DRIVER DROWSINESS DETECTION
USING OPENCV PYTHON
RAFEEA HAFIZ RAHMAN
ROLL NO: 5
MTECH CSE
CONTENTS
INTRODUCTION
OBJECTIVES
LITERATURE REVIEW
TECHONOLOGIES
METHODOLOGIES
CONCLUSION
REFERENCES
INTRODUCTION
The number of fatalities on the road due to drowsiness is very high
Drowsiness Detection is the detection of a person to check whether
the person is feeling sleepy while performing a significant task.
This detection has many applications in medical and safety fields.
This detection can be quickly done using “shape predictor face
landmarks” that mark the essential landmarks on the face.
OBJECTIVES
The design aims to achieve the following
The purpose of this is to look at the physical goods of prostration
and doziness
To produce a system that detects prostration and doziness by
closing eyes and yawning
LITERATURE REVIEW
PAPER 1:
Camera based Drowsiness Reference for Driver State Classitcation
under Real Driving Conditions” by Fabian Friedrichs and Bin Yang
To develop warning systems that detect reduced vigilance based on the
behavior of driving, a reliable and accurate drowsiness reference is
necessary
in this paper the performance of the latest eye tracking based invehicle
fatigue prediction measures are evaluated.
These measures are assessed statistically and by a classitcation method
based on a large dataset of 90 hours of real road drives.
The results show that eye-tracking based drowsiness detection works well
for some drivers as long as the blinks detection works properly
Paper 2:
“Extracting Driver’s Facial Features During Driving ”by M. Wang, H. P. Chou,
C. F. Hsu, S. W. Chen
A vision system for monitoring driver's facial features is discussed here.
To begin with, the driver's face is located in the input video sequence
Then it is tracked over the subsequent images.
The facial features of eyes, mouth and head are kept detecting in the
course of face tracking
Feature detection and tracking are performed in parallel, so that the
precise can be improved
.
TECHONOLOGIES
Opencv:
Opencv provides framework in which we can work with images and
videos
we will be using OpenCV for gathering the images from webcam and
feed them into a Deep Learning model which will classify whether the
person's eyes are 'Open' or 'Closed'.
Dlib:
The Dlib library is utilised on the server to identify facial landmarks, and
a threshold value is used to determine whether or not the driver is
sleepy.
The EAR (Eye Aspect Ratio) is then computed using these face
landmarks and given to the driver.
Python:
python allows the model of deep learning algorithm via including the use
of OpenCV.
python also provides the flexibility for detecting such serious and significant
detection via OpenCV modules.
Vscode:
it is used as main code editor
Visual Studio is an integrated development environment (IDE)
METHODOLOGIES
The proposed technique is primarily based on eye blinking and yawning of
driver which can be a behavioural measures
The aim of this project is to detect closed eyes and opened mouth this is
yawning and alert to the driver
This is done by placing a camara infront of driver and capture real time
video by opencv and dlib
There are 3 modules for the process
1. Face ,eye and mouth detection
2. Eye closure detection
3. Open mouth detection
1.FACE ,EYE AND MOUTH DETECTION
face is detected using dlib library
Shape predictor that is implemented in dlib library is used to find facial
lanmarks
The predictor gives landmark points that can be applied to localize the
regions of face such as eye ,mouth, nose,ears
By appliying landmark detection eyes and mouth can be localized
and detected
Landmark depicted by dlib facial predictor
2 .EYE CLOSURE DETECTION
Each eye is characterized by 6 coordinates
An equation called eye aspect ratio ( EAR ) which described the relation
between width and height of coordinates can be derived
The ratio of eye landmark distance can be used to determine whether the
person is blinking or not
3. OPEN MOUTH DETECTION
Yawning is characterized by wide opening of mouth
Mouth is characterized with the hel of coordinates
Using the coordinates the distance between lips are calculated
and determine whether the driver mouth is open
If the lip distance is greater than threshold amount then subject is
determined to be yawning and alert is given accordingly.
CONCLUSION
This project looks at how to detect tiredness in a driver at real time by
looking at eye closure and yawning
This techonology has andvantage of detecting tiredness early on and
sounding an alarm before accident
The face eye and mouth are easily detected by using this technology and
these are captured using a webcam
It detect whether the eyes are opened or closed during monitoring
A warning signal will be issued if the eyes are closed for extended period of
time and if yawing is detected
REFERENCES
Wanghua Deng , Ruoxue Wu , “Real time driver- drowsiness detection
system using facial features”,IEEE Access , vol.7 , pp. 227-238 , August 2019
Zhong-xun Wang , Wenqi Wang , “The research onedge detection
algorithm of lane” , EURASIP Journal on Image and Video Processing ,
Springer ,October 2018.
Nawal Alioua , Mohammed Rziza , Abdelaziz Bensrhair , “Driver head pose
estimation using efficient descriptor fusion” , EURASIP Journal on Image and
Video Processing , Springer , 2016.
Shruti Mohanty , Shruti V Hegde , Supriya Prasad , “Design of Real-time
Drowsiness Detection System using Dlib” , 5th IEEE International Conference
on Electrical and Computer Engineering ,IEEE , 2018.
THANKYOU
