Deep Learning–Based Building Attribute Estimation from Google Street View Images for Flood Risk Assessment Using Feature Fusion and Task Relation Encoding
Open Access
- 1 November 2022
- journal article
- research article
- Published by American Society of Civil Engineers (ASCE) in Journal of Computing in Civil Engineering
- Vol. 36 (6) , 04022031
Abstract
Floods are the most common and damaging natural disaster worldwide in terms of both economic losses and human casualties. Currently, policymakers rely on data collected through labor-intensive and, consequently, expensive street-level surveys to assess flood risks. We propose a laborless and financially feasible alternative: a framework that can effectively and efficiently collect building attribute data without manual street surveys. By utilizing deep learning, the proposed framework analyzes Google Street View (GSV) images to estimate multiple attributes of buildings simultaneously—including foundation height, foundation type, building type, and number of stories—that are necessary for assessing flood risks. The proposed framework achieves a 0.177-m mean absolute error (MAE) for foundation height estimation and classification F1 scores of 77.96% for foundation type, 83.12% for building type, and 94.60% for building stories, and requires less than five days to predict the attributes of 0.8 million buildings in coastal Louisiana.Keywords
This publication has 69 references indexed in Scilit:
- Future flood losses in major coastal citiesNature Climate Change, 2013
- Estimating Surge-Based Flood Risk with the Coastal Louisiana Risk Assessment ModelJournal of Coastal Research, 2013
- Perception and Communication of Flood Risks: A Systematic Review of Empirical ResearchRisk Analysis, 2012
- Using Google Street View to Audit Neighborhood EnvironmentsAmerican Journal of Preventive Medicine, 2011
- A revised (PTVA) model for assessing the vulnerability of buildings to tsunami damageNatural Hazards and Earth System Sciences, 2009
- Episodic flooding and the cost of sea-level riseEcological Economics, 2007
- Can We Detect Trends in Extreme Tropical Cyclones?Science, 2006
- HAZUS-MH Flood Loss Estimation Methodology. II. Damage and Loss AssessmentNatural Hazards Review, 2006
- Increasing destructiveness of tropical cyclones over the past 30 yearsNature, 2005
- Estimating flood probabilities within specific time intervalsJournal of Hydrology, 1963