Semi-Automated Surface Water Detection with Synthetic Aperture Radar Data: A Wetland Case Study
In this study, a new method is proposed for semi-automated surface water detection using synthetic aperture radar data via a combination of radiometric thresholding and image segmentation based on the simple linear iterative clustering superpixel algorithm. Consistent intensity thresholds are select...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2017-11-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/9/12/1209 |
| _version_ | 1819294781237362688 |
|---|---|
| author | Amir Behnamian Sarah Banks Lori White Brian Brisco Koreen Millard Jon Pasher Zhaohua Chen Jason Duffe Laura Bourgeau-Chavez Michael Battaglia |
| author_facet | Amir Behnamian Sarah Banks Lori White Brian Brisco Koreen Millard Jon Pasher Zhaohua Chen Jason Duffe Laura Bourgeau-Chavez Michael Battaglia |
| author_sort | Amir Behnamian |
| collection | DOAJ |
| description | In this study, a new method is proposed for semi-automated surface water detection using synthetic aperture radar data via a combination of radiometric thresholding and image segmentation based on the simple linear iterative clustering superpixel algorithm. Consistent intensity thresholds are selected by assessing the statistical distribution of backscatter values applied to the mean of each superpixel. Higher-order texture measures, such as variance, are used to improve accuracy by removing false positives via an additional thresholding process used to identify the boundaries of water bodies. Results applied to quad-polarized RADARSAT-2 data show that the threshold value for the variance texture measure can be approximated using a constant value for different scenes, and thus it can be used in a fully automated cleanup procedure. Compared to similar approaches, errors of omission and commission are improved with the proposed method. For example, we observed that a threshold-only approach consistently tends to underestimate the extent of water bodies compared to combined thresholding and segmentation, mainly due to the poor performance of the former at the edges of water bodies. The proposed method can be used for monitoring changes in surface water extent within wetlands or other areas, and while presented for use with radar data, it can also be used to detect surface water in optical images. |
| first_indexed | 2024-12-24T04:31:46Z |
| format | Article |
| id | doaj.art-4b2a7085ffd946aab77ec49c8a6b7180 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-12-24T04:31:46Z |
| publishDate | 2017-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-4b2a7085ffd946aab77ec49c8a6b71802022-12-21T17:15:22ZengMDPI AGRemote Sensing2072-42922017-11-01912120910.3390/rs9121209rs9121209Semi-Automated Surface Water Detection with Synthetic Aperture Radar Data: A Wetland Case StudyAmir Behnamian0Sarah Banks1Lori White2Brian Brisco3Koreen Millard4Jon Pasher5Zhaohua Chen6Jason Duffe7Laura Bourgeau-Chavez8Michael Battaglia9Environment and Climate Change Canada, National Wildlife Research Centre, 1125 Colonel By Drive, Ottawa, ON K1S 5B6, CanadaEnvironment and Climate Change Canada, National Wildlife Research Centre, 1125 Colonel By Drive, Ottawa, ON K1S 5B6, CanadaEnvironment and Climate Change Canada, National Wildlife Research Centre, 1125 Colonel By Drive, Ottawa, ON K1S 5B6, CanadaCanada Centre for Mapping and Earth Observation, Natural Resources Canada, 560 Rochester St., Ottawa, ON K1S 5K2, CanadaDefence Research and Development Canada (DRDC), Ottawa Research Center, 3701 Carling Ave., Ottawa, ON K2K 2Y7, CanadaEnvironment and Climate Change Canada, National Wildlife Research Centre, 1125 Colonel By Drive, Ottawa, ON K1S 5B6, CanadaEnvironment and Climate Change Canada, National Wildlife Research Centre, 1125 Colonel By Drive, Ottawa, ON K1S 5B6, CanadaEnvironment and Climate Change Canada, National Wildlife Research Centre, 1125 Colonel By Drive, Ottawa, ON K1S 5B6, CanadaMichigan Tech Research Institute, Michigan Technological University, Ann Arbor, MI 48105, USAMichigan Tech Research Institute, Michigan Technological University, Ann Arbor, MI 48105, USAIn this study, a new method is proposed for semi-automated surface water detection using synthetic aperture radar data via a combination of radiometric thresholding and image segmentation based on the simple linear iterative clustering superpixel algorithm. Consistent intensity thresholds are selected by assessing the statistical distribution of backscatter values applied to the mean of each superpixel. Higher-order texture measures, such as variance, are used to improve accuracy by removing false positives via an additional thresholding process used to identify the boundaries of water bodies. Results applied to quad-polarized RADARSAT-2 data show that the threshold value for the variance texture measure can be approximated using a constant value for different scenes, and thus it can be used in a fully automated cleanup procedure. Compared to similar approaches, errors of omission and commission are improved with the proposed method. For example, we observed that a threshold-only approach consistently tends to underestimate the extent of water bodies compared to combined thresholding and segmentation, mainly due to the poor performance of the former at the edges of water bodies. The proposed method can be used for monitoring changes in surface water extent within wetlands or other areas, and while presented for use with radar data, it can also be used to detect surface water in optical images.https://www.mdpi.com/2072-4292/9/12/1209water mappingsurface waterwetlandSARRADARSAT-2histogramthresholdsegmentationsuperpixel |
| spellingShingle | Amir Behnamian Sarah Banks Lori White Brian Brisco Koreen Millard Jon Pasher Zhaohua Chen Jason Duffe Laura Bourgeau-Chavez Michael Battaglia Semi-Automated Surface Water Detection with Synthetic Aperture Radar Data: A Wetland Case Study Remote Sensing water mapping surface water wetland SAR RADARSAT-2 histogram threshold segmentation superpixel |
| title | Semi-Automated Surface Water Detection with Synthetic Aperture Radar Data: A Wetland Case Study |
| title_full | Semi-Automated Surface Water Detection with Synthetic Aperture Radar Data: A Wetland Case Study |
| title_fullStr | Semi-Automated Surface Water Detection with Synthetic Aperture Radar Data: A Wetland Case Study |
| title_full_unstemmed | Semi-Automated Surface Water Detection with Synthetic Aperture Radar Data: A Wetland Case Study |
| title_short | Semi-Automated Surface Water Detection with Synthetic Aperture Radar Data: A Wetland Case Study |
| title_sort | semi automated surface water detection with synthetic aperture radar data a wetland case study |
| topic | water mapping surface water wetland SAR RADARSAT-2 histogram threshold segmentation superpixel |
| url | https://www.mdpi.com/2072-4292/9/12/1209 |
| work_keys_str_mv | AT amirbehnamian semiautomatedsurfacewaterdetectionwithsyntheticapertureradardataawetlandcasestudy AT sarahbanks semiautomatedsurfacewaterdetectionwithsyntheticapertureradardataawetlandcasestudy AT loriwhite semiautomatedsurfacewaterdetectionwithsyntheticapertureradardataawetlandcasestudy AT brianbrisco semiautomatedsurfacewaterdetectionwithsyntheticapertureradardataawetlandcasestudy AT koreenmillard semiautomatedsurfacewaterdetectionwithsyntheticapertureradardataawetlandcasestudy AT jonpasher semiautomatedsurfacewaterdetectionwithsyntheticapertureradardataawetlandcasestudy AT zhaohuachen semiautomatedsurfacewaterdetectionwithsyntheticapertureradardataawetlandcasestudy AT jasonduffe semiautomatedsurfacewaterdetectionwithsyntheticapertureradardataawetlandcasestudy AT laurabourgeauchavez semiautomatedsurfacewaterdetectionwithsyntheticapertureradardataawetlandcasestudy AT michaelbattaglia semiautomatedsurfacewaterdetectionwithsyntheticapertureradardataawetlandcasestudy |