Abstract An exposure model is a key component for assessing potential human and economic losses from natural disasters. An exposure model consists of a spatially disaggregated description of the infrastructure and population of a region under study. Depending on the size of the settlement area, developing such models can be a costly and time-consuming task. In this paper we use a manually annotated dataset consisting of approximately 10,000 photos acquired at street level in the urban area of Medellin to explore the potential for using a convolutional neural network (CNN) to automatically detect building materials and types of lateral-load resisting systems, which are attributes that define a building's structural typology (which is a key issue in exposure models for seismic risk assessment). The results of the developed model achieved a precision of 93% and a recall of 95% when identifying nonductile buildings, which are the buildings most likely to be damaged in an earthquake. Identifying fine-grained material typology is more difficult, because many visual clues are physically hidden, but our model matches expert level performances, achieving a recall of 85% and accuracy scores ranging from 60% to 82% on the three most common building typologies, which account for 91% of the total building population in Medellin. Overall, this study shows that a CNN can make a substantial contribution to developing cost-effective exposure models.

中文翻译：

---

使用深度学习方法在街道图像上自动检测建筑类型

摘要 暴露模型是评估自然灾害造成的潜在人类和经济损失的关键组成部分。暴露模型包括对所研究区域的基础设施和人口的空间分解描述。根据定居区的大小，开发此类模型可能是一项昂贵且耗时的任务。在本文中，我们使用手动注释的数据集，该数据集包含在麦德林市区的街道上采集的大约 10,000 张照片，以探索使用卷积神经网络 (CNN) 自动检测建筑材料和抗横向负载系统类型的潜力，这些属性定义了建筑物的结构类型（这是地震风险评估暴露模型中的一个关键问题）。所开发模型的结果在识别非延性建筑物时达到了 93% 的精度和 95% 的召回率，这是最有可能在地震中损坏的建筑物。识别细粒度的材料类型更加困难，因为许多视觉线索在物理上是隐藏的，但我们的模型符合专家级性能，在三种最常见的建筑类型上实现了 85% 的召回率和 60% 到 82% 的准确度得分，占麦德林总建筑人口的 91%。总的来说，这项研究表明，CNN 可以为开发具有成本效益的曝光模型做出重大贡献。因为许多视觉线索在物理上是隐藏的，但我们的模型达到了专家级的表现，在三种最常见的建筑类型上实现了 85% 的召回率和 60% 到 82% 的准确率，这三种建筑类型占总建筑人口的 91%在麦德林。总的来说，这项研究表明，CNN 可以为开发具有成本效益的曝光模型做出重大贡献。因为许多视觉线索在物理上是隐藏的，但我们的模型达到了专家级的表现，在三种最常见的建筑类型上实现了 85% 的召回率和 60% 到 82% 的准确率，这三种建筑类型占总建筑人口的 91%在麦德林。总的来说，这项研究表明，CNN 可以为开发具有成本效益的曝光模型做出重大贡献。