PROJECT REPORT

ON

Drowsiness Detectors for Drivers

SUBMITTED IN PARTIAL FULFILMENT OF THE REQUIREMENT FOR THE
DEGREE OF

SECOND YEAR ENGINEERING

In
COMPUTER ENGINEERING

By

Chaskar Shravani Exam. No: S190434246

Chauhan Priya Exam. No: S190434247
Dahihande Varadraj Exam. No: S190434250
Dalavi Vedant Exam. No: S190434252

Under the Guidance of

Prof.S.H.Thengil

Submitted to
DEPARTMENT OF COMPUTER ENGINEERING
STES’S SINHGAD ACADEMY OF ENGINEERING, PUNE-411048
2023-2024
 CERTIFICATE

This is to certify that the Project Report entitled

Drowsiness Detectors for Drivers

Submitted By

Chaskar Shravani Exam. No: S190434246

Chauhan Priya Exam. No: S190434247
Dahihande Varadraj Exam. No: S190434250
Dalavi Vedant Exam. No: S190434252

Is a bonafide work carried out by them under the supervision by Prof. S.H.Thengil and
it is approved for the partial fulfilment of the requirement of Savitribai Phule Pune
University for the Project in the second Year of Computer Engineering.

Prof.S.H.Thengil Prof. S.N.Shelke Dr. K. P. Patil

Guide H.O.D Principal

Dept. of Computer Engg. Dept. of Computer Engg.
SAOE, Pune

Place: Pune External Examiner Prof. P.J. Hajare

Date: / /2024 Project Co-ordinator

 ACKNOWLEDGEMENT

We would like to take this opportunity to thank all the people who were part of this
seminar in numerous ways, people who gave un-ending support right from the initial stage.
In particular we wish to thank Prof.S.H.Thengil as internal project guide who gave
their co-operation timely and precious guidance without which this project would not have
been a success. We thank them for reviewing the entire project with painstaking efforts and
more of his, unbanning ability to spot the mistakes.
We would like to thank our H.O.D Prof.S.N.Shelke for his continuous encouragement,
support and guidance at each and every stage of project.
And last but not the least we would like to thank all my friends who were Associated
with me and helped me in preparing my project. The project named “Drowsiness Detetctor
for Drivers” would not been possible without the extensive support of people who were
directly or indirectly involved in its successful execution.

Project Group Members:

Chaskar Shravani Exam. No: S190434246

Chauhan Priya Exam. No: S190434247

Dahihande Varadraj Exam. No: S190434250

Dalavi Vedant Exam. No: S190434252

 ABSTRACT

The proposed system aims to lessen the number of accidents that occur due to drivers’
drowsiness and fatigue, which will in turn increase transportation safety. This is becoming a
common reason for accidents in recent times. Several faces and body gestures are considered such
as signs of drowsiness and fatigue in drivers, including tiredness in eyes and yawning.
These features are an indication that the driver’s condition is improper. EAR (Eye
Aspect Ratio) computes the ratio of distances between the horizontal and vertical eye landmarks
which is required for detection of drowsiness. For the purpose of yawn detection, a YAWN value
is calculated using the distance between the lower lip and the upper lip, and the distance will be
compared against a threshold value. We have deployed an eSpeak module (text to speech
synthesizer) which is used for giving appropriate voice alerts when the driver is feeling drowsy or
is yawning.
The proposed system is designed to decrease the rate of accidents and to contribute to
the technology with the goal to prevent fatalities caused due to road accidents.

Keywords: Drowsiness, eSpeak module, Eye aspect ratio, Head Movements.

 Table of Contents

Acknowledgment iii
Abstract iv
Table of Contents v
List of Figures vii

Chapter 1 Introduction 1

1.1 Introduction
1.2 Motivation
1.3 Problem Statement
1.4 Objectives of the proposed work

Chapter 2 Literature Review

2.1 Literature Review

Chapter 3 Software Requirements

Chapter 4 System Design

Chapter 5 Results

Chapter 6 Conclusion
 INDEX

Sr. No. Title of Chapter Page No.

01 Introduction 1
1.1 Overview 1
1.2 Motivation 3
1.3 Problem Statement 4
1.4 Objectives of proposed work 5
02 Literature Survey 6
03 Software Requirements 9
3.1 System Requirements 9
3.1.1 Database Requirements 9
3.1.2 Software Requirements (Platform Choice) 9
3.1.3 Hardware Requirements 10
04 System Design 10
4.1 System Architecture 10
4.2 Data Flow Diagrams 11
4.3 UML Diagrams 12
4.4 Algorithm Details 13
05 Results 16
5.1 Outcomes 16
5.2 Screen Shots 17
06 Conclusions 18
6.1 Applications 18
6.2 Conclusions 19
6.3 Future Scope 20
References 21
Aditya Ranjan, Karan Vyas, Sujay Ghadge, Siddharth Patel,
Suvarna Sanjay Pawar, “Driver Drowsiness Detection System
Using Computer Vision.”, in International Research Journal of
Engineering and Technology(IRJET), 2020.
 LIST OF FIGURES

FIGURE ILLUSTRATION PAGE NO.

1.1 Drowsiness Detetction System 2

2.1 Alert System 8

2.2 Eye Lid ani Iris Tracking 8
4.1 High Level System Architecture 10
4.2.1 DFD Level – 0 10
4.2.2 DFD Level – 1 11
4.3.1 Use case Diagram 12
4.3.2 UML Diagram (A) 12
4.4.1 Facial Landmark Detection 13
4.4.2 EAR Calculation 14
4.4.3 Drowsiness Detection 14
4.4.4 Alert Generation 15
5.2.1 Awake Condition 17
5.2.3 Drowsy State Alert 17
 CHAPTER 1. INTRODUCTION

1.1 INTRODUCTION

In recent years, road accidents caused by driver drowsiness have become a significant
concern worldwide, leading to devastating consequences in terms of loss of life and property.
According to statistics from the World Health Organization (WHO), a substantial portion of road
accidents is attributed to drivers falling asleep or experiencing drowsiness behind the wheel. To
mitigate this alarming trend, advanced technologies are being harnessed to develop proactive
systems capable of detecting driver drowsiness in real-time.

Among the various technological approaches, computer vision emerges as a promising

solution due to its ability to analyze facial cues and physiological signals indicative of drowsiness.
By leveraging sophisticated algorithms and machine learning techniques, computer vision systems
can monitor drivers' facial expressions, eye movements, and other behavioral patterns to
accurately identify signs of fatigue or drowsiness.

This project presents a comprehensive exploration into the realm of drowsiness detection
using computer vision techniques. We delve into the underlying principles of computer vision
algorithms, including facial landmark detection, eye tracking, and image processing
methodologies, which form the backbone of our proposed drowsiness detection system.

Furthermore, we discuss the challenges associated with real-time drowsiness detection in

diverse driving conditions, such as varying lighting conditions, driver occlusions, and facial
expressions. Addressing these challenges requires the integration of robust computer vision
algorithms capable of robust performance under dynamic and unpredictable environments.

Moreover, we highlight the potential applications and societal impact of deploying

drowsiness detection systems in vehicles, ranging from enhancing road safety and preventing
accidents to reducing economic costs associated with traffic incidents and fatalities. In summary,
this project aims to contribute to the ongoing efforts in developing effective drowsiness detection
systems using computer vision technology. By advancing our understanding and implementation
of such systems, we strive towards a safer and more secure transportation ecosystem
for all road users.
[1]
SAE, Department of Computer Engineering 2023-24
 Fig 1.1. Drowsiness Detetction System

[2]
SAE, Department of Computer Engineering 2023-24
1.2 MOTIVATION

In recent years, road accidents caused by driver drowsiness have become a significant
concern worldwide, leading to devastating consequences in terms of loss of life and property.
According to statistics from the World Health Organization (WHO), a substantial portion of road
accidents is attributed to drivers falling asleep or experiencing drowsiness behind the wheel. To
mitigate this alarming trend, advanced technologies are being harnessed to develop proactive
systems capable of detecting driver drowsiness in real-time.

Among the various technological approaches, computer vision emerges as a promising

solution due to its ability to analyze facial cues and physiological signals indicative of drowsiness.
By leveraging sophisticated algorithms and machine learning techniques, computer vision systems
can monitor drivers' facial expressions, eye movements, and other behavioral patterns to
accurately identify signs of fatigue or drowsiness.

This project presents a comprehensive exploration into the realm of drowsiness detection
using computer vision techniques. We delve into the underlying principles of computer vision
algorithms, including facial landmark detection, eye tracking, and image processing
methodologies, which form the backbone of our proposed drowsiness detection system.

Furthermore, we discuss the challenges associated with real-time drowsiness detection in

diverse driving conditions, such as varying lighting conditions, driver occlusions, and facial
expressions. Addressing these challenges requires the integration of robust computer vision
algorithms capable of robust performance under dynamic and unpredictable environments.

In summary, this project aims to contribute to the ongoing efforts in developing effective
drowsiness detection systems using computer vision technology. By advancing our understanding
and implementation of such systems, we strive towards a safer and more secure transportation
ecosystem for all road users.

[3]
SAE, Department of Computer Engineering 2023-24
1.3 PROBLEM STATMENT

Despite significant advancements in automotive safety technology, road accidents caused by

driver drowsiness remain a pervasive and critical issue. The problem stems from the difficulty in
detecting drowsiness in real-time, especially in dynamic driving conditions where factors such as
varying lighting conditions, driver occlusions, and facial expressions pose significant challenges.

Current methods of drowsiness detection, including physiological sensors and manual

observation, are often intrusive, unreliable, or impractical for widespread deployment. There is a
clear need for a non-invasive, automated solution capable of accurately identifying signs of
drowsiness in drivers to prevent accidents and save lives.

The primary goal of this research is to develop an effective drowsiness detection system using
computer vision techniques. This system must be capable of robust performance under diverse
driving conditions, accurately analyzing facial cues and behavioral patterns indicative of
drowsiness in real-time.

Key challenges to address include:

1. Developing robust computer vision algorithms capable of accurately detecting facial landmarks
and tracking eye movements under varying lighting conditions and driver orientations.
2. Integrating machine learning models to analyze facial expressions and physiological signals to
accurately distinguish between alert and drowsy states.
3. Designing a real-time processing pipeline that can efficiently process video feeds from onboard
cameras and provide timely alerts to drivers when signs of drowsiness are detected.
4. Ensuring the system's reliability and effectiveness in preventing accidents while minimizing
false alarms and maintaining user privacy.

By addressing these challenges, our aim is to contribute to the development of proactive

drowsiness detection systems that enhance road safety and reduce the incidence of drowsiness-
related accidents on our roads.

[4]
SAE, Department of Computer Engineering 2023-24
1.4 OBJECTIVES OF PROPOSED WORK

1. Algorithm Development: Develop robust computer vision algorithms for detecting facial
landmarks, tracking eye movements, and analyzing facial expressions indicative of drowsiness.

2. Data Collection and Annotation: Collect a diverse dataset of annotated video footage
depicting drivers in various states of alertness and drowsiness to train and validate the proposed
algorithms.

3. Machine Learning Model Training: Train machine learning models using the collected
dataset to accurately classify driver states as alert or drowsy based on facial cues and behavioral
patterns.

4. Real-time Processing Pipeline: Design and implement a real-time processing pipeline capable
of efficiently processing video feeds from onboard cameras and detecting signs of drowsiness in
drivers.

5. Integration with Automotive Systems: Integrate the developed drowsiness detection system
with existing automotive systems, ensuring seamless interoperability and minimal performance
impact on vehicle operation.

6. Performance Evaluation: Conduct rigorous performance evaluation tests to assess the

accuracy, reliability, and computational efficiency of the proposed drowsiness detection system
under various driving conditions and scenarios.

7. User Interface Design: Design an intuitive user interface for drivers to interact with the
drowsiness detection system, providing timely alerts and recommendations to prevent accidents.

8. Validation and Deployment: Validate the effectiveness of the developed system through real-
world testing and validation studies, ensuring its readiness for deployment in commercial vehicles
to enhance road safety.

[5]
SAE, Department of Computer Engineering 2023-24
 CHAPTER 2. LITERATURE REVIEW

2.1 LITERATURE REVIEW

Sr.No Paper Author Year of Abstract

Name Publish
1. Driver Aditya 2020 A driver drowsiness detection system is
Drowsiness Ranjan, proposed that involves detection of driver
Detection Karan drowsiness by use of an algorithm. For detection
System Vyas, of drowsiness, the most relevant visual indicators
Using Sujay that reflect driver's condition is the eye behavior.
Computer Ghadge, The facial algorithm employed makes use of an
Vision Siddharth eye aspect ratio and physical landmark
Patel, measurements. Landmark detectors used in the
Suvarna algorithm demonstrate robustness against varied
Sanjay head orientations, facial expressions and lighting
Pawar conditions. The proposed real time algorithm will
estimate eye aspect ratio that measures eye open
level in each video frame. It perceives eye blink
pattern as EAR values. By doing so, potential
drowsiness is detected. A large number of road
mishaps occur due to drivers falling asleep due to
exhaustion or long-haul driving and negligence.
The proposed system under development can help
prevent the same by providing non-invasive and
easy to use specialized devices.
2. Driver Abhijit 2019 This proposed system can be used to reduce the
Drowsiness Khadke , number accidents on the road which are caused
Detection Ashutosh by the drowsiness or the tired driver. The system
System A. Nikalje proposed in this paper aim to reduce those
, Omkar J. numbers of Accidents. Several body gestures can
Domb , taken into considered as a sign of drowsiness and
Ajay H. fatigue of the driver. Tiredness of the eyes and
Jagadale , frequent yawning are indications that the driver
Suraj D. condition is improper. features are an indication
Bagdure that the driver’s condition is improper. EAR (Eye
Aspect Ratio) computes the ratio of distances
between the horizontal and vertical eye
landmarks which is required for detection of
drowsiness. For the purpose of yawn detection, a
YAWN value is calculated using the distance
between the lower lip and the upper lip, and the
distance will be compared against a threshold
value The proposed system is designed to
decrease the rate of accidents and to contribute to
the technology with the goal to prevent fatalities
caused due to road accidents.

[6]
SAE, Department of Computer Engineering 2023-24
Sr.No Paper Author Year of Abstract
Name Publish
3. The Chris 2019
detection of Schwarz, Drowsiness is a major cause of driver impairment
drowsiness John leading to crashes and fatalities. Research has
using a Gaspar, established the ability to detect drowsiness with
driver Thomas various kinds of sensors. We studied drowsy
monitoring Miller & driving in a high-fidelity driving simulator and
system Reza evaluated the ability of an automotive production-
Yousefian ready driver monitoring system (DMS) to detect
drowsy driving. Additionally, this feature was
compared to and combined with signals from
vehicle-based sensors.The National Advanced
Driving Simulator was used to expose drivers to
long, monotonous drives. Twenty participants
drove for about 4 h in the simulator between 10
p.m. and 2 a.m. They were allowed to use cruise
control and traffic was sparse and semirandom,
with both slower- and faster-moving vehicles.
Observational ratings of drowsiness (ORDs) were
used as the ground truth for drowsiness, and
several dependent measures were calculated from
vehicle and DMS signals. Drowsiness
classification models were created that used only
vehicle signals, only driver monitoring signals,
and a combination of the 2 sources.

4. Computer Rahul Atul 2019 Since the advent of high-speed motorized vehicles
Vision based drowsy driving accidents have claimed the lives
Bhope
drowsiness of millions of people across the globe. With more
detection for research happening in advanced high-speed
motorized engines, the risk of such accidents has increased
vehicles with ten-fold times. To avoid such accidents, this paper
Web Push proposes a Computer Vision-basedsystem
Notifications drowsiness system for motorized vehicles with
Web Push Notifications to notify the driver before
any accident occurs. A real-time video system
captures the face of the driver and a pre-trained
machine learning model detects the eye
boundaries from that real-time video stream. Then
each eye is represented by 6 - coordinates (x,y)
starting from the left corner of the eye and then
working clockwise around the eye. The EAR (Ear
Aspect Ratio) is calculated for 20 consecutive
frames, which if less than a threshold sounds an
alarm and sends an alert on your mobile device
through a Web Push Notification. The alert when
opened also shows some coffee shops near the
driver's location to increase the driver's alertness.

[7]
SAE, Department of Computer Engineering 2023-24
 Fig 2.1 Alert System

Fig 2.2 Eye Lid and Iris Tracking

[8]
SAE, Department of Computer Engineering 2023-24
 CHAPTER 3.SOFTWARE REQUIREMENTS

3.1 DATABASE REQUIRMENTS

a. Storage for storing historical data (optional, for analysis and reporting)
b. Database management system (DBMS) for storing and querying data (optional, depending
on the need for data logging and analysis)

3.2 SOFTWARE REQUIRMENTS

a. Operating system compatibility (e.g., Windows, Linux, macOS)

b. Programming languages and frameworks (e.g., Python, TensorFlow, OpenCV)
c. Image processing libraries for facial detection and recognition
d. Machine learning libraries for training and inference (e.g., TensorFlow, PyTorch)
e. Real-time processing capabilities for continuous monitoring.
f. Integration with alerting mechanisms (e.g., sound alarms, visual alerts)

3.3 HARDWARE REQUIRMENTS

a. Camera hardware with suitable resolution and frame rate.

b. Sufficient processing power (CPU/GPU) for real-time image processing and analysis.
c. Memory (RAM) for storing and processing image data.
d. Storage space for storing trained models, data, and logs.
e. Power supply for continuous operation (if deployed in vehicles or other mobile settings)

Additionally, considerations may need to be made for deployment environments (e.g.,

vehicles, workplaces) and any regulatory requirements related to privacy and data protection. The
system should also be designed to handle various lighting conditions and environmental factors
that may affect drowsiness detection accuracy.

[9]
SAE, Department of Computer Engineering 2023-24
 CHAPTER 4. SOFTWARE DESIGNS

4.1 SYSTEM ARCHITECTURE

Fig.4.1. High-Level System Architecture

4.2 DATA FLOW DAIGRAMS

Fig.4.2.1 Data Flow Diagram

[10]
SAE, Department of Computer Engineering 2023-24
 Fig.4.2.2 DFD Level 1

[11]
SAE, Department of Computer Engineering 2023-24
4.3 UML DIAGRAMS

Open cv Application

Fig.4.3.1 UML Diagram

Fig.4.3.2 UML Diagram (A)

[12]
SAE, Department of Computer Engineering 2023-24
4.4 ALGORITHM DETAILS

1. Face Detection and Landmark Detection: Utilize dlib's pre-trained face detector and facial
landmark detector to detect faces and locate key facial landmarks such as eyes, eyebrows, and
mouth.

Fig 4.4.1 Facial Landmark Detection

2. Eye Aspect Ratio (EAR) Calculation: Calculate the EAR using the detected facial landmarks.
You can use the formula for EAR calculation:

EAR = (||P2 - P6|| + ||P3 - P5||) / (2 * ||P1 - P4||)

Where P1 to P6 represent specific facial landmarks around the eyes.

[13]
SAE, Department of Computer Engineering 2023-24
 Fig.4.4.2 EAR Calculation

3. Drowsiness Detection: Monitor changes in the EAR over time. When the EAR falls below a
certain threshold, it indicates that the eyes are closing or drooping, suggesting drowsiness. You
can set a threshold based on experimentation or prior research.

Fig 4.4.3 Drowsiness Detection

[14]
SAE, Department of Computer Engineering 2023-24
4. Alert Generation: When drowsiness is detected, trigger an alert to notify the individual. This
could be a sound alarm, visual warning, or any other form of alert.

Fig 4.4.4 Alert Generation

[15]
SAE, Department of Computer Engineering 2023-24
 CHAPTER 5.RESULTS

5.1 OUTCOMES

1. Real-time Alert System: The system can provide real-time alerts to the individual, such as
visual or auditory warnings, when signs of drowsiness are detected. This could include messages
like "Take a break" or "Stay awake" to prompt the person to take necessary actions to prevent
accidents.

2. Data Logging and Analysis: The system can log data on instances of drowsiness detection
over time, including frequency, duration, and severity of drowsy episodes. This data can be
analyzed to identify patterns and trends, helping individuals understand their sleep patterns and
make lifestyle adjustments accordingly.

3. Integration with Vehicles or Machinery: Drowsiness detection systems can be integrated into
vehicles or machinery to automatically alert drivers or operators when they are becoming drowsy.

4. Customizable Thresholds and Alerts: Users may have different thresholds for drowsiness or
preferences for alert types. The system can be designed to allow customization of detection
thresholds and alert settings to accommodate individual preferences and needs.

5. Remote Monitoring and Support: In scenarios where individuals are operating vehicles or
machinery as part of their job, drowsiness detection systems can provide remote monitoring
capabilities. Supervisors or support staff can receive alerts when drowsiness is detected, allowing
them to intervene or provide assistance as needed.

6. Behavioral Feedback and Coaching: Over time, the system can provide feedback and
coaching to help individuals improve their sleep habits and reduce instances of drowsiness. This
could include suggestions for better sleep hygiene, relaxation techniques, or reminders to take
regular breaks during long periods of activity.

[16]
SAE, Department of Computer Engineering 2023-24
5.2 SCREENSHOTS

Fig 5.2.1Awake Condition

Fig 5.2.2 Drowsy State Alert

[17]
SAE, Department of Computer Engineering 2023-24
 CHAPTER 6. CONCLUSION

6.1 APPLICATIONS

1. Transportation Safety: Integrating drowsiness detection systems into vehicles (cars, trucks,
buses, trains, etc.) to alert drivers when they exhibit signs of drowsiness, thereby reducing the risk
of accidents due to driver fatigue.

2. Workplace Safety: Implementing drowsiness detection in industries where alertness is critical,

such as manufacturing, construction, and healthcare, to prevent accidents and errors caused by
sleepy workers.

3. Aviation: Incorporating drowsiness detection technology into cockpit systems to monitor pilot
alertness and prevent incidents related to fatigue during flight operations.

4. Public Safety: Deploying drowsiness detection in surveillance systems in public spaces (e.g.,
airports, train stations, stadiums) to identify individuals who may pose a risk due to fatigue or
sleep deprivation.

5. Healthcare Monitoring: Utilizing drowsiness detection in medical settings to monitor patients'

sleep patterns, assess the effectiveness of treatments for sleep disorders, and enhance patient safety
in hospitals and long-term care facilities.

6. Education and Research: Employing drowsiness detection technology in educational and

research settings to study sleep patterns, fatigue, and cognitive performance, and develop
interventions to improve sleep quality and alertness.

7. Consumer Electronics: Integrating drowsiness detection features into wearable devices (e.g.,
smartwatches, fitness trackers) and smartphones to provide users with personalized insights into
their sleep habits and promote healthier sleep behaviors.

[18]
SAE, Department of Computer Engineering 2023-24
6.2 CONCLUSION

This project is about drowsiness detection using computer vision could highlight the
effectiveness of such systems in identifying signs of drowsiness based on visual cues like eye
movements, head position, and facial expressions. It could also emphasize the potential benefits
in various fields such as transportation safety, workplace monitoring, and healthcare.
Additionally, it might mention ongoing challenges like real-time processing, accuracy
improvement, and ensuring privacy and ethical considerations in deploying such systems. Overall,
the conclusion could stress the promising future of drowsiness detection using computer vision
technology with continued research and development efforts.

[19]
SAE, Department of Computer Engineering 2023-24
6.2 FUTURE SCOPE
1. Enhancing Accuracy: Continuously improving algorithms to accurately detect subtle signs of
drowsiness in various environmental conditions and diverse populations.

2. Real-Time Implementation: Developing real-time processing capabilities to enable

instantaneous detection and timely interventions, particularly in critical settings like
transportation.

3. Integration with AI: Integrating advanced artificial intelligence techniques such as deep
learning for more robust and adaptive drowsiness detection systems.

4. Multimodal Approaches: Exploring the combination of computer vision with other modalities
such as physiological signals to enhance detection accuracy and reliability.

5. Wearable Devices: Designing wearable devices equipped with computer vision technology to
provide continuous monitoring of drowsiness levels in real-world scenarios.

6. Human Factors Research: Conducting studies to understand user acceptance, usability, and
potential societal impacts of deploying drowsiness detection systems in various contexts.

7. Privacy and Ethical Considerations: Addressing concerns related to privacy, data security,
and potential biases inherent in computer vision algorithms, ensuring responsible deployment and
adherence to ethical guidelines.

[20]
SAE, Department of Computer Engineering 2023-24
 REFERENCES

1. X. Fan, B. Yin, and Y. Sun, "Yawning detection for monitoring driver fatigue", Proceedings of
the International Conference on Machine Learning and Cybernet, vol. 2, pp. 664-668, Aug. 2007.
2. L. Li, Y. Chen and Z. Li, "Yawning detection for monitoring driver fatigue based on two
cameras", Proceedings of the 12th International IEEE Conference Intelligent Transportation
Systems., pp. 1-6, Oct. 2009.
3. T. Danisman, I.M. Bilasco, C. Djeraba and N. Ihaddadene, “Drowsy driver detection system
using eye blink patterns,” Universite Lille 1 & Telecom Lille 1, Marconi, France, 2010.
4. S. Abtahi, B. Hariri and S. Shirmohammadi, "Driver drowsiness monitoring based on yawning
detection", Proceedings of the IEEE International Control, Measurement and Instrumentation
(CMI), IEEE, pp. 1-4, May 2011.
5. Z. Mardi, S. N. Ashtiani, and M. Mikaili, “EEG-based drowsiness detection for safe driving
using chaotic features and statistical tests,” Journal of Medical Signals and Sensors, vol. 1, pp.
130–137, 2011.
6. Rahul Atul Bhope, “Computer Vision based drowsiness detection for motorized vehicles with
Web Push Notifications”, IEEE 4th International Conference on Internet of Things, IEEE,
Ghaziabad, India, 2019.
7. Jasper S. Wijnands, Jason Thompson, Kerry A. Nice, Gideon D. P, Aschwanden & Mark
Stevenson, “Real-time monitoring of driver drowsiness on mobile platforms using 3D neural
networks”, Neural Computing and Applications, 2019.
8. Chris Schwarz, John Gaspar, Thomas Miller & Reza Yousefian, “The detection of drowsiness
using a driver monitoring system” , in Journal of Traffic Injury Prevention (Taylor and Francis
Online), 2019.
9. B.Mohana, C.M.Sheela Rani, “Drowsiness Detection Based on Eye Closure and Yawning
Detection”, in International Research Journal of Engineering and Technology(IRJET), 2019.
10. Aditya Ranjan, Karan Vyas, Sujay Ghadge, Siddharth Patel, Suvarna Sanjay Pawar, “Driver
Drowsiness Detection System Using Computer Vision.”, in International Research Journal of
Engineering and Technology(IRJET), 2020.

[21]
SAE, Department of Computer Engineering 2023-24