Damage and Defects Assessment
COLLABORATIVE RESEARCH: MACHINE VISION ENHANCED POST EARTHQUAKE INSPECTION AND RAPID LOSS ESTIMATION
NSF Grant #1000700, PI: Reginald DesRoches, $360,032
This project combines infrastructure objects and damage recognition from video with structural engineering to enable quantitative assessments of buildings damaged by earthquakes. The purpose is to create the missing link between measured damage data and the condition of the building as a whole, so as to assist structural specialists in making an assessment decision grounded on measurements. The proposed automated procedure will classify component damage per the ATC-20 guidelines using empirically based models. Component damage will be compiled to determine the damage state of the building, recommend red, yellow, or green tagging of the building, and estimate repair time and cost. Building damage state, configuration and type will be used to query a set of fragility curves defining the likelihood of building collapse during an aftershock and, thereby, provide an improved understanding of risk. The validation of this work will be based on structural tests from NEESR and other sources. Leading student researcher: Stephanie German