This thesis explores the process of designing an automatic multisensordrone detection system using machine learning and sensorfusion. Besides the more common video and audio sensors, the systemalso includes a thermal infrared camera. The results show thatutilizing an infrared sensor is a feasible solution to the drone detectiontask, and even with slightly lower resolution, the performance isjust as good as a video sensor. The detector performance as a functionof the sensor-to-target distance is also investigated. Using sensor fusion, the system is made more robust than the individualsensors. It is observed that when using the proposed sensorfusion approach, the output system results are more stable, and thenumber of false detections is mitigated. A video dataset containing 650 annotated infrared and visible videosof drones, birds, airplanes and helicopters is published. Additionally,an audio dataset with the classes drones, helicopters and backgroundsis also published.

<div>Recently, with the advancement in drone technology, more and more hobby drones are being manufactured and sold across the world. However, these drones can be repurposed</div><div>for the use in illicit activities such as hostile-load delivery. At the moment there are not many systems readily available for detecting and intercepting those hostile drones. Although there is a prototype of a working drone interceptor system built by the researchers of Purdue University, the system was not ready for the general public due to its nature of proof-of-concept and the high price range of the military-grade RADAR used in the prototype. It is essential to substitute such high-cost elements with low-cost ones, to make such drone interception system affordable enough for large-scale deployment.</div><div><br></div><div><div>This study aims to provide an alternative, affordable way to substitute an expensive, high-precision RADAR system with Convolutional Neural Network based drone detection system, which can be built using multiple low-cost single board computers. The experiment will try to find the feasibility of the proposed system and will evaluate the accuracy of the drone detection in a controlled environment.</div></div>

<div> <div> <div> <p>With the advancement in Unmanned Aerial Vehicles (UAV) technology, UAVs have become accessible to the public. However, recent world events have highlighted that the rapid increase of UAVs is bringing with it a threat to public privacy and security. Thus, it is important to think about how to prevent the threats of UAVs to protect our privacy and safety. This study aims to provide an alternative way to substitute an expensive system by using 2D optical sensors that can be easily utilized by people. One of the main challenges for aerial object recognition with computer vision is discriminating other flying objects from the targets, in the far distance. There are limitation to classify the flying object when it appears as a set of small black pixels on the frame. The movement feature can help the system to extract the discriminative feature, so that the classifier can classify the UAV and other objects, such as a bird. Thus, this study proposes a drone detection system using two elements of information, which are appearance information and motion information to overcome the limitation of a vision based system. </p> </div> </div> </div>

No description available.

Similar to a car’s license plate, the European Union Aviation Safety Agency (EASA) has released new regulations imposing the registration of drone operators and the broadcasting of the drone’s “digital license plate”, i.e., the drone Remote Identification (RID) in flight, which gives a new opportunity in drone surveillance. Thus, it is meaningful to test the performance of Direct Remote Identification (DRI). To evaluate whether DRI can further improve the performance of the current Counter-Unmanned Aerial System (CUAS), it is essential to understand the performance of DRI, e.g., the effective region (maximal range). In this project, the field test of DRI reception with two broadcast protocols, Wireless Fidelity (Wi‑Fi) and Bluetooth, is carried out. As a result, with a 10dB high-gain receiving antenna and Mavic 3 as the transmitter in suburban areas, the maximal range can reach 1300 meters and still performs well in urban areas with a 700-meter maximal range when predicted with empirical propagation models. The field test results regard DRI signal as a helpful assistant in drone detection and surveillance. Therefore, a DRI receiver is developed in this project. All the basic functions like signal receiving and processing, Internet connection, and data transmission are successfully implemented. With further developments, the receiver could become a product that provides drone detection and tracking services. / Liknande en bils registreringsskylt har Europeiska unionens byrå för luftfartssäkerhet (EASA) infört nya regler som kräver registrering av drönaroperatörer och sändning av drönarens ”digitala registreringsskylt”, det vill säga fjärridentifiering (RID) under flygning, vilket ger nya möjligheter inom drönarövervakning. Därför är det meningsfullt att testa prestandan för Direkt Fjärridentifiering (DRI). För att utvärdera om DRI kan förbättra prestandan för det nuvarande systemet för bekämpning av obemannade luftfarkoster (CUAS), är det väsentligt att förstå DRIs prestanda, till exempel den effektiva regionen (maximal räckvidd). I detta projekt genomförs fälttest av DRI-mottagning med två sändningsprotokoll, Wireless Fidelity (Wi-Fi) och Bluetooth. Som resultat, med en 10dB högvinstantenn och Mavic 3 som sändare i förortsområden, kan maximal räckvidd nå 1300 meter och presterar fortfarande bra i urbana områden med en maximal räckvidd på 700 meter när det förutsägs med empiriska propagationsmodeller. Fälttestresultaten betraktar DRI-signalen som en hjälpsam assistent i drönardetektion och övervakning. Därför utvecklas en DRI-mottagare i detta projekt. Alla grundläggande funktioner som signal mottagning och bearbetning, internetanslutning och datatransmission är framgångsrikt implementerade. Med ytterligare utvecklingar kan mottagaren bli en produkt som tillhandahåller tjänster för detektering och spårning av drönare.

In recent years, unmanned aerial vehicles (UAV), also called drones, have experienced a rapid increase, which leads to the concern of illegal use of them. Passive RF is one of the effective ways to detect drones by receiving drones’ communication signals. After receiving the signal from drones, one can utilize the prior knowledge of signal characteristics for identifying and locating the drones. The angle of arrival (AoA) measured by multiple passive RF sensors can be used for localization by triangulation. However, the accuracy of the AoA measured by the passive RF sensors is strongly affected by the environment. In particular in urban areas, the multipath effect is prominent due to the building blockage and complicated terrestrial conditions that introduce certain errors to the result. So the service provider of the sensors needs a tool to perform the environment analysis to understand the quality of the service. A fast tool that can simulate the sensor network and surrounding environment can offer a flexible solution to optimize the sensor coverage and indicate the blind zone of detection. Especially when the sensors are deployed on the mobile platform, such tool can significantly improve the defensive quality of the drone detection system by optimizing real-time deployment and indicating low observable areas. In order to plan the sensor locations and assess the performance after the deployment of the sensor at a fast speed, We propose a multipath-based model to calculate the AoA error. The model is able to utilize the input of geometrical information for simulating the AoA error within a region. In this thesis, we investigate the outdoor channel at 2.4GHz using the ray-tracing method as it is the most used channel for UAVs. Massive simulations have been carried out and real test flights have been conducted to evaluate the accuracy of the modeling. Both simulations and test flights are carried out in Kista center where buildings are from high-rises to one-floor houses with various heights. In the simulation, the AoA is obtained by MUltiple SIgnal Classification (MUSIC) algorithm. Test flights are conducted using an existing Software-defined radio (SDR) based RF sensor. We tried our best to carry out the same trajectories in both simulations and test flights to provide fair comparisons. The simulation results show that the multipath model can predict the trend of AoA error when the height changes, while not sufficient to predict the error when the 2D position changes. Thus, to more accurately characterize the signal transmission, it is essential to extend this thesis to include more detailed environmental information and adaption based on measurement. / Under de senaste åren har obemannade flygfarkoster (UAV), även kallade drönare, ökat snabbt, vilket leder till oro för olaglig användning av dem. Passiv RF är ett av de effektiva sätten att upptäcka drönare genom att ta emot drönarnas kommunikationssignaler. Efter att ha tagit emot signalen från drönare kan man använda den tidigare kunskapen om signalegenskaperna för att identifiera och lokalisera drönarna. AoA som mäts av flera passiva RF-sensorer kan användas för lokalisering genom triangulering. Noggrannheten hos AoA som mäts av de passiva RF-sensorerna påverkas dock starkt av miljön. Särskilt i stadsområden är multipath-effekten framträdande på grund av byggnadsblockering och komplicerade markförhållanden som medför vissa fel i resultatet. Därför behöver leverantören av sensorer ett verktyg för att utföra miljöanalysen för att förstå tjänstens kvalitet. Ett snabbt verktyg som kan simulera sensornätverket och den omgivande miljön kan erbjuda en flexibel lösning för att optimera sensortäckningen och ange den blinda zonen för upptäckt. Särskilt när sensorerna placeras på en mobil plattformkan ett sådant verktyg avsevärt förbättra drönardetektionssystemets försvarskvalitet genom att optimera utplaceringen i realtid och ange områden med låg observationsgrad. För att planera sensorernas placering och bedöma prestandan efter att sensorn har placerats ut i snabb takt föreslår vi en multipath-baserad modell för att beräkna AoAfelet. Modellen kan utnyttja inmatningen av geometrisk information för att simulera AoA-felet inom ett område. I denna avhandling undersöker vi utomhuskanalen vid 2:4 GHz med hjälp av raytracing- metoden eftersom det är den mest använda kanalen för UAV:er. Massiva simuleringar har utförts och verkliga testflygningar har genomförts för att utvärdera modelleringens noggrannhet. Både simuleringar och testflygningar har utförts i Kista centrum där byggnaderna är allt från höghus till envåningshus med olika höjd. I simuleringen erhålls AoA med hjälp av MUSIC-algoritmen. Testflygningar genomförs med hjälp av en befintlig SDR-baserad RF-sensor. Vi gjorde vårt bästa för att utföra samma banor i både simuleringar och testflygningar för att ge rättvisa jämförelser. Simuleringsresultaten visar att multipathmodellen kan förutsäga trenden för AoA-felet när höjden ändras, medan den inte är tillräcklig för att förutsäga felet när 2D-positionen ändras. För att mer exakt karakterisera signalöverföringen är det därför viktigt att utöka denna avhandling till att omfatta mer detaljerad miljöinformation och anpassning baserad på mätning.

<p><em>Imbulgoda Liyangahawatte, Gihan Janith Mendis Ph.D., Purdue University, May</em></p> <p><em>2023. Deep learning for securing critical infrastructure with the emphasis on power</em></p> <p><em>systems and wireless communication. Major Professor: Dr. Jin Kocsis.</em></p> <p><br></p> <p><em>Critical infrastructures, such as power systems and communication</em></p> <p><em>infrastructures, are of paramount importance to the welfare and prosperity of</em></p> <p><em>modern societies. Therefore, critical infrastructures have a high vulnerability to</em></p> <p><em>attacks from adverse parties. Subsequent to the advancement of cyber technologies,</em></p> <p><em>such as information technology, embedded systems, high-speed connectivity, and</em></p> <p><em>real-time data processing, the physical processes of critical infrastructures are often</em></p> <p><em>monitored and controlled through cyber systems. Therefore, modern critical</em></p> <p><em>infrastructures are often viewed as cyber-physical systems (CPSs). Incorporating</em></p> <p><em>cyber elements into physical processes increases efficiency and control. However, it</em></p> <p><em>also increases the vulnerability of the systems to potential cybersecurity threats. In</em></p> <p><em>addition to cyber-level attacks, attacks on the cyber-physical interface, such as the</em></p> <p><em>corruption of sensing data to manipulate physical operations, can exploit</em></p> <p><em>vulnerabilities in CPSs. Research on data-driven security methods for such attacks,</em></p> <p><em>focusing on applications related to electrical power and wireless communication</em></p> <p><em>critical infrastructure CPSs, are presented in this dissertation. As security methods</em></p> <p><em>for electrical power systems, deep learning approaches were proposed to detect</em></p> <p><em>adversarial sensor signals targeting smart grids and more electric aircraft.</em></p> <p><em>Considering the security of wireless communication systems, deep learning solutions</em></p> <p><em>were proposed as an intelligent spectrum sensing approach and as a primary user</em></p> <p><em>emulation (PUE) attacks detection method on the wideband spectrum. The recent</em></p> <p><em>abundance of micro-UASs can enable the use of weaponized micro-UASs to conduct</em></p> <p><em>physical attacks on critical infrastructures. As a solution for this, the radio</em></p> <p><em>frequency (RF) signal-analyzing deep learning method developed for spectrum</em></p> <p><em>sensing was adopted to realize an intelligent radar system for micro-UAS detection.</em></p> <p><em>This intelligent radar can be used to provide protection against micro-UAS-based</em></p> <p><em>physical attacks on critical infrastructures.</em></p>

No description available.

As drones are becoming ubiquitous, robust detection and tracking of potentially hostile drones is becoming a necessity. Among the many approaches being investigated in this relatively new research area, one cost effective option is the use of optical cameras equipped with computer vision algorithms. With the use of deep learning, it becomes possible to achieve high accuracy by generalizing from large datasets. However, drones are small and visually similar to birds, which has proven to be a major difficulty for purely vision based systems. This thesis investigates the utility of trajectory information (velocity and acceleration) in addition to temporal appearance features for detection and tracking of drones. While both kinds of information has been used in a variation of ways, work combining the two is largely lacking. Our approach uses background subtraction to generate candidate objects that initialize an LSTM which in turn combines trajectory and appearance information over multiple frames for joint detection and tracking of drones. While our specific implementation fails to outperform a traditional object detector in the form of YOLOv8, this could change with the solution of two problems identified with our approach. First problem being how to effectively incorporate large amounts of background data into the training of our network. Second being how to avoid repeatedly proposing the same non-drone candidates, while still being able to quickly resume tracking of a lost drone. / I takt med att drönare blir allt vanligare stiger kraven på robusta system som kan upptäcka och spåra hotfulla drönare. Bland de flertal tillvägagångssätt som undersöks i detta relativt nya forskningsområde är användandet av optiska kameror utrustade med datorseende-algoritmer ett kostnadseffektivt val. Genom användningen av djupinlärning har det blivit möjligt att uppnå hög pricksäkerhet genom att generalisera utifrån stora dataset. Men, drönare är små och utseendemässigt sett lika fåglar vilket är ett svåröverkomligt problem för system som endast förlitar sig på datorseende. I detta examensarbete undersöks vilken nytta som kan fås om man även tar hänsyn till information om drönarens trajektoria i form av hastighet och acceleration. Trots att både visuellt utseende och trajektoria är välstuderat när det kommer till drönardetektering, saknas det till stor del forskning som behandlar båda tillsammans. Vi använder bakgrundssubtraktion för att generera kandidater som startpunkt för en LSTM för att sedan kombinera trajektoria med utseende för förenad detektering och spårning av drönare. Fastän vår specifika implementation inte lyckas överträffa en traditionell objektdetekterare i form av YOLOv8, skulle detta kunna ändras givet en lösning på två identifierade problem med vårt tillvägagångssätt. Det första problemet är att hitta ett effektivt sätt att inkorporera stora mängder bakgrundsdata i träningen av vårt nätverk. Det andra är att undvika att gång på gång föreslå samma kandidater och samtidigt kunna snabbt återuppta spårningen av en förlorad drönare.

During the last century, various countries' armed forces have used unmanned aerial vehicles, commonly known as drones. In recent years, strives have been made to develop small commercial drones that have allowed the general public to afford and use them for recreational purposes. The availability of drones has led to immoral applications of the technology. Such applications need to be faced with anti-measures and effective detection methods. Therefore, this thesis aims to develop a mobile reconnaissance robot that can detect commercial drones with radar. It describes integrating radar sensors with single-board computers to detect and localise air-bound objects. The finished product aims to be used for educational and exhibition purposes at the Swedish Armed Forces technical school to increase awareness of the technology. / <p>Försvarsmaktens tekniska skola i Halmstad var intressenter för uppsatsen.</p>