超像素极化合成孔径雷达影像谱聚类算法研究Superpixel based PolSAR image septrcal clustering
崔鸣,余洁,王彦兵,谢东海
摘要(Abstract)：
针对基于像素的谱聚类计算量大、效率低,且受到影像斑点噪声影响严重的问题,该文结合极化合成孔径雷达影像的统计特性,提出了一种基于超像素的极化合成孔径雷达影像谱聚类算法。该方法首先用基于梯度分割影像的分水岭算法得到影像的初始分割;然后按区域邻接关系合并含像素个数较少的极小区域得到超像素图像;最后以超像素为基本数据单元,采用修正Wishart距离作为超像素之间的距离度量标准,通过Nystrm逼近的采样方法获得最终的分类结果。最后利用模拟数据和1991年获取的荷兰Flevoland地区L波段稻田数据验证了该算法的有效性,总体分类精度达到了98.17%。
关键词(KeyWords)： 超像素;谱聚类;修正Wishart距离;PolSAR影像分类
基金项目(Foundation): 国家863高技术发展研究计划(2011AA120404);; 北京市教委科研基地建设项目
作者(Author): 崔鸣,余洁,王彦兵,谢东海
DOI: 10.16251/j.cnki.1009-2307.2015.03.017
参考文献(References)：
- [1]LIU B,HU H,WANG H,et al.Superpixel-Based Classification With an Adaptive Number of Classes for Polarimetric SAR Images[C]//IEEE Transactions on Geoscience and Remote Sensing,2013,51(2):907-924.
- [2]邓磊,曾文华,孙晨.利用PolSAR数据提取人造目标的进展分析[J].遥感信息,2013(4).
- [3]NG A Y,JORDAN M I,WEISS Y.On Spectral Clustering:Analysis and an Algorithm[C]//Advances in Neural Information Processing Systems 14.Cambridge,MA,US,2002:849-856.
- [4]FOWLKES C,BELONGIE S,CHUNG F,et al.Spectral Grouping Using the Nystrom Method[C]//IEEE Transactions on Pattern Analysis and Machine Intelligence,2004,26(2):214-225.
- [5]蔡晓妍,戴冠中,杨黎斌.谱聚类算法综述[J].计算机科学,2008,35(17):14-18.
- [6]ERSAHIN K,CUMMING I G,YEDLIN M J.Classification of Polarimetric SAR Data Using Spectral Graph Partitioning[C]//International Geoscience and Remote Sensing Symposium.Denver,Colorado,USA,2006:1756-1759.
- [7]ANFINSEN S N,JENSSEN R,ELTOFT T.Spectral Clustering of Polarimetric SAR Data with Wishart-derived Distance Measures[C]//Proc.3th Int.Workshop POLinSAR.Frascati,Italy,2007:01-08.
- [8]ZHANG X,JIAO L,LIU F,et al.Spectral Clustering Ensemble Applied to SAR Image Segmentation[C]//IEEE Transactions on Geoscience and Remote Sensing,2008,46(7):2126-2136.
- [9]ERSAHIN K,CUMMING I G,WARD R K.Segmentation and Classification of Polarimetric SAR Data Using Spectral Graph Partitioning[C]//IEEE Transactions on Geoscience and Remote Sensing,2010,48(1):164-174.
- [10]REN X,MALIK J.Learning a Classification Model for Segmentation[C]//Proc.9th Int.Conf.Computer Vision,2003:10-17.
- [11]ACHANTA R,SHAJI A,SMITH K,et al.Slic Superpixels[R].EPFL Technical Report,2010.
- [12]LI W,BENIE G B,HE D C,et al.Watershed-based Hierarchical SAR Image Segmentation[J].International Journal of Remote Sensing,1999,20(17):3377-3390.
- [13]马秀丽,焦李成.基于分水岭-谱聚类的[J].红外与毫米波学报,2008,27(6):452-456.
- [14]LI Y,SHI H,JIAO L,et al.Quantum Evolutionary Clustering Algorithm Based on Watershed Applied to SAR Image Segmentation[J].Neurocomputing,2012(87):90-98.
- [15]CHARLESS F,SERGE B,FAN C,et al.Spectral Grouping Using the Nystrom method[C]//IEEE Transactions on Pattern Analysis and Machine Intelligence,2004,26(2):214-225.