Land cover classification from hyperspectral data: an investigation of spectral, spatial and noise issues


Foody, G.M., Sargent, I.M.J., Atkinson, P.M.A. and Williams, J.L. (2001) Land cover classification from hyperspectral data: an investigation of spectral, spatial and noise issues. In, Geoscience and Remote Sensing Symposium, 2001. IGARSS '01. IEEE 2001 International. IGARSS 2001 Conference Sydney, Australia, IEEE, 2728-2730. (doi: 10.1109/IGARSS.2001.978143).

Download

Full text not available from this repository.

Description/Abstract

The effect of spatial, spectral and noise degradations on the accuracy of two thematic labelling scenarios with hyperspectral data was investigated. Although all of the degradations significantly influenced accuracy, the noise content of the data was consistently noted as a major variable affecting the accuracy of both supervised classification and sub-pixel anomaly detection analyses

Item Type: Book Section
Related URLs:
Subjects: G Geography. Anthropology. Recreation > G Geography (General)
Divisions: University Structure - Pre August 2011 > School of Geography > Remote Sensing and Spatial Analysis
ePrint ID: 15239
Date Deposited: 08 Apr 2005
Last Modified: 27 Mar 2014 18:05
URI: http://eprints.soton.ac.uk/id/eprint/15239

Actions (login required)

View Item View Item