DSpace
 

Researchspace >
General science, engineering & technology >
General science, engineering & technology >
General science, engineering & technology >

Please use this identifier to cite or link to this item: http://hdl.handle.net/10204/4804

Title: Optimizing tree-species classification in hyperspectal images
Authors: Barnard, E
Cho, MA
Debba, P
Mathieu, R
Wessels, K
van Heerden, C
van der Walt, C
Asner, GP
Keywords: Tree-species
Hyperspectacle images
Spectral resolution
Biodiversity assessment
Savanna
PRASA 2010
Issue Date: Nov-2010
Publisher: PRASA 2010
Citation: Barnard, E, Cho, MA, Debba, P et al. 2010. Optimizing tree-species classification in hyperspectal images. 21st Annual Symposium of the Pattern Recognition Association of South Africa (PRASA). Stellenbosch, South Africa, 22-23 November 2010, pp 33-37
Series/Report no.: Conference Paper;
Abstract: The authors investigate the classification of eight prominent savanna tree species, based on hyperspectral reflectance data. Although two principal components account for 95% of the variance of the data, up to 20 components are found to be useful for classification. Scaling of these components so that all features have equal variance is found to be useful, and their best performance (88.9% accurate classification) is achieved with 15 scaled features and a support vector machine as classifier. A graphical analysis suggests that several exemplars (“endmembers”) are required for each class, and this observation is confirmed by the large number of support vectors employed by the best classifier.
Description: 21st Annual Symposium of the Pattern Recognition Association of South Africa (PRASA). Stellenbosch, South Africa, 22-23 November 2010
URI: http://hdl.handle.net/10204/4804
ISBN: 978-0-7992-2470-2
Appears in Collections:Earth observation
Ecosystems processes & dynamics
General science, engineering & technology

Files in This Item:

File Description SizeFormat
Barnard1_2010.pdf2.36 MBAdobe PDFView/Open
View Statistics

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

 

Valid XHTML 1.0! DSpace Software Copyright © 2002-2010  Duraspace - Feedback