Handheld net capture launching system for low-altitude target trajectory prediction
The handheld net capture and launch system for low-altitude target trajectory prediction, which combines binocular vision and Kalman filtering algorithms with a uniform acceleration model, solves the problems of low hit rate and high operational difficulty, and achieves efficient capture of high-speed moving UAVs.
Patent Information
- Application Number
- CN202511581181.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-10-31
- Publication Date
- 2026-01-23
AI Technical Summary
Existing handheld net capture systems have a low hit rate when hitting high-speed moving drones and rely on the user's experience and judgment, making them difficult to operate.
A binocular vision depth camera is used to acquire image information of the UAV, and the trajectory is predicted by combining the Kalman filter algorithm and the uniform acceleration model. The launch is then carried out by aiming at the predicted net position.
It improves the hit rate against fast-moving drones, reduces the difficulty of operation, and enables non-professionals to quickly and accurately hit targets.
Smart Images
Figure CN121383774A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of anti-drone technology, and more specifically, to a handheld net-capture and launch system for predicting the trajectory of low-altitude targets. Background Technology
[0002] With the widespread application of drone technology, unauthorized "black flights" pose a serious threat to airspace security. Against this backdrop, the demand for counter-drone technology is increasing across society. Existing counter-drone methods mainly include radio jamming, decoys, laser targeting, and physical interception. Net capture systems are a countermeasure that captures drones through physical interception. Their core principle is to launch a capture net made of materials such as metal / nylon to entangle the target drone, forcing it to crash or lose control. Handheld net capture systems are widely used in security operations, important events, and the protection of sensitive airspace due to their non-lethality, portability, low cost, and ease of operation.
[0003] However, its disadvantages include a short effective range, the need for precise hits on the drone target, and the fact that most net capture systems are disposable devices that need to be refilled after use, resulting in a low hit rate against high-speed moving drones. In view of this, the inventors propose a handheld net capture and launch system for low-altitude target trajectory prediction. Summary of the Invention
[0004] The purpose of this invention is to provide a handheld net capture and launch system for low-altitude target trajectory prediction, which combines a denoising diffusion probability model and an attention mechanism to develop an image brain tumor segmentation model, improves the accuracy of automatic segmentation algorithms and their robustness to noise, and promotes the application and development of artificial intelligence in smart healthcare.
[0005] The above-mentioned technical objective of the present invention is achieved through the following technical solution: The first aspect of this invention provides a handheld net-capture and launch method for predicting the trajectory of low-altitude targets, comprising the following steps: Acquire drone image information, and obtain the target drone's position, velocity, and acceleration information through continuous frame motion analysis; The position, velocity, and acceleration information of the UAV are input into the Kalman filter algorithm to obtain the predicted trajectory of the UAV and calculate the predicted net position after time Δt.
[0006] In conjunction with the first aspect, the present invention is further configured such that: the method for acquiring UAV image information is a user handheld device that initially aims at a low-altitude target UAV, uses a binocular visual depth camera to collect image information, converts the pixel coordinates of the image information into world coordinates, and obtains UAV image information.
[0007] In conjunction with the first aspect, the present invention is further configured such that: the coordinate transformation formula is ; in, World coordinates Z represents the pixel coordinates of the feature point; Z represents the depth value. These are the camera intrinsic and extrinsic parameter matrices.
[0008] In conjunction with the first aspect, the present invention is further configured such that the predicted net position is calculated using a uniform acceleration model.
[0009] In conjunction with the first aspect, the present invention is further configured such that: the distance (depth) Z between the target UAV and the system is measured by a depth camera, and the net-catching flight speed is... The solution is obtained by combining the predicted flight state of the net: ; in, Let t be the position of the UAV in the coordinate system with the camera as the origin. Let t be the position of the UAV in the world coordinate system at time t.
[0010] In conjunction with the first aspect, the present invention is further configured to: obtain the predicted position of the net, convert the coordinates, output them on the access screen, and launch the net to hit the target drone by aiming at the predicted position of the net.
[0011] A second aspect of the present invention also provides a handheld net-capturing launcher / device / system for low-altitude target trajectory prediction, comprising a memory, a processor, and a computer program stored in the memory, characterized in that the processor executes the computer program to implement the steps of the above method.
[0012] A third aspect of the present invention also provides a computer-readable storage medium having a computer program / instructions stored thereon, which, when executed by a processor, implement the steps of the above-described method.
[0013] A fourth aspect of the present invention also provides a computer program product, including a computer program / instructions that, when executed by a processor, implement the steps of the above-described method.
[0014] In summary, the present invention has the following beneficial effects: Traditional launching devices rely on the user's experience and judgment, which has limitations. This invention improves the hit rate against fast-moving drone targets and effectively solves the problems of "difficulty in calculating lead time and aiming point lag" that exist in handheld net capture devices when targeting high-speed, low-altitude small drones. The visual guidance provided by this invention presents the target trajectory prediction results to the user intuitively, reducing the difficulty of operating the device and enabling non-professionals to quickly get started and accurately hit the target. Attached Figure Description
[0015] Figure 1 This is a flowchart of the handheld net capture and launch method for low-altitude target trajectory prediction in Embodiment 1 of the present invention; Figure 2 This is a flowchart of the handheld net capture and launch method for low-altitude target trajectory prediction in Embodiment 2 of the present invention. Detailed Implementation
[0016] 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. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0017] Example 1: A handheld net-capture and launch method for low-altitude target trajectory prediction includes the following steps: S1. Manual Guidance and Data Acquisition The user uses a handheld device to initially target a low-altitude drone. Considering the limited effective range of the net and the inability of the handheld system to handle excessively large or heavy hardware, a binocular vision depth camera is used to acquire image information. The position and velocity information of the target drone are obtained through motion analysis of consecutive frames.
[0018] The images and depth images captured by binocular vision are converted to world coordinates using the following formula:
[0019] in, World coordinates Feature point pixel coordinates Z: Depth value Camera intrinsic and extrinsic parameter matrices The intrinsic parameter matrix contains internal camera attribute parameters, such as focal length, while the extrinsic parameter matrix contains camera attitude parameters measured using its built-in IMU (Inertial Measurement Unit). Movement or rotation will change its parameter information.
[0020] By comparing the drone's position information in previous and next frames, its displacement vector can be obtained, from which the drone's velocity can be calculated and its acceleration can be further obtained.
[0021] S2. Trajectory Prediction and Fusion Computation The Kalman filter algorithm is used to calculate and predict the trajectory of a UAV, employing a uniform acceleration model as an approximation. The UAV's position, velocity, and acceleration information are input into the Kalman filter algorithm to obtain the predicted trajectory.
[0022] Let k be the current state of the target at time k.
[0023]
[0024] Coordinate system position Velocity component : Acceleration component The transfer equation and the observation equation are as follows:
[0025]
[0026] Transition matrix, observation matrix and These are the normally distributed process noise and the normally distributed measurement noise, respectively, both following a 0-mean normal distribution. ~N(0,Q), ~N(0,R), where P and Q are the covariance matrices.
[0027] in:
[0028]
[0029] Therefore, the covariance matrix is obtained. This leads to the Kalman gain. .
[0030] Therefore, the optimal state estimate at time k can be obtained. ,and .
[0031] Based on the uniform acceleration model, the position of the UAV after time Δt is predicted:
[0032] The time difference Δt needs to be determined by the distance (depth) Z between the target UAV and the system, measured by the depth camera, and the net-catching flight speed. The solution is based on the predicted flight state of the net, taking into account the case of a short capture distance. Therefore, it is assumed that the net travels in a straight line and opens:
[0033] The position of the UAV at time t in the coordinate system with the camera as the origin. S3. Dynamic aiming and trigger firing: After obtaining the predicted net position, the world coordinates and pixel coordinates are transformed inversely and output to the screen connected to the camera to visualize the result.
[0034] The predicted hit point is displayed on the screen. Even if the camera loses sight of the drone target due to the rotating system, the previous prediction is still retained. At this time, the user can aim at the hit point through the net-launching system to hit the target drone.
[0035] Example 2: A handheld net-capture and launch method for low-altitude target trajectory prediction, such as Figure 2 As shown, it includes the following steps: S100. Acquire UAV image information, and obtain the position, velocity and acceleration information of the target UAV through continuous frame motion analysis; S200. Input the UAV's position, velocity, and acceleration information into the Kalman filter algorithm to obtain the UAV's predicted trajectory and calculate the predicted net position after time Δt.
[0036] In this embodiment, the method for acquiring UAV image information involves a user holding a handheld device, initially aiming at a low-altitude UAV target, using a binocular visual depth camera to collect image information, converting the pixel coordinates of the image information into world coordinates, and obtaining the UAV image information.
[0037] In this embodiment, the coordinate transformation formula is:
[0038] in, World coordinates Z represents the pixel coordinates of the feature point; Z represents the depth value. These are the camera intrinsic and extrinsic parameter matrices.
[0039] The intrinsic parameter matrix contains internal camera attribute parameters, such as focal length, while the extrinsic parameter matrix contains camera attitude parameters measured using its built-in IMU (Inertial Measurement Unit). Movement or rotation will change its parameter information.
[0040] By comparing the drone's position information in previous and next frames, its displacement vector can be obtained, from which the drone's velocity can be calculated and its acceleration can be further obtained.
[0041] In this embodiment, the predicted net location is calculated using a uniform acceleration model.
[0042] The Kalman filter algorithm is used to calculate and predict the trajectory of a UAV, employing a uniform acceleration model as an approximation. The UAV's position, velocity, and acceleration information are input into the Kalman filter algorithm to obtain the predicted trajectory.
[0043] Let k be the current state of the target at time k.
[0044]
[0045] Coordinate system position Velocity component : Acceleration component The transfer equation and the observation equation are as follows:
[0046]
[0047] Transition matrix, observation matrix and These are the normally distributed process noise and the normally distributed measurement noise, respectively, both following a 0-mean normal distribution. ~N(0,Q), ~N(0,R), where P and Q are the covariance matrices.
[0048] in:
[0049]
[0050] Therefore, the covariance matrix is obtained. This leads to the Kalman gain. .
[0051] Therefore, the optimal state estimate at time k can be obtained. ,and .
[0052] Based on the uniform acceleration model, the position of the UAV after time Δt is predicted:
[0053] In this embodiment, Δt is the distance (depth) Z between the target UAV and the system measured by the depth camera, and the net-catching flight speed is... The solution is obtained by combining the predicted flight state of the net:
[0054] in, Let t be the position of the UAV in the coordinate system with the camera as the origin. Let t be the position of the UAV in the world coordinate system at time t.
[0055] In this embodiment, S300. Obtain the predicted position of the net, convert the coordinates, output them on the access screen, and launch the net to hit the target drone by aiming at the predicted position of the net.
[0056] The present invention also provides a device / equipment / system for a handheld net capture and launch system for low-altitude target trajectory prediction, comprising a memory, a processor, and a computer program stored in the memory, characterized in that the processor executes the computer program to implement the steps of the above method.
[0057] The present invention also provides a computer-readable storage medium having a computer program / instructions stored thereon, which, when executed by a processor, implement the steps of the above-described method.
[0058] The present invention also provides a computer program product, including a computer program / instructions that, when executed by a processor, implement the steps of the above-described method.
[0059] Finally, it should be noted that the above descriptions are merely preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.
Claims
1. A handheld net-capture and launch method for low-altitude target trajectory prediction, characterized by: Includes the following steps: Acquire drone image information, and obtain the target drone's position, velocity, and acceleration information through continuous frame motion analysis; The position, velocity, and acceleration information of the UAV are input into the Kalman filter algorithm to obtain the predicted trajectory of the UAV and calculate the predicted net position after time Δt.
2. The handheld net capture and launch method according to claim 1, characterized in that: The method for acquiring UAV image information involves a user holding a handheld device, aiming at a low-altitude UAV target, collecting image information, converting the pixel coordinates of the image information into world coordinates, and obtaining the UAV image information.
3. The handheld net capture and launch method according to claim 2, characterized in that: The formula for coordinate transformation is: ； in, World coordinates Z represents the pixel coordinates of the feature point; Z represents the depth value. These are the camera intrinsic and extrinsic parameter matrices.
4. The handheld net capture and launch method according to claim 1, characterized in that: The predicted net location is calculated using a uniform acceleration model.
5. The handheld net capture and launch method according to claim 1, characterized in that: The distance (depth) Z between the target UAV and the system, measured by the depth camera, is given by the net-catching flight speed. The solution is obtained by combining the predicted flight state of the net: ； in, Let t be the position of the UAV in the coordinate system with the camera as the origin. Let t be the position of the UAV in the world coordinate system at time t.
6. The handheld net capture and launch method according to claim 1, characterized in that: Also includes: The predicted net location is converted to coordinates and output on the connected screen. By aiming at the predicted net location, the net is launched to hit the target drone.
7. A device / equipment / system for a handheld net capture and launch system for low-altitude target trajectory prediction, comprising a memory, a processor, and a computer program stored in the memory, characterized in that, The processor executes the computer program to implement the steps of the method according to any one of claims 1-6.
8. A computer-readable storage medium having a computer program / instructions stored thereon, characterized in that, When the computer program / instructions are executed by the processor, they implement the steps of the method described in any one of claims 1-6.
9. A computer program product comprising a computer program / instructions, characterized in that, When the computer program / instructions are executed by the processor, they implement the steps of the method described in any one of claims 1-6.