Use of Deep Learning Models in Street Level Images to Classify One-Story Unreinforced Masonry Buildings Based on Roof Diaphragm

Description

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

"Use of Deep Learning Models in Street Level Images to Classify One-Story Unreinforced Masonry Buildings Based on Roof Diaphragm"

Diego Rueda-Plata¹, Daniela Gonzalez², Ana B. Acevedo², Juan C. Duque³, Raúl Ramos-Pollán⁴

¹ Universidad Industrial de Santander. Bucaramanga, Colombia.

² Department of Civil Engineering. Universidad EAFIT. Medellín, 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

In this paper we explore the potential of convolutional neural networks to classify street-level imagery of one-story unreinforced masonry (MUR) buildings according to the flexibility (rigid or flexible) of the roof diaphragm, aiming to provide a better understanding of the vulnerability of such building typology}. This information is a relevant input for vulnerability studies, disaster risk assessments, disaster management strategies, etc. and is of great importance in those cities where non-reinforced masonry structures is the most common building typology or where the majority of the population resides on such buildings. Our methodological contribution could be very useful for local governments of cities in developing countries working towards progress in SDG 11 that seeks to make cities more sustainable and safe, as well as significantly reducing the number of deaths caused by disasters. Vgg19 was the architecture with best results with an accuracy of 0.80, a precision of 0.88, and a recall of 0.84. The results are encouraging and could be used to reduce the amount of resources (human and economic) for the development of detail exposure models for unreinforced masonry buildings.

License

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

Bibtext entry

@article{XX,
    author = {Rueda-Plata, D. AND Gonzalez, D. AND  AND Acevedo, A. B. AND Duque, J. C. AND Ramos-Pollán, R. },
    journal = {},
    publisher = {},
    title = {Use of Deep Learning Models in Street Level Images to Classify One-Story Unreinforced Masonry Buildings Based on Roof Diaphragm},
    year = {2020},
    month = {mm},
    volume = {vv},
    url = {xx},
    pages = {},
    abstract = {},
    number = {nn},
    doi = {xx}
}