STM Journals Peer-reviewed research from Consortium e-Learning Network

Trends in Opto-electro & Optical Communication

Driver Drowsiness Detection System Using Python, OpenCV and Raspberry Pi

  1. Venkata Ramana Kammampati
  2. Vyshnavi N
  3. D.V.A.N. Ravi Kumar

Abstract

The number of accidents and deaths can be greatly decreased by using intelligent systems to prevent auto accidents. Human mistakes, such as drowsy driving, are one of the variables that significantly contribute to accidents. The system looks for symptoms of fatigue and sleepiness on a person's face while they are driving. It is based on an image processing technique. This project presents a way to analyze and anticipate driver drowsiness with the help of built-in Python and OpenCV libraries to locate eyes in the video frames. The Eye Aspect Ratio (EAR) is computed for each frame, and the outcome is then assessed against a predefined threshold value. Once tiredness is identified, a warning signal or alarm is activated to alert the driver to get up and stop being drowsy. This approach initially identifies the eyes and subsequently determines whether they are open or closed. The system detects the driver's inactivity if the eyes are closed for a minimum of 10 consecutive frames, determines that the person who drives is dozing off, and sends a warning signal or sets off an alert using the buzzer attached to the Raspberry Pi to wake the person up.

Keywords

Support