Forest Fire Detection Using Sensor Networks

“Forest fire detection using sensor networks”
PROJECT REPORT
Submitted for the course-‘Measurement and Instrumentation’
COURSE CODE- “EEE2004”
NAME OF FACULTY- Associate Professor

Vivekanandan S (SCHOOL OF ELECTRICAL
ENGINEERING)
CERTIFICATE
This is to certify, that the project entitled “Forest fire detection using sensor
networks” submitted by the following students, B. Tech, VIT University, Vellore
for the partial fulfillment of the B. Tech- Measurement and Instrumentation CAL
course, is a record of bonafide carried out by the students under my supervision, as
per VIT regulation of academic.
The project carried by the following students have not submitted in

anywhere in the University.
Name of the students
Muskan Agarwal 16BEE0143
Ananyo Bannerjee 16BEE0148
Place: Vellore Signature of FACULTY
Date: 8 November 2017 Prof. Vivekanandan S

ACKNOWLEDGEMENT
With all our gratitude we would like to thank VIT UNIVERSITY for giving us the
opportunity to work under this project as a team. We would like to express our
sincere thanks to Prof. Vivekanandan S for guiding us and in completing this

project successfully, your guidance helped us a lot.
At last we would thank the university staff for letting us access the resources and
giving their expertise suggestions.
ABSTRACT
Forest Fires are one of the most important and prevalent

type of disasters and they can create a great deal of
Environmental Impacts due to which their early detection is
very vital. The main need for choosing this particular
application for the detection of forest fires is to overcome
the demerits present in the existing technologies of MODIS
and Basic Wireless Sensor Network-based Forest Fire
Detection Systems and an advanced system is developed for
the detection of forest fires. The two main modules present
in the project are the Monitoring Area Module and the
Forest Area Module. All these together are split into two
sub-modules for step-by-step development and
implementation. Those include Sensors’ Module, Serial
Communication Module using Zigbee. These two sub-
modules belong to the Forest Area Module. They are
integrated together and mechanical modeling is done to
place it in the forest, whereas, the PC-based Web Server is
developed for the Monitoring Area.
INTRODUCTION
Forests are part of the important and indispensable resources for human survival
and social development that protect the balance of the earth ecology. However,
because of some uncontrolled anthropogenic activities and abnormal natural
conditions, Forest Fires occur frequently. These fires are among the most serious
disasters to forest resources and the human environment. In recent years, the
frequency of forest fires has increased considerably due to climate changes,
human activities and other factors. The prevention and monitoring of Forest Fires
has become a global concern in Forest Fire prevention organizations. Currently,
Forest Fire prevention methods largely consist of Patrols, Observation from watch
towers, Satellite Monitoring and lately Wireless Sensor Networks . Although
observation from watch towers is easy and feasible, it has several defects. In the
first place, this method requires many financial and material resources and a
trained labor force. Second, many problems with fire protection personnel
abound, such as carelessness, absence from the post, inability for real-time
monitoring and the limited area coverage.
Methodology Involved
This project was carried out in python using various dependency which involves
Open CV2, Sk-Learn, Ski-Image, Numpy, Collections. The algorithm used in this
project is multilayer perceptron. The dataset is taken from MNIST (Modified
National Institute of Standards and Technology database).
There are four steps to build the isolated digits recognition system :
Image acquisition : We will acquire an image to our system as an input .this

image should have a specific format, for example, bmp format and with a
determined size such as 30×20 pixels. This image can be acquired through the
scanner or, digital camera or other digital input devices.
Preprocessing : After acquiring the image, it will be processed through sequence

of preprocessing steps to be ready for the next step.
Noise removal : Reducing noise in an image. For on-line there is no noise to

eliminate so no need for the noise removal. In off-line mode, the noise may come
from the writing style or from the optical device captures the image.
Normalization-scaling : standardize the font size within the image. This

problem appears clearly in handwritten text, because the font size is not restricted
when using handwriting.
Thinning and skeletonization : Representing the shape of the object in a

relatively smaller number of pixels. Thinning algorithms can be parallel or
sequential. Parallel is applied on all pixels simultaneously. Sequential examine
pixels and transform them depending on the preceding processed results.
Segmentation : Since the data are isolated, no need for segmentation. With regards
to the isolated digits, to apply vertical segmentation on the image containing more
than digit will isolate each digit alone.
Normalization scaling and translation : Handwriting produces variability in

size of written digits. This leads to the need of scaling the digits size within the
image to a standard size, as this may lead to better recognition accuracy. We tried
to normalize the size of digit within the image and also translate it to a specific
position by the following.
Feature extraction : Feature extraction is not part of this project. Feature types
are categorized as follows:
• Structural features: It describes geometrical and topological characteristics of
a pattern by representing its global and local properties
• Statistical features: Statistical features are derived from the statistical distribution
of pixels and describe the characteristic measurements of the pattern
• Global transformation: Global transformation technique transforms the pixel
representation to a more compact form. This reduces the dimensionality of the
feature vector and provides feature invariants to global deformation like translation,
dilation and rotation
Classification and recognition : Neural Network is a network of non-linear

system that may be characterized according to a particular network topology.
Where, this topology is determined by the characteristics of the neurons and the
learning methodology. The most popular architecture Of Neural Networks used in
Arabic digits recognition takes a network with three layers. These are: Input layer,
hidden layer and output layer. The number of nodes in the input layer differs
according to the feature vector’s dimensionality of the segment image size.
CODE – (Arduino Output)
int ThermistorPin = 0;
int Vo;
float R1 = 10000;
float logR2, R2, T, Tc, Tf;
float c1 = 1.009249522e-03, c2 = 2.378405444e-04, c3 = 2.019202697e-07;
void setup() {
Serial.begin(9600);
}
void loop() {
Vo = analogRead(ThermistorPin);
R2 = R1 * (1023.0 / (float)Vo - 1.0);
logR2 = log(R2);
T = (1.0 / (c1 + c2*logR2 + c3*logR2*logR2*logR2));
Tc = T - 273.15;
Tf = (Tc * 9.0)/ 5.0 + 32.0;
Serial.print("Temperature: ");
Serial.print(Tf);
Serial.print(" F; ");
Serial.print(Tc);
Serial.println(" C");
delay(500);
}
Snapshots
Results and Observations
1. Xbee output
2 Arduino outputs
Need of Digit Recognition
In this fast moving, evolving world there is a need of systems to fasten our works
and in this the processing of handwritten documents plays a major role. We several
times observe that while at the banks we see the workers at the bank looking at
those number and many times they cannot identify the numbers due to several
reasons , here comes the need of this algorithm where it can observe the digits,
makes the project faster and even helps in differentiating the digits due to its vast
MNIST database. It can also be used for directories and also for observing the
number plates of vehicles for several purposes. This change in this world will help
the humans and will also show the advancement of our society in this pacing
environment.
CONCLUSION
An advanced system for Forest Fire Detection was developed which overcomes
the demerits of the Existing technologies of Forest Fire Detection. It can be
ensured that the system developed can be implemented on a large scale due to
its promising results. Mechanical modeling for accessible and inaccessible areas
helps in the easy implementation of the Forest Area modules. The system can
also be upgraded with low-power elements, higher versions of Zigbee in order to
make the system run for longer periods with increased efficiency..

Forest Fire Detection Using Sensor Networks

Uploaded by

Copyright:

Available Formats

Forest Fire Detection Using Sensor Networks

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Forest Fire Detection Using Sensor Networks

Uploaded by

Copyright:

Available Formats

“Forest fire detection using sensor networks”

Submitted for the course-‘Measurement and Instrumentation’

COURSE CODE- “EEE2004”

NAME OF FACULTY- Associate Professor

The project carried by the following students have not submitted in

Name of the students

Muskan Agarwal 16BEE0143

Ananyo Bannerjee 16BEE0148

Place: Vellore Signature of FACULTY

Date: 8 November 2017 Prof. Vivekanandan S

sincere thanks to Prof. Vivekanandan S for guiding us and in completing this

Forest Fires are one of the most important and prevalent

Image acquisition : We will acquire an image to our system as an input .this

Preprocessing : After acquiring the image, it will be processed through sequence

Noise removal : Reducing noise in an image. For on-line there is no noise to

Normalization-scaling : standardize the font size within the image. This

Thinning and skeletonization : Representing the shape of the object in a

Normalization scaling and translation : Handwriting produces variability in

Classification and recognition : Neural Network is a network of non-linear

You might also like