Skip to content

Latest commit

 

History

History
51 lines (31 loc) · 3.41 KB

README.md

File metadata and controls

51 lines (31 loc) · 3.41 KB

Automatic detection of building typology using deep learning methods on street level images

Description

This repository contains all supplementary data that were used in the paper:

"Automatic detection of building typology using deep learning methods on street level images"

Daniela Gonzalez1, Diego Rueda-Plata2, Ana B. Acevedo1, Juan C. Duque3, Raúl Ramos-Pollán4, Alejandro Betancourt3 and Sebastian García3

1 Department of Civil Engineering. Universidad EAFIT. Medellín, Colombia.

2 Universidad Industrial de Santander. Bucaramanga, Colombia.

3 Research in Spatial Economics (RiSE) Group. Universidad EAFIT. Medellín, Colombia.

4 Universidad de Antioquia. Medellín, Colombia.

maintainer = "RiSE Group" (http://www.rise-group.org/). Universidad EAFIT

Corresponding author = [email protected] (JCD)

Abstract

An exposure model is a key component for assessing potential human and economic losses from natural disasters. An exposure model consists of a spatially disaggregated description of the infrastructure and population of a region under study. Depending on the size of the settlement area, developing such models can be a costly and time-consuming task. In this paper we use a manually annotated dataset consisting of approximately 10,000 photos acquired at street level in the urban area of Medellín to explore the potential for using a convolutional neural network (CNN) to automatically detect building materials and types of lateral-load resisting systems, which are attributes that define a building’s structural typology (which is a key issue in exposure models for seismic risk assessment). The results of the developed model achieved a precision of 93% and a recall of 95% when identifying nonductile buildings, which are the buildings most likely to be damaged in an earthquake. Identifying fine-grained material typology is more difficult because many visual clues are physically hidden, but our model matches expert level performances, achieving a recall of 85% and accuracy scores ranging from 60% to 82% on the three most common building typologies, which account for 91% of the total building population in Medellín. Overall, this study shows that a CNN can make a substantial contribution to developing cost-effective exposure models.

License

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.

Bibtext entry

@article{gonzalez2020automatic,
    author = {Gonzales, D. AND Rueda-Plata, D. AND Acevedo, A. B. AND Duque, J. C. AND Ramos-Pollán, R. AND Betancur, A. AND García, S.},
    journal = {Building and Environment},
    publisher = {Elsevier},
    title = {Automatic detection of building typology using deep learning methods on street level images},
    year = {2020},
    month = {06},
    volume = {177},
    url = {https://www.sciencedirect.com/science/article/abs/pii/S0360132320301633},
    pages = {106805},
    doi = {https://doi.org/10.1016/j.buildenv.2020.106805}
}