VISVESVARAYA TECHNOLOGICAL UNIVERSITY

“JNANA SANGAMA” BELAGAVI-590018, KARNATAKA

MINI PROJECT REPORT on “DROWSY DRIVER

DETECTION SYSTEM”

Submitted in the fulfillment of the requirement of the award of

Bachelor of Engineering
In
Computer Science and Engineering
Submitted By
NAME USN
PUNEETH KUMAR M 1BO22CS054
SANDESH K 1BO22CS060
DARSHAN K K 1BO23CS401
NIKHIL T 1BO23CS403
Under The Guidance of
Prof.DIKSHA M
Dept. Computer Science and Engineering

Brindavan College of Engineering

Dwarakanagar, Bagalur Main Road, Yelahanka, Bengaluru – 560063
Affiliated to VTU Belagavi, Approved by AICTE, New Delhi, India
Accredited ‘B++’ level by NAAC

2024-2025
 Brindavan College of Engineering
Dwarakanagar, Bagalur Main Road, Yelahanka, Bengaluru – 560063
Affiliated to VTU Belagavi, Approved by AICTE, New Delhi, India
Accredited ‘B++’ level by NAAC

2024-2025
Department of Computer Science and Engineering
CERTIFICATE

This is to certify that the Mini Project work entitled “Drowsy Driver Detection
System” is a Bonafide work carried out by PUNEETH KUMAR M (1BO22CS054),
SANDESH K (1BO22CS060), DARSHAN K K (1BO23CS401), NIKHIL T
(1BO23CS403) in partial fulfilment for the award of Bachelor of Engineering in of
Visvesvaraya Technological University, Belagavi during the year 2023-24. It is
certified that all corrections and suggestions indicated for the internal assessment have
been incorporated in the report deposited in the department library. The Mini Project
report has been approved as it satisfies the academic requirements in respect to the
work prescribed for the Bachelor of Engineering Degree.

………………………. ……………………….
Signature of the Guide Signature of HOD
Ms.DIKSHA M Mrs. AVINASH
Department of computer science and Department of computer science and
Engineering Engineering

Name of committee member Signature with Date

1 ________________ 1 ________________

2 ________________ 2 ________________
2
 ACKNOWLEDGEMENT
First and foremost, I would like to thank God Almighty for giving me the opportunity to
undertake this Project work. Without his blessings, it would not have been possible to take up
this Mini Project work.
I express my sincere thanks to Padma Shri Dr. B.R. Shetty, Chairman, Brindavan Group of
Institutions, Bengaluru, for providing excellent facilities in the institution.

I convey my sincere thanks to Dr. Shruti Sharma, CEO, Brindavan Group of Institutions for her
support and motivation.

I wish to express my sincere thanks to Dr. Venugopal A R, Director, Brindavan Group of Institutions
for his support and motivation.

I express my sincere thanks to Dr. Bhagappa, Principal, Brindavan College of Engineering,

Bengaluru, for providing necessary facilities and motivation to carry out project work successfully.

I express my heartfelt gratitude and humble thanks to Mr. Avinash , HOD Department of Computer
Science and Engineering Brindavan College of Engineering, for the constant encouragement and
help to carry out project work successfully.

I am profoundly grateful to my guide MS. Diksha M, Department of Computer Science and

Engineering, Brindavan College of Engineering for guiding and having facilitated us to complete my
project work successfully.

I would like to mention my special thanks to all the faculty members Department of Artificial
Intelligence and Machine Learning Brindavan College of Engineering, Bengaluru for their invaluable
support and guidance. I finally thank my family and friends who have been encouraging us constantly
and inspiring throughout the completion of my project.

Student Names USN

Puneeth kumar M 1BO22CS054
Sandesh K 1BO22CS060
Darshan K K 1BO23CS401
Nikhil T 1BO23CS403

3
 TABLE OF CONTENT

CERTIFICATE 2
3
ACKNOWLEDGEMENT
4
TABLE OF CONTENT
5
LIST OF FIGURES 6

ABSTRACT
Chapter 1 INTRODUCTION
1.1 Overview 7
1.2 Problem Statement 8

1.3 Objectives 8

Chapter 2 LITERATURE SURVEY 9

Chapter 3 METHODOLOGY 10

3.1 Proposed Method 11-12

Chapter 4 RESULTS AND DISCUSSION 13

4.1 Expected Outcome 14

Chapter 5 CONCLUSION AND FUTURE SCOPE 15

REFERENCES 16

4
 LIST OF FIGURES

Fig No. Title Page No.

3.0 General Architecture of Drowsiness Detection System 10

3.1.1 EAR(Opened eyes) 12

3.1.2 EAR(Closed eyes) 12

4.1.1 Drowsiness not detected 13

4.1.2 Drowsiness detected 13

4.1.3 (Yawning) Drowsiness detected 13

5
 ABSTRACT

Road accidents due to drowsy driving are a major concern, often leading to severe injuries and
fatalities. Traditional methods of drowsiness detection, such as vehicle movement patterns and driver
inputs, lack the immediacy and accuracy required for effective intervention. This project addresses
the need for an advanced drowsy driver detection system that utilizes computer graphics and image
processing to analyze the driver’s facial features, eye closure, and head position to determine their
level of alertness. The Drowsy Driver Detection System (DDDS) is an innovative solution designed
to combat the growing concern of drowsy driving. According to the National Highway Traffic Safety
Administration (NHTSA), drowsy driving is responsible for thousands of crashes, injuries, and
fatalities every year. To address this issue, our system utilizes a combination of computer vision and
machine learning techniques to detect early signs of driver fatigue. By analyzing facial features, eye
movements, and head pose, the DDDS can accurately identify when a driver is becoming drowsy.

The proposed system consists of several modules, including facial feature extraction, eye movement
analysis, head pose estimation, and machine learning-based classification. Facial feature extraction
involves detecting and tracking facial landmarks, such as eye contours, eyebrows, and mouth. Eye
movement analysis monitors eye blinking, gaze direction, and pupil dilation. Head pose estimation
tracks head movements and orientation. Finally, the machine learning-based classification module
uses a trained model to classify the driver's state as alert or drowsy.

The DDDS has been tested and validated through a series of experiments, demonstrating its
effectiveness in detecting drowsy driving. The system achieved an accuracy of [insert accuracy
percentage] in detecting drowsy driving, making it a reliable and efficient solution for improving road
safety. With its real-time alerts and warnings, the DDDS has the potential to reduce the number of
accidents caused by drowsy driving, saving lives and preventing injuries.

6
 CHAPTER 1

INTRODUCTION

1.1 OVERVIEW
Drowsy driving is a significant safety hazard on roadways worldwide. The subtle onset of fatigue can
impair a driver’s reaction time, decision-making ability, and overall vehicle control. Drowsy driving
is a significant contributor to road accidents worldwide. Fatigue impairs reaction times, vigilance,
and decision-making abilities, making it as dangerous as drunk driving. These technologies enable
the development of systems capable of real-time monitoring and detection of driver drowsiness. By
leveraging facial recognition algorithms, eye movement tracking, and behavioral analysis, such
systems can alert drivers to the onset of fatigue, prompting them to take necessary actions to prevent
accidents. This project aims to explore the application of computer graphics and image processing in
creating an effective drowsy driver detection system. The Drowsy Driving System is an innovative
technology designed to enhance road safety by detecting and alerting drivers of fatigue. This
comprehensive safety solution combines advanced sensors and machine learning algorithms to
prevent accidents caused by driver drowsiness. The system utilizes biometric sensors, camera
technology, and real-time data analysis to detect drowsiness. The Drowsy Driving System is a
comprehensive safety solution that combines advanced sensors and machine learning algorithms to
prevent accidents caused by driver drowsiness. This technology promotes safe driving practices and
reduces the risk of fatalities and injuries on the road.

The DDDS is a comprehensive safety solution that combines multiple technologies to prevent
accidents caused by driver fatigue. Its primary objectives are:

1. Early Detection: Identify drivers showing signs of drowsiness.

2. Alert System: Provide timely warnings to alert drivers.

3. Prevention: Minimize the risk of accidents.

7
1.2 PROBLEM STATEMENT
Driver’s inattention might be the result of a lack of alertness when driving due to driver drowsiness
and distraction. Driver distraction occurs when an object or event draws a person’s attention away
from the driving task. Unlike driver distraction, driver drowsiness involves no triggering event but,
instead, is characterized by a progressive withdrawal of attention from the road and traffic demands.
Both driver drowsiness and distraction, however, might have the same effects, that is decreased
driving performance, longer reaction time, and an increased risk of crash involvement.

1.3 OBJECTIVE
The primary objective of this project is to design and implement a drowsy driver detection system
that employs computer graphics and image processing techniques. The specific goals are:

 To develop a real-time monitoring system that can detect early signs of drowsiness by
analyzing the driver’s facial expressions and eye movements.

 To utilize machine learning algorithms to improve the accuracy of drowsiness detection based
on visual data.

 To create a user-friendly interface that can alert drivers with auditory or visual signals when
signs of fatigue are detected.

 To evaluate the system’s performance in diverse driving conditions and refine the detection
algorithms accordingly.

8
 To contribute to road safety by providing a technological solution that can be integrated into
modern vehicles, thereby reducing the risk of accidents caused by drowsy driving.

9
 CHAPTER 2

LITERATURE SURVEY

DROWSY DRIVER DETECTION SYSTEM by Jibin Joy [2023]. It uses a camera to track the
driver’s eyes and employs algorithms to detect fatigue, sending alerts if drowsiness is detected. High
implementation costs ,Complexity in maintenance due to advanced technology reliance.

Drowsy Driver Detection Using Viola-Jones Algorithm by Shahirah Mohamed Hatim[2021]. Detects
driver drowsiness using the Viola-Jones algorithm, employing blinking rate as an indicator to alert
drivers and prevent accidents. The system’s reliance on visual cues may limit effectiveness in lowlight
conditions.

Adrian Rosebrock, PyImageSearch Blog [2022]. Reduces drowsy driving related accidents , Gathers
data for safety research. Buzzer will be alarmed and the message will be sent to the driver in slow.

International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395- 0056
Volume: 11 Issue: 03 | Mar 2024. Buzzer will be alarmed and the message will be sent to the driver
in slow. Cost: High-end systems with advanced features can be expensive.

10
 CHAPTER 3
METHODOLOGY

Process description:
1.Video Input: The system receives video input, likely from a webcam pointed at the driver.
2.Extracting Frames: The first step involves extracting individual frames from the video stream.
3.Face Detection: Each frame is then analyzed to detect the presence of a face.
4.Eye Detection: If a face is found, the system focuses on the facial region and attempts to locate the
driver's eyes.
5.Drowsiness Decision: Based on features extracted from the eyes, the system determines if the driver
is drowsy or not.
Yes: If drowsiness is detected, the system likely triggers an alert.
No: If drowsiness isn't detected, the system presumably continues processing the next video frame

Fig 3.0. Architecture of Drowsiness Detection System

3.1 PROPOSED METHOD

11
1.Data Collection:
-Collect video footage of drivers in various states of alertness and drowsiness.
-Ensure diverse datasets with different lighting conditions, facial orientations, and
individual variations.

2. Face and Eye Detection:

- Use Haar cascades or deep learning-based models (like Dlib or OpenCV) to detect the face and
eyes in each frame.
- Extract the region of interest (ROI) around the eyes for further analysis

3. Eye Aspect Ratio (EAR) Calculation:

- Compute the Eye Aspect Ratio (EAR) for each frame to measure the degree of eye closure. - The
EAR is calculated using the distances between specific facial landmarks around the eyes.

4. Mouth aspect ratio (MAR) Calculation:

-is a measurement used in driver drowsiness detection systems to determine if a driver is
yawning.
-MAR is the ratio of the vertical distance of the mouth to its horizontal distance.

5. Alertness:
-When the system detects signs of drowsiness, it alerts the driver to bring their focus back on
the road or take a break.

12
1.Each eye is represented by 6 (x, y)-coordinates, starting at the left-corner of the eye (as if you
were looking at the person), and then working clockwise around the eye.

2.It checks 20 consecutive frames and if the Eye Aspect ratio is less than 0.25, Alert is
generated.

Fig 3.1.1 EAR(Opened eyes) Fig 3.1.2 EAR(Closed eyes)

13
 CHAPTER 4

RESULTS AND DISCUSSION

Fig 4.1.1 Drowsiness detection Fig 4.1.2 Drowsiness not detected

Fig 4.1.3 (Yawning) Drowsiness Detected

14
4.1 EXPECTED OUTCOMES

1.Detection Accuracy: High accuracy in detecting drowsiness, measured by metrics such as precision,
recall, F1 score, and overall accuracy. A goal could be set, for instance, an accuracy of above 90%.

2.Timely Alerts: The system should provide timely alerts (auditory, visual, or both) when drowsiness
is detected to prevent potential accidents.

3.Low False Positives/Negatives: Minimal false positives (alerting when the driver is not drowsy) and
false negatives (not alerting when the driver is drowsy).

15
 CHAPTER 5

CONCLUSION AND FUTURE SCOPE

5.1 Conclusion:
• The driver anomaly observing framework created is able of identifying laziness intoxicated
and careless practices of driver in brief time.

• The laziness detecting framework created based on eye closure of the driver can separate
ordinary eye flicker and tiredness and distinguish the laziness while driving.

• Information about the head and eyes position is obtained to a range of self developed
photograph processing algorithms during the monitoring the system is able to figure out if the
eyes are opened or closed.

• When the eyes have been closed for too long a warning sign is issued, processing judges the
driver’s alertness level on the ground work of continuous eye closures.

5.2 Future Scope:

• Improved road safety: The technology could reduce the number of accidents caused by
drowsy driving, which is a significant contributor to road accidents.
• In-car devices: The technology could be developed into an in-car device that can alert the
driver or prevent them from sleeping.
• Self-driving mode: The system could activate a self-driving mode if the driver's eyes are
closed for a certain amount of time.
• Heart attack: By adding a sensor to track the heart rate in order to prevent the accident caused
due to sudden heart attack to the driver.
• Other uses: same model and technique can be used for various other uses like Netflix and
other streaming services can detect when is asleep and stop the video accordingly.

16
 REFERENCES

[1] DROWSY DRIVER DETECTION SYSTEM by Jibin Joy [2023].

[2] Drowsy Driver Detection Using Viola-Jones Algorithm by Shahirah Mohamed

Hatim[2021].

[3] Adrian Rosebrock, PyImageSearch Blog [2022].

[4] International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-
0056 Volume: 11 Issue: 03 | Mar 2024.

[5] “Drowsy Driving.” [Online], Available: http://sleepcenter.ucla.edu/drowsy-driving.

17