Student Attention Monitoring: An Automated Approach

Active learning plays a pivotal role in promoting effective education within the classroom. The careful examination of student engagement holds significant importance in improving both the learning and teaching processes. Successful learning hinges on the central element of attention. The idea is to use technology to improve teaching method and to support students based on their behaviour and engagement during learning. In this paper, we propose an algorithm that automatically detects the alertness of a student in the classroom environment through face detection, tracking and behavioral analysis. Tracking multiple faces and behavior analysis is carried out with the YOLOv8, ensuring accurate real-time identification. Behavior analysis evaluates eye status and head orientation, contributing to a detailed assessment. The results are compared with YOLOv7.