ACCIDENT AVOIDANCE SYSTEM USING DROWSINESS DETECTION

BASED ON ML & IP
INTRODUCTION
 In today’s modern world, transportation and the need for the use of the cars,
bikes and motor cycles has tremendously increased over past few decades.
 The ever increase in the population is one of the reason behind the growing
number of vehicles.
 In today’s world the use of transportation requires lot of safety system and
maintenance. Currently we are using vehicles with safety system that
includes use of the brakes, air bags, seat belt etc.
 But these are only helpful post-accident and lack to alert the driver before
the accident occurs.
 Driver fatigue detection system can be used for preventing the above
problems without endangering human life and hence is one of the effective
ways to stop accidents.
 In driver fatigue or Drowsiness detection system it depends on the motion of
eye Blinking period, the time interval between them and also the movement
pattern of the head.
 The system does not break down and it can be used for more advanced driver
visual attention monitoring.
 The hardware system involves the usage of the IR illuminator Along with the
implementation of the software that makes use of the fuzzy logic helps in the
measurement of the level of alertness of the driver.
 The system has been tested in the day as well as the night environments
hence can be able to work in the any of the environment.
 This project involves implementation of the fuzzy Logic hence depending on
different background environment and lights it can predict the fatigue state
of the driver and warns the driver in advance in order to avoid the accident In
Section 2 will discuss the algorithm of drowsiness and the section 3 will
discuss the hardware and software implementation of the system.
BLOCK DIAGRAM:
STEPS FOR PERFORMING DRIVER DROWSINESS DETECTION:
Step 1 – Take Image as Input from a Camera
 
Step 2 – Detect Face in the Image and Create a Region of Interest (ROI)
 

Step 3 – Detect the eyes from ROI and feed it to the classifier
 
 
Step 4 – Classifier will categorize whether Eyes are open or closed
 
 
Step 5 – Calculate Score to check whether Person is Drowsy
 
PROJECT PREREQUISITES / REQUIREMENTS:

The requirement for this Python project is a webcam through which we will
capture images. You need to have Python (3.6 version recommended) installed on
your system, then using pip, you can install the necessary packages.
 

I. OpenCV – pip install opencv-python (face and eye detection).

II. TensorFlow – pip install tensorflow (keras uses TensorFlow as backend).

III. Keras – pip install keras (to build our classification model).

IV. Pygame – pip install pygame (to play alarm sound).

V. SMS Python Quickstart -- With just a few lines of code, your Python

application can send Alert SMS messages with Programmable Messaging.

ALGORITHM OF DROWSINESS DETECTION

New Image

Adjust brightness
& contrast

Face detection
YES

Success
NO
YES

Eye detection

Success
NO
YES
Extract eye
region
 Eye feature
extraction

Determine – close
OR open eye

Calculation of
Drowsiness

Drowsy
Driver NO
YES

Alarm/Alert
METHEDOLOGY:
 The new image is been input and is detected for the face detection.
 The image brightness and contrast ratios are adjusted for the detection of face
 the later it undergoes the face detection if it is detected
 then it undergoes eye detection then the frame is adjusted around the eye
region the eye region is extracted.
 The patterns are then processing for the eye blinking, whether the eyes are
open or closed during the driving of the car .
 Then the data has been for the calculation of the drowsiness that the driver
possess with the help of the fuzzy logic.
 If the driver is drowsy then the alarm signal is set on to make the driver alert
that he is undergoing drowsiness state and the driver needs to stop driving or
needs precautionary measure before the driving of the car.
 The first part is the eye detection function and the other is the Drowsiness
Calculation function.
SYSTEM IMPLEMENTATION
 Hardware:
 The hardware used is PC.
 The external hardware used is Logitech webcam which helps to capture images.
 Mother Board specification is Intel pentium4 processor Memory: DDR226, USB
Host and Device Port TFT LCD
 Software:
 Python (3.8 version recommended) 
 In this Python project, we will be using OpenCV for gathering the images from the
webcam
 OpenCV  
 TensorFlow
 Keras
 Pygame
 Dataset - Drowsy Driver Detection
 Step #1 — Look for faces in the input video stream Step #2 — Apply facial landmark localization to extract the eye regions from the face.

Step #3 — Compute the eye aspect ratio to determine if the eyes are closed. Step #4 — Sound an alarm if the eyes have been closed for a sufficiently long enough time.
ADVANTAGES:
Region of interest is clear to identify
Bounding box creation and tracking

APPLICATIONS:
Real time tracking applications
Classification of small particles

HARDWARE REQUIRMENTS:
Camera
Personal computer

SOFTWARE REQUIREMENTS:

Python 3.7 or above versions

Anaconda software 
CONCLUSION:

The driver abnormality monitoring system developed is capable of detecting

drowsiness, drunken and reckless behaviors of driver in a short time.
The Drowsiness Detection System developed based on eye closure of the driver
can differentiate normal eye blink and drowsiness and detect the drowsiness
while driving.
The proposed system can prevent the accidents due to the sleepiness while
driving.
Information about the head and eyes position is obtained through various self-
developed image processing algorithms.
During the monitoring, the system is able to decide if the eyes are opened or
closed.
When the eyes have been closed for too long, a warning signal is issued.
Processing judges the driver’s alertness level on the basis of continuous eye
closures.
REFFERENCES:

 [1] Miaou, “Study of Vehicle Scrap page Rates,” Oak Ridge National Laboratory, Oak
Ridge, TN,, S.P.,April 2012.
 [2] Wreggit, S. S., Kim, C. L., and Wierwille, W. W., Fourth Semi-Annual Research
Report”, Research on Vehicle-Based Driver Status Performance Monitoring”,
Blacksburg, VA: Virginia Polytechnic Institute and State University, ISE Department,
January 2013.
 [3] Bill Fleming, “New Automotive Electronics Technologies”, International Conference
on Pattern Recognition, pp. 484- 488,December 2012.
 [4] Ann Williamson and Tim Chamberlain,“Review of on-road driver fatigue monitoring
devices”, NSW Injury Risk Management Research Centre, University of New South
Wales, , July 2013.
 [5] E. Rogado, J.L. García, R. Barea, L.M. Bergasa, Member IEEE and E. López,
February, 2013, “Driver Fatigue Detection System”, Proceedings of the IEEE
International Conference on Robotics and Biometics, Bangkok, Thailand.
 [6] Boon-Giin Lee and Wan-Young Chung, Member IEEE, “Driver Alertness Monitoring
Using Fusion of Facial Features and Bio-Signals”, IEEE Sensors Journal, VOL. 12, NO. 7,
July 2012.
 [7] H. Singh, J. S. Bhatia, and J. Kaur, “Eye tracking based driver fatigue monitoring
and warning system”, in Proc. IEEE IICPE, New Delhi, India, Jan. 2014. 
QUESTIONS?
THANK YOU !