Internet of Things-enabled unmanned aerial vehicles for real-time traffic mobility analysis in smart cities

In modern traffic monitoring and mobility analysis, unmanned aerial vehicles (UAVs) have proven to be invaluable, overcoming the limitations of stationary surveillance cameras by offering dynamic, adaptable coverage. However, the full computational and communication potential of UAVs remains largely untapped in existing studies. This research presents an advanced UAV-based traffic monitoring system, integrating real-time image processing and Internet-of-Things (IoT)-enabled data transmission for enhanced mobility assessment. The UAV platform incorporates a high-performance neural accelerator for onboard image processing and IoT-compatible communication modules, transforming it into an autonomous, intelligent, and highly efficient traffic analysis tool. By leveraging the YOLOv8n object detection algorithm, the UAV achieves an 88% average success rate in real-time vehicle detection, enabling precise spatial mobility mapping along predefined flight routes. A comparative analysis was conducted against the latest YOLO variants, including YOLOv9t, YOLOv10n, and YOLOv11n, demonstrating that YOLOv8n provides the best trade-off between accuracy and real-time processing efficiency for UAV-based mobility monitoring. Unlike traditional methods that rely on batch processing, this system facilitates immediate data transmission to relevant regulatory bodies, and IoT networks, enabling responsive traffic management and decision-making. The study also underscores the transformative potential of UAVs as mobile computing and communication platforms, advocating for their broader adoption in real-time traffic mobility analysis within smart city infrastructures.