SHOCK 2 LAZY DRIVERS USING IMAGE

PROCESSING

Paper

Paper presented by:

P.RAMANAIAH K.ARUN SEKHAR

Electronics and Communication Dept.
SRI SATYANARAYANA ENGINEERING COLLEGE
(AN ISO 9001:2008 CERTIFIED INSTITUTION)
(Approved by AICTE, Affiliated to J.N.T.U, Kakinada)
Kurnool road, Ongole-523225, Prakasam (Dist.), A.P.

E_MAIL:[email protected]
C_no-8096518067
ABSTRACT
The Purpose of Proposing this paper is to develop a system for detecting the fatigue of
the driver during the journey, and to issue a warning signal to alert the driver. The system will
be primarily based on the processing of the images obtained from the driver’s face Using Image
Processing Technique. In this project, video is taken as an input and the system predicts the
driver drowsiness from the appearance of the eyes in the frame (in video sequence). This report
describes how Image Processing is used to find the Fatigue of the Driver and how to find the
position of the eyes, and also determines the eyes closure If the eyes are closed for 7 consecutive
frames, the system draws the conclusion that the driver is falling asleep and sounds a alarm as a
warning signal. This Paper finds applications in industries. The required Eye detection algorithm
can be developed in many languages like MATLAB using Image Processing
Toolbox and other languages.
INTRODUCTION
The ever-increasing number of traffic accidents in the world due to a diminished driver’s
vigilance level has become a problem of serious concern to society. Drivers with a diminished
vigilance level suffer from a marked decline in their abilities of perception, recognition, and
vehicle control and therefore pose serious danger to their own life and the lives of other people.
Statistics show that a leading cause for fatal or injury-causing traffic accidents is due to drivers
with a diminished vigilance level.
In the trucking industry, 57% fatal truck accidents are due to driver fatigue. It is the
number one cause for heavy truck crashes. 70% of Indian drivers report driving fatigued. The
National Highway Traffic Safety Administration (NHTSA) estimates that there are 100,000
crashes, which are caused by drivers in fatigue and result in more than 1,500 fatalities and
71,000 injuries each year in India. With the ever-growing traffic conditions, this problem will
further deteriorate.
For this reason, developing systems actively monitoring a driver’s level of vigilance and
alerting the driver of any insecure driving conditions is essential to accident prevention. Fatigue
Monitoring system method can form the basis of a system to potentially reduce accidents related
to sleepy driving. This is a video based system which measures Percentage of Eye Closure Over
Time (PERCLOS), a scientifically supported measure of fatigue associated with slow eye
closure.

IMAGE REPRESENTATION AND

MODELING
In image representation one is concerned with characterization of the quantity that each
pictureelement (also called pixel or pels) represents. An image could represent luminance of
objects in a scene (such as a pictures taken by ordinary camera), the absorption characteristics of
the body tissue (Xray imaging), the radar cross section of a target (radar imaging), the
temperature profile of a region (infrared imaging), or the gravitational field in an area (in
geophysical imaging). In general, any two-dimensional function that bears information can be
considered as an image.
DIGITAL IMAGE PROCESSING
Digital images are processed for different application. The principle objective of image
processing is to show the result image in a more suitable manner than the original image. The
ultimate goal of these techniques is to improve an image in some predefined sense. The
following are the various steps involved for processing of digital images.

FUNDAMENTAL STEPS IN DIGITAL IMAGE

PROCESSING
Image acquisition
Image enhancement
Image restoration
Image compression
Image segmentation
Representation & description
Object recognition

BACKBONE
Driver vigilance monitoring system
The monitoring starts with extracting visual parameters which characterize the person’s
level of vigilance. The system starts with finding of eyes in the image using the Hough transform
and eye detection algorithm. Based on this information and the sleeping history of the person, the
drowsiness of driver is found.
Basic Flow chart of Driver Vigilance
Monitoring System

Driver Vigilance Monitoring System

Eyes
The eye is a sensory organ which is used to detect contrast in objects illuminated by light.
The human eye has many components, but for the purpose of this report we will look at the
functions of the iris, pupil, sclera, cornea, retina, lens and their interactions with each other. The
iris makes up the coloured part of the eye. Its function is to regulate the amount of light that
enters the eye. This is achieved by regulation of the pupil, the dark centre spot in the iris which
allows light to enter the eye.
Fig. 3.2 Elements of the Eye
The pupillary sphincter muscle controls the size of the iris, automatically adjusting to
control the amount of light entering the eye. Diameters of a healthy pupil in dim conditions can
be enlarged to 8mm. This makes the pupil smaller, in the region of 1.5mm, which allows the eye
to function more efficiently in this condition. In ambient light conditions a normal pupil will
range from 3 to 4 mm diameter. The sclera is the outer protective layer of the eye. This layer is
opaque and usually white in healthy eyes.
The cornea is the transparent window of the eye. It sits over the pupil and iris,
transmitting and focusing light into the eye. Visual fatigue also reduces the powers of
accommodation and convergence of the eye, sensitivity to contrast and speed of perception. All
types of visual work can contribute to visual fatigue. Driving calls for rapid and precise eye
movements which make heavier demands on perception, concentration and motor control.

IMPLEMENTATION
Processes used in this project include the use of the Hough transform, eye detection
algorithms and pressure sensor analysis. This section discusses how they were implemented in
the project and how they were used to best effect.
Hough Transform
The Hough transform is a technique of finding any shape in a digital image. It is usually
used to find lines and curves or shapes that can be described by a set of parameters. The Hough
Transform is used to find the eye ball in the images of the driver.
Eye Detection Algorithm
This section describes the algorithm used to refine the data returned from the Hough
transform, the basic principals which the algorithm are based on are also discussed. Data
returned from the Hough transform function takes the form of two arrays, one a 2xN matrix
containing the coordinate information and the other a column vector with the corresponding radii
of the circles. The purpose of this screening of points is to improve the reliability the detection of
the eye. It was devised to reduce the level of error in the returned data that the geometric
properties of the face and eyes be used to differentiate points the Hough transform sees as
circular objects.
Output from Hough transform
Initially the points are screened based on colour information, setting a threshold to ignore
points that have a grayscale value towards the white end of the spectrum removes any shado ws
on the face or light source reflections from the returned data.
Pairing data points of the same radius allows for the identification of probable
matchingpairs of eyes. Healthy pupils should be of the same size and react together to any
changes in light so it is reasonable to assume they should be the same size. At this stage apoint
may have multiple pairings with other points.
The Results from the Hough Transform.Pairing Circles of similar radius

Excluding those pairs at large angles

The angle condition to be applied, this involves removing pairings from the selection that
fail to have a relatively small angle with the horizontal. This reflects the normal orientation of
the driver’s eyes during normal driving conditions. A tolerance is given to allow for leaning
Removal of Pairs that fail Angle Condition
Excluding those outside distance range
Now the distance condition is applied to the pairings, this is used as the distance between
the eyes is fixed and can be said to lie within a maximum and minimum distance range for the
majority of people, i.e. most people’s eyes are greater than 2cm apart but less than 20cm. This is

a broad range but eliminates any outlying points.

Removal of Pairs that do not fit Distance Criteria
From the final check we can identify which pair of circles are eyes. Fig 4.9 shows the
resulting circles which show eyes in the image. The screening process is done form the radius,
angle, distance which will almost give the exact coordinates of eyes in An imeage

.
Best Match Selection of Circles
The result is successful eye detection, pupils are shown in the fig 4.9 and centre point is
crossed with red mark
Eye Tracking
 Since the system continuously check the eyes in every image from the video sequence, a
tracking program has to be written. The tracking program checks the eye in every frame from the
video and shows the position of the eyes in each frame surrounded with a redsquare and alerts
the driver when he is found to be in sleepy. The alerting is an audio signal which awakens the
driver. Since the normal eye-lid ofman is about 0.3 sec, if the person close his eyes continuously
about 0.3sec the alert system will be activated. Here 7 frames is taken as reference for the sleepy
condition since in 0.3sec nearly 7 frames will be played depending on the frame rate of the video
file

APPLICATIONS
Road users have long been known to fall asleep while driving. Driving long hours can
induce fatigue causing lack of concentration and occasionally road accidents. This is even more
critical on motorways where traffic travels at higher speeds and drivers can succumb to
“motorway hypnosis” as the repetitive and somewhat passive experience of driving on long,
wide, straight roads can cause the driver to relax and lose concentration from the road and traffic
around them. This allows drivers who “legally” are fit to drive but physically are not, on the
roads. Many of these drivers are unaware of their fatigue and danger they pose to themselves and
other road users. A main application of this system is primarily to protect such people described
by alerting
them to their fatigue.

CONCLUSION
Eye detection is inevitable as world culture dictates higher safety standards in all aspects
of life. In today’s world there are more vehicles on the roads than ever before at all hours of the
night and day. This increase in road usage is a factor in the rate of traffic accidents on roads. In
addition, especially in India, hundreds of thousands commute over long distances to work, day
in, and day out. This long daily commute very early in the morning and late in the evening can
fatigue the driver thus inhibiting their ability to react to non-expectant events and even worse, it
can cause the driver to fall asleep at the wheel. This is why such a system, outlined in this project
would be of benefit to
drivers and their community.

REFERENCE PAPERS
1. IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY, VOL. 53,
NO. 4, JULY 2004Real- Time Nonintrusive Monitoring and Prediction of Driver Fatigue Qiang
Ji, Zhiwei Zhu, and Peilin Lan