Article

Exploiting ConvNet Diversity for Flooding Identification

Details

Citation

Nogueira K, Fadel SG, Dourado IC, Werneck RdO, Munoz JAV, Penatti OAB, Calumby RT, Li LT, dos Santos JA & Torres RdS (2018) Exploiting ConvNet Diversity for Flooding Identification. IEEE Geoscience and Remote Sensing Letters, 15 (9), pp. 1446-1450. https://doi.org/10.1109/lgrs.2018.2845549

Abstract
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.

Keywords
Geotechnical Engineering and Engineering Geology; Electrical and Electronic Engineering

Journal
IEEE Geoscience and Remote Sensing Letters: Volume 15, Issue 9

StatusPublished
FundersFundação de Amparo à Pesquisa do Estado de São Paulo, Fundação de Amparo à Pesquisa do Estado de São Paulo, Fundação de Amparo à Pesquisa do Estado de São Paulo, Fundação de Amparo à Pesquisa do Estado de São Paulo, Fundação de Amparo à Pesquisa do Estado de São Paulo, Fundação de Amparo à Pesquisa do Estado de São Paulo, Fundação de Amparo à Pesquisa do Estado de Minas Gerais, Conselho Nacional de Desenvolvimento Científico e Tecnológico and Coordenação de Aperfeiçoamento de Pessoal de Nível Superior
Publication date30/09/2018
Publication date online27/06/2018
Date accepted by journal05/06/2018
URLhttp://hdl.handle.net/1893/30393
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
ISSN1545-598X

People (1)

Dr Keiller Nogueira

Dr Keiller Nogueira

Lecturer, Computing Science

Files (1)

Research centres/groups