Automated building classification framework using convolutional neural network

Abstract

Despite extensive study, performing Rapid visual screening is still a challenging task for many countries. The challenges include the lack of trained engineers, limited resources, and a large building inventory to detect. One of the most important aspect in rapid visual screening is to establish the building classification based on the guidelines’ specific criteria. This study proposes a general framework based on Convolutional Neural Network to perform automated building classification for the rapid visual screening procedure. The method classifies buildings based on the Federal Emergency Management Agency (FEMA)-154 guidelines and uses transfer learning techniques from a pre-trained network. The Indonesian building portfolio is used as a case study and a dataset of building images generated through web-scraping on Google Search™ engines and Google StreetView™ website is used for the method validation. Results show that the proposed framework has promising potential to automate the building classification based on FEMA-154 guidelines.

Keywords

• Building classification
• convolutional neural network
• transfer learning
• FEMA-154