利用高分辨率光学遥感图像检测震害损毁建筑物

叶昕; 秦其明; 王俊; 郑小坡; 王建华

doi:10.13203/j.whugis20150490

利用高分辨率光学遥感图像检测震害损毁建筑物

叶昕^1,,
秦其明^1, ,,
王俊¹,
郑小坡¹,
王建华¹

1.
北京大学遥感与地理信息系统研究所, 北京, 100871

基金项目:

高分辨率对地观测系统重大专项 11-Y20A05-9001-15/16

高分辨率对地观测系统重大专项 11-Y20A32-9001-15/17

国家高技术研究发展计划（863计划） 2012AA121305

详细信息

作者简介:
叶昕, 博士, 主要从事遥感图像处理研究。lanlang524@126.com

通讯作者:
秦其明, 博士, 教授。qmqinpku@163.com

中图分类号: P237.3
计量
- 文章访问数: 1998
- HTML全文浏览量: 243
- PDF下载量: 370
出版历程
- 收稿日期: 2017-09-11
- 发布日期: 2019-01-04

Detecting Damaged Buildings Caused by Earthquake from Remote Sensing Image Using Local Spatial Statistics Method

Institute of Remote Sensing and Geographic Information System, Peking University, Beijing 100871, China

Funds:

China National Major Project of High-Resolution Earth Observation 11-Y20A05-9001-15/16

China National Major Project of High-Resolution Earth Observation 11-Y20A32-9001-15/17

the National High Technology Research and Development Program (863 Program) of China 2012AA121305

More Information

Author Bio:
YE Xin, PhD, specializes in remote sensing image processing. E-mail: lanlang524@126.com

Corresponding author:
QIN Qiming, PhD, professor. E-mail: qmqinpku@163.com

摘要

摘要: 地震发生后，利用高分辨率遥感图像进行建筑物损毁检测，有利于快速评估灾害损失。在分析损毁建筑物梯度分布的基础上，提出了一种利用梯度局部空间统计检测震害损毁建筑物的方法。首先用Prewitt算子提取图像梯度信息；然后对梯度图像进行局部空间统计，统计各建筑物屋顶内部梯度的空间相关性，得到初步损毁检测结果；最后，在先验知识的指导下进行极小值分析和阴影检测，进一步修正建筑物损毁检测结果。分别以玉树地震后的Quickbird卫星遥感图像和盈江地震后的光学航空图像为例进行实验，结果表明，利用梯度局部空间统计检测震害损毁建筑物的方法效果优于传统损毁检测方法，总体精度达到80%以上，能够有效检测损毁建筑物。
- 损毁建筑物 /
- 遥感图像 /
- 梯度 /
- 局部空间统计 /
- 地震
Abstract: Damaged buildings detection from high-resolution remote sensing image helps to quick disaster losses evaluation after the earthquake. This paper presents a new method to detect damaged buildings using spectral gradient local spatial statistics, based on the analysis of gradient distribution characteristics of damaged buildings in the high-resolution remote sensing image. Firstly, spectral gradient image is obtained by Prewitt gradient operator. Secondly, local spatial statistics is used to evaluate the spectral gradient correlation within the roofs, and to generate the preliminary results. At last, the post processing steps, including minimal value analysis and shadow detection, are taken to optimize preliminary results and obtain the final results. The experiment results using a Quickbird image of Yushu earthquake and optical aerial image of Yingjiang earthquake demonstrate the effectiveness of the proposed method, which provides an overall accuracy of higher than 80%, are better than traditional methods.
- damaged building /
- remote sensing image /
- gradient /
- local spatial statistics /
- earthquake

HTML全文

图 1 建筑物损毁检测方法流程图

Figure 1. Flowchart of Building Damage Detection

下载: 全尺寸图片幻灯片

图 2 初始结果修正流程图

Figure 2. Flowchart of Initial Result Correction

下载: 全尺寸图片幻灯片

图 3 存在极小值的部分损毁建筑物

Figure 3. Partly Damage Building with Minimum Value

下载: 全尺寸图片幻灯片

图 4 有阴影的部分损毁建筑物

Figure 4. Partly Damage Building with Shadow

下载: 全尺寸图片幻灯片

图 5 研究区1遥感图像及其检测结果

Figure 5. Remote Sensing Image of Study Area 1 and Its Detection Results

下载: 全尺寸图片幻灯片

图 6 研究区2遥感图像及其检测结果

Figure 6. Remote Sensing Image of Study Area 2 and Its Detection Results

下载: 全尺寸图片幻灯片

表 1 本文方法与现有方法精度对比

Table 1 Comparison of the Performance

检测结果	Turker等^[4]方法	Sumer等^[10]方法	本文方法
损毁建筑物/栋	44	41	49
未损毁建筑物/栋	55	50	59
合计/栋	99	91	108
Kappa系数	0.53	0.41	0.67
总体精度/%	76.74	70.54	83.72

下载: 导出CSV

参考文献(20)

[1]	Dong L, Shan J. A Comprehensive Review of Earthquake-Induced Building Damage Detection with Remote Sensing Techniques[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2013, 84(7):85-99 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=a760006e8c1dee8a577eb5976e2573b0
[2]	眭海刚, 华凤, 范一大, 等.利用GIS与贝叶斯网络进行高分辨率SAR影像道路损毁信息提取[J].武汉大学学报·信息科学版, 2016, 41(5):578-583 http://ch.whu.edu.cn/CN/abstract/abstract5434.shtml Sui Haigang, Hua Feng, Fan Yida, et al. Road Damage Extraction from High-Resolution SAR Image Road Based on GIS Data and Bayes Network[J]. Geomatics and Information Science of Wuhan University, 2016, 41(5):578-583 http://ch.whu.edu.cn/CN/abstract/abstract5434.shtml
[3]	Tong X, Lin X, Feng T, et al. Use of Shadows for Detection of Earthquake-Induced Collapsed Buildings in High-Resolution Satellite Imagery[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2013, 79(5):53-67 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=0357eae6c32fb6312085c536eab2396d
[4]	Turker M, San B T. Detection of Collapsed Buildings Caused by the 1999 Izmit, Turkey Earthquake Through Digital Analysis of Post-Event Aerial Photographs[J]. International Journal of Remote Sensing, 2004, 25(21):4701-4714 doi: 10.1080/01431160410001709976
[5]	Iwasaki Y, Yamazaki F. Detection of Building Collapse from the Shadow Lengths in Optical Satellite Images[C].The 32nd Asian Conference on Remote Sensing, Taipei, China, 2011
[6]	Turker M, Sumer E. Building-based Damage Detection due to Earthquake Using the Watershed Segmentation of the Post-Event Aerial Images[J]. International Journal of Remote Sensing, 2008, 29(11):3073-3089 doi: 10.1080/01431160701442096
[7]	Guler M A, Turker M. Detection of the Earthquake Damaged Buildings from Post-event Aerial Photographs Using Perceptual Grouping[J]. International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences, 2004, 35(B3):1-4 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=CC0211211778
[8]	陈文凯, 何少林, 张景发, 等.利用遥感技术提取震害信息方法的研究进展[J].西北地震学报, 2008, 30(1):88-93 doi: 10.3969/j.issn.1000-0844.2008.01.018 Chen Wenkai, He Shaolin, Zhang Jingfa, et al. A Review on Methods of Extracting Earthquake Damage Information Using Remote Sensing Technology[J]. Northwestern Seismological Journal, 2008, 30(1):88-93 doi: 10.3969/j.issn.1000-0844.2008.01.018
[9]	Duan F, Gong H, Zhao W. Collapsed Houses Automatic Identification Based on Texture Changes of Post-Earthquake Aerial Remote Sensing Image[C]. The 18th IEEE International Conference on Geoinformatics, Beijing, China, 2010
[10]	Sumer E, Turker M. Building Damage Detection from Post-Earthquake Aerial Imagery Using Building Grey-Value and Gradient Orientation Analyses[C]. The 2nd IEEE International Conference on Recent Advances in Space Technologies, Istanbul, Turkey, 2005
[11]	李祖传, 马建文, 张睿, 等.利用融合纹理与形态特征进行地震倒塌房屋信息自动提取[J].武汉大学学报·信息科学版, 2010, 35(4):446-450 http://ch.whu.edu.cn/CN/abstract/abstract901.shtml Li Zuchuan, Ma Jianwen, Zhang Rui, et al. Extracting Damaged Buildings Information Automatically Based on Textural and Morphological Features[J]. Geomatics and Information Science of Wuhan University, 2010, 35(4):446-450 http://ch.whu.edu.cn/CN/abstract/abstract901.shtml
[12]	Vu T T, Ban Y. Context-based Mapping of Damaged Buildings from High-Resolution Optical Satellite Images[J]. International Journal of Remote Sensing, 2010, 31(13):3411-3425 doi: 10.1080/01431161003727697
[13]	Yamazaki F, Vu T T, Matsuoka M. Context-based Detection of Post-Disaster Damaged Buildings in Urban Areas from Satellite Images[C]. The 4th IEEE Urban Remote Sensing Joint Event, Paris, France, 2007
[14]	窦爱霞.震害遥感图像变化检测技术研究[D].青岛: 山东科技大学, 2003 Dou Aixia. Study on Seismic Damage Change Detecting Technique Based on Remote Sensing Images[D]. Qingdao: Shandong University of Science and Technology, 2003
[15]	Anselin L. Local Indicators of Spatial Association-LISA[J]. Geographical Analysis, 1995, 27(2):93-115 doi: 10.1111-j.1538-4632.1995.tb00338.x/
[16]	朱钟正, 苏伟.基于局部空间统计分析的SPOT 5影像分类[J].遥感学报, 2011, 15(5):957-972 http://d.old.wanfangdata.com.cn/Periodical/ygxb201105006 Zhu Zhongzheng, Su Wei. The Analysis of the Classification of SPOT 5 Image Based on Local Spatial Statistics[J]. Journal of Remote Sensing, 2011, 15(5):957-972 http://d.old.wanfangdata.com.cn/Periodical/ygxb201105006
[17]	涂继辉, 眭海刚, 冯文卿, 等.利用词袋模型检测建筑物顶面损毁区域[J].武汉大学学报·信息科学版, 2018, doi: 10.13203/j.whugis20150665 Tu Jihui, Sui Haigang, Feng Wenqing, et al. Detection of Damaged Areas Based on Visual Bag-of-Words Model from Aerial Remove Sensing Images[J]. Geomatics and Information Science of Wuhan University, 2018, doi: 10.13203/j.whugis20150665
[18]	Schweier C, Markus M. Classification of Collapsed Buildings for Fast Damage and Loss Assessment[J].Bulletin of Earthquake Engineering, 2006, 4(2):177-192 doi: 10.1007/s10518-006-9005-2
[19]	张斌, 马国锐, 余健, 等.利用灾前光学影像和灾后VHR SAR影像对地震低层建筑物进行变化检测[J].武汉大学学报·信息科学版, 2014, 39(2):239-243 http://d.old.wanfangdata.com.cn/Periodical/whchkjdxxb201402024 Zhang Bin, Ma Guorui, Yu Jian, et al. Change Detection of Low Buildings After Earthquake Using Very-High Resolution Preevent Optical and Post-event SAR Images[J]. Geomatics and Information Science of Wuhan University, 2014, 39(2):239-243 http://d.old.wanfangdata.com.cn/Periodical/whchkjdxxb201402024
[20]	涂继辉, 眭海刚, 吕枘蓬, 等.基于基尼系数的倾斜航空影像中建筑物立面损毁检测[J].武汉大学学报·信息科学版, 2017, doi: 10.13203/j.whugis20150376 Tu Jihui, Sui Haigang, Lv Ruipeng, et al. Building Facade Damage Detection Based on the Gini Index from Oblique Aerial Images[J]. Geomatics and Information Science of Wuhan University, 2017, doi: 10.13203/j.whugis20150376

施引文献(36)

期刊类型引用(30)

1.	刘焱雄，陈义兰，杨龙，高珊. 基于测绘学角度探讨海岸线及其测定方法. 海洋科学进展. 2024(03): 425-436 . 百度学术
2.	王继鹏，金云智，辛忠华，吉才宇，郭龙. 基于PSO-BP的北斗卫星导航海底高程拟合技术的研究. 天然气与石油. 2024(06): 153-160 . 百度学术
3.	付五洲，许宝华，陆彬，李涛. 重力场模型在长江口岛礁垂直基准建立中的应用. 现代测绘. 2023(04): 57-60 . 百度学术
4.	王双喜，肖强，孙雪洁. 复杂海域高精度海底地形测量关键问题研究. 海洋技术学报. 2022(01): 7-12 . 百度学术
5.	周颖，王瑞. 远海PPK测量潮位用于深度基准面计算的研究. 港工技术. 2022(02): 23-26 . 百度学术
6.	柯灝，赵建虎，周丰年，吴敬文，暴景阳，赵祥伟，谢朋朋. 联合大地水准面、海面地形和潮波运动数值模拟的长江口陆海垂直基准转换关系. 武汉大学学报(信息科学版). 2022(05): 731-737+746 . 百度学术
7.	单瑞，李浩军，刘慧敏，赵钊，董凌宇，杜凯. GNSS PPP/INS紧组合模式下的远海无验潮水深测量. 海洋地质前沿. 2022(10): 87-93 . 百度学术
8.	张颖，闫玉茹，章家保，李静，裘露露. 潮滩冲淤观测技术发展现状. 海洋科学. 2021(03): 152-162 . 百度学术
9.	王森，刘立龙，黄良珂，周威. 基于潮汐调和分析的全球定位系统-多路径反射测量技术潮位预报. 科学技术与工程. 2021(09): 3481-3486 . 百度学术
10.	魏荣灏，陈佳兵，徐达. 基于PPK无验潮的水下地形测量技术研究. 海洋技术学报. 2021(01): 57-62 . 百度学术
11.	王挺，王萃. GNSS-PPK在远距离潮位观测的应用研究. 江西测绘. 2021(04): 8-11 . 百度学术
12.	王正杰，王峰，吴自银，曹振轶，罗孝文，李守军. 基于GPS PPK技术确定测深点瞬时潮位及分析. 海洋技术学报. 2020(02): 58-63 . 百度学术
13.	王小刚，赵薛强，许军. 珠江口瞬时水位解算方法研究及应用. 水利水电技术. 2020(11): 117-124 . 百度学术
14.	梁冠辉，陶常飞，周兴华，周东旭，王朝阳. 新型远距离验潮系统集成设计与研制. 海洋科学进展. 2019(01): 129-139 . 百度学术
15.	王智明，孙月文. 无验潮模式下的宁波杭州湾水下地形测量. 城市勘测. 2019(02): 157-159 . 百度学术
16.	陈正伟，韩磊. 基于高精度GNSS定位解算及姿态数据获取潮位研究. 海洋技术学报. 2019(05): 55-59 . 百度学术
17.	李梦昊，王胜利，高兴国，陈冠旭，刘焱雄. 基于混合编程的实时精密单点定位方法. 海岸工程. 2018(01): 66-73 . 百度学术
18.	黄辰虎，陆秀平，边刚，黄贤源，管明雷，翟国君，黄谟涛. 中短期验潮站验潮零点不规则漂移精密处理. 武汉大学学报(信息科学版). 2018(11): 1673-1680 . 百度学术
19.	Yuanxi YANG，Tianhe XU，Shuqiang XUE. Progresses and Prospects of Marine Geodetic Datum and Marine Navigation in China. Journal of Geodesy and Geoinformation Science. 2018(01): 16-24 . 必应学术
20.	臧建飞，范士杰，易昌华，秦学彬，华亮，麻德明. 实时精密单点定位的远海实时GPS潮汐观测. 测绘科学. 2017(06): 155-160 . 百度学术
21.	臧建飞，范士杰，易昌华，秦学彬，陈冠旭，华亮. 远海实时GPS潮汐的实时精密单点定位观测. 测绘科学. 2017(08): 79-84 . 百度学术
22.	杨元喜，徐天河，薛树强. 我国海洋大地测量基准与海洋导航技术研究进展与展望. 测绘学报. 2017(01): 1-8 . 百度学术
23.	赵建虎，欧阳永忠，王爱学. 海底地形测量技术现状及发展趋势. 测绘学报. 2017(10): 1786-1794 . 百度学术
24.	王朝阳，周兴华，李延刚，梁冠辉，付延光. 远距离GNSS潮位测量精度的影响因素研究. 海洋技术学报. 2017(03): 1-6 . 百度学术
25.	辛保稳，李友龙. GPS PPK技术在海底地形测量中的应用. 科技展望. 2017(18): 161 . 百度学术
26.	杨涛，葛俊洁，李路. GPS测量技术及其在工程测量中的应用. 电子测试. 2016(06): 126+125 . 百度学术
27.	暴景阳，翟国君，许军. 海洋垂直基准及转换的技术途径分析. 武汉大学学报(信息科学版). 2016(01): 52-57 . 百度学术
28.	周东旭，周兴华，梁冠辉，王朝阳，杨磊. GPS浮标天线高的动态标定方法. 测绘科学. 2015(12): 121-124 . 百度学术
29.	赵建虎，王爱学. 精密海洋测量与数据处理技术及其应用进展. 海洋测绘. 2015(06): 1-7 . 百度学术
30.	赵元元，殷行. 土地测量中GPS实时动态技术的应用研究. 价值工程. 2015(20): 161-162 . 百度学术