Urban traffic congestion is a major challenge in modern transportation management, while conventional monitoring systems remain limited in providing transparent and easily understandable information. This study aims to analyze the use of Artificial Intelligence to enhance the transparency of road congestion analysis through visual interpretation. Traffic imagery data was obtained from CCTV cameras at urban intersections and processed using the YOLOv8 model to detect vehicles and visualize traffic conditions. Subsequently, heatmap visualizations and Explainable Artificial Intelligence approaches were employed to clarify areas of vehicle concentration. The results show that the system can identify vehicle distribution patterns and present a visual representation of density based on concentration and object categories. This visualization provides more transparent, informative, and intuitive information regarding traffic conditions. Thus, this approach has the potential to support the development of smart transportation systems and data-driven traffic monitoring in urban environments effectively, accurately, and sustainably.
Copyrights © 2026