应用相关近邻局部线性嵌入算法的高光谱遥感影像分类

刘嘉敏; 罗甫林; 黄鸿; 刘亦哲

doi:10.3788/OPE.20142206.1668

您当前的位置：

首页 >

文章列表页 >

应用相关近邻局部线性嵌入算法的高光谱遥感影像分类

信息科学 | 更新时间：2020-08-13

- 应用相关近邻局部线性嵌入算法的高光谱遥感影像分类
- Classification of Hyperspectral remote sensing images using correlation neighbor LLE
- 光学精密工程 2014年22卷第6期页码：1668-1676
- 作者机构：
  
  重庆大学光电技术及系统教育部重点实验室重庆,400044
- 作者简介：
- 基金信息：
  
  国家自然科学基金资助项目（No.61101168，No.41371338）();中国博士后科学基金资助项目（No.2012M511906，No.2013T60837）(
- DOI：10.3788/OPE.20142206.1668
  中图分类号： TP751.1
- 收稿日期：2013-07-12，
  
  修回日期：2013-09-10，
  
  纸质出版日期：2014-06-25
- 稿件说明：
移动端阅览
刘嘉敏, 罗甫林, 黄鸿等. 应用相关近邻局部线性嵌入算法的高光谱遥感影像分类[J]. 光学精密工程, 2014,22(6): 1668-1676

LIU Jia-min, LUO Fu-lin, HUANG Hong etc. Classification of Hyperspectral remote sensing images using correlation neighbor LLE[J]. Editorial Office of Optics and Precision Engineering, 2014,22(6): 1668-1676
刘嘉敏, 罗甫林, 黄鸿等. 应用相关近邻局部线性嵌入算法的高光谱遥感影像分类[J]. 光学精密工程, 2014,22(6): 1668-1676 DOI： 10.3788/OPE.20142206.1668.

LIU Jia-min, LUO Fu-lin, HUANG Hong etc. Classification of Hyperspectral remote sensing images using correlation neighbor LLE[J]. Editorial Office of Optics and Precision Engineering, 2014,22(6): 1668-1676 DOI： 10.3788/OPE.20142206.1668.

摘要

传统的局部线性嵌入（LLE）算法需用欧氏距离度量近邻，但欧氏距离只表示两点间的直线距离，在高维空间中不一定能反映数据间的真实空间分布，导致近邻选取不稳定。针对此问题，本文提出了相关近邻（CN）LLE（CN-LLE）和相关最近邻分类（CNN）算法。提出的算法首先利用相关系数度量数据间的近邻，实现更准确的局部重构，提取鉴别特征；然后用CNN对低维嵌入特征进行分类。在KSC和Indian Pine高光谱遥感数据集上的地物分类实验结果表明：本文提出的CN-LLE+CNN算法比LLE、LLE+CNN和CN-LLE等算法的总分类精度提升了2.11%~11.55%，Kappa系数提升了0.026~0.143。由于该算法增加了近邻为同类的概率，便于更有效地提取同类数据的鉴别特征，且有更好的稳定性，故能更有效地实现高光谱遥感数据的地物分类。

Abstract

Traditional Locally Linear Embedding (LLE) manifold learning algorithm uses Euclidean distance to measure neighbor points. However

Euclidean distance represents the straight line distance between two points and does not necessarily reflect the actual data distribution in a high dimension space

which leads to the instability of neighbor point selecttion. In order to solve this problem

an algorithm based on Correlation Neighbor LLE (CN-LLE) and Correlation Nearest Neighbor (CNN) classification is proposed. This algorithm uses the correlation coefficient of data to measure the neighbor points and to achieve more effective local reconstruction to extract the distinguishing character. Then

it uses the CNN to classify the reduced dimension data. The experiment results from KSC and Indian Pine hyperspectral remote sensing data sets show that the total accuracy of the proposed CN-LLE+CNN algorithm is improved by 2.11%-11.55% and the Kappa coefficient is improved 0.026-0.143 as compared with those of LLE

LLE+CNN and CN-LLE. The CN-LLE+CNN algorithm increases the probability of the same class neighbor

can extract the distinguishing characters of the same data effectively and has a better stability. This algorithm can effectively classify hyperspectral remote sensing data of ground objects.

关键词

Keywords

references

YANG J M,KUO B C,YU P T, et al.. A dynamic subspace method for hyperspectral image classification [J]. IEEE Transactions on Geoscience and Remote Sensing, 2010, 48(7): 2840-2853.

黄鸿,杨媚,张满菊,等. 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 H,YANG M,ZHANG M J, et al.. Hyperspectral remote sensing image classification based on SDE [J]. Opt. Precision Eng.,2013, 21(11):2922-2930.(in Chinese)

董超,田联房. 最速上升关联向量机高光谱影像分类[J]. 光学精密工程, 2012, 20(6):1398-1405. DONG CH, TIAN L F. Hyperspectral image classification by steepest ascent relevance vector machine [J]. Opt. Precision Eng., 2012, 20(6): 1398-1405.(in Chinese)

BACHMANN C M, AINSWORTH T L. Exploiting manifold geometry in hyperspectral imagery [J]. IEEE Transactions on Geoscience and Remote Sensing, 2005, 43(3): 441-454.

WEN J H, TIAN ZH, SHE H W, et al.. Feature extraction of hyperspectral images based on preserving neighborhood discriminant embedding [C].2010 International Conference on Image Analysis and Signal Processing (IASP). Zhejiang, 2010: 257-262.

CHEN Y C, CRAWFORD M M, GHOSH J. Applying nonlinear manifold learning to hyperspectral data for land cover classification [C].IGARSS: Proceedings of the 2005 IEEE International Geoscience and Remote Sensing Symposium, Washington, DC: IEEE Computer Society, 2005: 24-29.

QIAN H E, CHEN G. A new nonlinear dimensionality reduction method with application to hyperspectral image analysis [C].IGARSS: Proceeding of the 2007 IEEE International Geoscience and Remote Sensing Symposium,Washington, DC: IEEE Computer Society, 2007: 270-273.

TENENBAUM J B,SILVA V D, LANGFORD J C. A global geometric framework for nonlinear dimensionality reduction [J]. Science, 2000, 290: 2319-2323.

PAN Y, GE S S, MAMUN A Al. Weighted locally linear embedding for dimension reduction [J]. Pattern Recognition, 2009, 42: 798-811.

CARVALHO JUNIOR O A, GUIMARAES R F, GILLESPIE A R, et al.. A new approach to change vector analysis using distance and similarity measures[J]. Remote Sensing, 2011, 3(11):2473-2493.

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

HOSSEINI A, Ghassemian H. Classification of hyperspectral and multispectral images by using fractal dimension of spectral response curve [C].20th Iranian Conference on Electrical Engineering (ICEE). Tehran, 2012:1452-1457.

YE CH Q,LIU X L,ZHANG ZH Y Z, et al.. Multi-Spectral and panchromatic image fusion based on region correlation coefficient in nonsubsampled Contourlet transform domain [C].2010 Fourth International Conference on Genetic and Evolutionary Computing (ICGEC), Shenzhen,2010: 517-521.

YU R L, QIANG W, YU E L, et al.. Hyperspectral image classification using kernel method based on the correlation coefficients of neighbor bands [C].Second IITA International Conference on Geoscience and Remote Sensing (IITA-GRS), Qingdao, 2010, 2: 230-233.

FALIE D, DAVID L. Correlation coefficient based on independent component analysis [C].9th International Conference on Communications (COMM), Bucharest, 2012: 59-62.

XUEJUN Z, XU Q. Spectral characteristics research of the hyperspectral image based on the correlation matrix [C].Fourth International Symposium on Information Science and Engineering (ISISE), Shanghai, 2012: 372-374.

HAM J, CHEN Y, CRAWFORD M M, et al.. Investigation of the random forest framework for classification of hyperspectral data [J]. IEEE Transactions on Geoscience and Remote Sensing, 2005, 43(3): 492-501.

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. Hyperspectral remote sensing image classification based on SSMFA and kNNS [J]. Acta Electronica Sinica, 2012, 40(4): 780-787.(in Chinese)

浏览量

363

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

一种新颖的人脸图像超分辨率技术研究

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

空-谱协同流形重构的高光谱影像分类