Real Time Attention Monitoring System in Classrooms

Abstract

 A real-time attention monitoring system in classrooms focuses on understanding how attentive students are during lectures using modern technology. It combines computer vision and machine learning to observe student behavior without interrupting the class. Cameras capture live video, and the system analyzes facial expressions, eye movement, and posture to detect attention levels. Instead of manual observation, the system automatically identifies whether students are focused or distracted. The collected data is processed instantly, allowing teachers to get real-time feedback on classroom engagement. This helps in identifying students who may be struggling to concentrate. A dashboard provides a simple visualization of attention levels, making it easier for teachers to adjust their teaching methods. At the same time, privacy and data protection are carefully considered while designing the system. It can be implemented in different classroom sizes and supports smart classroom environments. Overall, this system helps create a more interactive and effective learning experience by bridging the gap between teaching and student engagement.

1.    Classroom Behavior Recognition Using Computer Vision:     A    Systematic Review

https://doi.org/10.3390/s25020373MDPI

2.    Real-Time Attention Monitoring System for Classroom: A Deep Learning Approach for Student’s Behavior Recognition

https://doi.org/10.3390/bdcc7010048MDPI

3.    Real-time Monitoring of Students’ Attention in Classroom using Transfer Learning

https://doi.org/10.56201/ijcsmt.v10.no2.2024.pg170.178

4.    Predicting students’ attention in the classroom from Kinect facial and body features Available at: https://jivpeurasipjournals.springeropen.com/articles/10.1186/s13 640-017-0228-8

5.      Detecting Student Engagement in Classrooms for   Intelligent Tutoring Systems October 2019 Available at:

https://www.researchgate.net/publication/338942125_

6.      Y. Li, G. R. Lan, Z. Li, X. Zhong and F. Han, “Real-time Gaze Tracking via Head–Eye Cues on Head-Mounted Displays”,IEEE Trans. on Mobile Computing, 2024.https://doi.org/10.1109/TMC.2024.3425928

7.      S. Maiti and A. Gupta, “LocalEyenet: Deep Attention Framework for Localization of Eyes”, arXiv preprint, 2023.
 https://arxiv.org/abs/2303.12728

8.      R. Daza, L. F. Gomez, A. Morales, J. Fierrez, R. Tolosana, R. Cobos and J. Ortega-Garcia, “MATT: Multimodal Attention Level Estimation for E-learning Platforms”, arXiv preprint, 2023. https://arxiv.org/abs/2301.09174

9.      J. Oh et al., “Improved Feature-Based Gaze Estimation Using Self-Attention Modules”, Sensors, 2022.
https://www.mdpi.com/1424-8220/22/11/4026

10.  K. Shen et al., “Model-Based 3D Gaze Estimation Using a TOF Camera”, PMC (NCBI), 2024. https://www.ncbi.nlm.nih.gov/articles/PMC10891597