Abstract
Road infrastructure elements like guardrails, bollards, delineators, and traffic signs are critical for traffic safety but are significantly underrepresented in existing driving datasets, which primarily focus on vehicles and pedestrians. To address this crucial gap, we introduce DORIE (Dataset of Road Infrastructure Elements), a novel, high-resolution dataset specifically curated for real-time patrol vehicle monitoring along the A2 motorway in Spain. DORIE features 938 manually annotated images containing over 6800 object instances across ten safety-critical categories, including both static infrastructure and dynamic traffic participants. To establish a robust performance benchmark, we conducted an extensive evaluation of the YOLO family of detectors (versions 8, 11, and 12) across multiple scales and input resolutions. The results show that larger YOLO models and higher-resolution inputs yield up to 40% improvement in mean Average Precision (mAP) compared to smaller architectures, particularly for small and visually diverse classes such as traffic signs and bollards. The inference latency ranged between 5.7 and 245.2 ms per frame, illustrating the trade-off between detection accuracy and processing speed relevant to real-time operation. By releasing DORIE with detailed annotations and quantitative YOLO-based baselines, we provide a verifiable and reproducible resource to advance research in infrastructure monitoring and support the development of intelligent road safety and maintenance systems.