<![CDATA[With the rapid pace of urbanization, the number of vehicles traveling between cities has increased significantly. As a result, various traffic-related problems have emerged, such as congestion and excessive vehicle volume and types. To address these issues, comprehensive road data collection is essential. Therefore, in this study, we developed an intelligent traffic monitoring system based on You Only Look Once (YOLO) and a Fuzzy Convolutional Neural Network (CFNN), which records traffic volume and vehicle-type information from the roadway. In this system, YOLO is first used for vehicle detection and combined with a vehicle-counting method to calculate traffic flow. Then, two effective models (CFNN and Vector CFNN) along with a network mapping fusion method are proposed for vehicle classification. In our experiments, the proposed methods achieved an accuracy of 90.45% on a public dataset. On this dataset, the average precision and F-measure (F1) of the proposed YOLO-CFNN and YOLO-VCFNN vehicle classification methods reached 99%, outperforming other approaches. On real highways, the proposed YOLO-CFNN and YOLO-VCFNN methods not only attained high F1-scores for vehicle classification but also demonstrated remarkable accuracy in vehicle counting. Furthermore, the system maintained a detection speed of over 30 frames per second. Thus, the proposed intelligent traffic monitoring system is well-suited for real-time vehicle classification and counting in real-world environments.]]>
