Amateur Drone Research Articles

Vision-Based Amateur Drone Detection: Performance Analysis of New Approaches in Deep Learning

Vision-Based Amateur Drone Detection: Performance Analysis of New Approaches in Deep Learning

An automated accurate sound-based amateur drone detection method based on skinny pattern

Nowadays, the popularity of amateur drones (ADr) has increased marginally, and many research areas, such as machine learning, security systems, and the military industry, have been interested in ADrs. The prime goals of this paper are to present a new sound dataset for ADr detection and present an accurate classification model for ADr detection. This research proposes a novel classification model using the proposed skinny pattern and iterative neighborhood component analysis (INCA) feature selector using ADr sounds. The skinny pattern is a new nonlinear pattern that uses the skinny cipher's substitution box (S-Box). Tunable Q-factor wavelet transform (TQWT) and skinny pattern are used together to extract features in multilevel. The most informative features from the generated features are selected using the INCA selector. 16 classifiers were used in five categories to illustrate the general success of the presented model, and these categories are decision tree (DT), discriminant (D), support vector machine (SVM), k nearest neighborhood (kNN), and ensemble classifiers (EC). An ADr sound dataset was collected, and the presented skinny pattern and INCA-based model are applied to the gathered sound dataset to implement the presented model. The best classification accuracy was calculated as 99.72% using Fine kNN. The proposed model was also compared to other ADr detection/classification models, and it outperformed. These obtained results demonstrate the success of the skinny pattern and INCA-based ADr detection model.

An Investigation of the Reliability of Different Types of Sensors in the Real-Time Vibration-Based Anomaly Inspection in Drone.

Early drone anomaly inspection is vital to ensure the drone’s safety and effectiveness. This process is often overlooked, especially by amateur drone pilots; however, some faulty conditions are difficult to notice by the naked eye or discover, even though the drone inspection process has been conducted; therefore, a real-time early drone inspection approach based on vibration data is proposed in this study. Firstly, the reliability of several microelectromechanical systems (MEMS) sensors, namely the ADXL335 accelerometer, ADXL 345 accelerometer, ADXL377 accelerometer, and SW420 vibration sensor in detecting faulty conditions, were tested and compared. The experimental results demonstrated that the vibration parameter measured using ADXL335 and ADXL345 accelerometers are the best choice as most of the faulty conditions can be detected, in contrast to other MEMS sensors. The output produced from the anomaly inspection algorithm is then converted to the “Healthy” or “Faulty” state, which is displayed in a mobile application for easy monitoring.

Development of a new Light-Weight Convolutional Neural Network for acoustic-based amateur drone detection

In recent years, interest in autonomous Unmanned Aerial Vehicles (UAVs) has increased, especially due to their use in different application areas, together with their ability to operate autonomously. The widespread use of UAVs also brings serious security threats. The prevention should be taken for early detection of UAVs-based threats, especially in military areas and governmental buildings, where high-level security is required. In this study, a sound processing algorithm with a new Light-Weight Convolutional Neural Network (LWCNN) model is proposed for the detection of UAVs, by distinguishing them from air noises, animal noises, and vehicle noises in environments with high spatial noise density. The most important advantages of the proposed model are its low complexity and a small number of parameters, as well as its high classification performance. The Mel Frequency Spectrum coefficients are applied to extract the sound features required to distinguish the sounds of UAVs. The features obtained from the proposed LWCNN model are used as input to the Support Vector Machines (SVM), where different objects are classified. With the proposed method, it is possible to detect UAVs and distinguish them from different sounds such as birds, airplanes, helicopters, background noises, and storms. Experimental results show that the proposed methodology obtains better results than other methods proposed in the literature.

Optimising Land Consolidation by Implementing UAV Technology

The increase in population and the growing demand for food that accompanies it drive the need to achieve sustainable agriculture. Technological progress and methodological novelties provide tools that may support the processes of improving the spatial structure of agricultural lands, as well as their management. One of the examples may be the application of photogrammetric and remote-sensing products to facilitate land consolidation. In the following paper, the systematised procedure of conduct is investigated to determine the moments at which these products could be adopted. In identifying the possibilities for implementing the abovementioned tools, we analyse the legal regulations governing the process and the literature on the subject, as well as some practical examples encountered in surveying practice. In addition, the usefulness of such geospatial products is tested on data gathered during an exemplary UAV flight. We then investigate the issues with implementing the abovementioned tools and assess their advantages and disadvantages in smart agriculture. The research proves that reliable elaboration of the consolidation project concept is critical for its correct realisation, while modern measurement methods providing efficient, up-to-date, factual data facilitate the procedures and support rational decision making. Moreover, they enable us to ensure the necessary accuracy of the data for the scope of the land use and avoid analysing a compilation of several cartographic materials concerning the surveyed object. In the present study, the RMSExyz mean square error at the control points for the orthomosaic, generated using the Matrice 210 RTK v2 professional flying platform, is 5.6 cm, while for the orthomosaic created from images from the amateur drone Mavic 2 Pro RMSExyz, it is 9.2 cm. The results obtained also indicate the usefulness of low-budget drones during the land consolidation process.

An Automated Accurate Sound-Based Amateur Drone Detection Method Based on Skinny Pattern

An Automated Accurate Sound-Based Amateur Drone Detection Method Based on Skinny Pattern

An Automated Accurate Sound-Based Amateur Drone Detection Method Based on Skinny Pattern

An Automated Accurate Sound-Based Amateur Drone Detection Method Based on Skinny Pattern

An Automated Accurate Sound-Based Amateur Drone Detection Method Based on Skinny Pattern

An Automated Accurate Sound-Based Amateur Drone Detection Method Based on Skinny Pattern

A guide to novice for proper selection of the components of drone for specific applications

Since the introduction of drone technology, it has caught the attention of researchers across the world for utilizing it in different areas. But as it is known the same drone cannot be used for all the applications as each and every application has its own unique challenges and requirements. The existing literature emphasizes the use of sophisticated drones for certain applications. But if a novice wants to prepare a tailor made drone for a specific application it is a difficult task for them. This work is an attempt to address the challenges and requirements of drones namely for, agriculture, healthcare, firefighting, and food delivery applications. Which in turn shall be helpful in identifying the right components required for an application? It begins with the statement of various applications of drones and thereby defining the requirements for each application. As per the requirements vigorous calculations are imparted to choose the right combination of electronic components keeping minimal cost in mind. This work could guide any amateur drone enthusiasts to proceed with making their own drone for recreational or commercial purposes. Even the drone entrepreneurs can build their enterprise just by using the output of this manuscript with their expertise or research and development team through proper unmanned vehicle lab facilities.

An Automated Accurate Sound-Based Amateur Drone Detection Method Based on Skinny Pattern

An Automated Accurate Sound-Based Amateur Drone Detection Method Based on Skinny Pattern

Beyond drone vision: the embodied telepresence of first-person-view drone flight

ABSTRACT Drones, no matter whether military or civilian, have been widely theorized as a media technology. An important notion for conceptualizing the particular scopic regimes of drones has been “drone vision.” Recently, some scholars have suggested to shift the attention toward the “more-than-optical”, “more-than-visual” or “synesthetic” characteristics of drones. Drawing on a (post-)phenomenological reading of First Person View (FPV) drone flight, this article asks, firstly, how the “more-than” component in the notion “more-than-optical” emerges in the embodied actions and perceptions of amateur drone users, and secondly, how these experiences might be conceptualized. As a key concept for my reflection, I take up the notion of telepresence, which emerged in the discourse on remote control and teleoperation technologies and finally found its way as an artistic strategy and popular motif into our contemporary socio-technical imaginaries. This article suggests first steps toward an empirical and theoretical exploration of the heterogeneous technogene sensations of drones.

An Acoustic-Based Surveillance System for Amateur Drones Detection and Localization

Due to cost reduction and device miniaturization, amateur drones are now widely used in numerous civilian and commercial applications. However, the abuse of amateur drones has resulted in emerging threats to personal privacy and public security. To alleviate these threats, we design an acoustic-based surveillance system, which can achieve the capacity of amateur drones detection and localization with 24/7 (24 hours per day and 7 days per week under normal circumstances) availability. In the designed system, a detection fusion algorithm and a TDOA estimation algorithm based on the Bayesian filter are applied to improve the performance of drone detection and localization. Field experiments are carried out, and the results demonstrate that the designed system can detect and locate an amateur drone in real time with high accuracy and 24/7 availability.

Machine Learning Inspired Sound-Based Amateur Drone Detection for Public Safety Applications

In recent years, popularity of unmanned air vehicles enormously increased due to their autonomous moving capability and applications in various domains. This also results in some serious security threats, that needs proper investigation and timely detection of the amateur drones (ADr) to protect the security sensitive institutions. In this paper, we propose the novel machine learning (ML) framework for detection and classification of ADr sounds out of the various sounds like bird, airplanes, and thunderstorm in the noisy environment. To extract the necessary features from ADr sound, Mel frequency cepstral coefficients (MFCC), and linear predictive cepstral coefficients (LPCC) feature extraction techniques are implemented. After feature extraction, support vector machines (SVM) with various kernels are adopted to accurately classify these sounds. The experimental results verify that SVM cubic kernel with MFCC outperform LPCC method by achieving around 96.7% accuracy for ADr detection. Moreover, the results verified that the proposed ML scheme has more than 17% detection accuracy, compared with correlation-based drone sound detection scheme that ignores ML prediction.

Special issue on amateur drone and UAV communications and networks

The development of the mini-drones, formally called unmanned air vehicles (UAVs) have captured the attention of hobbyists and the investors due to their enormous applications. Drones have endless commercial applications as well due to the irrelatively small size and ability to fly without an on-board pilot such as in agriculture, photography, surveillance, and numerous public services. The use of drones for achieving high speed wireless communication is one of the most significant applications for next generation communication system (5G). Indeed, drone-based communication network offers encouraging solution to provide wireless connectivity for devices without infrastructure coverage due to e.g., severe shadowing by urban or mountainous terrain, or damage to the communication infrastructure caused by natural disasters.

Amateur Drone Surveillance: Applications, Architectures, Enabling Technologies, and Public Safety Issues: Part 2

The nine articles in this special section focus on amateur drone surveillance system implementation issues such as software-defined radio solutions for amateur drone surveillance, context-aware amateur drone localization, and moving target surveillance based on a cooperative drone network. The drone can be the key enabler to provide high-speed wireless communication for fifth-generation systems. But its deployment poses several public safety threats to national institutions such as atomic plants, historical places, and presidential houses because it may carry explosive and destructive chemicals or surveillance equipment. To cope with these security threats, surveillance drone deployment is required for counter-surveillance of amateur drones. The main motivation of deploying surveillance drones is to keep an eye on the amateur drones, which may lead to serious disasters if no precautionary measures are taken. The Feature Topic articles in this issue highlight the most recent advances in amateur drone survelliance system implementation issues such as software- defined radio solutions for amateur drone surveillance, context-aware amateur drone localization, and moving target surveillance based on a cooperative drones network.

Unauthorized Amateur UAV Detection Based on WiFi Statistical Fingerprint Analysis

Amateur drones are enjoying great popularity in recent years due to the wide commercial diffusion of small, rather low-cost devices. More and more user-friendly, easy-to-pilot aerial and terrestrial drones are available off the shelf, and people can even remotely pilot them using their smartphones. This situation brings up the problem of keeping unauthorized drones away from private or sensitive areas, where they can represent a personal or public threat. With this motivation, after a survey of the existing solutions, we propose a WiFi-based approach aimed at detecting nearby aerial or terrestrial devices by performing statistical fingerprint analysis on wireless traffic. This novel detection technique, tested in a variety of real-life scenarios, proved able to efficiently detect and identify intruder drones in all the considered experimental setups, making it a promising unmanned aerial vehicle detection approach in the framework of amateur drone surveillance.

Software Defined Radio and Wireless Acoustic Networking for Amateur Drone Surveillance

The advancement of the micro-electro-mechanical sensory industry and open source autopilot stacks, have dramatically reduced the cost and difficulty of making highly maneuverable UAVs. Such ease in flying drones has caused concerns about privacy, public safety, and security. One of the major threats is inadequate control of flying small drones over sensitive areas. In this research, we address this problem through a dual approach: detection and eviction. We propose a distributed system to identify the appearance and the approximate position of unwelcome drones using a wireless acoustic sensor network and machine learning algorithms. Next, we integrate software defined radio transceivers along with machine learning algorithm into a framework to specify and decode the UAV's telemetry protocols. Using decoded information, we can then send control commands to evict the trespassing drone away before sending aggressive surveillance UAVs.

Amateur Drone Monitoring: State-of-the-Art Architectures, Key Enabling Technologies, and Future Research Directions

The UAV or mini-drones equipped with sensors are becoming increasingly popular for various commercial, industrial, and public-safety applications. However, drones with uncontrolled deployment pose challenges for highly security-sensitive areas such as a President's house, nuclear plants, and commercial areas because they can be used unlawfully. In this article, to cope with security-sensitive challenges, we propose point-to-point and FANET architectures to assist the efficient deployment of MDrs. To capture an ADr, an MDr must have the capability to efficiently and quickly detect, track, jam, and hunt the ADr. We discuss the capabilities of the existing detection, tracking, localization, and routing schemes, and also present the limitations of these schemes as further research challenges. Moreover, the future challenges related to co-channel interference, channel model design, and cooperative schemes are discussed. Our findings indicate that MDr deployment is necessary for the care of ADrs, and intensive research and development is required to fill the gaps in the existing technologies.

An Amateur Drone Surveillance System Based on the Cognitive Internet of Things

Drones, also known as mini-unmanned aerial vehicles, have attracted increasing attention due to their boundless applications in communications, photography, agriculture, surveillance, and numerous public services. However, the deployment of amateur drones poses various safety, security, and privacy threats. To cope with these challenges, amateur drone surveillance has become a very important but largely unexplored topic. In this article, we first present a brief survey to show the stateof- the-art studies on amateur drone surveillance. Then we propose a vision, named Dragnet, tailoring the recently emerging Cognitive Internet of Things framework for amateur drone surveillance. Next, we discuss the key enabling techniques for Dragnet in detail, accompanied by the technical challenges and open issues. Furthermore, we provide an exemplary case study on the detection and classification of authorized and unauthorized amateur drones, where, for example, an important event is being held and only authorized drones are allowed to fly over.

Amateur Drone Surveillance: Applications, Architectures, Enabling Technologies, and Public Safety Issues: Part 1

The articles in this special section present the most recent advances in amateur drone surveillance network architecture and technologies. The advancement in communication, networking and sensing technologies has attracted researchers, hobbyists, and investors to deploy mini-drones, a.k.a. unmanned air vehicles (UAVs). Drones have boundless viable applications due to their small size and ability to fly without an on-board pilot such as in agriculture, surveillance, and numerous public services. The use of drones for achieving high speed wireless communication is one of the most significant applications for next-generation communication systems (5G). However, their deployment poses several public safety threats to national institutions such as atomic plants, historic places, and the homes of public officials because of their ability to carry explosives and other destructive chemicals. To cope with these security threats, the deployment of surveillance drones is required to monitor amateur drones. The main motivation of deploying surveillance drones is to keep an eye on amateur drones, which can cause serious disasters if no precautionary measures are taken on time. The increasing use of surveillance drones presents challenges such as robust detection, tracking, intruder localization, and jamming. The accuracy of detection is a basic requirement of the system. In general, accurate detection is time-consuming. In fact, a precise moving object detection method makes tracking more reliable and faster, and supports correct classification, which is quite important for surveillance drones to be successful.