基于机载LiDAR和多光谱图像的建筑物震害自动识别方法

地震破坏的建筑物在遥感影像上和空间上表现出的特征各异,致使遥感定量化估计其破坏程度较困难.本文介绍了基于LiDAR和多光谱影像相结合的多源遥感影像进行倒塌建筑物的面向对象识别的方法、分析处理步骤和特征参数选择,并以2010年1月12日海地地震后的太子港局部LiDAR数据和高分辨率卫星影像为例,提取了倒塌和未倒塌建筑物,经与高分影像目视解译结果比较,面向对象分类结果具有较高的分类精度.     

基于监督分类的震后高分辨率影像倒塌房屋快速识别

针对监督分类中样本设计与选取、关键特征提取两个关键环节,设计了多种不同样本提取方法和多种典型特征参数组合,对海地震后高分辨率影像倒塌房屋快速提取进行分析研究。结果表明,以倒塌样本与屋角样本作为训练样本,以灰度均值和灰度共生矩阵逆差矩作为参数组合,能够保证较好提取精度的同时,最大限度减少人工样本选取工作量,提高倒塌房屋快速提取效率。最后以该分类方法对玉树震后高分辨率影像的倒塌房屋进行自动识别,识别结果良好,进一步检验了该分类方法的有效性。     

基于多纹理特征融合的震后SAR图像倒塌建筑物信息提取

合成孔径雷达（SAR）凭借其全天候观测能力以及SAR图像中丰富的纹理信息,在震后建筑物倒塌评估中发挥了重要作用。针对SAR图像中倒塌建筑物纹理特征多样但利用率较低,且特征信息冗余的问题,提出一种基于主成分分析的SAR图像多纹理特征分类方法。该方法基于灰度直方图、灰度共生矩阵、局部二值模式、Gabor滤波器提取了26种纹理特征信息,构建主成分变量进行多维特征优选与降维融合,通过随机森林分类算法提取建筑物的倒塌信息。以2016年日本熊本地震为例验证了该方法的有效性,结果显示其提取精度高达79.85%,倒塌建筑物的识别效率有所提高,分类结果优于单种纹理特征提取方法及多种纹理特征组合提取法,可用于震后建筑物震害信息的快速提取。     

结合PolSAR影像纹理特征分析提取倒塌建筑物

利用震后1景极化SAR影像提取倒塌建筑物是一种快速有效的灾害调查手段。倒塌建筑和倾斜建筑物在PolSAR影像中的散射特征相似,易造成建筑物倒塌率的过度评估。由于倒塌建筑和倾斜建筑的纹理特征有较大差异,将利用这种纹理差异来解决倒塌建筑和倾斜建筑的混分问题。通过实验发现均值、同质性、熵及相关性4种基于灰度共生矩阵(Gray-Level Co-occurrence Matrix,GLCM)的纹理特征能够有效区分倾斜建筑和倒塌建筑,故利用这4种纹理特征提取倒塌建筑中混杂的倾斜建筑,从而降低倒塌建筑的虚警率。以玉树地震为例,提取城区的建筑物震害信息,实验证明该方法能够大幅提高建筑物震害评估精度。     

利用格式塔的高分辨率遥感影像建筑物提取

目的 格式塔心理学的理论基础为通过对事物的部分感知,实现对事物整体的认识。本文将该思想应用到建筑物提取中,提出一种兼顾目标细节及整体几何特征的高分辨率遥感影像建筑物提取方法。方法 首先,利用SIFT算法提取特征点作为候选边缘点;然后定义格式塔序列连续性原则判别边缘点,从而得到边缘点点集;并由边缘点点集拟合边缘,实现遥感影像建筑物提取。结果 利用提出算法,对WorldView-2遥感影像进行建筑物提取实验。通过与基于多尺度分割和区域合并的建筑物提取算法对比可以看出,提出算法能够更加准确、完整地提取出建筑物。采用分支因子、遗漏因子、检测率和完整性4个定量化指标对实验结果的定量评价,本文算法的检测率和完整性均大于对比算法,且本文算法的检测率均在95%以上,验证了提出基于格式塔理论的高分辨率遥感影像建筑物提取算法的有效性和准确性。结论 基于格式塔的高分辨率遥感影像建筑物提取算法能够准确刻画建筑物细节特征,同时兼顾建筑物整体几何轮廓,准确提取高分辨率遥感影像中的建筑物。本文算法针对高分辨率遥感影像,适用于提取边缘具有直线特征的建筑物。使用本文算法进行遥感影像建筑物提取时,提取精度会随分辨率降低而降低,建议实验影像分辨率在5 m以上。     

最优尺度下的面向对象建筑物提取北大核心CSCD

针对基于面向对象方法提取建筑物准确度与精度不高的问题,提出了一种面积方差最优尺度分割法。该方法利用SPOT 5卫星遥感影像,根据建筑物特征对影像进行多尺度分割,以所有类别分割对象与实际目标匹配程度作为衡量的依据获得最优尺度。在不同尺度等级的对象层次上,根据对象的多特征组合,完成对建筑物分层分类提取。实验结果表明,该方法大大减少了分类的不确定性,获取了较高的精度,为建筑物准确提取提供了思路。     

基于深度学习的村镇砖(混)木房屋识别

破坏性地震发生后, 相较按照抗震设防标准建设的城市公共设施和居民住宅, 广大无抗震设防的村镇居民自建房屋, 更易发生倒塌甚至完全损毁. 以往地震灾情预评估、地震灾害风险调查、地震重点危险区调研, 依靠专家现场踏勘, 确定不同结构类型建筑物数量及所占比例. 本研究借助深度学习和倾斜摄影技术, 进行砖(混)木结构房屋识别, 郯庐断裂带山东境内砖(混)木房屋影像制作数据集, 训练得到Faster R-CNN模型, 该区域内砖(混)木房屋识别平均精度为91.868%. 结果表明, 本文方法能够对砖(混)木房屋进行有效检测, 可应用于地震行业开展震前、震后各类现场工作, 提高政府部门应急管理能力.     

城市规则建筑物阴影去噪

针对建筑物阴影提取受同物异谱和异物同谱特点的噪声干扰较大这一问题,提出一种结合几何特征和语义特征约束条件去噪的城市规则建筑物阴影提取方法。首先,针对阴影在HIS色彩模型中低亮度、高色调和高饱和度的特性,采用归一化阴影指数进行初步阴影检测,并与经过过绿指数变换后的图像做差值运算去除偏蓝色地物的干扰,然后根据建筑物阴影特征采用4种几何指数和阴影方向进行去噪处理。分别选取高分辨率卫星影像和航空影像进行实验,结果表明,该方法对于城市规则建筑物阴影提取具有较高的精度,并且结果边界完整,无破碎图斑。     

基于多特征结合的损毁建筑物检测

针对震后高分辨率遥感图像的建筑物损毁区域,提出一种基于多特征结合的损毁建筑物检测方法。首先使用形态学属性剖面(MAP)与局部二值模式(LBP)算子提取图像中的几何特征与纹理特征;然后使用随机森林(RF)分类器提取损毁的建筑物,形成初步结果;最后针对分割的对象,根据对象损毁像元所占的比例获取最终的损毁建筑物区域。采用空间分辨率为0.1 m的玉树震后航空遥感图像进行实验。结果表明,该方法的总体精度比基于形态学剖面(MP)的方法提高了12%,能够有效检测高分辨率震后遥感图像中的损毁建筑物区域。     

场景解译框架下的高铁沿线建筑物自动识别

针对传统建筑物提取方法中图像高层语义和低层视觉特征之间存在的语义鸿沟问题,提出一种基于卷积神经网络模型场景解译框架下的高铁沿线建筑物隐患区域自动识别方法。该方法首先将遥感影像重叠地划分成一系列的影像块,生成卷积神经网络模型输入的基本单元;然后,根据训练样本集,学习获得模型参数,并预测每个待解译影像块内各地物类别的概率分布;最后,原始影像中每个像素的地物类别由所有覆盖该像素影像块的场景类别所共同确定,继而将获得的多分类图转化为二值分类图,实现建筑物区域的自动识别。2 675×6 465的大场景高铁沿线遥感影像下开展的实验结果表明,该方法建筑物提取精度明显优于传统分类方法,提取结果的紧凑性和平滑性得到显著提升,与地表真实值吻合度较高。     

Extraction of earthquake-induced collapsed buildings using very high-resolution imagery and airborne lidar data

Extraction of urban building damage caused by earthquake disasters, from very-high-resolution (VHR) satellite imagery and related geospatial data, has been widely studied in the past decade. In this study, a multi-stage collapsed building detection method, using bi-temporal (pre- and post-earthquake) VHR images and post-earthquake airborne light detection and ranging (lidar) data, is proposed. Ground objects that are intact and significantly different from collapsed buildings, such as intact buildings, pavements, shadows, and vegetation, were first extracted using the post-event VHR image and lidar data and masked out. Collapsed buildings were then extracted by classifying the combined bi-temporal VHR images and texture images of the remaining area using a one-class classifier, the One-Class Support Vector Machine (OCSVM). A post-processing procedure was adopted to refine the obtained result. The proposed method was quantitatively evaluated and compared to two existing methods in Port au Prince, Haiti, which was heavily hit by an earthquake in January 2010. In the two comparative methods, data for the whole study area were directly used. In the first method, collapsed buildings were extracted directly using the OCSVM, while in the second method, buildings and pavements were removed from the extraction result of the first method. The results showed that the proposed method significantly outperformed the existing methods, with increases of 21% and 40%, respectively, in the kappa coefficient. The proposed method provides a fast and reliable method to detect collapsed urban buildings caused by earthquake disasters, and could also be applied to other study areas using similar data combinations.     

Enhancing integrated earthquake simulation with high performance computing

Integrated earthquake simulation (IES) is a seamless simulation of the three earthquake processes, namely, the earthquake hazard process, the earthquake disaster process and the anti-disaster action process. High performance computing (HPC) is essential if IES, or particularly, the simulation of the earthquake disaster process is applied to an urban area in which 10^4∼6 structures are located. IES is enhanced with parallel computation, and its performance is examined, so that virtual earthquake disaster simulation will be made for a model of an actual city by inputting observed strong ground motion. It is shown that parallel IES has fairly good scalability even when advanced non-linear seismic structure analysis is used.     

基于多源地震空间数据信息系统集成研究

将基于多源地震空间数据思想应用在地震灾害信息系统集成的主要功能及系统结构中,并就建立多源地震空间数据信息系统集成做了初步探讨,详细论述了多源地震空间信息集成系统的构建方案。该集成系统融合了各个地震子课题的研究成果与各自的优点,这对于全面掌握一定范围内可能的地震灾害分布,预测和预报可能的地震灾害,快速及时的对地震灾害进行防护和处理,最终保障社会的安全有着极为重要的作用。     

基于Agent的防震减灾IDSS的研究与设计

针对传统防震减灾系统的不足,引入Agent技术构造了一个基于多Agent的防震减灾智能决策支持系统。首先构建了系统的基本结构,然后根据系统的不同功能需要对所使用的各个Agent进行设计,最后分析了各Agent之间的协作关系,构建系统的协作关系模型并完成整个系统的设计。系统中的Agent按照Goal、Plan、Belief和Action四个部分进行架构,Agent之间的复杂协作关系采用对相关Agent进行分组控制的方法来实现。     

灾情数据自动获取的地震灾情信息系统

为了及时掌握地震规模、空间分布、次生灾害,以及灾情发展趋势等灾情信息,将地震灾情数据采集装置与地震灾情数据管理系统相结合,建立了一种基于灾情数据自动获取的地震灾情信息系统.地震灾情数据采集装置配有多个信息采集单元,能够在感震器的触发下自动采集与上传地震灾情数据.而灾情数据管理系统基于三层体系结构的开发模型构建,提高了数据管理系统的响应速度和事件处理能力.系统集成实验表明,地震灾情信息系统能够独立完成地震灾情数据的自动采集、集中管理与应用共享.     

Does non‐destructive earthquake experience affect risk perception and motivate preparedness?

There are thousands of earthquakes every year, but most of them are small and are not disasters. This study explored whether non‐destructive earthquake experience affects public risk perception and motivates preparedness. The study respondents were from the Jiaodong Peninsula, China, where more than 20 small earthquakes have occurred during the past decade. The results show that non‐destructive earthquake experience positively affected public perception of the probability of an earthquake but not the perception of consequences. The relationship between non‐destructive earthquake experience and preparedness intention was not statistically significant. In addition, this study revealed that the perception of consequences was a positive predictor of earthquake preparedness intention, that is people with higher levels of perceived consequences of an earthquake were more likely to be motivated to prepare. However, non‐destructive earthquake experience moderated this relationship, that is weakened the strength of this relationship between perceived consequences and skill preparedness intention. These findings permit the identification of potential pathways to increase levels of disaster preparedness and potential barriers to enhancing disaster resilience in regions experiencing small hazards.     

Detection of collapsed buildings caused by the 1999 Izmit,Turkey earthquake through digital analysis of post-event aerial photographs

In this study, the post-earthquake aerial photographs were digitally processed and analysed to detect collapsed buildings caused by the Izmit, Turkey earthquake of 17 August 1999. The selected area of study encloses part of the city of Golcuk, which is one of the urban areas most strongly hit by the earthquake. The analysis relies on the idea that if a building is collapsed, then it will not have corresponding shadows. The boundaries of the buildings were available and stored in a Geographical Information System (GIS) as vector polygons. The vector building polygons were used to match the shadow casting edges of the buildings with their corresponding shadows and to perform analyses in a building-specific manner. The shadow edges of the buildings were detected through a Prewitt edge detection algorithm. For each building, the agreement was then measured between the shadow producing edges of the building polygons and the thresholded edge image based on the percentage of shadow edge pixels. If the computed percentage value was below a preset threshold then the building being assessed was declared as collapsed. Of the 80 collapsed buildings, 74 were detected correctly, providing 92.50% producer's accuracy. The overall accuracy was computed as 96.15%. The results show that the detection of the collapsed buildings through digital analysis of post-earthquake aerial photographs based on shadow information is quite encouraging. It is also demonstrated that determining the optimum threshold value for separating the collapsed from uncollapsed buildings is important.