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

被引:2
作者
Ritushree, D. K. [1 ]
Garg, Shagun [2 ]
Dasgupta, Antara [3 ]
Martinis, Sandro [4 ]
Selvakumaran, Sivasakthy [5 ]
Motagh, Mahdi [6 ]
机构
[1] GFZ German Res Ctr Geosci, RemoteSensing & Geoinformat Geodesy, Potsdam, Germany
[2] Univ Cambridge, Dept Engn, Future Infrastruct & Built Environm FIBE, Cambridge, England
[3] Univ Osnabruck, Inst Informat, Remote Sensing Working Grp, Osnabruck, Germany
[4] German Aerosp Ctr DLR, German Remote Sensing Data Ctr DFD, Oberpfaffenhonefen, Germany
[5] Univ Cambridge, Dept Engn, Cambridge, England
[6] Leibniz Univ Hannover, Inst Photogrammetry & Geoinformat, Hannover, Germany
来源
2023 INTERNATIONAL CONFERENCE ON MACHINE INTELLIGENCE FOR GEOANALYTICS AND REMOTE SENSING, MIGARS | 2023年
基金
英国工程与自然科学研究理事会;
关键词
Flood mapping; SAR; texture; Random Forest;
D O I
10.1109/MIGARS57353.2023.10064526
中图分类号
P [天文学、地球科学];
学科分类号
07 ;
摘要
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 similar to 26% higher overall accuracy for flood detection in arid regions.
引用
收藏
页码:175 / 178
页数:4
相关论文
共 13 条
  • [1] Constraints on future changes in climate and the hydrologic cycle
    Allen, MR
    Ingram, WJ
    [J]. NATURE, 2002, 419 (6903) : 224 - +
  • [2] ASF DAAC, 2015, CONT MOD COP SENT DA
  • [3] Random forests
    Breiman, L
    [J]. MACHINE LEARNING, 2001, 45 (01) : 5 - 32
  • [4] Landslide susceptibility estimation by random forests technique: sensitivity and scaling issues
    Catani, F.
    Lagomarsino, D.
    Segoni, S.
    Tofani, V.
    [J]. NATURAL HAZARDS AND EARTH SYSTEM SCIENCES, 2013, 13 (11) : 2815 - 2831
  • [5] Towards operational SAR-based flood mapping using neuro-fuzzy texture-based approaches
    Dasgupta, Antara
    Grimaldi, Stefania
    Ramsankaran, R. A. A. J.
    Pauwels, Valentijn R. N.
    Walker, Jeffrey P.
    [J]. REMOTE SENSING OF ENVIRONMENT, 2018, 215 : 313 - 329
  • [6] AUTOMATIC FLOOD DETECTION FROM SENTINEL-1 DATA USING DEEP LEARNING ARCHITECTURES
    Ghosh, B.
    Garg, S.
    Motagh, M.
    [J]. XXIV ISPRS CONGRESS: IMAGING TODAY, FORESEEING TOMORROW, COMMISSION III, 2022, 5-3 : 201 - 208
  • [7] TEXTURAL FEATURES FOR IMAGE CLASSIFICATION
    HARALICK, RM
    SHANMUGAM, K
    DINSTEIN, I
    [J]. IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS, 1973, SMC3 (06): : 610 - 621
  • [8] Water-related disasters and their health impacts: A global review
    Lee, Jiseon
    Perera, Duminda
    Glickman, Talia
    Taing, Lina
    [J]. PROGRESS IN DISASTER SCIENCE, 2020, 8
  • [9] A fully automated TerraSAR-X based flood service
    Martinis, Sandro
    Kersten, Jens
    Twele, Andre
    [J]. ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING, 2015, 104 : 203 - 212
  • [10] step.esa, SNAP-ESA Sentinel Application Platform v2.0.2