A Driver Drowsiness Detection Using Machine Learning and OpenCV

EasyChair Preprint 10097

Abstract

The rate at which cars, buses, and other motor vehicle-related accidents have increased in the past few years is becoming mind-bulging and fearful and the majority of these mishaps are drowsy drivers related. This has resulted in the loss of lives, goods, properties, etc. The essence of this analysis is to study and review the previous works on drowsy driving-related accidents, their causes, and measures taken. The gaps in these studies were noted in order to propose and design a new or robust system. This was achieved using various techniques such as image acquisition, computer vision, face detection, feature extraction, training, and classification. The techniques were designed using a universal modeling diagram and mathematical modeling approach based on the requirements for the object-oriented analysis design methodology adopted for the study. The designs were implemented as a prototype system using Python and tested with real-time driving behaviors.

Keyphrases: Data Science, Drowsiness Detection, EAR, OpenCV, Python, computer vision, machine learning

@booklet{EasyChair:10097,
  author    = {Nimesh Sinha and Jasmine Minj and Pooja Patre},
  title     = {A Driver Drowsiness Detection Using Machine Learning and OpenCV},
  howpublished = {EasyChair Preprint 10097},
  year      = {EasyChair, 2023}}