Zoom Classroom Engagement and Attention Detection System

This research presents a Zoom Classroom engagement and attention detection system, designed to enhance remote teaching and learning experiences. In the wake of the COVID-19 Pandemic, online Education has become the norm, and ensuring student engagement and attention in virtual classrooms has become a significant challenge. The proposed system aims to address these challenges by leveraging computer vision and YOLO V8. YOLO V8 is a deep learning model that falls under Convolutional Neural Networks (CNNs) and it is trained on large dataset to learn detecting and classifying objects in images. By analyzing video and audio streams, the system can detect students' engagement levels and attention spans in real time. To achieve this, various features and cues are extracted from students' facial expressions, body language, and speech patterns. These features are then fed into a YOLO v8 model, which predicts the level of engagement and attention for each student. Key features of the system include the ability to track students' eye movements, head orientations, and facial expressions to assess focus and attention. In addition, speech analysis algorithms are employed to detect instances of disengagement or distraction based on tone and content. The system can provide visualizations and summaries of students' engagement levels for educators, allowing them to adapt their teaching strategies accordingly. Through this Zoom classroom engagement and attention detection system, educators can identify students who may be struggling or disengaged, enabling proactive interventions and personalized support.