DROWSY DRIVER DETECTION SYSTEM

CHAPTER 1
INTRODUCTION

Drowsiness is a state of near sleep, where the person has a strong desire for sleep. It has
two distinct meanings, referring both to the usual state preceding falling asleep and the chronic
condition referring to being in that state independent of a daily rhythm. Sleepiness can be
dangerous when performing tasks that require constant concentration, such as driving a vehicle.
When a person is sufficiently fatigue while driving, they will experience drowsiness and this leads
to increase the factor of road accident. It can describe both the normal condition of winding down
for sleep and the chronic condition of remaining in that state on a regular basis. Driving while
sleepy is a recipe for disaster, as is engaging in any activity that requires constant focus. The
detection or prevention of driver drowsiness is a significant challenge in the development of
accident avoidance systems because of the increased risk of traffic accidents that occurs when a
person is sleepy while operating a vehicle. Because of the potential dangers associated with
sleepiness, methods must be developed to reduce them. The purpose of this work is to build
a system that can simulate sleepiness detection. It is claimed that keeping an eye on the eyes can
detect the signs of driver drowsiness in a sufficiently early stage, to avoid a car accident.

The most common cause of auto accidents is poor driving, so the focus will be on creating
a system that will precisely track whether the driver's eyes are open or closed. Such incidents are
common when a driver is under the influence of alcohol or fatigue. Fatigued driving is widely
recognised as a major cause of car crashes. Drunk driving is proven to account for over 20% of
all car accidents. The IR detector picks up the reflected infrared light from the eye. The IR
receiver's output is high if the eye is closed, and low otherwise. for identifying whether or not the
eye is closed. This is the signal that is sent to the logic circuit to trigger the alarm. The controlling
mishap brought on by unconsciousness via eye blink. One eye blink sensor is shown here placed
in vehicles so that if somebody passes out, the alarm will sound. The objective evaluation of
sleepiness and sequential fitting is used to construct a drowsiness detection algorithm.

DEPT OF CSE, GECT Page 1

 DROWSY DRIVER DETECTION SYSTEM

1.1 BACKGROUND

The feeling of being drowsy is a state of near-sleep. Being sleepy can be risky when performing
activities that call for constant concentration, like operating a vehicle. When a person is asleep while
driving, becomes sleepy, which raises the danger of a road accident. Detecting the driver's state and
determining whether or not they are sleepy presents the biggest obstacle. Main concept/aim of this
project is to develop a driver drowsiness detection along with alert system using deep learning
techniques. The goal will be to develop a system that can accurately determine whether the driver
is sleepy or not. This project uses CNN based detection of driver drowsiness. This technique says
that the number of times eyes are closed in particular successive frames This model verifies whether
the eyes are closed or opened for successive frames. The alarm sounds when the eyelids are closed
for over 12 to 20 consecutive frames and it stops when both eyes are fully opened.

1.2 MOTIVATION

Driver drowsiness is a significant factor in the increasing number of accidents on today’s roads
and has been extensively accepted. This proof has been verified by many researchers that have
demonstrated ties between driver drowsiness and road accidents. Although it is hard to decide the
exact number of accidents due to drowsiness, it is much likely to be underestimated. The above
statement shows the significance of a research with the objective of reducing the dangers of
accidents anticipated to drowsiness. So far, researchers have tried to model the behaviour by
creating links between drowsiness and certain indications related to the vehicle and to the driver.
Previous approaches to drowsiness detection primarily make pre-assumptions about the relevant
behavior, focusing on blink rate, eye closure, and yawning. The automobile business also has tried
to build several systems to predict driver drowsiness. The systems do not look at driver
performance and overlook driver ability and characteristics. Naturally, most people would agree
that different people drive differently. The system that being develop able to adapt to the changes
of the driver’s behaviour.

DEPT OF CSE, GECT Page 2

 DROWSY DRIVER DETECTION SYSTEM

Fig1.1:Statistic of Road Accident from 2005 to 2009

Figure 1 shows the statistic of road accident. The numbers of vehicles involved in road accident
keep increasing each year. From Figure 1, car and taxi type of vehicles shows about nearly 400,000
cases of road accident has been recorded .It keeps increasing every year and by the year 2009, it
shows the number of roadaccidentwasrecordedbynearly500,000.

Fig 1.2: Examples of Fatigue and Drowsiness Condition

Figure 2: Examples of Fatigue &Drowsiness Condition The development of technologies for

detecting or preventing drowsiness while driving is a major challenge in the field of accident
avoidance system.
DEPT OF CSE, GECT Page 3
 DROWSY DRIVER DETECTION SYSTEM

Because of the hazard that drowsiness presents on the road, methods need to be developed for
counteracting its affects. The aim of this project is to develop a simulation of drowsiness detection
system. The focus will be placed on designing a system that will accurately monitor the open
or closed state of the driver’s eyes and mouth. By monitoring the eyes, it is believed that the
symptoms of driver's drowsiness can be detected in sufficiently early stage, to avoid a car accident.
Yawning detection is a method to assess the driver’s fatigue. When a person is fatigue, they keep
yawning to ensure that there is enough oxygen for the brain consumption before going to
drowsiness state . Detection of fatigue and drowsiness involves a sequence of images of a face,
and the observation of eyes and mouth open orclosed duration. Another method to detect eye
closure is PERCLOS. This detection method is based on the time of eyes closed which refers to
percentage of a specific time. The analysis of face images is a popular research area with
applications such as face recognition, and human identification and tracking for security systems.
This project is focused on the localization of the eyes and mouth, which involves looking at the
entire image of the face, and determining the position of the eyes and mouth, by applying the
existing methods in image processing algorithm. Once the position of the eyes is located, the
system is designed to determine whether the eyes and mouth are opened or closed, and detect
fatigue and drowsiness.

1.3 OBJECTIVES

• The objective of this intermediate Python project is to build a drowsiness detection system that
will detect that a person’s eyes are closed for a few seconds.

• This system will alert the driver when drowsiness is detected. Building a drowsiness detection
system will reduce the number of accidents.

• Optimization of the Algorithm to Capture and Detect the drowsiness of the driver.

DEPT OF CSE, GECT Page 4

 DROWSY DRIVER DETECTION SYSTEM

CHAPTER 2

LITERATURESURVEY

A. Malla, P. Davidson, P. Bones, R. Green and R. Jones, "Automated Video-based Measurement

of Eye Closure for Detecting Behavioral Microsleep", in 32nd Annual International Conference
of the IEEE, Buenos Aires, Argentina, 2010. Peter Davidson, an expert in automotive safety
systems, has spoken extensively about driver drowsiness detection technologies. These systems
are designed to monitor a driver’s alertness and provide warnings or interventions to prevent
accidents caused by fatigue. He work on driver drowsiness detection and alarming systems
represents a significant advancement in automotive safety, aiming to reduce accidents and save
lives through innovative technology and meticulous research.

P. Viola and M. Jones, "Rapid Object Detection using a Boosted Cascade of Simple Features",
in Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern
Recognition, 2001. Philippe Voila, a renowned expert in automotive safety and technology,
has made significant contributions to the development of driver drowsiness detection systems. His
project focuses on leveraging advanced technologies to enhance the accuracy and reliability of
these systems. His contributions emphasize the importance of integrating advanced technologies
to enhance the accuracy, reliability, and user-friendliness of these systems.

Ayman Altameem Ankit Kumar Ramesh Chandra Poonia Sandeep Kumar and Abdul Khader
Jilani Saudagar “Early identification and detection of driver drowsiness by hybrid machine
learning” He has made notable contributions to the field of driver drowsiness detection systems,
focusing on leveraging advanced technologies and innovative approaches to improve road safety.
His work encompasses a range of methods and insights aimed at accurately detecting driver
fatigue and providing effective warnings. He work in driver drowsiness detection systems is
characterized by a commitment to leveraging cutting- edge technology and interdisciplinary
approaches to improve road safety.

DEPT OF CSE, GECT Page 5

 DROWSY DRIVER DETECTION SYSTEM

His innovative use of sensors, machine learning, and real-time data processing sets a high standard
for the development of effective and reliable drowsiness detection systems. T. Hong, H. Qin and
Q. Sun, "An Improved Real Time Eye State Identification System in Driver Drowsiness
Detection", in proceeding of the IEEE International Conference on Control and
Automation,Guangzhou, CHINA, 2007. He has contributed significantly to the field of driver
drowsiness detection systems. Their work, often cited in academic and industry research, includes
developing methods to detect when a driver is drowsy based on various parameters such as eye
movements, head posture, and physiological signals. These systems typically use sensors and
cameras to monitor the driver's behavior in real-time, employing algorithms to analyze the
collected data and determine the likelihood of drowsiness. By enhancing the system's ability to
recognize signs of drowsiness, their work aims to reduce the risk of accidents caused by fatigued
driving, thereby improving road safety.

E.Varadharaj, R.Dharani, S.Jeevitha [5] the author presented the system which used the
Eigenfaces approach for face recognition. They have performed face detection followed by a
cropping of faces then worked on background subtraction for greyscale images and binary images.
The author has used the Eigenface method due to its simplicity, speed, and learning capability. He
has also made significant contributions to the development of driver drowsiness detection systems.
Their research typically focuses on utilizing advanced signal processing and machine learning
techniques to accurately identify signs of driver fatigue. The systems aim to enhance road safety
by providing reliable, real-time detection of driver fatigue using sophisticated, multimodal
approaches and advanced machine learning techniques.

DEPT OF CSE, GECT Page 6

 DROWSY DRIVER DETECTION SYSTEM

CHAPTER 3
SYSTEM MODEL
3.1 PROPOSED MODEL

Drowsy driving is a major cause of accidents, but they may be avoided with the use of eye blink
sensors. The driver must wear an eye blink sensor frame at all times when operating a motor
vehicle, and each blink must be sustained for several seconds to reliably detect fatigue. When the
steering motion fluctuates erratically, the wheel speed drops. The threshold of the vibration sensor
may be changed, allowing for tailored responses. Therefore, if the driver turns off, the eye blink
sensor's frame vibrates and the LCD also displays the warnings.

Depending on the circumstance, the wheel either slows down or stops. The circuit should be wired
as shown in the block diagram. Second, debug the code on the Arduino Nano board. When an eye
blinks, the eye blink sensor registers that fact. There will be a complete halt and the driver will be
alerted. For Step 7 to work, you must reset the button. The purpose of this project is to create an
eye-blink-based drowsiness detection and alerting system for drivers using an RF transceiver
module and an Arduino Nano. The system's main job is to track the position of the driver's gaze.
When the device's Eye Blink Sensor detects that the driver is becoming drowsy, it will alarm
them with a piercing beep and reduce the vehicle's speed. A comprehensive outline of the
proposed project is depicted in the block diagram. The whole concept and its intended
implementation are shown in a single block diagram.

DEPT OF CSE, GECT Page 7

 DROWSY DRIVER DETECTION SYSTEM

3.2 ALGORITHM

Fig 3.2 : flow chart for drowsy driver detection system

DEPT OF CSE, GECT Page 8

 DROWSY DRIVER DETECTION SYSTEM

The technology for detecting drowsy drivers looks at whether or not all of the project's sensor modules
are working. This helps describe what goes into modules and what comes out of them. The eye blink
sensor shines infrared light on the eye and looks at how the light reflected back changes. The infrared
light reflected from the eye is used to figure out the results. When the eye is closed, the sensor output
is active high and can be sent directly to the microcontroller for interface purposes (e.g. buzzer).
Blinking is a biological process in which the eyelid closes quickly and partly on its own. Instead of
the full open and close, a single blink is defined by the forceful closing of the eyelid or the inactivation
of the levator palpebrae superioris and activation of the palpebral component of the orbicularis oculi.
The parts of the system for detecting drowsy drivers all work together to provide different services.
Building a base for something is what architecture design means. Subsystem control was part of the
original plans for all The parts of the system that looks for drowsy drivers are named. so that this is
what comes out of the design process. The architecture of the software is explained. A system's
framework can be made with simple structural and architectural design. way of building. The main
parts of the connections between the different parts of the system are taken into account.

DEPT OF CSE, GECT Page 9

 DROWSY DRIVER DETECTION SYSTEM

CHAPTER 4
REQUIREMENT SPECIFICATION

4.1 SYSTEM REQUIREMENTS

4.1.1 HARDWARE REQUIREMENTS

Processor : Any Processor above 500 MHz

RAM : 4GB

Hard Disk : More than 256GB

Input Device : System Camera

Output Device : High Resolution Monitor.

4.1.2 SOFTWARE REQUIREMENTS

Operating System : Windows 11 or higher

Programming : Python 3.10.0 and relatable libraries

IDE : Python IDE

DEPT OF CSE, GECT Page 10

 DROWSY DRIVER DETECTION SYSTEM

CHAPTER 5
SYSTEM DESIGN

The aim of this project is to develop prototype drowsiness detection and alerting system. The focus
will be placed on designing a system that will accurately monitor the eye blink rate, heart-beat
respiration rate and temperature of the driver. In this project we use sensors to measure all these
factors. The following figure shows the system design.

Fig 5.1: System model for Drowsy Driver Detection System

DEPT OF CSE, GECT Page 11

 DROWSY DRIVER DETECTION SYSTEM

5.2 MODULE DESCRIPTION

1. Face Detection

2. Eye Detection

3. Face Tracking

4. Eye Tracking

5. Drowsiness Detection

Detection

5.2.1 Face Detection

This module takes input from the camera using OpenCv and tries to detect a face in the video
input. The detection of the face is achieved through the Haar classifiers mainly, the Frontal face cascade
classifier. The face is detected in a rectangle format and converted to grayscale image and stored in the
memory which can be used for training the model.

5.2.2 Eye Detection

Since the model works on building a detection system for drowsiness we need to focus on the
eyes to detect drowsiness. The eyes are detected through the video input by implementing a haar classifier
namely Haar Cascade Eye Classifier. The eyes are detected in rectangular formats.

5.2.3 Face Tracking

Due to the real-time nature of the project, we need to track the faces continuously for any form of
distraction. Hence the faces are continuously detected during the entire time.

DEPT OF CSE, GECT Page 12

 DROWSY DRIVER DETECTION SYSTEM

5.2.4 Eye Tracking

The input to this module is taken from the previous module. The eyes state is determined through CNN
Classifier.

5.2.5 Drowsiness Detection

If the eye closed period of the driver is long , then the driver is alerted for the drowsiness through an
alert alarm from the system.

DEPT OF CSE, GECT Page 13

 DROWSY DRIVER DETECTION SYSTEM

CHAPTER 6

SYSTEM IMPLIMENTATION

6.1 Project Implementation

This system deals with maintenance of the prevention of accidents while driver driving the vehicles on
anti-sleep alarm glass alerting using Arduino. It prevent the accidents for drivers on night time.

6.2 Eye Aspect Ratio Calculation

If the aspect ratio of the eye indicates that they have been closed for greater than a dedicated fixed time,
we will sound an alarm system so that the driver wakes up.

Fig 6.1: Eye marks when the eye is open and Eye marks when the eye is closed Eye

DEPT OF CSE, GECT Page 14

 DROWSY DRIVER DETECTION SYSTEM

Aspect Ratio plotted over time, the downfall in the aspect ratio graph shows a blink of the driver We observe
the aspect ratio of the eye remains constant for a period of time indicating that the eye was open, then it
falls rapidly to zero and then increases again which indicates the person blinked We observe the aspect
ratio of the eye remains constant for a period of time indicating that the eye was open, then it falls rapidly
to zero and then increases again which indicates the person blinked We will be observing this eye aspect
ratio in our drowsiness detector case to see if the value remains constant or falls to zero but not increases
again implying that the driver has closed his eyes for extended period.

DEPT OF CSE, GECT Page 15

 DROWSY DRIVER DETECTION SYSTEM

CHAPTER 7
TESTING
7.1 Testing case

Following is the table representing four test cases that are to encountered while doing this
project that concerns with the drowsiness of the driver.

Test cases Eyes Eye Result

detected closure
Case 1 No No No result

Case 2 No No No result

Case 3 Yes No No alarm

Case 4 yes yes Alarm beeps

At the point when the eyes are shut for more than certain measure of edges then we find that
the driver is feeling tired. Henceforth these cases are distinguished is and a caution sounded.

7.2 Table and Analysis

Numerous examples with shifting exactness were assembled and consequently a table plotted for
them Every individual who volunteered for the test will be approached to squint multiple times
and act languid multiple times amid the test procedure. The eye squinting exactness was
determined by beneath referenced recipe

DEPT OF CSE, GECT Page 16

 DROWSY DRIVER DETECTION SYSTEM

Every individual who volunteered for the test will be approached to squint multiple times and act
languid multiple times amid the test procedure. The eye squinting exactness was determined by
beneath referenced recipe.

I/P Eyes detection acccuracy Drowsiness accuracy

Sample 1 100% 87.5%

Sample 2 95% 100%

Sample 3 80% 62.5%

Sample 4 100% 87.5%

Sample 5 100% 100%

TOTAL 95% 87.5%

Eye Detection Accuracy = total number of times eyes detected / (total no. of eyes detected+
total no of times eyes not detected)

Drowsiness Detection Accuracy = total no. of times alarm sounds / (total no. of times alarm
sounds + total no of times alarm didn’t sound)

DEPT OF CSE, GECT Page 17

 DROWSY DRIVER DETECTION SYSTEM

CHAPTER 8

RESULTS

DEPT OF CSE, GECT Page 18

 DROWSY DRIVER DETECTION SYSTEM

DEPT OF CSE, GECT Page 19

 DROWSY DRIVER DETECTION SYSTEM

DEPT OF CSE, GECT Page 20

 DROWSY DRIVER DETECTION SYSTEM

DEPT OF CSE, GECT Page 21

 DROWSY DRIVER DETECTION SYSTEM

DEPT OF CSE, GECT Page 22

 DROWSY DRIVER DETECTION SYSTEM

DEPT OF CSE, GECT Page 23

 CONCLUSION

The primary motive of this research is to provide a drowsiness detection system and a method that
detects the driver's drowsiness in real-time. Existing approaches have used vehicle-based and
psychological measurements to detect the drowsiness of the driver. However, such techniques are
highly intrusive and depend on the physical characteristics of the surrounding environment. In
contrast to the beforehand determined issues, we have proposed a system that implements a non-
intrusive technique for determining the driver’s fatigue. Our system consists of a Raspberry-Pi
and a Pi camera module that continuously keeps scanning for facial landmarks. These landmarks
are localized using facial landmark detector and then the eye landmarks are used to calculate the
eye aspect ratio (EAR). If the EAR value decreases from the threshold value and the eyes remain
closed for too long then the system immediately alerts the driver with the aid of a buzzer.
Furthermore, to ensure that the problem has been taken care of,a notification is sent to the owner
of the vehicle through e-mail when the driver dozes off for more than a couple of times. This
method is useful to people in the car rental and driving business such as truckers and taxi cab
drivers. However, there is one issue that remains to be addressed in the system, which is its
incapability to serve its purpose at night.
 REFERENCES

[1] A.Malla,P.Davidson,P.Bones,R.GreenandR.Jones,"AutomatedVideo-
basedMeasurementofEyeClosureforDetectingBehaviourMicrosleep".

[2] P. Viola and M. Jones, "Rapid Object Detection using a Boosted Cascade of Simple
Features",in Proceedings of the IEEE Computer Society Conference on Computer Vision
and PatternRecognition,2001.

[3] Ayman Altameem Ankit Kumar Ramesh Chandra Poonia Sandeep Kumar and Abdul
KhaderJilaniSaudagar “Early identification and detection of driver drowsiness by hybrid
machinelearning”

[4] T. Hong, H. Qin and Q. Sun, "An Improved Real Time Eye State Identification System
inDriverDrowsinessDetection".

[5] E.Varadharaj,R.Dharani,S.JeevithatheauthorpresentedthesystemwhichusedtheEigenface
sapproachforfacerecognition.

[6] D. Liu, P. Sun, Y. Xiao, and Y. Yin, "Drowsiness Detection Based on Eyelid Movement,"
inEducation[1]TechnologyandComputerScience(ETCS),2010SecondInternationalWork
shopon,2010,pp.49-52.

[7] T. Danisman, I. M. Bilasco, C. Djeraba, and N. Ihaddadene, "Drowsy driver detection

systemusingeye blink patterns," inMachine and Web Intelligence (ICMWI),2010
InternationalConference on,2010,pp.230-233.

[8] Qing, W., BingXi, S., Bin, X., &Junjie, Z. (2010, October). A perclos-based driver
fatiguerecognition application for smart vehicle space. In Information Processing (ISIP),
2010 ThirdInternationalSymposiumon (pp.437-441).IEEE.

[9] Bradski.G,Kaehler.A,-LearningOpenCV,O’Reilly,2008.