DRIVER DROWSINESS DETECTION OF USING
EYE BLINK SENSOR
Janani P
UG Degree Department of BME UG Degree Department of
GRT Institute Of Engineering and GRT Institute Of Engineering
Technology,Tiruttani and Technology,Tiruttani
jananipurusothamanjananipuruso@gmail.com Priyababu1812@gmail.com
Abstract -Accidents due to driver drowsiness can be
prevented using eye blink sensors. The driver is
supposed to wear the eye blink sensor frame
throughout the course of driving and blink has to be
for a couple of seconds to detect drowsiness. Any
random changes in steering movement leads to
reduction in wheel speed. The threshold of the
vibration sensor can be varied and accordingly action
can be taken. The outcome is that the vibrator
attached to eye blink sensor’s frame vibrates if the
driver falls asleep and also the LCD displays the
warning messages. The wheel is slowed or stopped
depending on the condition. This is accompanied by
the owner being notified through the GSM module,
so the owner can retrieve the driver’s location,
photograph and police station list near to driver’s
location. This is how the driver CAN BE alerted
during drowsiness Iand the owner can be notified
simultaneously
1. INTRODUCTION
For any vehicle accidents driver’s faults are the
most accountable aspect to cause dangerous
problem to the society. Many drivers cannot control
the vehicles due to different reasons it may cause
severe accidents and sometime death. For vehicle
accidents various factors involved such as drunk
driving, over speeding, many distractions like
texting while driving, talking with others, playing
with children etc. one of the important factor is
sleeping on the wheel. People know the dangerous
of alcohol consumption and run the vehicles but
they not understand the seriousness of fatigue
Priya B Umasupriya P T
UG Degree Department of
BME BME
GRT Institute Of Engineering
and Technology,Tiruttani
umasupriyapt@gmail.com
driving. In India, Ministry of Road Transport and
Highway released a report in 2015, every day
around 1,374 accidents may happen and almost 400
people deaths occur. Every hour because of vehicle
accidents approximately 57 road accidents and 17
people dies. In that 54.1 percent of people are in the
age group of 15 to 34 years are killed in vehicle
accident. The Government of India, Ministry of
Road Transport and Highway Government of India
prepare a strategy to diminish the amount of
motorway accidents and losses by 50 % by 2020.
Globally vehicle accidents have seemed one of the
major community health problems. In India almost
5 lakh road accidents happened in the year 2015. A
fatigue Driver those who falls asleep at the move
fails to control the vehicle, not possible to take
immediate action and results in a crash so it is
necessary to monitor the drowsiness of the driver to
prevent accidents. .
2. LITERATURE SURVEY
Automatic driver drowsiness can be detected using
artificial intelligence and visual information.
System is to detect, track and examine face and
eyes of drivers for this different real vehicle image
of drivers are taken to validate the algorithms. It is a
real time system work in different light conditions
[1]. The numbers of accidents are increased due to
several factor, one of the main factor is that driver
fatigue. Driver’s sleepiness is also implemented
using video based approach. This system is non-
invasive and human related elements are used. Band
power and Empirical Mode Decomposition methods blink sensor,Buzzer,9v battery. When driver fall
are used to investigate and extract the signal, SVM asleep is detected by eye blink sensor then the
(Support Vector Machine) used to confirm the buzzer will start giving alarm sound. The working
analysis and to categorize the state of vigilance of of eye blink sensor is it will transmits. IR ray
the driver [2]. The system designs to find the towards the eye. While if the driver eye is closed,
drivers drowsiness using the hypothesis of Bayesian the IR rays will reflect back with a large in density
networks. The interaction between driver and and the photodiode will detect it and then the buzzer
vehicle features are extracted to get reliable will start to alarm.
symptoms of driver drowsiness. It presents more
suitable and accurate strategies to design drowsy 4. BLOCK DIAGRAM
driver detection system [3]. Brain and visual
activity is used in drowsiness detection system.
Electroencephalographic (EEG) channel used to
monitor the brain activity. Diagnostic techniques
and fuzzy logic are used in EEG based drowsiness
detector. Using blinking detection and
characterization for visual activity monitored.
Electrooculographic (EOG) channel are used to
extract the Blinking features [4]. Image processing
and pattern classification used to take the driver
facial pictures, tracking the features of driver face
and categorizing the driver’s sleepiness level. 17
In our method we would first detect the face and
different feature points are determined after
crop the facial image which will isolate the face
examining the facial muscle activities using Active
region from the background image and makes the
Appearance Model (AAM). K-Nearest-Neighbour
eye detection more accurate because in this case
method applied to categorize sleepiness into 6
instead of processing the whole image we would
levels, driver’s smile also detected with this method
just focus on the facial image. We use a simple
[5]. Head posture estimation method is used for
webcam which takes gray scale frames and by using
detection of drowsy driver. In this method Viola
a face detection library [6] we can accurately
and Jones algorithm for driver face detection [6].
determine the position of the face and crop it. We
This method is nonintrusive and sturdy for finding
can define a threshold for face detection which can
the driver drowsiness in real time. Support Vector
be varied from -10 to 10 depend on the environment
Machine (SVM) is using for extracting the face
to reach better results. Another advantage of using
from video frames and Circular Hough Transform
face detection before eye detection is that you can
(CHT) is useful for mouth and eye state analysis
use this system in higher distances which is not
[7]. In this approach machine learning used to
accessible in many previous works. In this project
determine the human behaviour during driver
we first used the system without enhancing face
drowsiness, for this 30 different facial actions
detection which resulted in about 95% accuracy [8]
including eye blink, yawning and head movements
which was not satisfactory since the other methods
are collected to detect the driver drowsiness [8].
would result in higher accuracy but after enhancing
face detection to our system the accuracy reached
3. METHODOLOGY
97% when the eyes are open and 98% when the
The main objective of the project is based on
eyes are closed. In the face detection processes we
drowsy driver detection system focuses on the
have used a new reduced set method for support
functioning of this sensor modules used in the
vector machines (SVMs) which creates sparse
project. This helps explain the inputs received by
kernel expansions that can be evaluated via
modules and the outputs they produce. In
separable filters. The detail of this method was
glasses,we are connecting Ardunio pro mini ,eye
described in [6]. Fig.2 shows the detected faces
using this method for different distances.
EYE DETECTION
After isolating the face from the background
image, it is time to process the facial image to find
the eyes in the cropped image. As we are using the
grey scale images it is easy to separate the whole
eye from the face by using its brightness and then
after removing other parts of the face from the
image we can use the roundness of the iris to
determine the position of the eye. As we know the
iris is the roundest object in the face so by defining
two limits for the roundness we will check the
roundness of the remained objects with these
limitations and finally find the position of the eyes.
Shows a sample of detected eye. As we can see in
this figure there are other detected objects that can
be omitted by defining limitations for the roundness EYE BLINK SENSOR
of detected objects and then by doing some This Eye Blink sensor senses the eyeblink using
morphological process the exact location of the eyes infrared. The Variation Across the eye will vary as
is 52 determined. Fig.3 shows the detected eye by per eye blink. If the eye is closed the output is high
red circles. As can be seen in fig.4 when the eyes otherwise the output is low. Eye Blink Sensor EYE
are closed no round object is detected according to Sensor kit 3-pin female header. This product is
our definition and so no eye is detected. strictly restricted for hobby projects and not
ARDUINO PRO MINI recommended for real-time use is closed the output
The Arduino Pro Mini is a microcontroller board is high otherwise the output is low. Eye Blink
based on the ATmega328P. It has 14 digital Sensor EYE Sensor kit 3-pin female header. This
input/output pins (of which 6 can be used as PWM product is strictly restricted for hobby projects and
outputs), 6 analog inputs, an on-board resonator, a not recommended for real-time use.
reset button, and holes for mounting pin headers. A
six pin header can be connected to an FTDI cable or
Sparkfun breakout board to provide USB power and
communication to the board. The Arduino Pro Mini
is intended for semi-permanent installation in
objects or exhibitions. The board comes without
pre-mounted headers, allowing the use of various
types of connectors or direct soldering of wires. The
pin layout is compatible with the Arduino Mini.
There are two version of the Pro Mini. One runs at
3.3V and 8 MHz, the other at 5V and 16 MHz. The
Arduino Pro Mini was designed and is BUZZER
manufactured by SparkFun Electronics. You can An audio signaling device like a beeper or buzzer
find hereyour board warranty information. may be electromechanical or piezoelectric or
mechanical type. The main function of this is to
. convert the signal from audio to sound. Generally, it
is powered through DC voltage and used in timers,
alarm devices, printers, alarms, computers, etc.
Based on the various designs, it can generate
different sounds like alarm, music, bell & siren. The
pin configuration of the buzzer is shown below. It
includes two pins namely positive and negative.
The positive terminal of this is represented with the
‘+’ symbol or a longer terminal. This terminal is
powered through 6Volts whereas the negative
terminal is represented with the ‘-‘symbol or short
terminal and it is connected to the GND terminal.
very common size is known as PP3, introduced for
early transistor radios. The PP3 has a rectangular
prism shape with rounded edges and two polarized
snap connectors on the top. This type is commonly
used for many applications including household
uses such as smoke and gas detectors, clocks, and
toys. The nine-volt PP3-size battery is commonly
available in primary zinc-carbon and alkaline
chemistry, in primary lithium iron disulfide and
lithium manganese dioxide (sometimes designated
CRV9, and in rechargeable form in nickel-cadmium
(Ni–Cd), nickel-metal hydride (Ni–MH) and
lithium-ion. Mercury batteries of this format, once
common, have been banned in many countries due
to their drowsy,the system will continuously check
whether driver is sleeping or
not.The system will also check alcohol presence
and fire presence in the vehicle .If any one is
detected it will alert the driver by buzzing the
alarm, and sending an alert message to the owner of
the car

BATTERY 9V
The nine-volt battery, or 9-volt battery, is an
electric battery that supplies a nominal voltage of 9
volts. Actual voltage measures 7.2 to 9.6 volts,
depending on battery chemistry. Batteries of various
sizes and capacities are manufactured; a very
common size is known as PP3, introduced for early
transistor radios. The PP3 has a rectangular prism
shape with rounded edges and two polarized snap
connectors on the top. This type is commonly used
for many applications including household uses
such as smoke and gas detectors, clocks, and toys.
The nine-volt PP3-size battery is commonly
available in primary zinc-carbon and alkaline
chemistry, in primary lithium iron disulfide and
lithium manganese dioxide (sometimes designated
CRV9, and in rechargeable form in nickel-cadmium
(Ni–Cd), nickel-metal hydride (Ni–MH) and
lithium-ion. Mercury batteries of this format, once
common, have been banned in many countries due
to their toxicity. The nine-volt battery, or 9-volt
battery, is an electric battery that supplies a nominal CIRCUIT DIAGRAM
voltage of 9 volts. Actual voltage measures 7.2 to
9.6 volts, depending on battery chemistry. Batteries
of various sizes and capacities are manufactured; a

RESULT
This system detects whether the driver is feeling
drowsy or not .If the driver is drowsy ,then the
system will alert the driver through buzzing alarm.
But if the driver is not drowsy,the system will
continuously check whether driver is sleeping
ornot.The system will also check alcohol presence
and fire presence in the vehicle .If any one is
detected it will alert the driver by buzzing the
alarm, and sending an alert message to the owner of
the car
CONCLUSION
Nowadays, people have become more prone to
accident. So, we as an engineer need to take action
against this and look for the desired solution. For
the safety of the human being some automation is
made. The purpose of such a model is to advance a
system to detect fatigue symptoms in drivers and
alert the driver by buzzing the alarm to avoid
accidents.
FUTURE WORK
Using drowsiness detection system, driver safety
can be implemented in normal cars also. scope for
future work: The future works may focus on the
utilization of outer factors such as vehicle states,
sleeping hours, weather conditions, mechanical
data, etc, for fatigue measurement. The future
works may focus on the utilization of outer factors
suchas vehicle states, sleeping hours, weather
conditions, mechanical data, etc, for fatigue
measurement. Driver drowsiness pose a major
threat to highway safety, and the problem
particularly severe for commercial motor vehicle
operators. Twenty-four hour operations, high annual
mileage, exposure to challenging environmental
conditions, and demanding work schedules all
contribute to this serious safety issue. Monitoring
the driver’s state of drowsiness and vigilance and
providing feedback on their condition so that they
can take appropriate action is one crucial step in a
series of preventive measures necessary to address
this problem. Currently there is not adjustment in
zoom or direction of the camera during operation.
Future work may be to automatically zoom in on
the eyes once they are localized.
REFERENCE
[1] MarcoJavier Flores, JoséMaría Armingol and
Arturo de la Drowsiness Warning System Using
Visual Escalera, ―Driver Information for Both
Diurnal and Nocturnal Illumination Conditions‖,
Springer, EURASIP Journal on Advances in Signal
Processing, 2010.
[2] Belhassen AkroutWalid Mahdi, ―A Blinking
Measurement Method for Driver Drowsiness
Detection‖, Springer, Proceedings of the 8th
International Conference on Computer Recognition
Systems CORES, pp 651-660, 2013.
[3] Ji Hyun Yang, Zhi-Hong Mao, Member, IEEE,
Louis Tijerina, Tom Pilutti, Joseph F. Coughlin, and
Eric Feron, ―Detection of Driver Fatigue Caused
by Sleep Deprivation‖, IEEE TRANSACTIONS
ON SYSTEMS, MAN, AND CYBERNETICS—
PART A: SYSTEMS AND HUMANS, VOL. 39,
NO. 4, JULY 2009.
[4] Antoine Picot, Sylvie Charbonnier, Alice
Caplier, ―On-Line
Detection of Drowsiness Using Brain and Visual
Information‖, Published in: IEEE Transactions on
Systems, Man, and Cybernetics - Part A: Systems
and Humans (Volume: 42, Issue:3) Page(s): 764 –
775, May 2012.
[5] Satori Hachisuka, Kenji Ishida, Takeshi Enya,
Masayoshi Kamijo ―Facial Expression
Measurement for Detecting Driver Drowsiness‖,
springer, International Conference on Engineering
Psychology and Cognitive Ergonomics. EPCE
2011: Engineering Psychology and Cognitive
Ergonomics pp 135-144, 2011.
[6] Ines Teyeb, Olfa Jemai, Mourad Zaied, Chokri
Ben Amar, ―A Drowsy Driver Detection System
Based on a New Method of Head Posture
Estimation‖, springer. International Conference on
Intelligent Data Engineering and Automated
Learning. IDEAL
2014: Intelligent Data Engineering and Automated
Learning –IDEAL 2014 pp 362-369, 2014.
[7] Nawal Alioua, Aouatif Amine, Mohammed
Rziza, Driss Aboutajdine, ―Driver’s Fatigue and
Drowsiness Detection to Reduce Traffic Accidents
on Road‖, springer. International Conference on
Computer Analysis of Images and Patterns, CAIP:
Computer Analysis of Images and Patterns pp 397-
404, 2011.
[8] Esra Vural, Mujdat Cetin, Aytul Ercil, Gwen
Littlewort, Marian Bartlett, Javier Movellan,
―Drowsy Driver Detection Through Facial
Movement Analysis‖, springer, International
Workshop on Human-Computer Interaction HCI
2007: Human–Computer Interaction pp 6-18, 2007.
[9] Lin, Chin-Teng, et al. ―Drowsiness estimation
for safety driving using independent component
analysis‖, Circuits and Systems I: Regular Papers,
IEEE Transactions on 52.12: 2726-2738 pg-20-30,
2005.
[10] Clarke Sr, James Russell, and Phyllis Maurer
Clarke, ―Sleep detection and driver alert
apparatus‖, U.S. Patent No. 5, 689, 241, pg25-70 18
Nov. 1997.
[11] Hayami, Takchito, et al. ―Detecting
drowsiness while driving by measuring eye
movement-a pilot study‖, Intelligent Transportation
Systems, Proceedings. The IEEE 5th International
Conference on. IEEE, 2002 pg30-35, 2002.
[12] Hu, Shuyan, and Gangtie Zheng, ―Driver
drowsiness detection with eyelid related parameters
by Support Vector Machine‖, Expert Systems with
Applications 36.4, pg651-658, 2009.
[13] Ito, Takehiro, et al, ―Driver blink
measurement by the motion