Scribd
Upload
3 views

Report Final Front

The project report presents an optimized driver alertness monitoring system that utilizes eye aspect ratio and facial landmark analysis to detect drowsiness in real-time, enhancing road safety. It integrates computer vision and machine learning techniques to provide alerts and recommendations for rest stops based on driver fatigue levels. The system aims to mitigate fatigue-related accidents by offering immediate feedback through audio warnings and notifications.

Uploaded by

bombaipothavaraja
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
3 views

Report Final Front

The project report presents an optimized driver alertness monitoring system that utilizes eye aspect ratio and facial landmark analysis to detect drowsiness in real-time, enhancing road safety. It integrates computer vision and machine learning techniques to provide alerts and recommendations for rest stops based on driver fatigue levels. The system aims to mitigate fatigue-related accidents by offering immediate feedback through audio warnings and notifications.

Uploaded by

bombaipothavaraja
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 9

OPTIMIZED DRIVER ALERTNESS MONITORING

SYSTEM USING EYE ASPECT RATIO AND FACIAL


LANDMARK ANALYSIS

A PROJECT REPORT

Submitted by

KIRUBASHANKAR A(727721EUIT079)

KAVIN S(727722EUIT509)

MUHILAN D S(727721EUIT094)

In partial fulfillment for the award of the degree

Of

BACHELOR OF TECHNOLOGY

IN

INFORMATION TECHNOLOGY

SRI KRISHNA COLLEGE OF ENGINEERING AND TECHNOLOGY


An Autonomous Institution | Approved by AICTE | Affiliated to Anna University | Accredited by NAAC with A++ Grade
Kuniamuthur, Coimbatore – 641008.

APRIL 2025
SUSTAINABLE DEVELOPMENT GOALS

The Sustainable Development Goals are a collection of 17 global goals designed to


blue print to achieve a better and more sustainable future for all. The SDGs, set in
2015 by the United Nations General Assembly and intended to be achieved by the
year 2030, In 2015, 195 nations agreed as a blue print that they can change the world
for the better. The project is based on one of the 17 goals.

Questions Answer Samples


Which SDGs does the project directly SDG 3 –Good wealth and health
address? being.
What strategies or actions are being LiDAR data updates HD maps for
implemented to achieve these goals? better navigation.
How is progress measured and reported Progress is tracked by accuracy,
in relation to the SDGs? speed, and map updates.
How were these goals identified as Improves mobility, infrastructure, and
relevant to the project’s objectives? transport safety.
Are there any partnerships or Collaborates with LiDAR providers,
collaborations in place to enhance this mapping firms, and transport agencies.
impact?
BONAFIDE CERTIFICATE

Certified that this project report “OPTIMIZED DRIVER ALERTNESS


MONITORING SYSTEM USING EYE ASPECT RATIO AND FACIAL
LANDMARK ANALYSIS” is the bonafide word of “KIRUBASHANKAR A
(727721EUIT079), KAVIN S (727722EUIT509), MUHILAN D S
(727721EUIT094)” who carried out the project work under my supervision.

SIGNATURE SIGNATURE

Dr.S.Venkata Lakshmi Dr.U.M.Ramya

HEAD OF THE DEPARTMENT SUPERVISOR

Professor Assistant Professor


Department of Information Technology Department of Information Technology
Sri Krishna College of Engineering and Sri Krishna College of Engineering and
Technology, Coimbatore Technology, Coimbatore

Submitted for the Project viva-voce examination held on

INTERNAL EXAMINER EXTERAL EXAMINER


ABSTRACT

This study proposes a real-time driver drowsiness detection system leveraging


computer vision and machine learning techniques to enhance road safety. The
system begins with a calibration phase to determine a personalized Eye Aspect Ratio
(EAR) threshold, crucial for accurately distinguishing between open and closed eye
states. Using a live video feed, the system analyzes facial landmarks to compute
EAR, detect yawning through mouth aspect ratio calculations, and assess head
posture for signs of fatigue. By integrating these parameters, the system identifies
drowsiness with high precision and triggers appropriate alerts. Audio warnings and
on-screen notifications provide immediate feedback, while persistent fatigue
prompts recommendations for nearby resting spots using Google Maps integration.
This comprehensive solution offers a reliable approach to mitigating fatigue-related
accidents, ensuring a safer driving experience.
TABLE OF CONTENTS

CHAPTER .NO TITLE PAGE NO.


ABSTRACT iv
LIST OF TABLES v
LIST OF FIGURES viii
LIST OF ABBREVIATIONS ix
1. 1. INTRODUCTION 1
1.1 DROWSINESS DETECTION 1
1.2 EYE ASPECT RATIO 2
1.3 DRIVER SAFETY 3
1.4 FACIAL LANDMARK DETECTION 3
1.5 OBJECTIVES 4

2. LITERATURE SURVEY 5
2.1 DRIVER FATIGUE DETECTION 5
2.2 PRIVACY PRESERVATION
COMPUTATION 6
2.3 IMPLEMENTATION OF CKKS
SCHEME 7
2.4 FEDERATED LEARNING TO
FEDERATED NEURAL NETWORK 8
2.5 FEDERATED LEARNING FOR IOT 9
2.6 DEEP TRANSFER LEARNING FOR
ANOMOLY DETECTION 10
2.7 CONTRASTIVE LEARNING FOR
ROBUST SCENE TRANSFER 11
2.8 REINFORCEMENT LEARNING 13
2.9 FEDERATED LEARNING 14
2.10 SENSITIVE ATTRIBUTE
PROTECTION 15
3. SYSTEM ANALYSIS 16
3.1 EXISTING SYSTEM 16
3.1.1 Drawbacks 16
3.2 PROPOSED SYSTEM 17
3.2.1 Advantages 17
3.3 FEASIBILITY STUDY 18
3.3.1 Technical Feasibility 18
3.3.2 Operational Feasibility 19
3.3.3 Economical Feasibility 19

4. SYSTEM SPECIFICATION 20
4.1 HARDWARE CONFIGURATION 20
4.2 SOFTWARE SPECIFICATION 20

5. SOFTWARE DESCRIPTION 29
5.1 FRONT END 21

6. PROJECT DESCRIPTION 27
6.1 PROBLEM DEFINITION 27
6.2 MODULE DESCRIPTION 27
6.2.1 Webcam 27
6.2.2 Detect face 27
6.2.3 Alert System Module 28
6.2.4 Drowsiness Detection 28
6.3 SYSTEM FLOW DIAGRAM 29
6.4 INPUT DESIGN 30
6.5 OUTPUT DESIGN 30

7. SYSTEM TESTING AND IMPLEMENTATION 31


7.1 SYSTEM TESTING 31
7.2 SYSTEM IMPLEMENTATION 31
8. SYSTEM MAINTENANCE 32
8.1 CORRECTIVE MAINTENANCE 33
8.2 ADAPTIVE MAINTENANCE 33
8.3 PERFECTIVE MAINTENANCE 33
8.4 PREVENTIVE MAINTENANCE: 34

9. CONCLUSION AND FUTURE 36


ENHANCEMENT
10. APPENDICES 37
10.1 SOURCE CODE 37
10.2 SCREEN SHOTS 53

11. REFERENCES
LIST OF FIGURES

FIGURE NO. TITTLE PAGE NO.

1 Driver Drowsiness 2

2 Eye Aspect Ratio 2

3 Driver Safety 3

4 Facial Landmark Detection 4


LIST OF ABBREVIATIONS

ABBREVIATION FULL FORM

EAR Eye Aspect Ratio

CNN Convolutional Neural Network

FL Federated Learning

CLI Cloud Line Interface

ANN Artificial Neural Network

PFDL Production flow Description


Language

You might also like