Unmanned aerial vehicle interference and laser strike system

By designing drone interference and laser strike systems and using a variety of detection and interference equipment, the problem that traditional air defense systems are difficult to cope with low-altitude drones is solved, effectively identifying and interfering with low-altitude drones is achieved, and defense is improved ability.

CN119063579APending Publication Date: 2024-12-03HAINAN RES INST OF ZHEJIANG UNIV +1

Patent Information

Application Number
CN202411524485.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-10-30
Publication Date
2024-12-03

AI Technical Summary

Technical Problem

Traditional air defense systems are difficult to effectively detect and deal with low-altitude drones, and cannot effectively defend against the threat of low-slow small drones.

Method used

A drone interference and laser strike system was designed, including energy storage system, power supply, control system, detection subsystem, strike subsystem, laser gimbal, communication management system and energy supply control system, through radio detection equipment , low-altitude detection radar, photoelectric identification and tracking equipment, navigation deception equipment, radio interference equipment and laser strike equipment to detect, identify, track and interference of drones.

Benefits of technology

The system can effectively identify and interfere with or strike low-altitude drones, prevent them from entering sensitive areas, and improve their defense capabilities against low-altitude drones.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119063579A_ABST
    Figure CN119063579A_ABST
Patent Text Reader

Abstract

The embodiment of the invention discloses an unmanned aerial vehicle interference and laser strike system. According to one specific embodiment, the unmanned aerial vehicle interference and laser strike system comprises a detection subsystem used for detection, identification and tracking of an unmanned aerial vehicle, and the detection subsystem comprises a radio detection device, a low-altitude detection radar and a photoelectric identification tracking device; the strike subsystem comprises a navigation decoy device, a radio interference device and a laser strike device; the energy supply control system is connected with the navigation decoy equipment, the radio interference equipment and the laser strike equipment and is used for supplying power to the navigation decoy equipment, the radio interference equipment and the laser strike equipment and remotely charging the navigation decoy equipment, the radio interference equipment and the laser strike equipment; and the control system sends an instruction to the strike subsystem according to a detection result of the detection subsystem so as to carry out navigation decoy, radio interference or laser strike. According to the embodiment, accurate positioning and striking of the unmanned aerial vehicle target are improved, and the safety of a low-altitude airspace is guaranteed.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The embodiments of the present disclosure relate to the field of drone jamming and laser strikes, and in particular to drone jamming and laser strike systems. Background Art

[0002] Drone technology has developed rapidly in recent years, and its application scope has been expanding from military use to civilian and commercial fields. However, the popularity of drones also brings security risks, including illegal intrusion into sensitive areas, threats to public safety, invasion of privacy, and potential terrorist activities.

[0003] Traditional air defense systems mainly target medium and high altitude targets. Traditional radars and air defense systems are difficult to effectively detect and respond to low, slow, and small targets such as drones. Drones can evade traditional defense measures by flying at low altitudes, being highly concealed, and being flexible and maneuverable.

[0004] The above information disclosed in this Background section is only for enhancement of understanding of the background of the inventive concept and therefore it may contain information that does not form the prior art that is already known in this country to a person of ordinary skill in the art. Summary of the invention

[0005] The content of this disclosure is used to introduce concepts in a brief form, which will be described in detail in the detailed implementation section below. The content of this disclosure is not intended to identify the key features or essential features of the technical solution claimed for protection, nor is it intended to limit the scope of the technical solution claimed for protection.

[0006] Some embodiments of the present disclosure propose a drone jamming and laser strike system to solve one or more of the technical problems mentioned in the above background technology section.

[0007] In a first aspect, some embodiments of the present disclosure provide a UAV jamming and laser strike system, which includes: an energy storage system, a power supply, a control system, a detection subsystem, a strike subsystem, a laser pan-tilt platform, a communication management system and an energy supply control system; it is characterized in that the energy storage system supplies power to the power supply, and the power supply supplies power to the control system, the detection subsystem, the strike subsystem, the laser pan-tilt platform, the communication management system and the energy supply control system; the control system is communicatively connected with the detection subsystem, the strike subsystem, the laser pan-tilt platform and the communication management system through a communication interface; the detection subsystem is used for detecting, identifying and tracking UAVs, and transmitting the detected UAV information to the control system in real time. Among them, the above-mentioned detection subsystem includes: radio detection equipment, low-altitude detection radar, optoelectronic identification and tracking equipment; the above-mentioned strike subsystem includes: navigation deception equipment, radio jamming equipment, laser strike equipment; the above-mentioned laser gimbal is integrated with the laser strike equipment; the above-mentioned communication management system is connected to the control system for comprehensive scheduling and situation visualization of each system; the above-mentioned energy supply control system is connected to the navigation deception equipment, radio jamming equipment, and laser strike equipment to supply power and remotely charge the navigation deception equipment, radio jamming equipment, and laser strike equipment; the above-mentioned control system sends instructions to the strike subsystem according to the detection results of the detection subsystem to perform navigation deception, radio jamming or laser strike, and control the rotation and pitch of the laser gimbal.

[0008] Optionally, the above-mentioned radio detection equipment monitors the radio signals in the air in real time, identifies the spectrum characteristics of the UAV, and transmits the detected radio signal information to the control system, which performs spectrum analysis and target identification; the above-mentioned low-altitude detection radar detects the position data of the UAV in real time, and transmits the position data of the UAV to the control system; the above-mentioned optoelectronic identification and tracking equipment captures the image of the UAV, performs target identification and tracking through the built-in image processing module, and transmits the identification and tracking results to the control system in real time.

[0009] Optionally, the above-mentioned navigation decoy device receives decoy instructions sent by the control system, and interferes with the UAV by transmitting false navigation signals, causing the UAV to deviate from its route or execute erroneous instructions; the above-mentioned radio jammer transmits jammer signals to block the communication and navigation of the UAV; after receiving the strike instruction from the control system, the above-mentioned laser strike device adjusts the output power, and the laser gimbal adjusts the direction of the laser beam in real time to achieve the strike on the target.

[0010] Optionally, the detection subsystem is configured to: control radio detection equipment and low-altitude detection radar to monitor airspace information in real time, identify drone targets, and transmit identification data to the control system; in response to identifying drone targets, control optoelectronic identification and tracking equipment to obtain drone images corresponding to drone targets, identify target features through a built-in image processing module, and determine whether the drone target is a threat object; and the control system is configured to: determine whether the drone target is a threat object based on the received identification data; if the drone target is a threat, select a corresponding interference method based on the threat level, wherein the interference methods include: navigation deception, radio interference, and laser strike; according to the above interference method, send a corresponding strike instruction to the strike subsystem, and send a laser beam direction adjustment instruction to the laser gimbal.

[0011] Optionally, the above-mentioned radio detection equipment is configured to: use a spectrum analyzer to collect radio signals within a preset frequency band to generate radio spectrum data; preprocess the radio spectrum data to generate preprocessed radio spectrum data; extract radio features in the above-mentioned preprocessed radio spectrum data; input the radio features into a pre-trained drone signal recognition model to obtain a drone signal recognition result; in response to determining that the drone signal recognition result represents the drone signal, mark the target corresponding to the radio signal as a drone target.

[0012] Optionally, the above-mentioned photoelectric recognition and tracking device is configured to: capture the surrounding environment image in real time through the built-in high-definition camera; pre-process the collected environment image to generate a pre-processed environment image; perform target detection on the pre-processed environment image through a pre-trained target detection model to generate a target detection image, wherein the above-mentioned target detection image contains a candidate bounding box of the target; perform feature extraction on the image area within the candidate bounding box in the above-mentioned target detection image to obtain target image area features; classify the above-mentioned target image area features through a pre-trained target classification detection model to obtain feature classification detection results; in response to determining that the above-mentioned feature classification detection results characterize the drone, continuously track the detected drone through a preset tracking algorithm.

[0013] Optionally, the above-mentioned radio detection equipment also includes: a drone signal recognition model training processor; and the above-mentioned drone signal recognition model training processor is configured to: obtain a drone radio spectrum signal group set, wherein a drone radio spectrum signal group in the drone radio spectrum signal group set corresponds to a drone radio spectrum signal type; label each drone radio spectrum signal in the above-mentioned drone radio spectrum signal group set to obtain a labeled drone radio spectrum signal group set as a drone radio spectrum signal sample group set; determine an initial drone signal recognition model; for each drone radio spectrum signal sample group in the above-mentioned drone radio spectrum signal sample group set, perform the following processing steps: select candidate drone radio spectrum signal samples from the above-mentioned drone radio spectrum signal sample group; perform signal enhancement and format conversion processing on the above-mentioned candidate drone radio spectrum signal samples to obtain a drone radio spectrum image matrix; according to each drone radio spectrum image matrix, train the initial drone signal recognition model to obtain a trained drone signal recognition model.

[0014] Optionally, the above-mentioned optoelectronic recognition and tracking device also includes: a target recognition model training processor; and the above-mentioned target recognition model training processor is configured to: obtain a drone environment image set, wherein a drone environment image group in the drone environment image set corresponds to a drone environment type; perform drone labeling on each drone environment image in the above-mentioned drone environment image set to generate a labeled drone environment image set as a drone environment image sample set; determine an initial target recognition model, wherein the above-mentioned initial target recognition model includes: an initial target detection model and an initial target classification detection model; select a target drone environment image sample from each drone environment image sample group in the above-mentioned drone environment image sample set to obtain a target drone environment image sample set; train the initial target detection model and the initial target classification detection model according to the above-mentioned target drone environment image sample set to obtain a trained target detection model and a target classification detection model. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and that components and elements are not necessarily drawn to scale.

[0016] Figure 1 is a schematic system architecture diagram of the drone jamming and laser strike system according to the present disclosure; Figure 2 A physical screenshot showing an internal test device of the laser gimbal and laser striking equipment. DETAILED DESCRIPTION

[0017] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments set forth herein. On the contrary, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0018] It should also be noted that, for ease of description, only the parts related to the invention are shown in the drawings. In the absence of conflict, the embodiments and features in the embodiments of the present disclosure can be combined with each other.

[0019] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0020] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0021] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0022] The present disclosure will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments.

[0023] Figure 1 The system architecture of the UAV jamming and laser strike system according to the present disclosure is shown. The UAV jamming and laser strike system includes: an energy storage system 1, a power supply 2, a control system 3, a detection subsystem 4, a strike subsystem 5, a laser gimbal 6, a communication management system 7 and an energy supply control system 8.

[0024] In some embodiments, the energy storage system 1 supplies power to the power supply 2, and the power supply 2 supplies power to the control system 3, the detection subsystem 4, the strike subsystem 5, the laser pan-tilt 6, the communication management system 7 and the energy supply control system 9. The energy storage system 1 can provide a stable power supply to prevent the system from failing to work due to power outages. The energy storage system 1 can be an energy storage power station including energy and material input and output, energy conversion and storage equipment. For example, the energy storage system 1 can be a battery energy storage system, including a battery energy storage system, a supercapacitor energy storage system, etc. The power supply 2 can directly provide power to the control system 3, the detection subsystem 4, the strike subsystem 5, the laser pan-tilt 6, the communication management system 7 and the energy supply control system 9. The control system 3 can be a computing device for controlling each system. For example, the control system 3 can be a central processor with the following functions: 1. Receive data from the detection subsystem, perform target identification and threat determination; 2. Issue instructions to the strike subsystem to perform deception, interference or laser strikes; 3. Dispatch the laser pan-tilt to achieve accurate aiming and strikes on the target; 4. Communicate with the communication management system, update the system operation status, and receive remote control instructions. The detection subsystem 4 may include: radio detection equipment, low-altitude detection radar, optoelectronic identification and tracking equipment for detecting, identifying and tracking drones. The radio detection equipment may be equipment for detecting radio signals of drones. For example, the radio detection equipment may be a radio detector or a wireless signal detector. The low-altitude detection radar may be a low-altitude radar for detecting the position data of drones in real time. The optoelectronic identification and tracking equipment may refer to a device that combines visible light and infrared imaging technology, collects optical information of drone targets through an optical system, and converts it into electrical signals for processing and analysis to achieve rapid and accurate identification and tracking of targets. The strike subsystem 5 may include: navigation deception equipment, radio jamming equipment, and laser strike equipment. The navigation deception equipment may refer to a drone navigation deception equipment, which, by emitting simulated satellite navigation signals, performs navigation deception on drones that break into sensitive areas, thereby achieving defense and control of drones. The radio jamming equipment may refer to a radio signal jammer. For example, the radio jamming equipment may be a drone countermeasure equipment. The laser strike equipment may refer to a laser for striking drones. The laser gimbal 6 may be a gimbal carrying a laser strike equipment, which may include: a camera, a lens, and a gimbal. The camera and lens are used to track the target. The pan / tilt rotation angle is 360 degrees, and it supports power-off memory and automatic cruise function. The pan / tilt pitch angle is -45 degrees to +45 degrees. The communication management system 7 can be a management device for device access management, situation visualization and policy management. Device access management: a management system that uniformly manages and controls various devices accessing the system to ensure the normal operation and collaborative work of the devices.The communication management system 7 can be used to register devices (control system 3, detection subsystem 4, strike subsystem 5, laser gimbal 6, energy supply control system 8). When each device is started, it first sends a registration request to the communication management system 7, including information such as device type, ID, status, location, function, etc.; secondly, it monitors the status of the registered devices in real time, including the operating status, connection status, power, temperature, performance, etc. of the devices; the status data is sent to the platform by the devices regularly for updating. Situation visualization: Receive data from the detection subsystem, display the detection and tracking information of the drone in real time, and assist the operator in making decisions and commanding. Strategy management: After the operator enters the strategy, send a strategy adjustment instruction to the control system to flexibly adjust the strike and interference measures according to different situations. For example, the communication management system 7 can be a management system that integrates a registration server, a display terminal and a computing processor. The energy supply control system 8 can refer to an energy conversion system that converts light energy into electrical energy, and through voltage conversion control, it supplies power and remote charging for navigation deception equipment, radio jamming equipment, and laser strike equipment.

[0025] In some embodiments, the control system is connected to the detection subsystem, the strike subsystem, the laser PTZ, and the communication management system through a communication interface. The communication interface may include but is not limited to: an Ethernet interface, an RS-232 interface, a multi-machine synchronization interface, a serial interface, etc.

[0026] In some embodiments, the detection subsystem is used to detect, identify and track drones, and transmit the detected drone information to the control system in real time. The detection subsystem includes: radio detection equipment, low-altitude detection radar, and optoelectronic identification and tracking equipment.

[0027] Among them, radio detection equipment can detect the radio signals of drones and identify their spectrum characteristics. Using spectrum analysis technology, it covers the 20M-8G frequency band to meet the needs of complex scenarios. Use deep learning algorithms to train and annotate drone spectrum graphs for accurate identification. Low-altitude detection radar can detect and locate drones flying at low altitudes at an early stage. Covering low-altitude areas, it provides real-time drone location information and assists other detection equipment in making comprehensive judgments. Photoelectric identification and tracking equipment can capture drone images for target identification and tracking. Equipped with high-definition cameras and image processing technology, it can extract and classify features by dividing images into grids to achieve automatic identification and tracking of drones.

[0028] In some embodiments, the above-mentioned strike subsystem includes: navigation deception equipment, radio jamming equipment, and laser strike equipment. Among them, the navigation deception equipment can send false navigation signals to interfere with the navigation system of the drone. By sending false signals through precise positioning, the drone deviates from the predetermined route or executes wrong instructions.

[0029] The core of the navigation deception device is to forge GPS signals and make their strength cover the real signal to trick the drone into receiving and trusting the false positioning information. The process is divided into the following steps: 1. UAV positioning: The real-time location of the UAV is obtained through the detection subsystem, including the current coordinates and heading of the UAV.

[0030] 2. False signal generation: Based on the current position of the drone, a false position of a target is calculated (interfering with the target position) and a set of false GPS data packets is constructed.

[0031] 3. Signal transmission: Using radio transmission equipment, the fake GPS signal is transmitted to the location of the target drone, covering the real GPS signal so that the drone receives and trusts the fake signal.

[0032] 4. Real-time update: Continuously monitor the drone’s response and dynamically adjust the false signal according to its movement status to ensure the effectiveness of the interference.

[0033] Radio jammers can emit high-power jamming signals to block drone communications and navigation. They can use omnidirectional or directional methods to emit jamming signals to form an electronic fence, covering the 400M-5.8G frequency band, with a jamming distance of up to 3 kilometers, forcing drones to return, make an emergency landing, or hover.

[0034] The laser striking equipment may include a laser and a cooling system. For example, the model of the laser may be DK-YSM-3000; optical parameters: continuous working mode, laser center wavelength 1060nm±3nm, average output power ≥3000W, beam quality M2≤1.3; the cooling system may be used to cool the laser; the working mode of the cooling system may be a water cooling mode, the cooling water temperature is 23±1℃, and the flow rate is not less than 30L / min.

[0035] In some embodiments, the laser platform is integrated with the laser striking device. The laser striking device is arranged on the laser platform, such as Figure 2 As shown, a screenshot of an internal test device of a laser pan-tilt and laser striking device is shown, that is, the position of the laser and the camera is as shown in FIG. Figure 2 The example given.

[0036] In some embodiments, the communication management system is connected to a control system for comprehensive scheduling and situation visualization of each system.

[0037] In some embodiments, the energy supply control system is connected to the navigation deception device, the radio jamming device, and the laser strike device to provide power and remote charging for the navigation deception device, the radio jamming device, and the laser strike device.

[0038] In some embodiments, the control system sends instructions to the strike subsystem based on the detection results of the detection subsystem to perform navigation deception, radio interference or laser strike, and control the rotation and pitch of the laser gimbal. For example, when the detection results indicate that an abnormal drone is detected, the control system sends a strike instruction to the strike subsystem. The strike instruction includes but is not limited to: navigation deception, radio interference, and laser strike.

[0039] Optionally, the above-mentioned radio detection equipment monitors the radio signals in the air in real time, identifies the spectrum characteristics of the UAV, and transmits the detected radio signal information to the control system, which performs spectrum analysis and target identification; the above-mentioned low-altitude detection radar detects the position data of the UAV in real time, and transmits the position data of the UAV to the control system; the above-mentioned optoelectronic identification and tracking equipment captures the image of the UAV, performs target identification and tracking through the built-in image processing module, and transmits the identification and tracking results to the control system in real time.

[0040] Optionally, the above-mentioned navigation decoy device receives decoy instructions sent by the control system, and interferes with the drone by transmitting false navigation signals, causing the drone to deviate from its route or execute erroneous instructions; the above-mentioned radio jammer transmits jammer signals to block the communication and navigation of the drone.

[0041] Optionally, after receiving a strike command from the control system, the laser strike device adjusts the output power, and the laser gimbal adjusts the direction of the laser beam in real time to achieve a strike on the target.

[0042] Optionally, the above-mentioned detection subsystem is configured to: control the radio detection equipment and the low-altitude detection radar to monitor the airspace information in real time, identify the UAV target, and transmit the identification data to the control system; in response to the identification of the UAV target, control the optoelectronic identification and tracking equipment to obtain the UAV image corresponding to the UAV target, identify the target features through the built-in image processing module, and determine whether the UAV target is a threat object.

[0043] Optionally, the control system is configured to: determine whether the UAV target is a threat object based on the received identification data; if the UAV target is a threat, select a corresponding interference method based on the threat level, wherein the interference methods include: navigation deception, radio interference, and laser strike; according to the above interference methods, send a corresponding strike instruction to the above strike subsystem, and send a laser beam direction adjustment instruction to the laser gimbal.

[0044] Optionally, the radio detection device is configured to: collect radio signals within a preset frequency band using a spectrum analyzer to generate radio spectrum data; preprocess the radio spectrum data to generate preprocessed radio spectrum data; extract radio features from the preprocessed radio spectrum data; input the radio features into a pre-trained drone signal recognition model to obtain a drone signal recognition result; in response to determining that the drone signal recognition result represents the drone signal, mark the target corresponding to the radio signal as a drone target. The preset frequency band may be a 20 MHz to 8 GHz frequency band. The preprocessing may be: denoising, filtering, and normalization. Extracting radio features from the preprocessed radio spectrum data includes: extracting features from the preprocessed radio spectrum data, such as frequency, amplitude, phase, modulation mode, etc., and converting them into feature vectors. The drone signal recognition model may be a pre-trained neural network model that takes radio features as input and outputs drone signal recognition results. For example. The drone signal recognition model may be a pre-trained CNN model.

[0045] As an illustration, the radio spectrum identification algorithm of the radio detection equipment works as follows: Step 1: The signal acquisition module (spectrum analyzer) acquires real-time radio spectrum data from the 20MHz-8GHz frequency band.

[0046] Step 2: The preprocessing module denoises, filters and normalizes the radio spectrum data.

[0047] Step 3: The feature extraction module extracts features from the preprocessed radio spectrum data to generate radio features.

[0048] Step 4: The deep learning model (CNN) analyzes the radio features and outputs the target category.

[0049] Therefore, the radio signals of drones are detected by radio detection equipment to identify their spectrum characteristics. Spectrum analysis technology is used to cover the 20M-8G frequency band to meet the needs of complex scenarios. Deep learning algorithms are used to train and annotate drone spectrum graphs to achieve accurate identification.

[0050] Optionally, the above-mentioned photoelectric recognition and tracking device is configured to: capture the surrounding environment image in real time through the built-in high-definition camera; pre-process the collected environment image to generate a pre-processed environment image; perform target detection on the pre-processed environment image through a pre-trained target detection model to generate a target detection image, wherein the above-mentioned target detection image contains a candidate bounding box of the target; perform feature extraction on the image area within the candidate bounding box in the above-mentioned target detection image to obtain target image area features; classify the above-mentioned target image area features through a pre-trained target classification detection model to obtain feature classification detection results; in response to determining that the above-mentioned feature classification detection results characterize the drone, continuously track the detected drone through a preset tracking algorithm.

[0051] As an illustration, the drone identification algorithm of the optoelectronic identification and tracking device is as follows: 1. Image acquisition: The high-definition camera in the photoelectric recognition and tracking device can capture the surrounding environment images in real time.

[0052] 2. Image preprocessing: Perform preprocessing operations such as grayscale, normalization, and enhancement on the collected environmental images to improve image quality and reduce noise interference.

[0053] 3. Object detection: Use object detection models such as YOLO (You Only Look Once) or SSD (Single Shot MultiBoxDetector) to detect the position of the drone in the environment image and generate candidate bounding boxes.

[0054] 4. Feature extraction: Perform feature extraction on the target area within the candidate bounding box, and use a convolutional neural network (CNN) to extract the spatial features of the drone, such as shape, texture, color, etc.

[0055] 5. Classification and tracking: Use the pre-trained target classification detection model to classify the extracted features and determine whether it is a drone. Continuous tracking of drones is achieved through tracking algorithms (such as KCF, SORT, Deep SORT, etc.).

[0056] 6. Multi-target processing: In multi-UAV environments, target detection and tracking algorithms are combined to achieve real-time monitoring of multiple UAVs.

[0057] Therefore, the photoelectric recognition and tracking equipment is used to capture the drone image for target recognition and tracking. Equipped with high-definition cameras and image processing technology, the image is divided into grids for feature extraction and classification, realizing automatic recognition and tracking of drones.

[0058] Optionally, the radio detection device includes: a drone signal recognition model training processor. The drone signal recognition model training processor may refer to a processor for training a drone signal recognition model.

[0059] Optionally, the drone signal recognition model training processor is configured to: The first step is to obtain a drone radio spectrum signal group set, where a drone radio spectrum signal group in the drone radio spectrum signal group set corresponds to a drone radio spectrum signal type. For example, collect radio spectrum signals of a large number of different types of drones, covering multiple frequency bands (20M-8G). When collecting data, it is necessary to ensure the diversity of different drone types, distances, and environmental conditions.

[0060] The second step is to label each drone radio spectrum signal in the drone radio spectrum signal set to obtain a labeled drone radio spectrum signal set as a drone radio spectrum signal sample set. For example, the collected drone radio spectrum signals are labeled, including labels such as drone model and signal type, to form a labeled data set.

[0061] The third step is to determine the initial drone signal recognition model. For example, a convolutional neural network (CNN) is selected as the initial drone signal recognition model. For example, architectures such as ResNet and VGG, or a customized CNN network structure suitable for spectrum graph feature extraction.

[0062] In the fourth step, for each drone radio spectrum signal sample group in the drone radio spectrum signal sample group set, the following processing steps are performed: 1. Select a candidate drone radio spectrum signal sample from the drone radio spectrum signal sample group. A drone radio spectrum signal sample can be randomly selected from the drone radio spectrum signal sample group as a candidate drone radio spectrum signal sample.

[0063] 2. Perform signal enhancement and format conversion on the above candidate drone radio spectrum signal samples to obtain a drone radio spectrum image matrix. Signal enhancement may include: denoising, filtering, normalization and other processing. Format conversion may refer to conversion into an image matrix format.

[0064] The fifth step is to train the initial drone signal recognition model according to each drone radio spectrum image matrix to obtain a trained drone signal recognition model. The labeled drone radio spectrum image matrix is ​​input into the initial drone signal recognition model for training. The cross entropy loss function is used as the loss indicator, and the model parameters are iteratively adjusted using optimization algorithms such as stochastic gradient descent (SGD) until the model converges. After that, the trained drone signal recognition model is tested using the validation set to evaluate the recognition accuracy of the model and adjust the model structure and parameters to improve performance.

[0065] As an example, some of the code corresponding to the drone signal recognition model training logic is as follows: { import numpy as np import torch import torch.nn as nn import torch.optim as optim # CNN model definition class CNNModel(nn.Module): def __init__(self): super(CNNModel, self).__init__() self.conv1=nn.Conv2d(1, 32, kernel_size=3, stride=1, padding=1) self.conv2=nn.Conv2d(32, 64, kernel_size=3, stride=1, padding=1) self.conv3=nn.Conv2d(64, 128, kernel_size=3, stride=1,padding=1) self.fc1=nn.Linear(128 * 8 * 8, 256) self.fc2=nn.Linear(256, 10) #Assume there are 10 types of drone signals self.relu = nn.ReLU() self.maxpool = nn.MaxPool2d(kernel_size=2, stride=2) def forward(self, x): x = self.relu(self.conv1(x)) x = self.maxpool(x) x = self.relu(self.conv2(x)) x = self.maxpool(x) x = self.relu(self.conv3(x)) x = self.maxpool(x) x = x.view(x.size(0), -1) x = self.relu(self.fc1(x)) x = self.fc2(x) return x #Load the trained CNN model cnn_model = CNNModel() cnn_model.load_state_dict(torch.load('radio_cnn_model.pth')) cnn_model.eval() #Radio signal recognition function def radio_signal_recognition(signal): # Preprocess the signal preprocessed_signal = preprocess_signal(signal) #Custom signal preprocessing function #Convert the signal to a tensor and add batch and channel dimensions input_tensor= torch.tensor(preprocessed_signal).float().unsqueeze(0).unsqueeze(0) #Prediction through CNN model with torch.no_grad(): output = cnn_model(input_tensor) # Output classification results prediction = torch.argmax(output, dim=1).item() return prediction #Pseudocode: Signal preprocessing function (including filtering, normalization, etc.) def preprocess_signal(signal): #Denoising, filtering, normalization and other processing filtered_signal = signal_processing_filter(signal) normalized_signal = (filtered_signal - np.min(filtered_signal)) / (np.max(filtered_signal) - np.min(filtered_signal)) return normalized_signal }; CNNModel: defines a simple CNN model for spectrum recognition.

[0066] radio_signal_recognition: Preprocesses the input radio signal and recognizes it through the CNN model, outputting the target classification.

[0067] preprocess_signal: Pseudocode representing signal preprocessing operations, including denoising and normalization.

[0068] Optionally, the above-mentioned photoelectric recognition and tracking device includes: a target recognition model training processor. The target recognition model training processor may refer to a processor for training a target recognition model. The target recognition model may include: a target detection model and a target classification detection model.

[0069] Optionally, the target recognition model training processor is configured to: The first step is to obtain a set of drone environment image groups. Among them, the drone environment image group in the drone environment image group set corresponds to a drone environment type. For example, a large amount of drone image data is collected through a camera, including drone images of different types, angles, distances and light conditions, to build a rich drone environment image set.

[0070] The second step is to label each drone environment image in the above drone environment image set with drones to generate a labeled drone environment image set as a drone environment image sample set. For example, the collected drone environment images are labeled to mark the border position, type, size and other information of the drone in the drone environment image to generate a drone environment image sample set.

[0071] The third step is to determine the initial target recognition model. The initial target recognition model includes: initial target detection model and initial target classification detection model. For example, YOLOv5 or SSD is selected as the initial target detection model for real-time identification of drones; CNN structures such as ResNet and Inception can be further selected as the initial target classification detection model.

[0072] In the fourth step, a target drone environment image sample is selected from each drone environment image sample group in the drone environment image sample group set to obtain a target drone environment image sample set. For each drone environment image sample group, a drone environment image sample can be randomly selected from the drone environment image sample group as the target drone environment image sample.

[0073] The fifth step is to train the initial target detection model and the initial target classification detection model according to the above target UAV environment image sample set to obtain the trained target detection model and target classification detection model.

[0074] The fifth step may include: 1. Initial object detection model training: Input the labeled data set into the YOLOv5 or SSD model for training, and use the cross entropy loss function and bounding box regression loss to jointly optimize the model parameters.

[0075] 2. Initial target classification detection model training: Use convolutional neural network (CNN) to extract target features, classify drones, and use cross entropy loss function to optimize model parameters.

[0076] Optionally, use an independent test set to test the trained model, evaluate the accuracy of object detection and classification, and adjust model parameters to improve recognition performance.

[0077] Optionally, use data augmentation techniques (such as image flipping, rotation, scaling, cropping, etc.) to increase the diversity of training data and prevent model overfitting.

[0078] As an example, part of the code corresponding to the object recognition model training logic is as follows: { pip install yolov5 YOLO object detection and SORT tracking import cv2 import torch from sort import Sort #Use SORT for target tracking #Load YOLOv5 model yolo_model = torch.hub.load('ultralytics / yolov5', 'yolov5s') # Can be replaced with a custom model suitable for drone detection; # Initialize the SORT tracker tracker = Sort() # Target detection and tracking functions def detect_and_track(video_path): #Open the video stream cap = cv2.VideoCapture(video_path) while cap.isOpened(): ret, frame = cap.read() if not ret: break #Use YOLOv5 for target detection results = yolo_model(frame) detections = results.xyxy[0].numpy() # [x1, y1, x2, y2, conf,class] #Filter the detection results and only keep the drone category filtered_detections = [] for detection in detections: x1, y1, x2, y2, conf, cls = detection if int(cls) == 0: #Assume that class 0 represents a drone filtered_detections.append([x1, y1, x2, y2, conf]) # Pass the detection results to the SORT tracker tracks = tracker.update(np.array(filtered_detections)) #Draw the tracking box for track in tracks: x1, y1, x2, y2, track_id = track cv2.rectangle(frame, (int(x1), int(y1)), (int(x2), int(y2)), (0, 255, 0), 2) cv2.putText(frame, f'ID: {int(track_id)}', (int(x1), int(y1) - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 255, 0), 2) # Display results cv2.imshow('Drone Detection and Tracking', frame) #Exit conditions if cv2.waitKey(1) & 0xFF == ord('q'): break cap.release() cv2.destroyAllWindows() }.

[0079] Therefore, the yolov5 library is used to load the pre-trained YOLO model for target detection, and the SORT algorithm is used to track the detected drones to provide continuous target location information.

[0080] The above descriptions are only some preferred embodiments of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present disclosure is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above inventive concept. For example, the above features are replaced with (but not limited to) technical features with similar functions disclosed in the embodiments of the present disclosure.

Claims

1. A UAV jamming and laser strike system, the UAV jamming and laser strike system comprising: Energy storage system, power supply, control system, detection subsystem, strike subsystem, laser PTZ, communication management system and energy supply control system; characterized in that, The energy storage system supplies power to the power supply, and the power supply supplies power to the control system, detection subsystem, strike subsystem, laser gimbal, communication management system and energy supply control system; The control system is connected to the detection subsystem, the strike subsystem, the laser PTZ, and the communication management system through a communication interface; The detection subsystem is used for detecting, identifying and tracking UAVs, and transmitting the detected UAV information to the control system in real time, wherein the detection subsystem includes: radio detection equipment, low-altitude detection radar, photoelectric identification and tracking equipment; The strike subsystem includes: navigation deception equipment, radio jamming equipment, and laser strike equipment; The laser pan / tilt platform is integrated with the laser striking equipment; The communication management system is connected to the control system and is used for comprehensive scheduling and situation visualization of each system; The energy supply control system is connected to the navigation deception device, the radio jamming device, and the laser strike device to supply power and remotely charge the navigation deception device, the radio jamming device, and the laser strike device; The control system sends instructions to the strike subsystem based on the detection results of the detection subsystem to perform navigation deception, radio interference or laser strike, and control the rotation and pitch of the laser gimbal.

2. The UAV jamming and laser strike system according to claim 1 is characterized in that: The radio detection equipment monitors the radio signals in the air in real time, identifies the spectrum characteristics of the UAV, and transmits the detected radio signal information to the control system, which performs spectrum analysis and target identification; The low-altitude detection radar detects the position data of the UAV in real time and transmits the position data of the UAV to the control system; The optoelectronic identification and tracking device captures drone images, performs target identification and tracking through a built-in image processing module, and transmits the identification and tracking results to the control system in real time.

3. The UAV jamming and laser strike system according to claim 2 is characterized in that: The navigation deception device receives the deception instruction sent by the control system, and interferes with the UAV by transmitting a false navigation signal, causing the UAV to deviate from the route or execute an erroneous instruction; The radio jammer transmits jamming signals to block the communication and navigation of the UAV; After receiving the strike command from the control system, the laser strike device adjusts the output power, and the laser pan / tilt adjusts the direction of the laser beam in real time to achieve the strike on the target.

4. The UAV jamming and laser strike system according to claim 3 is characterized in that: The detection subsystem is configured to: Control radio detection equipment and low-altitude detection radar to monitor airspace information in real time, identify drone targets, and pass identification data to the control system; In response to identifying the drone target, controlling the optoelectronic identification and tracking device to obtain the drone image corresponding to the drone target, identifying the target features through the built-in image processing module, and determining whether the drone target is a threat object; And the control system is configured to: Determine whether the drone target is a threat object based on the received identification data; If the drone target is a threat, select the corresponding interference method according to the threat level, where the interference methods include: navigation deception, radio interference, and laser strike; According to the interference mode, a corresponding striking instruction is sent to the striking subsystem, and an instruction for adjusting the direction of the laser beam is sent to the laser gimbal.

5. The UAV jamming and laser strike system according to claim 4 is characterized in that: The radio detection device is configured to: Using a spectrum analyzer, radio signals within a preset frequency band are collected to generate radio spectrum data; preprocessing the radio spectrum data to generate preprocessed radio spectrum data; extracting radio features from the preprocessed radio spectrum data; Input the radio features into the pre-trained drone signal recognition model to obtain the drone signal recognition result; In response to determining that the drone signal identification result represents the drone signal, a target corresponding to the radio signal is marked as a drone target.

6. The UAV jamming and laser strike system according to claim 5 is characterized in that: The photoelectric identification and tracking device is configured to: Capture surrounding environment images in real time through the built-in high-definition camera; Preprocessing the collected environment image to generate a preprocessed environment image; Performing target detection on the preprocessed environment image by using a pre-trained target detection model to generate a target detection image, wherein the target detection image includes a candidate bounding box of the target; Extracting features of an image region within a candidate frame in the target detection image to obtain target image region features; Classifying the target image region features through a pre-trained target classification detection model to obtain a feature classification detection result; In response to determining that the feature classification detection result characterizes a drone, the detected drone is continuously tracked using a preset tracking algorithm.

Citation Information

Patent Citations

  • Unmanned aerial vehicle target recognition and classification method based on deep learning

    CN110084094A

  • Urban low, slow and small unmanned aerial vehicle target monitoring device and monitoring method

    CN111986523A

  • Low-slow-small flying target designated point deception method based on low-altitude denial system

    CN112902756A

  • Low-altitude denial system and method for precise strike

    CN114046690A

  • Unmanned aerial vehicle prevention and control system based on square cabin

    CN114353594A

Cited By

  • Automatic positioning method and device of unmanned aerial vehicle in sensitive area based on 5G network

    CN119767404A

  • Method and device for automatic positioning of a drone in a sensitive area based on a 5g network

    CN119767404B

  • Unmanned aerial vehicle interference system and method

    CN119987436A