Building information extraction and earthquake damage prediction in an old urban area based on UAV oblique photogrammetry

Abstract Seismic performance investigation and earthquake damage prediction of buildings in old urban areas are of great significance for the resistance to earthquake risks. Building properties are fundamental to the regional earthquake damage prediction. However, the properties of buildings in old urban may be insufficient and outdated. In this paper, the following researches are carried out to address the above problems: based on tilt photogrammetry, the properties including the spatial characteristics of footprint outline, number of storeys, footprint area, roof style and distribution density, etc. are extracted; The typical buildings in the old urban area are further distinguished with the direct spatial features of house, and the age of house is predicted by machine learning; The house model parameters are determined based on the extracted building properties that determine the seismic performance, and the floor shear model is used to carry out elasto-plastic time history analysis to complete the earthquake damage prediction.