International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395 -0056
Volume: 03 Issue: 03 | Mar-2016 www.irjet.net p-ISSN: 2395-0072
© 2016, IRJET ISO 9001:2008 Certified Journal Page 589
SMART HELMET - INTELLIGENT SAFETY FOR MOTORCYCLIST USING
RASPBERRY PI AND OPEN CV
Shabrin
1
, Bhagyashree Jagadish Nikharge
2
, Maithri M Poojary
3
, T Pooja
4
, Sadhana B
5
1
Student, Information Science and Engineering, Canara Engineering College, Karnataka, India
2
Student, Information Science and Engineering, Canara Engineering College, Karnataka, India
3
Student, Information Science and Engineering, Canara Engineering College, Karnataka, India
4
Student, Information Science and Engineering, Canara Engineering College, Karnataka, India
5
Asst Prof, Information Science and Engineering, Canara Engineering College, Karnataka, India
---------------------------------------------------------------------***---------------------------------------------------------------------
Abstract - Smart Helmet - Intelligent Safety Helmet for
Motorcyclist is a project undertaken to increase the rate of
road safety among motorcyclists. The idea is obtained after
knowing that there is increased number of fatal road
accidents over the years. Through the study identified, it is
analysed that the helmets used is not in safety features
such as not wearing a helmet string and not use the
appropriate size. Therefore, this project is designed to
introduce safety systems for the motorcyclist to wear the
helmet properly. With the use of Image processing unit using
Raspberry Pi and Open Cv , the motorcycle can move if there is
helmet pound wearing, in accordance with the project title
Smart Helmet - Intelligent Safety for Motorcyclist using
Raspberry Pi and Open Cv. Safety system applied in this
project meet the characteristics of a perfect rider and the
application should be highlighted. The project is expected to
improve safety and reduce accidents, especially fatal to the
motorcyclist.
Key Words: Safety, Standard Detection, Motor Ignition,
Raspberry Pi, Open Cv.
1. INTRODUCTION
Two-wheelers, the mode of transport most Indians use,
continue to be the most vulnerable to accidents. Indian roads
were at their deadliest in 2014 claiming more than 16 lives
every hour on average. Over 1.41 lakh people died in
crashes, 3% more than the number of fatalities in 2013.
Accidents involving two-wheelers and accounted for nearly
half of the lives lost in road crashes. While 13,787 two-
wheeler drivers were killed in crashes, 23,529 other people
were killed in accidents involving these vehicles, while close
to 1.4 lakh people were left injured in them. The top five
states - Uttar Pradesh, Tamil Nadu, Maharashtra, Karnataka
and Rajasthan - accounted for over 40% of the fatalities.
Among 53 mega cities, Delhi registered the highest number
of fatalities at 2,199 and Chennai recorded 1,046 such
deaths. Bhopal and Jaipur ranked third and fourth with the
city roads claiming 1,015 and 844 lives respectively[1, 2].
A motorcycle’s helmet is a type of protective
headgear used by the motorcyclist. The main purpose is for
safety, which is to protect the rider's head from the impact
during an accident. )t protects the rider’s head as the helmet
provides ventilation system. Speeding and not wearing a
helmet are the main reasons of fatalities and injuries.
Here we are implementing a model which uses DC
Motor, Relay and Raspberry Pi which in real time system is
related to the ignition system of the Motorcycle.
2. RELATED WORK
The system automatically detects motorcycle riders and
determines that they are wearing safety helmets or not. The
system extracts moving objects and classifies them as a
motorcycle or other moving objects based on features
extracted from their region properties using K-Nearest
Neighbour (KNN) classifier. The heads of the riders on the
recognized motorcycle are then counted and segmented
based on projection profiling. The system classifies the head
as wearing a helmet or not using KNN based on features
derived from 4 sections of segmented head region.
Experiment results show an average correct detection rate
for near lane, far lane, and both lanes as 84%, 68%, and 74%,
respectively [3].
The helmet is the main safety equipment of
motorcyclists, but many drivers do not use it. If an
motorcyclist is without helmet an accident can be fatal. This
paper aims to explain and illustrate an automatic method for
motorcycles detection and classification on public roads and
a system for automatic detection of motorcyclists without
helmet. For this, a hybrid descriptor for features extraction is