Building Recognition using AI at Large-Scale¶
What is BRAILS¶
The SimCenter tool - Building Recognition using AI at Large-Scale (BRAILS) is an AI-enabled software to assist regional-scale simulations. BRAILS utilizes machine learning (ML), deep learning (DL), and computer vision (CV) to extract information from satellite and street view images for being used in computational modeling and risk assessment of the built environment. It also provides the architecture, engineering, and construction professionals the insight and tools to more efficiently plan, design, construct, and manage buildings and infrastructure systems.
The released v2.0 is re-structured with modules for performing specific analyses of images. The expanded module library enables BRAILS’ capability of predicting a larger spectrum of building attributes including occupancy class, roof type, foundation elevation, year built, soft-story.
The new release also features a streamlined workflow, CityBuilder, for automatic creation of regional-scale building inventories by fusing multiple sources of data, including OpenStreetMap, Microsoft Footprint Data, Google Maps, and extracting information from them using the modules.
Examples of its application in natural hazard engineering include: The identification of roof shapes and foundation elevation to improve the damage and loss calculations for the hurricane workflow; The identification of soft-story buildings to improve models in earthquake workflows.
How to cite¶
Charles Wang, Qian Yu, Frank McKenna, Barbaros Cetiner, Stella X. Yu, Ertugrul Taciroglu & Kincho H. Law. (2019, October 11). NHERI-SimCenter/BRAILS: v1.0.1 (Version v1.0.1). Zenodo. http://doi.org/10.5281/zenodo.3483208
Benjamin Bischke, Patrick Helber, Joachim Folz, Damian Borth, and Andreas Dengel. Multi-task learning for segmentation of building footprints with deep neural networks. 2019 IEEE International Conference on Image Processing (ICIP), pages 1480–1484, 2019.
Pierre Goovaerts. Geostatistics for natural resources evaluation. Oxford University Press on Demand, 1997.
Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, 770–778. 2016.
David H Hubel and Torsten N Wiesel. Receptive fields and functional architecture of monkey striate cortex. The Journal of physiology, 195(1):215–243, 1968.
Weijia Li, Conghui He, Jiarui Fang, Juepeng Zheng, Haohuan Fu, and Le Yu. Semantic segmentation-based building footprint extraction using very high-resolution satellite images and multi-source gis data. Remote Sensing, 11(4):403, 2019.
Microsoft. US Building Footprints. URL: https://github.com/microsoft/USBuildingFootprints.
Christian Szegedy, Vincent Vanhoucke, Sergey Ioffe, Jon Shlens, and Zbigniew Wojna. Rethinking the inception architecture for computer vision. Proceedings of the IEEE conference on computer vision and pattern recognition, pages 2818–2826, 2016.
Erik Vanmarcke. Random fields: analysis and synthesis. World Scientific, 2010.
C Wang and Q Chen. A hybrid geotechnical and geological data-based framework for multiscale regional liquefaction hazard mapping. Géotechnique, 68(7):614–625, 2018.
Chaofeng Wang, Qiushi Chen, Mengfen Shen, and C Hsein Juang. On the spatial variability of cpt-based geotechnical parameters for regional liquefaction evaluation. Soil Dynamics and Earthquake Engineering, 95:153–166, 2017.
Charles Wang, Qian Yu, Frank McKenna, Barbaros Cetiner, Stella X. Yu, Ertugrul Taciroglu, and Kincho H. Law. Nheri-simcenter/brails: v1.0.1. October 2019. URL: https://doi.org/10.5281/zenodo.3483208, doi:10.5281/zenodo.3483208.
Kang Zhao, Jungwon Kang, Jaewook Jung, and Gunho Sohn. Building extraction from satellite images using mask r-cnn with building boundary regularization. CVPR Workshops, pages 247–251, 2018.