Hyperspectral Image Classification Based on Sample Augment and Spectral Space Iteration

ZHANG Aizhu; LI Renren; LIANG Shuneng; SUN Genyun; FU Hang

doi:10.13203/j.whugis20220708

您当前的位置：

首页 >

文章列表页 >

Hyperspectral Image Classification Based on Sample Augment and Spectral Space Iteration

Photogrammetry and Remote Sensing | 更新时间：2026-11-05

- Hyperspectral Image Classification Based on Sample Augment and Spectral Space Iteration
- Geomatics and Information Science of Wuhan University Vol. 50, Issue 1, Pages: 97-109(2025)
- 作者机构：
  
  1.中国石油大学（华东）海洋与空间信息学院，山东青岛，266580
  2.青岛海洋科学与技术试点国家实验室海洋矿产资源评价与探测技术功能实验室，山东青岛，266237
  3.自然资源部国土卫星遥感应用中心，北京，100048
- 作者简介：
- 基金信息：
- DOI：10.13203/j.whugis20220708
  CLC： P237
- Received：17 May 2023，
  
  Published：05 January 2025
- 稿件说明：
移动端阅览
张爱竹,李忍忍,梁树能，等.联合样本扩充和谱空迭代的高光谱影像分类[J].武汉大学学报（信息科学版）,2025,50(1):97-109.

ZHANG Aizhu,LI Renren,LIANG Shuneng,et al.Hyperspectral Image Classification Based on Sample Augment and Spectral Space Iteration[J].Geomatics and Information Science of Wuhan University,2025,50(1):97-109.
张爱竹,李忍忍,梁树能，等.联合样本扩充和谱空迭代的高光谱影像分类[J].武汉大学学报（信息科学版）,2025,50(1):97-109. DOI：10.13203/j.whugis20220708

ZHANG Aizhu,LI Renren,LIANG Shuneng,et al.Hyperspectral Image Classification Based on Sample Augment and Spectral Space Iteration[J].Geomatics and Information Science of Wuhan University,2025,50(1):97-109. DOI：10.13203/j.whugis20220708

摘要

光谱和空间信息结合可以显著提升高光谱影像的分类性能。然而，真实场景中标记样本数量有限制约了分类精度。为充分利用高光谱的谱空信息并解决标记样本数量不足问题，提出了一种基于嵌套滑动窗口样本扩充和谱空迭代的高光谱影像分类方法。首先，对高光谱影像进行主成分变换，降低光谱维数；然后，提出一种基于嵌套滑动窗口的样本扩充方法，在最优子窗口中选取代表性像素加入训练集；最后，使用迭代支持向量机-联合双边滤波器进行分类，得到最终分类图。在印第安松、帕维亚大学和萨利纳斯数据集上分别选取2%、0.2%和0.2%的训练样本，所提算法分类精度分别高达94.42%、95.82%和96.39%。实验结果表明，扩充训练样本集和充分利用光谱空间信息能有效提升分类精度，所提算法在有限训练样本情况下优于其他先进对比算法。

Abstract

Objectives

The combination of spectral and spatial information can significantly improve the classification performance of hyperspectral images. However

the number of labeled training samples is limi‑ted in real scenes

which restricts the classification accuracy. To make full use of spectral spatial information and solve the problem of limited number of hyperspectral image labeled samples

we propose a hyperspectral image classification method based on nested sliding window sample augment and spectral space iteration.

Methods

First

principal component transform is used to reduce spectral dimension of hyperspectral image. Then

a sample augment method based on nested sliding windows is proposed

in which representative pixels are selected from the optimal sub windows and added to the training set. Finally

iterative support vector machine and joint bilateral filter are used for classification

and a decision rule is proposed to terminate iteration to obtain the final classification diagram.

Results

It is verified on three hyperspectral datasets: Indian Pines

Pavia University and Salinas. The experimental results show that when the training samples are limited and the samples of the three datasets are 2%

0.2% and 0.2% respectively

the classification accuracy of the algorithm reaches 94.42%

95.82% and 96.39% respectively. Compared with spectral classifier support vector machine

the overall classification accuracy of the proposed algorithm on the three datasets is improved by 28.1%

20.1% and 13.1% respectively. Compared with S

-PCA based on small samples

the overall classific

ation accuracy of the proposed algorithm on the three datasets is improved by about 3%

5.5% and 4.5% respectively.

Conclusions

The proposed algorithm can obtain satisfactory classification results in the case of limited training samples

which is superior to other advanced comparison algorithms.

关键词

Keywords

references

HE L ， LI J ， LIU C ， et al . Recent Advances on Spectral‑Spatial Hyperspectral Image Classification： An Overview and New Guidelines ［J］.IEEE Transa‑ctions on Geoscience and Remote Sensing， 2018 ， 56 （ 3 ）： 1579 - 1597 .

IMANI M ， GHASSEMIAN H . An Overview on Spectral and Spatial Information Fusion for Hyperspectral Image Classification： Current Trends and Challenges ［J］. Information Fusion， 2020 ， 59 ： 59 - 83 .

张良培，刘蓉，杜博 . 使用量子优化算法进行高光谱遥感影像处理综述［J］. 武汉大学学报 <math id="M170"><mo stretchy="false">(</mo></math> https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=72168085&type= 3.04800010 https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=72168102&type= 0.76200002 信息科学版）， 2018 ， 43 （ 12 ）： 1811 - 1818 .

ZHANG Liangpei ， LIU Rong ， DU Bo . Hyperspectral Remote Sensing Image Processing by Using Quantum Optimization Algorithm ［J］. Geomatics and Information Science of Wuhan University， 2018 ， 43 （ 12 ）： 1811 - 1818 .

FABIYI S D ， VU H ， TACHTATZIS C ， et al . Varietal Classification of Rice Seeds Using RGB and Hyperspectral Images ［J］. IEEE Access， 2020 （ 8 ）： 22493 - 22505 .

KHAN M J ， KHAN H S ， YOUSAF A ， et al . Modern Trends in Hyperspectral Image Analysis： A Review ［J］. IEEE Access， 2018 （ 6 ）： 14118 - 14129 .

MORONI M ， LUPO E ， MARRA E ， et al . Hyperspectral Image Analysis in Environmental Monito‑ring： Setup of a New Tunable Filter Platform ［J］. Procedia Environmental Sciences， 2013 ， 19 ： 885 - 894 .

SUN G ， FU H ， REN J ， et al . SpaSSA： Superpixelwise Adaptive SSA for Unsupervised Spatial-Spectral Feature Extraction in Hyperspectral Image ［J］. IEEE Trans Cybern， 2022 ， 52 （ 7 ）： 6158 - 6169 .

高奎亮，余旭初，张鹏强，等 . 利用胶囊网络实现高光谱影像空谱联合分类［J］. 武汉大学学报（信息科学版）， 2022 ， 47 （ 3 ）： 428 - 437 .

GAO Kuiliang ， YU Xuchu ， ZHANG Pengqiang ， et al . Hyperspectral Image Spatial-Spectral Classification Using Capsule Network Based Method ［J］. Geomatics and Information Science of Wuhan University， 2022 ， 47 （ 3 ）： 428 - 437 .

JIA X ， RICHARDS J A . Cluster-Space Classification： A Fast k -Nearest Neighbour Classification for Remote Sensing Hyperspectral Data ［C］// IEEE Workshop on Advances in Techniques for Analysis of Remotely Sensed Data ， GreenBelt， MD， USA， 2003 .

MOUNTRAKIS G ， IM J ， OGOLE C . Support Vector Machines in Remote Sensing： A Review ［J］. ISPRS Journal of Photogrammetry and Remote Sensing， 2011 ， 66 （ 3 ）： 247 - 259 .

ZHANG Y ， CAO G ， LI X ， et al . Cascaded Random Forest for Hyperspectral Image Classification ［J］. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing， 2018 ， 11 （ 4 ）： 1082 - 1094 .

TARABALKA Y ， FAUVEL M ， CHANUSSOT J ， et al . SVM- and MRF-Based Method for Accurate Classification of Hyperspectral Images ［J］. IEEE Geoscience and Remote Sensing Letters， 2010 ， 7 （ 4 ）： 736 - 740 .

KANG X ， LI S ， BENEDIKTSSON J A . Spectral‑Spa‑tial Hyperspectral Image Classification with Edge-Preserving Filtering ［J］. IEEE Transactions on Geoscience and Remote Sensing， 2014 ， 52 （ 5 ）： 2666 - 2677 .

ZHONG S ， CHANG C L ， ZHANG Y . Iterative Edge Preserving Filtering Approach to Hyperspectral Image Classification ［J］. IEEE Geoscience and Remote Sensing Letters， 2019 ， 16 （ 1 ）： 90 - 94 .

职露，余旭初，邹滨，等 . 多层级二值模式的高光谱影像空-谱分类［J］. 武汉大学学报（信息科学版）， 2019 ， 44 （ 11 ）： 1659 - 1666 .

ZHI Lu ， YU Xuchu ， ZOU Bin ， et al . A Multi-Layer Binary Pattern Based Method for Hyperspectral Imagery Classification Using Combined Spatial-Spectral Characteristics ［J］. Geomatics and Information Science of Wuhan University， 2019 ， 44 （ 11 ）： 1659 - 1666 .

KANG X ， XIANG X ， LI S ， et al . PCA-Based Edge-Preserving Features for Hyperspectral Image Classification ［J］. IEEE Transactions on Geoscience and Remote Sensing， 2017 ， 55 （ 12 ）： 7140 - 7151 .

FANG L ， HE N ， LI S ， et al . A New Spatial-Spectral Feature Extraction Method for Hyperspectral Images Using Local Covariance Matrix Representation ［J］. IEEE Transactions on Geoscience and Remote Sensing， 2018 ， 56 （ 6 ）： 3534 - 3546 .

HE N ， PAOLETTI M E ， HAUT J M ， et al . Feature Extraction with Multiscale Covariance Maps for Hyperspectral Image Classification ［J］.IEEE Transactions on Geoscience and Remote Sensing， 2019 ， 57 （ 2 ）： 755 - 769 .

FU H ， SUN G ， REN J ， et al . Fusion of PCA and Segmented-PCA Domain Multiscale 2-D-SSA for Effective Spectral-Spatial Feature Extraction and Data Classification in Hyperspectral Imagery ［J］. IEEE Transactions on Geoscience and Remote Sensing， 2022 ， 60 （ 1 ）： 1 - 14 .

JIANG J ， MA J ， CHEN C ， et al . SuperPCA： A Superpixelwise PCA Approach for Unsupervised Feature Extraction of Hyperspectral Imagery ［J］. IEEE Transactions on Geoscience and Remote Sensing， 2018 ， 56 （ 8 ）： 4581 - 4593 .

ZHANG X ， JIANG X ， JIANG J ， et al . Spectral-Spatial and Superpixelwise PCA for Unsupervised Feature Extraction of Hyperspectral Imagery ［J］. IEEE Transactions on Geoscience and Remote Sensing， 2022 ， 60 （ 2 ）： 1 - 10 .

田彦平，陶超，邹峥嵘，等 . 主动学习与图的半监督相结合的高光谱影像分类［J］. 测绘学报， 2015 ， 44 （ 8 ）： 919 - 926 .

TIAN Yanping ， TAO Chao ， ZOU Zhengrong ， et al . Semi-supervised Graph-Based Hyperspectral Image Classification with Active Learning ［J］. Acta Geodetica et Cartographica Sinica， 2015 ， 44 （ 8 ）： 919 - 926 .

WANG L ， HAO S ， WANG Q ， et al . Semi-supervised Classification for Hyperspectral Imagery Based on Spatial-Spectral Label Propagation ［J］. ISPRS Journal of Photogrammetry and Remote Sensing， 2014 ， 97 （ 1 ）： 123 - 137 .

CUI B ， MA X ， ZHAO F ， et al . A Novel Hyperspectral Image Classification Approach Based on Multiresolution Segmentation with a Few Labeled Samples ［J］. International Journal of Advanced Robotic Systems， 2017 ， 14 （ 3 ）： 1 - 10 .

ZHENG C ， WANG N ， CUI J . Hyperspectral Image Classification with Small Training Sample Size Using Superpixel-Guided Training Sample Enlargement ［J］. IEEE Transactions on Geoscience and Remote Sensing， 2019 ， 57 （ 10 ）： 7307 - 7316 .

CUI B ， CUI J ， HAO S ， et al . Spectral-Spatial Hyperspectral Image Classification Based on Superpixel and Multi-classifier Fusion ［J］. International Journal of Remote Sensing， 2020 ， 41 （ 16 ）： 6157 - 6182 .

YU H ， GAO L ， LIAO W ， et al . Group Sparse Representation Based on Nonlocal Spatial and Local Spectral Similarity for Hyperspectral Imagery Classification ［J］. Sensors， 2018 ， 18 （ 6 ）： 1695 .

SHEN X ， YU H ， YU C ， et al . Global Spatial and Local Spectral Similarity Based Sample Augment and Extended Subspace Projection for Hyperspectral Image Classification ［C］// IEEE International Geoscience and Remote Sensing Symposium ， Brussels， Belgium ， 2021 .

HU J ， SHEN X ， YU H ， et al . Extended Subspace Projection Upon Sample Augmentation Based on Global Spatial and Local Spectral Similarity for Hyperspectral Imagery Classification ［J］. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing， 2021 ， 14 （ 1 ）： 8653 - 8664 .

KANG X ， LI S ， BENEDIKTSSON J A . Feature Extraction of Hyperspectral Images with Image Fusion and Recursive Filtering ［J］. IEEE Transactions on Geoscience and Remote Sensing， 2014 ， 52 （ 6 ）： 3742 - 3752 .

YUAN Y ， JIN M . Multi-type Spectral Spatial Feature for Hyperspectral Image Classification ［J］. Neurocomputing， 2021 ， 492 ： 637 - 650 .

CHENG C ， LI H ， PENG J ， et al . Hyperspectral Image Classification via Spectral-Spatial Random Patches Network ［J］.IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing， 2021 ， 14 （ 1 ）： 4753 - 4764 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Key Technologies and Applications of EasyFeature—An Intelligent Interpretation System for Remote Sensing Images

Oblique Factor Model for Selecting Training Samples

Lightweight Relational Network for Small Sample Hyperspectral Image Classification

High-Resolution L-Band InSAR Study of Intense Near-Field Deformation Associated with Shallow Moderate Earthquakes

Geometric and Frequency-Domain Constrained Single-Step Diffusion for Seabed Terrain Super-Resolution Reconstruction

Related Author

ZHANG Zuxun

WANG Xingkun

ZHAN Yuanzeng

FENG Cunjun

GONG Jinqi

RAO Youzhuo

PANG Shiyan

JIANG Huiwei

Related Institution

School of Remote Sensing and Information Engineering, Wuhan University

Wuhan Daspatial Technology Co. Ltd

National Geomatics Center of China

Faculty of Artificial Intelligence in Education, Central China Normal University

Wuhan Handleray Technology Co. Ltd

AI问答

⁰