Li Qiang, Zhang Jingfa, Jiang Hongbo
National Institute of Natural Hazards, Ministry of Emergency, Beijing, No. 1 Anning Zhuang Road, Xisanqi, Haidian District, 100085, China.
Heliyon. 2024 Jun 12;10(12):e32851. doi: 10.1016/j.heliyon.2024.e32851. eCollection 2024 Jun 30.
After an earthquake, efficiently and accurately acquiring information about damaged buildings can help reduce casualties. Earth observation data have been widely used to map affected areas after earthquakes. However, fine post-earthquake assessment results are needed to manage recovery and reconstruction and to estimate economic losses. In this paper, for quantification and precision purposes, a method of earthquake-induced building damage information extraction incorporating multi-source remote sensing data is proposed. The method consists of three steps： (1) Analysis of multisource features that describe texture, colour, and geometry, (2) rough set theory is carried out to further determine the feature parameters, (3) Logistic regression model (LRM) was built to describe the relationship between the occurrence and absence of destroyed buildings within an individual object. Old Beichuan County (centered at approximately 31.833︒N, 104.459° E), China, the area most devastated by the Wenchuan earthquake on May 12, 2008, is used to test the proposed hypothesis. Multi-source remote sensing imagery include optical data, synthetic aperture radar (SAR) data, and digital surface model (DSM) data generated by interpolating light detection and ranging (LiDAR) point cloud data. Through comparison with the ground survey, the experimental results show that the detection accuracy of the proposed method is 94.2 %; the area under the receiver operating characteristic (ROC) curve is 0.827. The efficiency of the proposed method is demonstrated using 6 modes of data combination acquired from the same area in old Beichuan County. The approach is one of the first attempts to extract damaged buildings through the fusion of three types of data with different features. The approach addresses multivariate regression methodologies and compares the potential of features for application in the damage detection field.
地震发生后，高效、准确地获取受损建筑物信息有助于减少人员伤亡。地球观测数据已被广泛用于绘制地震后的受灾区域。然而，灾后精细评估结果对于管理恢复和重建以及估算经济损失是必要的。本文为了进行量化和提高精度，提出了一种结合多源遥感数据的地震诱发建筑物损伤信息提取方法。该方法包括三个步骤：（1）分析描述纹理、颜色和几何形状的多源特征；（2）运用粗糙集理论进一步确定特征参数；（3）建立逻辑回归模型（LRM）来描述单个对象内受损建筑物的存在与缺失之间的关系。以中国旧北川县（中心位置约为北纬31.833°，东经104.459°）为例，该地区在2008年5月12日汶川地震中受灾最为严重，用于检验所提出的假设。多源遥感影像包括光学数据、合成孔径雷达（SAR）数据以及通过对光探测和测距（LiDAR）点云数据进行插值生成的数字表面模型（DSM）数据。通过与地面调查结果进行比较，实验结果表明所提方法的检测准确率为94.2%；接收者操作特征（ROC）曲线下的面积为0.827。利用从旧北川县同一区域获取的6种数据组合模式证明了所提方法的有效性。该方法是通过融合三种具有不同特征的数据来提取受损建筑物的首批尝试之一。该方法涉及多元回归方法，并比较了各特征在损伤检测领域的应用潜力。
