Feature extraction of hyperspectral image with semi-supervised multi-graph embedding

Hong HUANG; Yu-xiao TANG; Yu-le DUAN

doi:10.3788/OPE.20202802.0443

您当前的位置：

首页 >

文章列表页 >

Feature extraction of hyperspectral image with semi-supervised multi-graph embedding

Information Sciences | 更新时间：2020-07-16

- Feature extraction of hyperspectral image with semi-supervised multi-graph embedding
- Optics and Precision Engineering Vol. 28, Issue 2, Pages: 443-456(2020)
- 作者机构：
  
  重庆大学光电技术与系统教育部重点实验室，重庆 400044
- 作者简介：
- 基金信息：
- DOI：10.3788/OPE.20202802.0443
  CLC： TP394.1; TH691.9
- Received：07 May 2019，
  
  Revised：06 July 2019，
  
  Accepted：06 July 2019，
  
  Published：25 February 2020
- 稿件说明：
移动端阅览
Hong HUANG, Yu-xiao TANG, Yu-le DUAN. Feature extraction of hyperspectral image with semi-supervised multi-graph embedding[J]. Optics and precision engineering, 2020, 28(2): 443-456.
DOI：

Hong HUANG, Yu-xiao TANG, Yu-le DUAN. Feature extraction of hyperspectral image with semi-supervised multi-graph embedding[J]. Optics and precision engineering, 2020, 28(2): 443-456. DOI： 10.3788/OPE.20202802.0443.

摘要

针对传统图嵌入方法仅采用单一图结构无法有效表征高维数据中复杂本征结构，本文提出了一种半监督多图嵌入(SSMGE)方法，并应用于高光谱影像特征提取。该方法首先利用标记样本的类内、类间近邻点来构建类内超图、类间超图、类内普通图、类间普通图，然后通过无标记样本的近邻点和远离点构建无监督本征超图和惩罚超图，并以多图协同方式来表征高维数据间的复杂几何关系，实现鉴别特征提取。本文提出的SSMGE方法不仅能有效揭示数据点间超图和普通图的结构，而且在低维嵌入空间中增强同类数据聚集性和非同类数据的远离性，提取的鉴别特征可改善地物分类精度。在PaviaU和Urban高光谱数据集上进行了分类实验，本文方法的总体分类精度分别可达到85.92%和79.74%。相比普通图嵌入和超图方法，该算法明显提升了地物的分类性能。

Abstract

Traditional graph embedding methods often use single graph structures for feature extraction (FE).However

these methods cannot effectively represent the complex intrinsic structuresof high-dimensional data. To address this problem

a Semi-Supervised Multi-Graph Embedding (SSMGE) algorithm was proposed for FE of Hyper Spectral Images (HSIs). First

the SSMGE method constructed one of each of intra-and inter-class hypergraphs and intra-and inter-class graphs through intra-and inter-class neighbors of labeled samples.In addition

it constructs an unsupervised intrinsic hypergraph and a penalty hypergraph using unlabeled samples. The fusion of graphs and hypergraphs can effectively characterize the complex relationships in high-dimensional data. The SSMGE method not only effectively reveals the intrinsic structure of an HSI by exploring the collaboration of graphs and hypergraphs but also enhances the discriminative ability of extracted features in low-dimensional embedding space.This enables improved classification performance of HSI data. Experimental results on the PaviaU and Urban hyperspectral datasets show that the overall accuracies of the proposed method reached 85.92% and 79.74%

respectively. The SSMGE method can significantly improve classification performance as compared with some state-of-the-art FE methods.

关键词

Keywords

references

闫敬文 , 陈宏达 , 刘蕾 . 高光谱图像分类的研究进展 . 光学精密工程 , 2019 . 27 ( 3 ): 680 - 693 . http://www.eope.net/CN/abstract/abstract17944.shtml http://www.eope.net/CN/abstract/abstract17944.shtml .

J W YAN , H D CHEN , L LIU . Research progress in classification of hyperspectral images . Opt. Precision Eng , 2019 . 27 ( 3 ): 680 - 693 . http://www.eope.net/CN/abstract/abstract17944.shtml http://www.eope.net/CN/abstract/abstract17944.shtml .

黄鸿 , 陈美利 , 段宇乐 , 等 . 空-谱协同流形重构的高光谱影像分类 . 光学精密工程 , 2018 . 26 ( 7 ): 1827 - 1836 . http://www.eope.net/CN/abstract/abstract17689.shtml http://www.eope.net/CN/abstract/abstract17689.shtml .

H HUANG , M L CHEN , Y L DUAN , 等 . Hyperspectral image classification with spatial-spectral collaboration and manifold reconstruction error . Opt. Precision Eng , 2018 . 26 ( 7 ): 1827 - 1836 . http://www.eope.net/CN/abstract/abstract17689.shtml http://www.eope.net/CN/abstract/abstract17689.shtml .

M L CHEN , Q WANG , X L LI . Discriminant analysis with graph learning for hyperspectral image classification . Remote Sensing , 2018 . 10 ( 6 ): 836 http://cn.bing.com/academic/profile?id=4a352c48e23412f1598df2994418969e&encoded=0&v=paper_preview&mkt=zh-cn http://cn.bing.com/academic/profile?id=4a352c48e23412f1598df2994418969e&encoded=0&v=paper_preview&mkt=zh-cn .

L HE , J LI , C LIU , 等 . Recent advances on spectral-spatial hyperspectral image classification: an overview and new guidelines . IEEE Transactions on Geoscience and Remote Sensing , 2017 . 56 ( 3 ): 1579 - 1597 . http://cn.bing.com/academic/profile?id=dbb5e20e765a01d68f491886465e9b94&encoded=0&v=paper_preview&mkt=zh-cn http://cn.bing.com/academic/profile?id=dbb5e20e765a01d68f491886465e9b94&encoded=0&v=paper_preview&mkt=zh-cn .

王庆超 , 付光远 , 汪洪桥 , 等 . 多核融合多尺度特征的高光谱影像地物分类 . 光学精密工程 , 2018 . 26 ( 4 ): 980 - 988 . http://www.eope.net/CN/abstract/abstract17574.shtml http://www.eope.net/CN/abstract/abstract17574.shtml .

Q CH WANG , G Y FU , H Q WANG , 等 . Fusion of multi-scale feature using multiple kernel learning for hyperspectral image land cover classification . Opt. Precision Eng , 2018 . 26 ( 4 ): 980 - 988 . http://www.eope.net/CN/abstract/abstract17574.shtml http://www.eope.net/CN/abstract/abstract17574.shtml .

李志敏 , 张杰 , 黄鸿 , 等 . 面向高光谱图像分类的半监督丛流形学习 . 光学精密工程 , 2015 . 23 ( 5 ): 1434 - 1442 . http://www.eope.net/CN/abstract/abstract15817.shtml http://www.eope.net/CN/abstract/abstract15817.shtml .

ZH M LI , J ZHANG , H HUANG , 等 . Semi-supervised bundle manifold learning for hyperspectral image classification . Opt. Precision Eng , 2015 . 23 ( 5 ): 1434 - 1442 . http://www.eope.net/CN/abstract/abstract15817.shtml http://www.eope.net/CN/abstract/abstract15817.shtml .

MENEZES J, POOJARY N. Dimensionality reduction and classification of hyperspectral images using DWT and DCCF[C]. Mec International Conference on Big Data and Smart City. IEEE , 2016: 47-52.

X KANG , X XIANG , S LI , 等 . PCA-based edge-preserving features for hyperspectral image classification . IEEE Transactions on Geoscience and Remote Sensing , 2017 . 55 ( 12 ): 7140 - 7151 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=dda3d92173b9147a0f974435d3f2ba13 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=dda3d92173b9147a0f974435d3f2ba13 .

J WEN , X FANG , J CUI , 等 . Robust sparse linear discriminant analysis . IEEE Transactions on Circuits & Systems for Video Technology , 2018 . 29 ( 2 ): 390 - 403 . http://cn.bing.com/academic/profile?id=0890d2aa3fe0ed5695521ec9535e31e2&encoded=0&v=paper_preview&mkt=zh-cn http://cn.bing.com/academic/profile?id=0890d2aa3fe0ed5695521ec9535e31e2&encoded=0&v=paper_preview&mkt=zh-cn .

J C XU , H Y MU , Y WANG , 等 . Feature genes selection using supervised locally linear embedding and correlation coefficient for microarray classification . Computational and Mathematical Methods in Medicine , 2018 . 2018 1 - 11 . http://cn.bing.com/academic/profile?id=f885f15962f50fd9717e4e1f19f5c5fb&encoded=0&v=paper_preview&mkt=zh-cn http://cn.bing.com/academic/profile?id=f885f15962f50fd9717e4e1f19f5c5fb&encoded=0&v=paper_preview&mkt=zh-cn .

X XU , H YANG , C LIAN , 等 . Self-learning control using dual heuristic programming with global Laplacian Eigenmaps . IEEE Transactions on Industrial Electronics , 2017 . 64 ( 12 ): 9517 - 9526 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=a6323abf700e03d3e0692ae38f63d0e0 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=a6323abf700e03d3e0692ae38f63d0e0 .

W SUN , G YANG , B DU , 等 . A sparse and low-rank near-isometric linear embedding method for feature extraction in hyperspectral imagery classification . IEEE Transactions on Geoscience and Remote Sensing , 2017 . 55 ( 7 ): 4032 - 4046 . http://cn.bing.com/academic/profile?id=623c9f7728a77b733c3fc4ee318a6d93&encoded=0&v=paper_preview&mkt=zh-cn http://cn.bing.com/academic/profile?id=623c9f7728a77b733c3fc4ee318a6d93&encoded=0&v=paper_preview&mkt=zh-cn .

Y H YONG , Q Z XIAO . Multi-phase batch process monitoring based on multiway weighted global neighborhood preserving embedding method . Journal of Process Control , 2018 . 69 44 - 57 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=17389d93c5d0b08aeef4f36175264580 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=17389d93c5d0b08aeef4f36175264580 .

Q YU , R WANG , B N LI , 等 . Robust locality preserving projections with cosine-based dissimilarity for linear dimensionality reduction . IEEE Access , 2017 . 5 ( 99 ): 2676 - 2684 . http://cn.bing.com/academic/profile?id=2bc2ca62922a9414af4bf55d09a3f2e3&encoded=0&v=paper_preview&mkt=zh-cn http://cn.bing.com/academic/profile?id=2bc2ca62922a9414af4bf55d09a3f2e3&encoded=0&v=paper_preview&mkt=zh-cn .

J ZHONG , Y W PANG , Y YUAN , 等 . Relevance and irrelevance graph based marginal Fisher analysis for image search reranking . Signal Processing , 2016 . 121 139 - 152 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=d4f0d56b0955c8a58a92fdcc98532383 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=d4f0d56b0955c8a58a92fdcc98532383 .

M VAN , H J KANG . Bearing defect classification based on individual wavelet local Fisher discriminant analysis with particle swarm optimization . IEEE Transactions on Industrial Informatics , 2017 . 12 ( 1 ): 124 - 135 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=50c57c3a4ca9a54393d16bfd2512ed02 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=50c57c3a4ca9a54393d16bfd2512ed02 .

F L LUO , H HUANG , Y DUAN , 等 . Local geometric structure feature for dimensionality reduction of hyperspectral imagery . Remote Sensing , 2017 . 9 ( 8 ): 790 http://cn.bing.com/academic/profile?id=9b5d538598026ea2f74b3feba3407166&encoded=0&v=paper_preview&mkt=zh-cn http://cn.bing.com/academic/profile?id=9b5d538598026ea2f74b3feba3407166&encoded=0&v=paper_preview&mkt=zh-cn .

T I DHAMECHA , R SINGH , M VATASA . On incremental semi-supervised discriminant analysis . Pattern Recognition , 2016 . 52 135 - 147 . http://d.old.wanfangdata.com.cn/Periodical/njdxxb201204005 http://d.old.wanfangdata.com.cn/Periodical/njdxxb201204005 .

S GAO , J ZHOU , Y YAN , 等 . Recursively global and local discriminant analysis for semi-supervised and unsupervised dimension reduction with image analysis . Neurocomputing , 2016 . 216 672 - 683 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=9ef6dd803112c946bd492f06075d0283 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=9ef6dd803112c946bd492f06075d0283 .

F L Luo , H HUANG , Z MA , 等 . Semisupervised sparse manifold discriminative analysis for feature extraction of hyperspectral images . IEEE Transactions on Geoscience and Remote Sensing , 2016 . 54 ( 10 ): 6197 - 6211 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=2fa398944a73fbdbdca89e2d4985cf94 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=2fa398944a73fbdbdca89e2d4985cf94 .

H L YUAN , Y Y TANG . Learning with hypergraph for hyperspectral image feature extraction . IEEE Geoscience & Remote Sensing Letters , 2015 . 12 ( 8 ): 1695 - 1699 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=9440fe5778ac72c9303b20f14094a6c7 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=9440fe5778ac72c9303b20f14094a6c7 .

S HUANG , D YANG , Y X GE , 等 . Discriminant hyper-Laplacian projections and its scalable extension for dimensionality reduction . Neurocomputing , 2016 . 173 ( 2 ): 145 - 153 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=87efcdbe1a38893a05fc57a39a688f35 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=87efcdbe1a38893a05fc57a39a688f35 .

Y SUN , S WANG , Q LIU , 等 . Hypergraph embedding for spatial-spectral joint feature extraction in hyperspectral images . Remote Sensing , 2017 . 9 ( 5 ): 506 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=MDPI000000184156 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=MDPI000000184156 .

S WANG , Y SUN , R HANG , 等 . Spatial-spectral locality constrained elastic net hypergraph for hyperspectral image clustering . International Journal of Remote Sensing , 2017 . 38 ( 23 ): 7374 - 7388 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=4b1752bb8ccd4df3b9f8462495820186 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=4b1752bb8ccd4df3b9f8462495820186 .

S YAN , D XU , B ZHANG , 等 . Graph embedding and extensions: A general framework for dimensionality reduction . IEEE Transactions on Pattern Analysis and Machine Intelligence , 2007 . 29 ( 1 ): 40 - 51 . http://cn.bing.com/academic/profile?id=10f1981f47d358d7e20563ff4926c1e6&encoded=0&v=paper_preview&mkt=zh-cn http://cn.bing.com/academic/profile?id=10f1981f47d358d7e20563ff4926c1e6&encoded=0&v=paper_preview&mkt=zh-cn .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Spatial-spectral discriminant analysis for hyperspectral image classification

End-to-end recognition of nighttime wildlife based on semi-supervised learning

Hyperspectral images feature extraction and classification based on fractional differentiation

Lightweight deep global-local knowledge distillation network for hyperspectral image scene classification

Semi-supervised instance object detection method based on SVD co-training

Related Author

Bang-huan HOU

Min-li YAO

Wei-min JIA

Feng-gan ZHANG

Dao-ping WANG

LU Han

CUI Bolun

WAN Huayang

Related Institution

Rocket Force Engineering University

Beijing Institute of Space Mechanics & Electricity

School of Mechatronic Engineering and Automation，Shanghai University

School of Electronic Engineering， Xi’an University of Posts and Telecommunications

School of Electronic Engineering， Xidian University

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