期刊
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING
卷 136, 期 -, 页码 144-153出版社
ELSEVIER SCIENCE BV
DOI: 10.1016/j.isprsjprs.2017.11.006
关键词
SAR; Water extraction; Support vector machine; Active contour; Inundation analysis
类别
资金
- China Special Funds for Meteorological Research in the Public Interest [GYHY201306055]
- National Natural Science Foundation of China [41631178, 41325005, 41672230, 41611130047]
- Program of International S&T Cooperation of China [S2015ZR1074]
- Fundamental Research Funds for the Central Universities
Remote sensing techniques offer potential for effective flood detection with the advantages of low-cost, large-scale, and real-time surface observations. The easily accessible data sources of optical remote sensing imagery provide abundant spectral information for accurate surface water body extraction, and synthetic aperture radar (SAR) systems represent a powerful tool for flood monitoring because of their all-weather capability. This paper introduces a new approach for flood monitoring by the combined use of both Landsat 8 optical imagery and COSMO-SkyMed radar imagery. Specifically, the proposed method applies support vector machine and the active contour without edges model for water extent determination in the periods before and during the flood, respectively. A map difference method is used for the flood inundation analysis. The proposed approach is particularly suitable for large-scale flood monitoring, and it was tested on a serious flood that occurred in northeastern China in August 2013, which caused immense loss of human lives and properties. High overall accuracies of 97.46% for the optical imagery and 93.70% for the radar imagery are achieved by the use of the techniques presented in this study. The results show that about 12% of the whole study area was inundated, corresponding to 5466 km(2) of land surface. (C) 2017 International Society for Photogrammetry and Remote Sensing, Inc. (ISPRS). Published by Elsevier B.V. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据