ABSTRACT
This paper explores the application of deep learning techniques in the task of assessing disaster impact from satellite imagery. Identifying the regions impacted by a disaster is critical for effective mobilization of relief efforts. Satellite images, with their vast coverage of ground surface, are a valuable resource that can be leveraged for this purpose. However, the task of analysing a satellite image to detect regions impacted by disaster is challenging. In recent years, the increasing availability of satellite images of a place presents an opportunity to utilize deep learning on these images to provide a preliminary insight on the impact of a disaster after its occurrence. We particularly focus on water related disasters like floods and hurricanes. To identify the impacted regions, we employ Convolutional Neural Networks to semantically segment topographical features like roads on pre and post-disaster satellite images and find the regions with maximal change. However, this approach is less applicable on rural landscapes due to the sparse distribution of topographical features like roads. To address such cases of imagery from rural areas, we propose a bitemporal image classification approach to compare pre and post disaster scenes and directly identify if the regions are impacted or not. On testing against a ground truth satellite image from DigitalGlobe with labeled regions depicting the impacts of Hurricane Harvey, the flooded road extraction approach achieved an accuracy of 0.845 with a F1-Score of 0.675. Similarly, the bitemporal image classification approach registered an accuracy of 0.94 when tested against a rural landscape impacted by South Asian Monsoon Flooding of 2017.
- Orchid. 2015. ORCHID researchers provide Nepal earthquake response. Retrieved from: http://www.orchid.ac.uk/presses/orchid-researchers-provide-nepal-earthquake-response/Google Scholar
- Voigt, S., Giulio, F. T., et al. 2016. Global trends in satellite-based emergency mapping. Science. 353. 247--252. DOI: https://dx.doi.org/10.1126/science.aad8728Google Scholar
- Voigt, S., Kemper, T., Riedlinger, T.,Kiefl, R., Scholte, K. and Mehl, H. 2007. Satellite Image Analysis for Disaster and Crisis-Management Support. IEEE T. Geoscience and Remote Sensing. 45. 1520--1528. DOI: https://dx.doi.org/10.1109/TGRS.2007.895830Google Scholar
- Trekin, A., Novikov, G., Potapov, G., Ignatiev, V. and Burnaev, E. 2018. Satellite Imagery Analysis for Operational Damage Assessment in Emergency Situations. arXiv:1803.00397. Retrieved from: https://arxiv.org/abs/1803.00397Google Scholar
- Gueguen, L. and Hamid, R. 2015. Large-Scale Damage Detection Using Satellite Imagery. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (Boston, MA, USA, June 07-12, 2017). IEEE. 1321--1328. DOI: https://dx.doi.org/10.1109/CVPR.2015.7298737Google Scholar
- Matikainen, L., Juha, H., Kaartinen, H., et al. 2004. Automatic detection of changes from laser scanner and aerial image data for updating building maps, Matrix, 35, 434--439.Google Scholar
- Vu, T. T., Matsuoka, M. and Yamazaki, F. 2004. LIDAR-based Change Detection of Buildings in Dense Urban Areas. In Proceedings of the IEEE International Geoscience and Remote Sensing Symposium (Anchorage, AK, USA, September 20-24, 2004). IEEE. 2--6. DOI: https://dx.doi.org/10.1109/IGARSS.2004.1370438Google Scholar
- Nogueira, K., Fadel, S., Dourado, I., Werneck, R., et al. 2017. Exploiting ConvNet Diversity for Flooding Identification. IEEE Geoscience and Remote Sensing Letters. 15. 1446--1450. DOI: https://dx.doi.org/10.1109/LGRS.2018.2845549Google Scholar
- Cao, Q. D. and Choe, Y. 2018. Building Damage Annotation on Post-Hurricane Satellite Imagery Based on Convolutional Neural Networks. arXiv: 1807.01688. Retrieved from: https://arxiv.org/abs/1807.01688Google Scholar
- Binti, A., Siti, N. K. and Aoki, Y. 2017. Disaster detection from aerial imagery with convolutional neural network. International Electronics Symposium on Knowledge Creation and Intelligent Computing (Surabaya, Indonesia, September 26-27, 2017;. 239--245. DOI: https://dx.doi.org/10.1109/KCIC.2017.8228593Google Scholar
- Cooner, A. J., Shao, Y. and Campbell, J. B. 2016. Detection of Urban Damage Using Remote Sensing and Machine Learning Algorithms: Revisiting the 2010 Haiti Earthquake. Remote Sensing. 8, 868. DOI: https://doi.org/10.3390/rs8100868Google ScholarCross Ref
- Doshi, J., Basu, S. and Pang, G. 2018. From Satellite Imagery to Disaster Insights. arXiv: 1812.07033. Retrieved from: https://arxiv.org/abs/1812.07033Google Scholar
- Doshi, J. 2018. Residual inception skip network for binary segmentation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops (Salt Lake City, UT, USA, June 18-22, 2018). IEEE. 216-219 DOI: https://doi.org/10.1109/CVPRW.2018.00037Google ScholarCross Ref
- Ronneberger, O., Fischer, P. and Brox, T. U-Net: Convolutional Networks for Biomedical Image Segmentation. arXiv: 1505.04597. Retrieved from: https://arxiv.org/abs/1505.04597Google Scholar
- Demir, I., Koperski, K., Lindenbaum, D., et al. 2018. DeepGlobe 2018: A Challenge to Parse the Earth through Satellite Images. arXiv:1805.06561. Retrieved from: https://arxiv.org/abs/1805.06561Google Scholar
- DeepGlobe Open Data Program. Retrieved from: https://www.digitalglobe.com/ecosystem/open-dataGoogle Scholar
- Schelhamer, E., Long, J. and Darrel, T. 2016. Fully Convolutional Networks for Semantic Segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence. 39. 640--651. DOI: https://doi.org/10.1109/TPAMI.2016.2572683Google Scholar
- He, K., Zhang, X., Ren, S. and Sun, J. 2015. Deep Residual Learning for Image Recognition. arXiv:1512.03385. Retrieved from: https://arxiv.org/abs/1512.03385Google Scholar
- Xie, S., Girshick, R., Dollar, P., Tu, D. and He, K. Aggregated Residual Transformations for Deep Neural Networks. arXiv:1611.05431. Retrieved from: https://arxiv.org/abs/1611.05431Google Scholar
- Bukenya, F., Yuhaniz, S., Hashim, S. Z. M. and Kalema, A. K. 2012. Detecting floods using an object based change detection approach. International Conference on Computer and Communication Engineering (Kuala Lumpur, Malaysia, July 3-5, 2012). IEEE. DOI: https://doi.org/10.1109/ICCCE.2012.6271149Google Scholar
Index Terms
- Disaster Assessment from Satellite Imagery by Analysing Topographical Features Using Deep Learning
Recommendations
Rapid Earthquake Assessment from Satellite Imagery Using RPN and Yolo v3
Intelligent Computing Theories and ApplicationAbstractNepal suffers from earthquakes frequently as it lies in a highly earthquake prone region. The relief that is to be sent to the earthquake affected area requires rapid earliest assessment of the impact in the area. The number of damaged buildings ...
Convolutional neural network based hurricane damage detection using satellite images
AbstractHurricanes are tropical storms that cause immense damage to human life and property. Rapid assessment of damage caused by hurricanes is extremely important for the first responders. But this process is usually slow, expensive, labor intensive and ...
Multi-sensor Snow Cover Mapping and Emergency Assessment of the Snow Disaster in Xinjiang
GIT4NDM '13: Proceedings of the 2013 Fifth International Conference on Geo-Information Technologies for Natural Disaster ManagementAccurate and timely extraction of snow cover information is of great significance in the monitoring and assessment of snow disasters. However, remote sensing observations in snowing weathers were susceptible to the impacts of clouds and atmospheric ...
Comments