Land-use classification using multitemporal ERS-1, Radarsat and JERS SAR-images

Author

Törmä, Markus ; Koskinen, Jarkko

Author_Institution

Inst. of Photogrammetry & Remote Sensing, Helsinki Univ. of Technol., Espoo, Finland

Volume

4

fYear

1998

fDate

6-10 Jul 1998

Firstpage

2125

Abstract

Land-use classification was performed by using a set of ERS-1, JERS- and Radarsat images. Classes were water, forests (with subclasses according to stem volume), agricultural field, mire and urban area. Median filtering was used for speckle reduction and principal component analysis for feature extraction. Spectral classification was performed by using self-organizing feature map and learning vector quantization. Contextual classification was performed as a post-processing step. The overall accuracy of the spectral classification was 86.4% and the best contextual classification 89.8%

Keywords

agriculture; feature extraction; forestry; geophysical signal processing; geophysical techniques; geophysics computing; image classification; image sequences; image texture; radar imaging; remote sensing by radar; self-organising feature maps; spaceborne radar; ERS-1; JERS SAR-images; Radarsat; SAR; agricultural field; agriculture; city; context; contextual classification; feature extraction; forest; geophysical measurement technique; image classification; image processing; image sequence; land surface; land use; learning vector quantization; median filtering; mire; multitemporal; post-processing; principal component analysis; radar imaging; radar remote sensing; self-organizing feature map; spaceborne radar; speckle reduction; spectral classification; synthetic aperture radar; terrain mapping; town; urban area; vegetation mapping; Adaptive optics; Feature extraction; Filtering; Filters; Pixel; Principal component analysis; Space technology; Speckle; Testing; Urban areas;

fLanguage

English

Publisher

ieee

Conference_Titel

Geoscience and Remote Sensing Symposium Proceedings, 1998. IGARSS '98. 1998 IEEE International

Conference_Location

Seattle, WA

Print_ISBN

0-7803-4403-0

Type

conf

DOI

10.1109/IGARSS.1998.703762

Filename

703762