Home damage estimation after disasters using crowdsourcing ideas and Convolutional Neural Networks

DOI

10.2991/icmia-16.2016.156How to use a DOI?

Keywords

Remote Sensing, Damage Estimation, Crowdsourcing, Convolutional Neural Networks, Deep Learning, Image Processing

Abstract

Recently, natural disasters like earthquake, flooding, and landslides evoke our intensive awareness. The first priority to be concerned is the home status left by people, because from which can we largely estimate the damage level of the catastrophe and manage the rescue action better. However, to investigate the problem requires amount of expertizes working day and night, scrutinizing on the satellite images of the suffering areas and tagging damage levels to each building inefficiently. Thanks to both the ideas, the crowdsourcing approaches and widespread applications of machine learning (especially deep learning) dominating the science world recently, this issue can be easily tackled in a noble way. This paper presents our ideas of how to utilize our established platform to help simplify the problems with crowdsourcing ideas and Convolutional Neural Networks approaches to make effective automatic home damage level estimation.

Copyright

© 2016, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Zhanghua Li
AU  - Kun Tian
AU  - Fushan Wang
AU  - Xiaocui Zheng
AU  - Fei Wang
PY  - 2016/11
DA  - 2016/11
TI  - Home damage estimation after disasters using crowdsourcing ideas and Convolutional Neural Networks
BT  - Proceedings of the 2016 5th International Conference on Measurement, Instrumentation and Automation (ICMIA 2016)
PB  - Atlantis Press
SN  - 1951-6851
UR  - https://doi.org/10.2991/icmia-16.2016.156
DO  - 10.2991/icmia-16.2016.156
ID  - Li2016/11
ER  -