Rapid visual screening of soft-story buildings from street view images using deep learning classification
- PDF / 3,834,281 Bytes
- 12 Pages / 595.276 x 841.89 pts (A4) Page_size
- 76 Downloads / 234 Views
EARTHQUAKE ENGINEERING AND ENGINEERING VIBRATION
October, 2020
DOI: https://doi.org/10.1007/s11803-020-0598-2
Earthq Eng & Eng Vib (2020) 19: 827-838
Rapid visual screening of soft-story buildings from street view images using deep learning classification Qian Yu1†, Chaofeng Wang2†, Frank McKenna2‡, Stella X. Yu1§, Ertugrul Taciroglu3*, Barbaros Cetiner3† and Kincho H. Law4* 1. International Computer Science Institute, University of California, Berkeley, CA, USA 2. Department of Civil and Environmental Engineering, University of California, Berkeley, CA, USA 3. Civil and Environmental Engineering, University of California, Los Angeles, CA, USA 4. Civil and Environmental Engineering, Stanford University, CA, USA
Abstract:
Rapid and accurate identification of potential structural deficiencies is a crucial task in evaluating seismic vulnerability of large building inventories in a region. In the case of multi-story structures, abrupt vertical variations of story stiffness are known to significantly increase the likelihood of collapse during moderate or severe earthquakes. Identifying and retrofitting buildings with such irregularities—generally termed as soft-story buildings—is, therefore, vital in earthquake preparedness and loss mitigation efforts. Soft-story building identification through conventional means is a labor-intensive and time-consuming process. In this study, an automated procedure was devised based on deep learning techniques for identifying soft-story buildings from street-view images at a regional scale. A database containing a large number of building images and a semi-automated image labeling approach that effectively annotates new database entries was developed for developing the deep learning model. Extensive computational experiments were carried out to examine the effectiveness of the proposed procedure, and to gain insights into automated soft-story building identification.
Keywords: soft-story building; deep learning; CNN; rapid visual screening; street view image
1 Introduction Soft-story (SS) buildings are a common archetype that have distinct visual characteristics, such as having a large opening on the ground floor, e.g., a garage (One key criterion of defining a soft-story building is the stiffness of the ground floor relative to that of the floors above. In appearance, a soft-story building typically has an open space such as a garage on the ground floor). Such ample opening space can make a ground floor not as stiff as the higher floors, leading to the name ‘soft-story’. Consequently, an SS building is vulnerable to a moderate or severe earthquake (see Fig. 1). Take Los Angeles for example, in the 1994 Northridge earthquake, where twothirds of the approximately 49,000 destroyed or damaged apartment units were SS buildings (https://la.curbed. com/2018/1/17/16871368/earthquake-apartments-safenorthridge). Since the west coast of the United States is situated along the belt of high seismicity, residents and Correspondence to: Chaofeng Wang, Department of Civil and Environmental Eng
Data Loading...
