TY - JOUR
T1 - A framework of rapid regional tsunami damage recognition from post-event terraSAR-X imagery using deep neural networks
AU - Bai, Yanbing
AU - Gao, Chang
AU - Singh, Sameer
AU - Koch, Magaly
AU - Adriano, Bruno
AU - Mas, Erick
AU - Koshimura, Shunichi
N1 - Funding Information:
Manuscript received June 1, 2017; revised August 19, 2017 and September 18, 2017; accepted October 23, 2017. Date of publication December 4, 2017; date of current version December 27, 2017. This work was supported in part by JST CREST, Japan, under Grant JPMJCR1411 and in part by the China Scholarship Council. (Corresponding author: Yanbing Bai.) Y. Bai is with the Graduate School of Engineering, Tohoku University, Sendai 980-8579, Japan (e-mail: ybbaipku@gmail.com). C. Gao is with the Department of Computer Science, The University of Hong Kong, Hong Kong. S. Singh is with the Department of Computer Science, University of California at Irvine, Irvine, CA 92697-3435 USA. M. Koch is with the Center for Remote Sensing, Boston, MA 02215 USA. B. Adriano, E. Mas, and S. Koshimura are with the International Research Institute of Disaster Science, Tohoku University, Sendai 980-0845, Japan. Color versions of one or more of the figures in this letter are available online at http://ieeexplore.ieee.org. Digital Object Identifier 10.1109/LGRS.2017.2772349
Publisher Copyright:
© 2017 IEEE.
PY - 2018/1
Y1 - 2018/1
N2 - Near real-time building damage mapping is an indispensable prerequisite for governments to make decisions for disaster relief. With high-resolution synthetic aperture radar (SAR) systems, such as TerraSAR-X, the provision of such products in a fast and effective way becomes possible. In this letter, a deep learning-based framework for rapid regional tsunami damage recognition using post-event SAR imagery is proposed. To perform such a rapid damage mapping, a series of tile-based image split analysis is employed to generate the data set. Next, a selection algorithm with the SqueezeNet network is developed to swiftly distinguish between built-up (BU) and nonbuilt-up regions. Finally, a recognition algorithm with a modified wide residual network is developed to classify the BU regions into wash away, collapsed, and slightly damaged regions. Experiments performed on the TerraSAR-X data from the 2011 Tohoku earthquake and tsunami in Japan show a BU region extraction accuracy of 80.4% and a damage-level recognition accuracy of 74.8%, respectively. Our framework takes around 2 h to train on a new region, and only several minutes for prediction.
AB - Near real-time building damage mapping is an indispensable prerequisite for governments to make decisions for disaster relief. With high-resolution synthetic aperture radar (SAR) systems, such as TerraSAR-X, the provision of such products in a fast and effective way becomes possible. In this letter, a deep learning-based framework for rapid regional tsunami damage recognition using post-event SAR imagery is proposed. To perform such a rapid damage mapping, a series of tile-based image split analysis is employed to generate the data set. Next, a selection algorithm with the SqueezeNet network is developed to swiftly distinguish between built-up (BU) and nonbuilt-up regions. Finally, a recognition algorithm with a modified wide residual network is developed to classify the BU regions into wash away, collapsed, and slightly damaged regions. Experiments performed on the TerraSAR-X data from the 2011 Tohoku earthquake and tsunami in Japan show a BU region extraction accuracy of 80.4% and a damage-level recognition accuracy of 74.8%, respectively. Our framework takes around 2 h to train on a new region, and only several minutes for prediction.
UR - http://www.scopus.com/inward/record.url?scp=85040833619&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85040833619&partnerID=8YFLogxK
U2 - 10.1109/LGRS.2017.2772349
DO - 10.1109/LGRS.2017.2772349
M3 - Article
AN - SCOPUS:85040833619
VL - 15
SP - 43
EP - 47
JO - IEEE Geoscience and Remote Sensing Letters
JF - IEEE Geoscience and Remote Sensing Letters
SN - 1545-598X
IS - 1
ER -