HOME AUTOMATION THROUGH WEB BASED

MOBILE DEVICE USING RASPBERRY PI R.Sathyaraj1, R.Shanmugapriya2, K.Shanmugapriya3, S.Shobika4, S.Sindhuja5

Assistant Professor1, U.G Student2,3,4,5

Department of Electronics and Communication,

Kings College of Engineering, Punalkulam, Pudukottai.

Abstract— Home automation web based mobile device

project will be able to design and implement automatic

intruder sensing and alerting system using raspberry pi 3

based video acquisition system. For an effective Human

Computer Intelligent Interaction, we integrate Raspberry pi

based real-time security that needs to recognize the motion in

unauthorized area. Here an efficient Scale-invariant feature

transform (SIFT) combined with optical flow algorithm. If

any abnormal condition exists then it will send an image to

relevant person via WhatsApp.

Index Terms—Frame separation, Intruder Detection,

Training, Alerting (key words).

I. INTRODUCTION

Motion detection is an important security operation in the

selection of significant segments of the video signals. The

ongoing research on object tracking in video sequences has

attracted many researchers. Detecting the objects in the video

and tracking its motion to identify its characteristics has been

merging as a demanding research area in the domain of image

processing and computer vision.

An image capture system with python computing can

extract information from images without need for an external

processing unit, and interface devices used to make results

available to other devices. The choosing of a python platform

is very unique and easy to implement.

Considering the requirements of image capturing and

recognition algorithm, Raspberry Pi processing module and its

peripherals, implementing based on this platform, finally

actualized Image Capturing using Raspberry Pi system

(ICSRS). Experimental results show that the designed system

is fast enough to run the image capturing, recognition

algorithm, and the data stream can flow smoothly between the

camera and the Raspberry Pi board.

By receiving alerts on your device the user are informed of all

possible issues occurring in the house and it gives them

various possibilities to deal with the problems. This is how an

automated system proves useful to people in providing them

security, comfort and easily accessible.

II. EXISTING SYSTEM

A. Closed Circuit Television

Closed circuit televisions are also known as CCTV. These

systems are the most commonly used security system. CCTV

cameras record live videos or capture images. Two kind of

CCTV available are wireless and wired. These systems are

capable of recording live videos for a time period. CCTV

cameras can be applied anywhere but it is most commonly

used for security purposes in banks, airports, shopping centers

etc. CCTV cameras continuously monitor a particular place or

sometimes operated for a particular event. The earliest CCTV

systems were not capable of recording and storing

information. It was the development of reel-to-reel media

which became crucial turning point in the enhancement of

modern systems. These systems are highly influential in crime

prevention, industrial processes, traffic monitoring etc. Digital

Multiplexing allows several CCTV cameras to record at once.

These enable the recording events at various locations. The

latest CCTV systems enhanced its performance by coupling

with Internet. Industrial processes that take place under

conditions dangerous for humans are today often monitored

with CCTV systems. Chemical Industry and Nuclear Industry

are the examples of industries in which these systems

supervise and provide a highly beneficial device.

B. Home Alarm

Security alarm is a system designed to detect intrusion and

unauthorized entry into a building or area. These systems are

used in residential, commercial, Industrial and military

properties for protection against burglary or property damage,

as well as personal protection against intruders. Some alarm

system serves a single purpose burglary protection; the

combination system provide both fire and intrusion protection.

Systems range from small self-contained noisemakers, to com

plicate d, multi-area systems with computer monitoring and

control. Alarms comes with different of sensors such as

Passive Infrared Detectors (PIR), Ultra Sonic Detectors,

Microwave detectors, photoelectric beams, glass-break

detection, vibration or inertia detectors and so on.

III. PROPOSED SYSTEM

Block Diagram

Final frame

Video to frame

conversion

Camera

Opencv

Library

Whatsapp

alert

Rasbian OS

Power Unit

Raspberry Pi-3

With image

processing tools

Display

Monitor

Whatsapp

Library

WIFI/LAN

Blob analysis

Threshold

matching

Frame

preprocessing

Background

subtraction

The aim of our project is to propose a raspberry pi computer

with open CV based approach to identify the moving object

detection. It allows handling scenes containing moving

backgrounds and gradual illumination variations, and achieves

robust detection for different types of videos taken with

stationary cameras. This can also be used for obtaining

detection information related to the size, location and

direction of motion of moving objects for assessment

purposes. The motion capture image is sent to the owner’s

Whatsapp when such an alarm is risen which he can view from his mobile device, anywhere and anytime.

The proposed method uses the raspberry pi board is the main

controller. The latest version of raspbian wheezy is used on to

the board.

The system designed system can be operated in two

different sessions, ie one for capturing and creating a data base

and the other session is to capture the image and which can be

used for identifying or comparing the images in the database.

Here in the second session we use methodology of face

recognition for finding the matches.

It is realized that the real-time firmness of video flow with

high reliability to detect and track the object in frame

sequence.

IV.HARDWARE REQUIREMENTS

A. Raspberry Pi:

The Raspberry Pi 3 Model B features a quad-core 64-bit

ARM Cortex A53 clocked at 1.2 GHz. This puts the Pi 3

roughly 50% faster than the Pi 2. Compared to the Pi 2, the

RAM remains the same – 1GB of LPDDR2-900 SDRAM, and

the graphics capabilities, provided by the Video Core IV GPU,

are the same as they ever were. As the leaked FCC docs will

tell you, the Pi 3 now includes on-board 802.11n WIFI and

Bluetooth 4.0. WIFI, wireless keyboards, and wireless mice

now work out of the box.

B. Hardware Specifications

SOC: Broadcom BCM2837

CPU: 4×ARMCortex-A53,1.2GHz

GPU: Broadcom Video Core IV

RAM: 1GB LPDDR2 (900 MHz)

NETWORKING: 10/100 Ethernet, 2.4GHz 802.11n wireless

BLUETOOTH: Bluetooth 4.1 Classic, Bluetooth Low Energy

STORAGE: micro SD

GPIO: 40-pin header, populated

PORTS: HDMI, 3.5mm analogue audio-video jack, 4× USB

2.0, Ethernet, Camera Serial Interface (CSI), Display Serial

Interface (DSI)

C. Raspberry Pi Camera:

The camera module used in this paper is raspberry pi camera

module as shown in the figure. The camera module plugs to

the CSI connector on the Raspberry Pi. It's able to deliver

clear 5MP resolution image, or 1080p HD video recording at

30fps. The camera module attaches to Raspberry Pi by a 15

pin Ribbon Cable, to the dedicated 15 pin MIPI Camera Serial

Interface (CSI), which was designed especially for interfacing

to cameras. The CSI bus is capable of extremely high data

rates, and it exclusively carries pixel data to the BCM2835

processor.

V.SOFTWARE REQUIREMENTS

A. Python

It is a high level programming language which allows

programmers to express the concepts in fewer lines of codes.

It provides reduction in coding lines than the programming

languages such as c and JAVA.

B. Open CV

The application written for this thesis relies heavily on

computer vision, image processing and pixel manipulation, for

which there exists an open source library named Open CV

(Open Source Computer Vision Library), consisting of more

than 2500 optimized algorithms. Uses range from facial

recognition, object identifying, classifications of human

actions in videos, achieved with filters, edge mapping, image

transformations, detailed feature analysis and more. Having

Linux support, this is the perfect choice for developing an

application specifically for a Raspberry Pi based system.

C. Whatsapp Library

Yowsup is a python library that enables you build

application which use Whatsapp service. Yowsup has been

used to create an unofficial WhatsApp client. yowsup-cli is a

command Yowsup comes with a command line client exposes

many yowsup capabilities for quick access in command line.

At the moment it supports only a smaller set of yowsup

function as it's still in under heavy development, but

eventually it will expose every single yowsup capabilities.

III. ALGORITHM USED

A. Sift (Scale Invariant Feature Transform):

It is used to identify internal character and direction of

the object. Track images, detect and identify objects(which

can be partly hidden as well).This helps uniquely identify

features. Let’s say you have 50,000 features. With this

representation, you can easily identify the feature you are

looking for (say, a particular eye or a sign board).

B. BACKGROUND SUBTRACTION

Background subtraction is the process of separating out

foreground objects from the background in a sequence of

video frames. Background subtraction is used in many

emerging video applications, such as video surveillance,

traffic monitoring, and gesture recognition for human-machine

interfaces and etc.

C. Blob Analysis

When moving object is selected by the color background

modeling its performance degrades and morphology is tracked

individually because there may be occlusion occurred. Here in

this paper group tracking is used to remove the problem of

misidentification. Grouping scheme is required to classify

moving object into several object. Blob labeling is used to

group moving object which required less computational cost

also it is easily implemented.

VI.CONCLUSION

In this paper we proposed a security system, which is able to

monitor the home perimeter and notify the owner when a

visitor intrudes. The system is able to notify the user instantly

through Whatsapp message. Unlike the existing CCTV

systems, the software of the proposed system can be updated.

It is an efficient and cost effective security solution for home

security automation. The advantage of using this system is

that, it is very user friendly and more importantly it is very

simple to operate. This system is smaller, lighter and

with lower power consumption, so it is more convenient than

the PC-based face recognition system. Apart from, this

technique is better than other home automation methods, using

SMS and DTMF as the call tariff, is a big drawback.

REFERENCE

[1] 'Motion video sensor in the compressed domain'. SCS Euromedia Conf.,

Valencia, Spain, 2001.

[2] GieseandT.Poggio(2003) Neural mechanisms for the recognition of Biological movement sand action. Nature Reviews Neuro science

4:179–192.

[3] Neural Networks for 3D Motion Detection From a Sequence of Image Frames, Chan Lai Wan and Yip Pak Ching, IEEE, computer Science

Dept., The Chinese University of Hong Kong, 1991.

[4] Ferster and K.D. Miller. (2000). Neural mechanisms of orientation Selectivity in the visual cortex. Annual Review of Neuroscience,

23:441–471.

[5] Amit Narote, Abhishek Dsilva, Selma Misquitta and Palak Khandelwal (2015), Smart home automation using arm11, International Journal of

Current Engineering and Technology, vol. 5.

[6] Gayatri Kulkarni, Priyanka Gode, Jadi Pratap Reddy and Madhura Deshmukh (2015), Android based smart home system, International

Journal of Current Engineering and Technology, vol. 5.

[7] Pierre Raufast (2013), Raspberry Pi Open CV and camera board, https://thinkrpi.wordpress.com/opencv-andpi-camera-board/

[8] Lady ada (2014), PIR motion sensors, Pyroelectric (Passive) InfraRed

Sensors , https://learn.adafruit.com/pir-passive-infrared-proximity-motion-sensor/overview .

[9] Rakesh Ron (2013), L293D Motor Driver IC,

http://www.rakeshmondal.info/l293d-motor driver.

[10] Jason Barnett (2014), Controlling DC Motors Using Python with a

Raspberry Pi,

[11] http://computers.tutsplus.com/tutorials/controlling-dc-motors-using-python-with-a-raspberry-pi--cms-20051

[12] P.Vigneswari, V.Indhu, R.R.Narmatha, A.Sathinisha and J.M.Subashini

(2015), Automated security system using surveillance, International Journal of Current Engineering and Technology, vol. 5.