Download as pdf or txt
Download as pdf or txt
You are on page 1of 19

DRIVER DROWSINESS DETECTION

A PROJECT REPORT
Submitted by

SANDEEP NAYAK

in partial fulfillment for the award of the


degree of

MASTER
in
COMPUTER APPLICATIONS

SCHOOL OF ENGINEERING AND TECHNOLOGY


BHUBANESWAR CAMPUS
CENTURION UNIVERSITY OF TECHNOLOGY AND MANAGEMENT ODISHA

NOVEMBER 2023
DEPARTMENT OF MCA

1
BONAFIDE CERTIFICATE

Certified that this project report DRIVER DROWSINESS DETECTION is the bonafide work
of “SANDEEP NAYAK”,who carried out the project work under my supervision. This is to
further certify to the best of my knowledge, that this project has not been carried out earlier in
this institute and the university.

<<Signature of the Supervisor>>


SIGNATURE

(Mr. Trilochan Sahoo)


Professor of Computer Science and Engineering

Certified that the above-mentioned project has been duly carried out as per the norms of the
college and statutes of the university.

SIGNATURE
(Prof. Rakesh Kumar Ray)
HEAD OF THE DEPARTMENT
Professor of Computer Science and Engineering

DEPARTMENT SEAL

2
DECLARATION

I hereby declare that the project entitled “DRIVER DROWSINESS DETECTION” submitted for
the “Major Project” of 3rd semester MCA in Computer Science and Engineering is my original work
and the project has not formed the basis for the award of any Degree or any other similar titles in
any other University / Institute.

Name of the Student: Sandeep Nayak


Signature of the Student:

Registration No: 220720100144


Place: CUTM, BHUBNESWAR CAMPUS

Date:

3
ACKNOWLEDGEMENT
I wish to express my profound and sincere gratitude to Mr. Trilochan Sahoo, Department
of Computer Science and Engineering, SoET, Bhubaneswar Campus, who guided me into the
intricacies of this project nonchalantly with matchless magnanimity.
I thank Prof. Rakesh Kumar Ray, Head of the Department of Master in Computer
Applications, SoET, Bhubaneswar Campus and Prof. Sujata Chakravarthy, Dean, School of
Engineering and Technology, Bhubaneswar Campus for extending their support during Course of
this investigation.

I am highly grateful to Mr. Trilochan Sahoo who evinced keen interest and invaluable support
in the progress and successful completion of my project work.
I am indebted to Mr. Trilochan Sahoo for their constant encouragement, co- operation and
help. Words of gratitude are not enough to describe the accommodation and fortitude which they
have shown throughout my endeavor.

Name of the Student: Sandeep Nayak

Signature of the Student:

Registration No: 220720100144


Place: CUTM, BHUBNESWAR CAMPUS

4
5
CHAPTER NO. TITLE PAGE NO.

CERTIFICATE 2

DECLARATION Error! Bookmark not defined.

ACKNOWLEDGEMENT 3

1. ABSTRACT 01

2. INTRODUCTION 02

3. INTODUCTION ABOUT DATASET 03

4. LIBRARIES USED 04-05

5. CLASSIFICATION AND VISUALIZATION 06-17

6. SPLITTING AND MODEL IMPLEMENTATION 18-20

7. ACCURACY OF ALL MODELS 20-21

8. BUILDING A USERINPUT PREDICTIVE SYSTEM 22-23

9. CONCLUSION 24

10. FUTURE SCOPE 25

11. REFERENCE 26

6
1. Abstract

The "Driver Drowsiness Detection Project" aims to enhance road safety by implementing
an advanced system for real-time detection of driver drowsiness. The project leverages
state-of-the-art computer vision and machine learning techniques to analyze the driver's
behavior and physiological signals to determine their level of alertness. Key features
include facial recognition, eye movement tracking, and other relevant indicators to assess
the driver's cognitive state.

The system utilizes a combination of image and sensor data from in-vehicle cameras and
sensors to continuously monitor the driver's activity. Machine learning algorithms are
employed to analyze patterns associated with drowsiness, fatigue, or distraction. The
project focuses on developing a robust and reliable algorithm capable of accurately
identifying drowsy states while minimizing false positives.

In addition to real-time monitoring, the project incorporates an alert mechanism to notify


the driver when signs of drowsiness are detected. Alerts may include visual warnings,
auditory signals, or haptic feedback to prompt the driver to take corrective actions and
avoid potential accidents.

The project's evaluation involves testing the system in various driving conditions and
scenarios to assess its effectiveness and reliability. Performance metrics, such as accuracy,
sensitivity, and specificity, are used to measure the system's overall efficacy in detecting
and mitigating driver drowsiness.

The "Driver Drowsiness Detection Project" presents a significant contribution to road


safety technology, offering a proactive approach to address the risks associated with
drowsy driving. The integration of cutting-edge technologies in a cohesive system
demonstrates the potential for widespread adoption of such solutions in vehicles to reduce
the incidence of accidents caused by driver fatigue.

7
2.Introduction

In contemporary society, road safety stands as a paramount concern, and the role of
technology in mitigating potential hazards has become increasingly crucial. One significant
threat to road safety is driver drowsiness, a condition that significantly increases the risk of
accidents. The "Driver Drowsiness Detection Project" represents a proactive response to this
issue, aiming to leverage cutting-edge technologies to enhance driver safety and reduce the
incidence of drowsy-driving-related incidents. Fatigue and drowsiness are acknowledged as
leading contributors to road accidents worldwide. The consequences of a momentary lapse in
attention due to drowsiness can be severe, posing risks not only to the driver but also to
passengers and other road users. Recognizing the imperative to address this challenge, our
project focuses on the development and implementation of an advanced system that can
accurately detect signs of driver drowsiness in real-time. The project draws inspiration from
the escalating integration of artificial intelligence, computer vision, and machine learning in
various domains. By harnessing the capabilities of these technologies, our goal is to create a
robust and reliable system capable of continuously monitoring a driver's state and providing
timely alerts when signs of drowsiness are detected. This introduction will delve into the
motivation behind the project, the significance of addressing driver drowsiness, and an
overview of the methodologies and technologies employed. The subsequent sections will
detail the project's objectives, the scope of work, and the anticipated impact on road safety.
As we progress into an era of smart transportation, the "Driver Drowsiness Detection Project"
exemplifies a proactive initiative to integrate intelligent systems into vehicles, contributing to
the broader goal of creating safer and more secure road environments.

8
3.INFORMATION ABOUT DATASET:

• Data used: - DRIVER DROWSINESS DETECTION


• Size: -68 MB
• SOURCEOFOLLECTION - https://www.semanticscholar.org/
KAGGLE
TOTAL SIZES 1 FILE

4.Libraries used
 Pandas
 NumPy
 Matplotlib
 Sklearn

9
Pandas is a popular Python library for data analysis. It is not directly related to
Machine Learning. As we know that the dataset must be prepared before
training. In this case, Pandas comes handy as it was developed specifically for
data extraction and preparation. It provides high-level data structures and wide
variety tools for data analysis. It provides many inbuilt methods for grouping,
combining and filtering data.

NumPy is a very popular python library for large multi-dimensional array and
matrix processing, with the help of a large collection of high-level mathematical
functions. It is very useful for fundamental scientific computations in Machine
Learning. It is particularly useful for linear algebra,
Fouriertransform,andrandomnumbercapabilities.

Matplotlib is a very popular Python library for data visualization. Like Pandas,
it is not directly related to Machine Learning. It particularly comes in handy
when a programmer wants to visualize the patterns in the data. It is a 2D

10
plotting library used for creating 2D graphs and plots. A module named pyplot
makes it easy for programmers for plotting as it provides features to control
line styles, font properties, formatting axes, etc. It provides various kinds of
graphs and plots for data visualization, viz., histogram, error charts, bar chats
etc.

Scikit-learn is one of the most popular ML libraries for classical ML algorithms.


It is built on top of two basic Python libraries, viz., NumPy and SciPy. Scikit-
learn supports most of the supervised and unsupervised learning algorithms.
Scikit-learn can also be used for data-mining and data- analysis, which makes
it a great tool who is starting out with ML.

5.CLASSIFICATION AND
VISUALIZATION PART

SCREEN SHOT DATA SET:-

11
12
13
14
9.CONCLUSION

In conclusion, the "Driver Drowsiness Detection Project" represents a significant stride


towards enhancing road safety through the integration of advanced technologies. The project
successfully addressed the critical issue of drowsy driving, employing a comprehensive
approach that combined computer vision, machine learning, and real-time monitoring to detect
and mitigate driver fatigue.

Our research has demonstrated the feasibility and effectiveness of implementing a proactive
system for detecting drowsiness in real-time. By analyzing facial expressions, eye movements,
and other relevant indicators, the developed algorithm exhibited a high degree of accuracy in
identifying instances of driver drowsiness. The integration of this algorithm into an alert
mechanism, providing timely warnings to drivers, has the potential to substantially reduce the
risks associated with drowsy driving.

The project's evaluation under diverse driving conditions and scenarios has provided valuable
insights into the system's robustness and reliability. While the current implementation shows
promise, continuous refinement and optimization are essential for adapting to the dynamic
nature of real-world driving scenarios.

As we move forward, the implications of the "Driver Drowsiness Detection Project" extend
beyond the confines of this research effort. The integration of such systems into vehicles has
the potential to revolutionize road safety, significantly decreasing the likelihood of accidents
caused by driver fatigue. Furthermore, this project sets the stage for continued exploration and
improvement in the realm of smart transportation technologies.

In the future, ongoing research and development efforts should focus on refining the algorithm,
expanding the dataset to encompass a broader range of driving conditions, and exploring
potential collaborations with automotive manufacturers to integrate this technology into
commercially available vehicles. The culmination of these endeavors will contribute to a safer
and more secure road environment, aligning with the overarching goal of leveraging technology
to mitigate risks and enhance the overall safety of transportation systems.

15
10.FUTURE SCOPE

The future scope of a Driver Drowsiness Detection Project involves exploring potential
advancements, applications, and areas for improvement in the field. Here's a generic template
for discussing the future scope of such a project:

Future Scope:

The "Driver Drowsiness Detection Project" lays a foundation for future endeavors and presents
several avenues for further research, development, and implementation. The following
aspects highlight the potential future scope of this project: Algorithm Refinement and
Optimization, Integration with Advanced Driver Assistance Systems (ADAS), Real-time
Feedback and Intervention, Enhanced Sensor Technologies, Big Data and Predictive Analytics,
Human-Machine Interaction (HMI) Design, Regulatory Considerations and Standardization.

The future scope of the "Driver Drowsiness Detection Project" extends beyond the technical
aspects, encompassing societal, regulatory, and collaborative dimensions. By continuously
pushing the boundaries of innovation, this project has the potential to significantly contribute
to the evolution of road safety and smart transportation systems.
11.REFERENCE

[1] COMPUTATIONALLY EFFICIENT FACE DETECTION; B. SCHLKOPF-A. BLAKE, S. ROMDHANI, AND P. TORR.

[2] USE OF THE HOUGH TRANSFORMATION TO DETECT LINES AND CURVES IN PICTURE; R. DUDA AND P. E. HART.

[3] JAIN, “FACE DETECTION IN COLOR IMAGES; R. L. HSU, M. ABDELMOTTALEB, AND A. K. JAIN.

[4] OPEN/CLOSED EYE ANALYSIS FOR DROWSINESS DETECTION; P.R. TABRIZI AND R. A. ZOROOFI.

[5] http://ncrb.gov.in/StatPublications/ADSI/ADSI2015/chapter1A%20traffic %20accidents.pdf

[6] http://www.jotr.in/text.asp?2013/6/1/1/118718

[7] http://dlib.net/face_landmark_detection_ex.cpp.html

16
ASSESSMENT
Internal:

SL FULL REMARK
NO RUBRICS MARK MARKS OBTAINED S
Understanding the relevance, scope and
1 dimension of the project 10

2 Methodology 10
3 Quality of Analysis and Results 10
4 Interpretations and Conclusions 10
5 Report 10
Total 50

Date: Signature of the Faculty

17

You might also like