of guidance accuracy, transmission links, real-time control, and capture launch accuracy, which limit the application scope and combat effectiveness of UAV capture systems. Summary of the Invention

[0008] The purpose of this invention is to solve the technical problem of low target capture accuracy under the combined influence of factors such as target positioning accuracy, aiming accuracy, and target movement in the prior art, and to provide an optoelectronic guidance method and system for air-to-air capture of unmanned aerial vehicles.

[0009] To achieve the above objectives, the present invention employs the following technical solution: The first aspect of this invention provides an electro-optical guidance method for air-to-air capture of unmanned aerial vehicles, comprising the following steps: Based on the target's angle and position measured by a third-party radar, the drone is guided into the operating range of the optoelectronic equipment to complete the optoelectronic guidance handover; the optoelectronic equipment is installed on the drone. The target image is acquired in real time using optoelectronic equipment; small target recognition and full-screen detection are performed on the acquired target image to obtain the target's miss distance; Based on the target's miss distance, the target is tracked in real time; Based on the target's miss distance, the angle information of the target relative to the UAV is obtained; based on the angle information of the target relative to the UAV, the UAV is guided to fly closer to the target. When the distance between the drone and the target enters the operating range of the capture equipment, the attitude of the capture equipment is adjusted in real time based on the pitch frame angle information of the optoelectronic equipment. When the capture conditions are met, the capture equipment captures the target.

[0010] Furthermore, the method of guiding the UAV into the operating range of the optoelectronic equipment based on the target's angle and position measured by a third-party radar, thus completing the optoelectronic guidance handover, specifically involves: Based on the target's angle and position measured by a third-party radar, the drone's flight attitude and speed are adjusted to approach the target until the maximum angle between the drone and the target is less than or equal to the field of view of the optical sensor in the optoelectronic device. Switch the UAV's flight guidance mode from radar guidance to electro-optical guidance to complete the electro-optical guidance handover.

[0011] Furthermore, the process of performing small target recognition and full-screen detection on the acquired target image to obtain the target's miss distance is specifically as follows: The acquired target image is sliced ​​to obtain multiple slices; Small target recognition is performed on each slice to obtain the coordinates of the target corresponding to the slice; The NMS strategy is used to map the coordinates of the target corresponding to the slice onto the acquired target image to obtain the target's miss distance.

[0012] Furthermore, the step of performing small target recognition on each slice to obtain the coordinates of the target corresponding to the slice is specifically as follows: Each slice is processed using the inter-frame difference method to generate a frame difference temporal feature map; Each slice image is processed using a row and column morphological decoupling method to generate a morphological space feature map; The frame difference temporal feature map and the morphological space feature map are fused according to the principle of consistency of positive detection position of feature map to obtain a spatiotemporal feature fusion map; The spatiotemporal feature fusion map is upsampled and downsampled to obtain the coordinates of the target corresponding to the sliced ​​map.

[0013] Furthermore, the real-time tracking of the target based on the target's miss distance specifically includes: Based on the target's miss distance, the optoelectronic device performs image stabilization tracking of the target to ensure that the target is centered in the video tracker's view.

[0014] Furthermore, based on the target's miss distance, the angle information of the target relative to the UAV is obtained; based on the angle information of the target relative to the UAV, the UAV is guided to fly closer to the target, specifically as follows: Based on the target's miss distance and the frame angle information of the optoelectronic equipment, the angle information of the target relative to the UAV is obtained.

[0015] Furthermore, when the distance between the drone and the target enters the operating range of the capture equipment, the attitude of the capture equipment is adjusted in real time based on the pitch frame angle information of the optoelectronic device, specifically as follows: When the distance between the drone and the target enters the operating range of the capture equipment, the capture equipment will perform pitch follow-up based on the angle information of the pitch frame of the optoelectronic device to ensure that the launch center line of the capture equipment is parallel to the optical axis of the optoelectronic device.

[0016] Furthermore, the capture device has a pitch and displacement function.

[0017] Furthermore, when the capture conditions are met, the capture device captures the target, specifically as follows: When the capture conditions are met, the capture equipment captures the target; When the capture conditions are not met, the capture equipment continues to track the target and adjusts the attitude of the capture equipment in real time based on the pitch frame angle information of the photoelectric equipment until the capture conditions are met.

[0018] A second aspect of the present invention provides an optoelectronic guidance system for air-to-air capture of unmanned aerial vehicles, comprising: The optoelectronic guidance handover module is used to guide the UAV into the operating range of the optoelectronic equipment based on the target's angle and position measured by a third-party radar, thus completing the optoelectronic guidance handover; the optoelectronic equipment is installed on the UAV. The target recognition module is used to acquire target images in real time using photoelectric equipment; it performs small target recognition and full-screen detection on the acquired target images to obtain the target's miss distance; The target tracking module is used to track the target in real time based on the target's miss distance. The flight guidance module is used to obtain the target's angle information relative to the UAV based on the target's miss distance; and to guide the UAV to approach the target based on the target's angle information. The capture guidance module is used to adjust the attitude of the capture equipment in real time based on the pitch frame angle information of the optoelectronic device when the distance between the UAV and the target enters the working range of the capture equipment. The capture module is used to capture the target when the capture conditions are met.

[0019] Compared with the prior art, the present invention has the following beneficial effects: This invention discloses an optoelectronic guidance method for air-to-air capture of unmanned aerial vehicles (UAVs). Guided by an initial angle from a third-party radar, the UAV can quickly enter the operating range of the optoelectronic device. After the optoelectronic device takes over flight guidance control, it can automatically calculate the approach angle based on target image recognition and tracking, achieving precise guidance. By performing small target recognition and full-screen detection on the acquired target images, it can effectively identify small targets occupying only a few or tens of pixels at long distances. The full-screen detection technology improves the detection accuracy of small targets through image slicing and NMS strategies. It can convert visual tracking results into angle information to guide the UAV's flight, achieving dynamic and automatic flight guidance. The capture mechanism has a pitch displacement function, capable of following the pitch encoder value of the optoelectronic pod, improving the accuracy of capture and launch. The guidance accuracy reaches the pixel level, significantly improving compared to traditional radar guidance accuracy, effectively increasing the success rate of capturing dynamic targets. The entire process requires no intervention from ground control equipment, avoiding problems such as low update rate, large latency, and poor real-time control caused by excessively long data links. Attached Figure Description

[0020] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 This is a cross-sectional view of the photoelectric pod according to an embodiment of the present invention; Figure 2 This is a perspective view of the photoelectric pod according to an embodiment of the present invention; Figure 3This is a flowchart of the photoelectric guidance method for capturing drones according to an embodiment of the present invention; Figure 4 This is a schematic diagram illustrating the handover conditions for photoelectric guidance in an embodiment of the present invention; Figure 5 This is a block diagram of the photoelectric guidance method for air-to-air capture of unmanned aerial vehicles according to the present invention; Figure 6 This is a block diagram of the photoelectric guidance system for air-to-air capture drones according to the present invention.

[0022] The components are as follows: 1-Base assembly; 101-Mounting base; 102-External interface; 103-Base cover; 1031-Desiccant compartment; 104-Integrated control board; 105-Azimuth control board; 106-Secondary point source board; 2-Azimuth assembly; 201-Azimuth axis; 202-Azimuth bearing; 203-Azimuth motor; 204-Azimuth encoder; 205-Azimuth frame; 3-Pitch assembly; 301-Pitch frame; 302-Pitch motor; 303-Pitch motor shaft; 304-First pitch bearing; 305-Pitch encoder; 306-Pitch encoder shaft; 307-Second pitch bearing; 4-Photoelectric load; 401-Visible light camera module; 402-Infrared camera; 403-Pitch control board; 404-Photoelectric load mounting bracket; 405-Video tracker. Detailed Implementation

[0023] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. The components of the embodiments of the present invention described and marked in the accompanying drawings can generally be arranged and designed in various different configurations.

[0024] Therefore, the following detailed description of the embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the invention without inventive effort are within the scope of protection of the invention.

[0025] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0026] In the description of this invention, it should be understood that the terms "comprising" and "including" indicate the presence of the described features, integrals, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.

[0027] It should also be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used in this specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.

[0028] It should also be further understood that the term "and / or" as used in this specification and the appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes such combinations. For example, A and / or B can represent three cases: A alone, A and B simultaneously, and B alone. Additionally, the character " / " in this invention generally indicates that the preceding and following objects have an "or" relationship.

[0029] It should be understood that although terms such as first, second, third, etc., may be used in the embodiments of the present invention to describe the preset range, these preset ranges should not be limited to these terms. These terms are only used to distinguish the preset ranges from one another. For example, without departing from the scope of the embodiments of the present invention, the first preset range may also be referred to as the second preset range, and similarly, the second preset range may also be referred to as the first preset range.

[0030] Depending on the context, the word "if" as used here can be interpreted as "when," "when," "in response to determination," or "in response to detection." Similarly, depending on the context, the phrase "if determination" or "if detection (of the stated condition or event)" can be interpreted as "when determination," "in response to determination," "when detection (of the stated condition or event)," or "in response to detection (of the stated condition or event)."

[0031] The accompanying drawings illustrate various structural schematic diagrams according to embodiments disclosed in this invention. These drawings are not to scale, and some details have been enlarged for clarity, and some details may have been omitted. The shapes of the various regions and layers shown in the drawings, as well as their relative sizes and positional relationships, are merely exemplary and may deviate from reality due to manufacturing tolerances or technical limitations. Furthermore, those skilled in the art can design regions / layers with different shapes, sizes, and relative positions as needed.

[0032] The present invention will now be described in further detail with reference to the accompanying drawings: See Figure 1 and Figure 2 One embodiment of the present invention provides an optoelectronic device (optoelectronic pod), including a base assembly 1, an orientation assembly 2, a pitch assembly 3, and an optoelectronic load 4.

[0033] The base assembly 1 provides an installation and fixing interface, serving as the mounting foundation for the azimuth assembly 2. The base assembly 1 houses a control circuit board and an external interface; this external interface is the electrical interface for communication, image transmission, and control between the electro-optical pod and the UAV control system. The azimuth assembly 2 is mounted on the base assembly 1 via rolling bearings and can rotate on the base assembly 1. The pitch assembly 3, via rolling bearings, performs pitch oscillation on the azimuth assembly 2, with a pitch angle range of -120° to +30°. An electro-optical payload 4 is mounted on the pitch assembly 3. The base assembly 1 includes: a mounting base 101, an external interface 102, a base cover 103, a control board 104, an orientation control board 105, and a secondary power supply board 106. The mounting base 101 has fastening screw holes along its outer circumference, and an external interface is radially mounted on its outer circumference for connection to external information via a connector. The mounting base 101 has four circuit board mounting interfaces for mounting the control board 104, the secondary power supply board 106, the orientation control board 105, and one spare interface. Additionally, the mounting base 101 has multiple cable fixing structures. The base cover 103 has a columnar thin-walled structure, with a desiccant compartment 1031 on top for storing desiccant. The integrated control board 104 can receive control commands from the UAV, tracking miss distance, frame angle, and other information, and control the pitch and azimuth frames to complete search / positioning / tracking movements, and control the video tracker to complete tracking / unlocking operations. The azimuth control board 105 receives commands from the integrated control board 104 and controls the azimuth motor to complete search / positioning / tracking operations based on the gyro angular rate and frame angle data fed back by the integrated control board 104. The secondary power supply module 106 converts the power supply of the UAV to the power supply inside the pod and plays an isolation role to ensure the normal operation of the optoelectronic pod.

[0034] The orientation component 2 includes: an orientation shaft 201, an orientation bearing 202, an orientation motor 203, an orientation encoder 204, an orientation frame 205, a bearing retaining ring, and a bearing upper fixing ring; the orientation shaft 201 is mounted on the orientation frame 205; the orientation bearing 202 is mounted on the mounting base 101 and the orientation shaft 201, and is axially fixed by the bearing retaining ring and the bearing pressure block; the orientation motor 203 is used to drive the rotation of the orientation shaft 201, and the orientation motor 203 includes a rotor mounted on the orientation shaft and a stator mounted on the inner frame of the base; the orientation encoder 204 is used to measure the angle in the orientation direction, and is mounted on the orientation shaft 201 and axially fixed by the orientation encoder 204.

[0035] The pitch assembly 3 includes: a pitch frame 301 mounted on the azimuth frame 205 and rotatable relative to the azimuth frame 205; and a motor pitch assembly on the opposite side of the pitch frame 301, one side of which includes a pitch motor 302, a pitch motor shaft 303, a first pitch bearing 304 and a pitch motor bearing housing, and the other side includes a pitch encoder 305, a pitch encoder shaft 306, a second pitch bearing 307 and a pitch encoder bearing housing.

[0036] The optoelectronic payload 4 includes: a visible light camera module 401, an infrared camera 402, a video tracker 405, a pitch control board 403, an optoelectronic payload mounting bracket 404, and a three-axis MEMS gyroscope. The visible light camera module 401 and the infrared camera 402 are stacked vertically and mounted on the optoelectronic payload mounting bracket. The consistency of the dual optical axes is adjusted by the gap between the mounting holes. The video tracker is placed behind the camera module 401 and the infrared camera 402 and is cooled by contacting the housing through a heat dissipation adapter. The pitch control board is mounted on the upper part of the optoelectronic payload mounting bracket, and the three-axis MEMS gyroscope is mounted laterally.

[0037] See Figure 3 and Figure 5 This invention proposes an electro-optical guidance method for air-to-air capture of unmanned aerial vehicles, comprising the following steps: S1, A third-party radar measures the angle and position of the target; based on the angle and position of the target measured by the third-party radar, the UAV is guided into the operating range of the optoelectronic equipment to complete the optoelectronic guidance handover; the optoelectronic equipment is installed on the UAV; The photoelectric guidance handover refers to the process where, after the capture drone enters the operating range of the photoelectric equipment under the initial angle guidance of a third-party radar, the flight guidance control of the capture drone is handed over to the photoelectric equipment.

[0038] The capture drone enters the operating range of the optoelectronic equipment under the initial angle guidance of a third-party radar. The optoelectronic guidance system judges the handover conditions. If the handover conditions and timing meet the requirements, the system switches to optoelectronic guidance mode; otherwise, the handover judgment is performed again.

[0039] See Figure 4 During shift handover in photoelectric guidance, the target must be within the field of view of the photoelectric sensor. Due to third-party radar measurement errors, the actual target position lies within a sphere centered on the radar-measured target position and with the measurement error as its radius. The maximum angle between the capture drone and the actual target position is... α If the field of view (FOV) of the photoelectric sensor is ≥ 0, then FOV should be ≥ 0. α .

[0040] S2, use photoelectric equipment to acquire target images in real time; perform small target recognition and full-screen detection on the acquired target images to obtain the target's miss distance; Real-time acquisition of target images using optoelectronic equipment is achieved through a dual-light optoelectronic pod. The target image is acquired through a visible light module and an infrared camera. Based on image processing algorithms, small target recognition and full-screen detection are performed to identify the target and obtain the target's miss distance. After target recognition, automatic tracking is performed to continuously update the target position.

[0041] S201, Perform a cropping operation on the acquired target image to obtain multiple cropped images; Based on the size of the acquired target image, the acquired target image is sliced, and the slice size is determined to be 640*640, the overlap ratio is 0.2, the step size is 512, and the slices are slid from left to right and from top to bottom.

[0042] S202, perform small target recognition on each slice to obtain the coordinates of the target corresponding to the slice; Each slice is processed using the inter-frame difference method to generate a frame difference temporal feature map; In long-range flight, the target aircraft occupies only a few or tens of pixels, resulting in missing shape and texture and severe feature degradation. The input image is first preprocessed using inter-frame differencing to generate a frame difference temporal feature map. :

[0043] In the formula, This represents the number of pixels in the k-th frame of the video image. where x and y are the pixel coordinates. These are the length and height of the image, respectively. Image channel identifiers, For grayscale image channels, It has three channels: red, green, and blue.

[0044] Each slice image is processed using a row and column morphological decoupling method to generate a morphological space feature map; Morphological spatial feature map Described as:

[0045] In the formula, This image represents an intermediate result after morphological dilation and erosion transformations involving row and column decoupling. This represents a row decoupling structured operator. This represents the column decoupling structured operator.

[0046] The frame difference temporal feature map and the morphological space feature map are fused according to the feature map positive detection position consistency principle to obtain a spatiotemporal feature fusion map; the spatiotemporal feature fusion map is generated according to the feature map positive detection position consistency principle.

[0047] In the formula, Represented as the number of channels, Represents the frame difference temporal feature map. This represents the morphological space feature map. The spatiotemporal feature fusion map is then upsampled and downsampled to obtain the coordinates of the target corresponding to the sliced ​​image.

[0048] S203, using the NMS strategy, maps the coordinates of the target corresponding to the slice onto the acquired target image to obtain the target's miss distance. This is based on the coordinates of the top-left and bottom-right corners of the slice in the acquired target image. The Non-Maximum Suppression (NMS) strategy is used to suppress repeated predictions of targets in overlapping regions, thus mapping the target coordinates on the cropped image back to the original image. Compared to directly inputting the original image, this approach utilizes more information from the original image, improving the accuracy of small target detection. The NMS strategy is described as follows:

[0049] In the formula, The initial confidence score of the bounding box. Indicates a selection box With box The degree of overlap, This represents a preset threshold that determines whether to retain the confidence score of the bounding box.

[0050] Compared with other detection algorithms, this invention can detect 4*4 pixel targets under visible light and 1 pixel targets under infrared light, with high recognition accuracy.

[0051] S3 tracks the target in real time based on the target's miss distance; After the target is identified, it switches to automatic tracking, combines the servo drive of the optoelectronic device to perform image stabilization tracking, and moves the target to the center of the video tracker's screen in real time for video tracking guidance. S4: Based on the target's miss distance, obtain the target's angle information relative to the UAV; based on the target's angle information relative to the UAV, guide the UAV to approach the target. Based on the target's miss distance and the frame angle information of the optoelectronic device, the target's angle information relative to the UAV is obtained. The target's pitch and azimuth angles relative to the optoelectronic device are calculated using the miss distance information. These angles are then superimposed with the frame angle of the optoelectronic device to obtain the target's azimuth and pitch angles relative to the UAV, guiding the UAV to approach the target. Combined with the UAV's flight control module, dynamic and automatic flight guidance is achieved. The target's miss distance and the optoelectronic device's frame angle information include the horizontal miss distance. Vertical miss distance Orientation frame angle Pitch frame angle Then the angle information of the target relative to the drone is:

[0052] S5, when the distance between the drone and the target enters the working range of the capture equipment, the attitude of the capture equipment is adjusted in real time based on the pitch frame angle information of the optoelectronic equipment; When the distance between the drone and the target enters the operating range of the capture equipment, the capture equipment adjusts its pitch according to the angle information of the optoelectronic device's pitch frame, ensuring that the launch centerline of the capture equipment is parallel to the optical axis of the optoelectronic device. Because the optoelectronic pod moves the target to the center in real time during the tracking process, the capture equipment's homing energy improves the accuracy of the capture and launch.

[0053] S6, when the capture conditions are met, the capture equipment captures the target.

[0054] When the capture conditions are met, the capture equipment captures the target; When the capture conditions are not met, the capture equipment continuously tracks the target and adjusts its attitude in real time based on the pitch frame angle information of the optoelectronic equipment until the capture conditions are met. The capture equipment's follow-up guidance gives the capture mechanism (usually a net capture mechanism) pitch displacement function, which is based on the pitch encoder value of the dual-optical optoelectronic pod to improve the accuracy of capture and launch.

[0055] See Figure 6 An embodiment of the present invention provides an optoelectronic guidance system for air-to-air capture of unmanned aerial vehicles, comprising: The optoelectronic guidance handover module is used to guide the UAV into the operating range of the optoelectronic equipment based on the target's angle and position measured by a third-party radar, thus completing the optoelectronic guidance handover; the optoelectronic equipment is installed on the UAV. The target recognition module is used to acquire target images in real time using photoelectric equipment; it performs small target recognition and full-screen detection on the acquired target images to obtain the target's miss distance; The target tracking module is used to track the target in real time based on the target's miss distance. The flight guidance module is used to obtain the target's angle information relative to the UAV based on the target's miss distance; and to guide the UAV to approach the target based on the target's angle information. The capture guidance module is used to adjust the attitude of the capture equipment in real time based on the pitch frame angle information of the optoelectronic device when the distance between the UAV and the target enters the working range of the capture equipment. The capture module is used to capture the target when the capture conditions are met.

[0056] The above are merely preferred embodiments of the present invention and are not intended to limit the present invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A photoelectric guidance method for air-to-air capture of unmanned aerial vehicles, characterized in that, Includes the following steps: Based on the target's angle and position measured by a third-party radar, the drone is guided into the operating range of the optoelectronic equipment to complete the optoelectronic guidance handover; the optoelectronic equipment is installed on the drone. The target image is acquired in real time using optoelectronic equipment; small target recognition and full-screen detection are performed on the acquired target image to obtain the target's miss distance; Based on the target's miss distance, the target is tracked in real time; Based on the target's miss distance, the angle information of the target relative to the UAV is obtained; Based on the target's angle relative to the drone, guide the drone to fly closer to the target; When the distance between the drone and the target enters the operating range of the capture equipment, the attitude of the capture equipment is adjusted in real time based on the pitch frame angle information of the optoelectronic equipment. When the capture conditions are met, the capture equipment captures the target.

2. The photoelectric guidance method for air-to-air capture of unmanned aerial vehicles according to claim 1, characterized in that, The method of guiding the UAV into the operating range of the optoelectronic equipment based on the target's angle and position measured by a third-party radar, and completing the optoelectronic guidance handover, specifically involves: Based on the target's angle and position measured by a third-party radar, the drone's flight attitude and speed are adjusted to approach the target until the maximum angle between the drone and the target is less than or equal to the field of view of the optical sensor in the optoelectronic device. Switch the UAV's flight guidance mode from radar guidance to electro-optical guidance to complete the electro-optical guidance handover.

3. The photoelectric guidance method for air-to-air capture of unmanned aerial vehicles according to claim 1, characterized in that, The process of performing small target recognition and full-screen detection on the acquired target image to obtain the target's miss distance is as follows: The acquired target image is sliced ​​to obtain multiple slices; Small target recognition is performed on each slice to obtain the coordinates of the target corresponding to the slice; The NMS strategy is used to map the coordinates of the target corresponding to the slice onto the acquired target image to obtain the target's miss distance.

4. The photoelectric guidance method for air-to-air capture of unmanned aerial vehicles according to claim 3, characterized in that, The step of performing small target recognition on each slice to obtain the coordinates of the target corresponding to the slice is as follows: Each slice is processed using the inter-frame difference method to generate a frame difference temporal feature map; Each slice image is processed using a row and column morphological decoupling method to generate a morphological space feature map; The frame difference temporal feature map and the morphological space feature map are fused according to the principle of consistency of positive detection position of feature map to obtain a spatiotemporal feature fusion map; The spatiotemporal feature fusion map is upsampled and downsampled to obtain the coordinates of the target corresponding to the sliced ​​map.

5. The photoelectric guidance method for air-to-air capture of unmanned aerial vehicles according to claim 1, characterized in that, The target-based miss distance tracking in real time specifically involves: Based on the target's miss distance, the optoelectronic device performs image stabilization tracking of the target to ensure that the target is centered in the video tracker's view.

6. The photoelectric guidance method for air-to-air capture of unmanned aerial vehicles according to claim 1, characterized in that, The target's angle relative to the UAV is obtained based on the target's miss distance; based on this angle information, the UAV is guided to approach the target, specifically as follows: Based on the target's miss distance and the frame angle information of the optoelectronic equipment, the angle information of the target relative to the UAV is obtained.

7. The photoelectric guidance method for air-to-air capture of unmanned aerial vehicles according to claim 1, characterized in that, When the distance between the drone and the target enters the operating range of the capture equipment, the attitude of the capture equipment is adjusted in real time based on the pitch frame angle information of the optoelectronic device, specifically as follows: When the distance between the drone and the target enters the operating range of the capture equipment, the capture equipment will perform pitch follow-up based on the angle information of the pitch frame of the optoelectronic device to ensure that the launch center line of the capture equipment is parallel to the optical axis of the optoelectronic device.

8. The photoelectric guidance method for air-to-air capture of unmanned aerial vehicles according to claim 1, characterized in that, The capture device has a pitch and displacement function.

9. The photoelectric guidance method for air-to-air capture of unmanned aerial vehicles according to claim 1, characterized in that, When the capture conditions are met, the capture device captures the target, specifically as follows: When the capture conditions are met, the capture equipment captures the target; When the capture conditions are not met, the capture equipment continues to track the target and adjusts the attitude of the capture equipment in real time based on the pitch frame angle information of the photoelectric equipment until the capture conditions are met.

10. An electro-optical guidance system for air-to-air capture drones, based on the electro-optical guidance method for air-to-air capture drones as described in claim 1, characterized in that, include: The optoelectronic guidance handover module is used to guide the UAV into the operating range of the optoelectronic equipment based on the target's angle and position measured by a third-party radar, thus completing the optoelectronic guidance handover; the optoelectronic equipment is installed on the UAV. The target recognition module is used to acquire target images in real time using photoelectric equipment; it performs small target recognition and full-screen detection on the acquired target images to obtain the target's miss distance; The target tracking module is used to track the target in real time based on the target's miss distance. The flight guidance module is used to obtain the angle information of the target relative to the UAV based on the target's miss distance; Based on the target's angle relative to the drone, guide the drone to fly closer to the target; The capture guidance module is used to adjust the attitude of the capture equipment in real time based on the pitch frame angle information of the optoelectronic device when the distance between the UAV and the target enters the working range of the capture equipment. The capture module is used to capture the target when the capture conditions are met.

Images