<![CDATA[Objective: To develop and evaluate an artificial intelligence (AI)-based traffic counting system using the YOLO (You Only Look Once) deep learning algorithm to provide accurate and real-time traffic volume data for urban transportation management. Method: Employing a deep learning approach by implementing the YOLO algorithm for vehicle detection and traffic counting. Traffic video data from road objects in Surakarta City were processed to identify and classify various vehicle types. The AI-generated traffic counting results were then compared with manual traffic survey data to assess the system’s accuracy and effectiveness. Results: The findings indicate that the proposed AI-based traffic counting system can accurately detect and classify multiple vehicle categories, including cars, motorcycles, trucks, buses, bicycles, and Bajaj. The traffic-counting data produced by the system were highly readable and reliable. Comparison with manual traffic surveys showed that the AI-generated results were very similar while requiring significantly less time and human resources. The system achieved nearly 100% consistency with the available secondary traffic volume data, demonstrating its effectiveness in monitoring urban traffic conditions. Novelty: Application of the YOLO deep learning algorithm for automated traffic counting in the urban road environment of Surakarta City. The proposed system provides a practical and efficient alternative to conventional manual traffic surveys by delivering accurate, real-time traffic data with minimal human intervention, thereby supporting more effective urban transportation planning and management. These contributions are also relevant to SDG 11 (Sustainable Cities and Communities) by enabling data-driven traffic monitoring and facilitating smarter, more sustainable urban mobility management.]]>
Copyrights © 2026
