JSAI2025

Presentation information

Organized Session

Organized Session » OS-21

[2O5-OS-21b] OS-21

Wed. May 28, 2025 3:40 PM - 5:20 PM Room O (Room 1010)

オーガナイザ:橋本 武彦(GA technologies),清田 陽司(麗澤大学),山崎 俊彦(東京大学),諏訪 博彦(奈良先端科学技術大学院大学),清水 千弘(一橋大学),吉原 勝己(福岡ビルストック研究会)

3:40 PM - 4:00 PM

[2O5-OS-21b-01] Evaluation of building age prediction models using exterior images with deep learning

〇Hibiki Ayabe1, Kazushi Okamoto1, Atsushi Shibata2, Kei Harada1, Koki Karube1 (1. The University of Electro-Communications, 2. Advanced Institute of Industrial Technology)

Keywords:Building Age Prediction, Deep Learning, Image Recognition, Vision Transformer, Convolutional Neural Network

The age of real estate properties is used not only for property value estimation but also for assessing disaster risk.
However, obtaining accurate building age information remains challenging.
To address this issue, it is necessary to develop techniques for predicting building age using exterior images of real estate properties.
In this study, we aim to evaluate multiple deep learning architectures for such prediction.
Using approximately 9.5 million images from the LIFULL HOME'S dataset, we conducted experiments to analyze the prediction accuracy of five architectures, including, Vision Transformer (ViT), VGG16, and ResNet101\_V2.
In addition, we compared prediction accuracy across different regions.
Experimental results indicated that ViT achieved the best performance with a mean absolute error of 2.856, confirming its high accuracy and generalizability regardless of regional differences.

Authentication for paper PDF access
A password is required to view paper PDFs. If you are a registered participant, please log on the site from Participant Log In.
You could view the PDF with entering the PDF viewing password bellow.

Password