一种面向对象的机场跑道变化检测方法
|
摘要
利用遥感影像变化检测技术获取机场跑道变化信息,可以为机场跑道打击效果评估等多种军事应用提供决策支撑。为了快速、准确的检测出机场跑道的变化区域,并定量、定性的获得变化属性,文章以"资源三号"卫星影像为例,提出了一种新的面向对象的机场跑道变化检测方法。首先,将经过配准处理的前后时相遥感影像进行多尺度分割,分割尺度利用尺度参数估计(Estimation of Scale Parameters,ESP)算法确定;之后,利用影像分割结果对不同时相的对象进行切割,形成前后时相上位置、大小一致的对象单元,再利用不同时相对象间的变化向量大小确定变化区域;最后,利用特征空间优化之后的特征集合对已确定的变化区域对象进行监督分类,获得机场跑道内部各对象的变化属性。结果表明:在变化区域的检测上,该方法避免了单张影像的分类过程,可有效提高检测效率;在变化类别的检测上,该方法在检测出的变化区域基础上进行分类,可大幅提高变化类别的检测精度,并且能够获得更为丰富的变化属性和满足快速准确检测机场跑道相关变化的信息。
The remote sensing image change detection technology can be used to obtain the information of airport runway change,thus providing decision support for various military applications such as airport runway strike effect evaluation. In order to detect the change area of airport runway quickly and accurately, and to obtain the change attribute quantitatively and qualitatively, a new object-oriented method of airport runway change detection is put forward in this paper by taking ZY-3 satellite image as an example. Firstly, the pre-and post-time phase remote sensing images after registration processing are segmented, and the segmentation scale is determined by ESP algorithm. After that, the objects of different time are cut using the result of image segmentation to form the object unit with the same position and size on the different time image, and then the change region is determined using the change vector size between different time objects. Finally, the objects in the determined change area are performed Supervised Classification using the feature set optimized by feature space, and the change attributes of the objects in the airport runway are then obtained. The results show that in detecting changing area the proposed method can effectively improve the detection efficiency by avoiding the classification process of single image, and in detecting changing categories, the method can greatly improve the detection accuracy by classifying on the basis of the detected variation area. In addition, more abundant change attribute information can be obtained by the method. It should be noted that the method can meet the military needs in rapid and accurate detection of airport runway related changes.
The remote sensing image change detection technology can be used to obtain the information of airport runway change,thus providing decision support for various military applications such as airport runway strike effect evaluation. In order to detect the change area of airport runway quickly and accurately, and to obtain the change attribute quantitatively and qualitatively, a new object-oriented method of airport runway change detection is put forward in this paper by taking ZY-3 satellite image as an example. Firstly, the pre-and post-time phase remote sensing images after registration processing are segmented, and the segmentation scale is determined by ESP algorithm. After that, the objects of different time are cut using the result of image segmentation to form the object unit with the same position and size on the different time image, and then the change region is determined using the change vector size between different time objects. Finally, the objects in the determined change area are performed Supervised Classification using the feature set optimized by feature space, and the change attributes of the objects in the airport runway are then obtained. The results show that in detecting changing area the proposed method can effectively improve the detection efficiency by avoiding the classification process of single image, and in detecting changing categories, the method can greatly improve the detection accuracy by classifying on the basis of the detected variation area. In addition, more abundant change attribute information can be obtained by the method. It should be noted that the method can meet the military needs in rapid and accurate detection of airport runway related changes.
引文
[1]张振龙,曾志远,李硕,等.遥感变化检测方法研究综述[J].遥感信息,2005(5):64-66.ZHANG Zhenlong,ZENG Zhiyuan,LI Shuo,et al.A Summary of Change Detection Methods of Remote Sensing Image[J].Remote Sensing Information,2005(5):64-66.(in Chinese)
[2]陈世平.关于航天遥感的若干问题[J].航天返回与遥感,2011,32(3):1-8.CHEN Shiping.Some Issues about Space Remote Sensing[J].Spacecraft Recovery&Remote Sensing,2011,32(3):1-8.(in Chinese)
[3]李德仁.利用遥感影像进行变化检测[J].武汉大学学报(信息科学版),2003(S1):7-12.LI Deren.Change Detection from Remote Sensing Images[J].Journal of Wuhan University(Information Science Edition),2003(S1):7-12.(in Chinese)
[4]牛鹏辉,李卫华,李小春.基于变化检测的机场毁伤评估算法[J].电光与控制,2012,19(7):89-93.NIU Penghui,LI Weihua,LI Xiaochun.An Airport Damage Assessment Algorithm Based on Change Detection[J].Electronics Optics&Control,2012,19(7):89-93.(in Chinese)
[5]杨茂龙,夏德深.跑道毁伤识别中的变化检测研究[J].遥感技术与应用,2005,20(5):18-21.YANG Maolong,XIA Deshen.A Study on Change Detecting in Runway's Damage Recognition[J].Remote Sensing Technology and Application,2005,20(5):18-21.(in Chinese)
[6]刘小锋.基于遥感图像目标识别的机场毁伤情况研究[D].西安:西安电子科技大学,2013.LIU Xiaofeng.Study of Airport Damage Analysis Based on Remote Sensing Target Recognition[D].Xi'an:Xidian University,2013.(in Chinese)
[7]马波.基于图像分析的机场打击效果评估研究[D].武汉:华中科技大学,2004.MA Bo.Automatic Battle Damage Assessment of Airports Based on Image Analysis[D].Wuhan:Huazhong University of Science&Technology,2004.(in Chinese)
[8]范瑞彬.遥感图像中机场识别与毁伤分析研究[D].南京:南京理工大学,2004.FAN Ruibin.Research on Airport Recognition and Damage Analysis in Remote Sensing Images[D].Nanjing:Nanjing University of Science&Technology,2004.(in Chinese)
[9]尤晓建.基于目标识别的机场跑道打击效果评估研究[J].计算机与数字工程,2010,38(10):119-121.YOU Xiaojian.Study of the Runway Battle Damage Assessment Based on Target Recognition[J].Computer&Digital Engineering,2010,38(10):119-121.(in Chinese)
[10]蒲刚,许鹏,任平,等.基于图像分析的机场跑道毁伤效果评估研究[J].舰船电子工程,2012,32(2):31-33.PU Gang,XU Peng,REN Ping,et al.Research on Damage Effect Assessment of Airport Runways Based on Image Analysis[J].Ship Electronic Engineering,2012,32(2):31-33.(in Chinese)
[11]计宏磊,杨清文.基于图像分析的机场跑道功能性毁伤评估[J].计算机应用,2016,36(S1):165-168.JI Honglei,YANG Qingwen.Airport Runway Functional Damage Assessment Based on Image Analysis[J].Journal of Computer Applications,2016,36(S1):165-168.(in Chinese)
[12]DING M,TIAN Z,JIN Z,et al.Registration Using Robust Kernel Principal Component for Object-based Change Detection[J].IEEE Geoscience and Remote Sensing Letters,2010,7(4):761-765.
[13]MARCHESI S,BOVOLO F,BRUZZONE L.A Context-sensitive Technique Robust to Registration Noise for Change Detection in VHR Multispectral Images[J].IEEE Transactions on Image Processing,2010,19(7):1877-1889.
[14]杜培军.遥感原理与应用[M].徐州:中国矿业大学出版社,2006:254-257.DU Peijun.Principle and Application of Remote Sensing[M].Xuzhou:China University of Mining and Technology Press,2006:254-257.(in Chinese)
[15]BAATZ M,SCH?PE A.Multiresolution Segmentation:An Optimization Approach for High Quality Multi-scale Image Segmentation[C]//Angewandte Geographische Informationsverarbeitung XII Beitr?ge zum AGIT-Symposium Salzburg 2000.Karlsruhe:Herbert Wichmann Verlag,2000:12-23.
[16]RAFAEL C G,RICHARD E W.Digital Image Processing(Second Edition)[M].New Jersey:Prentice Hall,2002.
[17]DR?GU?L,CSILLIK O,EISANK C,et al.Automated Parameterisation for Multi-scale Image Segmentation on Multiple Layers[J].ISPRS Journal of Photogrammetry&Remote Sensing,2014,88(100):119-127.
[18]陈晋,何春阳,史培军,等.基于变化向量分析的土地利用/覆盖变化动态监测(I)--变化阈值的确定方法[J].遥感学报,2001,5(4):259-266.CHEN Jin,HE Yangchun,SHI Peijun,et al.Land Use/Cover Change Detection with Change Vector Analysis(CVA):Change Magnitude Threshold Determination[J].Journal of Remote Sensing,2001,5(4):259-266.(in Chinese)
[19]MICHAEL J,DE S,MICHAEL F,et al.Geospatial Analysis:A Comprehensive Guide to Principle,Techniques and Software Tools(2.ed.)[J].Transactions in GIS,2008,12(5):645-647.
[20]张秀英,冯学智,江洪.面向对象分类的特征空间优化[J].遥感学报,2009,13(4):664-669.ZHANG Xiuying,FENG Xuezhi,JIANG Hong.Feature Space Optimization of Object-oriented Classification[J].Journal of Remote Sensing,2009,13(4):664-669.(in Chinese)
[21]赵英时.遥感应用分析原理与方法[M].北京:科学出版社,2003:203-208.ZHAO Yingshi.Principle and Method of Remote Sensing Applied Analysis[M].Beijing:The Science Publishing Company,2003:203-208.(in Chinese)
[22]FAWCETT T.An Introduction to ROC Analysis[J].Pattern Recognition Letters,2006,27(8):861-874.
[23]CONGALTON R G.A Review of Assessing the Accuracy of Classifications of Remotely Sensed Data[J].Remote Sensing of Environment,1991,37(2):35-46.
[2]陈世平.关于航天遥感的若干问题[J].航天返回与遥感,2011,32(3):1-8.CHEN Shiping.Some Issues about Space Remote Sensing[J].Spacecraft Recovery&Remote Sensing,2011,32(3):1-8.(in Chinese)
[3]李德仁.利用遥感影像进行变化检测[J].武汉大学学报(信息科学版),2003(S1):7-12.LI Deren.Change Detection from Remote Sensing Images[J].Journal of Wuhan University(Information Science Edition),2003(S1):7-12.(in Chinese)
[4]牛鹏辉,李卫华,李小春.基于变化检测的机场毁伤评估算法[J].电光与控制,2012,19(7):89-93.NIU Penghui,LI Weihua,LI Xiaochun.An Airport Damage Assessment Algorithm Based on Change Detection[J].Electronics Optics&Control,2012,19(7):89-93.(in Chinese)
[5]杨茂龙,夏德深.跑道毁伤识别中的变化检测研究[J].遥感技术与应用,2005,20(5):18-21.YANG Maolong,XIA Deshen.A Study on Change Detecting in Runway's Damage Recognition[J].Remote Sensing Technology and Application,2005,20(5):18-21.(in Chinese)
[6]刘小锋.基于遥感图像目标识别的机场毁伤情况研究[D].西安:西安电子科技大学,2013.LIU Xiaofeng.Study of Airport Damage Analysis Based on Remote Sensing Target Recognition[D].Xi'an:Xidian University,2013.(in Chinese)
[7]马波.基于图像分析的机场打击效果评估研究[D].武汉:华中科技大学,2004.MA Bo.Automatic Battle Damage Assessment of Airports Based on Image Analysis[D].Wuhan:Huazhong University of Science&Technology,2004.(in Chinese)
[8]范瑞彬.遥感图像中机场识别与毁伤分析研究[D].南京:南京理工大学,2004.FAN Ruibin.Research on Airport Recognition and Damage Analysis in Remote Sensing Images[D].Nanjing:Nanjing University of Science&Technology,2004.(in Chinese)
[9]尤晓建.基于目标识别的机场跑道打击效果评估研究[J].计算机与数字工程,2010,38(10):119-121.YOU Xiaojian.Study of the Runway Battle Damage Assessment Based on Target Recognition[J].Computer&Digital Engineering,2010,38(10):119-121.(in Chinese)
[10]蒲刚,许鹏,任平,等.基于图像分析的机场跑道毁伤效果评估研究[J].舰船电子工程,2012,32(2):31-33.PU Gang,XU Peng,REN Ping,et al.Research on Damage Effect Assessment of Airport Runways Based on Image Analysis[J].Ship Electronic Engineering,2012,32(2):31-33.(in Chinese)
[11]计宏磊,杨清文.基于图像分析的机场跑道功能性毁伤评估[J].计算机应用,2016,36(S1):165-168.JI Honglei,YANG Qingwen.Airport Runway Functional Damage Assessment Based on Image Analysis[J].Journal of Computer Applications,2016,36(S1):165-168.(in Chinese)
[12]DING M,TIAN Z,JIN Z,et al.Registration Using Robust Kernel Principal Component for Object-based Change Detection[J].IEEE Geoscience and Remote Sensing Letters,2010,7(4):761-765.
[13]MARCHESI S,BOVOLO F,BRUZZONE L.A Context-sensitive Technique Robust to Registration Noise for Change Detection in VHR Multispectral Images[J].IEEE Transactions on Image Processing,2010,19(7):1877-1889.
[14]杜培军.遥感原理与应用[M].徐州:中国矿业大学出版社,2006:254-257.DU Peijun.Principle and Application of Remote Sensing[M].Xuzhou:China University of Mining and Technology Press,2006:254-257.(in Chinese)
[15]BAATZ M,SCH?PE A.Multiresolution Segmentation:An Optimization Approach for High Quality Multi-scale Image Segmentation[C]//Angewandte Geographische Informationsverarbeitung XII Beitr?ge zum AGIT-Symposium Salzburg 2000.Karlsruhe:Herbert Wichmann Verlag,2000:12-23.
[16]RAFAEL C G,RICHARD E W.Digital Image Processing(Second Edition)[M].New Jersey:Prentice Hall,2002.
[17]DR?GU?L,CSILLIK O,EISANK C,et al.Automated Parameterisation for Multi-scale Image Segmentation on Multiple Layers[J].ISPRS Journal of Photogrammetry&Remote Sensing,2014,88(100):119-127.
[18]陈晋,何春阳,史培军,等.基于变化向量分析的土地利用/覆盖变化动态监测(I)--变化阈值的确定方法[J].遥感学报,2001,5(4):259-266.CHEN Jin,HE Yangchun,SHI Peijun,et al.Land Use/Cover Change Detection with Change Vector Analysis(CVA):Change Magnitude Threshold Determination[J].Journal of Remote Sensing,2001,5(4):259-266.(in Chinese)
[19]MICHAEL J,DE S,MICHAEL F,et al.Geospatial Analysis:A Comprehensive Guide to Principle,Techniques and Software Tools(2.ed.)[J].Transactions in GIS,2008,12(5):645-647.
[20]张秀英,冯学智,江洪.面向对象分类的特征空间优化[J].遥感学报,2009,13(4):664-669.ZHANG Xiuying,FENG Xuezhi,JIANG Hong.Feature Space Optimization of Object-oriented Classification[J].Journal of Remote Sensing,2009,13(4):664-669.(in Chinese)
[21]赵英时.遥感应用分析原理与方法[M].北京:科学出版社,2003:203-208.ZHAO Yingshi.Principle and Method of Remote Sensing Applied Analysis[M].Beijing:The Science Publishing Company,2003:203-208.(in Chinese)
[22]FAWCETT T.An Introduction to ROC Analysis[J].Pattern Recognition Letters,2006,27(8):861-874.
[23]CONGALTON R G.A Review of Assessing the Accuracy of Classifications of Remotely Sensed Data[J].Remote Sensing of Environment,1991,37(2):35-46.