结合ICA相干斑抑制的全极化SAR图像分类

被引:5
作者
王海江 [1 ]
皮亦鸣 [1 ]
陈红艳 [2 ]
机构
[1] 电子科技大学电子工程学院
[2] 西南科技大学信息工程学院
关键词
独立分量分析; 全极化SAR; 相对相位信息; 相干斑抑制; Pauli分解; 颜色通道;
D O I
暂无
中图分类号
TN957.52 [数据、图像处理及录取];
学科分类号
080904 ; 0810 ; 081001 ; 081002 ; 081105 ; 0825 ;
摘要
本文提出了一种结合相干斑抑制的全极化SAR(Synthetic Aperture Radar)图像分类新方法.该方法先对图像数据做Pauli分解,获得三个极化组合通道,并分别用三种颜色表示这三个极化组合;再用独立分量分析稀疏编码(ICA-SCS)算法对各颜色通道进行相干斑抑制,最后把三个颜色通道混合,实现了对图像信息的分类.该方法很好的保留了极化通道间的相对相位信息,同时,相干斑抑制后的数据直接用于图像分类,不需要再做任何极化通道组合.对真实SAR图像的分类结果表明,该方法对分类效果和精度有明显改善.
引用
收藏
页码:2185 / 2189
页数:5
相关论文
共 9 条
[1]  
New decomposition of the radar target scatteringmatrix. Krogager E. Electronics Letters . 1990
[2]  
Independent Component Analysis. Hyvarinen A,et al. . 2001
[3]  
An entropy based classification schemefor land applications of polarimetric SAR. Cloudy S R,,Pottier E. IEEE Transac-tions on Geosciences and Remote Sensing . 1997
[4]  
A novel theory of SAR image restorationand enhancement with ICA. Chen C H,Wang X. Geoscience and Remote Sens-ing Symposium,IGARSS’04Proceedings . 2004
[5]  
Noisy independent component analysis,maximumlikelihood estimation,and competitive learning. Hyvarinen A. IEEE Inter-national Conference on Neural Networks-Conference Proceed-ings . 1998
[6]  
Polarimetric speckle reduction using multi-texture maximum likelihood method. Pi Yi-ming,et al. IEE Electronic Letter . 2003
[7]  
Proceedings[C]. 2011 2nd Asia-Pacific Conference on Wearable Computing Systems (APWCS 2011);2011 International Conference on Intelligent Control and Information Technology(ICICIT 2011),2011
[8]  
Properties of speckle integratedwith a finite aperture and logarithmically transformed. Arsenault H H,April G. Journal of the Optical Society of America . 1976
[9]  
Polarimetric SAR speckle filteringand its implication for classification. Lee J S,Mitchell R,et al. IEEE Transactions onGeosciences and Remote Sensing . 1999