IRJET- Land Use & Land Cover Change Detection using G.I.S. & Remote Sensing

International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 06 Issue: 04 | Apr 2019 www.irjet.net p-ISSN: 2395-0072
© 2019, IRJET | Impact Factor value: 7.211 | ISO 9001:2008 Certified Journal | Page 3001
LAND USE & LAND COVER CHANGE DETECTION USING G.I.S. &
REMOTE SENSING
Dhaval Dodiya1, Sarju Goswami2, Dhrohit Chauhan3, Mayur Bhuva4, Ruchita Parekh5
1,2,3,4Student, Civil Engineering Department, Sardar Patel College of Engineering, Bakrol, Gujarat, India
5Assistant Professor, Civil Engineering Department, Sardar Patel College of Engineering, Bakrol, Gujarat, India
---------------------------------------------------------------------***----------------------------------------------------------------------
Abstract :- Due to the growing nature and being the activity
of economic hub, Vadodara is changing regarding its land use
scenario. To avoid haphazard development meaningfully
crafted visionary action should be taken relating land use
planning. This project details out on the accurate, fast and
economical procedure for mapping land use and the land
cover of any area. Remote Sensing and GIS may help at large
for mapping and image classification. For the image
classification and for performing related functions, software
tools may be used. Vadodara case is attempted to explore the
extent of spatial growth. Present work is a compilation of two
decadal images from 1998 to 2008 obtained by the Landsat
satellite. The objectives of the study are availing two decadal
satellite pictures of Vadodara city. Research include a
classification of the images and detection of Land use/Land
cover changes in past two decades. This project also explains
step by step process of availing land use images from satellite
saving time and efforts. Thetechnicalspecificationsof imagery
and satellite also form some part sections. After preparing
maps, it is classified to extract the percentage of the desired
class. Present work discusses on the derivationof fourland use
classes i.e. built up, vegetation cover, vacant land, and water
body canal network. Following image classification, the area
of each land use category as obtained from the pixels of the
class discusses the land use distribution.
1. INTRODUCTION
Landscapes on the earth surface till in there natural state
due to some manmade activities. The earth surface on land
use and land cover may be change for during some time
Patten of land use land cover is change.
Using the Remote Sensing and GIS software, they providing
new tools for advanced eco- management. Data collected by
using remote sensing and analyses by earth-system-patens,
functional, regional with global scales over such time.
The earth surface is now to understanding the human
activities on natural land use and land cover over the base
time period. The study observation of the earth surface to
provide objective information of human utilization of the
landscape for refer past data from the earth sensing satellite
has become vital in mapping the earth features and
infrastructure facilitymanagingnatural resourceandstudies
for changes of landscape.
Using the Remote Sensing and GIS software, they providing
new tools for advanced eco- management. Data collected by
using remote sensing and analyses by earth-system-patens,
functional, regional with global scales over such time.
Therefore, we will attempt made in this study to map out
land use land cover of Vadodara between 1998 and 2008
years with one decade for a view to land use and change
detection for land consumption rate for particular time
interval (1998-2008) using GIS and Remote sensing data.
1.1 Study Area
Vadodara, inGujaratstate,hasremarkable expansiongrowth
of Vadodara for such activities like as development of
building, road network, railway network, deforestandmany
other activities since isinception 1997 justlikechange other
same.
Resulted images of Vadodara made with thedata adopted by
the landsate satelite-5 and this data usedformakingsatellite
images in different bands.
Change over time with a view of land consumption or
change that may occur in to status to plannerwecanprovide
basic information to planner to prediction of growthoftown
or city. If Vadodara will avoid the associate problems of a
growing city like many other city in the world.
1.2 Statement of the problem
Vadodara, inGujaratstate,hasremarkable expansiongrowth
of Vadodara for such activities like as development of
building, road network, railway network, deforestandmany
other activities since is inception 1997 just likechangeother
same.
Resulted images of Vadodara made with thedata adopted by
the land sate satelite-5 and this data used for making
satellite images in different bands.

Change over time with a view of landconsumptionorchange
that may occur in to status to planner we can provide basic
information to planner to prediction of growth of town or
city. If Vadodara will avoid the associate problems of a
growing city like many other city in the world.
2. METHODOLOGY
2.1Data Eenhancement, processing and Integration
2.1.1 Image preprocessing
Image preprocessing is challenging work in urban land
cover changedetectionprocess.Toidentifylandcoverchange
with accurately and preciselybetweenconsecutiveyears,the
atmosphere disturbance should be modeledsothatitwillnot
affect surface reflectance of land cover change detection
process. The accomplishment of landcover change detection
analysis by using multi-date remote sensing images depend
on the accurate radiometric and geometric correction.
Multitemporal Landsat imageries geometric correction and
radiometric correction are most important.
2.1.2 Geometric correction
Geometriccorrection is the processofgeoreferencingthe
satelliteimageries to UTM map projectionsystemtothezone
of interest and ratifying by using an evenly distributed
control points taken from digitized topographic map of
corresponding areas and re sampling to nearest
neighborhood. Geometric correction include identifying the
image coordinates similar with their truepositionsinground
coordinate and Re-sampling process is used to determine
digital values to place in the new pixel locations of the
corrected output images. There are three common methods
for re sampling which are nearest neighbor, bilinear
interpolation and cubic convolution.
2.1.3 Radiometric correction
Radiometric normalization of multi-date imageries is
important stage in change detection analysis. High accuracy
geometric registration of the multi-date image data is basic
requirement for change detection. The reflectance values
measured by the sensor are not the pure representation of
the values reflected by earth surface features due to some
external and in-sensor factors.Dealingwithmulti-dateimage
datasets requiresthatimagesobtainedbysensorsatdifferent
times are comparable in termsofradiometriccharacteristics.
So if any two or more datasets are to be used for quantitative
analysis based on radiometric information as in the case of
multi-date analysis for detecting surface changes, they may
be adjusted to compensate for radiometric divergence.
2.1.4 Image enhancement
Image enhancement is the process applied to image data
in order to more effectively display or record the data for
subsequent visual interpretation. Normally, image
enhancement contains many ways and methods applied for
increasing the visual distinguishing among structures in a
scene. The intention is to form or create new imageries from
an original image to increase the visual interpretation of
image and to improve the visual interpretability of an image
by increasing the apparent distinction between the features
Three Broad approaches to enhancement includes
manipulate the contrast of an image spatial feature
manipulation and multiple spectral bands of imagery.
Choosing the appropriate enhancement for any particular
application is the most challenging and an art and often a
matter of personal preference.
2.2Image classification process
Digital image classification in remote sensing contains
grouping of pixels of an image to set of classes, such that
pixels in the similar class are having like properties. The
common type of image classificationisbasedonthedetection
of the spectral response patterns of land cover classes.
Remote sensing studies aiming on image classification has
long attracted the devotionoftheremote-sensingcommunity
asclassification results are the basis formanyenvironmental

and socioeconomic applications. Scientists and practitioners
have madegreat effortsindevelopingadvancedclassification
approaches and techniques for improving classification
accuracy. However, classifying remotely sensed data into a
thematic map remains a challenge because many factors,
such as the complexity of the landscape in a study area,
selected remotely sensed data, and image-processing and
classification approaches, may affect the success of a
classification. Many factors such as spatial resolution of the
remotely sensed data, different sources of data a
classificationsystemandavailabilityofclassificationsoftware
must be taken into account when selecting a classification
method for use. Different classification methods have their
own merits. The question of which classification approach is
suitable for a specific study is not easy to answer. Different
classification results may be obtained depending on the
classifier chosen.
2.2.1 Supervised classification
Supervised classification can be very effective and
accurate in classifying satellite images and can be applied at
the individual pixel level or toimage objectsHowever,forthe
process to work effectively, the person processing the image
needs to have a priori knowledge of where the classes of
interest are located, or be able to identify them directly from
the imagery.
2.2.2 Unsupervised classification
One common application of remotely-sensed images to
rangeland management is the creation of maps of land cover,
vegetation type, or other discrete classes by remote sensing
software. In unsupervised classification, image processing
software classifies an image based on natural groupings of
the spectral properties of the pixels, without the user
specifying how to classify any portion of the image.
Conceptually, unsupervised classificationissimilartocluster
analysis where observations are assigned to the same class
because they have similar values.
2.3 Classification accuracy assessment
Accuracy assessment is very important for understanding
the developed results and employing these results for
decision-making. Classification accuracy assessment is very
important in land use mapping and to understand map
quality and reliability. Ultimately there is no satisfactory
method to assess the absolute accuracy of image
classification for remote sensing Earth observation
applications. Even an assessment or an estimate of the
relative accuracy of classification does, however, provide
valuable knowledge for us to accept or reject a classification
result at a certain confidence level.
3. RESULT
3.1 Classification Classes (Supervised Classification) :-
Sr. No Class Description
1 Agriculture Land
Garden, Play Ground,
Trees
2 Forest Land
Natural Vegetation,
Trees
3 Built Up Land
Residential Area,
Commercial Area,
Industrial Area,
4 Water Body
Lakes, Rivers, Ponds,
Canals
5 Road Network
RCC road, Bituminous
Road, WBM Road,
6 Barren Land Rock, Sand, Soil
Final Classification image 1998

Final Classification Image 2008
3.2 Area classification table :-
Class Area (Hector.)
Year 1998 Year 2008
Agricultural 8427.6 6217.74
Area
Forest Area 9801.72 6350.13
Road Network 3167.1 4559.31
Water body 1949.58 646.86
Built up area 21397.41 27798.66
Barren Land 20556.63 22511.79
Total 66692.25 66692.25
3.3 Area classification in percentage:-
Class % Percentage % Change
Year
1998
Year
2008
Agricultural 13.054 9.323 3.731(-)
Area
Forest Area 15.114 7.434 7.68(-)
Road Network 4.749 6.836 2.087(+)
Water body 2.923 0.970 1.953(-)
Built up area 32.084 41.682 9.598(+)
Barren Land 32.076 33.755 1.679(+)
Total 100 100
-
3.4 Change Detection Graph in % Percentage :-
4. CONCLUSION
This Study work demonstrates the ability of GIS and Remote
Sensing in capturing spatial-temporal data. Attempt was
made to capture as accurate as possible four land use land
cover classes as they change through time. The four classes
were distinctly produced for each study year but with more
emphasis on built-up land as it is a combination of
anthropogenic activities that make up this class; andindeed,
it is one that affects the other classes. However, the result of
the work shows a rapid growth in built-up land between
1998 and 2008 is 9.598% while the periods between 1998
and 2008 the agricultural land is reduced in 3.731% of the
study area. It was also observed that change by 1998 and
2008 the area of water body is slightly decreased by
introduce to Vishwamitri River. Also theroadnetwork ofthe
study area is increased by developing the city as well as the
village facilities. Its change between 1998 and 2008 is
2.087% of the total area.
REFERENCES
1. Monalisha Mishra, Kamal Kant Mishra, A.P. Subudhi.
Urban sprawl mapping and Land Use change analysis
using Remote Sensing and GIS: case study of
Bhubaneswar city, Orissa.
2. [M. Modara, M. Ait Belaid,S. Al-Jenaid(2013).Mapping
and assessing Land Use/ Land Cover change in
Muharraq island based on GIS and Remote Sensing
integration: case study of Muharraq Governorate.

3. ]. J.S. Rawat, Manish Kumar. Monitoring land
use/cover change using remote sensing and GIS
techniques: A case study of Hawalbagh block, district
Almora, Uttarakhand, IndiaCentre of Excellence for
NRDMS in Uttarakhand,
4. http://www.gadm.org/download
5. https://earthexplorer.usgs.gov

IRJET- Land Use & Land Cover Change Detection using G.I.S. & Remote Sensing

More Related Content

IRJET- Land Use & Land Cover Change Detection using G.I.S. & Remote Sensing