DIP Poster

Driver Drowsiness Detection System
Shabiqun Nahar ID:11908020

Nasir Uddin ID:11908041
Supervised by: Mahmuda Khatun, Assistant Professor
Dept. of CSE, Comilla University
Introduction
Driver drowsiness detection is a car safety technology which helps prevent accidents caused by the driver getting drowsy.
Driver Drowsiness refers to the state of extreame sleepiness or fatigue experience by drivers while operating a vehicle. 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.
Objective Methodology
 The main objective of a driver drowsiness detection system using  Haar casecade algorithm.
Python and OpenCV is to monitor a driver's level of drowsiness and  Importing Libraries: scipy, imutils, time, dlib, cv2 (OpenCV), and
alert them when they are at risk of falling asleep or losing pygame.
concentration while driving.
 This system aims to enhance road safety by detecting signs of
drowsiness in real-time and providing timely warnings to prevent
accidents caused by driver fatigue.
Literature Review Dataset

Title Author, Parameters Algorithm Limitation Advantages  The "shape_predictor_68_face_landmarks.dat" file contains a pre-trained
Publication year
machine learning model that can predict the locations of 68 facial landmarks on a
AUTOMATED G.Santhoshi, Drosiness I. Haar Feature 1. High cost Maximum
DRIVER Durga saiesh, Distraction, Eye selection 2. Sensors accuracy
human face. These landmarks represent specific points on the face, including the
DROWSINESS Gondesi Vamsi Tracking, Face II. Adaboost 3. Required due to corners of the eyes, nose, mouth, and other distinctive features.
DETECTION Krishna, Pollipalli Detection, Perclos Training 4. Takes longer combining
FOR NON 2 Krishna Priya, III.Cascading Time multiple
 Eyes: The corners and edges of the eyes (e.g., points for the inner and
WHEELERS Joga Likith. Classifiers algorithms. outer corners).
March 12,2020  Eyebrows: Points along the eyebrows, capturing their shape and position.
Fatigue Nafis IRTIJA, Fatigue detection, I. Support vector 1. Lack of Low cost  Mouth: Points along the edges of the mouth, capturing its shape and
Detection Using Mahsius SAMI, Facial expression Machine(SVM) datasets for of
Facial Md Atiqur Rahman recognition,Suppor II. Histogram of fatigued implementa
position.
Landmarks AHAD, t Vector Machine Oriented faces. tion Not  In the provided code, the "shape_predictor_68_face_landmarks.dat" file is
May 31, 2018 June Gradients 2. 82.79% detects
02, 2018 accuracy. properly
used with the Dlib library to detect and locate these facial landmarks.
blinking of Once the landmarks are identified, the code calculates various metrics,
eyes. such as eye aspect ratio and lip distance, which are then used to determine
if the person is exhibiting signs of drowsiness.
Eye Tracking Hardeep Singh Fatigue Warning, PERCLOS(Percent Steering Driver fast
based Driver M.E, E.P.D.T, Driver Drowsiness, eyelid closure pressure may be assistance,
Fatigue E&EC Eye tracking detection. Steering vary from Driver
Monitoring and Department, PEC system, Real time wheel gripping person to person. monitoring
warning system University of fatigue detection. pressure variability system.
Technology, detection unit.
India; J. S.
Bhatia; Jasbir Kaur
January 28, 2010
DRIVER Badiuzaman Bin To investigate the Electro Encephalo Records video Easy to
DROWSINESS Baharu, physical changes Graphy (EEG) for and process it is implement
DETECTION May 15, 2013 of fatigue and Drowsiness less accurate and and design  In summary, this pre-trained model is a key component in the facial
BY USING drowsiness. Detection. require physical the model landmark detection process, allowing the code to analyze and monitor
WEBCAM PERCLOS(Percent contact of with lowest specific features of the face for the purpose of drowsiness detection.
age of eye Closure) sensors. cost.
Result Limitation
 False Alarms: Some drowsiness detection systems may generate

false alarms due to factors such as bright lights, sudden movements,
or changes in the driver's posture.
 Reliance on Technology: Drowsiness detection systems rely on
technology, which can malfunction or fail.
 The quality of the camera used can impact the system's ability to
detect small eye movements, potentially leading to results.
Conclusion
In conclusion, driver drowsiness detection system technology is a vehicle protection technology to assist to save your injuries resulting from drowsy
drivers. It is important to detect and alert the driver early before any unwanted accidents happen that may lead to death. The proposed system can detect
driver drowsiness levels using an image processing technique that calculates and measures Eye Aspect Ratio, in other words, size of driver's eye.

DIP Poster

Uploaded by

Copyright:

Available Formats

DIP Poster

Uploaded by

Document Information

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

DIP Poster

Uploaded by

Copyright:

Available Formats

Driver Drowsiness Detection System

Shabiqun Nahar ID:11908020

Literature Review Dataset

 False Alarms: Some drowsiness detection systems may generate

You might also like

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.