RVM-based multi-class classification of remotely sensed data

Foody, Giles M. (2008) RVM-based multi-class classification of remotely sensed data. International Journal of Remote Sensing, 29 (6). pp. 1817-1823. ISSN 0143-1161

[img] PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
Download (340kB)

Abstract

The relevance vector machine (RVM), a Bayesian extension of the support vector machine (SVM), has considerable potential for the analysis of remotely sensed data. Here, the RVM is introduced and used to derive a multi-class classification of land cover with an accuracy of 91.25%, a level comparable to that achieved by a suite of popular image classifiers including the SVM. Critically, however, the output of the RVM includes an estimate of the posterior probability of class membership. This output may be used to illustrate the uncertainty of the class allocations on a per-case basis and help to identify possible routes to further enhance classification accuracy.

Item Type: Article
Additional Information: This is an Author's Accepted Manuscript of an article published in International Journal of Remote Sensing: Foody, G.M., RVM-based multi-class classification of remotely sensed data, International Journal of Remote Sensing, 29(6), 2008, copyright Taylor & Francis, available online at: http://www.tandfonline.com/10.1080/01431160701822115
Schools/Departments: University of Nottingham UK Campus > Faculty of Social Sciences > School of Geography
Depositing User: Foody, Prof Giles
Date Deposited: 14 Jun 2013 15:41
Last Modified: 15 Sep 2016 12:50
URI: http://eprints.nottingham.ac.uk/id/eprint/1997

Actions (Archive Staff Only)

Edit View Edit View