Extraction of earthquake damage buildings from multi-source remote sensing data based on correlation change detection and object-oriented classification techniques
-
摘要: 遥感图像面向对象分类作为空间信息提取的关键技术， 在震害信息提取方面发挥着非常重要的作用， 然而由于光学遥感影像是正射图像， 只能提取建筑物屋顶信息， 这使得单一利用震后光学影像进行震害信息提取存在一定的局限性. 针对该问题， 本文提出了一种基于合成孔径雷达(SAR)相关变化检测的光学影像震害建筑物面向对象提取方法， 即在光学影像面向对象提取的数据中融合SAR相关性， 对光学影像进行面向对象提取震害建筑物时不仅考虑建筑物的几何、 光谱等特征， 还加入震前震后变化信息即SAR相关性进行分类. 在此基础上， 选取2008年汶川MS8.0地震震区都江堰地区作为研究区进行试验. 结果表明， 本文提出的方法相对于单一使用光学影像进行震害建筑物提取, 其准确度有较明显的提高.Abstract: Object-oriented classification technology of remote sensing images, as a spatial information extraction method, plays a key role in earthquake damage information extraction. However, it has limitations in extracting buildings from optical remote sensing images due to the characteristic vulnerable to weather and other reasons. To solve this problem, this paper proposes a method for detecting building damage by optical image in combiniation with SAR correlation changes and object-oriented classification, which extracts buildings from fusion data including optical image and SAR correlation image. Not only the spatial and spectral features, but also the correlation of buildings is considered during the extraction. The MS8.0 Wenchuan earthquake caused a wide range of building’s collapse and casualties. Taking Dujiangyan area near the source as an example, the method above is tested. The results show that the accuracy of building extraction is improved by using the proposed method compared with the method only from optical image.
-
-
![]()
图 1 研究区IKONOS卫星光学影像图(a)和现场调查矢量图(叠加光学影像)(b)
Figure 1. IKONOS image (a) and field survey map (b) of the studied area
![]()
图 2 研究区震前(a)、 震后(b)SAR影像． 红色实线范围表示本文研究区
Figure 2. Pre-seismic (a) and post-seismic (b) SAR image of the studied area delineated by red solid lines
![]()
图 4 震后光学影像面向对象震害建筑物分类图
Figure 4. Object-oriented classification image of earthquake damaged buildings based on post-seismic IKONOS image
![]()
图 5 SAR图像相关图
Figure 5. Correlation image calculated from pre- and post-seismic SAR images
![]()
图 6 结合SAR相关性变化检测的光学影像面向对象震害信息提取流程图
Figure 6. Flow chart of earthquake damage buildings extraction from multi-source remote sensing data by using correlation change detection and object-oriented classification techniques
![]()
图 7 结合SAR相关性变化检测的光学影像面向对象震害建筑物分类图
Figure 7. Extraction of earthquake damaged buildings based on object-oriented classification map of IKONOS and SAR correlation fusion image
表 1 研究区SAR图像列表
Table 1 SAR images list of the studied area
编号 传感器 波段 成像时间 备注 1 ENVISAT ASAR C 2008-03-03 地震前 2 ENVISAT ASAR C 2008-07-21 地震后 
下载: 导出CSV
表 2 面向对象分类参数及阈值
Table 2 Parameters and thresholds of object-oriented classification
震害建筑物类型 光谱均值 延伸率 矩形拟合度 面积/m2 红波段 绿波段 蓝波段 基本完好建筑物 <160 >60 [2.8, 5] >0.47 [40, 1100] 中等破坏建筑物 <127.98 <60 [1, 2.8] [0.35, 0.47] [100, 500] 损毁建筑物 >160 <2.75 [0.26, 0.35] [100, 800]
下载: 导出CSV
表 3 震后光学影像面向对象震害建筑物分类准确度
Table 3 Classification accuracy of earthquake damaged building from post-seismic IKONOS image using object-oriented technique
震害类型 提取准确率 漏检率 错检率 基本完好建筑物 78.4% 21.6% 14.8% 中等破坏建筑物 64.8% 35.2% 62.3% 损毁建筑物 73.7% 26.3% 42.7% 总体 72.34%
下载: 导出CSV
表 4 结合SAR相关性变化检测的光学影像面向对象震害建筑物分类准确度
Table 4 Classification accuracy of earthquake damaged buildings from multi-source remote sensing data by using correlation change detection and object- oriented classification technique
震害类型 提取准确率 漏检率 错检率 基本完好建筑物 82.1% 17.9% 12.2% 中等破坏建筑物 77.3% 22.7% 43.6% 损毁建筑物 79.2% 20.8% 21.9% 总体 81.3%
下载: 导出CSV
-
赵福军. 2010. 遥感影像震害信息提取技术研究[D]. 哈尔滨: 中国地震局工程力学研究所: 113-114. Zhao F J. 2010. Seismic Disaster Information Extraction From Riotely Sensed Imagery[D]. Harbin: Institute of Engineering Mechanics, China Earthquake Administration: 113-114 (in Chinese).
Chesnel A L, Binet R, Wald L. 2007. Object oriented assessment of damage due to natural disaster using very high resolution images[C]//IEEE International Geoscience and Riote Sensing Symposium, IGARSS 2007. Barcelona: IEEE： 3736-3739.
Vu T T, Matsuoka M, Yamazaki F. 2005. Preliminary results in development of an object-based image analysis method for earthquake damage assessment[C]//Proceeding of International Workshop on Riote Sensing for Postdisaster Response. Chiba： Chiba University: 1-8.
计量
- 文章访问数: 701
- HTML全文浏览量: 258
- PDF下载量: 14
