Abstract
When a natural disaster occurs, damaged regions rely on timely damage assessments to receive relief. Currently, this is a slow and laborious process, during which emergency response groups conduct on-the-ground evaluations to form fiscal estimates. This project attempts to expedite relief efforts by applying novel computer vision algorithms to satellite images to quickly and accurately estimate physical and fiscal damage caused by natural disasters. This paper investigates a modified U-Net architecture to jointly localize buildings, classify damage, and establish change detection. In particular, a second encoder is added to the U-Net architecture to simultaneously process pre- and post-event imagery, with both encoders sharing weights. In this way, the decoder is trained to both locate buildings and classify damage estimates by formulating it as a single semantic segmentation problem – producing damage estimates in one pass without needing to re-visit pixels (i.e. detection + classification tasks). Finally, a downstream task is added that provides a pixel-based financial model capable of outputting financial costs according to the United States National Grid (USNG) coordinate system through an interactive web application.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
A partial visualization is publicly hosted at https://ermlickw.github.io/.
References
Gupta, R., et al.: xBD: A dataset for assessing building damage from satellite imagery. arXiv:1911.09296 [cs.CV] (2019)
Fujita, A., Sakurada, K., Imaizumi, T., Ito, R., Hikosaka, S., Nakamura, R.: Damage detection from aerial images via convolutional neural networks. In: 2017 Fifteenth IAPR International Conference on Machine Vision Applications (MVA), pp. 5–8, Nagoya, Japan, IEEE (2017)
Xu, J., Lu, W., Li, Z., Khaitan, P., Zaytseva, V.: Building damage detection in satellite imagery using convolutional neural networks. arXiv:1910.06444 [cs.CV] (2019)
Doshi, J., Basu, S., Pang, G.: From satellite imagery to disaster insights. arXiv:1812.07033 [cs.CV] (2018)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. Commun. ACM 60(6), 84–90 (2017)
Ji, M., Liu, L., Buchroithner, M.: Identifying collapsed buildings using post-earthquake satellite imagery and convolutional neural networks: a case study of the 2010 haiti earthquake. Remote Sens. 10(11), 1689 (2018)
Iandola, F.N., Han, S., Moskewicz, M.W., Ashraf, K., Dally, W.J., Keutzer, K.: SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and \(<\)0.5MB model size. arXiv:1602.07360 [cs.CV] (2016)
Ronneberger, O., Fisher, P., Brox, T.: U-Net: Convolutional networks for biomedical image segmentation. arXiv:1505.04597 [cs.CV] (2015)
He, K., Gkioxari, G., Dollar, P., Girshick, R.: Mask R-CNN: Facebook AI Research (FAIR) arXiv:1703.06870 [cs.CV] (2018)
Waleed, A.: Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow https://github.com/matterport/MaskRCNN
Sudre, C.H., et al.: Generalised dice overlap as a deep learning loss function for highly unbalanced segmentations. In: Cardoso, M.J., et al. (eds.) DLMIA/ML-CDS -2017. LNCS, vol. 10553, pp. 240–248. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-67558-9_28
Clinton County Ohio, United States National Grid. http://www.clintoncountyohgis.org/Maps/MapsIndex/Pages/MapsU/... united_states_national_grid.html (2020)
Federal Geographic Data Committee, United States National Grid. https://www.fgdc.gov/usng (2020)
Howard Butlet, mgrs. https://pypi.org/project/mgrs/ (2011)
National Geospatial-Inteligence Agency, MSP Geotrans Assistance. https://earth-info.nga.mil/GandG/update/index.php?action=home (2020)
Zillow Research, Zillow Home Value Index. https://www.zillow.com/research/data/ (2018)
United States Census Bureau, Geography Program. https://www.census.gov/programs-surveys/geography.html (2020)
National Ocean and Atomosphereic Administration, Billion-Dollar Weather and Climate Disasters: Events. https://www.ncdc.noaa.gov/billions/events (2020)
AI for Humanitarian Assistance and Disaster Relief, xView2unet. https://github.com/canktech/xview2unet (2020)
Ortiz, B., et al.: Improving Community Resiliency and Emergency Response with Artificial Intelligence. In: ISCRAM (2020)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Ermlick, W. et al. (2020). Natural Disaster Building Damage Assessment Using a Two-Encoder U-Net. In: Bebis, G., et al. Advances in Visual Computing. ISVC 2020. Lecture Notes in Computer Science(), vol 12509. Springer, Cham. https://doi.org/10.1007/978-3-030-64556-4_53
Download citation
DOI: https://doi.org/10.1007/978-3-030-64556-4_53
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-64555-7
Online ISBN: 978-3-030-64556-4
eBook Packages: Computer ScienceComputer Science (R0)