基于Contourlet变换和ICA的多时相遥感图像变化检测
|
摘要
为了提高多时相遥感图像变化检测的精确度和运算效率,本文提出了一种基于Contourlet变换和独立分量分析(ICA-Independent component analysis)的变化检测算法.利用Contourlet变换多尺度、多方向性和各向异性等性质,对图像数据进行多尺度分解,再对分解后的数据进行独立分量分析,利用改进的基于牛顿迭代的固定点ICA算法分离出互相独立的数据分量,然后将分离后的数据分量转变成图像分量,最终对变化图像分量经阈值分割实现变化检测.实验结果表明,与现有的基于PCA、基于ICA、基于小波变换与ICA三种变化检测算法相比,本文算法能有效地分离出变化信息,减少了计算的复杂性,得到的变化图像具有更高的精确度,且对背景有较强的稳健性.
In order to improve the accuracy and computational efficiency of change detection of multi-temporal remote sensing images,a change detection algorithm based on contourlet transform and independent component analysis(ICA)is proposed.Firstly,multi-scale decomposition of image data isperformed by using contourlet transform with multi-scale,directionality and anisotropy.Then independent component analysis is carried out for the decomposed data.And the independent data components are separated by the improved fixed point ICA algorithm based on Newton iteration.Next the separated data components are transformed into image components.Finally,change detection is achieved by threshold segmentation and filtering for change image components. The experimental results show that compared with the existing three change detection algorithms such as the algorithm based on PCA,the algorithm based on ICA and the algorithm based on wavelet transform and ICA,the proposed algorithm in this paper can more effectively separate change information and reduce computational complexity.The obtained change image has higher accuracy and good robustness to the background.
In order to improve the accuracy and computational efficiency of change detection of multi-temporal remote sensing images,a change detection algorithm based on contourlet transform and independent component analysis(ICA)is proposed.Firstly,multi-scale decomposition of image data isperformed by using contourlet transform with multi-scale,directionality and anisotropy.Then independent component analysis is carried out for the decomposed data.And the independent data components are separated by the improved fixed point ICA algorithm based on Newton iteration.Next the separated data components are transformed into image components.Finally,change detection is achieved by threshold segmentation and filtering for change image components. The experimental results show that compared with the existing three change detection algorithms such as the algorithm based on PCA,the algorithm based on ICA and the algorithm based on wavelet transform and ICA,the proposed algorithm in this paper can more effectively separate change information and reduce computational complexity.The obtained change image has higher accuracy and good robustness to the background.
引文
Bai R,Yang W H,Zhang Y N.2009.Remote sensing image fusion algorithm based on contourlet transform.Journal of Image and Graphics(in Chinese),14(6):1173-1177.
Berg M,Bondesson E,Low,et al.2005.A combined on-line PCA-ICA algorithm for blind source separation.Asia-Pacific Conference on Communications,Perth,Western Australia,969-972.
Chen Q,Xiong B L,Lu J,et al.2010.Improved two-dimensional Otsu image segmentation method and fast recursive realization.Journal of Electronics&Information Technology,32(5):1100-1104.
Durucan E,Ebrahimi T.2001.Change detection and background extraction by linear algebra.IEEE Transactions on Image Processing,89(10):1368-1381.
Fan H S,Ma A N,Li J.2001.Case study on image differencing method for land use change detection using thematic data in Renhe district of Panzhihua.Journal of Remote Sensing(in Chinese),5(1):75-80
Fan K G,Huang W G,He M X,et al.2012.Marine atmospheric boundary layer depth retrieval by SAR in China Sea.Chinese J.Geophys.(in Chinese),55(4):1137-1143.
Huang S Q,Liu D Z,Hu M X,et al.2010.Multi-temporal SARimage change detection technique based on wavelet transform.Acta Geodaetica et Cartographica Sinica(in Chinese),39(2):180-186.
Hyvrinen A,Karhunen J,Oja E.2004.Independent Component Analysis.John Wiley and Sons Inc.
Jha C S,Unni N V M.1994.Digital change detection of forest conversion of a dry tropical forest region.International Journal of Remote Sensing,15(13):2543-2552.
Khaparde 2012.A study of ICA algorithm for separation of mixed images.International Conference on Digital Information and Communication Technology,82-86.
Li F F,Xiao B L,Zhang Q.2010.New wetland change detection method based on improved independent component analysis.Journal of Computer Applications(in Chinese),30(5):1347-1350
Li P.2011.Multitemporal remote sensing images change detection based on wavelet transform and ICA[Master′s thesis].Xidian University.
Li S T,Fang L Y,Yin H T.2012.Multitemporal image change detection using a detail-enhancing approach with nonsubsampled Contourlet transform.IEEET ransactions on Geosciences and Remote Sensing,9(5):836-840.
Ma C.2010.Review of ICA based fixed-point algorithm for blind separation of mixed images.International Conference on Bioinformatics and Biomedical Engineering,Xi′an,China,1-3.
Marchesi S,Bruzzone L.2009.ICA and kernel ICA for change detection in multispectral remote sensing images.IEEE International Geoscience and Remote Sensing Symposium,Mantova,Italy,980983.
Pham D T,Cardoso J F.2001.Blind separation of instantaneous mixtures of nonstationary sources.IEEE Transactions Signal Processing,49(9):1837-1848.
Qiu B,Prinet V,Perrier E,et al.2003.Multi-block PCA method for image change detection.Proceedings of the 12th International Conference on Image Analysis and Processing Mantova,Italy,385390.
Wang C R,Du J,Zhang X L.Research of image separation based on improved independent component analysis.Chinese Journal of Scientific Instrument(in Chinese),27(6):785-786,797
Xie D G,Zhang X D,Li X L,et al.2007.Radar target recognition method based on independent component analysis.Systems Engineering and Electronics(in Chinese),29(2):164-166.
Yu X C,Cao T T,Hu D,et al.2010.Blind image separation based on wavelet transformation and sparse component analysis.Journal of Beijing University of Posts and Telecommunications(in Chinese),33(2):58-63.
Zeng S G,Zhu N B,Bao Y,et al.2003.A modified fast independent component analysis and its application to image separation.Journal of Image and Graphics(in Chinese),8(10):1160-1165.
Zhang H,Wang J G.2008.A SAR image change detection algorithm based on principal component analysis.Journal of Electronics&Information Technology(in Chinese),80(7):1727-1730.
Zhong J Q,Wang R S.2006.Multitemporal remote sensing images change detection based on ICA.Journal of Electronics&Information Technology(in Chinese),28(6):994-998.
白蕊,杨万海,张艳妮.2009.基于Contourlet变换的遥感图像融合.中国图象图形学报,14(6):1173-1177.
陈琪,熊博莅,陆军等.2010.改进的二维Otsu图像分割方法及其快速实现.电子与信息学报,32(5):1100-1104.
范海生,马蔼乃,李京.2001.采用图像差值法提取土地利用变化信息方法-以攀枝花仁和区为例.遥感学报,5(1):75-80.
范开国,黄韦艮,贺明霞等.2012.星载SAR遥感图像反演海洋大气边界层高度.地球物理学报,55(4):1137-1143.
黄世奇,刘代志,胡明星等.2010.基于小波变换的多时相SAR图像变化检测技术.测绘学报,39(2):180-186.
李芳芳,肖本林,张谦.2010.基于改进独立分量分析的湿地变化检测法.计算机应用,30(5):1347-1350.
黎萍.2011.基于小波变换和ICA的多时相遥感图像变化检测[硕士论文].西安:西安电子科技大学.
王翠茹,杜鹃,张鑫林.2006.基于改进的独立分量分析的图像分离技术.仪器仪表学报,27(6):785-786,797.
谢德光,张贤达,李细林等.2007.基于独立分量分析的雷达目标识别方法.系统工程与电子技术,29(2):164-166.
余先川,曹婷婷,胡丹等.2010.基于小波变换和稀疏成分分析的盲图像分离法.北京邮电大学学报,33(2):58-63.
曾生根,朱宁波,包晔等.2003.一种改进的快速独立分量分析算法及其在图象分离中的应用.中国图象图形学报,8(10):1160-1165.
张辉,王建国.2008.一种基于主分量分析的SAR图像变化检测算法.电子与信息学报,80(7):1727-1730.
钟家强,王润生.2006.基于独立成分分析的多时相遥感图像变化检测.电子与信息学报,28(6):994-998.
Berg M,Bondesson E,Low,et al.2005.A combined on-line PCA-ICA algorithm for blind source separation.Asia-Pacific Conference on Communications,Perth,Western Australia,969-972.
Chen Q,Xiong B L,Lu J,et al.2010.Improved two-dimensional Otsu image segmentation method and fast recursive realization.Journal of Electronics&Information Technology,32(5):1100-1104.
Durucan E,Ebrahimi T.2001.Change detection and background extraction by linear algebra.IEEE Transactions on Image Processing,89(10):1368-1381.
Fan H S,Ma A N,Li J.2001.Case study on image differencing method for land use change detection using thematic data in Renhe district of Panzhihua.Journal of Remote Sensing(in Chinese),5(1):75-80
Fan K G,Huang W G,He M X,et al.2012.Marine atmospheric boundary layer depth retrieval by SAR in China Sea.Chinese J.Geophys.(in Chinese),55(4):1137-1143.
Huang S Q,Liu D Z,Hu M X,et al.2010.Multi-temporal SARimage change detection technique based on wavelet transform.Acta Geodaetica et Cartographica Sinica(in Chinese),39(2):180-186.
Hyvrinen A,Karhunen J,Oja E.2004.Independent Component Analysis.John Wiley and Sons Inc.
Jha C S,Unni N V M.1994.Digital change detection of forest conversion of a dry tropical forest region.International Journal of Remote Sensing,15(13):2543-2552.
Khaparde 2012.A study of ICA algorithm for separation of mixed images.International Conference on Digital Information and Communication Technology,82-86.
Li F F,Xiao B L,Zhang Q.2010.New wetland change detection method based on improved independent component analysis.Journal of Computer Applications(in Chinese),30(5):1347-1350
Li P.2011.Multitemporal remote sensing images change detection based on wavelet transform and ICA[Master′s thesis].Xidian University.
Li S T,Fang L Y,Yin H T.2012.Multitemporal image change detection using a detail-enhancing approach with nonsubsampled Contourlet transform.IEEET ransactions on Geosciences and Remote Sensing,9(5):836-840.
Ma C.2010.Review of ICA based fixed-point algorithm for blind separation of mixed images.International Conference on Bioinformatics and Biomedical Engineering,Xi′an,China,1-3.
Marchesi S,Bruzzone L.2009.ICA and kernel ICA for change detection in multispectral remote sensing images.IEEE International Geoscience and Remote Sensing Symposium,Mantova,Italy,980983.
Pham D T,Cardoso J F.2001.Blind separation of instantaneous mixtures of nonstationary sources.IEEE Transactions Signal Processing,49(9):1837-1848.
Qiu B,Prinet V,Perrier E,et al.2003.Multi-block PCA method for image change detection.Proceedings of the 12th International Conference on Image Analysis and Processing Mantova,Italy,385390.
Wang C R,Du J,Zhang X L.Research of image separation based on improved independent component analysis.Chinese Journal of Scientific Instrument(in Chinese),27(6):785-786,797
Xie D G,Zhang X D,Li X L,et al.2007.Radar target recognition method based on independent component analysis.Systems Engineering and Electronics(in Chinese),29(2):164-166.
Yu X C,Cao T T,Hu D,et al.2010.Blind image separation based on wavelet transformation and sparse component analysis.Journal of Beijing University of Posts and Telecommunications(in Chinese),33(2):58-63.
Zeng S G,Zhu N B,Bao Y,et al.2003.A modified fast independent component analysis and its application to image separation.Journal of Image and Graphics(in Chinese),8(10):1160-1165.
Zhang H,Wang J G.2008.A SAR image change detection algorithm based on principal component analysis.Journal of Electronics&Information Technology(in Chinese),80(7):1727-1730.
Zhong J Q,Wang R S.2006.Multitemporal remote sensing images change detection based on ICA.Journal of Electronics&Information Technology(in Chinese),28(6):994-998.
白蕊,杨万海,张艳妮.2009.基于Contourlet变换的遥感图像融合.中国图象图形学报,14(6):1173-1177.
陈琪,熊博莅,陆军等.2010.改进的二维Otsu图像分割方法及其快速实现.电子与信息学报,32(5):1100-1104.
范海生,马蔼乃,李京.2001.采用图像差值法提取土地利用变化信息方法-以攀枝花仁和区为例.遥感学报,5(1):75-80.
范开国,黄韦艮,贺明霞等.2012.星载SAR遥感图像反演海洋大气边界层高度.地球物理学报,55(4):1137-1143.
黄世奇,刘代志,胡明星等.2010.基于小波变换的多时相SAR图像变化检测技术.测绘学报,39(2):180-186.
李芳芳,肖本林,张谦.2010.基于改进独立分量分析的湿地变化检测法.计算机应用,30(5):1347-1350.
黎萍.2011.基于小波变换和ICA的多时相遥感图像变化检测[硕士论文].西安:西安电子科技大学.
王翠茹,杜鹃,张鑫林.2006.基于改进的独立分量分析的图像分离技术.仪器仪表学报,27(6):785-786,797.
谢德光,张贤达,李细林等.2007.基于独立分量分析的雷达目标识别方法.系统工程与电子技术,29(2):164-166.
余先川,曹婷婷,胡丹等.2010.基于小波变换和稀疏成分分析的盲图像分离法.北京邮电大学学报,33(2):58-63.
曾生根,朱宁波,包晔等.2003.一种改进的快速独立分量分析算法及其在图象分离中的应用.中国图象图形学报,8(10):1160-1165.
张辉,王建国.2008.一种基于主分量分析的SAR图像变化检测算法.电子与信息学报,80(7):1727-1730.
钟家强,王润生.2006.基于独立成分分析的多时相遥感图像变化检测.电子与信息学报,28(6):994-998.