Soil & Water Res., 2006, 1(3):79-84 | DOI: 10.17221/6509-SWR
Object-oriented Fuzzy Analysis of Remote Sensing Data for Bare Soil Brightness MappingOriginal Paper
- Department of Soil Science and Geology, Faculty of Agrobiology, Food and Natural Resources, Czech University of Agriculture in Prague, Prague, Czech Republic
Remote sensing data have an important advantage; the data provide spatially exhaustive sampling of the area of interest instead of having samples of tiny fractions. Vegetation cover is, however, one of the application constraints in soil science. Areas of bare soil can be mapped. These spatially dense data require proper techniques to map identified patterns. The objective of this study was mapping of spatial patterns of bare soil colour brightness in a Landsat 7 satellite image in the study area of Central Bohemia using object-oriented fuzzy analysis. A soil map (1:200 000) was used to associate soil types with the soil brightness in the image. Several approaches to determine membership functions (MF) of the fuzzy rule base were tested. These included a simple manual approach, k-means clustering, a method based on the sample histogram, and one using the probability density function. The method that generally provided the best results for mapping the soil brightness was based on the probability density function with KIA = 0.813. The resulting classification map was finally compared with an existing soil map showing 72.0% agreement of the mapped area. The disagreement of 28.0% was mainly in the areas of Chernozems (69.3%).
Keywords: remote sensing; soil colour; digital soil mapping; fuzzy analysis; fuzzy membership function
Published: September 30, 2006 Show citation
References
- ARGIALAS D., TZOTSOS A. (2004): Automatic extraction of alluvial fans from ASTER satellite data and a digital elevation model using object-oriented image analysis. In: Proc. ISRPS 2004 Annual Conf., July 19-23, Istanbul.
- BAATZ M., SCHÄPE A. (2000): Multiresolution segmentation - an optimization approach for high quality multiscale image segmentation. In: STROBL J., BLASCHKE T., GREISEBENER G. (eds): Angewandte Geographische Informationsverarbeitung XI. Beiträge zum AGITSymposium Salzburg 1999. Herbert Wichmann Verlag, Karlsruhe, 12-23.
- BAATZ M., BENTZ U., DEHGHANI S., HEYNEN M. et al. (2004): eCognition User Guide 4. Definiens Imaging, Muenchen.
- BENZ U., HOFMANN P., WILLHAUCK G., LINGENFELDER I., HEYNEN M. (2004): Multi-resolution, object-oriented fuzzy analysis of remote sensing data for GIS-ready information. ISPRS Journal of Photogrammetry & Remote Sensing, 58: 239-258.
Go to original source... - CHEN Q., LUO J., ZHOU C. (2003): A geostatistic based segmentation approach for remotely sensed images. In: Proc. 24th Asian Conf. Remote Sensing. Busan.
- MCBRATNEY A.B., MENDONCA SANTOS M.L., MINASNY B. (2003): On digital soil mapping. Geoderma, 117: 3-5. Go to original source...
- MINASNY B., MCBRATNEY A.B. (2000): FuzME Version 2.0. Australian Centre for Precision Agriculture. NSW 2006, The University of Sydney, Sydney.
- NEUBERT M., MEINEL G. (2003): Evaluation of segmentation programs for high resolution remote sensing applications. In: Proc. ISPRS Joint Workshop High Resolution Mapping from Space 2003, October 6-8, Hannover.
- STEWART C.M., MCBRATNEY A.B. (2001): Using bare soil imagery to determine management zones for the variable-rate application of inputs for cotton. In: 3rd European Conf. Precision Agriculture, Montpellier, 319-324.
This is an open access article distributed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International (CC BY NC 4.0), which permits non-comercial use, distribution, and reproduction in any medium, provided the original publication is properly cited. No use, distribution or reproduction is permitted which does not comply with these terms.