Skip to content
/ Drooz Public
forked from Pulkit-100/Drooz_

Drowsiness Detection System in Django

Notifications You must be signed in to change notification settings

nitin10s/Drooz

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

9 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Preface

Drowsiness is a condition which diminishes the awareness caused by the absence of rest or weariness. Because of weariness, driver lose their control which may divert them from the street and prompts serious mishaps. Basically these mishaps may because of the driver tired condition. Driving continuosly for quite a while prompts tiredness and make them to lost their awareness. Due to substantial increment in the number of mischances day by day which makes a major issues.

Driver drowsiness detection is a car safety Technology which helps prevent accidents caused by the driver getting drowsy. Various studies have suggested that around 20% of all road accidents are fatigue-related, up to 50% on certain roads Some of the current systems learn driver patterns and can detect when a driver is becoming drowsy.

Solution

The goal of this project is to monitor driver's exhaustion progressively. One of the identification procedure is Percentage of squinting of eyes. Here we utilize a system totally in view of the development of eyes. The perception of eye development is essentially in view of the driver's condition.

As of now, a threshold hard-coded EAR is fed to the system that is used to detect if the user is drowsy or not which is medically incorrect. The fatigue level should be monitored on various parameters like:

  1. Percentage Long Closure
  2. Blink Total Duration
  3. Inter-Event Duration

Capture

Implementation

  • Awake state
    

    WhatsApp Image 2020-05-20 at 11 01 25 PM

  • Drowsy state
    

    WhatsApp Image 2020-05-20 at 11 01 12 PM

About

Drowsiness Detection System in Django

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • JavaScript 57.2%
  • CSS 31.3%
  • Python 8.6%
  • HTML 2.9%