Next Article in Journal
Precipitation Dominates Long-Term Water Storage Changes in Nam Co Lake (Tibetan Plateau) Accompanied by Intensified Cryosphere Melts Revealed by a Basin-Wide Hydrological Modelling
Next Article in Special Issue
Learning from the 2018 Western Japan Heavy Rains to Detect Floods during the 2019 Hagibis Typhoon
Previous Article in Journal
Fine-Tuning Self-Organizing Maps for Sentinel-2 Imagery: Separating Clouds from Bright Surfaces
Previous Article in Special Issue
Wetland Surface Water Detection from Multipath SAR Images Using Gaussian Process-Based Temporal Interpolation
Open AccessArticle

Deep Learning-Based Identification of Collapsed, Non-Collapsed and Blue Tarp-Covered Buildings from Post-Disaster Aerial Images

1
Department of Advanced Science and Engineering, Hiroshima University, Kagamiyama 1-4-1, Higashi-Hiroshima, Hiroshima 739-8527, Japan
2
Department of Architecture, Hiroshima University, Kagamiyama 1-4-1, Higashi-Hiroshima, Hiroshima 739-8527, Japan
3
Department of Architecture and Building Engineering, Tokyo Institute of Technology, Nagatsuta 4259, Yokohama, Kanagawa 226-8502, Japan
*
Author to whom correspondence should be addressed.
Remote Sens. 2020, 12(12), 1924; https://doi.org/10.3390/rs12121924
Received: 27 April 2020 / Revised: 26 May 2020 / Accepted: 10 June 2020 / Published: 14 June 2020
A methodology for the automated identification of building damage from post-disaster aerial images was developed based on convolutional neural network (CNN) and building damage inventories. The aerial images and the building damage data obtained in the 2016 Kumamoto, and the 1995 Kobe, Japan earthquakes were analyzed. Since the roofs of many moderately damaged houses are covered with blue tarps immediately after disasters, not only collapsed and non-collapsed buildings but also the buildings covered with blue tarps were identified by the proposed method. The CNN architecture developed in this study correctly classifies the building damage with the accuracy of approximately 95 % in both earthquake data. We applied the developed CNN model to aerial images in Chiba, Japan, damaged by the typhoon in September 2019. The result shows that more than 90 % of the building damage are correctly classified by the CNN model. View Full-Text
Keywords: deep learning; building damage; aerial image; earthquake; typhoon deep learning; building damage; aerial image; earthquake; typhoon
Show Figures

Graphical abstract

MDPI and ACS Style

Miura, H.; Aridome, T.; Matsuoka, M. Deep Learning-Based Identification of Collapsed, Non-Collapsed and Blue Tarp-Covered Buildings from Post-Disaster Aerial Images. Remote Sens. 2020, 12, 1924.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop