This document summarizes a student's internship project using digital image processing to separate crop and vegetation classes. The student analyzed satellite images of a region in Rajasthan, India from the LISS III and Landsat 8 sensors. The key steps involved pre-processing the images, calculating band reflectance and indices like NDVI, and analyzing the results. NDVI values were found to separate land covers, with higher values indicating denser vegetation. Croplands were extracted from NDVI ranges between 0.4-0.68. Additional indices like NDWI and NDBI were also tested. While results provided an understanding of digital image processing techniques, the student notes that ground truth data could improve accuracy of feature extractions like

1. Page 1
2015
Separation of crop and other
Vegetation based on Digital
image processing
Submitted by 
Mayank Singh Sakla
M.tech geomatics (II YEAR)
CEPT UNIVERSITY
Submitted to 
Mr. Chandrashekhar vaidya
Promoter- Compusense Automation
Ahmedabad

2. Page 2
Table of contents
Certificate of Internship Advisor’s consent..........................................................................3
Abstract ................................................................................................................................4
Introduction.......................................................................................................................... 5
Study Area............................................................................................................................ 6
Data and software used........................................................................................................ 7
Methodology ........................................................................................................................ 8
Understanding of band reflectance calculation.................................................................... 9
Understanding of index calculation......................................................................................10
Analysis part of study .........................................................................................................11
(analysis of study area is represented through maps)
Conclusion........................................................................................................................... 22
Reference ............................................................................................................................. 23

3. Page 3
Certificate of internship Advisor’s consent
This is to certify that the internship titled "Separation of crop and other vegetation based on
Digital image processing" has been submitted by Mayank singh sakla PT200814 towards
partial fulfilment of the requirements for the award of M.TECH GEOMATICS at CEPT
Universityand has been carried out under my supervision.
The student has carried out the modifications recommended by the advisors and to my
satisfaction.
Sign :
Name of Dissertation Advisor : Mr. Chandrashekhar Vaidya
Compusense automation
Date : 7 July 2015

4. Page 4
Abstract
This Study aims to separate land use classes i.e. vegetation and non vegetation areas based on
some specific concept of digital image processing . My area of study is taken from Rajasthan
INDIA(covering from 730
30’ to 740
0’E & 260
0N to 260
30’N). Main focus of work is to
differentiate class of vegetation in to different categories like fallow-land, crop , trees , forest etc
etc. For this over all work we have taken LISS III and Landsat 8 sensor’s image for the same
area for same time (same month and year i.e. September,2014) . Data analysis of work is carried
by spectral enhancement technique. This spectral image enhancement comprises of certain
indices among which our main focus is “NORMALISED DIFFERENCE VEGETATION INDEX”
(NDVI). Here different range of index shows different categorisation of vegetation and other
feature. Hence studying on that ranges and analysis we get some results and conclusion which
are attached along with in this report. Apart from NDVI certain other parameter can also be used
for this type of study but as per our aspect we want to derive this topic under analysis of indexes
only. For cross checking or precision purpose we have also calculated some other indexes also
like NDWI and NDBI (water and built up index respectively ) . after this all calculation of index
and performing algorithm according to need expected results area came but certain need are not
justified properly , means they require more analytical way to produce result like extraction of
Babool tree from whole range of index was a big task to perform. For this type of study and work
to be more precision ground truth is needed or any other instrument like reflectance meter can be
used so that proper algorithm can be run on digital image for acquiring output.
All the result and analysis part is shown in report conclusion and future scope is also illustrated.

5. Page 5
INTRODUCTION
In today’s world, Remote sensing is emerging in the research agenda on global and local
environment. It is treated as local action for global mission, hence many areas of study are served
by this technology, it is a technique in which knowledge and information of any object or body is
collected without coming in contact of that object. This technology serves us by both quality and
quantity of information. It consists of two data analysis typology named as 1. Visual
interpretation and 2. Digital techniques here , visual interpretation tends to be qualitative rather
than quantitative while digital techniques facilitate quantitative analysis. Which includes full
spectral information and avoid individual bias. In our objective of study we are using digital
techniques as a processing technique. This is named as “digital image processing” in this image
processing concept enhancement of satellite image is done by observer and data is gathered for
generation of specific output. Our study requires core of this DIP (Digital Image Processing) .
Digital image processing requires three type of enhancement like spectral radiometric and spatial
enhancement . we are taking “spectral enhancement ” as a datum here to carry out our required
work. It is referred as like spectral enhancement means anything to do with bands of satellite
image to carry out our work according to need.
FLOW OF WORK DONE
After enhancing the images suitable algorithm identification have been archived. So that required
range of category can be visualised and analysis accordingly.

6. Page 6
Study area
The study area is taken from a part of Rajasthan around Pali district. The study area is lies
between  from 730
30’E to 740
0’E & 260
0 N to 260
30’N
FIG. 1 STUDY AREA

7. Page 7
DATA AND SOFTWARE
Data used 
1. LISS III 
 Satellite name - RESOURCESAT-1
 Spatial resolution – 23.5 M
 Spectral resolution – 4 bands
 Radiometric resolution – quantization 7 bits
2. LANDSAT 8
 Spatial resolution – 30 M
 Spectral resolution – 7 bands
 Radiometric resolution – quantization 12 bits
Here , LISS III image was given by company( compusense automation) itself
,while landsat 8 image was downloaded from open source web portal of usgs earth
explorer.
Software used 
 ArcGIS 10.3.1 trial version
 ENVI 4.8
 ERDAS imagine 9.1
(Major part of study is performed on ArcGIS for perfoming algorithm and
analysis while rest software were used for making work precisely done by cross
sampling data.)

8. Page 8
Methodology
For the study, IRS LISS III satellite images of study area were acquired. The IRS LISS III data
for 19th
September 2014 were given from compusense automation. Another image of landsat 8 is
taken /downloaded from http://earthexplorer.usgs.gov/ website. The process of mosaicing, geo-
referencing and rectification using photogrammetric techniques were carried on.
Data Pre-Processing:
The raw satellite image are full of errors and will not be directly utilized for features
identification and any applications. It needs some correction. Pre-processing is done before the
main data analysis and extraction of information. Pre – processing has involved by layer stacking
and mosaicking the images in ArcGIS software. Processing has involved application of various
GIS function and advanced digital image processing technique including contrast manipulation,

9. Page 9
edge enhancement, and image registered. The images were geometrically rectified and registered
to the same projection namely.
Pre-processing aims to correct distorted data in order to create more faithful representation of the
original scene, this typically involves the initial processing of raw image data to correct for
geometric distortions, to calibrate the data radio metrically, and to eliminate noise present in the
data.
Band reflectance calculation
For calculation of any index in digital image processing it is essential to calculate band
reflectance according to index . the reason behind it is like that , when we download and pre-
process satellite data at that instant we only acquired digital number data like ranging on gray
scale level but for calculations of any such indices (like normalised difference vegetation index
or normalised difference water index or built-up index) it is required to convert this digital
number (DN) to reflectance number so that scientifically standard range of index could approach.
For this purpose of reflectance calculation we have used certain “identity” rule on band image
This identity is derived from meta data file attached with data which is based on sun angle and
correction parameter mathematically it is written as under 
1
2 for calculation of reflectance on LISS III image ENVI software have
been used in which sun angle and band has use as input parameter.
Reflectance =
((multiplying factor for band )* band DN number +
( addition number)) / sine of sun angle
(This formula have been used on LANDSAT 8 Image )
(Raster calculator is used for performing this identity)

10. Page
10
Calculation of NDVI (NORMALISED DIFFERENCE
VEGETATION INDEX )
After calculation of different band reflectance value the next step is to calculate index
Identity used for different indexes are as under 
For our interest of study we have worked more on NDVI only. Other two index are calculated
only for cross evaluation purpose for precise work. All this identity have band reflectance as
input parameter .
- This identity is performed on raster image by taking function as a float in raster
calculator.
- Index ranging from minimum (-1 to +1)maximum value.
- Range of index shows the category of land use or cover like waterbody, urban, effective
vegetation,crop field,or dense vegetation etc etc.
- Any feature based on their range can be extract using raster calculator or image
calculator in arcgis by using condition statement.

11. Page
11
Analysis part of work/study
Figure  2 Representation of study area by LISS III image
{date of image acquisition 19 September ,2014}
(source- liss iii)

12. Page
12
Figure 3 Representation of study area by landsat 8 image
{date of acquisition 21 October 2014}
Source-landsat 8

13. Page
13
Figure ->4
Green band
reflectance
From lansat8
Figure ->5
NIR band
reflectance
From lansat8
Representation of band reflectance

14. Page
14
Figure ->6
RED band
reflectance
From lansat8
Figure 7
SWIR2 band
reflectance from
Landsat8

15. Page
15
NDVI LANDSAT 8 IMAGE
Figure 8  Map is representing result of NDVI calculation on landsat8 image. It shows that
range of overall vegetation index is minimum (-0.564795) to maximum (0.736902). where
minimum value of ranges shows settlement and water body . and transition range shows fallow
land and open patches while higher range shows effect of vegetation.

16. Page
16
NDVI LISS III IMAGE
Figure 9  Map is representing result of NDVI calculation on LISS III image given by
compusense automation firm. It shows that range of overall vegetation index is minimum (-
0.173077) to maximum (0.765458). where minimum value of ranges shows settlement and water
body . and transition range shows fallow land and open patches while higher range shows effect
of vegetation.

17. Page
17
Over all vegetation over landsat 8 image
Figure 10  Map is representing overall range of vegetation from ndvi calculation of landsat 8
image. This overall vegetation have been extracted from figure 8 by using of conditional
statement from raster calculator (arcGIS software). It shows that total vegetation of study area
comes under range of 0.3 to 0.689905. Including light to dense patches of vegetation.

18. Page
18
Crop field extracted from landsat 8
Figure 11  Map is representing separation of crop from overall vegetation as shown in figure10
This is showing that range of crop field in NDVI is from 0.4 to 0.689905 .To prepare this map
firstly crop have been identified and than extraction of this crop have been done by conditional
statement from raster or image calculator (using ArcGIS software )

19. Page
19
Figure 12  Map representing range of conifer leaves form study area
Figure 13 representation of zoom area from figure 12 to show conifer leaves
Extraction of conifer leaf is
based on algorithm i.e conifer
leaf lies between range like –
NIR < 0.4
NOTE-This shows the
approximate solution to extract
tree form NDVI for precise
measurement ground truth
information needed. Which can
be achieved by reflectance
meter or flux meter
Solution to extract trees(babool trees) from overall vegetation. Babool tree
have conifer leaves.

20. Page
20
Overall process of separating crop from other vegetation over LISS-
III image
Figure 14 This map represents throughout analysis part over LISSIII image i.e. how separation
of crop from other vegetation have been completed. First part of map shows satellite imagery for
liss 3 data and second part shows the range of normalised difference vegetation index over image
(i.e. from -0.173077 to 0.765458). Third part of map shows a selected patch of image to extract
crop field while the last part of this map shows the extraction of crop value from NDVI which
shows that crop pattern falls under range of 0.4 to 0.77.

21. Page
21
Other spectral enhancement index
Figure 15 Map representing normalised difference builtup index
Figure 16 Map representing normalised difference water index
Both this figure are
analysed for cross
evaluation purpose.
Figure 15 Shows the NDBI
calculation for landsat 8
image which is calculated
by taking reflectance of
SWIR and NIR band of
image where higher range
values show built-up
feature.
Figure 16 Shows the
NDWI calculation for
landsat 8 image which is
calculated by taking
reflectance of GREEN and
NIR band of image where
higher range values shows
feature of water body.

22. Page
22
Conclusion
This study has revealed that the advancements in remote sensing namely digital image
processing have provide powerful tools for calculating index values, extraction of feature and
enhancement of satellite image according to objective. The present study shows that “Separation
of crop and other Vegetation based on Digital image processing” is very effective. This study
have been carried out for understanding use of digital techniques for achieving desired goal. For
this work/study we have taken normalised difference vegetation index as principle concept which
is very effective but this can be more précised if ground truth data also have been collected. For
cross evaluation purpose normalised built-up and water index has also been calculated but result
which comes are not accurate , they are approximate. If we use other instrument like reflectance
meter for survey of ground field than condition algorithms can be made more optimised. If we
use all this concept than every tree can be extract from study area. However present results are
satisfactory. Our main goal of understanding concept of digital image processing have been
achieved. The support from internship advisior - Mr Chandrashekhar vaidya and his team
(compusense automation ) was very excellent and helpful. Main objective of this internship was
to understand practical environment of firm and it has been achieved.

23. Page
23
Reference
 Classification-Tree-Analysis-IDRISI-Focus-Paper
 Estimation of spectral reflectance of snow from IRS-1D LISS-III sensor over the
Himalayan terrain
 Detection of crop water stress and its impact on productivity of crop land ecosystem
Nikita, Andhra University
 Carbon flux monitoring and modelling in Terai Central Forest Division, HALDWANI
Jayson, Andhra University
 http://bhuvan.nrsc.gov.in/data/download/index.php
 http://earthexplorer.usgs.gov/
 Book  Fundamental of Remote Sensing by George Joseph