1. K.S.R.M. COLLEGE OF ENGINEERING
(UGC-AUTONOMOUS)
Kadapa, Andhra Pradesh, India– 516 003
Approved by AICTE, New Delhi & Affiliated to JNTUA, Ananthapuramu.
An ISO 14001:2004 & 9001: 2015 Certified Institution
Project Abstract Review for the award of Bachelor of Technology
A remote sensing approach for monitoring and analysis of Land Use and Land
cover (LULC) classification over an area using high resolution satellite data
Under The Guidance of
Sri R. V. Sreehari, M. E,.
Associate Professor.
Batch No: C 01
Project Associates :
V. Yuvaraju – 199Y1A04H4
Y. Vinay Kumar – 199Y1A04H8
N. Narasimha Reddy – 209Y5A0415
S. Sameer Ahammad – 199Y1A04F1
U. Anuhya Bhai (W) – 199Y1A04G8
Department of Electronics and Communication Engineering
2022-2023
2. CONTENTS
• Abstract
• What is Land Use Land Cover Classification?
• Why Land Use Land Cover Classification?
• Methodology
• Required Tools
• Time Line
• Applications
• References
3. ABSTRACT
Land use and land cover (LULC) classification approaches based on remote sensing
data are used for land monitoring and analysis, as well as rapid environmental
change. The main focus of this project is to illustrate the practical approach to
analyzing and mapping land use and land cover features using high-resolution
satellite images. Land use and land cover (LULC) mapping is required by some
government institutions to manage their natural resources sustainably at various
temporal and spatial scales. This study uses Sentinel-2 satellite data from 2015 to
2020, from which we can classify and monitor the changes that occurred over a
particular area. Here, this study classifies land cover to additionally classify land use
categories and eventually obtain a LULC map over a yearly period with different
spatial resolutions.
4. What is Land Use Land Cover (LULC) classification?
• LULC is the process of assigning land cover classes to pixels and categorize them.
For instance, water, metropolitan, horticulture, buildings, woodlands, agriculture,
grasslands, mountains, and highlands.
5. Why Land Use Land Cover (LULC) classification?
• By knowing inch-by-inch information about land use and land cover in the study
unit, it is easy to make policies and launch programs to save our environment.
• For ensuring sustainable development, it is necessary to monitor the ongoing
process of land use/land cover pattern over a period of time.
• LULC maps also help us study the changes that are happening in our ecosystem
and environment.
• LULC maps also play a significant and prime role in planning, management, and
monitoring the programs at local, regional, and national levels.
• The other most satisfactory thing is that it is good to see the changes on our
mother earth.
6. METHODOLOGY
Data Preprocessing
Data Set Downloading
Training Vector Creation
Identification of Appropriate Classifier
Training the Classifier with the Vectors
Classification
Selection of Area for the Analysis
Analysis of LULC Changes over Years
Noise Correction
Subset
Resampling
Reprojection
7. REQUIRED TOOLS
❖For the Data Set USGS Earth Explorer
Copernicus Data Hub
❖For Data Preprocessing SNAP Tool Box
QGIS Application
❖For Training Vector
Creation QGIS Application
❖Classification SNAP Tool Box
QGIS Application
USGS – United Nations Geographical Survey
SNAP – SeNtinel Application Platform
QGIS – Quantum Geographical Information Survey
8. Time Line
Topic/application to learn Mentioning Time
Learning of Fundamentals
1. Data Downloading
2. SNAP Tool Box
3. QGIS
November
Data Set and Pre-processing Period
1. Interested Area Selection
2. Required Data Downloading
3. Pre-processing of Data
December
Selection of Appropriate Classifier
and Training Data Creation
1. Different Types of Classifiers
2. Creation of Training Vectors
3. Selection of Classification
Method
February and March
Classification and Analysis
1. Changes Occurred Over Years
2. Resultant Consequences
3. Required Measures to Be Taken
April
9. Applications
• Natural resource management.
• Can create baseline maps for GIS (Geological Information Survey) units.
• Analysis of Urban/Agricultural/Forest land expansion/encroachment.
• Environmental Changes Detection.
• It allows us to make policies and launch programs to save our environment.
10. REFERENCES
1. Dinesh Sathyanarayanan, DV Anudeep, C Anjana Keshav Das, Sanat Bhanadarkar, Uma D, R Hebbar, K. Ganesh Raj, “A
Multiclass Deep Learning Approach for LULC Classification of Multispectral Satellite Images”, IEEE India Geoscience
and Remote Sensing Symposium (IGARSS), DOI : 10.1109/InGARSS48198.2020.9358947, 2020.
2. R. Gladys Villegas, Frieke Van Coillie, Daniel Ochoa, “Mapping and Assessment of Land Use and Land Cover for
Different Ecoregions of Ecuador Using Phenology-Based Classification”, IEEE India Geoscience and Remote Sensing
Symposium (IGARSS), DOI : 10.1109/IGARSS47720.2021.9554218, 2021.
3. Anas Tukur Balarabe, Ivan Jordanov, “LULC Image Classification with Convolutional Neural Network”, IEEE India
Geoscience and Remote Sensing Symposium (IGARSS), DOI : 10.1109/IGARSS47720.2021.9555015, 2021.
4. Ruchi TripathiSantosh M. Pingale, Deepak Khare, “Assessment of LULC changes and urban water demand for
sustainable water management”, IEEE International Conference on Smart Cities Model (ICSCM), DOI :
10.1109/ICSCM46742.2019.9081818., 2019.