基于倾斜航空影像的建筑物结构性损毁评估方法研究
|
摘要
地震灾害是各种自然灾害中最为严重的灾害之一。由于它具有突发性、持续时间短和破坏性强的特点,严重威胁着人们的人身安全和财产安全,因此对震后建筑物实现快速的损毁评估有利于紧急救援的实施。传统的基于地面制图方法太慢,并且受地理位置的限制；高分辨率卫星影像和传统的航空影像能够提供高精度的影像数据,但是还存在诸多的限制,特别是进行建筑物的结构性损毁评估时,它们不能提供建筑物的立面信息。倾斜航空摄影技术的出现使得这一现象得到缓解,倾斜航空摄影除了提供垂直方向的视角还提供东、南、西、北四个方向的倾斜视角,这使对建筑物进行结构性损毁评估成为可能。因此,本文开展了面向对象的倾斜航空影像建筑物结构性损毁评估方法研究,包括以下工作：
(1)总结了倾斜航空摄影技术的发展史、系统组成、摄影原理、数据特点和主要应用。在此基础上,概括震后建筑物的类型并且列举了震后建筑物损毁特征的分析模型。
(2)研究了倾斜航空影像的分割技术,并且针对单阈值(最佳熵)分割算法存在对植被分割不完全的问题,本文利用自定义植被指数提出了改进的单阈值分割算法。
(3)在面向对象的影像对象分类中,分析了几种常用的分类方法,并选用模糊分类方法对影像对象进行分类。根据影像对象的光谱、纹理、形状等属性信息,实现了对建筑物的结构性损毁评估。
(4)引入了混淆矩阵,对模糊分类结果采用全局精度、用户精度、生产者精度和Kappa系数对实验结果进行定量分析。
研究表明,改进的最佳熵模型对倾斜航空影像的植被提取效果优于传统方法。本文在多尺度分割的基础上,选用特征模型对影像对象进行模糊分类,利用全局精度、用户精度、生产者精度和Kappa系数对分类结果进行定量分析,根据分析结果可知本文的研究方案可行。
Earthquake is one of the most serious disasters in the world. It seriously threatens to people's personal safety and property safety because of its unexpectedness, short duration and heavy destruction. So rapid damage assessment after disaster events is helpful to implement emergency rescue. The traditional ground-based mapping method is too slow, and restricted by geography site. High resolution remote satellite images and the traditional aerial image can provide image data with high precision, but there are still many restrictions. Especially the structural damage assessment of buildings, it cannot provide the facade perspective. Oblique aerial photography technology alleviate the phenomenon, because it provides the East, South, West, North four directions besides a vertical perspective. It is possible that the structural damage assessment of buildings. So this paper presents structural damage assessment based on object-oriented Technology with oblique aerial images and carries out the following work:
(1) Summarizing the development history, system composition, photographic principle, data characteristics and main application of oblique aerial photography technology. On the basis of this, summarizing the types of building after earthquake and listed the analysis model of damage characteristics.
(2) The segmentation technique of oblique airborne images is researched. And aiming at the problem of incomplete vegetation segmentation made of the ingle threshold segmentation algorithm (optimal entropy), this paper proposes an improved segmentation algorithm with custom vegetation index.
(3) Several classification methods are analyzed based on object-oriented classification of image objects and the fuzzy classification method is selected to classify the image objects. Structural damage assessment of buildings is achieved used fuzzy classification theory based on the spectrum, image texture, shape and other attribute information.
(4) The overall accuracy, user accuracy, producer's accuracy and Kappa coefficient related to the confusion matrix are used for quantitative analysis of the fuzzy classification results.
Studies show that the improved of optimal entropy is more effective than the traditional method for vegetation extraction. Feature models are selected to research for fuzzy classification with image objects based on multi-scale segmentation. And the overall accuracy, user accuracy, producer's accuracy and Kappa coefficient are used for quantitative analysis of the classification results,it is proved to be feasible.
(1)总结了倾斜航空摄影技术的发展史、系统组成、摄影原理、数据特点和主要应用。在此基础上,概括震后建筑物的类型并且列举了震后建筑物损毁特征的分析模型。
(2)研究了倾斜航空影像的分割技术,并且针对单阈值(最佳熵)分割算法存在对植被分割不完全的问题,本文利用自定义植被指数提出了改进的单阈值分割算法。
(3)在面向对象的影像对象分类中,分析了几种常用的分类方法,并选用模糊分类方法对影像对象进行分类。根据影像对象的光谱、纹理、形状等属性信息,实现了对建筑物的结构性损毁评估。
(4)引入了混淆矩阵,对模糊分类结果采用全局精度、用户精度、生产者精度和Kappa系数对实验结果进行定量分析。
研究表明,改进的最佳熵模型对倾斜航空影像的植被提取效果优于传统方法。本文在多尺度分割的基础上,选用特征模型对影像对象进行模糊分类,利用全局精度、用户精度、生产者精度和Kappa系数对分类结果进行定量分析,根据分析结果可知本文的研究方案可行。
Earthquake is one of the most serious disasters in the world. It seriously threatens to people's personal safety and property safety because of its unexpectedness, short duration and heavy destruction. So rapid damage assessment after disaster events is helpful to implement emergency rescue. The traditional ground-based mapping method is too slow, and restricted by geography site. High resolution remote satellite images and the traditional aerial image can provide image data with high precision, but there are still many restrictions. Especially the structural damage assessment of buildings, it cannot provide the facade perspective. Oblique aerial photography technology alleviate the phenomenon, because it provides the East, South, West, North four directions besides a vertical perspective. It is possible that the structural damage assessment of buildings. So this paper presents structural damage assessment based on object-oriented Technology with oblique aerial images and carries out the following work:
(1) Summarizing the development history, system composition, photographic principle, data characteristics and main application of oblique aerial photography technology. On the basis of this, summarizing the types of building after earthquake and listed the analysis model of damage characteristics.
(2) The segmentation technique of oblique airborne images is researched. And aiming at the problem of incomplete vegetation segmentation made of the ingle threshold segmentation algorithm (optimal entropy), this paper proposes an improved segmentation algorithm with custom vegetation index.
(3) Several classification methods are analyzed based on object-oriented classification of image objects and the fuzzy classification method is selected to classify the image objects. Structural damage assessment of buildings is achieved used fuzzy classification theory based on the spectrum, image texture, shape and other attribute information.
(4) The overall accuracy, user accuracy, producer's accuracy and Kappa coefficient related to the confusion matrix are used for quantitative analysis of the fuzzy classification results.
Studies show that the improved of optimal entropy is more effective than the traditional method for vegetation extraction. Feature models are selected to research for fuzzy classification with image objects based on multi-scale segmentation. And the overall accuracy, user accuracy, producer's accuracy and Kappa coefficient are used for quantitative analysis of the classification results,it is proved to be feasible.
引文
[1]吴剑.基于面向对象技术的遥感震害信息提取与评价方法研究[D].武汉大学博士学位论文.2010.
[2]魏成阶,刘亚岚,王世新,张立福,黄晓霞.四川坟川大地震震害遥感调查与评估[J].遥感学报.2008,12(5)：673-683.
[3]郑超.建筑物震害与地震烈度相关研究[D].中国地震局工程力学研究所工学硕士学位论文.2010.
[4]柳稼航,杨建峰,魏成阶,关泽群.震害信息遥感获取技术历史、现状和趋势[J].自然灾害学报,2004,13(6)：47-54.
[5]C.Lucian. Damage assessment of the 2003 Bam, Iran, earthquake using Ikonos Imagery[J]. Earthquake Spectra,vol.21,no.S1,pp.S219-S223,2005.
[6]P.B.Richards. Space technology contributions to emergency and disaster managemen[J]. Advances in Earth Oriented Applications of Space Technology, vol.1, no.4, pp.215-221, 1981.
[7]孟海东,郝永宽,宋飞燕,格日勒图.遥感图像非监督计算机分类方法的研究[J].计算机与现代化.2008,(7)：66-69.
[8]M.Turker, B.T.San. 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, vol.25,no.21,pp.4701-4714,2004.
[9]D. Brunner, GLemoine, and L.Bruzzone. Earthquake damage assessment ofbuildings using VHR optical and SAR imagery[J]. IEEE Trans. Geoscience and Remote Sensing, vol.48,no.5, pp.2403-2420,2010.
[10]S.Stramondo, C.Bignami, M.Chini, N.Pierdicca, and A.Tertulliani. Satellite radar and optical remote sensing for earthquake damage detection:results fromdifferent case studies[J]. International Journal of Remote Sensing, vol.27, no.20,pp.4433-4447.
[11]D. Ehrlich, H.D.Guo, K.Molch, J.W.Ma, and M.Pesaresi. Identifying damage caused by the 2008 Wenchuan earthquake from VHR remote sensing data[J]. International Journal of Digital Earth,vol.2,no.4,pp.309-326,2009.
[12]GLemoine. Validation of building damage assessments based on post-Haiti 2010 earthquake imagery using multi-source reference data[C].in Proc.Int.Conf.Validation of geo-information products for crisis management, Ispra, Italy, OCT.2010.
[13]S.Okada, and N.Takai. Classifications of structural types and damage patterns of buildings for earthquake field investigation[C].in Proc.Int.Conf. Twelfth World Conference onEarthquake Engineering. Auckland, New Zealand,2000, pp.2-8.
[14]刘士程.基于LiDAR数据提取建筑物顶面轮廓线方法研究[D].成都：西南交通大学,2012.
[15]M. Gerke, and N. Kerle. Automatic Structural Seismic Damage Assessment with Airborne Oblique Pictometry(c) Imagery [J]. PHOTOGRAMM ENG REM S,vol.77,no.9,pp.885-898,2011.
[16]杨久勇,高峰,向宇.倾斜航空摄影的原理与特点[C].中国测绘学2010年学术年会论文集.中国江苏南京.2010：341-343.
[17]J.G.Gorres, G. Markus, and F. Ilan.Photogrammetric image acquisition and image analysis of oblique imagery [J]. Photogrammetric Record, vol.23, no.124, pp.372-386. 2008.
[18]H. JOACHIM,and Aalborg. Photogrammetric Measurements in Oblique Aerial Images[J]. Photogrammetrie, Fernerkundung, Geoinformation, no.1,pp.7-14.2008.
[19]黎小东.面向对象的高空间分辨率遥感影像城市建筑物震害信息提取[D].成都理工大学硕士学位论文,2009.
[20]eCognition.2010. http://202.195.64.103/s/387/t/1525/a/84680/info.jspy(accessed 23 April.2012).
[21]N.Kerle,S.Heuel, and N.Pfeifer.Geospatial Information Technology for Emergency Response (S. Zlatanova and J. Li, editors)[M]. London:Taylor & Francis, pp.43-74.
[22]R.de Kok,A. Buck, T. Schneider, and U.Ammer.Analysis of Image Objects From VHR Imagery for Forest GIS Updating In the Bavarian Alps [J]. International Archives of Photogrammetry and Remote Sensing, Amsterdam, pp.222-228.2000.
[23]贾永红.数字图像处理[M].武汉：武汉大学出版社,978-7-307-07457-6,2010.02.
[24]陈丹峰,林陪,汲长远.自组织网络与模糊规则结合在遥感土地覆盖分类中的应用[J].中国土地科学,1998,12(5)：42～44.
[25]方芳.基于区域生长与聚类的彩色图像分割方法的改进[D].河北：燕山大学,2006.
[26]于子娟.基于模糊C均值聚类的彩色图像分割方法研究[D].中南大学硕士学位论文,2009.
[27]王慧敏,李艳.面向对象的损毁建筑物提取[J].遥感应用.2011,(5)：81-85.
[28]V. Metzler, T.Aach, and C. Thies.Object-Oriented image analysis by evaluating the causal Object hierarchy of a Partitioned reconstructive scale-space[C]. in Proc. Int. Conf.Redistribution rights reserved CSIRO Publishing.2002,265-276.
[29]B.Thomas,and J.H.Geoffrey.Object-oriented image analysis and scale-space:Theory and Methods for modeling and evaluating multiscale landscape structures [J]. International Archives of Photogrammetric and Remote Sensing, vol.34, no.4/W5, pp. 22-29,2001.
[30]张俊,朱国龙,李妍.面向对象高分辨率影像信息提取中的尺度效应及最优尺度研究[J].测绘科学,2011,36(2)：107-109.
[31]黄慧萍.面向对象影像分析中的尺度问题研究[D].北京：中国科学院研究生院,2003.
[32]李楠.面向对象的高分辨率遥感影像分割方法研究[D].西安：西安科技大学,2007.
[33]戴昌达,姜小光,唐伶俐.遥感图像处理应用与分析[M].北京：清华大学出版社,2004.
[34]黄雪青.基于高分辨率遥感影像的信息提取[D].重庆：重庆大学,2008.
[35]于海洋,程钢,张育民,卢小平.基于LiDAR和航空影像的地震灾害倒塌建筑物信息提取[J].国土资源遥感.2011,(3)：77-79.
[36]颜宏娟.面向对象的遥感影像模糊分类方法研究[D].西安：西安科技大学,2008.
[37]C.S.Lu, P.C.Chung, and C.F.Chen. Unsupervised texture segmentation via wavelet transform[J]. Pattern Recongnition,vol.30, no.5,pp.729-740,May.1997.
[38]郭德军,宋蛰存.基于灰度共生矩阵的纹理图像分类研究[J].林业机械与木工设备.2005,33(7)：21-23.
[39]韩晓微,杨喆,李彦平,徐心和.基于颜色相似系数的彩色图像分割方法[J].沈阳大学学报.2004,16(6)：15-16.
[40]X.Han, J.Li, and Y.Li. An approach of color object searching for vision system of soccer robot[C]. in Proc. IEEE Int. Conf. Robotics and Biomimetics,Shengyang,China, Aug.2004, pp.501-505.
[41]P.D. Zimmerman. The role of satellite remote sensing in disaster relief[J]. Space Communications,vol.8,no.2,pp.141-152,1991.
[42]郭雪松,袁治平,刘波.半模糊超球支持向量机多类分类方法研究[J].中国管理科学.2008,16(2)：141-144.
[43]董燕生,潘耀忠,方伟华等.基于面向对象技术的建筑物震害识别方法研究[J].地震研究.2011,34(3)：372-376.
[44]罗玲燕.提取铁路横断面属性信息的方法研究[D].成都：西南交通大学,2012.
[45]魏宇峰.高分辨率遥感影像道路信息提取关键技术研究与实现[D].北京：北京理工大学,2010.
[2]魏成阶,刘亚岚,王世新,张立福,黄晓霞.四川坟川大地震震害遥感调查与评估[J].遥感学报.2008,12(5)：673-683.
[3]郑超.建筑物震害与地震烈度相关研究[D].中国地震局工程力学研究所工学硕士学位论文.2010.
[4]柳稼航,杨建峰,魏成阶,关泽群.震害信息遥感获取技术历史、现状和趋势[J].自然灾害学报,2004,13(6)：47-54.
[5]C.Lucian. Damage assessment of the 2003 Bam, Iran, earthquake using Ikonos Imagery[J]. Earthquake Spectra,vol.21,no.S1,pp.S219-S223,2005.
[6]P.B.Richards. Space technology contributions to emergency and disaster managemen[J]. Advances in Earth Oriented Applications of Space Technology, vol.1, no.4, pp.215-221, 1981.
[7]孟海东,郝永宽,宋飞燕,格日勒图.遥感图像非监督计算机分类方法的研究[J].计算机与现代化.2008,(7)：66-69.
[8]M.Turker, B.T.San. 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, vol.25,no.21,pp.4701-4714,2004.
[9]D. Brunner, GLemoine, and L.Bruzzone. Earthquake damage assessment ofbuildings using VHR optical and SAR imagery[J]. IEEE Trans. Geoscience and Remote Sensing, vol.48,no.5, pp.2403-2420,2010.
[10]S.Stramondo, C.Bignami, M.Chini, N.Pierdicca, and A.Tertulliani. Satellite radar and optical remote sensing for earthquake damage detection:results fromdifferent case studies[J]. International Journal of Remote Sensing, vol.27, no.20,pp.4433-4447.
[11]D. Ehrlich, H.D.Guo, K.Molch, J.W.Ma, and M.Pesaresi. Identifying damage caused by the 2008 Wenchuan earthquake from VHR remote sensing data[J]. International Journal of Digital Earth,vol.2,no.4,pp.309-326,2009.
[12]GLemoine. Validation of building damage assessments based on post-Haiti 2010 earthquake imagery using multi-source reference data[C].in Proc.Int.Conf.Validation of geo-information products for crisis management, Ispra, Italy, OCT.2010.
[13]S.Okada, and N.Takai. Classifications of structural types and damage patterns of buildings for earthquake field investigation[C].in Proc.Int.Conf. Twelfth World Conference onEarthquake Engineering. Auckland, New Zealand,2000, pp.2-8.
[14]刘士程.基于LiDAR数据提取建筑物顶面轮廓线方法研究[D].成都：西南交通大学,2012.
[15]M. Gerke, and N. Kerle. Automatic Structural Seismic Damage Assessment with Airborne Oblique Pictometry(c) Imagery [J]. PHOTOGRAMM ENG REM S,vol.77,no.9,pp.885-898,2011.
[16]杨久勇,高峰,向宇.倾斜航空摄影的原理与特点[C].中国测绘学2010年学术年会论文集.中国江苏南京.2010：341-343.
[17]J.G.Gorres, G. Markus, and F. Ilan.Photogrammetric image acquisition and image analysis of oblique imagery [J]. Photogrammetric Record, vol.23, no.124, pp.372-386. 2008.
[18]H. JOACHIM,and Aalborg. Photogrammetric Measurements in Oblique Aerial Images[J]. Photogrammetrie, Fernerkundung, Geoinformation, no.1,pp.7-14.2008.
[19]黎小东.面向对象的高空间分辨率遥感影像城市建筑物震害信息提取[D].成都理工大学硕士学位论文,2009.
[20]eCognition.2010. http://202.195.64.103/s/387/t/1525/a/84680/info.jspy(accessed 23 April.2012).
[21]N.Kerle,S.Heuel, and N.Pfeifer.Geospatial Information Technology for Emergency Response (S. Zlatanova and J. Li, editors)[M]. London:Taylor & Francis, pp.43-74.
[22]R.de Kok,A. Buck, T. Schneider, and U.Ammer.Analysis of Image Objects From VHR Imagery for Forest GIS Updating In the Bavarian Alps [J]. International Archives of Photogrammetry and Remote Sensing, Amsterdam, pp.222-228.2000.
[23]贾永红.数字图像处理[M].武汉：武汉大学出版社,978-7-307-07457-6,2010.02.
[24]陈丹峰,林陪,汲长远.自组织网络与模糊规则结合在遥感土地覆盖分类中的应用[J].中国土地科学,1998,12(5)：42～44.
[25]方芳.基于区域生长与聚类的彩色图像分割方法的改进[D].河北：燕山大学,2006.
[26]于子娟.基于模糊C均值聚类的彩色图像分割方法研究[D].中南大学硕士学位论文,2009.
[27]王慧敏,李艳.面向对象的损毁建筑物提取[J].遥感应用.2011,(5)：81-85.
[28]V. Metzler, T.Aach, and C. Thies.Object-Oriented image analysis by evaluating the causal Object hierarchy of a Partitioned reconstructive scale-space[C]. in Proc. Int. Conf.Redistribution rights reserved CSIRO Publishing.2002,265-276.
[29]B.Thomas,and J.H.Geoffrey.Object-oriented image analysis and scale-space:Theory and Methods for modeling and evaluating multiscale landscape structures [J]. International Archives of Photogrammetric and Remote Sensing, vol.34, no.4/W5, pp. 22-29,2001.
[30]张俊,朱国龙,李妍.面向对象高分辨率影像信息提取中的尺度效应及最优尺度研究[J].测绘科学,2011,36(2)：107-109.
[31]黄慧萍.面向对象影像分析中的尺度问题研究[D].北京：中国科学院研究生院,2003.
[32]李楠.面向对象的高分辨率遥感影像分割方法研究[D].西安：西安科技大学,2007.
[33]戴昌达,姜小光,唐伶俐.遥感图像处理应用与分析[M].北京：清华大学出版社,2004.
[34]黄雪青.基于高分辨率遥感影像的信息提取[D].重庆：重庆大学,2008.
[35]于海洋,程钢,张育民,卢小平.基于LiDAR和航空影像的地震灾害倒塌建筑物信息提取[J].国土资源遥感.2011,(3)：77-79.
[36]颜宏娟.面向对象的遥感影像模糊分类方法研究[D].西安：西安科技大学,2008.
[37]C.S.Lu, P.C.Chung, and C.F.Chen. Unsupervised texture segmentation via wavelet transform[J]. Pattern Recongnition,vol.30, no.5,pp.729-740,May.1997.
[38]郭德军,宋蛰存.基于灰度共生矩阵的纹理图像分类研究[J].林业机械与木工设备.2005,33(7)：21-23.
[39]韩晓微,杨喆,李彦平,徐心和.基于颜色相似系数的彩色图像分割方法[J].沈阳大学学报.2004,16(6)：15-16.
[40]X.Han, J.Li, and Y.Li. An approach of color object searching for vision system of soccer robot[C]. in Proc. IEEE Int. Conf. Robotics and Biomimetics,Shengyang,China, Aug.2004, pp.501-505.
[41]P.D. Zimmerman. The role of satellite remote sensing in disaster relief[J]. Space Communications,vol.8,no.2,pp.141-152,1991.
[42]郭雪松,袁治平,刘波.半模糊超球支持向量机多类分类方法研究[J].中国管理科学.2008,16(2)：141-144.
[43]董燕生,潘耀忠,方伟华等.基于面向对象技术的建筑物震害识别方法研究[J].地震研究.2011,34(3)：372-376.
[44]罗玲燕.提取铁路横断面属性信息的方法研究[D].成都：西南交通大学,2012.
[45]魏宇峰.高分辨率遥感影像道路信息提取关键技术研究与实现[D].北京：北京理工大学,2010.