Reliable information about the spatial distribution of surface waters is critically important in various scientific disciplines. Synthetic Aperture Radar (SAR) is an effective way to detect floods and monitor water bodies over large areas. Sentinel-1 is a new available SAR and its spatial resolution and short temporal baselines have the potential to facilitate the monitoring of surface water changes, which are dynamic in space and time. While several methods and tools for flood detection and surface water extraction already exist, they often comprise a significant manual user interaction and do not specifically target the exploitation of Sentinel-1 data. The existing methods commonly rely on thresholding at the level of individual pixels, ignoring the correlation among nearby pixels. Thus, in this paper, we propose a fully automatic processing chain for rapid flood and surface water mapping with smooth labeling based on Sentinel-1 amplitude data. The method is applied to three different sites submitted to recent flooding events. The quantitative evaluation shows relevant results with overall accuracies of more than 98% and F-measure values ranging from 0.64 to 0.92. These results are encouraging and the first step to proposing operational image chain processing to help end-users quickly map flooding events or surface waters.
A Method for Automatic and Rapid Mapping of Water Surfaces from Sentinel-1 Imagery
F. Bioresita,A. Puissant,A. Stumpf,J. Malet
Published 2018 in Remote Sensing
ABSTRACT
PUBLICATION RECORD
- Publication year
2018
- Venue
Remote Sensing
- Publication date
2018-02-01
- Fields of study
Geology, Computer Science, Engineering, Environmental Science
- Identifiers
- External record
- Source metadata
Semantic Scholar
CITATION MAP
EXTRACTION MAP
CLAIMS
CONCEPTS
- flood and surface water mapping
The task of delineating flooded areas and surface water from remote-sensing imagery.
Aliases: surface water mapping, flood mapping
- f-measure
A performance metric that combines precision and recall for the mapped classes.
Aliases: F1 score, F1-measure
- fully automatic processing chain
A processing workflow that runs without manual user interaction.
Aliases: automatic processing chain
- overall accuracy
A classification metric measuring the proportion of correctly labeled pixels or samples.
Aliases: OA
- sentinel-1 amplitude data
SAR amplitude measurements from the Sentinel-1 mission used as input data.
Aliases: Sentinel-1 SAR amplitude data, Sentinel-1 imagery amplitude data
- smooth labeling
A labeling strategy that encourages spatially coherent class assignments among nearby pixels.
Aliases: spatially smooth labeling
- three flooding sites
Three case-study locations used to evaluate the method after recent flood events.
Aliases: three different sites
REFERENCES
Showing 1-46 of 46 references · Page 1 of 1