X-B8, 2012
values and the
alues. TNDVI
nount of green
' al. 1996). To
tions in lower
1 soil-adjusted
ction factor L
)0), developed
s the radiative
of the relative
eflectance in
in the green
yll a and b is
ndices studied
References
Birth and
McVey,
1968;
Colombo et
al.,2003
Rouse et
al.,1973;
Deering et
al.,1975;
Huete et al.,
2002
Huete and
Liu, 1994;
Running et
al., 1994
) Broge and
Leblanc,
2000
Tucker,
1979
work
ıch that noisy
he approach is
s or fuzzy K-
good' clusters
ethods need to
Uncertainty is
acquisition in
n processing,
is uncertainty
Usually, the
ia such as the
how the exact
ts. Unlike the
out forth for
classification
tispectral data
criteria are
classification
/e been shown
International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Volume XXXIX-B8, 2012
XXII ISPRS Congress, 25 August — 01 September 2012, Melbourne, Australia
Hj. ; 7 (dj, di, O, m) ()
where 1=k=c
I=j=c
and
uer] dim) Q)
0 >0, any float value greater than zero.
The objective function, which satisfies this requirement, may
be formulated as;
u = S u.d N Ó (3)
Uu. d) 02 u
(i rd ij ij EK kc p
And
V »0, any float value greater than zero
Ö >, any float value greater than zero
Where 8 >m>1, (any constant float value more than 1)
N= row * column (image size
i= stands for pixel position at i? location distance between X;
and Vj
2 2 T
V; 7 Mean Vector for each class
4. TEST DATA AND STUDY AREA
The study area taken for this research work was Aurangabad
(19° 53' N, 75? 23' E) region, in Maharashtra state in India
shown in figure 1. In this study remotely sensed images of
Indian Remote Sensing Satellite (IRS-P6) were selected for
cotton crop identification. In Aurangabad district the area under
cotton is comparatively higher than the other crops. Due to the
higher area under cotton cultivation and production of raw
cotton, the stakeholders involves in the cotton supply chain are
interdependent. For this purpose temporal images of Advanced
Wide Field Sensor (AWIFS) and Linear Imaging Self Scanner
sensor (LISS-III) with spatial resolution of 56m and 23.5m
respectively where used. LISS-III time-series multi-spectral
satellite data was used for testing purpose. Different datasets of
the time series multi-spectral images were taken for further
classification. These datasets were taken for making the
inference of suitable time-series images. Total five scenes of
the study areas were available. The datasets for AWIFS and
LISS-III are shown in table 2.
AWIFS LISS-III
Set 1 Set 2 Set 3 Set 1 Set 2 Set 3
May Nov Dec May Nov Dec
2010 2010 2010 2010 2010 2010
Nov Dec Jan Nov Dec Jan
2010 2010 2011 2010 2010 2011
Dec Jan Feb Dec Jan Mar
2010 2011 2011 2010 2011 2011
Jan Feb Jan Mar
2011 2011 2011 2011
Feb Mar
2011 2011
Table 2: AWIFS and LISS-III Datasets
IRS-P6 LISS-III data are well suited for agricultural and
forestry monitoring. LISS-III (IRS-P6) time-series multi-
spectral satellite data was used as testing data for accuracy
assessment. The coarse resolution images should be co-
registered against the fine resolution images. The characteristic
of the AWIFS and LISS-III sensor have been mentioned in
Table 3. The spatial pixel ratio between classification image
AWIFS and testing image LISS-III is 1:3, means that the one
pixel of AWIFS image is equal to nine pixels of LISS-III
image. Total five temporal scenes of LISS-III data were used
for generating testing data sets. The datasets are shown in table
2. In India cotton season start from last week of May and it runs
up to end of February. Depending on temperature and variety,
50 to 85 days are required from planting to first bud formation,
25 to 30 days for flower formation and 50 to 60 days from
flower opening to mature ball. No clear distinction can be made
in crop growth periods since vegetative growth is continued
during flowering and ball formation and flowering is continued
during ball formation.
Sensors
jer AWIFS LISS-III
Specifications
IGFOV 56 m (nadir) 23.5m
70m (at field
edge)
Spectral Bands B2: 0.52-0.59 B2: 0.52-0.59
B3: 0.62-0.68 B3: 0.62-0.68
B4: 0.77-0.86 B4: 0.76-0.86
B5: 1.55-1.70 B5: 1.55-1.70 (SWIR)
(SWIR)
Swath 370 km each head | 141 km
740 km
(combined)
Data 10 bit 7 bit (VNIR), 10 bit
Quantization (SWIR)
Table 3: Sensor specification of Resource Sat-1 (P6) satellite
May 2010 Nov.2010 | Dec.2010 Jan 2010 Mar 2010
Figure 1: Study area depicted through temporal LISS-III images
5. TIME SERIES DATASETS
The AWIFS and LISS-III images were stacked in three (03)
datasets. Considering the life-cycle of cotton crop, the Sets were
established with the aim to get the most suitable time-series
images, combining different multi-date in each set.