基于小波分析与无监督分类的多源遥感图象信息融合
|
摘要
遥感影象的数据融合是当今遥感技术领域中的一个研究热点。随着遥感信息获取手段的增多以及遥感技术的发展，遥感影象的融合受到了越来越多的关注。本文结合课题，在对小波理论和遥感图象融合技术进行了较为系统地学习和总结的基础之上，重点研究了以小波分析和无监督分类为工具的遥感图象融合方法及其算法仿真。
本文首先从小波理论在信号与信息处理学科领域中的应用角度对小波理论进行了系统的总结和介绍，分别利用Mallat算法和Trous算法实现了图象的正交小波变换和冗余小波变换。然后总结了现有典型的基于正交小波变换的像素级融合算法和基于冗余小波变换的图象融合算法，使用了标准差、信息熵和平均梯度三个标准作为融合结果的客观评价参数，并从理论上分析了各种算法的优劣。在以上分析的基础之上，作者提出了一种基于源图象活跃度和相似度的像素级融合算法，经过实验比较证明该算法的融合结果质量较同类算法有大幅度的提高。通过对图象纹理及其在多光谱图象融合中作用的深入研究，作者又提出了一种基于冗余小波纹理特征的重要中心系数(SCC)融合算法，通过与其它同类融合算法结果的比较证明了该算法在提高融合结果质量上的先进性。最后，还介绍了基于主成分分析(PCA)的多光谱图象融合方法以及非监督分类的方法，并实现了基于非监督分类的多光谱图象融合算法。
Data fusion of remote-sensing images is one of the most interesting problems in the field of remote sensing technology. With the increase of the means to acquire remote information and the development of remote-sensing technology, remote-sensing image fusion has attracted more and more attention in recent years. In this paper, theories about wavelet analysis and image fusion are reviewed and remote-sensing image fusion is realized using wavelet analysis and unsupervised classification.
First, wavelet transform theories are systematically reviewed and summarized from the point of view of signal and information processing. 2-D orthogonal wavelet transform and redundant wavelet transform are realized by use of Mallat algorithm and Trous algorithm respectively. Then typical existent fusion algorithms based on orthogonal and redundant wavelet transform are summarized. Standard deviation, entropy and average grads are advised to be the objective evaluation parameters. And the characteristics of each algorithm are analyzed theoretically. According to this analysis, a new pixel-level fusion algorithm based on the activity and similarity of source images is proposed and its performance is tested to be superior to the congeneric algorithms. By in-depth research of image texture and its application in multispectral image fusion, Significant Central Coefficient (SCC) algorithm based on redundant wavelet texture is proposed and its performance is tested to be also superior to the congeneric algorithms in the way of enhancing fusion quality. In the end, multispectral image fusion algorithms based on Principal Component Analysis and clustering algorithms are introduced. Multispectral image fusion based on unsupervised classification is realized.
本文首先从小波理论在信号与信息处理学科领域中的应用角度对小波理论进行了系统的总结和介绍，分别利用Mallat算法和Trous算法实现了图象的正交小波变换和冗余小波变换。然后总结了现有典型的基于正交小波变换的像素级融合算法和基于冗余小波变换的图象融合算法，使用了标准差、信息熵和平均梯度三个标准作为融合结果的客观评价参数，并从理论上分析了各种算法的优劣。在以上分析的基础之上，作者提出了一种基于源图象活跃度和相似度的像素级融合算法，经过实验比较证明该算法的融合结果质量较同类算法有大幅度的提高。通过对图象纹理及其在多光谱图象融合中作用的深入研究，作者又提出了一种基于冗余小波纹理特征的重要中心系数(SCC)融合算法，通过与其它同类融合算法结果的比较证明了该算法在提高融合结果质量上的先进性。最后，还介绍了基于主成分分析(PCA)的多光谱图象融合方法以及非监督分类的方法，并实现了基于非监督分类的多光谱图象融合算法。
Data fusion of remote-sensing images is one of the most interesting problems in the field of remote sensing technology. With the increase of the means to acquire remote information and the development of remote-sensing technology, remote-sensing image fusion has attracted more and more attention in recent years. In this paper, theories about wavelet analysis and image fusion are reviewed and remote-sensing image fusion is realized using wavelet analysis and unsupervised classification.
First, wavelet transform theories are systematically reviewed and summarized from the point of view of signal and information processing. 2-D orthogonal wavelet transform and redundant wavelet transform are realized by use of Mallat algorithm and Trous algorithm respectively. Then typical existent fusion algorithms based on orthogonal and redundant wavelet transform are summarized. Standard deviation, entropy and average grads are advised to be the objective evaluation parameters. And the characteristics of each algorithm are analyzed theoretically. According to this analysis, a new pixel-level fusion algorithm based on the activity and similarity of source images is proposed and its performance is tested to be superior to the congeneric algorithms. By in-depth research of image texture and its application in multispectral image fusion, Significant Central Coefficient (SCC) algorithm based on redundant wavelet texture is proposed and its performance is tested to be also superior to the congeneric algorithms in the way of enhancing fusion quality. In the end, multispectral image fusion algorithms based on Principal Component Analysis and clustering algorithms are introduced. Multispectral image fusion based on unsupervised classification is realized.
引文
[1] 朱述龙，张占睦．遥感图象获取与分析[M]．北京：科学出版社，2000．
[2] 李弼程，罗建书．小波分析及其应用[M]．北京：电子工业出版社，2003．
[3] 赵荣椿等．数字图象处理导论[M]．西安：西北工业大学出版社，2000．
[4] 程正兴．小波分析算法与应用[M]．西安：西安交通大学出版社，1999，
[5] 夏建涛．基于机器学习的高维多光谱图象分类．西安：西北工业大学博士论文，2003．
[6] 吴铮．小波编码技术及其在机载多光谱遥感图象压缩中的应用．西安：西北工业大学硕士论文，2001．
[7] 金剑秋，王章野，江照意，彭群生．多光谱图象的真实感融合[J]．中国图象图形学报，2001，7A(9)：926～931．
[8] 刘修国，高伟．基于Trous小波的影象融合[J]．地球科学——中国地质大学学报，2002，vol．27，No．3：338～340，
[9] 王海晖，彭嘉雄，吴巍．基于小波包变换的遥感图象融合[J]．中国图象图形学报，2002，7A(9)：932～937．
[10] 曹闻，李弼程，彭天强．一种基于小波包变换的遥感影象融合方法[J]．遥感技术与应用，2003，vol．18，No．4：248～253．
[11] 霍宏涛，游先样．小波变换在遥感图象融合中的应用研究[J]．中国图象图形学报，2003，8A(5)：551～556．
[12] 赵巍，毛士艺．一种像素级多传感器图象融合算法的研究[J]．电子与信息学报，2003，vol．25，No．8：1009～1013．
[13] 李晓春，陈京．基于小波变换的图象融合算法研究[J]．遥感技术与应用，2003，vol．18，No．1：27～30．
[14] 何国金，李克鲁，胡德永，从柏林，张雯华．多卫星遥感数据的信息融合：理论、方法与实践[J]，中国图象图形学报，1999，vol．4A(9)：744～750．
[15] 罗忠．多源遥感数据融合的现状[J]，测试技术学报，1999，vol．13，No．1：33～38．
[16] 瞿继双，王超，王正志．基于数据融合的遥感图象处理技术[J]．中国图象图形学报，2002，7A(10)：985～993．
[17] 张晓东，李德仁，蔡东翔，马洪超。?trous小波分解在边缘检测中的应用[J]．武汉大学学报信息科学版，2001，vol．26，No．1：29～33．
[18] Mingyi He, Jiantao Xia. High dimensional multispectral image fusion: classification by neural network[J]. Proc. Of SPIE, 2003, vol.4898, Pages:36～43.
[19] Yah Dongmei, Zhao Zhongming. Wavelet decomposition applied to image fusion[C].Info-tech and Info-net, 2001. Proceedings. ICII 2001 Beijing. 2001 International Conferences on, Volume: 1, Oct. 29-Nov. 1 2001. Pages: 291～295.
[20] Y. Chibani, A. Houacine. On the usc of thc redundant wavelet transform for multisensor image fusion[C]. Electronics, Circuits and Systems. 2000. ICECS 2000. The 7th IEEE International Conference on, Volume: 1, Dec. 17-20. 2000, Pages: 442～445.
[21] Gemma Piella. A region-based multiresolution image fusion algorithm[C]. Information Fusion, 2002. Proceedings of the Fifth International Conference on, Volume: 2, July 8-11, 2002, Pages:1557～1564.
[22] L. Alparone, S. Baronti and A. Garzelli. Assessment of image fusion algorithms based on noncritically-decimated pyramids and wavelets[C]. Geoscience and Remote Sensing Symposium, 2001. IGARSS'01, IEEE 2001 International, Volume: 2, July 9-13, 2001, Pages:852～854.
[23] Jong-Hyun Park, Kyoung-Ok Kim and Young-Kyu Yang. Image fusion using multiresolution analysis[C]. Geoscience and Remote Sensing Symposium, 2001. IGARSS '01. IEEE 2001 International, Volume: 2, July 9-13, 2001, Pages: 864～866.
[24] Li Hui, B.S. Manjunath and S.K. Mitra. Multi-sensor image fusion using the wavelet transform{Cl. Image Processing, 1994. Proceedings. ICIP-94., IEEE International Conference,Volume: 1, Nov. 13-16, 1994, Pages: 51～55.
[25] A. Garzelli. Possibilities and limitations of the use of wavelets in image fusion[C]. Geoscience and Remote Sensing Symposium, 2002. IGARSS '02.2002 IEEE International, Volume: 1,June 24～28, 2002, Pages: 66-68.
[26] Tseng Din-Chang, Chen Yi-Ling and Liu M.S.C. Wavelet-based multispectral image fusion[C]. Geoscience and Remote Sensing Symposium, 2001. IGARSS'01, IEEE 2001 International, Volume: 4, July 9-13, 2001. Pages: 1956～1958.
[27] L.J. Chipman, T.M. Orr and L.N. Graham. Wavelets and image fusion[C], Image Processing,1995. Proceedings., International Conference on, Volume: 3, Oct. 23-26, 1995, Pages: 248～251.
[28] B. Sankur, Y.P, Kahya, E.C. Guler and T. Engin. Feature extraction and classification of nonstationary signals based on the multiresolution signal decomposition[C]. Pattern Recognition, 1994. Volume: 2-Conference B: Computer Vision & Image Processing., Proceedings of the 12th IAPR International. Conference on, Volume: 2, Oct, 9-13 1994. Pages:592～595.
[29] Matlab6.1 小波工具箱
[2] 李弼程，罗建书．小波分析及其应用[M]．北京：电子工业出版社，2003．
[3] 赵荣椿等．数字图象处理导论[M]．西安：西北工业大学出版社，2000．
[4] 程正兴．小波分析算法与应用[M]．西安：西安交通大学出版社，1999，
[5] 夏建涛．基于机器学习的高维多光谱图象分类．西安：西北工业大学博士论文，2003．
[6] 吴铮．小波编码技术及其在机载多光谱遥感图象压缩中的应用．西安：西北工业大学硕士论文，2001．
[7] 金剑秋，王章野，江照意，彭群生．多光谱图象的真实感融合[J]．中国图象图形学报，2001，7A(9)：926～931．
[8] 刘修国，高伟．基于Trous小波的影象融合[J]．地球科学——中国地质大学学报，2002，vol．27，No．3：338～340，
[9] 王海晖，彭嘉雄，吴巍．基于小波包变换的遥感图象融合[J]．中国图象图形学报，2002，7A(9)：932～937．
[10] 曹闻，李弼程，彭天强．一种基于小波包变换的遥感影象融合方法[J]．遥感技术与应用，2003，vol．18，No．4：248～253．
[11] 霍宏涛，游先样．小波变换在遥感图象融合中的应用研究[J]．中国图象图形学报，2003，8A(5)：551～556．
[12] 赵巍，毛士艺．一种像素级多传感器图象融合算法的研究[J]．电子与信息学报，2003，vol．25，No．8：1009～1013．
[13] 李晓春，陈京．基于小波变换的图象融合算法研究[J]．遥感技术与应用，2003，vol．18，No．1：27～30．
[14] 何国金，李克鲁，胡德永，从柏林，张雯华．多卫星遥感数据的信息融合：理论、方法与实践[J]，中国图象图形学报，1999，vol．4A(9)：744～750．
[15] 罗忠．多源遥感数据融合的现状[J]，测试技术学报，1999，vol．13，No．1：33～38．
[16] 瞿继双，王超，王正志．基于数据融合的遥感图象处理技术[J]．中国图象图形学报，2002，7A(10)：985～993．
[17] 张晓东，李德仁，蔡东翔，马洪超。?trous小波分解在边缘检测中的应用[J]．武汉大学学报信息科学版，2001，vol．26，No．1：29～33．
[18] Mingyi He, Jiantao Xia. High dimensional multispectral image fusion: classification by neural network[J]. Proc. Of SPIE, 2003, vol.4898, Pages:36～43.
[19] Yah Dongmei, Zhao Zhongming. Wavelet decomposition applied to image fusion[C].Info-tech and Info-net, 2001. Proceedings. ICII 2001 Beijing. 2001 International Conferences on, Volume: 1, Oct. 29-Nov. 1 2001. Pages: 291～295.
[20] Y. Chibani, A. Houacine. On the usc of thc redundant wavelet transform for multisensor image fusion[C]. Electronics, Circuits and Systems. 2000. ICECS 2000. The 7th IEEE International Conference on, Volume: 1, Dec. 17-20. 2000, Pages: 442～445.
[21] Gemma Piella. A region-based multiresolution image fusion algorithm[C]. Information Fusion, 2002. Proceedings of the Fifth International Conference on, Volume: 2, July 8-11, 2002, Pages:1557～1564.
[22] L. Alparone, S. Baronti and A. Garzelli. Assessment of image fusion algorithms based on noncritically-decimated pyramids and wavelets[C]. Geoscience and Remote Sensing Symposium, 2001. IGARSS'01, IEEE 2001 International, Volume: 2, July 9-13, 2001, Pages:852～854.
[23] Jong-Hyun Park, Kyoung-Ok Kim and Young-Kyu Yang. Image fusion using multiresolution analysis[C]. Geoscience and Remote Sensing Symposium, 2001. IGARSS '01. IEEE 2001 International, Volume: 2, July 9-13, 2001, Pages: 864～866.
[24] Li Hui, B.S. Manjunath and S.K. Mitra. Multi-sensor image fusion using the wavelet transform{Cl. Image Processing, 1994. Proceedings. ICIP-94., IEEE International Conference,Volume: 1, Nov. 13-16, 1994, Pages: 51～55.
[25] A. Garzelli. Possibilities and limitations of the use of wavelets in image fusion[C]. Geoscience and Remote Sensing Symposium, 2002. IGARSS '02.2002 IEEE International, Volume: 1,June 24～28, 2002, Pages: 66-68.
[26] Tseng Din-Chang, Chen Yi-Ling and Liu M.S.C. Wavelet-based multispectral image fusion[C]. Geoscience and Remote Sensing Symposium, 2001. IGARSS'01, IEEE 2001 International, Volume: 4, July 9-13, 2001. Pages: 1956～1958.
[27] L.J. Chipman, T.M. Orr and L.N. Graham. Wavelets and image fusion[C], Image Processing,1995. Proceedings., International Conference on, Volume: 3, Oct. 23-26, 1995, Pages: 248～251.
[28] B. Sankur, Y.P, Kahya, E.C. Guler and T. Engin. Feature extraction and classification of nonstationary signals based on the multiresolution signal decomposition[C]. Pattern Recognition, 1994. Volume: 2-Conference B: Computer Vision & Image Processing., Proceedings of the 12th IAPR International. Conference on, Volume: 2, Oct, 9-13 1994. Pages:592～595.
[29] Matlab6.1 小波工具箱