基于半监督稀疏鉴别嵌入的高光谱遥感影像分类

黄鸿; 曲焕鹏

doi:10.3788/OPE.20142202.0434

您当前的位置：

首页 >

文章列表页 >

基于半监督稀疏鉴别嵌入的高光谱遥感影像分类

信息科学 | 更新时间：2020-08-13

- 基于半监督稀疏鉴别嵌入的高光谱遥感影像分类
- Hyperspectral remote sensing image classification based on SSDE
- 光学精密工程 2014年22卷第2期页码：434-442
- 作者机构：
  
  1. 重庆大学光电技术及系统教育部重点实验室重庆,400044
  2. 重庆川仪自动化股份有限公司技术中心重庆,401121
- 作者简介：
- 基金信息：
- DOI：10.3788/OPE.20142202.0434
  中图分类号： TP751
- 收稿日期：2013-06-21，
  
  纸质出版日期：2014-02-20
- 稿件说明：
移动端阅览
黄鸿,曲焕鹏,. 基于半监督稀疏鉴别嵌入的高光谱遥感影像分类[J]. 光学精密工程, 2014,22(2): 434-442

HUANG Hong,QU Huan-peng,. Hyperspectral remote sensing image classification based on SSDE[J]. Editorial Office of Optics and Precision Engineering, 2014,22(2): 434-442
黄鸿,曲焕鹏,. 基于半监督稀疏鉴别嵌入的高光谱遥感影像分类[J]. 光学精密工程, 2014,22(2): 434-442 DOI： 10.3788/OPE.20142202.0434.

HUANG Hong,QU Huan-peng,. Hyperspectral remote sensing image classification based on SSDE[J]. Editorial Office of Optics and Precision Engineering, 2014,22(2): 434-442 DOI： 10.3788/OPE.20142202.0434.

摘要

为了有效利用已标记与未标记样本提高高光谱遥感影像分类精度

提出一种新的半监督流形学习方法——半监督稀疏鉴别嵌入算法(SSDE)。该算法结合了近邻流形结构及稀疏性的优点

不仅保留样本间的稀疏重构关系

而且通过引入少量有标记的训练样本以及大量无标记训练样本来获得高维数据的内在属性以及低维流形结构

实现鉴别特征提取

提高分类精度。在Washington DC Mall和Indian Pine数据集上的分类识别实验表明

该算法能够较为有效地发现高维空间中数据的内蕴结构

分类性能比其他算法有明显的提升。在随机选取8个有类别标记和60个无类别标记的数据作为训练样本的情况下

本文提出的SSDE算法在上述两个数据集上的分类精度分别达到了77.36%和97.85%。

Abstract

To improve the classification accuracy of hyperspectral remote sensing images by utilizing labeled and unlabeled samples

a new semi-supervised manifold learning method called Semi-supervised Sparse Discriminant Embedding (SSDE) is proposed. By combining the advantages of manifold structure among classes and sparsity

the algorithm not only preserves the sparse reconstruction relationship between the samples

but also gets the intrinsic attribute of high dimensional data and the manifold structure of low dimensional data by introducing a few labeled training samples and a large number of unlabeled training samples .So

it extracts the discriminant feature of data and improves the classification accuracy . The classification experiments in Washington DC Mall and Indian Pine data set show that the method is a more effective way to find the internal structure of data in a high dimensional space. Compared to other methods

the SSDE obviously improves the classification performance. By taking randomly selected 8 training samples with classification labels and 60 ones without classification labels as examples

the highest classification precision of SSDE respectively reach 77.36% in Indian Pine and 97.85% in Washington DC Mall data set.

关键词

Keywords

references

陈进. 高光谱图像分类方法研究[D].长沙:国防科技大学,2010.

CHEN J. Hyperspectral image classification method[D].Changsha:National University of Defense Technology,2010.(in Chinese)

苏红军,杜培军,盛业华. 一种基于分形维数的高光谱遥感波段选择算法研究[J].测绘通报,2007(3):23-26.

SU H J,DU P J,SHENG Y H. A study of band selection algorithm of hyperspectral RS based on fractal dimensions [J].Bulletin of Surveying and Mapping,2007(3):23-26.(in Chinese)

黄鸿, 秦高峰, 冯海亮. 半监督流形学习及其在遥感影像分类中的应用[J].光学精密工程,2011,19(12):3025-3033.

HUANG H,QIN G F,FENG H L. Semi-supervised manifold learning and its application to remote sensing image classification[J].Opt. Precision Eng.,2011,19(12):3025-3033.(in Chinese)

BACHMANN C M,AINSWORTH T L, FUSINA R A. Exploiting manifold geometry in hyperspectral imagery [J]. IEEE Trans. On Geosciences and Remote Sensing,2005,43(3):884-897.

EDWARD J J. A Use’s Guide To Principal Components[M].New York: A Wiley-Interscience Publication,1992.

BELHUMEUR P N,HESPANHA J P,KRIEGMAN D. Eigenfaces vs. Fisherfaces: recognition using class specific linear projection [J].IEEE Trans. on Pattern Analysis and Machine Intelligence,1997,19(7):711-720.

HE X F,YAN SH CH, HU Y X, et al.. Face recognition using laplacianfaces [J]. IEEE Trans. on Pattern Analysis and Machine Intelligence,2005,27(3):328-340.

HE X F,CAI D,YAN SH CH, et al.. Neighborhood preserving embedding [C]. Proceedings of the 10th IEEE Int’l Conf. Computer Vision (ICCV’2005),Beijing,2005,2:1208-1213.

QIAO L SH,CHEN S C,TAN X Y. Sparsity preserving projections with applications to face recognition[J]. Pattern Recognition,2010,43 (1): 331-341.

WRIGHTJ, YANGAY, GANESHA, et al.. Robust face recognition via sparse representation [J].IEEE Transactions on Pattern Analysis Machine Intelligence,2009,31(2):210-227.

INABA F K,SALLES E O T. Face recognition based on sparse representation and joint sparsity model with matrix completion [J].IEEE Latin America Transactions,2012,10(1):1344-1351.

黄勇. 稀疏保留投影及在表情识别中的应用[J].计算机应用,2012,30(2):100-102.

HUANG Y. Sparse preserving projection and its application to expression recognition[J].Journal of Computer Applications,2012,30(2):100-102.(in Chinese)

黄鸿. 图嵌入框架下流形学习理论及应用研究[D].重庆:重庆大学,2008.

HUANG H. Research on manifold learning theories and applications under the framework of gragh embedding[D].Chongqing: Chongqing University,2008.(in Chinese)

ROWEIS S T,SAUL L K. Nonlinear dimensionality reduction by locally linear embedding[J].Science,2000,290(5500):2323-2326.

DEERWESTER S C,DUMAIS S T,LANDAUER T K, et al.. Indexing by latent semantic analysis[J]. Journal of the American Society of Information Science,1990,41(6):391-407.

FU Y, YAN S C,HUANG T S. Classification and feature extraction by simplexization[J].IEEE Trans. on Information Forensics and Security,2008,3(1):91-100.

王立志, 黄鸿, 冯海亮. 基于SSMFA与kNNS算法的高光谱遥感影像分类[J].电子学报,2012,40(4):780-787.

WANG L ZH,HUANG H,FENG H L. Hyperspecral remote sensing image classification based on SSMFA and kNNS[J].Acta Electronica Sinica,2012,40(4):780-787.(in Chinese)

GREGORY S,TREVORL D,PIOTR I. Nearest-neighbor Methods in Learning and Vision: Theory and Practice[M]. London: MIT Press,2006.

浏览量

429

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于稀疏鉴别嵌入的高光谱遥感影像分类

融合局部和全局结构的流形学习

面向高光谱图像分类的半监督双流网络

面向高光谱影像分类的深度流形重构置信网络

面向高光谱影像分类的多特征流形鉴别嵌入