A simple AI-powered Driver Monitoring System that uses MediaPipe Face Mesh and Computer Vision to monitor driver attention and detect signs of drowsiness in real time through a webcam.
👉 https://driver-monitoring-system-ugo8.onrender.com
Detects the driver's face in real time using MediaPipe Face Mesh.
Tracks facial landmarks to analyze driver behavior.
Detects whether the driver is:
- Looking Left
- Looking Right
- Looking Forward
Uses Eye Aspect Ratio (EAR) calculations to identify prolonged eye closure.
Displays driver status and monitoring information instantly.
Provides visual alerts when signs of drowsiness are detected.
- Accesses the webcam feed.
- Detects facial landmarks using MediaPipe Face Mesh.
- Tracks head orientation.
- Calculates Eye Aspect Ratio (EAR).
- Monitors eye closure duration.
- Triggers drowsiness alerts when thresholds are exceeded.
- HTML5
- CSS3
- JavaScript
- Python
- Flask
- MediaPipe Face Mesh
- Render
This project is currently a simple foundational version focusing on:
- Face Detection
- Head Pose Estimation
- Basic Drowsiness Detection
The purpose is to build a solid base before integrating more advanced AI-powered safety features.
Detect driver distraction caused by mobile phone usage.
Identify smoking behavior while driving.
Verify whether the driver is wearing a seatbelt.
Detect additional occupants inside the vehicle.
Improve fatigue detection accuracy.
Generate a safety score based on driver behavior.
Store and display past alerts.
Visualize driver behavior trends.
Add object detection capabilities for advanced monitoring.
Through this project, I learned:
- Real-time webcam processing
- Facial landmark detection
- Eye Aspect Ratio (EAR) analysis
- Computer Vision fundamentals
- Flask web application development
- Frontend and backend integration
- Deployment on Render
Suggestions, feedback, and contributions are welcome.
Feel free to fork the repository and create pull requests.
If you found this project interesting, consider giving it a ⭐ on GitHub.