False Positive Signal Reduction using AI in Counter UAS

Improving radar-based surveillance systems by using background estimation and foreground activity analysis. The system determines persistent objects at radar background locations, filters radar tracks with background motion, and generates alerts based on radar tracks and learned foreground activity patterns. It also fuses radar and vision data to improve scene understanding. The background estimation involves detecting radar objects at fixed locations and removing them. The foreground analysis involves learning typical radar track paths and generating alerts for unusual activity. This helps filter out false positives from moving background objects.

Source

A threat coping system for unmanned aerial vehicles (UAVs) that can autonomously intercept and destroy other UAVs without false positives or misfirings. The system has a control device that sets a no-coping area around targets that shouldn't be engaged. It generates instructions to the threat UAV to only intercept if it won't hit the no-coping area. This prevents collateral damage to nearby aircraft or ground targets. The no-coping area is based on factors like target speed, size, direction, and weapon characteristics.

Source

Detecting and taking countermeasures against unmanned aerial vehicles (UAVs) using AI-assisted object classification and adaptive jamming/spoofing. The system receives signals reflected by objects, conditions them to improve resolution and SNR, then uses AI to classify if the object is a UAV. If so, it takes over control using jamming and spoofing. Jamming disorients the UAV for a time, then spoofing establishes communication to remotely maneuver it. The jamming and spoofing parameters adapt based on range and velocity.

Source

Unauthorized unmanned aerial vehicles (UAVs) pose threats to public safety and individual privacy. Traditional object-detection approaches often fall short during their application in anti-UAV technologies. To address this issue, we propose the YOLOv7-GS model, which is designed specifically for the identification of small UAVs in complex and low-altitude environments. This research primarily aims to improve the models detection capabilities for small UAVs in complex backgrounds. Enhancements were applied to the YOLOv7-tiny model, including adjustments to the sizes of prior boxes, incorporation of the InceptionNeXt module at the end of the neck section, and introduction of the SPPFCSPC-SR and Get-and-Send modules. These modifications aid in the preservation of details about small UAVs and heighten the models focus on them. The YOLOv7-GS model achieves commendable results on the DUT Anti-UAV and the Amateur Unmanned Air Vehicle Detection datasets and performs to be competitive against other mainstream algorithms.

Source

Integrated system for low-altitude drone response that enables rapid identification and mitigation of unauthorized drones. The system combines radar, camera, and communication capabilities to detect and analyze drone presence, determine threat classification, and initiate response actions. The system integrates with a central server to manage drone traffic, including automatic threat detection, tracking, and response capabilities.

Source

A proposed strategy for managing airspace and preventing illegal drones from compromising security involves the use of autonomous drones equipped with three key functionalities. Firstly, the implementation of YOLO-v5 technology allows for the identification of illegal drones and the establishment of a visual-servo system to determine their relative position to the autonomous drone. Secondly, an extended Kalman filter algorithm predicts the flight trajectory of illegal drones, enabling the autonomous drone to compensate in advance and significantly enhance the capture success rate. Lastly, to ensure system robustness and suppress interference from illegal drones, an adaptive fast nonsingular terminal sliding mode technique is employed. This technique achieves finite time convergence of the system state and utilizes delay estimation technology for the real-time compensation of unknown disturbances. The stability of the closed-loop system is confirmed through Lyapunov theory, and a model-based hardware-in-the-loop simulation strategy is adopted to streamline system development and impro... Read More

Source

Unmanned aerial vehicle (UAV) technology has witnessed widespread utilization in target surveillance activities. However, cooperative multiple UAVs for the identification of multiple targets poses a significant challenge due to the susceptibility of individual UAVs to false positive (FP) and false negative (FN) target detections. Specifically, the primary challenge addressed in this study stems from the weak discriminability of features in Synthetic Aperture Radar (SAR) imaging targets, leading to a high false alarm rate in SAR target detection. Additionally, the uncontrollable false alarm rate during electro-optical proximity detection results in an elevated false alarm rate as well. Consequently, a cumulative error propagation problem arises when SAR and electro-optical observations of the same target from different perspectives occur at different times. This paper delves into the target association problem within the realm of collaborative detection involving multiple unmanned aerial vehicles. We first propose an improved triplet loss function to effectively assess the similarity ... Read More

Source

A system for detecting, classifying, and tracking unmanned aerial vehicles (UAVs) across various frequency bands. The system employs advanced AI-driven analysis to automatically detect and classify UAVs, while simultaneously providing direction-of-arrival information. The system utilizes multiple receivers to capture and process RF signals, with AI-powered signal processing and classification algorithms that can handle multiple modulation schemes. The system also enables real-time direction-finding capabilities, including bearing estimation and velocity calculation, and provides location estimation and trajectory prediction.

Source

Aiming at the six-rotor unmanned aerial vehicles subjected to false data injection attacks, an event-triggered-based distributed intelligent learning control strategy is proposed in this paper. The reinforcement learning algorithm which is designed based on neural networks is introduced to achieve intelligent optimal control. Under the actor-critic-identifier frame, three kinds of neural networks are used to realize the control action, evaluate the system performance, and estimate the unknown dynamic, respectively. Then, an improved event-triggered strategy including a decreasing function of the consensus error is designed to reduce the waste of resources while decreasing the adverse impact on tracking control performance as far as possible, which also does not exhibit Zeno behavior. Furthermore, an adaptive compensation control scheme is given, which can effectively compensate for the negative impacts brought by the false data injection attacks existing in information interaction among UAVs. Despite the impact of lumped disturbances and false data injection attacks, the proposed dis... Read More

Source

The efficient detection of "low-altitude, small, slow" UAV is always a difficult problem to overcome. In this paper, we are aiming at the application and threat cases of "low-altitude, small, slow" UAV, analyze the basic principle and development status of several kinds of methods in the detection of this target, and then makes an outlook on the future development direction of "low-altitude, small, slow" UAV detection.

Source

Unmanned aerial vehicles operating in illicit activities, commonly referred to as "black flights," pose an imminent risk regarding public safety and present strategies for detect individuals with such a poor attitude have difficulty striking an appropriate compromise within highest standard of quality as well as quickness.However, its effectiveness lies essence, especially regarding minor components along with detailed contexts.In order to answer those real issues, it offer minimal convolutional neural network including information improvement which will recognize moving creatures at such a lower elevations with high precision while in current moment as well as provide guidance material to suppress black-flying UAVs.Three modules comprise the network to be it has been offered.An innovation and social processing module significantly improves the model's ability to extract low-level features, when a correct detection method integrates low-level and advanced features to boost multi -resolution detection accuracy in complex environments, particularly for tiny objects.Such modules serve t... Read More

Source

A multi-hypothesis tracking system for tracking aerial targets that enables efficient processing of multiple sensor data in high false alarm environments. The system employs a structured branching approach to MHT, where multiple association hypotheses are computed for each new detection, and the least probable associations are omitted. The system maintains multiple reasonable alternatives while postponing final association decisions, enabling selection of the most probable associations within a given time. The system also incorporates bias corrections, cluster tracking, and track segment links to enhance tracking accuracy and robustness.

Source

Detection and classification of small unmanned aerial systems (sUAS) using multi-modal neural networks. The system employs a deep learning approach that combines passive RF detection with spectrographic analysis and sensor fusion. It enables the detection and classification of sUAS based on their RF signatures, radar and acoustic spectrograms, and electro-optical/infrared images. The system also includes a threat assessment component that determines the intent of the sUAS and predicts its frequency hopping sequences. This multi-modal approach enables robust detection and classification of sUAS, particularly in complex environments with non-threat emitters.

Source

In recent years, unmanned aerial vehicles (UAVs) have gained widespread use in both military and civilian fields with the advancement of aviation technology and improved communication capabilities. However, the phenomenon of unauthorized UAV flights, or "black flying", poses a serious threat to the safe flight of aircraft in airspace and public safety. To effectively interfere with and attack UAV targets, it is crucial to enhance the detection and identification of "low, slow and small" UAVs. This study focuses on achieving high-precision and lightweight detection and identification of four-rotor, six-rotor, and fixed-wing UAVs in low-altitude complex environments. By combining deep learning target detection with superresolution feature enhancement, a lightweight UAV detection model is designed and field-tested for verification. To address the challenge of detecting small UAV targets with limited information, the feature fusion network is enhanced based on the traditional YOLOv4 algorithm to improve the detection ability of small targets via small target enhancement and candidate box... Read More

Source

To date, the problems associated with increasing the stability of the flight of an unmanned aerial vehicle (UAV) are becoming quite relevant. This need is due to the presence of many factors that affect the UAV during the flight. Often the UAV is in an aggressive environment, and is also exposed to threats to information security. This study proposes a method for assessing the state of the flight and, on its basis, developing a solution for adjusting the flight parameters. Together, the system will make it possible to make a decision that contributes either to returning to the starting point to rescue the UAV, or to continuing the flight to a given target. A pilot study has shown that when using this UAV system, the target achievement rate increases to 86% when attacking a drone. In this case, detection and response occur with a probability of one hundred percent. Thanks to a new method for estimating the direction of parameter change and a more accurate determination of the boundaries of confidence intervals, the number of false positives is minimized. Thus, the presented software m... Read More

Source

Recently, with the significant rise of drones, reinforcing and securing aerial security and privacy has become an urgent task. Their malicious use takes benefit from the malevolent deployment which leverages some existing gaps in Artificial Intelligence (AI) and cybersecurity. Anti-drone systems are the spotlighted security solution developed to ensure aerial safety and security against rogue drones. However, the anti-drone systems are constraints to accurate airborne target identification and real-time detection to neutralize the target properly without causing damages. In this paper, we have developed a real-time multi-target detection model based on Yolov7 aiming to detect, identify and locate the airborne target properly and rapidly using a varied dataset which is biased and imbalanced due to the differences between the targets. In order to develop a model with the best compromise between a high performance and fast speed, we have used a series of improvements by incorporating the CSPResNeXt module in the backbone, a transformer block with the C3TR attention mechanism and decoupl... Read More

Source

Unmanned Aerial Vehicles (UAVs) have been widely used in many areas, including transportation, surveillance, and military. However, their potential for safety and privacy violations is an increasing issue and highly limits their broader applications, underscoring the critical importance of UAV perception and defense (anti-UAV). Still, previous works have simplified such an anti-UAV task as a tracking problem, where the prior information of UAVs is always provided; such a scheme fails in real-world anti-UAV tasks (i.e. complex scenes, indeterminate-appear and -reappear UAVs, and real-time UAV surveillance). In this paper, we first formulate a new and practical anti-UAV problem featuring the UAVs perception in complex scenes without prior UAVs information. To benchmark such a challenging task, we propose the largest UAV dataset dubbed AntiUAV600 and a new evaluation metric. The AntiUAV600 comprises 600 video sequences of challenging scenes with random, fast, and small-scale UAVs, with over 723K thermal infrared frames densely annotated with bounding boxes. Finally, we develop a novel a... Read More

Source

GPS spoofing attacks are a severe threat to unmanned aerial vehicles. These attacks manipulate the true state of the unmanned aerial vehicles, potentially misleading the system without raising alarms. Several techniques, including machine learning, have been proposed to detect these attacks. Most of the studies applied machine learning models without identifying the best hyperparameters, using feature selection and importance techniques, and ensuring that the used dataset is unbiased and balanced. However, no current studies have discussed the impact of model parameters and dataset characteristics on the performance of machine learning models; therefore, this paper fills this gap by evaluating the impact of hyperparameters, regularization parameters, dataset size, correlated features, and imbalanced datasets on the performance of six most commonly known machine learning techniques. These models are Classification and Regression Decision Tree, Artificial Neural Network, Random Forest, Logistic Regression, Gaussian Nave Bayes, and Support Vector Machine. Thirteen features extracted fr... Read More

Source

In recent years, civilian Unmanned Aerial Vehicles(UAV) have been widely used in various fields, which bringing convenience to people while also having many negative effects. Illegal flying UAVs have affected people's daily life, and there is an urgent need to establish an efficient UAV countermeasure mechanism for critical places such as government, hospitals, universities, and research institutes. To this end, this paper proposes a UAV recognition and tracking method for complex environments, firstly pre-identify UAV targets by YOLOv5, then combine the motion trajectory of targets in continuous images to discard the error outputs, finally use Kernel Correlation Filter to improve the continuous tracking capability. Experiments show that the algorithm in this paper can effectively improve 9.13% precision and the 11.54% recall compared with YOLOv5s network, and the recognition speed can reach to 27.64fps. Tested on the UAV interception platform developed by our team, the experimental results show that the platform deployed with our algorithm can continuously track the targets and inte... Read More

Source

Drones are gaining high popularity for their beneficial use in civilian applications and smart cities. Capable of being structured in networks, they can be used to collect several types of data, such as images, and be sent to centers for further processing. At the same time, they also become a new target for multiple types of attacks, among them False Data Injection (FDI), Denial of Service, GPS Spoofing, etc. Therefore, designing new systems and defense mechanisms against these attacks becomes urgent and necessary. In this paper, we emphasize the dangerous nature of the so-called False Data Injection (FDI) and describe a method based on deep learning for its detection. Considered a severe and powerful attack, an injection of false data into the data (images) collected by the drones can considerably alter a final decision that the processing center may take. To fight against this attack, our proposal relies on image analysis and classification using a deep learning approach. After scaling the received image to fit the classifier, using nearest neighbor interpolation (NNI), we feed a ... Read More

Source