Driver Drowsiness Detection System
A
Project Report
Submitted in partial fulfillment of the requirement for the award of
degree of
Bachelor of Technology
In
Information Tecnology
Submitted to
RAJIV GANDHI PROUDYOGIKI VISHWAVIDYALAYA,
BHOPAL (M.P.)
Guided By Submitted By
Prof. Pawan Makhija [Link] Dhaksiya(0827IT211005)
[Link] Singh
Parihar(0827IT211037)
[Link] Bhandari(0827IT211053)
[Link] katare(0827IT211062)
DEPARTMENT OF INFORMATION TECHNOLOGY/CSE(DS)/CS(IoT)
ACROPOLIS INSTITUTE OF TECHNOLOGY & RESEARCH,
INDORE (M.P.) 452020
2023-2024
Declaration
I hereby declared that the work, which is being presented in the
project entitled Driver Drowsiness Detection System partial
fulfilment of the requirement for the award of the degree of Bachelor
of Technology, submitted in the department of Information
Technology/CSE(DS)/CSE(IoT) at Acropolis Institute of
Technology & Research, Indore is an authentic record of my own
work carried under the supervision of “[Link] Makhija Project
Guide”. I have not submitted the matter embodied in this report for
award of any other degree.
[Link] Dhaksiya(0827IT211005)
[Link] Singh Parihar(0827IT211037)
[Link] Bhandari(0827IT211053)
[Link] katare(0827IT211062)
Prof./Mr./Pawan Makhija
Project Approval Form
I hereby recommend that the project Driver Drowsiness
Detection System prepared under my supervision by
Abhishek Dhaksiya(0827IT211005)
be accepted in partial fulfillment of the requirement for the
degree of Bachelor of Engineering in Computer Science &
Engineering.
Recommendation concurred in 2023-2024
Prof./Mr. Pawan Makhija
Project Incharge
Prof. Nivedita Tiwari
Project Coordinator
Acropolis Institute of Technology & Research
Deparment of Infromation Technology /CSE(DS)/CSE(IoT)
Certificate
The project work entitled Driver Drowsiness Detection
System submitted Abhishek Dhaksiya(0827IT211005),Gagan
Singh Parihar(0827IT211037),Jiya Bhandari (0827IT211053) ,
Kshitiz katare(0827IT211062) is approved as partial
fulfillment for the award of the degree of Bachelor of
Technology in Information Technology/CSE(DS)/CSE(IoT) by
Rajiv Gandhi Proudyogiki Vishwavidyalaya, Bhopal (M.P.).
Internal Examiner External Examiner
Name:………………. Name:……………..
Date: …./…/……….. Date: …./…/………..
Acknowledgement
With boundless love and appreciation, we/I would like to extend
our/my heartfelt gratitude and appreciation to the people who helped
us/me to bring this work in reality. We/I would like to have some
space of acknowledgement for them.
Foremost, our/I would like to express our/ my sincere gratitude to
our/my supervisor, Prof. Pawan Makhija whose expertise,
consistent guidance, ample time spent and consistent advices that
helped us/me to bring this study into success.
To the project in-charge Prof. Pawan Makhija for their constructive
comments, suggestions, and critiquing even in hardship.
To the honourable Prof. (Dr.) Prashant Lakkadwala, Head,
Department of Information Technology/CSE(DS)/CSE(IOT) for his
favourable responses regarding the study and providing necessary
facility.
To the honourable Dr. S.C. Sharma, Director, AITR, Indore for his
unending support, advises and effort to make possible.
Finally, I/we would like to pay my/our thanks to faculty members and
staff of Department of Computer Science & Engineering for their
timely help and support.
We/I also like to pay thanks to our/my parents for their eternal love,
support and [Link] them it is not possible.
[Link] Dhaksiya(0827IT211005)
[Link] Singh Parihar(0827IT211037)
[Link] Bhandari(0827IT211053)
[Link] katare(0827IT211062)
Abstract
Feeling sleepy while driving could cause hazardous traffic
accident. However, w hen driving alone on highway or
driving over a long period of time, drivers are inclined to
feel bored and sleepy, or even fall asleep.
Therefore, we came up with an idea and successfully
developed a sleepy detection and alarming system, which
could effectively meet this demand.
Drowsiness detection system is designed to improve road
safety by identifying and alerting drivers to signs of
drowsiness in real-time, with the help of face detection and
machine learning algorithms the system monitors and
issuing timely alerts when fatigue is detected. Detecting the
driver’s alertness and drowsiness is an efficient way to
prevent road accidents
1. INTRODUCTION
1.1 Rationale
Driver drowsiness detection system is a car safety technology app
which prevents accidents when the driver is getting drowsy or
sleepy. Detecting the driver’s alertness and drowsiness is an
efficient way to prevent road accidents
1.2 Existing systems
Driver safe app (Battery consumption,Data insecurity,Network
availability,low end features)
Fatigue Warning Alarm Devices (Expensive,Inconvenient)
1.3 Proposed solution
Customization and friendly interface- We will allow the driver
to customise the alerts and sensitivity of the system as the
requirements and needs.
Rating system- It will rates the drivers alertness and save the
data Then will tell drivers behaviour through the journey.
Levels of alertness- We will create different levels of alertness
that tell the condition of driver if it is safe to drive or not.
Double faced detection- If there is another phase detect in the
frame, then also it will alert, cause it may distract the driver.
Connected to the owner-The owner of truck or taxis will also get
alert if the driver behaves drowsy.
Data safety- Data will be secured
No network issue-we can use the app in offline also and without
network problem
1.4 Objective
The purpose of the drowsiness detection system is to aid in the
prevention of accidents passenger and commercial vehicles. The
system will detect the early symptoms of drowsiness before the
driver has fully lost all attentiveness and warn the driver that they
are no longer capable of operating the vehicle [Link] is simply a
tool for improving driver safety; focusing primarily on long-haul
truck drivers, nighttime drivers, people driving long distances
alone or people suffering from sleep deprivation.
1.5 Contribution of the project
1.5.1 Market potential
This application is built such a way that it suits for all type of
mobile users in future so every effort is taken to implement this
project,on successful implementation in this, we can compulsory
this in cars in future
1.5.2 Innovativeness
As the phone is used almost by everyone, but no one has a
tendency to use it as a tool to save their own lives or the other's
lives so we are building a system to improve road safety by
identifying and alerting drivers to signs of drowsiness in real-time.
1.6 Report Organization
Report consist of 6 chapters in which 1st is Introduction ,And
second chapter is a requirement engineering of sub topics
hardware and software requirements , Use case diagrams and 3 rd
chapter, which consist of analysis and conceptual design and
technical architecture and 4th chapter is implementation and testing
in 5th chapter we are talking about result and discussion And last
six, there is conclusion and future scope of the project
2. Requirement Engineering
2.1 Feasibility Study
2.2 Requirements
The requirements for an effective drowsy driver detection system
are as follows:
• A non-intrusive monitoring system that will not distract the
driver.
• A real-time monitoring system, to insure accuracy in detecting
drowsiness.
• A system that will work in both daytime and nighttime conditions.
The above requirements are subsequently the aims of this project.
The project will consist of a concept level system that will meet all
the above requirements.
2.3 Hardware and Software Requirement
2.3.1 Hardware Requirement
USER:- MOBILE PHONE OF RAM STORAGE
2GB 16GB
DEVELOPER:- SYSTEM OF RAM STORAGE
8GB 256GB
2.3.2 Software Requirements
DEVELOPER :- Python
Java
Android studio
USER :- Android
2.3 Use-Case Diagram
In here the system Driver and Camera are the actors .According to
diagram Actor driver will do work like start application ,face
detecting, eye detection, Landmark predictor, Alert sounds ,Alarm and
And camera will only face detect and eye detect of driver and it will
detect whether driver feels drowsy or not
Start
Application
face
detecting
Eye
detection
Landmark
<<entend>>
predictor
Camera
Driver Alert
period
if eye is
closed
Alert
sounds
Alarm
CHAPTER 3. Analysis and Conceptual Design and
Technical Architecture
3.1 Technical architecture
3.2 Flow of system
Chapter 4. Implementation and testing
4.1 Methodology
A) Face detection,
B) Eyes Location,
C) Face and eyes tracking
D) Identification of the eyes states,
4.2 Implementation and Testing Approach
Some efforts have been reported on the development of
the monitoring drowsiness systems based on the vision.
develop a light-insensitive system. They used the Haar
algorithm to detect objects and face classifier
implemented by in OpenCV libraries In Python. Eye regions
are derived from the facial region with anthropometric
factors. Then , they detect the eyelid to measure the level
of eye closure, implement a system to detect symptoms of
driver drowsiness based on an infrared camera. By
exploiting the phenomenon of bright pupils , an algorithm
for detecting and tracking the driver’s eyes has been
developed . When drowsiness is detected, the system
warns the driver with an alarm message.
Chapter 5. Result and discussion
We determine the driver state by measuring PERCLOS. If
the driver closed his eyes in at least 5 successive frames
several times over a period of up to 3 seconds Driver
Drowsiness Detection systemit is considered drowsy.
To validate our system we test on several drivers. We use
an IR camera with infrared lighting system
operatesautomatically under the conditions of reduced
luminosity and night even in total darkness.
ACTIVE:-
DROWSY:-
SLEEPING:-
Chapter 6. Conclusion And Future Scope
6.1 Conclusion
In this paper, we presented the conception and implementation of a
system for detecting driver drowsiness based on vision that aims to warn
the driver if he is in drowsy [Link] system is able to determine the
driver state under real day and night conditions camera. The results are
satisfactory with an opportunity for improvement in face detection using
other techniques concerning the calculation of symmetry.
6.2 Future Scope
Regarding future detecting and estimating wakefulness, the cost of the
system in which they are installed will decrease, if the use of machine
learning (deep learning) is promoted by the installation of computers and
GPUs, and also the accuracy of the system can be improved, and the
installation of such systems in vehicles is expected to increase
Drowsiness detection and estimation system for driving will be applied
not only to automobiles but also to other fields and industries related to
sleep in the future, in terms of detecting drowsiness and making people
feel comfortable.
REFERENCES
Appendix A: Project synopsis
Appendix B: Guide interaction report
Appendix C: User maual