The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences. Vol. XXXVII. Part B7. Beijing 2008
1356
Figure 1. The study area of the City of Alkhabra, Saudi Arabia
3. DATA ANALYSIS AND RESULTS
To produce satellite image map, good quality satellite data have
been selected. Processing procedure includes geometric
correction, contrast stretching, mosaicking, filtering and area
cutting. Band combination is made available both 321 in true
color. All image-processing analysis was carried out using PCI
Geomatica version 9.1.8 software at the School of Physics,
University of Science Malaysia (USM). Figure 2 shown a
satellite image map at scales of 1:91,831.00.
LEGEND
m Urban Area
H| Road
Vegetation
|4 Sand/Land
Figure 2. The satellite image map of the City of Alkhabra,
Saudi Arabia
The images analysis involved three basic steps in supervised
classification: the training stage, the classification stage and the
output stage. Training sites were needed for supervised
classification. In the training stage, the areas were established
using polygons. They are delineated by spectrally homogeneous
sub areas, which have, class name given. In the classification
stage, three supervised classification methods were selected to
classify the video images. Maximum Likelihood, Minimum
Distance-to-Mean, and Parallelepiped were applied in the
present study.
In the output stage, the classification map is a thematic map of
the land cover over Penang Island, Penang. Many methods of
accuracy assessment have been discussed in remote sensing
literatures. Kappa statistic was used in this study. It is widely
used because all elements in the classification error matrix, and
not just the main diagonal, contribute to its calculation and
because it compensates for change agreement (Selamat, et al.,
2002). Kappa coefficients were generated to describe the
proportion of agreement between the classification result and
the validation sites after random agreements by chance are
removed from consideration these data (Thomas, et. al., 2002).
Three measures of accuracy were tested in this study, namely
overall accuracy, error matrix and Kappa coefficient. In
thematic mapping from remotely sensed data, the term accuracy
is used typically to express the degree of ‘correctness’ of a map
or classification (Foody, 2002). Figure 3 shows the flow chart
for data processing of the images. The produced results in this
study are shown in Table 1 and the accuracy assessment results
were shown in Table 2. In this study, Maximum Likelihood
classifier was found to produce the best accuracy. Finally, the
land cover/use map of the desert area was classified using
Maximum Likelihood classifier and shown in Figure 4.
Figure 3. Flow chart for data processing of the image
Classification method
Kappa coefficient
Maximum Likelihood
0.9258
Minimum Distance-to-
Mean
0.8369
Parallelepiped
0.63285
Table 1. The Kappa coefficient for the image