Classroom Behavior Monitoring with YOLO An Empirical Study in Higher Education Settings
For higher education administrators and instructors, this work provides an automated tool to monitor student engagement, addressing scalability limitations of traditional observation methods.
This study introduces a real-world classroom video dataset (BAV-Classroom) with nine behavioral categories and evaluates state-of-the-art computer vision models, finding YOLOv11 achieves the best performance. Results show student concentration decreases notably during the final part of lectures, demonstrating the feasibility of automated classroom monitoring.
Classroom behavior monitoring plays a vital role in evaluating student engagement and improving teaching effectiveness. Traditional observation methods remain subjective and lack scalability. This study introduces a real-world dataset of classroom videos collected at the Banking Academy of Vietnam (BAV-Classroom dataset), annotated with nine distinctive behavioral categories. State-of-the-art Computer Vision models were evaluated and compared, with YOLOv11 achieving the best performance. Experimental results indicate that students' concentration often decreases notably during the final part of lectures, highlighting challenges in sustaining engagement. Our findings demonstrate the feasibility of applying computer vision for automated classroom monitoring, providing valuable insights for academic quality management.