How Driver Safety AI Works
Learn about the technology, algorithms, and safety measures behind our drowsiness detection system
MediaPipe Face Mesh
Google's state-of-the-art ML solution for detecting 468 facial landmarks in real-time
Next.js 16 & React 19
Modern React framework with server-side rendering and optimal performance
Client-Side Processing
All ML computations run in your browser - no data is sent to servers
Real-Time Analysis
60 FPS processing with optimized algorithms for instant detection
Eye Aspect Ratio (EAR)
Monitors eye openness and blink patterns
The system tracks 6 key landmarks around each eye to calculate the Eye Aspect Ratio. When eyes are open, EAR is high. During drowsiness, eyes partially close, causing EAR to drop below a threshold.
Mouth Aspect Ratio (MAR)
Identifies yawning as a fatigue indicator
Yawning is a strong indicator of drowsiness. The system measures mouth opening by analyzing the vertical distance between lips relative to mouth width. Frequent yawns significantly increase risk score.
Head Pose Estimation
Detects nodding and loss of head control
Drowsy drivers often experience head nodding or drifting. The system analyzes the spatial relationship between nose, eyes, and facial center to estimate head angle and detect abnormal movements.
The risk score is calculated using a weighted combination of all detection factors. Each metric contributes to the overall score, which determines the alert level.