The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences. Vol. XXXVII. Part B7. Beijing 2008
Classification method
Overall classification
accuracy (%)
Maximum Likelihood
93.61
Minimum Distance-to-
Mean
83.62
Parallelepiped
63.25
Table 2. The overall classification accuracy for the image
SyyUOOmH: 52
4 Ml V
■*
"I* -
iîL . L.% ‘
■ f
. w r c X
5 •-1 * ~‘~î4
■ * 1 ^ '
56 M
62 64 J«fp00mK
REFERENCES
Bruzzone, L., Cossu, R. and Vemazza, G. (2002). Combining
parametric and non-parametric algorithms for a partially
unsupervised classification of multitemporal remote-sensing
images. Information Fusion 3, 289 -297.
Duda, T. and Canty, M., 2002, Unsupervised classification of
satellite imagery: choosing a good algorithm. International
Journal of Remote Sensing, 23(11), 2193-2212.
Foody, G. M. 2002. Status of land cover classification accuracy
assessment. Remote Sensing and Environment, 80, 185-201.
Selamat, I., Nordin, L., Hamdan, N., Mohti, A. and Ha;id, M.,
2002, Evaluation of TiungSAt data for land cover/use mapping
application. Proceeding of the Seminar Kumpulan Pengguna
TiungSAT-1, Jabatan Remote Sensing dan Sains Geoinformasi,
Fakulti Kejuruteraan Dan Sains Geoinformasi Universiti
Teknologi Malaysia and Astronautic Technology (M) Sdn Bhd.
Thomas, V., Treitz, P., Jelinski, D., Miller, J., Lafleur, P. and
McCaughey, J. H., 2002. Image classification of a northern
peatland complex using spectral and plant community data.
Remote Sensing and Environment, 84, 83-99.
Figure 4. The satellite image map of the City of Alkhabra,
Saudi Arabia [Color Code: Green = vegetation, Orange =
land/sand, Red = urban area]
4. CONCLUSION
Satellite image as value-added data, is an alternative one that
would be cost effective, up-to-date sources. Special
requirements for digital format can also be made as that will be
available at scales of 1: 50,000.00. A satellite image map at
scales of 91,831.00 was produced in this study. This analysis
has demonstrated the potential of a spatial approach in studying
the land cover mapping. The Maximum Likelihood classifier
produced high degree of accuracy. This study performed for
creating the land cover map could be provides the useful for
estimation of the vegetation area over Makkah, Saudi Arabia.
From the result of the accuracy assessment, we were quite
confident of the classified shown.
ACKNOWLEDGEMENTS
This project was carried out using the Dr. Sultan AlSultan
grants from 2003 - up todat and QU&USMb short term grants
and Science Fund. We would like to thank the technical staff
who participated in this project. Thanks are extended to QU
Qassim Unv. Of Saudi Arabia, USM of Malaysia, (RSECO)
Remote Sensing Environmental Consultant Office of Saudi
Arabia, ISPRS, Commission 7.7 Middle East and The Islamic
Educational, Scientific and Cultural Organization (ISESCO)
for support and encouragement.
