Practical overview
When it fits
Use it as a code example or starting point when exploring eye-based drowsiness detection and driver alerting from video.
Who it is for
- Developers studying or adapting a driver-drowsiness monitoring prototype.
- Learners exploring facial eye landmarks and threshold-based computer vision.
Documented uses
- Process a real-time video stream to monitor eye closure.
- Generate an audible alert when the eye aspect ratio is below 0.25 for 20 consecutive frames.
- Study an example that represents each eye with six facial landmark coordinates.
Requirements & limits
The public GitHub repository is MIT-licensed. Its README specifies Python 2.7 or higher and lists OpenCV, imutils, dlib and scipy.
- The stated alert condition is an eye aspect ratio below 0.25 across 20 consecutive frames.
- The documented run command is python Drowsiness_Detection.py.
- The README does not describe installation, camera configuration or calibration steps.
Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.
Run the drowsiness detection script
Process a real-time video stream and generate an alert when the documented eye-closure threshold is met.
Before you start
- Python 2.7 or higher.
- The listed dependencies: cv2, imutils, dlib, and scipy.
- The project script Drowsiness_Detection.py.
Steps
Ensure the listed dependencies are available to the Python environment.
Run the command below.
python Drowsiness_Detection.pyThe program evaluates the eye aspect ratio across 20 consecutive frames; the README says an alert is generated when the ratio is below 0.25.
Expected outcome
The program is described as detecting drowsiness in a real-time video stream and playing an alarm when the user appears drowsy.
Guide limitations
- The README does not explain dependency installation or video input configuration.
- The README does not specify the camera requirements or provide a separate verification procedure.
- This guidance reflects the project documentation and does not establish suitability as a safety system.
Sources & review
Source record details
- Source availability
- Active
- Sources checked
- 15 October 2026
- Original website title
- akshaybahadur21/Drowsiness_Detection · Official homepage title · retained in its source language