Embry Riddle Aeronautical University
Assessing Computer Vision Based Conflict Detection in UAS Traffic Monitoring Under Secure Communication Constraints
Abstract
dc:description.abstractThe rapid growth of Unmanned Aircraft Systems (UAS) and Advanced Air Mobility (AAM) is creating a new low-altitude airspace ecosystem where drones, air taxis, service suppliers, communication networks, sensors, and ground-based monitoring systems must work together safely. Within this ecosystem, UAS Traffic Management (UTM) is expected to provide a digital framework for coordinating operations beyond traditional air traffic control. However, reliable integration also requires resilient monitoring methods that can detect non-cooperative aircraft, protect communication links, and maintain timely situational awareness under real-world constraints. This dissertation examines how computer vision can support cooperative monitoring systems such as Remote ID and ADS-B by detecting and tracking cooperative and non-cooperative UAS from visual data while accounting for the security and network constraints that affect information delivery. The study establishes a replay-based evaluation framework for assessing perception-derived UAS monitoring outputs, including detection performance, tracking continuity, conflict-detection timeliness, payload expansion, and end-to-end latency. The evaluation uses curated UAS video scenarios across different traffic-density conditions (low, medium and high) and examines system behavior under baseline, security, network-sensitivity, and combined worst-case configurations. Further, the dissertation evaluates how cybersecurity mechanisms, including encryption and authentication, affect monitoring-message size and end-to-end latency. It also analyzes how bandwidth limitation, network latency, packet loss, and combined degraded conditions influence the usefulness of vision-based monitoring outputs. The findings show that security overhead is manageable under favorable communication conditions, while bandwidth limitation and packet loss create more significant challenges for timely and reliable monitoring. The results also demonstrate that combined stress conditions can create greater degradation than individual constraints alone, especially when secured payloads are transmitted over constrained links. Overall, this dissertation provides assessment-driven evidence for integrating computer vision, secure communication, and network-aware design into future UTM and AAM monitoring environments. It highlights the value of vision-based monitoring as an additional awareness layer for cooperative and non-cooperative UAS traffic, while also identifying the communication and security conditions under which such monitoring remains operationally useful.
Degree
thesis:*- Name thesis:degree_name
- Doctor of Philosophy in Electrical Engineering & Computer Science
- Level thesis:degree_level
- Dissertation - Open Access
- Discipline thesis:degree_discipline
- Electrical, Computer, Software, and Systems Engineering
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Issoufou Anaroua, Fadjimata
Subjects
dc:subject × 7- Unmanned Aircraft Systems; UAS Traffic Management; Advanced Air Mobility; Computer Vision; UAS Detection and Tracking; Conflict Detection; Secure Communication; Cybersecurity; Network Constraints; Replay-Based Evaluation
- Aviation Safety and Security
- Digital Communications and Networking
- Multi-Vehicle Systems and Air Traffic Control
- Other Computer Engineering
- Systems and Communications
- Systems Engineering
Identifiers
dc:identifier.*- Repository record dc:identifier
- https://commons.erau.edu/edt/1010