Details
| Original language | English |
|---|---|
| Title of host publication | 2023 International Conference on Machine Intelligence for GeoAnalytics and Remote Sensing, MIGARS 2023 |
| Publisher | Institute of Electrical and Electronics Engineers Inc. |
| ISBN (electronic) | 9798350345421 |
| ISBN (print) | 979-8-3503-4543-8 |
| Publication status | Published - 2023 |
| Event | 2023 International Conference on Machine Intelligence for GeoAnalytics and Remote Sensing, MIGARS 2023 - Hyderabad, India Duration: 27 Jan 2023 → 29 Jan 2023 |
Abstract
Flood monitoring in arid regions is challenging using Synthetic Aperture Radar (SAR) due to the similar backscatter of water and dry sand in surrounding areas. Since textural information is abundant in SAR images, this study investigates the added value of texture in SAR-based flood detection by providing it as auxiliary information for flood delineation. Results show that texture enhanced SAR images in VH polarization substantially underpredicts the flooded area, so adding texture does not improve the classification accuracy. However, using both polarization (VV and VH) produce ∼26% higher overall accuracy for flood detection in arid regions.
Keywords
- Flood mapping, Random Forest, SAR, texture
ASJC Scopus subject areas
- Agricultural and Biological Sciences(all)
- Agronomy and Crop Science
- Computer Science(all)
- Artificial Intelligence
- Computer Science(all)
- Computer Science Applications
- Earth and Planetary Sciences(all)
- Atmospheric Science
- Earth and Planetary Sciences(all)
- Computers in Earth Sciences
- Environmental Science(all)
- Management, Monitoring, Policy and Law
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
2023 International Conference on Machine Intelligence for GeoAnalytics and Remote Sensing, MIGARS 2023. Institute of Electrical and Electronics Engineers Inc., 2023.
Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review
}
TY - GEN
T1 - Improving SAR-based flood detection in arid regions using texture features
AU - Ritushree, Dk
AU - Garg, Shagun
AU - Dasgupta, Antara
AU - Martinis, Sandro
AU - Selvakumaran, Sivasakthy
AU - Motagh, Mahdi
N1 - Funding Information: ACKNOWLEDGMENT This work was supported by the Helmholtz project AI for Near-Real Time Satellite-based Flood Response (AI4Flood), which is a joint collaboration between the German Research Center for Geosciences (GFZ) and German Aerospace Center (DLR) and EPSRC Centre for Doctoral Training in Future
PY - 2023
Y1 - 2023
N2 - Flood monitoring in arid regions is challenging using Synthetic Aperture Radar (SAR) due to the similar backscatter of water and dry sand in surrounding areas. Since textural information is abundant in SAR images, this study investigates the added value of texture in SAR-based flood detection by providing it as auxiliary information for flood delineation. Results show that texture enhanced SAR images in VH polarization substantially underpredicts the flooded area, so adding texture does not improve the classification accuracy. However, using both polarization (VV and VH) produce ∼26% higher overall accuracy for flood detection in arid regions.
AB - Flood monitoring in arid regions is challenging using Synthetic Aperture Radar (SAR) due to the similar backscatter of water and dry sand in surrounding areas. Since textural information is abundant in SAR images, this study investigates the added value of texture in SAR-based flood detection by providing it as auxiliary information for flood delineation. Results show that texture enhanced SAR images in VH polarization substantially underpredicts the flooded area, so adding texture does not improve the classification accuracy. However, using both polarization (VV and VH) produce ∼26% higher overall accuracy for flood detection in arid regions.
KW - Flood mapping
KW - Random Forest
KW - SAR
KW - texture
UR - http://www.scopus.com/inward/record.url?scp=85151277351&partnerID=8YFLogxK
U2 - 10.1109/MIGARS57353.2023.10064526
DO - 10.1109/MIGARS57353.2023.10064526
M3 - Conference contribution
AN - SCOPUS:85151277351
SN - 979-8-3503-4543-8
BT - 2023 International Conference on Machine Intelligence for GeoAnalytics and Remote Sensing, MIGARS 2023
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2023 International Conference on Machine Intelligence for GeoAnalytics and Remote Sensing, MIGARS 2023
Y2 - 27 January 2023 through 29 January 2023
ER -