Texture-based classification of sub-Antarctic vegetation communities on Heard Island
This study was the first to use high-resolution IKONOS imagery to classify vegetation communities on sub-Antarctic Heard Island. We focused on the use of texture measures, in addition to standard multispectral information, to improve the classification of sub-Antarctic vegetation communities. Heard...
Published in: | International Journal of Applied Earth Observation and Geoinformation |
---|---|
Main Authors: | , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
Elsevier
2010
|
Subjects: | |
Online Access: | http://www.sciencedirect.com https://doi.org/10.1016/j.jag.2010.01.006 http://ecite.utas.edu.au/60335 |
id |
ftunivtasecite:oai:ecite.utas.edu.au:60335 |
---|---|
record_format |
openpolar |
spelling |
ftunivtasecite:oai:ecite.utas.edu.au:60335 2023-05-15T13:35:38+02:00 Texture-based classification of sub-Antarctic vegetation communities on Heard Island Murray, H Lucieer, A Williams, RN 2010 application/pdf http://www.sciencedirect.com https://doi.org/10.1016/j.jag.2010.01.006 http://ecite.utas.edu.au/60335 en eng Elsevier http://ecite.utas.edu.au/60335/2/60335.pdf http://dx.doi.org/10.1016/j.jag.2010.01.006 Murray, H and Lucieer, A and Williams, RN, Texture-based classification of sub-Antarctic vegetation communities on Heard Island , International Journal of Applied Earth Observation and Geoinformation, 12, (3) pp. 138-149. ISSN 1569-8432 (2010) [Refereed Article] http://ecite.utas.edu.au/60335 Earth Sciences Physical Geography and Environmental Geoscience Physical Geography and Environmental Geoscience not elsewhere classified Refereed Article PeerReviewed 2010 ftunivtasecite https://doi.org/10.1016/j.jag.2010.01.006 2019-12-13T21:31:10Z This study was the first to use high-resolution IKONOS imagery to classify vegetation communities on sub-Antarctic Heard Island. We focused on the use of texture measures, in addition to standard multispectral information, to improve the classification of sub-Antarctic vegetation communities. Heard Islands pristine and rapidly changing environment makes it a relevant and exciting location to study the regional effects of climate change. This study uses IKONOS imagery to provide automated, up-to-date, and non-invasive means to map vegetation as an important indicator for environmental change. Three classification techniques were compared: multispectral classification, texture based classification, and a combination of both. Texture features were calculated using the Grey Level Co-occurrence Matrix (GLCM). We investigated the effect of the texture window size on classification accuracy. The combined approach produced a higher accuracy than using multispectral bands alone. It was also found that the selection of GLCM texture features is critical. The highest accuracy (85%) was produced using all original spectral bands and three uncorrelated texture features. Incorporating texture improved classification accuracy by 6%. Article in Journal/Newspaper Antarc* Antarctic Heard Island eCite UTAS (University of Tasmania) Antarctic Heard Island International Journal of Applied Earth Observation and Geoinformation 12 3 138 149 |
institution |
Open Polar |
collection |
eCite UTAS (University of Tasmania) |
op_collection_id |
ftunivtasecite |
language |
English |
topic |
Earth Sciences Physical Geography and Environmental Geoscience Physical Geography and Environmental Geoscience not elsewhere classified |
spellingShingle |
Earth Sciences Physical Geography and Environmental Geoscience Physical Geography and Environmental Geoscience not elsewhere classified Murray, H Lucieer, A Williams, RN Texture-based classification of sub-Antarctic vegetation communities on Heard Island |
topic_facet |
Earth Sciences Physical Geography and Environmental Geoscience Physical Geography and Environmental Geoscience not elsewhere classified |
description |
This study was the first to use high-resolution IKONOS imagery to classify vegetation communities on sub-Antarctic Heard Island. We focused on the use of texture measures, in addition to standard multispectral information, to improve the classification of sub-Antarctic vegetation communities. Heard Islands pristine and rapidly changing environment makes it a relevant and exciting location to study the regional effects of climate change. This study uses IKONOS imagery to provide automated, up-to-date, and non-invasive means to map vegetation as an important indicator for environmental change. Three classification techniques were compared: multispectral classification, texture based classification, and a combination of both. Texture features were calculated using the Grey Level Co-occurrence Matrix (GLCM). We investigated the effect of the texture window size on classification accuracy. The combined approach produced a higher accuracy than using multispectral bands alone. It was also found that the selection of GLCM texture features is critical. The highest accuracy (85%) was produced using all original spectral bands and three uncorrelated texture features. Incorporating texture improved classification accuracy by 6%. |
format |
Article in Journal/Newspaper |
author |
Murray, H Lucieer, A Williams, RN |
author_facet |
Murray, H Lucieer, A Williams, RN |
author_sort |
Murray, H |
title |
Texture-based classification of sub-Antarctic vegetation communities on Heard Island |
title_short |
Texture-based classification of sub-Antarctic vegetation communities on Heard Island |
title_full |
Texture-based classification of sub-Antarctic vegetation communities on Heard Island |
title_fullStr |
Texture-based classification of sub-Antarctic vegetation communities on Heard Island |
title_full_unstemmed |
Texture-based classification of sub-Antarctic vegetation communities on Heard Island |
title_sort |
texture-based classification of sub-antarctic vegetation communities on heard island |
publisher |
Elsevier |
publishDate |
2010 |
url |
http://www.sciencedirect.com https://doi.org/10.1016/j.jag.2010.01.006 http://ecite.utas.edu.au/60335 |
geographic |
Antarctic Heard Island |
geographic_facet |
Antarctic Heard Island |
genre |
Antarc* Antarctic Heard Island |
genre_facet |
Antarc* Antarctic Heard Island |
op_relation |
http://ecite.utas.edu.au/60335/2/60335.pdf http://dx.doi.org/10.1016/j.jag.2010.01.006 Murray, H and Lucieer, A and Williams, RN, Texture-based classification of sub-Antarctic vegetation communities on Heard Island , International Journal of Applied Earth Observation and Geoinformation, 12, (3) pp. 138-149. ISSN 1569-8432 (2010) [Refereed Article] http://ecite.utas.edu.au/60335 |
op_doi |
https://doi.org/10.1016/j.jag.2010.01.006 |
container_title |
International Journal of Applied Earth Observation and Geoinformation |
container_volume |
12 |
container_issue |
3 |
container_start_page |
138 |
op_container_end_page |
149 |
_version_ |
1766068176915791872 |