Land Cover Classification in SubArctic Regions Using Fully Polarimetric RADARSAT-2 Data
The expansion of shrub vegetation in Arctic and sub-Arctic environments observed in the past decades can have significant effects on northern ecosystems. There is a need for efficient tools to monitor those changes, not only in terms of the spatial coverage of shrubs, but also their vertical growth....
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2016-08-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | http://www.mdpi.com/2072-4292/8/9/697 |
| _version_ | 1828882104403886080 |
|---|---|
| author | Yannick Duguay Monique Bernier Esther Lévesque Florent Domine |
| author_facet | Yannick Duguay Monique Bernier Esther Lévesque Florent Domine |
| author_sort | Yannick Duguay |
| collection | DOAJ |
| description | The expansion of shrub vegetation in Arctic and sub-Arctic environments observed in the past decades can have significant effects on northern ecosystems. There is a need for efficient tools to monitor those changes, not only in terms of the spatial coverage of shrubs, but also their vertical growth. The objective of the current paper is to evaluate the performance of polarimetric C-band SAR datasets for land cover classification in sub-Arctic environments. A series of RADARSAT-2 quad-pol images were acquired between October 2011 and April 2012. The Support Vector Machine (SVM) classification scheme was used on three sets of features: the elements of the polarimetric coherency matrix [ T ] , the parameters extracted from a polarimetric decomposition based on the eigenvalues and eigenvectors of [ T ] and the parameters extracted from a model-based decomposition. Using a single image, the results show that the best classification accuracies ( ≈ 75 % ) are obtained using the [ T ] matrix with the October images. When adding a second image to the feature set, either from two different dates or two incidence angles, the classification accuracy is improved and reaches 90 . 1 % with two images from October 2011 and April 2012 at 27 ∘ incidence. The results show that C-band polarimetric SAR imagery is an adequate tool to map shrub vegetation in sub-Arctic environments. |
| first_indexed | 2024-12-13T10:21:37Z |
| format | Article |
| id | doaj.art-f189a332fb8d49b1ac806f14abbab86c |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-12-13T10:21:37Z |
| publishDate | 2016-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-f189a332fb8d49b1ac806f14abbab86c2022-12-21T23:51:11ZengMDPI AGRemote Sensing2072-42922016-08-018969710.3390/rs8090697rs8090697Land Cover Classification in SubArctic Regions Using Fully Polarimetric RADARSAT-2 DataYannick Duguay0Monique Bernier1Esther Lévesque2Florent Domine3Centre Eau Terre Environnement, Institut national de la recherche scientifique (INRS), 490 de la Couronne, Québec City , QC G1K 9A9, CanadaCentre Eau Terre Environnement, Institut national de la recherche scientifique (INRS), 490 de la Couronne, Québec City , QC G1K 9A9, CanadaCentre d’études nordiques, Laval University, Pavillon Abitibi-Price 2405, rue de la Terrasse Local 1202, Québec City, QC G1V 0A6, CanadaCentre d’études nordiques, Laval University, Pavillon Abitibi-Price 2405, rue de la Terrasse Local 1202, Québec City, QC G1V 0A6, CanadaThe expansion of shrub vegetation in Arctic and sub-Arctic environments observed in the past decades can have significant effects on northern ecosystems. There is a need for efficient tools to monitor those changes, not only in terms of the spatial coverage of shrubs, but also their vertical growth. The objective of the current paper is to evaluate the performance of polarimetric C-band SAR datasets for land cover classification in sub-Arctic environments. A series of RADARSAT-2 quad-pol images were acquired between October 2011 and April 2012. The Support Vector Machine (SVM) classification scheme was used on three sets of features: the elements of the polarimetric coherency matrix [ T ] , the parameters extracted from a polarimetric decomposition based on the eigenvalues and eigenvectors of [ T ] and the parameters extracted from a model-based decomposition. Using a single image, the results show that the best classification accuracies ( ≈ 75 % ) are obtained using the [ T ] matrix with the October images. When adding a second image to the feature set, either from two different dates or two incidence angles, the classification accuracy is improved and reaches 90 . 1 % with two images from October 2011 and April 2012 at 27 ∘ incidence. The results show that C-band polarimetric SAR imagery is an adequate tool to map shrub vegetation in sub-Arctic environments.http://www.mdpi.com/2072-4292/8/9/697SARpolarimetrysub-Arcticclassificationsupport vector machine |
| spellingShingle | Yannick Duguay Monique Bernier Esther Lévesque Florent Domine Land Cover Classification in SubArctic Regions Using Fully Polarimetric RADARSAT-2 Data Remote Sensing SAR polarimetry sub-Arctic classification support vector machine |
| title | Land Cover Classification in SubArctic Regions Using Fully Polarimetric RADARSAT-2 Data |
| title_full | Land Cover Classification in SubArctic Regions Using Fully Polarimetric RADARSAT-2 Data |
| title_fullStr | Land Cover Classification in SubArctic Regions Using Fully Polarimetric RADARSAT-2 Data |
| title_full_unstemmed | Land Cover Classification in SubArctic Regions Using Fully Polarimetric RADARSAT-2 Data |
| title_short | Land Cover Classification in SubArctic Regions Using Fully Polarimetric RADARSAT-2 Data |
| title_sort | land cover classification in subarctic regions using fully polarimetric radarsat 2 data |
| topic | SAR polarimetry sub-Arctic classification support vector machine |
| url | http://www.mdpi.com/2072-4292/8/9/697 |
| work_keys_str_mv | AT yannickduguay landcoverclassificationinsubarcticregionsusingfullypolarimetricradarsat2data AT moniquebernier landcoverclassificationinsubarcticregionsusingfullypolarimetricradarsat2data AT estherlevesque landcoverclassificationinsubarcticregionsusingfullypolarimetricradarsat2data AT florentdomine landcoverclassificationinsubarcticregionsusingfullypolarimetricradarsat2data |