Polarimetric Guided Nonlocal Means Covariance Matrix Estimation for Defoliation Mapping
In this study we investigate the potential for using synthetic aperture radar (SAR) data to provide high resolution defoliation and regrowth mapping of trees in the tundra-forest ecotone. Using aerial photographs, four areas with live forest and four areas with dead trees were identified. Quad-polar...
Main Authors: | , , |
---|---|
Format: | Article in Journal/Newspaper |
Language: | unknown |
Published: |
arXiv
2020
|
Subjects: | |
Online Access: | https://dx.doi.org/10.48550/arxiv.2001.08976 https://arxiv.org/abs/2001.08976 |
id |
ftdatacite:10.48550/arxiv.2001.08976 |
---|---|
record_format |
openpolar |
spelling |
ftdatacite:10.48550/arxiv.2001.08976 2023-05-15T18:40:25+02:00 Polarimetric Guided Nonlocal Means Covariance Matrix Estimation for Defoliation Mapping Agersborg, Jørgen A. Anfinsen, Stian Normann Jepsen, Jane Uhd 2020 https://dx.doi.org/10.48550/arxiv.2001.08976 https://arxiv.org/abs/2001.08976 unknown arXiv arXiv.org perpetual, non-exclusive license http://arxiv.org/licenses/nonexclusive-distrib/1.0/ Image and Video Processing eess.IV Machine Learning stat.ML FOS Electrical engineering, electronic engineering, information engineering FOS Computer and information sciences Article CreativeWork article Preprint 2020 ftdatacite https://doi.org/10.48550/arxiv.2001.08976 2022-03-10T16:23:21Z In this study we investigate the potential for using synthetic aperture radar (SAR) data to provide high resolution defoliation and regrowth mapping of trees in the tundra-forest ecotone. Using aerial photographs, four areas with live forest and four areas with dead trees were identified. Quad-polarimetric SAR data from RADARSAT-2 was collected from the same area, and the complex multilook polarimetric covariance matrix was calculated using a novel extension of guided nonlocal means speckle filtering. The nonlocal approach allows us to preserve the high spatial resolution of single-look complex data, which is essential for accurate mapping of the sparsely scattered trees in the study area. Using a standard random forest classification algorithm, our filtering results in over $99.7 \%$ classification accuracy, higher than traditional speckle filtering methods, and on par with the classification accuracy based on optical data. : Update to match final submitted version accepted to IGARSS 2020. 4 pages, 2 columns, 3 figures Article in Journal/Newspaper Tundra DataCite Metadata Store (German National Library of Science and Technology) |
institution |
Open Polar |
collection |
DataCite Metadata Store (German National Library of Science and Technology) |
op_collection_id |
ftdatacite |
language |
unknown |
topic |
Image and Video Processing eess.IV Machine Learning stat.ML FOS Electrical engineering, electronic engineering, information engineering FOS Computer and information sciences |
spellingShingle |
Image and Video Processing eess.IV Machine Learning stat.ML FOS Electrical engineering, electronic engineering, information engineering FOS Computer and information sciences Agersborg, Jørgen A. Anfinsen, Stian Normann Jepsen, Jane Uhd Polarimetric Guided Nonlocal Means Covariance Matrix Estimation for Defoliation Mapping |
topic_facet |
Image and Video Processing eess.IV Machine Learning stat.ML FOS Electrical engineering, electronic engineering, information engineering FOS Computer and information sciences |
description |
In this study we investigate the potential for using synthetic aperture radar (SAR) data to provide high resolution defoliation and regrowth mapping of trees in the tundra-forest ecotone. Using aerial photographs, four areas with live forest and four areas with dead trees were identified. Quad-polarimetric SAR data from RADARSAT-2 was collected from the same area, and the complex multilook polarimetric covariance matrix was calculated using a novel extension of guided nonlocal means speckle filtering. The nonlocal approach allows us to preserve the high spatial resolution of single-look complex data, which is essential for accurate mapping of the sparsely scattered trees in the study area. Using a standard random forest classification algorithm, our filtering results in over $99.7 \%$ classification accuracy, higher than traditional speckle filtering methods, and on par with the classification accuracy based on optical data. : Update to match final submitted version accepted to IGARSS 2020. 4 pages, 2 columns, 3 figures |
format |
Article in Journal/Newspaper |
author |
Agersborg, Jørgen A. Anfinsen, Stian Normann Jepsen, Jane Uhd |
author_facet |
Agersborg, Jørgen A. Anfinsen, Stian Normann Jepsen, Jane Uhd |
author_sort |
Agersborg, Jørgen A. |
title |
Polarimetric Guided Nonlocal Means Covariance Matrix Estimation for Defoliation Mapping |
title_short |
Polarimetric Guided Nonlocal Means Covariance Matrix Estimation for Defoliation Mapping |
title_full |
Polarimetric Guided Nonlocal Means Covariance Matrix Estimation for Defoliation Mapping |
title_fullStr |
Polarimetric Guided Nonlocal Means Covariance Matrix Estimation for Defoliation Mapping |
title_full_unstemmed |
Polarimetric Guided Nonlocal Means Covariance Matrix Estimation for Defoliation Mapping |
title_sort |
polarimetric guided nonlocal means covariance matrix estimation for defoliation mapping |
publisher |
arXiv |
publishDate |
2020 |
url |
https://dx.doi.org/10.48550/arxiv.2001.08976 https://arxiv.org/abs/2001.08976 |
genre |
Tundra |
genre_facet |
Tundra |
op_rights |
arXiv.org perpetual, non-exclusive license http://arxiv.org/licenses/nonexclusive-distrib/1.0/ |
op_doi |
https://doi.org/10.48550/arxiv.2001.08976 |
_version_ |
1766229755254800384 |