TY - JOUR

T1 - Exploiting ConvNet diversity for flooding identification

AU - Nogueira, Keiller

AU - Fadel, Samuel G.

AU - Dourado, Icaro C.

AU - De Werneck, Rafael O.

AU - Munoz, Javier A.V.

AU - Penatti, Otavio A.B.

AU - Calumby, Rodrigo T.

AU - Li, Lin Tzy

AU - Dos Santos, Jefersson A.

AU - Torres, Ricardo Da S.

PY - 2018/9

Y1 - 2018/9

N2 - Flooding is the world's most costly type of natural disaster in terms of both economic losses and human causalities. A first and essential procedure toward flood monitoring is based on identifying the area most vulnerable to flooding, which gives authorities relevant regions to focus. In this letter, we propose several methods to perform flooding identification in high-resolution remote sensing images using deep learning. Specifically, some proposed techniques are based upon unique networks, such as dilated and deconvolutional ones, whereas others were conceived to exploit diversity of distinct networks in order to extract the maximum performance of each classifier. The evaluation of the proposed methods was conducted in a high-resolution remote sensing data set. Results show that the proposed algorithms outperformed the state-of-the-art baselines, providing improvements ranging from 1% to 4% in terms of the Jaccard Index.

AB - Flooding is the world's most costly type of natural disaster in terms of both economic losses and human causalities. A first and essential procedure toward flood monitoring is based on identifying the area most vulnerable to flooding, which gives authorities relevant regions to focus. In this letter, we propose several methods to perform flooding identification in high-resolution remote sensing images using deep learning. Specifically, some proposed techniques are based upon unique networks, such as dilated and deconvolutional ones, whereas others were conceived to exploit diversity of distinct networks in order to extract the maximum performance of each classifier. The evaluation of the proposed methods was conducted in a high-resolution remote sensing data set. Results show that the proposed algorithms outperformed the state-of-the-art baselines, providing improvements ranging from 1% to 4% in terms of the Jaccard Index.

KW - Flooding identification

KW - inundation

KW - MediaEval

KW - natural disaster

KW - remote sensing

KW - satellites

UR - http://www.scopus.com/inward/record.url?scp=85049144059&partnerID=8YFLogxK

U2 - 10.1109/LGRS.2018.2845549

DO - 10.1109/LGRS.2018.2845549

M3 - Journal articles

AN - SCOPUS:85049144059

VL - 15

SP - 1446

EP - 1450

JO - IEEE Geoscience and Remote Sensing Letters

JF - IEEE Geoscience and Remote Sensing Letters

SN - 1545-598X

IS - 9

M1 - 8398414

ER -