PROJECT PROPOSAL

DROWSINESS DETECTION WHILE DRIVING USING EYE-

TRACKING

Muhammad Shaban
BSCS-F18-M-54

Zain ul Hasan
BSCS-F18-M-66

Usman Afzal Butt

BSCS-F18-M-78

Shuja Ali Cheema

BSCS-F18-M-90
 Chapter 1

1. INTRODUCTION
Driver drowsiness detection is a car safety technology which prevents accidents when the
driver is getting drowsy. Various studies have suggested that around 20% of all road accidents
are fatigue-related, up to 50% on certain roads; driver fatigue is a significant factor in a large
number of vehicle accidents. Recent statistics estimate that annually 1,200 deaths and 76,000
injuries can be attributed to fatigue related crashes. The development of technologies for
detecting or preventing drowsiness at the wheel is a major challenge in the field of accident
avoidance systems. Because of the hazard that drowsiness presents on the road, methods need
to be developed for counteracting its effects. related, up to 50% on certain roads. Driver fatigue
is a significant factor in a large number of vehicle accidents.
Recent statistics estimate that annually 1,200 deaths and 76,000 injuries can be attributed to
fatigue related crashes. The development of technologies for detecting or preventing
drowsiness at the wheel is a major challenge in the field of accident avoidance systems.
Because of the hazard that drowsiness presents on the road, methods need to be developed for
counteracting its effect. Drowsiness detection is one of those common problems needed to be
solved to prevent road accidents. In recent time's automobile fatigue connected crashes have
increased.

2. PROBLEM STATEMENT
Driver’s inattention might be the result of a lack of alertness when driving due to driver
drowsiness and distraction. Driver distraction occurs when an object or event draws a person’s
attention away from the driving task. Unlike driver distraction, driver drowsiness involves no
triggering event but, instead, is characterized by a progressive withdrawal of attention from the
road and traffic demands. Both driver drowsiness and distraction, however, might have the
same effects, that is decreased driving performance, longer reaction time, and an increased risk
of crash involvement.
Fatigue is a safety problem that has not yet been deeply tackled by any country in the world
mainly because of its nature. Fatigue, in general, is very difficult to measure or observe unlike
alcohol and drugs, which have clear key indicators and tests that are available easily. Probably,
the best solutions to this problem are awareness about fatigue-related accidents and
promoting drivers to admit fatigue when needed. The former is hard and much more expensive
to achieve, and the latter is not possible without the former as driving for long hours is very
lucrative.
3. APPROACH
Based on acquisition of video from the camera that is in front of the driver, perform real-time
processing of an incoming video stream in order to infer the driver’s level of fatigue. If the
drowsiness is estimated then it will give the alert by sensing the eyes. A new approach towards
automobile safety and security with autonomous region primarily based automatic automotive
systems is projected during this conception. A drowsy driver detection system and a traffic
detection system with external vehicle intrusion dodging primarily based conception. So as to
attenuate these problems, we've incorporated a driver alert system by watching each driver's
eyes. Once it's detected that the driver is drowsy then the particular score is generated and the
alarm rings to make the driver aware.
 RECORD THE VIDEO THROUGH THE WEB CAMERA AND CAPTURE IT.

 TRACK THE EYES AND GENERATE THE PLOT.

 SOUND THE ALARM IF THE EYES GET CLOSE AND THE PERSON FEELS
DROWSY
 Chapter 2

Literature review:

4. Objectives:
The project focuses on these objectives, which are: To suggest ways to detect fatigue and
drowsiness while driving. To study on eyes and mouth from the video images of participants in
the experiment of driving simulation conducted by MIROS that can be used as an indicator of
fatigue and drowsiness. To investigate the physical changes of fatigue and drowsiness. To
develop a system that uses eyes closure and yawning as a way to detect fatigue and
drowsiness.
5. EYE TRACKING
Eye tracking is the process of measuring either the point of gaze (where one is looking) or the
motion of an eye relative to the head. An eye tracker is a device for measuring eye positions
and eye movement. Eye trackers are used in research on the visual system, in psychology, in
psycholinguistics, marketing, as an input device for human-computer interaction, and in
product design. Eye trackers are also being increasingly used for rehabilitative and assistive
applications (related for instance to control of wheel chairs, robotic arms and prostheses).
There are a number of methods for measuring eye movement. The most popular variant uses
video images from which the eye position is extracted. Other methods use search coils or are
based on the electrooculogram. We here are using eye tracking in detecting the drowsiness of
the driver. Eye tracking is helping us to detect and sense the sleep of the driver, whether he is
sleeping, wanting to sleep, getting exhausted while driving etc.
6. TECHNIQUE INVOLVED
a. PYTHON
b. JUPYTER Lab
c. IMAGE PROCESSING
d. MACHINE LEARNING
6.1 EYE TRACKING AND DETECTION OF FACE THROUGH VIDEOS
We are first trying to generate a preview of the driver through the web camera of the laptop.
The driver’s preview image is being captured simultaneously by the web camera and the
camera forms to give us a preview image. The camera now starts to record the video and
automatically saves it in the backend so that it can be analyzed. The recorded video is in grey,
HSV color and original form. This different type of recording is because it helps to give us data
in all the frames- gray scale or black and white, colored frame and original frame. After the
images, videos, frames are being recorded and saved.
6.2 EYE-TRACKING AND PLOT GENERATION
Eye-tracking involves calculating the value for the eye aspect ratio and gives the figures and
plots to detect the data being recorded.
The numbers marked 37,38,39,40,41,42,43,44,45,46,47,48 are the main region of interest for
us in this project.
7. NEED FOR DROWSINESS DETECTION
1. Drowsiness Detection System is necessary.
2. It will protect the driver while driving and will ask him to drive safely.
3. No risk of death or any accident will be there.
4. The driver will feel safe at night too while driving.
5. Driver will get alert with it.
8. EYE TRACKING REQUIREMENTS
Software Requirements Specification
• Python 3
 Libraries
Numpy, Scipy, Playsound, Dlib, Imutils, opencv,
 OS
Windows or Ubuntu
Hardware Requirements Specification
● WEB CAMERA
● Laptop
8.1 EYE DETECTION USING MULTIPLE PROCESSED IMAGES-
Multiple images help to sense the drowsiness detection smoothly. All the images give us an
accurate measure of drowsiness to be sensed and detected.
The next step after face detection is to extract the driver’s eyes from the detected face image.
However, the bounding boxes for the eyes also contain eyebrows which act as noise, Since, our
proposed method is based on the curvature of the eyelids and the eyebrows have a similar
orientation, they are likely to generate falsely detected eyelids.
9. ALGORITHM USED
A few algorithms and technique has been used in the process of detecting face, eyes and
mouth. The algorithm and technique used is Cascade Object Detector. The Cascade Object
Detector uses the Viola-Jones algorithm to detect people’s face, nose, eyes, mouth or upper
body.
10. HIGH LEVEL SYSTEM COMPONENTS:
The system is composed of four parts, that is, image preprocessing, face detection, eye state
recognition, and fatigue evaluation.
Front face detection: 39
Open state detection: 8
Close state detection: 4
In this system, images are obtained by external camera with high resolution which is placed on
front left of drivers. The first step is to denoise the images. Then, after detecting the face
region, eyes location and states can be obtained easily and quickly based on the detected face
region.

Chapter 3

Methodology:

11. DROWSINESS DETECTION FLOW CHART:

The chart depicts how the full function of drowsiness detection is carried out.
It describes the importance of each step that is required to complete the detection of
drowsiness.
We can see how first the brightness and contrast level of the camera is adjusted.
Then the face is detected.
If it is successfully previewed then only the further step is taken.
The eye detection takes place.
The decision for proper eye detection is taken and then the eye region is focused and extracted.
The eyes are determined whether they are closed or opened.
The drowsiness is calculated through the data being stored and saved.
The drowsiness is judged now.
If the drowsiness is drowsy then the alarm rings loud and alert is given to him.
This is how it works.
12. GANTT CHART:
13. EXPERIMENTAL RESULT
Test Result of preview generation on driver’s captured data
Here the preview generation is done using the web camera. The preview is perfectly taken with
no ambiguity and is being saved at the backend.
Results of video recording through webcam
Video recording gives live updates of the driver while he is driving.
No risk in driving as at the back the driver is being observed.
Results of alarm generation and plot view.
The plot is generated with the stored and backup data at the end.
The alarm rings and sounds loud once the region of drowsiness is detected.
CONCLUSION
It completely meets the objectives and requirements of the system. The framework has
achieved an unfaltering state where all the bugs have been disposed of.
It is a four-step method that first detects the face of the driver in the image from among several
detected faces. Finally, the eyes are classified as closed or open based on the curvature of the
eyelids. The proposed method achieved an average classification accuracy of 95% on a simple
image dataset with homogeneous backgrounds, an average classification accuracy of 70% on a
complex benchmark image dataset, and greater than 95% classification accuracy on two real-
time driving surveillance videos.

REFERENCES
● https://en.wikipedia.org/wiki/Driver_drowsiness_detection
● https://www.pyimagesearch.com/2017/04/24/eye-blink-detection-opencv-python-dlib/
● https://scholar.google.co.in/scholar?q=driver+drowsiness+detection+system+conclusio
n&hl=en&as_sdt=0&as_vis=1&oi=scholart
● https://www.pyimagesearch.com/2017/05/08/drowsiness-detection-opencv/
● Author: Tobias Altmüller Drowsiness Detection Using Image Processing Book by
Hanojhan Rajahrajasingh Driver Drowsiness Detection: Systems and Solutions Book by
Aleksandar Čolid, Borko Furht, and Oge Marques
● P. Smith, M. Shah, and N. da Vitoria Lobo, “Determining driver visual attention with one
camera,” IEEE Transactions on Intelligent Transportation Systems, vol. 4, no. 4, pp. 205–
218, 2003. Publisher Site | Google Scholar