ISSN (Online) 2581-9429

IJARSCT
International Journal of Advanced Research in Science, Communication and Technology (IJARSCT)

Volume 3, Issue 2, April 2023

Impact Factor: 7.301

Driver Safety using Raspberry Pi

Archana S. Gaikwad
Lecturer, Department of E&TC
Pimpri Chinchwad Polytechnic, Pune, Maharashtra, India

Abstract: This provides an approach to identifying driver drowsiness due to sleep or addiction or use of
mobile phone during driving a vehicle in real time. 22 percent of injuries are attributed to cell phones, and
33 percent of incidents are due to drug or alcohol consumption, according to government report.
Developing such a technology in vehicle that can track alcohol intake and use of driver's cell phones is
currently a major challenge. This image processing method may be more effective to complete this task. We
develop a device which uses Raspbian OS supports the camera. This device we can monitor the driver's
real-time condition and turn on the warning when the mobile phone and drug or alcohol use is detected by
the raspberry pi-based signal that shuts off the vehicle’s ignition power source.

Keywords: Alcohol Sensor, L293d, Raspberry pi, Camera, GSM, Buzzer, Power Supply, Speaker, LED
(Hazard Light)

I. INTRODUCTION
The level of attention of driver while driving the vehicle degrade because of less sleep, use of mobile phones, drunk
driving, long continuous driving. Several surveys on road accidents say that around 30 present of accidents are caused
by fatigue of the driver. When driver drives for more than normal period for human then excessive fatigue is caused and
also results in tiredness which drives the driver to sleepy condition or loss of consciousness. Most of the road accidents
are caused because of drowsiness, use of mobile phones and drunk driving and also working environments, reduced
sleep and time factor. Driver drowsiness and fatigue drunk driving reduces the driver decision making capability and
perception level.
These two situations affect the ability to control the vehicle. There are some techniques which are used to detect cell
phone use and drowsiness in drivers like by sensing of driver operation or physiological characteristics of driver or
vehicle movement etc. Traffic survey shows that driver fatigue and use of mobile may be a contributory factor in up to
20% and due to alcohol drinking it is about 31% of all road accidents. The main aim of this cell phone and alcohol
monitoring system is to build a device that can minimize the number of injuries induced by drowsiness and drunk
driving in the vehicle.
The first part of this project measures drowsiness by tracking the motions of the eyelids during a given amount of time
by recording the facial images. Using Open CV, The Input 8-megapixel camera which is capable of capturing images
and video in real time, eye tracking is the essential part of this project. The caught frame is for Raspberry pi to handle.
Using Python, CNN Algorithm is implemented.

II. METHODOLOGY OF SYSTEM

2.1 Description of Block Diagram
Figure 1 shows system architecture of design system. To train the classifier, the classifier must be equipped using the
algorithm with a lot of positive images (face images) and negative images (faceless images). It then extracts features
from it. - function was a single value obtained by subtracting number of pixels from the number of pixels under the
black rectangle under the white rectangle. The number of pixels under white and black rectangles was determined by
image integral for each measurement of the function. It simplifies computation of sum of pixels, however large may be
the number of pixels, to an operation involving only four pixels. Each and every feature on all the training images has
been applied. The best criterion was added for each attribute which could rate the faces positively and negatively. Yet
clearly mistakes or misclassifications were possible.

Copyright to IJARSCT DOI: 10.48175/568 113

www.ijarsct.co.in
 ISSN (Online) 2581-9429
IJARSCT
International Journal of Advanced Research in Science,, Communication and Technology (IJARSCT)

Volume 3, Issue 2, April 2023

Impact Factor: 7.301

Therefore, the features with least error rate were chosen, meaning they were the features that best distinguish the
representations of the face and non-face.
face. A weighted
weighted sum of those weak classifiers is the final classifier. It's considered
weak because the image cannot be labelled by itself, but together with others, it forms a strong classifier. If eye blinking
frequency of driver increase system generate an alert and
and ignition system become locked and owner get information
about that. Also system can detect alcohol level of driver for such a system we use python language to build system.
Basic building block architecture shown in figure.1
fig

III. SYSTEM BLOCK DIAGRAM

Figu 1 (System Block Diagram / Architecture)

Figure.

Copyright to IJARSCT DOI: 10.48175/568 114

www.ijarsct.co.in
 ISSN (Online) 2581-9429
IJARSCT
International Journal of Advanced Research in Science,, Communication and Technology (IJARSCT)

Volume 3, Issue 2, April 2023

Impact Factor: 7.301

IV. FLOW CHART

Copyright to IJARSCT DOI: 10.48175/568 115

www.ijarsct.co.in
 ISSN (Online) 2581-9429
IJARSCT
International Journal of Advanced Research in Science, Communication and Technology (IJARSCT)

Volume 3, Issue 2, April 2023

Impact Factor: 7.301

V. ADVANTAGES
 Alcohol Detection in Real-Time to Prevent Drunken Driving
 System for Road Transportation Safety in Smart City
 Accident Avoiding
 Increase in awareness of safety
 System will keep close eye on Driver
 Vehicle safety
 Low cost solution
 Multiple alert system (Voice message, Buzzer and SMS to vehicle owner)
 Less time required for Programming
 Component cost is less
 Component mounting and component fitment is easy
 Awareness in the surrounding regarding the use of the feature may help the people educate and know
importance of automation.
 Driver Drowsiness (Image process, all Driver Actions will be captured)
 Cost saving (All possible Driver negligence is covered in single project)

VI. CONCLUSION
In this research, we introduced computer vision technology with image processing and use of the new embedded
systems aimed at reducing road accidents related to driver drowsiness, mobile phone use and intoxicated addiction that
locates and monitors the eyes. Due to road accidents, tracking and detecting the conductor's behaviour to ensure road
safety as well as protecting human life is extremely important. It is therefore important to capture driver behaviour that
will control the accidents due to alcohol-influenced rash driving. The proposed device deals with alcohol identification,
cell phone use while driving and Drowsiness using sensors and steps are taken to deliver the warning alert to the user
accordingly. Experimental findings should suggest that the Improved Drowsiness Warning System has been
successfully tested and that alcohol dependence is also operating successfully. This is cost saving solution because we
have combined all the safety aspects in one project. In some cases avaible are having individual development which
adds cost and with less safety

VI. FUTURE SCOPE

The future works may focus on the utilization of outer factors such as vehicle states, sleeping hours, weather conditions,
mechanical data, etc, for fatigue measurement. Driver drowsiness pose a major threat to highway safety, and the
problem is particularly severe for commercial motor vehicle operators. Twenty-four hour operations, high annual
mileage, exposure to challenging environmental conditions, and demanding work schedules all contribute to this serious
safety issue. Monitoring the driver’s state of drowsiness and vigilance and providing feedback on their condition so that
they can take appropriate action is one crucial step in a series of preventive measures necessary to address this problem.
Currently there is not adjustment in zoom or direction of the camera during operation. Future work may be to
automatically zoom in on the eyes once they are localized

REFERENCES
[1]. Pandurang N. Kathar, D.L.BhuyarDesign and Implementation of Driver Drowsiness and Alcohol
Intoxication Detection Using Raspberry PI”International Journal of Innovative Research in Computer and
Communication EngineeringVol. 4, Issue 8, August 2016

Copyright to IJARSCT DOI: 10.48175/568 116

www.ijarsct.co.in
 ISSN (Online) 2581-9429
IJARSCT
International Journal of Advanced Research in Science, Communication and Technology (IJARSCT)

Volume 3, Issue 2, April 2023

Impact Factor: 7.301

[2]. QiangJi, Zhiwei Zhu and PeilinLan ―IEEE transactions on Vehicular Technology Real Time Non-intrusive
Monitoring and Prediction of Driver Fatigue, vol. 53, no. 4, July 2004
[3]. T.DPrasanthi,K.Rajasekhar,T.V.Janardhanarao,and B.V.V.satyanarayana,”Design of ARM based face
Recognition system using Open CV library”, International Journal of Advanced Research in Computer &
Technology(IJARCET),Volume 01,Issue-9, pp-233-240, 2012
[4]. Varsha. E. dahiphale and Prof.sathyanarayanaR,”Computer Vision System for Driver Fatigue Detection”,
International Journal of AdvancedRsearch in Electronics and communication Engineering (IJARECE),
volume 04,Issue-9, pp-2331-2334,201
[5]. Saeid.fazli and Parisa .Esfehani,”Tracking Eye State for Fatigue Detection”, International Conference on
advanced in Computer and Electrical Engineering (ICACEE’2012), 2012
[6]. Lorraine Saju, ChristeenaJestine, FarhanaYasmin, and Surekha Mariam Varghese, “Drowsiness Detection
System for Drivers using Haartraining and Template Matching”, International Journal of Engineering
Applied Sciences and Technology, Vol. 1, Issue 6, pp. 106-110, 2016.
[7]. DhavalPimplaskar,Dr.M.S.Nagmode,AtulBorkar,”Real Time Eye Blinking Detection and Tracking Using
OpenCV”,International Journal of Engineering Research and Application,Vol.03,Issue 05, PP-1780-
1787,2013
[8]. Naveen M. and Sudarvizhi S., “Finger Vein Recognition Based Driver Authentication and Alertness System
Using GSM”, International Journal of Research in Engineering & Advanced Technology (IJREAT), Volume
3, Issue 1, pp.211-216, 2015
[9]. Srinivasu Batchu and S. Praveen Kumar, “Driver Drowsiness Detection to Reduce the Major Road Accidents
in Automotive Vehicles”, International Research Journal of Engineering and Technology (IRJET), Volume
02, Issue 01, pp. 345-349, 2015
[10]. L.Nikitha,J.Kiranmai,B.Vidhyalakshmi,”Driver Behaviour Analysis Using Non-Invasive sensors”,
International Journal of Advance in Engineering and Science(IJATES),Volume 03,Issue 01,pp 707-714,2015
[11]. Prof.Saurabh Thakur, ShekharDure, AjinkyaKhutwad,”Advance Vehicle Control and Safety System Using
Face Detection”, International Journal of Advance Research In Science And Engineering
(IJARSE),Vol.No.4,Issue 05,pp.141-146,2015

Copyright to IJARSCT DOI: 10.48175/568 117

www.ijarsct.co.in