| 遥感分类方法在建筑物震害提取中的应用（以玉树地震为例） |
| |
| 引用本文： | 文翔,周斌,阎春恒.遥感分类方法在建筑物震害提取中的应用（以玉树地震为例）[J].地震地磁观测与研究,2014,35(5):134-143. |
| |
| 作者姓名： | 文翔 周斌 阎春恒 |
| |
| 作者单位： | 中国南宁530022 广西壮族自治区地震局 |
| |
| 基金项目： | 广西科技攻关计划12426001项目资助 |
| |
| 摘 要： | 建筑物损毁情况是地震灾害评估的一项重要指标,利用遥感技术快速提取震后建筑物震害信息,对科学指导地震应急救援工作具有重要意义.利用2010年4月14日青海玉树7.1级地震前后玉树县结古镇团结村高分辨率遥感影像,结合像素光谱和空间特性的纹理、结构等多源信息,基于支持向量机（SVM）方法,对地震前后建筑物信息进行分类提取,变化检测出建筑物损毁情况,并与面向对象多源信息复合的模糊分类法的分类精度、提取效率进行对比分析.研究结果表明,多源数据复合的SVM影像分类方法能够有效解决模糊分类影像破碎问题,地震前后两实相影像分类总精度达到77.53％和73.56％,提高了建筑物震害信息提取精度.
|
| 关 键 词： | 面向对象 模糊分类 SVM 变化检测 损毁建筑物 |
Building damage detection based on object-oriented classification method——a case study in Yushu earthquake |
| |
| Wen Xiang,Zhou Bin,Yan Chunheng.Building damage detection based on object-oriented classification method——a case study in Yushu earthquake[J].Seismological and Geomagnetic Observation and Research,2014,35(5):134-143. |
| |
| Authors: | Wen Xiang Zhou Bin Yan Chunheng |
| |
| Institution: | (Earthquake Administration of Guangxi Zhuang Autonomous Region, Nanning 530022, China) |
| |
| Abstract: | The collapse of building is a critical measurement on the earthquake hazard assessment. Using remote sensing technology to rapidly extracte earthquake building damages,and scien- tifically guiding earthquake emergency work has important significance. In this paper, it is illustrated how to extraete building integrality information with SVM method, using the re- mote sensing images of unity village before and after 7.1 earthquake in Yushu county, Qing- hal on April 14, 2010, and combining with multi-source data of pixel spectra and spatial fea- ture of texture and structure, then detect the building damages and compare the accuracy of image classification and the extracting efficiency based on fuzzy method with multi-source data. This shows that the image classification based on SVM method with multi-source data can solve the image classification fragmentation which is based on the fuzzy method. The total accuracy of classification reached 77.53 % and 73.56 % using the images of before and after earthquake. The method can improve the extracting accuracy of building damagein- formation. |
| |
| Keywords: | object-oriented the fuzzy classification support vector machine change detection damage buildings |
| 本文献已被 维普 万方数据 等数据库收录！ |
|
