基于独立分量分析的高光谱图像降维与压缩算法
|
摘要
论文提出了一种基于快速独立分量分析的高光谱图像降维算法。利用虚拟维数算法估计需要保留的独立分量数目,采用非监督端元提取算法自动获取端元矢量,并对快速独立分量分析的混合矩阵进行有效初始化。采用最大噪声分离变换对原始数据进行预处理,利用快速独立分量分析从变换后的主分量中依次提取出各端元对应的独立分量,最后对各个独立分量分别实施无损压缩。实验结果表明,该算法降维后的独立分量具有较好的地物分类性能,并且可以获得较好的压缩性能。
This paper presents a fast independent component analysis(fastICA)approach to dimensionality reduction for hyperspectral imagery.Virtual dimensionality is introduced to determine the number of independent component to be retained.The mixing matrix of fast-ICA is initialized by endmember vectors extracted from hyperspectral imagery by using unsupervised method,which can resolve the random order of independent components.Maximum noise fraction is used for preprocessing of original data,and fastICA transformation is performed on the selected principal components to generate independent components according to the acquired endmembers.Finally,the independent components are compressed losslessly by JPEG-LS.Experimental results show that the proposed algorithm can achieve better coding performance,the independent components after dimensionality reduction can also provide better object classification results.
This paper presents a fast independent component analysis(fastICA)approach to dimensionality reduction for hyperspectral imagery.Virtual dimensionality is introduced to determine the number of independent component to be retained.The mixing matrix of fast-ICA is initialized by endmember vectors extracted from hyperspectral imagery by using unsupervised method,which can resolve the random order of independent components.Maximum noise fraction is used for preprocessing of original data,and fastICA transformation is performed on the selected principal components to generate independent components according to the acquired endmembers.Finally,the independent components are compressed losslessly by JPEG-LS.Experimental results show that the proposed algorithm can achieve better coding performance,the independent components after dimensionality reduction can also provide better object classification results.
引文
[1]童庆喜,张兵,郑芬兰.高光谱遥感-原理、技术与应用[M].北京:高等教育出版社,2006.TONG Qingxi,ZHANG Bing,ZHENG Lanfen.Beijing:Hyperspectral Remote Sensing-Principle,Technology and Application[M].Beijing:Higher Education Press,2006.
[2]Penna B,Tillo T,Magli E,et al.Transform Coding Techniques for Lossy Hyperspectral Data Compression[J].IEEE Transaction on Geoscience and Remote Sensing,2007,45(5):1408-1421.
[3]Penna B,Tillo T,Magli E,et al.Hyperspectral Image Compression Employing a Model of Anomalous Pixels[J].IEEE Geoscience and Remote Sensing Letters,2007,4(4):664-668.
[4]Du Q,Fowler J.E.Hyperspectral image compression using JPEG2000and principal component analysis[J].IEEE Geoscience and Remote Sensing Letters,2007,4(2):201-205.
[5]周宗潭,董国华,徐昕,等.独立分量分析[M].北京:电子工业出版社,2007.ZHOU Zongtan,DONG Guohua,XU Xin,et al.Independent Component Analysis[M].Beijing:Electronic Industry Press,2007.
[6]Ramakrishna B,Wang J,Chang C I,et al.Spectral/Spatial Hyperspectral Image Compression in Conjunction with Virtual Dimensionality[C]//Proceedings of the SPIE,Boston,USA,2005,5806:772-781.
[7]Wang J,Chang C I.Mixed PCA/ICA Spectral/Spatial Compression for Hyperspectral Imagery[C]//Proceedings of the SPIE,Boston,USA,2005:11-22.
[8]冯燕,何明一,宋江红,等.基于独立分量分析的高光谱图像数据降维及压缩[J].电子与信息学报,2007,29(12):2871-2875.FENG Yan,HE Mingyi,SONG Jianghong,et al.ICA-Based Dimensionality Reduction and Compression of Hyperspectral Images[J].Journal of E1ectronics&Information Technology,2007,29(12):2871-2875.
[9]Hyvarinen A,Oja E.A Fast Fixed-Point Algorithm for Independent Component Analysis[J].Neural Computation,1997,9(7):1483-1492.
[10]李智勇.高光谱图像异常探测方法研究[D].长沙:国防科技大学,2004.LI Zhiyong.Research on Anomalous Detection of Hyperspectral Iimages[D].Changsha:National University of Defense Technology,2004.
[11]Chang C I,Du Q.Estimation of Number of Spectrally Distinct Signal Sources in Hyperspectral Imagery[J].IEEE Transaction on Geoscience and Remote Sensing,2004,42(3):608-619.
[12]苏令华,李纲,衣同胜,等.一种稳健的高光谱图像压缩方法[J].光学精密工程,2007,15(10):1609-1615.SU Linghua,LI Gang,YI Tongsheng,et al.A Robust Hyperspectral Image Compression Method[J].Optics and Precision Engineering,2007,15(10):1609-1615.
[13]粘永健,张志,王力宝,等.基于FastICA的高光谱图像目标分割[J].光子学报,2010,39(6):1003-1009.NIAN Yongjian,ZHANG Zhi,WANG Libao,et al.Target Segmentation of Hyperspectral Images Based on FastICA,2010,39(6):1003-1009.
[14]Xin Q,Nian Y J,Li X,et al.Dimensionality reduction for hyperspectral imagery based on FastICA[J].Journal of Electronics(China),2009,26(6):831-835.
[15]耿修瑞.高光谱图像异常探测与分类技术研究[D].北京:中国科学院遥感应用研究所,2005.GENG Xiurui.Research on Anomalous Detection and Classification of Hyperspectral Images[D].Beijing:Research institute of application of remote sensing of Chinese Academy of Sciences,2005.
[16]Landgrebe D.Multispectral data analysis:A signal theory perspective[D].Purdue:Purdue University,1998:98-102.
[17]Melgani F,Bruzzone L.Classification of Hyperspectral Remote Sensing Images with Support Vector Machines[J].IEEE Transactions on Geoscience and Remote Sensing,2004,42(8):1778-1790.
[2]Penna B,Tillo T,Magli E,et al.Transform Coding Techniques for Lossy Hyperspectral Data Compression[J].IEEE Transaction on Geoscience and Remote Sensing,2007,45(5):1408-1421.
[3]Penna B,Tillo T,Magli E,et al.Hyperspectral Image Compression Employing a Model of Anomalous Pixels[J].IEEE Geoscience and Remote Sensing Letters,2007,4(4):664-668.
[4]Du Q,Fowler J.E.Hyperspectral image compression using JPEG2000and principal component analysis[J].IEEE Geoscience and Remote Sensing Letters,2007,4(2):201-205.
[5]周宗潭,董国华,徐昕,等.独立分量分析[M].北京:电子工业出版社,2007.ZHOU Zongtan,DONG Guohua,XU Xin,et al.Independent Component Analysis[M].Beijing:Electronic Industry Press,2007.
[6]Ramakrishna B,Wang J,Chang C I,et al.Spectral/Spatial Hyperspectral Image Compression in Conjunction with Virtual Dimensionality[C]//Proceedings of the SPIE,Boston,USA,2005,5806:772-781.
[7]Wang J,Chang C I.Mixed PCA/ICA Spectral/Spatial Compression for Hyperspectral Imagery[C]//Proceedings of the SPIE,Boston,USA,2005:11-22.
[8]冯燕,何明一,宋江红,等.基于独立分量分析的高光谱图像数据降维及压缩[J].电子与信息学报,2007,29(12):2871-2875.FENG Yan,HE Mingyi,SONG Jianghong,et al.ICA-Based Dimensionality Reduction and Compression of Hyperspectral Images[J].Journal of E1ectronics&Information Technology,2007,29(12):2871-2875.
[9]Hyvarinen A,Oja E.A Fast Fixed-Point Algorithm for Independent Component Analysis[J].Neural Computation,1997,9(7):1483-1492.
[10]李智勇.高光谱图像异常探测方法研究[D].长沙:国防科技大学,2004.LI Zhiyong.Research on Anomalous Detection of Hyperspectral Iimages[D].Changsha:National University of Defense Technology,2004.
[11]Chang C I,Du Q.Estimation of Number of Spectrally Distinct Signal Sources in Hyperspectral Imagery[J].IEEE Transaction on Geoscience and Remote Sensing,2004,42(3):608-619.
[12]苏令华,李纲,衣同胜,等.一种稳健的高光谱图像压缩方法[J].光学精密工程,2007,15(10):1609-1615.SU Linghua,LI Gang,YI Tongsheng,et al.A Robust Hyperspectral Image Compression Method[J].Optics and Precision Engineering,2007,15(10):1609-1615.
[13]粘永健,张志,王力宝,等.基于FastICA的高光谱图像目标分割[J].光子学报,2010,39(6):1003-1009.NIAN Yongjian,ZHANG Zhi,WANG Libao,et al.Target Segmentation of Hyperspectral Images Based on FastICA,2010,39(6):1003-1009.
[14]Xin Q,Nian Y J,Li X,et al.Dimensionality reduction for hyperspectral imagery based on FastICA[J].Journal of Electronics(China),2009,26(6):831-835.
[15]耿修瑞.高光谱图像异常探测与分类技术研究[D].北京:中国科学院遥感应用研究所,2005.GENG Xiurui.Research on Anomalous Detection and Classification of Hyperspectral Images[D].Beijing:Research institute of application of remote sensing of Chinese Academy of Sciences,2005.
[16]Landgrebe D.Multispectral data analysis:A signal theory perspective[D].Purdue:Purdue University,1998:98-102.
[17]Melgani F,Bruzzone L.Classification of Hyperspectral Remote Sensing Images with Support Vector Machines[J].IEEE Transactions on Geoscience and Remote Sensing,2004,42(8):1778-1790.