Feature Extraction of Hyperspectral Images With Semisupervised Graph Learning

被引:35
作者
Luo, Renbo [1 ,2 ]
Liao, Wenzhi [2 ]
Huang, Xin [3 ]
Pi, Youguo [1 ]
Philips, Wilfried [2 ]
机构
[1] South China Univ Technol, Sch Automat Sci & Engn, Guangzhou 510640, Guangdong, Peoples R China
[2] Univ Ghent, Dept Telecommun & Informat Proc, B-9000 Ghent, Belgium
[3] Wuhan Univ, Sch Remote Sensing & Informat Engn, Wuhan 430079, Peoples R China
关键词
Classification; feature extraction; graph; hyperspectral images (HSIs); semisupervised; LINEAR DISCRIMINANT-ANALYSIS; DIMENSIONALITY REDUCTION; NEAREST-NEIGHBOR; CLASSIFICATION;
D O I
10.1109/JSTARS.2016.2522564
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
We propose a semisupervised graph learning (SEGL) method for feature extraction of hyperspectral remote sensing imagery in this paper. The proposed SEGL method aims to build a semisupervised graph that can maximize the class discrimination and preserve the local neighborhood information by combining labeled and unlabeled samples. In our semisupervised graph, we connect labeled samples according to their label information and unlabeled samples by their nearest neighborhood information. By sorting the mean distance between a unlabeled sample and labeled samples of each class, we connect the unlabeled sample with all labeled samples belonging to its nearest neighborhood class. Moreover, the proposed SEGL better models the actual differences and similarities between samples, by setting different weights to the edges of connected samples. Experimental results on four real hyperspectral images (HSIs) demonstrate the advantages of our method compared to some related feature extraction methods.
引用
收藏
页码:4389 / 4399
页数:11
相关论文
共 50 条
[1]   Semisupervised Local Discriminant Analysis for Feature Extraction in Hyperspectral Images [J].
Liao, Wenzhi ;
Pizurica, Aleksandra ;
Scheunders, Paul ;
Philips, Wilfried ;
Pi, Youguo .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2013, 51 (01) :184-198
[2]   Feature Extraction of Hyperspectral Images With Semi-supervised Sparse Graph Learning [J].
Luo, Renbo ;
Wen, Ya ;
Liu, Xingnan ;
Wu, Zhifeng .
2018 FIFTH INTERNATIONAL WORKSHOP ON EARTH OBSERVATION AND REMOTE SENSING APPLICATIONS (EORSA), 2018, :444-447
[3]   Latent Low-Rank Projection Learning with Graph Regularization for Feature Extraction of Hyperspectral Images [J].
Pan, Lei ;
Li, Hengchao ;
Dai, Xiang ;
Cui, Ying ;
Huang, Xifeng ;
Dai, Lican .
REMOTE SENSING, 2022, 14 (13)
[4]   Collaborative representation-based semisupervised feature extraction of hyperspectral images using attraction points [J].
Li, Fanduo ;
Lv, Meng ;
Jing, Ling .
JOURNAL OF APPLIED REMOTE SENSING, 2020, 14 (02)
[5]   Semisupervised Sparse Manifold Discriminative Analysis for Feature Extraction of Hyperspectral Images [J].
Luo, Fulin ;
Huang, Hong ;
Ma, Zezhong ;
Liu, Jiamin .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2016, 54 (10) :6197-6211
[6]   Semisupervised Feature Extraction of Hyperspectral Image Using Nonlinear Geodesic Sparse Hypergraphs [J].
Duan, Yule ;
Huang, Hong ;
Wang, Tao .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2022, 60
[7]   Semisupervised Feature Extraction Based on Collaborative Label Propagation for Hyperspectral Images [J].
Zhang, Jinxin ;
Zhang, Peng ;
Li, Baocheng ;
Jing, Ling ;
Lv, Tongling .
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2020, 17 (11) :1958-1962
[8]   Feature Extraction of Hyperspectral Image Based on Sparse Representation and Learning Graph Regularity [J].
Zhang Minghua ;
Luo Hongling ;
Song Wei ;
Huang Dongmei ;
He Qi ;
Su Cheng .
ACTA PHOTONICA SINICA, 2021, 50 (04)
[9]   Semisupervised dimensionality reduction for hyperspectral images based on the combination of semisupervised learning and metric learning [J].
Ahmadi, Seyyed Ali ;
Mehrshad, Nasser ;
Razavi, Seyyed Mohammad .
IMAGING SCIENCE JOURNAL, 2018, 66 (05) :320-327
[10]   Semisupervised collaborative representation graph embedding for hyperspectral imagery [J].
Li, Yi ;
Zhang, Jinxin ;
Lv, Meng ;
Jing, Ling .
JOURNAL OF APPLIED REMOTE SENSING, 2020, 14 (03)