TY - CHAP

T1 - Graph-Based Early-Fusion for Flood Detection

AU - De Werneck, Rafael O.

AU - Dourado, Icaro C.

AU - Fadel, Samuel G.

AU - Tabbone, Salvatore

AU - Torres, Ricardo Da S.

N1 - Conference code: 25

PY - 2018/8/29

Y1 - 2018/8/29

N2 - Flooding is one of the most harmful natural disasters, as it poses danger to both buildings and human lives. Therefore, it is fundamental to monitor these disasters to define prevention strategies and help authorities in damage control. With the wide use of portable devices (e.g., smartphones), there is an increase of the documentation and communication of flood events in social media. However, the use of these data in monitoring systems is not straightforward and depends on the creation of effective recognition strategies. In this paper, we propose a fusion-based recognition system for detecting flooding events in images extracted from social media. We propose two new graph-based early-fusion methods, which consider multiple descriptions and modalities to generate an effective image representation. Our results demonstrate that the proposed methods yield better results than a traditional early-fusion method and a specialized deep neural network fusion solution.

AB - Flooding is one of the most harmful natural disasters, as it poses danger to both buildings and human lives. Therefore, it is fundamental to monitor these disasters to define prevention strategies and help authorities in damage control. With the wide use of portable devices (e.g., smartphones), there is an increase of the documentation and communication of flood events in social media. However, the use of these data in monitoring systems is not straightforward and depends on the creation of effective recognition strategies. In this paper, we propose a fusion-based recognition system for detecting flooding events in images extracted from social media. We propose two new graph-based early-fusion methods, which consider multiple descriptions and modalities to generate an effective image representation. Our results demonstrate that the proposed methods yield better results than a traditional early-fusion method and a specialized deep neural network fusion solution.

KW - Early fusion

KW - Flood detection

KW - Graph-based fusion

KW - Image representation

KW - MediaEval

UR - http://www.scopus.com/inward/record.url?scp=85062912293&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2018.8451011

DO - 10.1109/ICIP.2018.8451011

M3 - Article in conference proceedings

AN - SCOPUS:85062912293

SN - 978-1-4799-7062-9

T3 - Proceedings - International Conference on Image Processing, ICIP

SP - 1048

EP - 1052

BT - 2018 IEEE International Conference on Image Processing, ICIP 2018 - Proceedings

PB - IEEE - Institute of Electrical and Electronics Engineers Inc.

T2 - 25th IEEE International Conference on Image Processing - ICIP 2018

Y2 - 7 October 2018 through 10 October 2018

ER -