首页 > 论文 > 光学学报 > 38卷 > 4期(pp:428001--1)

一种极化SAR影像分类中的半监督降维方法

A Semi-Supervised Dimension Reduction Method for Polarimetric SAR Image Classification

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

针对极化合成孔径雷达(SAR)应用中存在的特征冗余问题,结合线性判别分析(LDA)和局部线性嵌入(LLE)的思想,提出一种半监督降维算法:半监督局部判别分析(SLDA)。该算法首先基于LLE的局部保持特性建立正则项,以避免学习中的过拟合问题。然后,在标记样本集上进行正则化的判别分析,以增强算法的推广能力,同时保持所有样本点在原始空间的局部几何结构。利用RADARSAT-2和AIRSAR卫星获得的Flevoland地区的全极化SAR数据进行降维实验,结果表明SLDA提取的低维特征具有“类内紧聚,类间分离”的特性;进一步的分类实验结果表明,SLDA只需1‰~2‰的标记样本就能使分类精度达到90%左右,分类性能优于其他对比方法。

Abstract

Aiming at the problem of feature redundancy in polarimetric synthetic aperture radar (SAR) application, a semi-supervised dimension reduction algorithm: semi-supervised local discriminant analysis (SLDA) is proposed by combining the thoughts of linear discriminant analysis (LDA) and locally linear embedding (LLE). Firstly, the regularization term is established based on local preserving property of LLE to avoid overfitting problem during learning. Then, discriminant analysis with regularization is performed on labeled data set in order to improve the generalization ability and preserve the local geometric structure in original space for the whole data. Dimension reduction experiments are performed on all polarimetric SAR data from Flevoland regions obtained by RADARSAT-2 and AIRSAR satellites. The results show that the low dimensional features extracted by SLDA has the characteristics of “intra compactness and inter separation”. Further classification experiment results show that SLDA can make the classification accuracy reach about 90% only with 1‰-2‰ labeled samples, and the classification performance of SLDA is superior to other comparison algorithms.

Newport宣传-MKS新实验室计划
补充资料

中图分类号:TP391.4

DOI:10.3788/aos201838.0428001

所属栏目:遥感与传感器

基金项目:高分辨率对地观测重大专项技术研究与开发项目(03-Y20A10-9001-15/16)

收稿日期:2017-10-19

修改稿日期:2017-11-16

网络出版日期:--

作者单位    点击查看

谢欣芳:武汉大学电子信息学院, 湖北 武汉 430072
徐新:武汉大学电子信息学院, 湖北 武汉 430072
董浩:武汉大学电子信息学院, 湖北 武汉 430072
吴晗:武汉大学电子信息学院, 湖北 武汉 430072
李珞茹:武汉大学电子信息学院, 湖北 武汉 430072

联系人作者:徐新(xinxu@whu.edu.cn)

备注:谢欣芳(1994-),女,硕士研究生,主要从事合成孔径雷达图像解译方面的研究。E-mail: xiexinfang@whu.edu.cn

【1】Uhlmann S, Kiranyaz S. Integrating color features in polarimetric SAR image classification[J]. IEEE Transactions on Geoscience & Remote Sensing, 2014, 52(4): 2197-2216.

【2】Zou T, Yang W, Dai D, et al. Polarimetric SAR image classification using multifeatures combination and extremely randomized clustering forests[J]. EURASIP Journal on Advances in Signal Processing, 2009, 2010: 465612.

【3】Shi L, Zhang L, Yang J, et al. Supervised graph embedding for polarimetric SAR image classification[J]. IEEE Geoscience & Remote Sensing Letters, 2013, 10(2): 216-220.

【4】Shi L, Zhang L, Zhao L, et al. The potential of linear discriminative Laplacian eigenmaps dimensionality reduction in polarimetric SAR classification for agricultural areas[J]. ISPRS Journal of Photogrammetry & Remote Sensing, 2013, 86(12): 124-135.

【5】Cai D, He X, Han J. Semi-supervised discriminant analysis[C]. IEEE International Conference on Computer Vision, 2007: 1-7.

【6】Zhang P Q, Tan X, Xu X C, et al. Hyperspectral imagery feature extraction based on kernel semi-supervised discriminant analysis[J]. Journal of Geomatics Science and Technology, 2016, 33(3): 258-262.
张鹏强, 谭熊, 余旭初, 等. 基于核半监督判别分析的高光谱影像特征提取[J]. 测绘科学技术学报, 2016, 33(3): 258-262.

【7】Sun X, Huang P P, Tu S T, et al. Polarimetric SAR image classification using multiple-feature fusion and ensemble learning[J]. Journal of Radars, 2016, 5(6): 692-700.
孙勋, 黄平平, 涂尚坦, 等. 利用多特征融合和集成学习的极化SAR图像分类[J]. 雷达学报, 2016, 5(6): 692-700.

【8】Zhu D X. Semi-supervised dimensionality reduction methods for polarimetric SAR classification[D]. Xi′an: Xidian University, 2015: 20-50.
朱德祥. 极化SAR半监督降维方法[D]. 西安: 西安电子科技大学, 2015: 20-50.

【9】Song C, Xu X, Gui R, et al. Polarimetric synthetic aperture radar feature analysis and classification based on multi-layer support vector machine classifier[J]. Journal of Computer Application, 2017, 37(1): 224-250.
宋超, 徐新, 桂容, 等. 基于多层支持向量机的极化合成孔径雷达特征分析与分类[J]. 计算机应用, 2017, 37(1): 244-250.

【10】Roweis S T, Saul L K. Nonlinear dimensionality reduction by locally linear embedding[J]. Science, 2000, 290(5500): 2323-2326.

【11】Liu H, Zhu D, Yang S, et al. Semisupervised feature extraction with neighborhood constraints for polarimetric SAR classification[J]. IEEE Journal of Selected Topics in Applied Earth Observations & Remote Sensing, 2016, 9(7): 3001-3015.

【12】Ye Z, Bai L, Nian Y J. Hyperspectral image classification algorithm based on Gabor feature and locality-preserving dimensionality reduction[J]. Acta Optica Sinica, 2016, 36(10): 1028003.
叶珍, 白璘, 粘永健. 基于Gabor特征与局部保护降维的高光谱图像分类算法[J]. 光学学报, 2016, 36(10): 1028003.

【13】Zhang J J, Zhou X Y, Liu Q. Improved dimensionality reduction algorithm of large-scale hyperspectral scenes using manifold[J]. Acta Optica Sinica, 2013, 33(11): 1128001.
张晶晶, 周晓勇, 刘奇. 一种改进的大尺度高光谱流形降维算法[J]. 光学学报, 2013, 33(11): 1128001.

【14】Wang Y C, Guo J B, Zhou L Y. Image Hash algorithm based on data dimension reduction and symmetric binary pattern[J]. Laser & Optoelectronics Progress, 2017, 54(2): 021004.
王彦超, 郭静博, 周丽宴. 基于数据降维与对称二值模式的图像Hash算法[J]. 激光与光电子学进展, 2017, 54(2): 021004.

引用该论文

Xie Xinfang,Xu Xin,Dong Hao,Wu Han,Li Luoru. A Semi-Supervised Dimension Reduction Method for Polarimetric SAR Image Classification[J]. Acta Optica Sinica, 2018, 38(4): 0428001

谢欣芳,徐新,董浩,吴晗,李珞茹. 一种极化SAR影像分类中的半监督降维方法[J]. 光学学报, 2018, 38(4): 0428001

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF