VISVESVARAYA TECHNOLOGICAL UNIVERSITY

"Jnana Sangama", Belgaum: 590018

Technical Seminar (18CSS84)

Report on

Advancements In Driver Drowsiness Detection

Submitted in partial fulfillment of the requirement for the award of the degree of
Bachelor of Engineering
In
Computer Science & Engineering

Submitted by

Karthik . K. S
1AY20CS067

Under the guidance of

Mrs. Bharathi K.
Assistant Professor
Dept. of CS&E,
AIT, Bangalore

ACHARYA INSTITUTE OF TECHNOLOGY

DEPARTMENT OF COMPUTER SCIENCE & ENGINEERING
(Affiliated to Visvesvaraya Technological University, Belgaum,
Approved by AICTE, New Delhi and Accredited by NBA and NAAC)
Soladevanahalli, Bangalore – 560107
2023-2024
ACHARYA INSTITUTE OF TECHNOLOGY
(Affiliated to Visvesvaraya Technological University, Belgaum,
Approved by AICTE, New Delhi and Accredited by NBA and NAAC)
Soladevanahalli, Bangalore – 560107

DEPARTMENT OF COMPUTER SCIENCE & ENGINEERING

Certificate

This is to certify that the seminar titled “Advancements in Driver Drowsiness Detection” is
presented by Karthik .K.S in partial fulfillment of the award of the degree of Bachelor of
Engineering in Computer Science and Engineering of Visvesvaraya Technological
University, Belgaum during the year 2023-24. It is certified that all corrections / suggestions
indicated during seminar presentation have been incorporated in the report. The seminar report
(18CSS84) has been approved as it satisfies the academic requirements in respect of seminar
presentation prescribed for the Bachelor of Engineering degree.

Technical Seminar Guide Technical Seminar Coordinator Head of the Department

Mrs. Bharathi .K Mrs. Deeksha/Mrs. Shruthi N G Dr. Ajith Padyana

Assistant Professor Assistant Professor Dept. of CS&E,
Dept. of CS&E, Dept. of CS&E, Acharya Institute of Technology,
Acharya Institute of Technology, Acharya Institute of Technology, Bangalore
Bangalore Bangalore
 ACKNOWLEDGEMENT
I express my gratitude to our institution and management for providing me with good infrastructure,
laboratory facilities and inspiring staff, and whose gratitude was of immense help in completion of
<Write your Technical seminar topic here> successfully.

I express my sincere gratitude to Dr. Rajath Hegde, Principal, Acharya Institute of Technology,
Bangalore and Mr. Marigowda C K, Vice Principal, Acharya Institute of Technology, Bangalore
for providing me the required environment in completion of this technical seminar.

My sincere thanks to Dr. Ajith Padyana, Head of the Department, Computer Science and
Engineering, Acharya Institute of Technology for his valuable support and also for rendering me
the resources for the technical seminar.

I heartily thank my guide, Mrs. Bharathi .K , Technical Seminar coordinators from Department of
Computer Science and Engineering, Acharya Institute of Technology who guided me with their
valuable suggestions at every stage for completing this technical seminar.

My gratitude is rendered to everyone who helped me in all possible ways.

Karthik.K.S
1AY20CS067

i
 ABSTRACT
It is a Data science project as the data is collected in real-time. The data so collected is the eye motion of the
driver, his body posture, and facial movements. These are then fed as information into the program that is
written using python.

This system already exists in multiple high-end cars and vehicles. Since the statistics majorly reflect that most
of our Indian cars do not feature this particular functionality, it gave me the motiveto develop such a system.
We often see newspaper articles where accidents occurred as drivers felt drowsy and hit the vehicle in front of
them. This could have been avoided if their vehicle were fitted with a technological feature called “The
drowsiness Detection System” which off-late is seenin higher-end vehicles. We have used Open Libraries
such as (Open CV, Dlib, Flask,Pyhton IDLE) is a open-source distribution of the python programming
language for data science that aims to simplify package management and deployment.

ii
 TABLE OF CONTENTS

Acknowledgement………………………………………………………………………………i
Abstract………………………………………………………………………………………....ii
Table of Contents………………………………………………………………………….......iii
List of figures…………………………………………………………………………………..iv

Chapter no. Chapter name Page no.

01 Introduction 01 – 03
02 Literature Review 04
03 Methadology 05 – 09
04 Results 10
05 Conclusion 11
06 References 12

iii
 List of Figures

Figure no Figure name Page no.

1.1 Representation of driver 01
drowsiness detection
3.1 Visual Representation of 05
Detection process
3.3 System architecture 07
3.4 Flowchart 08

List of Tables

Sl no. Table name Page no.

01 Literature Survey 04
02 Test Cases 10

iv
 Driver Drowsiness Detection 2023-2024

CHAPTER 1

INTRODUCTION

Driver drowsiness detection system is a Data Science project that helps in identifying
the drowsiness of drivers at an early stage and avoids accidents and unforeseen
circumstances.

We regard this as a data science project as the data is collected in real-time. The data
so collected is the eye motion of the driver, his body posture, and facial movements.
These are then fed as information into the program that is written using python. Open
libraries such as Open CV (Open Computer Vision), Dlib (For facial recognition),
matplotlib are used to facilitate the detection.

It is a car safety technology which helps prevent accidents caused by the driver
getting drowsy. Various studies have suggested that around 20% of all road accidents
are fatigue-related, up to 50% on certain roads.

This system already exists in multiple high-end cars and vehicles. Since the statistics
majorly reflect that most of our Indian cars do not feature this particular functionality,
it gave me the motive to develop such a system.

Figure: 1.1 Representation of drowsiness detection

Department of CSE, AIT, Bangalore-107 Page 1

Driver Drowsiness Detection 2023-2024

1.1 Problem statement

 Driver drowsiness is a significant factor contributing to road accidents,

resulting in injuries, fatalities, and property damage.
 To address this issue and improve road safety, there is a need for an effective
driver drowsiness detection system.
 The goal is to develop a system capable of detecting signs of drowsiness in
real-time and alerting drivers to take appropriate actions to prevent accidents.

Department of CSE, AIT, Bangalore-107 Page 2

Driver Drowsiness Detection 2023-2024

1.2 Objective

• Provide instant alerts and warnings when the signs of drowsiness are detected
• Enable the system to recognize signs of drowsiness at an early stage
• Implement a system that continuously monitors the driver’s state .
• Contribute significantly to road safety and reduce risk .
• Encourage drivers to prioritize adequate rest and sleep, promoting healthier
and safer driving habits.
• Develop user-friendly interfaces and systems that are easy to use and
understand, ensuring widespread adoption and compliance among drivers.

Department of CSE, AIT, Bangalore-107 Page 3

Driver Drowsiness Detection 2023-2024

CHAPTER 2
LITERATURE SURVEY
 The table below shows the literature survey based on researches made in
recent days.

Table 2.1 Literature Survey

Department of CSE, AIT, Bangalore-107 Page 4

 Driver Drowsiness Detection 2023-24

CHAPTER 3

IMPLEMENTATION

3.1 Proposed System

Since this project is a pilot run, We would be implementing this as a simulation on
our laptop. This is an attempt to tell or inform the driver that he is drowsy and he
needs to be alert. It raises an alert when the facial movements detected by the webcam
of the computer generate a voice message to be alert. The continues detection of eye-
lid movement is being monitored using a threshold flag variable which is responsible
for activation of the system.

This system is developed using

 Python language.
 Open Libraries such as (Open CV, Dlib, Flask)
 Python IDLE

Fig 3.1 Visual Representation of Detection Process.

Department of CSE, AIT, Bangalore-107 Page 5

Driver Drowsiness Detection 2023-24

3.2 System Requirement

Software requirement:

• Operating system: macOS, Windows XP/7 or higher.

• Coding language: Python , HTML.
• Platform: Python IDLE.

Hardware requirement:

• Webcam.
• Monitor with HardDisk 500gb.
• Processor I3 with RAM 8gb.
• Webcam

Department of CSE, AIT, Bangalore-107 Page 6

 Driver Drowsiness Detection 2023-24

3.3 System Architecture

It is a conceptual model that describes the structure and behavior of multiple

components and subsystems like multiple software applications, network devices,
hardware, and even other machinery of a system. It is Architecture Description
Language (ADL) which helps to describe the entire system architecture. So, it is a
much broader topic. System architecture can be broadly categorized into centralized
and decentralized architectural an organization.
A software architecture is a set of principles that define the way software is designed
and developed. An architecture defines the structure of the software system and how it
is organized. It also describes the relationships between components, levels of
abstraction, and other aspects of the software system.

An architecture can be used to define the goals of a project, or it can be used to guide
the design and development of a new system. A software architecture is a set of
principles that define the way software is designed and developed. An architecture
defines the structure of the software system and how it is organized.

Drowsiness Detection System

Behavioral Approach

Eyes Face Head Yawing

Fig 3.3 System Architecture Representation

Department of CSE, AIT, Bangalore-107 Page 7

Driver Drowsiness Detection 2023-24

3.4 Methodology

Fig:3.4 Flowchart.

Department of CSE, AIT, Bangalore-107 Page 8

Driver Drowsiness Detection 2023-24

• Importing Required Libraries : Import necessary libraries such as Flask for

web development, OpenCV for computer vision tasks, dlib for face detection
and facial landmark recognition, numpy for numerical operations, and pygame
for playing audio files.
• Initializing Flask app : Create a Flask application instance.
• Initializing Sound Effects : Initialize sound effects using pygame for alerts such
as no driver detected, sleep detected, etc.
• Defining Utility Function : Define functions for computing distances between
facial landmarks, detecting eye blinks, calculating mouth aspect ratio, and
checking for driver fatigue.
• Main Detection Loop : This function continuously captures frames from the
webcam, detects faces, and analyzes facial landmarks to determine the driver's
state. It checks for eye blinks, mouth aspect ratio, and the absence of a driver.
Depending on the state, appropriate actions are taken, such as playing sound
alerts or updating the status displayed on the screen.
• Flask Routes:
• /open_camera: This route starts the detection process by calling the detech
function.
• /: This route renders the home page, which could be an HTML template where
you might display the webcam feed and driver status.
• Running Flask App : Finally, the Flask application is run with debugging
enabled.

Department of CSE, AIT, Bangalore-107 Page 9

 Driver Drowsiness Detection 2023-24

CHAPTER 4
RESULTS

Test Case No. Test Case Expected output

1 Webcam Access See the Face (Capture

Face)
Webcam Access Error No Face Detected

2 Webcam Access with Posture Detected (Raise

Face Detected alarm if sleepy).

Webcam Access with Yawn Detected (Raise

Face Detected alarm if sleepy).

Webcam Access with Eye Closure Detected

Face Detected (Raise alarm if Closed)
If flag reach maximum.
End the Detection

Table 4.1 Test Cases.

Department of CSE, AIT, Bangalore-107 Page 10

Driver Drowsiness Detection 2023-24

CHAPTER 5

CONCLUSION

The drowsiness detection and correction system developed is capable of

detecting drowsiness in a rapid manner .The system which can differentiate
normal eye blink and drowsiness which can prevent the driver from entering
the state of sleepiness while driving .When the eyes have been closed for
about two seconds, the alarm beeps to alert the driver and speed of the
vehicle is reduced .Using drowsiness detection system, driver safety can be
implemented in normalcars also.

Department of CSE, AIT, Bangalore-107 Page 11

 Driver Drowsiness Detection 2023-24

REFERENCES
[1] https://pyimagesearch.com/2017/05/08/drowsiness-detection-opencv/

[2] https://www.pantechsolutions.net/driver-drowsiness-detection-using-opencv-and-python

[3] https://data-flair.training/blogs/python-project-driver-drowsiness-detection-system/

[4] https://en.wikipedia.org/wiki/Driver_drowsiness_detection

Department of CSE, AIT, Bangalore-107 Page 12