ul 2004 International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Vol XXXV, Part B7. Istanbul 2004
——
Figure 3. Comparison of image classification results
(a) Pixel-based classification (with maximum likelihood classifier)
(b) Object-based classification
(c) Vegetation map based on field study
Photogrammetry and Remote Sensingin 2003 pp. 125-128.
7. CONCLUSIONS (in Japanese)
This paper described the vegetation mapping using IKONOS
data and the hybrid analysis method combining object-based
; e Acknowledgements
and pixel-based image classifiers. The purpose of the
development of the vegetation mapping methodology is to The authors wish to thank the Kouch river and road
provide an objective and cost-effective survey method utilizing management office of the Ministry of Land, Infrastructure, and
satellite remote sensing for the nationwide river environment Transport of Japan for allowing us to use their vegetation maps,
information acquisition project. The result of the tentative base maps for river management for the accuracy assessment of
analysis using the hybrid approach and IKONOS data in this the image classification in this study.
study suggests that IKONOS data would be a useful additional
information source for the vegetation mapping for the river
ATI environment management.
per-like
dy area References
remote
seen as Baatz, M. and Schüpe, A., 2000. Multiresolution segmentation
sensing - an optimization approach for high quality multi-scale image
y high- segmentation. In Angewandte Geographische
fication
Informationsverarbeitung * + edited by Strobl, J., Blaschke,
riented 1 MU
rien T.. and Griesebner, G., (Heidelberg: Wichmann-Verlag), pp.
results
12-23.
on and
ated by P
Ministry of Land, Infrastructure, and Transport of Japan, River
Bureau, River Environment Section, 1997. Manual of River
| using Census (Biological Study). (in Japanese).
er, and
Usuda, Y., et al. 2003. A study on the optimization of image
segmentation in object-Oriented Classification. Proceedings
of the annual conference of the Japan Society for
289
