RVM-based multi-class classification of remotely sensed data

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...

Full description

Bibliographic Details
Main Author: Foody, Giles M.
Format: Article
Published: Taylor & Francis 2008
Online Access:https://eprints.nottingham.ac.uk/1997/
_version_ 1848790701173637120
author Foody, Giles M.
author_facet Foody, Giles M.
author_sort Foody, Giles M.
building Nottingham Research Data Repository
collection Online Access
description 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.
first_indexed 2025-11-14T18:16:48Z
format Article
id nottingham-1997
institution University of Nottingham Malaysia Campus
institution_category Local University
last_indexed 2025-11-14T18:16:48Z
publishDate 2008
publisher Taylor & Francis
recordtype eprints
repository_type Digital Repository
spelling nottingham-19972020-05-04T20:27:43Z https://eprints.nottingham.ac.uk/1997/ RVM-based multi-class classification of remotely sensed data Foody, Giles M. 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. Taylor & Francis 2008 Article PeerReviewed 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 http://www.tandfonline.com/doi/full/10.1080/01431160701822115 doi:10.1080/01431160701822115 doi:10.1080/01431160701822115
spellingShingle Foody, Giles M.
RVM-based multi-class classification of remotely sensed data
title RVM-based multi-class classification of remotely sensed data
title_full RVM-based multi-class classification of remotely sensed data
title_fullStr RVM-based multi-class classification of remotely sensed data
title_full_unstemmed RVM-based multi-class classification of remotely sensed data
title_short RVM-based multi-class classification of remotely sensed data
title_sort rvm-based multi-class classification of remotely sensed data
url https://eprints.nottingham.ac.uk/1997/
https://eprints.nottingham.ac.uk/1997/
https://eprints.nottingham.ac.uk/1997/