A smart computer vision system that detects signs of fatigue, eye strain, and microsleep using a standard webcam.
FatiguEye is a real-time fatigue detection system based on eye tracking and facial landmark analysis.
It helps identify early signs of drowsiness by measuring:
- 👁️ Eye Aspect Ratio (EAR)
- 🔁 Blink frequency
- ⏱️ Prolonged eyelid closure
⚠️ Microsleep events
Ideal for driver monitoring, industrial safety, or ergonomic fatigue prevention.
FatiguEye uses MediaPipe Face Mesh to extract eye landmarks, and computes the EAR (Eye Aspect Ratio) on each video frame.
- 🎥 Webcam feed is captured in real-time
- 🧠 Facial landmarks (eyes) are detected with Mediapipe
- 📏 EAR is calculated per eye
- 🧮 Blink count and eye closure duration are analyzed
- 🔔 Fatigue alerts are raised (visual + audio)
| Tech | Description |
|---|---|
| Python | Core language |
| OpenCV | Webcam video processing + overlays |
| MediaPipe | Face mesh & eye landmark detection |
| NumPy | EAR computation |
| Streamlit | Live web dashboard |
| winsound | Audio alert (Windows only) |
git clone https://github.com/Tirovo/fatigueye.git
cd fatigueye
python -m venv venv
source venv/bin/activate # Or venv\Scripts\activate on Windows
pip install -r requirements.txt