|
Full Length Research Paper
|
|
Integrated method to
extract information from high and very high resolution RS
images for urban planning
D. Amarsaikhan1*, M. Ganzorig1, H.
H. Blotevogel2, B. Nergui1 and R.
Gantuya1
1Institute of Informatics and RS, Mongolian Academy of Sciences, av.
Enkhtaivan-54B, Ulaanbaatar-51, Mongolia.
2Dortmund
University of Technology, Faculty of Spatial Planning
Institute of Spatial Planning, August-Schmidt-Str. 10,
D-44221 Dortmund, Germany.
*Corresponding author. E-mail:
amar64@arvis.ac.mn.
Tel: 976-11-453660.
Fax: 976-11-458090
Accepted 3 September, 2009 |
|
|
|
Abstract |
|
|
The aim of this
research is to propose an integrated methodology for the
extraction of information from high and very high resolution
satellite images and also to demonstrate how the extracted
information can be used for urban area studies. For the information
extraction,
three different approaches such as interpretation,
automatic and artificial
intelligence
methods are
used. As the interpretation
method a visual
interpretation is used, whereas as the automatic
method a
refined maximum likelihood classification that uses spatial
thresholds defined from the local knowledge is applied. For the
artificial
intelligence
method, a
rule-based algorithm
which consists of a set of rules,
containing an initial image segmentation procedure as
well as the
constraints on spectral parameters and
spatial
thresholds
is constructed. Overall,
the research
indicates that the high and very high resolution
satellite
images
can be successfully used for general and detailed urban studies
and
the proposed methods can be efficiently used for
the
extraction of accurate thematic information.
Key words:
Interpretation, automatic, artificial
intelligence, urban study, satellite image. |
