期刊
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
卷 57, 期 2, 页码 722-739出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TGRS.2018.2860054
关键词
Active contours; change detection; flood mapping; synthetic aperture radar (SAR); thresholding
类别
资金
- Research Foundation Flanders [G.0179.16N]
- Bijzonder Onderzoeksfonds of Ghent University
In our changing world, floods are a threat of increasing concern. Within this context, flood mapping is important for both damage assessment and forecast improvement. Due to the suitability of synthetic aperture radar (SAR) for flood mapping, a broad range of SAR-based flood mapping algorithms has been developed during the past years. However, most of these algorithms were presented based on a single test case only and comparisons between methods are rare. This paper presents an in-depth assessment and comparison of the established pixel-based flood mapping approaches, including global and enhanced thresholding, active contour modeling and change detection. The methods were tested on medium-resolution SAR images of different flood events and lakes across the U.K. and Ireland and were evaluated on both accuracy and robustness. Results indicate that the most suited method depends on the area of interest and its characteristics as well as the intended use of the observation product. Due to its high robustness and good performance, tiled thresholding is suited for automated, near-real time flood detection and monitoring. Active contour models can provide higher accuracies but require long computation times that strongly increase with increasing image sizes, making them more appropriate for accurate flood mapping in smaller areas of interest.
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