Here, the user has to provide the location of a class in the form
of row and column or latitude and longitude. Based on class
location, spectral information as grey value from all the bands
will be read and using minimum, maximum operators to find
out which bands have minimum, maximum gray values to
establish maximum range in spectral difference. Then these
bands are used in indices by setting that band having minimum
grey value as well as maximum grey value band. Here a simple
condition is also applied that if indices values were negative
then replace it with zero value. This enhances the concerned
class of interest and only requires geo-location of a class, while
spectral remote sensing data information is not required.
2.2 Noise Classifier
Dave (1991), introduced concept of "Noise Cluster’ such that
noisy data points may be assigned to the noise class. The
approach is developed for objective functional type (fuzzy K-
means) algorithms and its ability to detect 'good' clusters
amongst noisy data is demonstrated. The classification
performance is evaluated by criteria such as the accuracy and
reliability. These criteria cannot show the exact quality and
certainty of the classification results. This study proposes the
noise classifier, as a special criterion for visualizing and
evaluating the uncertainty of the results. The class membership
matrix 4i, j for a class and Pic+i for noise present is given by;
Hj j - (d^j,d^4,0,m) @)
Hj oq 7 OH dy, m) G)
where lk c, 1x j € c and Ö >, any float value greater than
zero. The objective function, which satisfies this requirement,
may be formulated as;
DEE Ey ge
(Jayde; Noa
and 1<m<, (any constant float value more than 1 ), N= row *
column (image size) and dj; = stands for ji mean class factor;
2 2 T
y j — Mean vector for each class.
In this study, it has been presented how various indices and
band ratios along with a special form of noise classifier; impact
the accuracy of the temporal liquefaction classification. For this
the automatic land cover mapping approach (ALCM) module
from, SMIC: Sub-Pixel Multi-Spectral Image Classifier
package (Kumar et al, 2010) has been used. The ALCM
module has capability to process multiple multi-spectral images
for single land cover class extraction at sub-pixel level using
supervised approach.
62
2.3 Entropy Analysis
The uncertainty affects the extracted information quality in
remote sensing and propagates in processing, transmitting and
classification processes. Usually, the classification performance
is evaluated by criteria such as the accuracy and reliability.
These criteria cannot show the exact quality and certainty of the
classification results. This study uses the entropy, as a special
criterion for visualizing and evaluating the uncertainty of the
results. To have a global measure of uncertainty (fuzziness) for
the whole dataset, the mean index of fuzziness (IF) can be
computed from Eq (5);
jp -XUn (5)
c
where IF values range from 0.0 (no uncertainty) to 1.0
(complete uncertainty. Thus, these measures may allow
depiction of the uncertainties in the datasets, which can either
be a classified image (i.e. soft classification outputs) or the
reference data (Ibrahim et al. 2005, Hamid and Hassan 2006).
2.4 Test Data and Study Area
The remote sensing data used for this work was Landsat-7
satellite multispectral two date's (Jan'8, 2001 and Fab'9, 2001)
temporal data from ETM- sensor. To create multispectral data
6 spectral bands {blue (0.45-0.515 um), green (0.525-0.605
pm), red (0.63-0.69 pm), near infrared (0.75- 0.90 um), mid
infrared] (1.55-1.75 um) and mid infrared 2 (2.09-2.35 um)}
are used.
The test site for this work has been identified as Rann of
Kachchh (Lat 23?22'N-23?38'N and Long 69?52'-70?33'E) in
Gujarat state of India for liquefaction identification. To separate
liquefied area with pre-earthquake existing water bodies with
boundary coordinates Lat 23?13'N-23?16'N and Long 70?05'E-
70°09’E was taken.
3. METHODOLOGY
There has been requirement for identifying only one class that
is, liquefaction, in Kachchh area. Keeping this in mind, the
work was divided into four steps as shown in figure 1.
Er EPA] UT Sri te]
Ew ep
: | || bandratio | |
podmage sy errr band ati | |
| Band selection method —
| 9-Feb-2001 | | — — — | | Conventionat]
| multispectral — » spectral band e
| image | | mf ||
| Accuracy assessment | | Fuzzy based noise
| through entropy "| classification for * —À
| analysis || extracting single class |
Figure 1, Methodology adopted
Firstly both pre and post earthquake Landsat-7 multispectral
images were identified. To create the models of all band ratio
indices, ERDAS Model Maker was used. Initially, an attempt
have been made with conventional spectral band ratio temporal
indices, later on, CBSI spectral band ratio indices from
equatic
noise |
single
Finally
equati
This :
aroun(
after t
using
is that
differ:
distin
class
discri
water
| | Temporal Indices |
Q
T deg
0
=
=
a
Temporal Indices