Automatic Mapping of Tropical Cyclone-Induced Coastal Inundation in SAR Imagery Based on Clustering of Deep Features

Researchers have already verified that the deep learning (DL) technology can realize accurate and robust mapping of tropical cyclone-induced coastal inundation in synthetic aperture radar imagery. In order to liberate the DL-based inundation mapping from human supervision, we propose to use the clus...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE International Geoscience and Remote Sensing Symposium proceedings s. 5765 - 5768
Hlavní autoři: Liu, Bin, Li, Xiaofeng, Zheng, Gang
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 26.09.2020
Témata:
clustering
Coastal inundation mapping
deep convolutional autoen-coder (DCAE)
Feature extraction
Floods
Radar imaging
Radar polarimetry
Sea measurements
Sensors
Synthetic aperture radar
synthetic aperture radar (SAR) imagery
ISSN:2153-7003
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Researchers have already verified that the deep learning (DL) technology can realize accurate and robust mapping of tropical cyclone-induced coastal inundation in synthetic aperture radar imagery. In order to liberate the DL-based inundation mapping from human supervision, we propose to use the clustering of deep convolutional autoencoder-generated features. The mapping results of Lekima 2019-induced inundation demonstrate the advantages and availability of the proposed method.
ISSN:2153-7003
DOI:10.1109/IGARSS39084.2020.9324529