Forest Preservation and Deforestation Prevention
Alert System using Digital Signal Component
Analysis and Detection
Minor Project Proposal
Submitted to: Submitted by:
Dr. Abhijit Bhattacharyya Deepak Kamat (17427)
Project Coordinator (B.Tech) Mukul C. Mahadik (17469)
ECED, NIT Hamirpur Akshat Gupta (17489)
Adarsh Jhariya (17490)
Under the guidance of
Dr. ASHOK KUMAR
Associate Professor
Department of Electronics and Communication Engineering
DEPARTMENT OF
ELECTRONICS & COMMUNICATION ENGINEERING
NATIONAL INSTITUTE OF TECHNOLOGY
HAMIRPUR-177005, HP (INDIA)
AUG-DEC 2020
PROJECT PROPOSAL
Title: Forest Preservation and Deforestation Prevention Alert System using
Digital Signal Component Analysis and Detection.
Introduction:
As the world seeks to slow the pace of climate change, preserve wildlife, and support billions of
people, trees inevitably hold a major part of the answer. Yet the mass destruction of trees—
deforestation—continues, sacrificing the long-term benefits of standing trees for short-term gain.
Forests cover about 30 percent of the world’s land area, but they are getting wiped off at an
alarming rate. Between 1990 and 2016, the world lost 1.3 million square kilometers of forest —
an area larger than South Africa. Since humans started cutting down forests, 46 percent of trees
have been felled, according to a 2015 study in the journal Nature. We need trees for a variety of
reasons, not least of which is that they absorb not only the carbon dioxide that we exhale, but
also the heat-trapping greenhouse gases that human activities emit. As those gases enter the
atmosphere, global warming increases, a trend scientists now prefer to call climate change.
Ending deforestation is our best chance to conserve wildlife and defend the rights of forest
communities. On top of that, it’s one of the quickest and most cost effective ways to curb global
warming. That’s why we’re campaigning for a deforestation-free future.
The system consists of a device which can record and transmit the local sound near the trees
which can then be processed and monitored to detect any kind of smuggling activities using
digital signal processing.
It is a low powered device that is equipped with a sound analysis module that can isolate
different bands of sound. This device is programmed to identify the sound of a logging
machinery such as a chainsaw and then alert the authorities. It is a device that detects
deforestation using sound signal analysis detecting the surrounding areas of the felled trees.
Literature Survey:
A research by the International Union of Forest Research Organizations published in the
Hindustan Times says that India is placed on third position for illegally importing logged timber
in the world. With a yearly import estimation of over Rs. 40 billion, India represents nearly one
tenth of the worldwide illicit trading of wood.
Although many researchers are working on acoustic signal processing, still detection of tree
cutting through acoustic signals is done by very few researchers. This survey presents a summary
of algorithms used for acoustic signal recognition and detection.
G. Sharma et al. (Sharma et al., 2016, Sharma, 2018) gave a measurable solution for detecting
tree cutting using acoustic signals which was observed by saw scratching through a bole. The
noise was separated from acoustic signals using Signal-to-noise (SNR) based algorithm.
P. Sharma in 2017 proposed an efficient SNR based algorithm which is used for deriving
different attributes in a speech sound for different tasks in the recognition of speech. The authors
used a method which consists of two stages. The first stage involves learning various dictionaries
for every speech entity and the second stage involves using a sparse solver to obtain sparse
features.
One more research project (Mitsubishi Research Institute, 2019) from Mitsubishi Research
Institute can recognize seven sorts of sound signals, for example, a chime ringing, hand clap etc
with a precision of 80% or more. This Framework uses an array of microphone and a personal
computer to process sound signals. It also recognizes the sound and even tries to find the relative
position of the source of sound.
Objective:
The main objectives of this project are as follows:
1. Real-time alerts issued to forest officials and authorities
2. An acoustic signature can provide valuable information about the activities of any
intruder inside the forest.
3. The early method of detection of tree cutting is to regularly monitor the forest area using
some automatic techniques
4. Assistance to organizations implementing forestry programmes.
5. Protection of the environment in order to promote sustainable development.
Methodology:
1. Captures acoustic signal from audio signal recording devices.
2. Remove noise using signal analysis software such as MATLAB.
3. Component extraction from a signal comprising multiple components.
4. Whenever an intrusion is detected a message or alert signal will be sent to the nearby
authorities.
