English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

We propose a novel approach for rapid segmentation of flooded buildings byfusing multiresolution, multisensor, and multitemporal satellite imagery in aconvolutional neural network. Our model significantly expedites the generationof satellite imagery-based flood maps, crucial for first responders and localauthorities in the early stages of flood events. By incorporating multitemporalsatellite imagery, our model allows for rapid and accurate post-disaster damageassessment and can be used by governments to better coordinate medium- andlong-term financial assistance programs for affected areas. The networkconsists of multiple streams of encoder-decoder architectures that extractspatiotemporal information from medium-resolution images and spatialinformation from high-resolution images before fusing the resultingrepresentations into a single medium-resolution segmentation map of floodedbuildings. We compare our model to state-of-the-art methods for buildingfootprint segmentation as well as to alternative fusion approaches for thesegmentation of flooded buildings and find that our model performs best on bothtasks. We also demonstrate that our model produces highly accurate segmentationmaps of flooded buildings using only publicly available medium-resolution datainstead of significantly more detailed but sparsely available veryhigh-resolution data. We release the first open-source dataset of fullypreprocessed and labeled multiresolution, multispectral, and multitemporalsatellite images of disaster sites along with our source code.

Multi$^{\mathbf{3}}$Net: Segmenting Flooded Buildings via Fusion of Multiresolution, Multisensor, and Multitemporal Satellite Imagery