This article presents the design, implementation, and comparative evaluation of two Unmanned Aerial Vehicles (UAV)-based architectures for automated road data acquisition and processing. The first system uses Arduino Portenta H7 boards to perform real-time inference at the edge, reducing connectivity dependency. The second employs ESP32-CAM modules that transmit raw data for remote server-side processing. We experimentally validated and compared both systems in terms of power consumption, latency, and detection accuracy. Results show that the Portenta-based system consumes 36.2% less energy and achieves lower end-to-end latency (10,114 ms vs. 11,032 ms), making it suitable for connectivity-constrained scenarios. Conversely, the ESP32-CAM system is simpler to deploy and allows rapid model updates at the server. These findings provide a reference for Intelligent Transportation System (ITS) deployments requiring scalable, energy-efficient, and flexible road monitoring solutions.

This paper presents a scalable big data infrastructure designed to support traffic optimization and accident prevention in automated and connected road environments. The proposed system integrates real-time data acquisition from heterogeneous sources, including multichannel roadside camera gantries and IoT-enabled vehicle telemetry. The architecture is built upon technologies such as Apache Kafka, Apache Beam, and MongoDB, enabling high-throughput data ingestion, processing, and storage. To validate its performance, two experimental use-cases were developed: one for large-scale image ingestion and another for vehicle telemetry data streaming. The system successfully handled over 48 GB of image data and more than 3.4 million telemetry messages under real-time constraints. Results show that applying data compression techniques—such as resolution reduction and transmission throttling—reduced image upload durations by up to 77%, improving ingestion efficiency without compromising system robustness. These findings demonstrate the feasibility of deploying the proposed infrastructure as a foundational layer for future intelligent traffic management systems.