Accurate determination of surface reference data in digital photographs in ice-free surfaces of Maritime Antarctica
The ice-free areas of Maritime Antarctica show complex mosaics of surface covers, with wide patches of diverse bare soils and rock, together with various vegetation communities dominated by lichens and mosses. The microscale variability is difficult to characterize and quantify, but is essential for...
Published in: | Science of The Total Environment |
---|---|
Main Authors: | , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
Elsevier
2017
|
Subjects: | |
Online Access: | http://hdl.handle.net/10451/28185 https://doi.org/10.1016/j.scitotenv.2016.08.104 |
id |
ftunivlisboa:oai:repositorio.ul.pt:10451/28185 |
---|---|
record_format |
openpolar |
spelling |
ftunivlisboa:oai:repositorio.ul.pt:10451/28185 2023-05-15T13:37:42+02:00 Accurate determination of surface reference data in digital photographs in ice-free surfaces of Maritime Antarctica Pina, Pedro Vieira, Goncalo Bandeira, Lourenço Mora, Carla 2017-06-26T14:56:49Z http://hdl.handle.net/10451/28185 https://doi.org/10.1016/j.scitotenv.2016.08.104 eng eng Elsevier Science of the Total Environment 573 (2016) 290–302 0048-9697 http://hdl.handle.net/10451/28185 doi:10.1016/j.scitotenv.2016.08.104 closedAccess Image analysis Segmentation Object-based classification Ice-free surfaces Polar regions article 2017 ftunivlisboa https://doi.org/10.1016/j.scitotenv.2016.08.104 2022-05-25T18:36:51Z The ice-free areas of Maritime Antarctica show complex mosaics of surface covers, with wide patches of diverse bare soils and rock, together with various vegetation communities dominated by lichens and mosses. The microscale variability is difficult to characterize and quantify, but is essential for ground-truthing and for defining classifiers for large areas using, for example high resolution satellite imagery, or even ultra-high resolution unmanned aerial vehicle (UAV) imagery. The main objective of this paper is to verify the ability and robustness of an automated approach to discriminate the variety of surface types in digital photographs acquired at ground level in ice-free regions of Maritime Antarctica. The proposed method is based on an object-based classification procedure built in two main steps: first, on the automated delineation of homogeneous regions (the objects) of the images through the watershed transform with adequate filtering to avoid an over-segmentation, and second, on labelling each identified object with a supervised decision classifier trained with samples of representative objects of ice-free surface types (bare rock, bare soil, moss and lichen formations). The method is evaluated with images acquired in summer campaigns in Fildes and Barton peninsulas (King George Island, South Shetlands). The best performances for the datasets of the two peninsulas are achieved with a SVM classifier with overall accuracies of about 92% and kappa values around 0.89. The excellent performances allow validating the adequacy of the approach for obtaining accurate surface reference data at the complete pixel scale (sub-metric) of current very high resolution (VHR) satellite images, instead of a common single point sampling. info:eu-repo/semantics/publishedVersion Article in Journal/Newspaper Antarc* Antarctica King George Island Universidade de Lisboa: repositório.UL Bare Rock ENVELOPE(-45.589,-45.589,-60.704,-60.704) Barton ENVELOPE(-58.733,-58.733,-62.233,-62.233) Fildes ENVELOPE(-58.817,-58.817,-62.217,-62.217) King George Island Science of The Total Environment 573 290 302 |
institution |
Open Polar |
collection |
Universidade de Lisboa: repositório.UL |
op_collection_id |
ftunivlisboa |
language |
English |
topic |
Image analysis Segmentation Object-based classification Ice-free surfaces Polar regions |
spellingShingle |
Image analysis Segmentation Object-based classification Ice-free surfaces Polar regions Pina, Pedro Vieira, Goncalo Bandeira, Lourenço Mora, Carla Accurate determination of surface reference data in digital photographs in ice-free surfaces of Maritime Antarctica |
topic_facet |
Image analysis Segmentation Object-based classification Ice-free surfaces Polar regions |
description |
The ice-free areas of Maritime Antarctica show complex mosaics of surface covers, with wide patches of diverse bare soils and rock, together with various vegetation communities dominated by lichens and mosses. The microscale variability is difficult to characterize and quantify, but is essential for ground-truthing and for defining classifiers for large areas using, for example high resolution satellite imagery, or even ultra-high resolution unmanned aerial vehicle (UAV) imagery. The main objective of this paper is to verify the ability and robustness of an automated approach to discriminate the variety of surface types in digital photographs acquired at ground level in ice-free regions of Maritime Antarctica. The proposed method is based on an object-based classification procedure built in two main steps: first, on the automated delineation of homogeneous regions (the objects) of the images through the watershed transform with adequate filtering to avoid an over-segmentation, and second, on labelling each identified object with a supervised decision classifier trained with samples of representative objects of ice-free surface types (bare rock, bare soil, moss and lichen formations). The method is evaluated with images acquired in summer campaigns in Fildes and Barton peninsulas (King George Island, South Shetlands). The best performances for the datasets of the two peninsulas are achieved with a SVM classifier with overall accuracies of about 92% and kappa values around 0.89. The excellent performances allow validating the adequacy of the approach for obtaining accurate surface reference data at the complete pixel scale (sub-metric) of current very high resolution (VHR) satellite images, instead of a common single point sampling. info:eu-repo/semantics/publishedVersion |
format |
Article in Journal/Newspaper |
author |
Pina, Pedro Vieira, Goncalo Bandeira, Lourenço Mora, Carla |
author_facet |
Pina, Pedro Vieira, Goncalo Bandeira, Lourenço Mora, Carla |
author_sort |
Pina, Pedro |
title |
Accurate determination of surface reference data in digital photographs in ice-free surfaces of Maritime Antarctica |
title_short |
Accurate determination of surface reference data in digital photographs in ice-free surfaces of Maritime Antarctica |
title_full |
Accurate determination of surface reference data in digital photographs in ice-free surfaces of Maritime Antarctica |
title_fullStr |
Accurate determination of surface reference data in digital photographs in ice-free surfaces of Maritime Antarctica |
title_full_unstemmed |
Accurate determination of surface reference data in digital photographs in ice-free surfaces of Maritime Antarctica |
title_sort |
accurate determination of surface reference data in digital photographs in ice-free surfaces of maritime antarctica |
publisher |
Elsevier |
publishDate |
2017 |
url |
http://hdl.handle.net/10451/28185 https://doi.org/10.1016/j.scitotenv.2016.08.104 |
long_lat |
ENVELOPE(-45.589,-45.589,-60.704,-60.704) ENVELOPE(-58.733,-58.733,-62.233,-62.233) ENVELOPE(-58.817,-58.817,-62.217,-62.217) |
geographic |
Bare Rock Barton Fildes King George Island |
geographic_facet |
Bare Rock Barton Fildes King George Island |
genre |
Antarc* Antarctica King George Island |
genre_facet |
Antarc* Antarctica King George Island |
op_relation |
Science of the Total Environment 573 (2016) 290–302 0048-9697 http://hdl.handle.net/10451/28185 doi:10.1016/j.scitotenv.2016.08.104 |
op_rights |
closedAccess |
op_doi |
https://doi.org/10.1016/j.scitotenv.2016.08.104 |
container_title |
Science of The Total Environment |
container_volume |
573 |
container_start_page |
290 |
op_container_end_page |
302 |
_version_ |
1766096911979249664 |