用建筑外观图预测日本房屋防火等级和建造年份，提升灾风险评估精度。
Estimation of Fireproof Structure Class and Construction Year for Disaster Risk Assessment
- 多任务学习模型从外墙图像同时预测建造年份、结构类型和房型
- 在真实数据集上对建造年份回归误差小，对三类防火等级分类准确率高
- 规则映射结合官方标准，适合保险、城市规划等需要可解释性评估的场景
建筑防火分类对日本灾害风险评估与保险定价至关重要。然而，二手房市场中关键建筑元数据（如建造年份、结构类型）常缺失或过时。本文提出一种多任务学习模型，仅通过建筑外观图像预测这些属性。模型联合估计建造年份、建筑结构与物业类型，并依据官方保险标准，通过规则映射推导出结构防火等级（H：非防火，T：半防火，M：防火）。研究基于大规模日本住宅图像数据集训练与评估，经过严格去重与过滤。模型在建造年份回归任务中表现优异，在类别不平衡条件下仍保持稳健分类性能。定性分析表明，模型能有效捕捉与建筑年龄及材料相关的视觉特征。本方法验证了可扩展、可解释的图像驱动风险评估系统的可行性，为保险、城市规划与防灾准备提供潜在应用路径。
原文摘要 · Abstract (English)
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 However, key building metadata such as construction year and structure type are often missing or outdated, particularly in the second-hand housing market.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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。