A method of combined texture features and morphology for building seismic damage information extractionbased on GF remote sensing images
-
摘要: 为提高震害信息获取时效性，对基于我国国产高分遥感影像的建筑物震害信息提取方法进行深入研究，本文以2017年5月11日新疆塔县MS5.5地震为例，利用该地震前后极灾区高分遥感影像，利用结合纹理和形态学特征的方法进行了建筑物震害信息提取，通过变化检测分析获取了极灾区建筑物震害信息，并与基于像元级和基于目标级的信息提取结果进行对比，采用震后无人机影像目视解译结果对本文结果进行了精度验证。结果表明：通过缩减研究区范围可大力提高数据提取精度和速度；运用灰度共生矩阵、二值化、数学形态学等方法对影像进行迭代运算，能较好地提取高分遥感影像中的建筑物信息；通过对地震前后建筑物提取结果进行变化检测分析，能够有效地提取完全倒塌的建筑物，信息提取总体精度为90.45%，比基于像元级和基于目标级信息提取结果的精度分别提高了5.78%和5.23%，可为震后快速确定人员压埋点、部署救援力量提供决策依据，提高地震应急救援的时效性。Abstract: It is of great significance to study the methods in the extraction of building seismic damage information based on high-resolution remote sensing images in China, which can improve the timeliness of seismic damage information acquisition. Taking an earthquake with MS5.5 occurred near Taxkorgan Tajik Autonomous County, Kashi Prefecture, Xinjiang Uygur Autonomous Region, China, on May 11, 2017, as an example, based on high-resolution remote sensing images before and after the earthquake, building information was extracted by the method of combined texture features and morphology. Building damage information in extremely disaster areas was extracted through change detection and analysis, and then compared with the results extracted by pixel-based and object-based methods. Finally, the accuracy was verified by visual interpretation results of unmanned aerial vehicle images after the earthquake. The results show that the accuracy and speed of data extraction can be greatly improved by reducing the scope of the studied area. Using gray level co-occurrence matrix, binarization, mathematical morphology and other methods we can extract building information from GF remote sensing images more effectively. Through the change detection and analysis of building extraction results before and after the earthquake, completely collapsed buildings can be effec-tively extracted. The overall accuracy of information extraction is 90.45%, which is 5.78% and 5.23% higher than that of pixel-based and object-based information extraction, respectively. The completely collapsed buildings information can provide decision-making basis for rapid determination of people buried places and deployment of rescue forces after earthquakes, and improve the timeliness of earthquake emergency rescue.
-
Keywords:
- texture features /
- morphology /
- GF satellite remote sensing /
- building /
- seismic damage
-
-
![]()
图 1 建筑物震害信息提取的技术路线图
Figure 1. Technology route line of seismic damage information extraction
![]()
图 2 研究区预处理后的GF卫星遥感影像图
（a） 预处理后的震前GF-1影像图；（b） 预处理后的震后GF-2影像图；（c） 裁剪震后的GF-2居住区影像图
Figure 2. GF remote sensing images preprocessed in the studied area
（a） GF-1 image before earthquake after pre-processing；（b） GF-2 image after earthquake after pre-processing；（c） Clip image of GF-2 residential area after the earthquake
![]()
图 3 建筑物纹理特征图像
（a） 均值；（b） 方差；（c） 同质性；（d） 对比度；（e） 非相似性；（f） 熵；（g） 角二阶矩；（h） 相关性
Figure 3. Texture feature of buildings
（a） Mean；（b） Variance；（c） Homogeneity；（d） Contrast；（e） Dissimilarity；（f） Entropy； （g） Angular second moment；（h） Correlation
![]()
图 4 不同尺度的对比度特征图
Figure 4. Contrast feature images with different scales
（a） 3×3；（b） 5×5；（c） 7×7；（d） 9×9；（e） 11×11；（f） 13×13；
![]()
图 5 通过密度分割 （a）、二值化 （b）、形态学运算 （c） 的建筑物信息提取
Figure 5. Building information extraction by density segmentation （a），binarization （b） and morphological operation （c）
![]()
图 6 塔县地震前（a）、后（b）的建筑物提取结果图
Figure 6. Extraction results of buildings before （a） and after （b） the Taxkorgan Tajik earthquake
![]()
图 7 塔县地震后极灾区建筑物震害提取结果图
（a） 未倒塌建筑物分布图；（b） 倒塌建筑物分布图；（c） 新建未倒塌建筑物分布图
Figure 7. Damage extraction map of buildings in the extreme disaster areas of Taxkorgan Tajik earthquake
（a） Distribution of uncollapsed buildings；（b） Distribution of collapsed buildings； （c） Distribution of newly built uncollapsed buildings
![]()
图 8 支持向量机法（a）和面向对象方法（b）的建筑物震害信息提取结果图
Figure 8. Extraction result of seismic damage information of buildings by Support Vector Machine method （a） and by object-oriented methord （b）
![]()
图 9 无人机影像区域提取结果对比图
（a） 无人机影像覆盖区域；（b） 安居富民房航拍区对比结果图；（c） 村委会附近航拍区对比结果图
Figure 9. Contrast Map of UAV Image Region
（a） UAV images coverage area；（b） Comparison of aerial photography area of the rural housing project in Xinjiang；（c） Comparison of aerial photography area near village committee
表 1 不同提取方法分类精度的比较
Table 1 Comparison of classification accuracy with different extraction method
分类方法 总体精度 Kappa系数 本文方法 90.45% 0.87 支持向量机法 84.67% 0.78 面向对象分析法 85.22% 0.79 
下载: 导出CSV
-
李金香,李亚芳,李帅,王伟,陈勇. 2016. 面向地震应急准备的居民地遥感提取及量化分析[J]. 地理科学,36(11):1743–1750. Li J X,Li Y F,Li S,Wang W,Chen Y. 2016. Remote sensing extraction and quantitative analysis of residential area for earthquake emergency preparedness[J]. Scientia Geographica Sinica,36(11):1743–1750 (in Chinese).
林祥国,张继贤. 2017. 面向对象的形态学建筑物指数及其高分辨率遥感影像建筑物提取应用[J]. 测绘学报,46(6):724–733. doi: 10.11947/j.AGCS.2017.20170068 Lin X G,Zhang J X. 2017. Object-based morphological building index for building extraction from high resolution remote sensing imagery[J]. Acta Geodaetica et Cartographica Sinica,46(6):724–733 (in Chinese).
柳稼航,杨建峰,魏成阶,关泽群. 2004. 震害信息遥感获取技术历史、现状和趋势[J]. 自然灾害学报,13(6):46–52. doi: 10.3969/j.issn.1004-4574.2004.06.008 Liu J H,Yang J F,Wei C J,Guan Z Q. 2004. Acquisition of earthquake damage information based on remote sensing technology:History,current situation and trend[J]. Journal of Natural Disasters,13(6):46–52 (in Chinese).
欧阳平,张玉方. 2009. 形态学开闭运算在居民地边缘检测中的应用[J]. 测绘通报,(1):40–41. Ouyang P,Zhang Y F. 2009. Application of morphology open and close operation in resident edge detection[J]. Bulletin of Surveying and Mapping,(1):40–41 (in Chinese).
王光霞,杨培. 2000. 数学形态学在居民地街区合并中的应用[J]. 测绘学院学报,17(3):201–203. doi: 10.3969/j.issn.1673-6338.2000.03.014 Wang G X,Yang P. 2000. Application of mathematic morphology in uniting blocks of residential area[J]. Journal of Institute of Surveying and Mapping,17(3):201–203 (in Chinese).
王龙,王晓青,丁香,窦爱霞. 2007. 基于遥感和GIS的建筑物震害损失评估方法研究与实现[J]. 地震,27(4):77–83. doi: 10.3969/j.issn.1000-3274.2007.04.009 Wang L,Wang X Q,Ding X,Dou A X. 2007. Study on loss assessment of construction earthquake damage based on remote sensing and GIS[J]. Earthquake,27(4):77–83 (in Chinese).
王晓青,魏成阶,苗崇刚,张景发,单新建,马庆尊. 2003. 震害遥感快速提取研究:以2003年2月24日巴楚—伽师6.8级地震为例[J]. 地学前缘,10(增刊1):285–291. Wang X Q,Wei C J,Miao C G,Zhang J F,Shan X J,Ma Q Z. 2003. The extraction of seismic damage from remote sensing images:A case study of Bachu-Jiashi earthquake with MS=6.8 occurred on Feb. 24,2003[J]. Earth Science Frontiers,10(S1):285–291 (in Chinese).
王晓青,黄树松,丁香,崔丽萍,窦爱霞,李旖雯. 2015. 尼泊尔8.1级地震建筑物震害遥感提取与分析[J]. 震灾防御技术,10(3):481–490. doi: 10.11899/zzfy20150301 Wang X Q,Huang S S,Ding X,Cui L P,Dou A X,Li Y W. 2015. Extraction and analysis of building damage caused by Nepal MS8.1 earthquake from remote sensing images[J]. Technology for Earthquake Disaster Prevention,10(3):481–490 (in Chinese).
叶昕,王俊,秦其明. 2016. 基于高分一号卫星遥感图像的建筑物震害损毁检测研究:以2015年尼泊尔MS8.1地震为例[J]. 地震学报,38(3):477–485. doi: 10.11939/jass.2016.03.015 Ye X,Wang J,Qin Q M. 2016. Damaged building detection based on GF-1 satellite remote sensing image:A case study for Nepal MS8.1 earthquake[J]. Acta Seismologica Sinica,38(3):477–485 (in Chinese).
余先川,安卫杰,贺辉. 2012. 基于面向对象的无监督分类的遥感影像自动分类方法[J]. 地球物理学进展,27(2):744–749. doi: 10.6038/j.issn.1004-2903.2012.02.042 Yu X C,An W J,He H. 2012. A method of auto classification based on object oriented unsupervised classification[J]. Progress in Geophysics,27(2):744–749 (in Chinese).
翟辉琴,王明孝. 2005. 小波变换和数学形态学的高分辨率图像居民地识别[J]. 地球信息科学,7(4):25–28. doi: 10.3969/j.issn.1560-8999.2005.04.007 Zhai H Q,Wang M X. 2005. The habitat abstraction of the high resolution remote sensing imagery based on wavelet transform and mathematics morphologic subject[J]. Geo-Information Science,7(4):25–28 (in Chinese).
翟永梅,陈刚,黄晓峰. 2015. 面向对象遥感图像处理方法在建筑物震害评估中的应用研究[J]. 防灾减灾学报,31(1):16–21. Zhai Y M,Chen G,Huang X F. 2015. Research on application of object-oriented analysis to assessment of earthquake damage from remote sensing image[J]. Journal of Disaster Prevention and Reduction,31(1):16–21 (in Chinese).
张景发,谢礼立,陶夏新. 2002. 建筑物震害遥感图像的变化检测与震害评估[J]. 自然灾害学报,11(2):59–64. doi: 10.3969/j.issn.1004-4574.2002.02.010 Zhang J F,Xie L L,Tao X X. 2002. Change detection of remote sensing image for earthquake-damaged buildings and its application in seismic disaster assessment[J]. Journal of Natural Disasters,11(2):59–64 (in Chinese).
张景发,李强,焦其松. 2017. 建筑物震害多源遥感特征与机理分析[J]. 地震学报,39(2):257–272. doi: 10.11939/jass.2017.02.009 Zhang J F,Li Q,Jiao Q S. 2017. Multi-source remote sensing characteristics and mechanism analyses of building seismic damages[J]. Acta Seismologica Sinica,39(2):257–272 (in Chinese).
张志强,张新长,辛秦川,杨晓羚. 2018. 结合像元级和目标级的高分辨率遥感影像建筑物变化检测[J]. 测绘学报,47(1):102–112. doi: 10.11947/j.AGCS.2018.20170483 Zhang Z Q,Zhang X C,Xin Q C,Yang X L. 2018. Combining the pixel-based and object-based methods for building change detection using high-resolution remote sensing images[J]. Acta Geodaetica et Cartographica Sinica,47(1):102–112 (in Chinese).
赵妍,张景发,姚磊华. 2016. 基于面向对象的高分辨率遥感建筑物震害信息提取与评估[J]. 地震学报,38(6):942–951. doi: 10.11939/jass.2016.06.014 Zhao Y,Zhang J F,Yao L H. 2016. Seismic damage information extraction and evaluation of buildings with high resolution remote sensing based on object-oriented method[J]. Acta Seismologica Sinica,38(6):942–951 (in Chinese).
Dong L G,Shan J. 2013. A comprehensive review of earthquake-induced building damage detection with remote sensing techniques[J]. ISPRS J Photogr Remote Sens,84:85–99. doi: 10.1016/j.isprsjprs.2013.06.011
Haralick R M. 1979. Statistical and structural approaches to texture[J]. Proceedings of the IEEE,67(5):786–804.
Huang X,Zhu T T,Zhang L P,Tang Y Q. 2014. A novel building change index for automatic building change detection from high-resolution remote sensing imagery[J]. Remote Sens Lett,5(8):713–722. doi: 10.1080/2150704X.2014.963732
Turker M,Cetinkaya B. 2005. Automatic detection of earthquake-damaged buildings using DEMs created from pre- and post-earthquake stereo aerial photographs[J]. Int J Remote Sens,26(4):823–832. doi: 10.1080/01431160512331316810
Turker M,Sumer E. 2008. Building-based damage detection due to earthquake using the watershed segmentation of the post-event aerial images[J]. Int J Remote Sens,29(11):3073–3089. doi: 10.1080/01431160701442096
Yamazaki F,Yano Y,Matsuoka M. 2005. Visual damage interpretation of buildings in Bam city using QuickBird images following the 2003 Bam,Iran,earthquake[J]. Earthq Spectra,21(S1):329–336. doi: 10.1193/1.2101807
计量
- 文章访问数: 983
- HTML全文浏览量: 555
- PDF下载量: 38
