An Amateur Drone Surveillance System Based on Cognitive Internet of Things (1711.10738v1)

Abstract: 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 becomes a very important but largely unexplored topic. In this article, we firstly present a brief survey to show the state-of-the-art studies on amateur drone surveillance. Then, we propose a vision, named Dragnet, by tailoring the recent emerging cognitive internet of things framework for amateur drone surveillance. Next, we discuss the key enabling techniques for Dragnet in details, accompanied with 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.

An Overview of Amateur Drone Surveillance Using Cognitive IoT

The rise of amateur drones, identified as mini-unmanned aerial vehicles (UAVs), presents significant potential across various applications such as communications, agriculture, and public services. However, their proliferation also brings forth various safety, security, and privacy concerns. The paper "An Amateur Drone Surveillance System Based on Cognitive Internet of Things" addresses these issues by proposing a surveillance system designed specifically for amateur drones. The system, termed "Dragnet," leverages the cognitive Internet of Things (IoT) framework to enhance modern anti-drone methodologies.

State-of-the-Art in Amateur Drone Surveillance

The current landscape of anti-drone technologies, although primarily used in military contexts, forms a foundation for amateur drone surveillance. The paper categorizes existing anti-drone measures into four major areas: warning, spoofing, jamming, and mitigation. A variety of systems are available that utilize combinations of these techniques. For instance, the Anti-UAV Defense System (AUDS) integrates radar and electro-optical video for target detection and tracking. Despite their capabilities, these systems face limitations, such as the difficulty in detecting small-sized amateur drones and the low generalization of technologies designed for specific environments.

Dragnet: A Cognitive IoT Approach

The paper introduces "Dragnet," a comprehensive surveillance system leveraging the cognitive IoT framework that augments traditional IoT capabilities with cognitive functions. Dragnet establishes an ecosystem where both machine intelligence and human crowd-sensing can collaboratively detect and counteract rogue drones. By implementing a fog-to-cloud computing architecture, the system jointly uses edge (fog) computational resources, such as local radars and cameras integrated on edge nodes, and centralized cloud resources to process vast amounts of surveillance data. Ultimately, this enables real-time decision-making and supports intelligent actions against unauthorized drones.

Key Technologies for Dragnet

The paper identifies several technologies essential for an effective amateur drone surveillance system:

• Detection: The integration of multiple sensor modalities to detect drones, despite environmental challenges and varying drone types. Techniques like heterogeneous data fusion and quickest detection enhance the precision and speed of reaction.
• Localization: For effective response, accurate 3D localization of drones is necessary. This component involves advanced signal processing techniques to estimate the position of drones detected.
• Tracking: Ongoing monitoring of drone trajectories is crucial for predicting future movements and behaviors.
• Control: Once a drone is confirmed as unauthorized, the system must be capable of deploying appropriate countermeasures, ranging from benign redirection to more aggressive interventions.

Implications and Future Perspectives

The implications of this research are far-reaching within both practical and theoretical domains. Practically, Dragnet provides a robust framework for maintaining airspace security over sensitive areas such as airports and government installations. Theoretically, it paves the way for further developments in cognitive IoT, exemplifying how intelligent systems can be deployed for sophisticated environmental monitoring tasks. The integration of fog-to-cloud architectures further emphasizes the shift toward decentralized yet connected intelligence processing.

The Dragnet framework lays a groundwork for future explorations into more nuanced cognitive IoT applications, likely enhancing capabilities such as predictive analytics and autonomous decision-making in surveillance systems. As drone technology continues to evolve, so too must systems like Dragnet advance in intelligence and adaptability, maintaining a balance between the burgeoning opportunities presented by UAVs and the mitigation of their associated risks.