Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2510.22683 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914116092821504 |
|---|---|
| author | Ayabe, Hibiki Okamoto, Kazushi Karube, Koki Shibata, Atsushi Harada, Kei |
| author_facet | Ayabe, Hibiki Okamoto, Kazushi Karube, Koki Shibata, Atsushi Harada, Kei |
| contents | Structural fireproof classification is vital for disaster risk assessment and insurance pricing in Japan. However, key building metadata such as construction year and structure type are often missing or outdated, particularly in the second-hand housing market. This study proposes a multi-task learning model that predicts these attributes from facade images. The model jointly estimates the construction year, building structure, and property type, from which the structural fireproof class - defined as H (non-fireproof), T (semi-fireproof), or M (fireproof) - is derived via a rule-based mapping based on official insurance criteria. We trained and evaluated the model using a large-scale dataset of Japanese residential images, applying rigorous filtering and deduplication. The model achieved high accuracy in construction-year regression and robust classification across imbalanced categories. Qualitative analyses show that it captures visual cues related to building age and materials. Our approach demonstrates the feasibility of scalable, interpretable, image-based risk-profiling systems, offering potential applications in insurance, urban planning, and disaster preparedness. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_22683 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Estimation of Fireproof Structure Class and Construction Year for Disaster Risk Assessment Ayabe, Hibiki Okamoto, Kazushi Karube, Koki Shibata, Atsushi Harada, Kei Computer Vision and Pattern Recognition Structural fireproof classification is vital for disaster risk assessment and insurance pricing in Japan. However, key building metadata such as construction year and structure type are often missing or outdated, particularly in the second-hand housing market. This study proposes a multi-task learning model that predicts these attributes from facade images. The model jointly estimates the construction year, building structure, and property type, from which the structural fireproof class - defined as H (non-fireproof), T (semi-fireproof), or M (fireproof) - is derived via a rule-based mapping based on official insurance criteria. We trained and evaluated the model using a large-scale dataset of Japanese residential images, applying rigorous filtering and deduplication. The model achieved high accuracy in construction-year regression and robust classification across imbalanced categories. Qualitative analyses show that it captures visual cues related to building age and materials. Our approach demonstrates the feasibility of scalable, interpretable, image-based risk-profiling systems, offering potential applications in insurance, urban planning, and disaster preparedness. |
| title | Estimation of Fireproof Structure Class and Construction Year for Disaster Risk Assessment |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2510.22683 |