Building façade datasets for analyzing building characteristics using deep learning

Abstract

Building characteristics are vital across various domains such as construction management and architectural design. Static Street View Images (SSVIs) can be utilized with deep learning techniques to interpret building characteristics without the need for a physical visit. Deep learning approaches have demonstrated a high capability for generalization, enabling the automation of manual tasks related to image analysis. However, there is no publicly available labeled dataset of building characteristics from building facade images for training deep learning models. In this article, we focus on constructing a dataset for four different tasks: classification of the number of stories, classification of building typologies, classification of exterior cladding materials, and classification of usable SSVIs. To develop deep learning models, this article constructed a dataset sourced from London and Scotland in the UK. The dataset was labeled by annotation experts. While the focus of this research is on specific tasks, the raw dataset can be used for other purposes (e.g., ascertaining the age of buildings or identifying window types) by annotating the data for the corresponding tasks.