Drowsiness Detection

A Python script to detect driver drowsiness in a real-time and sound an alarm if driver appears to be drowsy.

Setup

Dependencies

pip install -r requirements.txt

Execution

python detect_drowsiness.py \
--shape-predictor shape_predictor_68_face_landmarks.dat \
--alarm alarm.wav

Description

A computer vision system that uses a real-time algorithm to detect eye blinks in a video sequence from a standard camera and sound an alarm if the driver appears to be drowsy.

Algorithm

Given an input image (and normally an ROI that specifies the object of interest), a shape predictor attempts to localize key points of interest along the shape. Detecting facial landmarks is therefore a two step process:

1. Localize the face in the image.
2. Detect the key facial structures on the face ROI.

Now, 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 every video frame, the eye landmarks are detected. The eye aspect ratio (EAR) between height and width of the eye is computed. If the eye aspect ratio value is less than a threshold value for sufficient time, an alarm is set to wake up the driver.

Plots

References

Drowsiness detection with OpenCV

Real-Time Eye Blink Detection using Facial Landmarks