The effect of input data transformations on object-based image analysis
Open Access
- 1 January 2012
- journal article
- research article
- Published by Taylor & Francis in Remote Sensing Letters
- Vol. 3 (1) , 21-29
Abstract
The effect of using spectral transform images as input data on segmentation quality and its potential effect on products generated by object-based image analysis are explored in the context of land cover classification in Accra, Ghana. Five image data transformations are compared to untransformed spectral bands in terms of their effect on segmentation quality and final product accuracy. The relationship between segmentation quality and product accuracy is also briefly explored. Results suggest that input data transformations can aid in the delineation of landscape objects by image segmentation, but the effect is idiosyncratic to the transformation and object of interest.Keywords
This publication has 21 references indexed in Scilit:
- Assessing object-based classification: advantages and limitationsRemote Sensing Letters, 2010
- MODIS‐derived visible atmospherically resistant index for monitoring chaparral moisture contentInternational Journal of Remote Sensing, 2005
- Estimating impervious surface distribution by spectral mixture analysisRemote Sensing of Environment, 2003
- Existential uncertainty of spatial objects segmented from satellite sensor imageryIEEE Transactions on Geoscience and Remote Sensing, 2002
- Vegetation and soil lines in visible spectral space: A concept and technique for remote estimation of vegetation fractionInternational Journal of Remote Sensing, 2002
- Estimation of urban vegetation abundance by spectral mixture analysisInternational Journal of Remote Sensing, 2001
- A comparative evaluation of NOAA/AVHRR vegetation indexes for burned surface detection and mappingIEEE Transactions on Geoscience and Remote Sensing, 1999
- Nested-hierarchical scene models and image segmentationInternational Journal of Remote Sensing, 1992
- On the nature of models in remote sensingRemote Sensing of Environment, 1986
- Ecological Fallacies and the Analysis of Areal Census DataEnvironment and Planning A: Economy and Space, 1984