Fatigue Detection

A Desktop based application that can automatically detect driver fatigue in a real-time video stream
and generate an alarm if the eye Aspect ratio is less than 0.25.

Quick Start

To start using Fatigue_Detection application:

Get code

Clone repo via git
https://github.com/fahadfiaz/Fatigue-Detection

Install Dependencies

1. OpenCV
2. immutils
3. dlib
4. scipy
5. Python 2.7 or higher
6. Open Drowsiness_Detection.py file and update the path where Shape_predictor_68_face_landmarks.dat file is located

Algorithm

Each eye is represented by 6 (x, y)-coordinates, starting at the left-corner of the eye (as if you were looking at the person), and then working clockwise around the eye:

Condition for fatigueness

It checks 20 consecutive frames and if the Eye Aspect ratio is lesst than 0.25, Alert is generated.

Relationship

Conclusion

Execution

To run the code, type Fatigue_Detection.py