Real-Time Student Engagement Monitoring System
DOI:
https://doi.org/10.63856/w6t2sf54Keywords:
Student Engagement, Computer Vision, Artificial Intelligence, Eye Aspect Ratio (EAR), Head Pose Estimation, MediaPipe FaceMesh, Real-Time Monitoring, Streamlit Dashboard, Learning Analytics, Online Education.Abstract
In today’s rapidly evolving educational landscape, digital learning platforms play a vital role in modern education. However, monitoring student engagement during online or hybrid sessions remains a significant challenge. Traditional observation methods are often subjective, time-consuming, and impractical for large classrooms.This project presents a Real-Time Student Engagement Monitoring System that uses Computer Vision and Artificial Intelligence (AI) to automatically detect and analyze student attentiveness. The system captures live video through a standard webcam and utilizes MediaPipe’s FaceMesh model to extract facial landmarks. Key parameters such as Eye Aspect Ratio (EAR) and head yaw angle are computed to classify engagement levels into three categories: Attentive, Confused, and Distracted.An interactive Streamlit dashboard displays real-time analytics, including engagement percentage, attention trends, and time-based insights. The system also records engagement data for post-session analysis, enabling educators to identify inattentive periods and improve teaching strategies.This lightweight and cost-effective solution demonstrates the practical application of AI in education. It enhances teaching effectiveness and supports personalized learning by bridging the gap between traditional observation and digital learning environments.
References
1. T. Soukupová and J. Čech, “Real-Time Eye Blink Detection Using Facial Landmarks,” Proceedings of the 21st Computer Vision Winter Workshop, CEUR-WS, 2016.
2. Q. Zhan, J. Li, and Y. Chen, “Attention Detection in Online Learning Using Head Pose Estimation,” IEEE Access, vol. 9, pp. 12245–12253, 2021.
3. S. D’Mello and A. Graesser, “Feeling, Thinking, and Computing with Affect-Aware Learning Technologies,” in The Oxford Handbook of Affective Computing, R. Calvo et al., Eds. Oxford: Oxford University Press, 2015.
4. X. Li, Y. Chen, and Y. Zhao, “Deep Learning-Based Emotion Recognition for Smart Education Systems,” Journal of Educational Technology, vol. 15, no. 2, pp. 45–57, 2020.
5. Google, “MediaPipe Documentation – FaceMesh API.” [Online]. Available: https://developers.google.com/mediapipe.
6. OpenCV, “Open Source Computer Vision Library Documentation.” [Online]. Available: https://docs.opencv.org.
7. Streamlit, “Streamlit for Data Science and Web Apps Documentation.” [Online]. Available: https://docs.streamlit.io
8. NumPy Developers, “NumPy User Guide,” 2023. [Online]. Available: https://numpy.org/doc.
9. Pandas Development Team, “Pandas Documentation: Data Analysis in Python,” 2023. [Online]. Available: https://pandas.pydata.org/docs.
10. Plotly Technologies Inc., “Plotly Python Graphing Library Documentation,” 2023. [Online]. Available: https://plotly.com/python.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 International Journal of Integrative Studies (IJIS)
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
