REAL TIME VEHICLE THFT DECLINE AND MONITORING SYSTEM
R. Leela prasanna1,T. Swapna Rani2
1
M.Tech, Dept of ECE, CMR College of Engineering &Technology, Hyderabad, TS-India,
Email: leelaprasannaravuri@gmail.com
2
Assoc.Prof, Dept of ECE, CMR College of Engineering &Technology, Hyderabad, TS-India,
Email:swapna4aruna@gmail.com
Abstract— The use of vehicles must in everyone. At the same,
protection from theft is also important. Protection of vehicle theft
can be done remotely by an authorized person. The location of
the vehicle can be found by using GPS and GSM controlled by
ARM7. In this paper face reorganization is used to identify the
person and comparison is done with preloaded faces for
authorization. The vehicle will start only when the authorized
person’s face is identified. In the event of theft attempt or
unauthorized person’s trail to drive the vehicle, an alert SMS
and EMAIL will be sent to owner along with the location. Once
the person is authorized system checks the alcohol level with the
help of breathalyzer. If the level is more than 60 percentage
system locks the vehicle and level is lesser engine will start and
the person should wear sceptical which have IR sensors to count
the eye blinks per minute to find the driver drowsiness. If the
blinks are below 20 buzzers will ring. For face recognition, a
Principal Component Analysis (PCA) algorithm is developed
using visual studio. the EMAIL sending method is written in
vb.net. the proposed application can be implemented with some
modifications in the system wherever the face recognition or
detection is needed like, airports, international borders, banking
applications ete.
Keywords— PCA, GPS, GPS, sensors (eye blink and alcohol),
ARM7.
1. INTRODUCTION
Nowadays everywhere in the world automotive accidents
and thefts are being increased. The Manufacturers are
attaining the security features of their products by introducing
advanced technologies to avoid the thefts particularly in the
case of cars. However, car thefts are increasing in number day
by day. Usually, biometric and non bio-metric methods are
used to provide such security features required. In non biometric methods, personal ID and password are used to identify
the person, where in the possibility of theft remains. Biometric methods involve no such possibilities, because, they
employ techniques such as voice recognition, fingerprint
recognition and face recognition. Of these, face recognition
and detection systems are more sophisticated.
This paper deals with design and development of real
time face recognition system using ARM7 as control platform.
This system can recognize the person who enters in to the
vehicle and it checks whether he\she is authorized or not.
When unauthorized person operates the vehicle, the GPS and
GSM modules which are attached to the system will send the
location and person’s image through SMS and EMAIL to the
owner. The camera which is installed at the ignition unit of the
vehicle will capture the photograph of the person and system
compares the same with the photos of the authorized persons
in the database in different postures, check whether it is the
image of the authorized person and not. The Principal
Component Analysis (PCA) algorithm is used for face
recognition. The PCA converts a number of possibly
correlated variables into number of uncorrelated variables
called Principal Component related to original variables by
using statistical methods.
PCA is a dimensionality reduction technique which is used
for compression and recognition problem. Motor vehicle theft
is the criminal act of stealing or attempting to steal a motor
vehicle (such as an automobile, truck, bus, coach,
motorcycle). According to NICB, National wide in 2010,
there were an estimated l.2 million motor vehicle thefts, or
approximately 416.7 motor vehicles stolen for every 100,000
inhabitants. Property losses due to motor vehicle theft in 2011
were estimated at $7.6 billion. In 2013, around 117,000 motor
vehicles worldwide were identified as stolen, thanks to the
SMV database. By the end of the year, the number of database
records had risen to more than 7.2 million. Vehicles are not
only stolen for their own sake, but are also trafficked to
finance other crimes. They can also be used as bomb carriers
or in the perpetration of other crimes. The National Insurance
Crime Bureau (NICB) is a North American non-profit
membership organization located in Des Plaines, Illinois. Yet
the stolen rate of the auto mobiles was not reduced. For that a
new method should be proposed that reduces the stolen rate
along with the thief catching technique. The main objectives
of this project are to reduce the vehicle theft ratio as well as
introduced a method for identifying and catch the thief. Fig1
shows components of proposed system.
Fig:1 block diagram of proposed system
2. SYSTEM IMPLEMENTATION
Face recognition and detection
There are many algorithms used in face recognition and
detection and many more are being developed.PCA is the best
and mostly used algorithm in face recognition. It is used for
compression and overcome many of the recognition quires
like pose variations, illumination etc. The Linear Discriminate
Analysis (LDA), and some other systems are developed by
combining different algorithms. PCA is also known as “Eigen
faces” algorithm. The main idea is de-correlate data in order
to highlight differences and similarities by finding the
principal direction (i.e, the Eigen vector) of the covariance
matrix of a multidimensional data. A part of the great
efficiency of the PCA algorithm is to take only the best
eigenvectors in order to generate the subspace (face space)
where the gallery images will be projected onto, leading to a
reduction of dimensionalities.
Principal Component Analysis
The purpose of PCA is to reduce the large dimensionality
of the data space (observed variables) to the smaller Intrinsic
dimensionality of feature space (independent variables),
which are needed to describe the data economically. The main
idea of using PCA for face recognition is to express the large
10 vector of pixels constructed from 15 facial images into the
compact principal components of the feature space. This can
be called Eigen face Projection.
3 Find covariance matrix of the matrix obtained from step 2
for this covariance matrix.
4 Find Eigen values and Eigen vectors, and then find Eigen
faces with larger Eigen values.
5 Find out weight vector using this Eigen faces
6 For new/unknown image also the process will be echoed
from step 1to3 and then find out weight vector for test image.
7 Now find Euclidian distance between weight vectors of
unknown image and database images.
8 If this distance is less than threshold then test image is
considered to be in database and hence authorized, otherwise
unauthorized.
Benefits of PCA:
1. The reduction in the dimension of the data.
2. No data redundancy, as components are orthogonal.
3. Complexity of grouping the images can be reduced.
4. Used for criminal investigation.
5.Entrance control in buildings, access control for
computers, for Automated Teller Machines, at the post offace, passport verification, and identifying the faces in a given
database.
Fig3: Proposed method circuit
3. EXPERIMENTAL RESULTS
In this project the real time face recognition is performed
using PCA method with the help of web camera.
Fig2: Flow chart of PCA algorithm
Steps of PCA:
1 Get database set of images and then find mean of the
images
2 Find the difference between mean image and each of
database images.
Fig 4: Add images into data base
CONCLUSION
Fig 5:After adding database images
This paper has been successfully designed and tested.
When compared with the existing system the advantage of this
paper is that we can prevent the vehicle theft by using face
recognition. In this paper a remote control system based on
Global System for Mobile (GSM), Global Positioning system
(GPS) and CORTEX-M3 is introduced. The system is
suitable for a real time monitoring in car security, controlling
and avoiding theft
with face recognition
and
detection.GSM/GPS has been used for the sending MMS and
knowing location of the car. By using suitable camera (3D
camera) all face recognition troubles like poor light and
background conditions, pose variations etc., will be covered.
With the adoption of standards and community awareness,
this technology will become more and more acceptable.
REFERENCES
[1]
Saurabh P.Bahurupi, D.S.Chaudhari“Principal Component Analysis for
Face Recognition “International Journal of Engineering and Advanced
Technology(IJEAT) ISSN: 2249 –8958, Volume-1, Issue-5, June 2012.
[2]
Zhang Wen, Jiang Meng” Design of Vehicle positioning System
Basedon ARM”, Business Management and Electronic Information
(BMEI), International Conference 2011 IEEE.
[3]
Jian Xiao and Haidong Feng, “A Low-cost Extendable
FrameworkforEmbedded Smart Car Security System” Proceedings of
the 2009 IEEE International Conference on Networking, Sensing and
Control,
Okayama,
Japan,
pp
829-833,
2009
[4]
Saifullah, Dr. Attaullah Khawaja, Hamza, and Arsalan, Maryam,mAnu
“Keyless Car Entry through Face Recognition Using FPGA” ,
International Conference on Future Information Technology and
Management Engineering, pp.224-227, 2010.
Chee-Ming Ting, Lih-Heng Chan, and ShHussainSalleh, "Face
Biometrics Based On Principal Component Analysis and Linear
Discriminant Analysis", Journal of Computer Science, 20 I 0, pp. 693699.
Guiming, and Zhixiong Liu, "A Vehicle Antitheft and Ala= System
Based on Computer Vision", IEEE on Electrical Systems, 2005,
pp.326-330.
Fig6 : Recognition of authorized person
Fig5&fig6 shows the screen shot after the collection of images
and recognition of authorized person.
[5]
Fig7 shows the screen shot of unauthorized person.
[6]
Author’s Details
Fig8: Alert message sent to owner mobile. Fig8 shows an alert
message sent to owner mobile. For checking the working
status of the GSM modem with the GPRS service.
Leela Prasanna Ravuri, Recevied her
B.tech degree from JNTU
Kakinada, currently pursuing her
M.tech on embedded system in CMR
College of Engineering Technology,
Hyderabad.
T. Swapna Rani,received her M.tech
degree from Osmania University,
Hyderabad, in the area of VLSI and
Embedded
Systems.
Currently
working as Assistant Professor in ECE
Dept, CMR College of Engineering
Technology, Hyderabad.