Object-based classification of IKONOS data for vegetation mapping in Central Japan
Vegetation mapping using IKONOS data was implemented at a countryside study area in central Japan, where small patches of various plant communities are mixed together in a complicated mosaic pattern. Pixel-based and object-based classifications using only spectral features were implemented and their accuracies were compared. In addition, the object-based classification was also performed on a combination of spectral and textural features, with a stepwise regression model used in the discriminate analysis to select the most relevant features. Classifications were implemented at four levels, the highest of which used seven vegetation categories. The object-based classification proved more accurate than the pixel-based classification. In addition, the addition of textural features generated significant improvements in accuracy. The overall classification accuracy and Kappa coefficients at the highest level were 52.8% and 0.373 for the pixel-based classification; 58.9% and 0.458 for the object-based with spectral features only; and 65.0% and 0.542 for the object-based with additional features. Some problems with misclassification remained, but the overall results demonstrate that object-based classification of very high resolution satellite images using additional features is a practical tool for vegetation mapping in Japan.
KeywordsVegetation mapping Object-based classification Texture IKONOS Feature selection
Unable to display preview. Download preview PDF.
- Alexander R, Millington AC (2000) Vegetation Mapping. John Wiley & Sons Ltd, ChichesterGoogle Scholar
- Baatz M, Schape A (2000) Multiresolution Segmentation–an optimization approach for high quality multi-scale image segmentation. In: Strobl J, Blaschke T (ed) Angewandte Geographische Informations Verarbeitung XII, Wichmann-Verlag, pp.12-23Google Scholar
- Biodiversity Center of Japan (2004) The 6th National Survey on the Natural Environment; Survey of Vegetation, Japan. (in Japanese)Google Scholar
- http://www.vegetation.jp/6thgaiyou/sakusei.html (accessed 15 Mar. 2005)Google Scholar
- Braun-Blanquet J (1932) Plant sociology: The study of plant communities. McGraw-Hill, New York and LondonGoogle Scholar
- Haga T, Hashiomto S (1980) Regression analysis and principal component analysis. JUSE Press, Ltd., Tokyo (in Japanese)Google Scholar
- Kamagata N, Hara K, Mori M, Akamatsu Y, Li Q, Hoshino Y (2006) A new method of vegetation mapping by object-based classification using high resolution satellite data. Journal of the Japan Society of Photogrammetry and Remote Sensing 45:43-49 (in Japanese)Google Scholar
- Laliberte AS, Fredrickson EL, Rango A (2007) Combining decision tree with hierarchical object-oriented image analysis for mapping arid rangelands. Photogrammetric Engineering & Remote Sensing 73:197-207Google Scholar
- Levine DM, Ramsey PP, Smidt RK (2001) Applied statistics for engineers and scientists. Prentice Hall, Upper Saddle RiverGoogle Scholar
- Okuno T, Haga T, Kume H, Yoshizawa T (1981) Multivariate analysis revised edition. JUSE Press, Ltd., Tokyo (in Japanese)Google Scholar
- Suzuki H, Ito S, Toyohara G (1985) Method of Vegetation Survey II: Phytosociological Approach. Kyoritsu shuppan, Ltd, Tokyo (in Japanese)Google Scholar
- von Eye A, Schuster C (1998) Regression Analysis for Social Sciences, ACADEMIC PRESS, CaliforniaGoogle Scholar