Real-Time Pothole Detection with Edge Intelligence and Digital Twin in Internet of Vehicles

In intelligent transportation systems (ITSs), computer vision and digital twin (DT) technologies are crucial for enhancing safety and efficiency. High-speed vehicles require timely alert systems to prevent collisions with other vehicles and infrastructure, as even a single misjudgment can lead to severe road accident. Advanced driver-assistance systems (ADASs) and vehicular ad-hoc networks (VANETs) enable vehicle-to-vehicle cooperation, facilitating the exchange of critical alerts. By deploying time-sensitive processing techniques at the edge and utilizing DTs for comprehensive analysis, vehicles can take preemptive actions to avoid accidents. Road potholes contribute to traffic disruptions, the accordion effect, and vehicle damage, making their detection essential. This work explores advanced computer vision techniques implemented at the edge, specifically on vehicles. Roadside units (RSUs) offload DT data, and edge detection results are updated on the DT, providing a control center with accurate road condition information and maintaining a precise virtual replica of the environment. This distributed edge intelligence (DEI) enables rapid decision making with reduced latency while offering a comprehensive view of vehicle lifecycle management through DT data. The proposed algorithm, tested in real time, achieves mean average precision of 85% using YOLOv9t with minimal latency of 3 ms, ensuring effective pothole detection and seamless communication among nearby vehicles.