Unsupervised urban land-cover classification using WorldView-2 data and self-organizing maps

Author

Zhang, Jie ; Kerekes, John

Author_Institution

Chester F. Carlson Center for Imaging Sci., Rochester Inst. of Technol., Rochester, NY, USA

fYear

2011

fDate

24-29 July 2011

Firstpage

150

Lastpage

153

Abstract

Fully automated land-cover classification from commercial remote sensing satellite imagery has had limited success in part due to their limited spectral bands. New promise of unsupervised analysis has emerged with the recent launch of the eight-band high resolution satellite WorldView-2. In this paper, a fully unsupervised classification algorithm is proposed based on self-organizing maps and watershed segmentation. The results demonstrate that the proposed algorithm performs better in classifying homogeneous regions while achieving better accuracy than k-means.

Keywords

geophysical image processing; hydrological techniques; image classification; image segmentation; self-organising feature maps; terrain mapping; unsupervised learning; water resources; WorldView-2 data; commercial remote sensing satellite imagery; eight band high resolution satellite; fully automated land cover classification; homogeneous region; self-organizing map; spectral band; unsupervised analysis; unsupervised classification algorithm; unsupervised urban land cover classification; watershed segmentation; Accuracy; Classification algorithms; Clustering algorithms; Feature extraction; Image segmentation; Merging; Remote sensing; WorldView-2; segmentation; self-organizing map; unsupervised classification;

fLanguage

English

Publisher

ieee

Conference_Titel

Geoscience and Remote Sensing Symposium (IGARSS), 2011 IEEE International

Conference_Location

Vancouver, BC

ISSN

2153-6996

Print_ISBN

978-1-4577-1003-2

Type

conf

DOI

10.1109/IGARSS.2011.6048920

Filename

6048920