城市环境与住宅建筑健康有何关联？一种用于建筑层面房屋检查的视觉与兴趣点融合框架
How Does Urban Context Relate to Residential Building Health? A Vision-POI Fusion Framework for Building-Level Housing Inspection
- School of Information Management, Qingdao University of Technology（青岛理工大学信息管理学院）
- Embodied AI & Robot Research Institute, Qingdao University of Technology（青岛理工大学具身人工智能与机器人研究所）
- College of Architecture and Urban Planning, Qingdao University of Technology（青岛理工大学建筑与城乡规划学院）
- Innovation Institute for Sustainable Maritime Architecture Research and Technology (iSMART), Qingdao University of Technology（青岛理工大学可持续海洋建筑研究与技术创新研究所）
- Department of Urban Planning and Design, Xi’an Jiaotong-Liverpool University（西交利物浦大学城市规划与设计系）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
研究探讨城市环境与住宅建筑健康的关联，提出视觉与兴趣点融合框架，通过多视图视觉检查与兴趣点邻里环境结合评估建筑健康。经实验，多视图聚合提升性能，兴趣点上下文补充信息，提高了建筑层面宏F1分数。
AI中文摘要：
房屋层面的城市体检对于识别住宅建筑问题和支持有针对性的城市更新至关重要。现有自动化检查研究主要依赖单个图像，很少研究周围城市功能环境能否为建筑层面评估提供补充信息。本研究提出了一种视觉与兴趣点融合框架，将多视图视觉检查与从兴趣点得出的邻里环境相结合，用于住宅建筑健康评估。实证数据集涵盖中国青岛的92个老旧住宅小区、3237栋住宅建筑和25608张实地采集的检查图像，包含七类与住房相关的问题。首先，评估多个目标检测模型以从单个图像中提取问题位置、类别和置信度分数，然后将图像层面的输出跨多个视图聚合以构建可解释的建筑层面表示。其次，在500米、1000米和1500米的邻里缓冲区中提取兴趣点特征以表征周围功能环境，使用皮尔逊和斯皮尔曼相关性分析并结合错误发现率校正来识别候选上下文特征。最后，在社区隔离空间交叉验证下，使用成本敏感随机森林分类器整合视觉和兴趣点特征。结果表明，多视图聚合带来了主要性能提升，将建筑层面的宏F1从直接检测下的60.84%提高到74.95%。纳入兴趣点上下文进一步将宏F1提高到76.79%，尽管额外增益不大且与类别相关。因此，兴趣点信息起到补充上下文先验的作用，而非直接视觉证据的替代品或建筑状况的因果决定因素。
英文摘要：
Housing-level urban physical examination is essential for identifying residential building problems and supporting targeted urban renewal. Existing automated inspection studies primarily rely on individual images and rarely examine whether surrounding urban functional context can provide supplementary information for building-level assessment. This study proposes a vision-POI fusion framework that combines multi-view visual inspection with POI-derived neighborhood context for residential building health assessment. The empirical dataset covers 92 old residential communities, 3,237 residential buildings, and 25,608 field-acquired inspection images in Qingdao, China, encompassing seven categories of housing-related issues. First, multiple object detection models are evaluated to extract issue locations, categories, and confidence scores from individual images. The image-level outputs are subsequently aggregated across multiple views to construct interpretable building-level representations. Second, POI features are extracted within 500m, 1,000m, and 1,500m neighborhood buffers to characterize surrounding functional environments. Pearson and Spearman correlation analyses, combined with false discovery rate correction, are used to identify candidate contextual features. Finally, visual and POI features are integrated using a cost-sensitive Random Forest classifier under community-isolated spatial cross-validation. The results show that multi-view aggregation provides the main performance improvement, increasing the building-level Macro-F1 from 60.84% under Direct Detection to 74.95%. Incorporating POI context further increases Macro-F1 to 76.79%, although the additional gain is modest and category-dependent. POI information therefore functions as a supplementary contextual prior rather than a substitute for direct visual evidence or a causal determinant of building condition.
