In the bustling heart of Ankara, Turkey, a groundbreaking development is unfolding that could revolutionize how we maintain our roads and, by extension, our energy infrastructure. Zeynep Demirel, a pioneering researcher from the Department of Civil Engineering at Çankaya University, has introduced an innovative AI-powered web framework called TriRoad AI. This cutting-edge technology is set to transform road damage detection and mapping, offering a scalable solution for smart infrastructure monitoring and preventive maintenance planning in urban environments.
TriRoad AI integrates multiple versions of the You Only Look Once (YOLO) object detection algorithms—specifically YOLOv8 and YOLOv11—to automate the detection of potholes and cracks. The platform’s user-friendly browser interface enables real-time image analysis, confidence-based prediction filtering, and severity-based geolocation mapping using OpenStreetMap. “This technology is a game-changer,” says Demirel. “It addresses current gaps in generalization, accessibility, and practical deployment, offering a scalable solution for smart infrastructure monitoring and preventive maintenance planning in urban environments.”
The experimental evaluation of TriRoad AI was conducted using two datasets: one from online sources and another from field-collected images in Ankara. YOLOv8 achieved a mean accuracy of 88.43% on internet-sourced images, while YOLOv11-B demonstrated higher robustness in challenging field environments with a detection accuracy of 46.15%, and YOLOv8 followed closely with 44.92% on mixed field images. The Gemini AI model, although highly effective in controlled environments (97.64% detection accuracy), exhibited a significant performance drop of up to 80% in complex field scenarios, with its accuracy falling to 18.50%.
The implications of this research are vast, particularly for the energy sector. Efficient detection of road surface defects is vital for timely maintenance and traffic safety, but it also plays a crucial role in the upkeep of energy infrastructure. Roads often serve as conduits for energy pipelines and cables, and their condition can significantly impact the safety and efficiency of these systems. By leveraging AI-powered detection and mapping, energy companies can proactively address potential issues, reducing the risk of costly and dangerous incidents.
Moreover, the fully integrated, browser-based design of TriRoad AI requires no device-specific installation, making it accessible and easy to use. This accessibility is a significant step forward in the field of smart infrastructure monitoring, as it allows for widespread adoption and implementation.
The research, published in the journal ‘Future Transportation’ (translated to English as ‘Future Transportation’), highlights the potential of AI in transforming traditional industries. As Demirel notes, “The proposed platform’s uniqueness lies in its fully integrated, browser-based design, requiring no device-specific installation, and its incorporation of severity classification with interactive geospatial visualization.” This innovation not only addresses current gaps in the market but also paves the way for future developments in AI-driven infrastructure management.
In conclusion, the work of Zeynep Demirel and her team at Çankaya University represents a significant advancement in the field of road damage detection and mapping. By leveraging the power of AI, TriRoad AI offers a scalable, accessible, and effective solution for smart infrastructure monitoring and preventive maintenance planning. As the energy sector continues to evolve, technologies like TriRoad AI will play a crucial role in ensuring the safety, efficiency, and sustainability of our energy infrastructure. The future of road maintenance is here, and it’s powered by AI.