An AI-based smart classroom system that detects and analyzes the attention levels of students in real time using computer vision and machine learning.
The Classroom Attention Monitor is designed to observe student behavior in a classroom environment and classify their attention states such as Listening, Distracted, Sleeping, or Inactive. The system uniquely identifies each student and records behavioral changes using an event-based approach to minimize storage.
- Real-time multi-student monitoring
- Face recognition-based student identification
- Body posture and head orientation analysis
- Eye-gaze and blink detection
- Event-based logging (stores only behavioral changes)
- Individual student attention analytics
- Overall classroom engagement visualization
- Admin-secured dashboard access
| Category | Tools / Libraries |
|---|---|
| Programming | Python |
| Computer Vision | OpenCV, MediaPipe |
| Face Recognition | DeepFace |
| Detection | YOLOv8 |
| Tracking | SORT / DeepSORT |
| Backend | Flask |
| Database | SQLite |
| Visualization | Chart.js |
Camera → Face Detection → Student Identification → Pose & Eye Analysis → Behavior Classification → Event Logging → Dashboard Visualization
- Student-wise attention reports
- Classroom attention percentage
- Attention distribution charts
- Behavioral timeline per student
- Admin-only login system
- ( admin username : admin )
- ( password : admin123 )
- Session-protected dashboard
- Hashed credential storage
- Smart classrooms
- Student engagement analysis
- Academic monitoring
- Educational AI research
Saravanakumar B.Tech – Artificial Intelligence & Data Science
- Mobile dashboard
- Cloud data storage
- Emotion-aware engagement analysis
- Automated teaching feedback
⭐ This project demonstrates the integration of AI, computer vision, and analytics to enhance classroom learning efficiency.