Professional Documents
Culture Documents
Aayush Choudhary
(17BIS0013)
Swarnim Shalin
(17BIS0021)
Himanshu Ranjan
(17BIS0062)
Project Report
of
ECE3026 –IoT System Architecture
Fall Sem 2019-20
Swarnim Shalin
(17BIS0021)
Project Report
of
ECE3026 –IoT System Architecture
Fall Sem 2019-20
In the world of Internet of Things (IoT) when we have all the technologies to revolutionize our
life, it's a great idea to develop a system which can be controlled and monitored from anywhere.
There are many types of good security systems and cameras out there for home security but they
are much expensive so today we will build a low cost simple Raspberry Pi based Intruder Alert
System, which not only alert you through an email but also sends the picture of Intruder when it
detects any.
In this IoT based Project, we will build a Home Security System using PIR Sensor and PI
Camera. This system will detect the presence of Intruder and quickly alert the user by sending
him an alert mail. This mail will also contain the Picture of the Intruder, captured by Pi camera.
Raspberry Pi is used to control the whole system. This system can be installed at the main door
of your home or office and you can monitor it from anywhere in the world using your Email over
internet
1. Introduction
In this IoT based Project, we will build a Home Security System using PIR Sensor and PI
Camera. This system will detect the presence of Intruder and quickly alert the user by sending
him a alert mail. This mail will also contain the Picture of the Intruder, captured by Pi camera.
Raspberry Pi is used to control the whole system. This system can be installed at the main door
of your home or office and you can monitor it from anywhere in the world using your Email over
internet.
2. Literature Review
With data and information accumulating in abundance, there is a crucial need for high security.
Biometrics has now received more attention. Face biometrics, useful for a person’s
authentication is a simple and non-intrusive method that recognizes face in complex
multidimensional visual model and develops a computational model for it. In this paper first we
present an overview of face recognition and discuss the methodology and its functioning.
Thereafter we represent the most recent face recognition techniques listing their advantages and
disadvantages. Some techniques specified here also improve the efficiency of face recognition
under various illumination and expression condition of face images.
Hardware components:
Raspberry Pi
Pi Camera
PIR Sensor
LED
Bread Board
Resistor (1k)
Connecting wires
Power supply
Software:
Raspbian Stretch
Opencv
Dlib and face_recognition python libraries
4. Proposed Work
A PIR sensor is used to detect the presence of any person and a Pi Camera is used to capture the
images when the presence it detected. Whenever anyone or intruder comes in range of PIR
sensor, PIR Sensor triggers the Pi Camera through Raspberry Pi. Raspberry pi sends commands
to Pi camera to click the picture and save it. And after that facial recognition part comes into
play, using dnn modules, facial recognition libraries and trainer it compares the image captured
with the saved data of the user. If the user is detected the cameras shows the name and allow the
person to enter the site. And it the person is an unknown then it shows as an intruder and After it,
Raspberry Pi creates a mail and sends it to the defined mail address with recently clicked images.
The mail contains a message and picture of intruder as attachment. Here we have used the
message “Please find the attachment”, you can change it accordingly in the Code given at the
end. Here the pictures are saved in Raspberry Pi with the name which itself contains the time and
date of entry. So that we can check the time and date of intruder entry by just looking at the
Picture name.
5. Design
6. Implementation
PIR MOTION SENSOR : Infrared radiation is electromagnetic radiation (EMR) with longer
wavelengths than those of visible light, and is therefore invisible to the human eye. It is
sometimes called infrared light. It extends from the nominal red edge of the visible spectrum at
700 nanometers (frequency 430 THz), to 1 millimetre (300 GHz) although specially pulsed lasers
can allow humans to detect IR radiation up to 1050 nm.). Most of the thermal radiation emitted
by objects near room temperature is infrared. Like all EMR, IR carries radiant energy, and
behaves both like a wave and like its quantum particle, the photon.
FACIAL RECOGNITION: Face recognition uses the visible physical structure of the face and
analyses the spatial geometry of distinguishing features in it identify an individual. Facial
recognition systems have a higher relative unit cost, they do offer increased accuracy levels.
Inherently the technology has a number of advantages, most notably, that it is readily acceptable
by the public and relatively easy to integrate with other security systems, particularly CCTV. But
development work still needs to be done to improve its performance. It needs to make allowance
for the changes that occur to the human face over time - aging, facial hair, skin tone, glasses, etc.
All of which could impede the recognition. Software. And technically, the affect of prevailing
light conditions and the angle of the image need to be reduced, thereby allowing faster and more
accurate Processing.
7. Screenshots
8. Results and conclusions
This project will detect the presence of Intruder and quickly alert the user by sending him an
alert mail and will also detect whether the person is authenticated or not by using facial
recognition. We are using dlib and facial recognition libraries for the facial recognition and
authentication which will recognise the know persons and send a mail to the admin mail
containing the picture of the person .Raspberry Pi is used to control the whole system. This
system can be installed at the main door of your home or office and you can monitor it from
anywhere in the world using your Email over internet.
9. References
1. Aishwarya , Dr. J Arokia Renjith, ”,2017” Enhanced Home Security Using IOT and Raspberry
PI”
2. E. Isa and N. Sklavos, 2016” Smart Home Automation: GSM Security System Design &
Implementation”
3. Lalit Negi ,Anju Gupta, Pooja Khurana, May 2017,” Enhancing Security System using Finger
Print based Authentication”, Volume 166 – No.3
4. R. Rani, S.Lavanya, ,2018 , “IoT Based Home Security System Using Raspberry Pi with
Email and Voice Alert”
5. Siddharth Wadhwani, Uday Singh, Prakarsh Singh, Shraddha Dwivedi, 2018,” Smart home
automation and security system usinh IoT and Arduino”
6. Xin Hong , 2016, Chenhui Yang , Chunming Rong,” Smart Home Security Monitor System”