Detecting and Geolocating City-Scale Soft-Story Buildings by Deep Machine Learning for Urban Seismic Resilience
Publication: Natural Hazards Review
Volume 23, Issue 1
Abstract
Seismic resilience is of great concern and vital importance for cities in earthquake zones. It is not only desirable but also mandatory for the cities to prepare an emergency response plan for possible seismic events. One important task is to identify the seismic vulnerable buildings, e.g., soft-story (SS) buildings. The identified SS buildings can be retrofitted to minimize the risk of possible damage and the mitigation plan can be made accordingly to allocate the needed resources to the vulnerable buildings when earthquake strikes. However, it is time-consuming and costly for structural engineers to identify SS buildings manually by walking through each street. This paper presents an integrated approach for automatically detecting and geolocating SS buildings at a city scale. The approach proceeds in multiple steps, including (1) obtaining a list of addresses of engineer-identified SS buildings in city of Santa Monica, CA; (2) extracting the Google Street View images of the SS buildings; (3) labeling the SS building in the images; (4) training a deep convolutional neural network with the annotated images; and (5) testing the trained model on an independent image data set. The detected SS buildings are geocoded in Google map for users to verify the results quickly and virtually.
Get full access to this article
View all available purchase options and get full access to this article.
Data Availability Statement
Some or all data, models, or code generated or used during the study are proprietary or confidential in nature and may only be provided with restrictions. Soft-story building information for city of Sana Monica is available at https://gis-smgov.opendata.arcgis.com/datasets/locations.
Acknowledgments
Authors thank Mr. Evan Reis from the US Resiliency Council, who provided more than 2,000 images of soft-story buildings and his valuable insights for the research. The authors also thank Bentley colleagues Raoul Karp, Kaustubh Page, and Jason Chickneas for their help and suggestions on the initiative of the research project.
References
Adalier, K., and O. Aydingun. 2001. “Structural engineering aspects of the June 27, 1998 Adana–Ceyhan (Turkey) earthquake.” Eng. Struct. 23 (4): 343–355. https://doi.org/10.1016/S0141-0296(00)00046-8.
ASCE. 2002. Seismic evaluation of existing buildings: Second public ballot. Reston, VA: ASCE.
Avşar, Ö., and O. Tunaboyu. 2014. “Influence of structural walls on the seismic performance of RC buildings during the May 19, 2011 Simav earthquake in Turkey.” J. Perform. Constr. Facil. 28 (4): 04014016. https://doi.org/10.1061/(ASCE)CF.1943-5509.0000473.
Bency, A. J., S. Rallapalli, R. K. Ganti, M. Srivatsa, and B. S. Manjunath. 2017. “Beyond spatial auto-regressive models: Predicting housing prices with satellite imagery.” In Proc., 2017 IEEE Winter Conf. on Applications of Computer Vision (WACV). New York: IEEE.
Burton, H., A. R. Rad, Z. Yi, D. Gutierrez, and K. Ojuri. 2018. “Seismic collapse performance of Los Angeles soft, weak, and open-front wall line woodframe structures retrofitted using different procedures.” Bull. Earthquake Eng. 17 (4): 2059–2091. https://doi.org/10.1007/s10518-018-00524-w.
Çelebi, E., M. Aktas, N. Çağlar, A. Özocak, M. Kutanis, N. Mert, and Z. Özcan. 2012. “October 23, 2011 Turkey/Van–Ercis earthquake: Structural damages in the residential buildings.” Nat. Hazard. 65 (3): 2287–2310.
Doǧangün, A. 2004. “Performance of reinforced concrete buildings during the May 1, 2003 Bingöl Earthquake in Turkey.” Eng. Struct. 26 (6): 841–856. https://doi.org/10.1016/j.engstruct.2004.02.005.
He, K., X. Zhang, S. Ren, and J. Sun. 2016. “Deep residual learning for image recognition.” In Proc., 2016 IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 770–778. New York: IEEE.
Huang, J., et al. 2017. “Speed/accuracy trade-offs for modern convolutional object detectors.” In Proc., 2017 IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 3296–3305. New York: IEEE.
Hui, J. 2018. “Image segmentation with Mask R-CNN.” Accessed August 15, 2020. https://jonathan-hui.medium.com/image-segmentation-with-mask-r-cnn-ebe6d793272.
Ioffe, S., and C. Szegedy. 2015. “Batch normalization: Accelerating deep network training by reducing internal covariate shift.” Preprint, submitted February 11, 2015. https://arxiv.org/abs/1502.03167.
Kang, H., Z. Yi, and H. Burton. 2019. “Effect of the Los Angeles Soft-Story Ordinance on the post-earthquake housing recovery of impacted residential communities.” Nat. Hazard. 99 (1): 161–188. https://doi.org/10.1007/s11069-019-03734-w.
Kano, M., M. M. Wood, M. M. Kelley, and L. B. Bourque. 2009. “The study of household preparedness: Preparing California for earthquakes.” Accessed April 20, 2021. https://ssc.ca.gov/wp-content/uploads/sites/9/2020/08/cssc_09-03_the_study_of_household_preparedness.pdf.
Law, S., B. Paige, and C. Russell. 2019. “Take a look around: Using Street View and satellite images to estimate house prices.” ACM Trans. Intell. Syst. Technol. 10 (5): 1–19. https://doi.org/10.1145/3342240.
LeCun, Y., Y. Bengio, and G. Hinton. 2015. “Deep learning.” Nature 521 (7553): 436–444. https://doi.org/10.1038/nature14539.
Lin, T.-Y., M. Maire, S. Belongie, J. Hays, P. Perona, D. Ramanan, P. Dollár, and C. L. Zitnick. 2014. “Microsoft COCO: Common objects in context.” Preprint, submitted May 1, 2014. https://arxiv.org/abs/1405.0312.
Liu, X., Q. Chen, L. Zhu, Y. Xu, and L. Lin. 2017. “Place-centric visual urban perception with deep multi-instance regression.” In Proc., 2017 ACM on Multimedia Conf.—MM ’17, 19–27. New York: Association for Computing Machinery.
Naik, N., J. Philipoom, R. Raskar, and C. Hidalgo. 2014. “Streetscore—Predicting the perceived safety of one million streetscapes.” In Proc., 2014 IEEE Conf. on Computer Vision and Pattern Recognition Workshops, 793–799. New York: IEEE.
Simonyan, K., and A. Zisserman. 2014. “Very deep convolutional networks for large-scale image recognition.” Preprint, submitted September 4, 2014. https://arxiv.org/abs/1409.1556.
Szegedy, C., S. Ioffe, V. Vanhoucke, and A. A. Alemi. 2017. Inception v4, Inception-resnet and the impact of residual connections on learning, 4278–4284. Menlo Park, CA: Association for the Advancement of Artificial Intelligence.
Szegedy, C., W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, and A. Rabinovich. 2015. “Going deeper with convolutions.” In Proc., 2015 IEEE Conf. on Computer Vision and Pattern Recognition (CVPR). New York: IEEE.
Teddy, L., G. Hardiman, N. Nuroji, and S. Tudjono. 2018. “The soft story challenge to architectural design in earthquake-prone areas.” Jurnal Kejuruteraan 30 (2): 141–151. https://doi.org/10.17576/jkukm-2018-30(2)-03.
Tilio, L., B. Murgante, F. Di Trani, M. Vona, and A. Masi. 2011. “Resilient city and seismic risk: A spatial multicriteria approach.” Comput. Sci. Appl. 2011 (Jun): 410–422. https://doi.org/10.1007/978-3-642-21928-3_29.
US Resiliency Council. 2019. “Community resilience and the U.S. resiliency council’s building rating system.” Accessed August 20, 2019. http://www.usrc.org/.
Wu, Z. Y., M. Hmosze, and R. Kalfarisi. 2019. “Soft-story building detection using deep convolutional neural network for complying building resilience ordinance.” In Proc., ASCE Engineering Mechanics Institute Conf. 2019. Pasadena, CA: California Institute of Technology.
Yu, Q., C. Wang, F. McKenna, X. Y. Stella, E. Taciroglu, B. Cetiner, and K. H. Law. 2020. “Building information modeling and classification by visual learning at a city scale.” Preprint, submitted October 14, 2019. https://arxiv.org/abs/1910.06391.
Information & Authors
Information
Published In
Natural Hazards Review
Volume 23 • Issue 1 • February 2022
Copyright
© 2021 American Society of Civil Engineers.
History
Received: Nov 20, 2020
Accepted: Oct 27, 2021
Published online: Dec 11, 2021
Published in print: Feb 1, 2022
Discussion open until: May 11, 2022
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.
Cited by
- Jongwon Han, Jaejun Kim, Seongkyung Kim, Seunghyeon Wang, Effectiveness of Image Augmentation Techniques on Detection of Building Characteristics from Street View Images Using Deep Learning, Journal of Construction Engineering and Management, 10.1061/JCEMD4.COENG-15075, 150, 10, (2024).
- M K Evangelista, D H Aquino, J A Ramos, Utilizing Google Street View for Rapid Seismic Vulnerability Assessment: Case Study in the City of Manila, Philippines, IOP Conference Series: Earth and Environmental Science, 10.1088/1755-1315/1091/1/012037, 1091, 1, (012037), (2022).
- Chaofeng Wang, Sascha Hornauer, Stella X. Yu, Frank McKenna, Kincho H. Law, Instance segmentation of soft‐story buildings from street‐view images with semiautomatic annotation, Earthquake Engineering & Structural Dynamics, 10.1002/eqe.3805, (2022).