Bakirci, Murat2025-03-172025-03-1720250263-22411873-412Xhttps://doi.org/10.1016/j.measurement.2024.116579https://hdl.handle.net/20.500.13099/2021Conventional methods of transportation security, such as fixed security camera surveillance, offer limited coverage and constrained viewing angles. Moreover, the full potential of unmanned systems, widely utilized in various fields, remains underexploited in transportation security. This study integrates Intelligent Transportation Systems (ITS) with Unmanned Aerial Vehicles (UAVs) to address these limitations and propose a comprehensive approach to urban mobility monitoring and control. By enhancing both the software and hardware of a test UAV, the system is transformed into a robust mobile computing platform capable of real-time vehicle detection and traffic monitoring. The UAV's upgraded communication infrastructure enables rapid data transmission to control stations, facilitating timely decision-making. Various size variants of YOLOv8 are tested for their suitability for real-time applications, with the YOLOv8n variant proving particularly effective, achieving faster detection times and a precision rate of 0.706 in vehicle detection tasks on the Jetson Nano platform. YOLOv8n was also compared against various variants of the state-of-the-art algorithms YOLOv9, YOLOv10, and YOLO11. While it did not achieve the highest precision, the difference was minor, and it demonstrated the best balance between precision and recall. The system reliably tracks specific vehicles, providing accurate real-time vehicle trajectories to the control station. Additionally, using the UAV's hovering mode, the study successfully maps traffic density at critical transportation nodes, ensuring consistent monitoring and control.eninfo:eu-repo/semantics/closedAccessUrban mobilityVehicle detectionIntelligent transportation systemsUAVMobile computing platformYOLOv8nYOLO11Article10.1016/j.measurement.2024.116579244Q1WOS:0014025429000012-s2.0-85213083249Q3