You are on page 1of 33

A.V.

C COLLEGE OF ENGINEERING
IT6811 - PROJECT WORK - VIII Semester
DEPARTMENT OF INFORMATION TECHNOLOGY

REAL TIME ROAD SIGNS AND DRIVER DROWSINESS USING EMBEDDED


LINUX DASHBOARD SYSTEM

Batch No:3
R.Anusha - 820315205003
A.Atchaya - 820315205004
R.Priyanga - 820315205031
T.Sujatha - 820315205045

Guided by
Dr.N.Rajganesh Ph.D.,
(Assistant Professor-IT)1
AGENDA

• Objectives
• Abstract
• Introduction
• Literature Survey
• Proposed Overview
• Algorithm Used
• Module Description
• Results and Discussion
• Conclusion
• Scope for future work
• References
• Publication Details

2
OBJECTIVES

• To ensure the drivers drowsiness and to detect the road signs using web camera
with the help of open cv.

• To identified driver drowsiness as a high priority vehicle safety issue and also there
is some people who are careless in identifying the road signs.

• To increase the interest with respect to the design and advancement of computer
controlled automotive applications to overcome those problems by enhancing
safety to reduce accidents, increase traffic flow, and enhance comfort for drivers.

• To presenting a way to detect drowsiness in driver non intrusively by warning the


drivers, preventing accidents and to improve safety on the motorways

3
ABSTRACT

The main aim of this Project is to detect driver drowsiness and road signs
with the help of Live Web camera. It reduces the accidents by sending an alert
message to driver and concern people (owner), if any parameters exceeds the
predefined threshold level. It also detect the road signs to indicate drivers about the
road crossing and turn, then it send a audio alert to driver.

To develop and design, Raspberry pi3 embedded board is used with python
programming. Whenever the driver’s drowsiness and Road signs detected, the
raspberry pi will start alerting the driver through SMS. Similarly, it will give a
warning alarm to get rid of the danger.

4
INTRODUCTION

• The accidents and the accident injuries in the world is increasing in our day
today life so there must be good and efficient control for the safety of human
life. The violation of traffic rules like drunk driving, careless driving are some
causes of road accidents as we know we cannot stop the accidents but we can
reduce the accidents by some precautionary measures.

• To solve the major problem several methods have been adopted but most of them
are largely ineffective or manually operated and depend on the user's ability to
be alert when using them. As such, an smart security to humans and alert is
needed to inform a driver if any parameters are going wrong.

5
Title Year Description Advantage Disadvantage
it repre
Vehicle safety 2018 This paper presents into two Fuzzy control Search space
monitoring parts, the first part is the provide the reliable limited by initial
system based network-coordinator and information of solution(normal
on Internet of router which were installed vehicle movements distribution sample
Things and on the road, and second part should use in
Identification is the network-end device initialize step)
with that installed on the vehicles
Physiological
characteristics

Yawning 2017 This paper present a It analyse the lip The mouth of the
detection by approach to yawn detection movements in real driver is invisible it
the analysis of for monitoring driver time makes less
variational drowsiness. It consist in the accuracy
descriptor for localised lips by active
monitoring contours it represents the
driver non-stationary and non-
drowsiness linear signals. This signal is
analysed to detect yawn
states of driver
6
Title Year Description Advantage Disadvantage
Accident 2016 This paper describes a Eye based control The Eye Blink
Prevention Using real-time online prototype will be the future Sensor based
Eye Blinking and driver fatigue monitor. It of all types of Driver monitoring
Head uses remotely located device control, provide less
Movement charge-coupled device thus making the reliability
cameras equipped with operation much
active infrared easier with less
illuminators to acquire human presence.
video images of the driver.

Driver Drowsiness 2015 It utilizes face detection It identify eye state Detected eyes
Detection in and eye detection to using complexity images are too
Embedded System initialize the location of function to make small to identify
drivers eye; that an object higher accuracy eyes states its
tracking method is used to results are not
keep tracking of the eyes good

7
Proposed Overview

8
ALGORITHMS USED

• Haar Cascade Classifiers


In Haar Cascade Classifiers, a lot of similar and dissimilar
images are trained in order to detect fatigue of the driver. OpenCV
is a learning-based method, packed with a detector as well as a
trainer. For training, a separate database is maintained for eyes
with several positive and negative images having eye closed and
opened conditions and different set facial images.

9
MODULE DESCRIPTION

• Detection of Drowsiness using Webcam


• Detection of Road Sign using Webcam
• Sending Emergency SMS using GSM Module

10
Module 1-Detection of Drowsiness using Webcam

The driver drowsiness can be measured using Haar-cascade in


OpenCV. First it is needed to load the required XML classifiers.

Camera Video Raspberry Pi


Frame

11
Module 2-Detection of Road Sign using Webcam

• The Road signs are captured using web camera using this it identifies
the speed limit and turnings images, it analysis the original image and
warped images to identify the signs.

Camera Video
Raspberry Pi
Frame

12
Module 3-Sending Emergency SMS using GSM Module

• The important Alert messages are send to Recognized users through


the Global System for Mobile communication.

GSM Module Raspberry Pi USER

13
HARDWARE COMPONENTS

 Raspberry Pi

 GSM Modem

 Web camera

14
Raspberry pi

• Raspberry pi is a low cost credit card sized computer that connects


to a computer monitor or TV using HDMI and uses a standard
keyboard and mouse.
• It can run a host of operating system such as Rasbian, Android,
windows 10, IoT core, etc.
• Raspberry pi can be plugged into a TV, computer monitor, and its
uses a standard keyboard and mouse.

15
GSM modem

• Global system for mobile communication (GSM) is a globally


accepted standard for digital cellular communication.

16
Web camera

• Frame Rate 640x480 up to 30 frame/sec CIF


• 640x480 up to 15 frame/sec VGA
• Video Format 24-bit RGB
• Sensor Size 4386x3.64mm

17
SOFTWARE COMPONENTS

• Jessie Raspbian

• Language – Python

• Open Cv

18
JESSIE RASPBIAN

• Raspbian is a Debian based computer operating


system for Raspberry Pi.
• It is now officially provided by the Raspberry Pi Foundation, as
the primary operating system for the family of Raspberry
PI single-board computers.

19
PYTHON

• Python is a general purpose programming language that can be


used on any modern computer operating system.
• Python is an easy to learn. It has efficient high-level data
structures and a simple but effective approach to object-oriented
programming.
• The Python interpreter is easily extended with new functions and
data types implemented in C or C++ (or other languages callable
from C).
• Python is also suitable as an extension language for customizable
applications.

20
OpenCV

• OpenCV was started at Intel in 1999 by Gary Bradsky.


• OpenCV-Python is a library of Python bindings designed to solve
computer vision problems.
• OpenCV is a learning-based method, packed with a detector as
well as a trainer.
• For training, a separate database is maintained for eyes with
several positive and negative images having eye closed and
opened conditions and different set facial images.

21
RESULTS AND DISCUSSION

• The driver drowsiness can be measured using Haar-cascade in OpenCV. First


it is needed to load the required XML classifiers. Then load the input video in
gray scale mode. Eye closing rate is measured and if the value crosses
threshold value, then the alert signal is generated to wake up the driver from
sleepy state and also the alert message is sent to the concern people.
• In traffic sign detection and recognition. It describes the characteristics of the
road signs and how to deal with outdoor images. First the image is convert
RGB image to gray scale image. Image is further converted into black and
white image in order to apply image processing steps.

22
SCREENSHOTS

23
.

24
.

25
.

26
CONCLUSION

• It is a system for Driver drowsiness detection is designed mainly


to keep the driver awake while driving to avoid the accident due to
sleepiness. Fatigue is measured by detecting eye using Haar-
Cascade Classifier.
• The Road signs are detected using webcam. The audio alert is
generated from embedded device to alert the drivers like speed
limit and turnings.
• When drowsiness reaches maximum threshold the driver will be
alarmed by a loud warning that will wake up the driver from the
sleepy state and GSM is used to alert the concern people by
sending alert messages.

27
SCOPE FOR FUTURE WORK

• Currently there is no adjustment in zoom or direction of the


camera during operation. Future work may be automatically zoom
in on eyes once they are localized. This would avoid trade-off
between having wide field of view in order to locate the eyes,
and narrow view in order to detect fatigue.
• The usage of cloud will implement the automatic alert messages to
the nearby hospitals and police stations using location tracking.

28
REFERENCES
• Akrout, B. and Mahdi, W. (2016, November) ‘ Yawning detection by the analysis
of variational descriptor for monitoring driver drowsiness’, International Image
Processing, Applications and Systems (IPAS) (pp. 1-5). IEEE.
• Chellappa, A., Reddy, M. S., Ezhilarasie, R., Suguna, S. K., and Umamakeswari,
A. (2018) ‘Fatigue Detection Using Raspberry Pi 3’, International Journal of
Engineering & Technology, 7(2.24), 29-32.
• Hmida, R., Abdelali, A. B., and Mtibaa, A. (2018) ‘Hardware implementation and
validation of a traffic road sign detection and identification system’,Journal of
Real-Time Image Processing, 15(1), 13-30.
• Hong, T., and Qin, H. (2007, December) ‘Drivers drowsiness detection in
embedded system’, IEEE International Conference on Vehicular Electronics and
Safety (pp. 1-5). IEEE.
• Jianmin Duan, Malichenko Viktor (2015,October) ‘Real Time Road Edges
Detection And Road Signs Recognition’, International Conference on Control,
Automation and Information Sciences(ICCAIS) October 29-31.

29
.

• Katyal, Y., Alur, S., and Dwivedi, S. (2014, May) ‘Safe driving by
detecting lane discipline and driver drowsiness’, IEEE International
Conference on Advanced Communications, Control and Computing
Technologies (pp. 1008-1012). IEEE.
• Khan, J. F., Bhuiyan, S. M., and Adhami, R. R. (2011) ‘Image
segmentation and shape analysis for road-sign detection’, IEEE
Transactions on Intelligent Transportation Systems, 12(1), 83-96.
• Kim, J. G., Yoo, J. H., and Koo, J. C. (2018, January) ‘Road and lane
detection using stereo camera’, IEEE International Conference on Big
Data and Smart Computing (BigComp) (pp. 649-652). IEEE
• Palani, S. and Kothandaraman, S. (2013) ‘A Low Cost Drivers
Drowsiness Detection System For Autonomous Mobile Vehicle’,
International Journal Of Engineering Research & Technology,
ISSN:2278-0181, Vol. 2 Issue 4.
• Saini, V. and Saini, R. (2014) ‘Driver drowsiness detection system and
techniques: a review’, International Journal of Computer Science and
Information Technologies, 5(3), 4245-4249.

30
PUBLICATION DETAILS

ANUSHA. R, ATCHAYA. A, PRIYANGA. R, SUJATHA. T,


“REAL TIME ROAD SIGNS AND DRIVER DROWSINESS
MONITORING USING EMBEDDED LINUX DASHBOARD
SYSTEM”, in the NATIONAL CONFERENCE OF EMERGING
TRENDS IN ELECTRONICS AND COMMUNICATION
ENGINEERING (NCETECE-2019), Kings College of
Engineering, Thanjavur, 2019

31
QUERIES

32
THANK YOU

33

You might also like