Improving SAR-based flood detection in arid regions using texture features

Autor(en): Ritushree, Dk
Garg, Shagun
Dasgupta, Antara
Martinis, Sandro
Selvakumaran, Sivasakthy
Motagh, Mahdi
Stichwörter: Added values; Arid regions; Auxiliary information; Dry sand; Flood detections; Flood mapping; Flood monitoring; Floods; Forestry; Image enhancement; Image texture; Polarization; Radar imaging; Random Forest; Random forests; SAR; Synthetic aperture radar; Synthetic aperture radar images; Textural information; texture; Texture features; Textures
Erscheinungsdatum: 2023
Herausgeber: Institute of Electrical and Electronics Engineers Inc.
Enthalten in: 2023 International Conference on Machine Intelligence for GeoAnalytics and Remote Sensing, MIGARS 2023
Zusammenfassung: 
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. © 2023 IEEE.
Beschreibung: 
Cited by: 0; Conference name: 2023 International Conference on Machine Intelligence for GeoAnalytics and Remote Sensing, MIGARS 2023; Conference date: 27 January 2023 through 29 January 2023; Conference code: 187316
ISBN: 9798350345421
DOI: 10.1109/MIGARS57353.2023.10064526
Externe URL: https://www.scopus.com/inward/record.uri?eid=2-s2.0-85151277351&doi=10.1109%2fMIGARS57353.2023.10064526&partnerID=40&md5=0bb2836cb21b27fe07a11d1f4a23fba0

Show full item record

Page view(s)

9
Last Week
2
Last month
0
checked on Jun 17, 2024

Google ScholarTM

Check

Altmetric