Hyperspectral Remote Sensing Image Classification Based on SDE

HUANG Hong1; 2; YANG Mei1; ZHANG Man-ju3

doi:10.3788/OPE.20132111.2922

您当前的位置：

首页 >

文章列表页 >

Hyperspectral Remote Sensing Image Classification Based on SDE

更新时间：2020-08-12

- Hyperspectral Remote Sensing Image Classification Based on SDE
- Optics and Precision Engineering Vol. 21, Issue 11, Pages: 2922-2930(2013)
- 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 400030
  2. 重庆川仪自动化股份有限公司技术中心，重庆 401121
  3. 酒泉卫星发射中心，甘肃酒泉 735300
- 作者简介：
- 基金信息：
- DOI：10.3788/OPE.20132111.2922
  CLC： TP751.1
- Received：28 March 2013，
  
  Revised：28 April 2013，
  
  Published Online：22 November 2013，
  
  Published：15 November 2013
- 稿件说明：
移动端阅览
黄鸿, 杨媚, 张满菊. 基于稀疏鉴别嵌入的高光谱遥感影像分类[J]. 光学精密工程, 2013,21(11): 2922-2930

HUANG Hong, YANG Mei, ZHANG Man-Ju. Hyperspectral Remote Sensing Image Classification Based on SDE[J]. Editorial Office of Optics and Precision Engineering, 2013,21(11): 2922-2930
黄鸿, 杨媚, 张满菊. 基于稀疏鉴别嵌入的高光谱遥感影像分类[J]. 光学精密工程, 2013,21(11): 2922-2930 DOI： 10.3788/OPE.20132111.2922.

HUANG Hong, YANG Mei, ZHANG Man-Ju. Hyperspectral Remote Sensing Image Classification Based on SDE[J]. Editorial Office of Optics and Precision Engineering, 2013,21(11): 2922-2930 DOI： 10.3788/OPE.20132111.2922.

摘要

稀疏保持投影(SPP)是一种基于l1图的新型降维算法，它利用样本间的稀疏重构关系建图，但是SPP为非监督算法，分类效果受到限制。针对此问题，本文提出了一种新的稀疏流形学习算法-稀疏鉴别嵌入(SDE)。该算法在利用样本的稀疏重构关系建图时引入了样本的类别信息，并通过优化目标函数来得到投影矩阵，使得不同类的数据点在低维嵌入空间中尽可能地分散开。SDE通过结合数据稀疏性及类间流形结构的优点，不仅保留样本间的稀疏重构关系，而且通过引入训练样本的类别信息实现稀疏鉴别特征提取，更有利于分类。在Urban和Washington DC Mall数据集上的实验结果表明：SDE算法比其他算法的分类性能有明显的提升，在每类随机选取16个训练样本的情况下，SDE算法的分类精度分别达到了73.47%和98.35%。

Abstract

Sparsity Preserving Projection(SPP) is a new algorithm for reducing dimensions of dataset based on a weighted graph( l1-Graph)

which reconstructs the weighted graph by the sparse relationship of train samples. However

SPP is an unsupervised learning method essentially

and it doesnt employ any prior knowledge of class to extract identification features. For this issue

a novel algorithm

Sparsity Discriminant Embedding (SDE) is proposed. Unlike SPP

the SDE adopts the class information of train samples when it constructs weighted graph of sparse reconstruction relationship. The projection matrix of the SDE is obtained via optimizing objective function and making different kinds of data points separate in the low-dimensional embedding space via a projection. By combining both interclass manifold structure and sparse property

the SDE keeps the sparse reconstructive relationships of dataset

and employs the class information of train samples to increase the classification rate. The experimental results obtained from operations on Urban and Washington DC Mall datasets show that the classification efficiency of the SDE has improved greatly as compared to those of other algorithms. The obtained classification accuracy has been 73.47% and 98.35%

respectively

when 16 samples of each class are randomly selected for training.

关键词

Keywords

references

童庆禧,张兵,郑芬兰.高光谱原理技术与应用[M].北京:高等教育出版社,2008.TONG Q X,ZHANG B,ZHENG F L.Principles and Application of Hyperspectral Remote Sensing[M].Beijing:Higher Education Press, 2008.(in Chinese)[2]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)[3]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)[4]乔立山.基于图的降维技术研究及应用[D].南京:南京航空航天大学, 2009.QIAO L SH.Research on graph-based dimensionality reduction and its applications[D].Nanjing:Nanjing University of Aeronautics and Astronautics, 2009.(in Chinese)[5]姚明海,瞿心昱.基于自适应子空间在线PCA的手势识别[J]. 模式识别与人工智能, 2011,24(2):299-304.YAO M H,QU X Y.Hand gesture recognition based on online PCA with adaptive subspace[J]. Pattern Recognition and Artificial Intelligence, 2011,24(2):299-304.(in Chinese)[6]沈凌云,郎百和,朱明.一种基于人工神经网络的人脸识别方法[J].液晶与显示,2011,26(6):836-840.SHEN L Y,LANG B H,ZHU M.Face recognition method based on artificial neural network [J].Chinese Journal of Liquid Crystals and Displays, 2011,26(6): 836-840.(in Chinese)[7]林玉娥,李敬兆,梁兴柱,等.直接正交鉴别保局投影算法[J]. 光电子激光, 2012,23(3):561-565. LIN Y E,LI J ZH,LIANG X ZH,et al.. Direct orthogonal discriminant locality preserving projections method[J].Journal of OptoelectronicsLaser, 2012,23(3):561-565.(in Chinese)[8]张大明,符茂胜,罗斌,等.基于二维近邻保持嵌入的图像识别[J].模式识别与人工智能, 2011,24(6):810-815.ZHANG D M,FU M SH,LUO B,et al.. Image recognition with two-dimensional neighbourhood preserving embedding [J].Pattern Recognition and Artificial Intelligence, 2011,24(6):810-815.(in Chinese)[9]杜海顺,柴秀丽,汪凤泉,等.一种邻域保持判别嵌入人脸识别方法[J].仪器仪表学报, 2010,31(3):625-629.DU H SH,CHAI X L,WANG F Q,et al..Face recognition method using neighborhood preserving discriminant embedding [J].Chinese Journal of Scientific Instrument, 2010,31(3):625-629.(in Chinese)[10]ANDREW B J,PANG Y H.Analysis on supervised neighborhood preserving embedding [J]. IEICE Electronics Express., 2009,6(23):1631-1637.[11]HAN X H,CHEN Y W.A supervised nonlinear neighborhood embedding of color histogram for image indexing[C].IEEE International Conference on Image Processing(ICIP),San Diego,United states, 2008,949-952.[12]彭澄宇.图像稀疏建模理论与应用研究[D].重庆:重庆大学, 2012.PENG CH Y.Image the sparse modeling theory and applied research[D].Chongqing:Chongqing University, 2012.(in Chinese)[13]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.[14]YAN S C,XU D,ZHANG B Y,et al..Graph embedding and extensions:a general framework for dimensionality reduction[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007,29(1):40-51.[15]QIAO L S.Sparsity preserving projections with applications to face recognition [J].Pattern Recognition, 2010,43(1):331-341.[16]LU G F,JIN Z,ZOU J.Face recognition using discriminant sparsity neighborhood preserving embedding [J].Knowledge-Based Systems, 2012,31:119-127.[17]REN G B,ZHANG J,MA Y.Generative model based semi-supervised learning method of remote sensing image classification [J].Journal of Remote Sensing, 2010,14(6):1090-1104.[18]FAN M Y,QIAO H,ZHANG B.Discriminative sparsity preserving projections for semisupervised dimensionality reduction[J].IEEE Signal Processing Letters, 2012,19(7):391-394.[19]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)[20]LANDGREBE D A.Signal Theory Methods in Multispectral Remote Sensing[M].Hoboken,NJ:Wiley, 2003.[21]于长淞,方超.基于小波变换的ESPI图像去噪及边缘提取[J].液晶与显示,2011,26(6):818-822.YU CH S,FANG CH.ESPI image denoising and edge extraction based on wavelet transform[J].Chinese Journal of Liquid Crystals and Displays, 2011,26(6):818-822.(in Chinese)[22]郑玉权.温室气体遥感探测仪器发展现状[J].中国光学，2011，4（6）：546-561.ZHENG Y Q. Development status of remote sensing instruments for greenhouse gases [J]. Chinese Optics, 2011,4(6):449-560. (in Chinese)[23]刘倩倩，郑玉权.超高分辨率光谱定标技术发展概况[J].中国光学，2012，5（6）：566-577.LIU Q Q, ZHENG Y Q. Development of spectral calibration technologies with ultra-high resolutions [J].Chinese Optics, 2012,5(6):566-577. (in Chinese)

Views

105

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Hyperspectral remote sensing image classification based on SSDE

Fusion of local and globle structures for manifold learning

Semi-supervised dual path network for hyperspectral image classification

Deep manifold reconstruction belief network for hyperspectral remote sensing image classification

Multi-features manifold discriminant embedding for hyperspectral image classification

Related Author

HUANG Hong

QU Huan-peng

HUANG Hong

LI Jian-wei

FENG Hai-liang

Hong HUANG

Zhen ZHANG

Ling JI

Related Institution

Key Laboratory of Opto-electronic Technique of the Ministry of Education, Chongqing University

The Technical Center of Chongqing Chuanyi Automation Co., Ltd.

Professor Mobile Station,Chongqing Institute of Technology

Key Laboratory of Optoelectronic Technology and System， Ministry of Education， Chongqing University

The 34th Research Institute of China Electronics Technology Group Corporation

AI问答

Address：No.3888 Dong Nanhu Road, Changchun, Jilin, China Postal code：130033
Tel：0431-86176855 Email：gxjmgc@ciomp.ac.cn
Technical support is provided by Beijing Founder electronics co., LTD 吉ICP备11002662号-17 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰