Classifying segmented hyperspectral data from a heterogeneous urban environment using support vector machines
- 1 January 2007
- journal article
- Published by SPIE-Intl Soc Optical Eng in Journal of Applied Remote Sensing
- Vol. 1 (1), 013543-013543-17
- https://doi.org/10.1117/1.2813466
Abstract
Classifying remotely sensed images from urban environments is challenging. Urban land cover classes are spectrally heterogeneous and materials from different classes have similar spectral properties. Image segmentation has become a common preprocessing step that helped to overcome such problems. However, little attention has been paid to impacts of segmentation on the data's spectral information content. Here, urban hyperspectral data is spectrally classified using support vector machines (SVM). By training a SVM on pixel information and applying it to the image before segmentation and after segmentation at different levels, the classification framework is maintained and the influence of the spectral generalization during image segmentation hence directly investigated. In addition, a straightforward multi-level approach was performed, which combines information from different levels into one final map. A stratified accuracy assessment by urban structure types is applied. The classification of the unsegmented data achieves an overall accuracy of 88.7%. Accuracy of the segment-based classification is lower and decreases with increasing segment size. Highest accuracies for the different urban structure types are achieved at varying segmentation levels. The accuracy of the multi-level approach is similar to that of unsegmented data but comprises the positive effects of more homogeneous segment-based classifications at different levels in one map.Keywords
This publication has 28 references indexed in Scilit:
- A Multilevel Context-Based System for Classification of Very High Spatial Resolution ImagesIEEE Transactions on Geoscience and Remote Sensing, 2006
- Use of impervious surface in urban land-use classificationRemote Sensing of Environment, 2006
- A competitive pixel-object approach for land cover classificationInternational Journal of Remote Sensing, 2005
- Spatial analysis of global urban extent from DMSP-OLS night lightsRemote Sensing of Environment, 2005
- Classification of hyperspectral data from urban areas based on extended morphological profilesIEEE Transactions on Geoscience and Remote Sensing, 2005
- Integration of object-based and pixel-based classification for mapping mangroves with IKONOS imageryInternational Journal of Remote Sensing, 2004
- Spectrometry for urban area remote sensing—Development and analysis of a spectral library from 350 to 2400 nmRemote Sensing of Environment, 2004
- High spatial resolution spectral mixture analysis of urban reflectanceRemote Sensing of Environment, 2003
- A combined fuzzy pixel-based and object-based approach for classification of high-resolution multispectral data over urban areasIEEE Transactions on Geoscience and Remote Sensing, 2003
- Automated differentiation of urban surfaces based on airborne hyperspectral imageryIEEE Transactions on Geoscience and Remote Sensing, 2001