Unsupervised classification and spectral unmixing for sub-pixel labelling

A. Villa*, J. Chanussot, J. A. Benediktsson, C. Jutten

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

3 Citations (Scopus)

Abstract

The unsupervised classification of hyperspectral images containing mixed pixels is addressed in this paper. Hyperspectral images are characterized by a trade-off between the spectral and the spatial resolution, this leading to data sets containing mixed pixels, e.g. pixels jointly occupied by more than a single land cover class. In [1], a preliminary research based on spectral unmixing concepts was conducted, in order to handle mixed pixels and to obtain thematic maps at a finer spatial resolution. In this work, we extend the investigation by proposing a new methodology based on image clustering. Experiments conducted on real data show the comparative effectiveness of the proposed method, which provides good results in terms of accuracy and is less sensitive to pixels with extreme values of reflectance.

Original languageEnglish
Title of host publication2011 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2011 - Proceedings
Pages71-74
Number of pages4
DOIs
Publication statusPublished - 2011
Event2011 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2011 - Vancouver, BC, Canada
Duration: 24 Jul 201129 Jul 2011

Publication series

NameInternational Geoscience and Remote Sensing Symposium (IGARSS)

Conference

Conference2011 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2011
Country/TerritoryCanada
CityVancouver, BC
Period24/07/1129/07/11

Fingerprint

Dive into the research topics of 'Unsupervised classification and spectral unmixing for sub-pixel labelling'. Together they form a unique fingerprint.

Cite this