Machine-Learning-Based Hyperspectral Image Processing
1st Edition
Published on 13. April 2026
Book
Hardback
704 pages
978-1-394-26785-9 (ISBN)
Description
An authoritative deep dive into the most recent machine learning approaches to hyperspectral remote sensing image processing
In Machine-Learning-Based Hyperspectral Image Processing, a team of distinguished researchers led by Dr. Bing Zhang delivers an up-to-date discussion of machine learning-based approaches to hyperspectral image analysis. The contributors comprehensively review machine learning approaches to hyperspectral image denoising and super-resolution tasks, offering coverage of a variety of perspectives.
The book also explores the most recent research on machine learning hyperspectral unmixing methods and hyperspectral image classification. It explains the algorithms used for hyperspectral image target and change detection, as well.
Readers will also find:
A thorough introduction to the novel concept of applying advanced machine learning techniques to the analysis of hyperspectral imagery
Comprehensive explorations of the most recent developments in this technology and its applications
Practical discussions of how to effectively process and extract valuable insights from hyperspectral data
Complete treatments of a variety of hyperspectral remote sensing image processing tasks, including classification, target detection, and change detection.
Perfect for postgraduate students and research scientists with an interest in the subject, Machine-Learning-Based Hyperspectral Image Processing will also benefit researchers, academicians, and students engaged in machine learning-based approaches to image analysis.
In Machine-Learning-Based Hyperspectral Image Processing, a team of distinguished researchers led by Dr. Bing Zhang delivers an up-to-date discussion of machine learning-based approaches to hyperspectral image analysis. The contributors comprehensively review machine learning approaches to hyperspectral image denoising and super-resolution tasks, offering coverage of a variety of perspectives.
The book also explores the most recent research on machine learning hyperspectral unmixing methods and hyperspectral image classification. It explains the algorithms used for hyperspectral image target and change detection, as well.
Readers will also find:
A thorough introduction to the novel concept of applying advanced machine learning techniques to the analysis of hyperspectral imagery
Comprehensive explorations of the most recent developments in this technology and its applications
Practical discussions of how to effectively process and extract valuable insights from hyperspectral data
Complete treatments of a variety of hyperspectral remote sensing image processing tasks, including classification, target detection, and change detection.
Perfect for postgraduate students and research scientists with an interest in the subject, Machine-Learning-Based Hyperspectral Image Processing will also benefit researchers, academicians, and students engaged in machine learning-based approaches to image analysis.
More details
Language
English
Place of publication
United States
Publishing group
John Wiley & Sons Inc
Target group
Professional and scholarly
Product notice
sewn/stitched
Cloth over boards
ISBN-13
978-1-394-26785-9 (9781394267859)
Copyright in bibliographic data and cover images is held by Nielsen Book Services Limited or by the publishers or by their respective licensors: all rights reserved.
Schweitzer Classification
Other editions
Additional editions
E-Book
04/2026
1st Edition
Wiley
€120.99
Available for download
E-Book
04/2026
1st Edition
Wiley
€120.99
Available for download
Person
Bing Zhang, PhD, is Full Professor and Deputy Director of the Aerospace Information Research Institute, CAS. He has authored over 300 publications and currently serves as the Chief Editor for the Chinese Journal of Remote Sensing and Associate Editor for the IEEE Transactions on Geoscience and Remote Sensing.
Content
About the Editor xxi
List of Contributors xxiii
1 Review for Machine-Learning-Based Hyperspectral Image Analysis 1
He Sun and Ruitong Du
1.1 Overview 1
1.2 Denoising 2
1.3 Super-resolution 4
1.4 Unmixing 7
1.5 Classification 8
1.6 Target Detection 11
1.7 Change Detection 13
1.8 Experimental Datasets 15
1.9 Chapter Arrangement and Writing Purpose 19
References 20
2 Hyperspectral Image Denoising Based on Low-rank Regularization 31
Yong Chen, Hongyu Chen, and Wei He
Mathematical Symbols Used in This Chapter 31
2.1 Introduction 31
2.2 Model-driven Approaches 32
2.3 Data-driven Approaches 41
2.4 Conclusion and Outlook 46
References 47
3 Hyperspectral Image Denoising Based on Tensor Models 51
Yu-Bang Zheng, Jian-Li Wang, and Xi-Le Zhao
Mathematical Symbols Used in This Chapter 51
3.1 Introduction 51
3.2 HSI Reconstruction 52
3.3 Tensor Modeling-based HSI Reconstruction Methods 53
3.4 Numerical Experiments 66
3.5 Conclusion 67
References 68
4 Hyperspectral Image Denoising Based on Spatial-Spectral Joint Constraints 73
Bin Zhao, Magnus O. Ulfarsson, Jakob Sigurdsson, Jon Atli Benediktsson, and Jocelyn Chanussot
Mathematical Symbols Used in This Chapter 73
4.1 Non-local Means Low-rank Approximation 73
4.2 Wavelet-based Block Low-rank Representations 79
4.3 Conclusions 84
References 84
5 Hyperspectral Image Reconstruction Based on Spectral Super-resolution 87
Prof. Yanfeng Gu
Mathematical Symbols Used in This Chapter 87
5.1 Introduction 87
5.2 Experimental Datasets and Evaluation Indicators 90
5.3 A Learning Subpixel Super-resolution Model Based on Coupled Dictionary 95
5.4 A Collaborative Spectral-super-resolution Model Based on Adaptive Learning 106
5.5 Conclusion 124
References 124
6 Hyperspectral Image Reconstruction From Supervision to Blindness 129
Jie Xie, Jie Wu, Zhicheng Wang, Lina Zhuang, and Leyuan Fang
Mathematical Symbols Used in This Chapter 129
6.1 Introduction 129
6.2 Full Supervised HSI SR 132
6.3 Weakly Supervised HSI SR 137
6.4 Self-supervised HSI SR 153
6.5 Blind HSI SR 169
6.6 Conclusion and Discussion 181
References 183
7 Hyperspectral Image Reconstruction Based on Unsupervised Learning 191
Ying Qu, Jiangsan Zhao, Hairong Qi, Chiman Kwan, and Liqiang Zhang
Mathematical Symbols Used in This Chapter 191
7.1 Introduction 191
7.2 Problem Formulation 193
7.3 Unsupervised Hyperspectral Image Super-resolution with Dirichlet Net 193
7.4 Unsupervised and Unregistered Hyperspectral Image Super-resolution 196
7.5 Improving SR Performance with Endmember-assisted Camera Response Function Learning 200
7.6 Conclusions 201
References 201
8 Hyperspectral Image Reconstruction Based on Adaptive Learning 207
Ke Zheng, Jiaxin Li, Lianru Gao, and Bing Zhang
Mathematical Symbols Used in This Chapter 207
8.1 Introduction 207
8.2 Problem Formulation 208
8.3 Numerical Model-guided Nonlinear Spectral Unmixing 209
8.4 Experiment and Results 218
8.5 Conclusion 227
References 227
9 Hyperspectral Unmixing with Nonnegative Matrix Factorization 229
Jun Li, Yuanchao Su, Shaoquan Zhang, and Ruoqing Xu
9.1 Introduction 229
9.2 Methodologies 230
9.3 Experiments 235
9.4 Conclusion 239
References 239
10 Hyperspectral Unmixing Based on Low-rank Representation and Sparse Constraint 243
Xiangrong Zhang, Jingyan Zhang, Guanchun Wang, and Licheng Jiao
10.1 Introduction 243
10.2 Linear Unmixing Algorithms 244
10.3 Hybrid Unmixing Algorithms 251
10.4 Experiments 257
10.5 Conclusions 266
References 267
11 Endmember Purification and Geographical Knowledge Graph-guided Endmember Selection 271
Wenfei Luo and Rui Wu
11.1 Introduction 271
11.2 Endmember Purification 272
11.3 Unmixing with Geographic Knowledge Graph 283
11.4 Experimental Results and Analysis 289
11.5 Conclusion 298
Acknowledgment 298
References 298
12 Hyperspectral Unmixing Based on Deep Autoencoder Networks 301
Yuanchao Su, Jun Li, Lianru Gao, Ruoqing Xu, Zhiqing Zhu, and Paolo Gamba
12.1 Introduction 301
12.2 Methodologies 302
12.3 Experimental Results 314
12.4 Conclusion 318
12.5 Discussion 318
References 318
13 Numerical-model-guided Nonlinear Spectral Unmixing 321
Bin Yang and Bin Wang
13.1 Introduction 321
13.2 Nonlinear Mixture Models and Extensions 324
13.3 Numerical-model-guided Nonlinear Spectral Unmixing 327
13.4 Conclusions 344
13.5 Challenges and Future Directions 346
References 347
14 Spatial-Spectral Gabor-based Hyperspectral Image Classification 351
Sen Jia, Shuyu Zhang, Qi Ren, Wangquan He, Meng Xu, and Jiasong Zhu
14.1 Spatial-Spectral Gabor Feature Extraction 351
14.2 Pixel-wise Gabor Features for Hyperspectral Image Classification 359
14.3 Superpixel-wise Gabor Features for HSI Classification 372
References 386
15 Domain Adaptation for Hyperspectral Image Classification 389
Chong Li, Weiwei Sun, Jiangtao Peng, and Kai Ren
15.1 Basic Concepts of Domain Adaptation 389
15.2 Domain Adaptation for Hyperspectral Image Classification 390
15.3 Deep Domain-adaptation-based Hyperspectral Image Classification 391
15.4 Conclusion 402
References 402
16 Unsupervised Domain Adaptation for Classification of Hyperspectral Images 405
li Ma and Qian Du
16.1 Introduction 405
16.2 Unsupervised Domain Adaptation Problem 408
16.3 Traditional Unsupervised Domain Adaptation Methods 408
16.4 Deep-learning-based Unsupervised Domain Adaptation Methods 411
16.5 Experimental Results and Analysis 414
16.6 Conclusions 420
References 420
17 Lightweight Models for Hyperspectral Image Classification 425
Hongmin Gao, Shufang Xu, Zhonghao Chen, and Yiyan Zhang
17.1 Introduction 425
17.2 Lightweight Feature Extraction-based Hyperspectral Image Classification 427
17.3 Experimental Results and Analysis 438
17.4 Conclusion 446
References 448
18 Ensemble Method Based Hyperspectral Image Classification 453
Wei Feng and Mengdao Xing
18.1 Background 453
18.2 Introduction to Ensemble Learning 454
18.3 Ensemble Learning in HSI Classification 459
18.4 Conclusion 467
References 468
19 Spectral-Spatial Hyperspectral Image Classification Based on Sparse Representation 471
Haoyang Yu, Jia Jia, Chuhan Shen, Jiaochan Hu, Chein-I Chang, and Lianru Gao
19.1 Introduction 471
19.2 Related Models Description 472
19.3 Hyperspectral Image Classification Based on Sparse Representation 475
19.4 Experimental Results and Analysis 485
19.5 Conclusion 495
Acknowledgment 496
References 496
20 Hyperspectral Image Classification with Limited Samples 499
Yuebin Wang, Liqiang Zhang, Bing Zhang, Antonio Plaza, and Xiao Xiang Zhu
20.1 Introduction 499
20.2 Method 503
20.3 Experimental Results 509
20.4 Conclusions 519
References 520
21 Constrained Energy Minimization Based Hyperspectral Image Target Detection 521
Zhenwei Shi, Zhengxia Zou, Bowen Chen, and Liqin Liu
21.1 Introduction 521
21.2 Overview of CEM 522
21.3 CEM-based Methods 525
21.4 Conclusions 539
References 541
22 Hyperspectral Target Detection Based on Weighted Cauchy Distance Graph and Local Adaptive Collaborative Representation 543
Wei Li and Kun Gao
22.1 Introduction 543
22.2 Related Works 545
22.3 The Proposed Detection Methodology 546
22.4 Experiments and Analysis 551
22.5 Conclusion 558
References 558
23 Weakly Supervised Learning-based Hyperspectral Image Anomaly/Target Detection 561
Weiying Xie, Xin Zhang, Yunsong Li, and Qian Du
23.1 Introduction 561
23.2 Weakly Supervised Hyperspectral Anomaly Detection (WSLRR) 564
23.3 Weakly Supervised Hyperspectral Target Detection (BLTSC) 573
23.4 Rank-aware Hyperspectral Band Selection (R-GAN) 578
23.5 Conclusions 587
References 589
24 Hyperspectral Anomaly Detection via Background-separable Mode 593
Bing Tu, Xianchang Yang, Jun Li, Antonio Plaza, and Kaiyuan Chen
24.1 Hyperspectral Anomaly Detection Using Dual Window Density 593
24.2 Hyperspectral Anomaly Detection Using Reconstruction Fusion of Quaternion Frequency Domain Analysis 603
24.3 Ensemble Entropy Metric for Hyperspectral Anomaly Detection 619
References 631
25 Spectral Change Analysis for Multitemporal Change Detection in Hyperspectral Remote Sensing Images 633
Sicong Liu, Kecheng Du, Xiaohua Tong, and Peijun Du
25.1 Introduction 633
25.2 Related Works 635
25.3 Spectral Change Analysis in Hyperspectral Images 637
25.4 Experimental Setup 643
25.5 Results and Analysis 643
25.6 Conclusion 650
Acknowledgement 650
References 650
26 Challenges and Future Directions 655
Bing Zhang, He Sun, and Ruitong Du
26.1 Challenges and Future Directions in Hyperspectral Image Denoising 655
26.2 Challenges and Future Directions in Hyperspectral (HS) and Multispectral (MS) Image Fusion 657
26.3 Challenges and Future Directions in NMF-based Hyperspectral Unmixing 659
26.4 Challenges and Future Directions in Knowledge Graph-enhanced Hyperspectral Unmixing 660
26.5 Challenges and Future Directions in Numerical Model-guided Nonlinear Hyperspectral Unmixing 660
26.6 Challenges and Future Directions in Hyperspectral Image Classification 661
26.7 Chapter on Challenges and Future Directions in Hyperspectral Target Detection 662
References 663
Index 665
List of Contributors xxiii
1 Review for Machine-Learning-Based Hyperspectral Image Analysis 1
He Sun and Ruitong Du
1.1 Overview 1
1.2 Denoising 2
1.3 Super-resolution 4
1.4 Unmixing 7
1.5 Classification 8
1.6 Target Detection 11
1.7 Change Detection 13
1.8 Experimental Datasets 15
1.9 Chapter Arrangement and Writing Purpose 19
References 20
2 Hyperspectral Image Denoising Based on Low-rank Regularization 31
Yong Chen, Hongyu Chen, and Wei He
Mathematical Symbols Used in This Chapter 31
2.1 Introduction 31
2.2 Model-driven Approaches 32
2.3 Data-driven Approaches 41
2.4 Conclusion and Outlook 46
References 47
3 Hyperspectral Image Denoising Based on Tensor Models 51
Yu-Bang Zheng, Jian-Li Wang, and Xi-Le Zhao
Mathematical Symbols Used in This Chapter 51
3.1 Introduction 51
3.2 HSI Reconstruction 52
3.3 Tensor Modeling-based HSI Reconstruction Methods 53
3.4 Numerical Experiments 66
3.5 Conclusion 67
References 68
4 Hyperspectral Image Denoising Based on Spatial-Spectral Joint Constraints 73
Bin Zhao, Magnus O. Ulfarsson, Jakob Sigurdsson, Jon Atli Benediktsson, and Jocelyn Chanussot
Mathematical Symbols Used in This Chapter 73
4.1 Non-local Means Low-rank Approximation 73
4.2 Wavelet-based Block Low-rank Representations 79
4.3 Conclusions 84
References 84
5 Hyperspectral Image Reconstruction Based on Spectral Super-resolution 87
Prof. Yanfeng Gu
Mathematical Symbols Used in This Chapter 87
5.1 Introduction 87
5.2 Experimental Datasets and Evaluation Indicators 90
5.3 A Learning Subpixel Super-resolution Model Based on Coupled Dictionary 95
5.4 A Collaborative Spectral-super-resolution Model Based on Adaptive Learning 106
5.5 Conclusion 124
References 124
6 Hyperspectral Image Reconstruction From Supervision to Blindness 129
Jie Xie, Jie Wu, Zhicheng Wang, Lina Zhuang, and Leyuan Fang
Mathematical Symbols Used in This Chapter 129
6.1 Introduction 129
6.2 Full Supervised HSI SR 132
6.3 Weakly Supervised HSI SR 137
6.4 Self-supervised HSI SR 153
6.5 Blind HSI SR 169
6.6 Conclusion and Discussion 181
References 183
7 Hyperspectral Image Reconstruction Based on Unsupervised Learning 191
Ying Qu, Jiangsan Zhao, Hairong Qi, Chiman Kwan, and Liqiang Zhang
Mathematical Symbols Used in This Chapter 191
7.1 Introduction 191
7.2 Problem Formulation 193
7.3 Unsupervised Hyperspectral Image Super-resolution with Dirichlet Net 193
7.4 Unsupervised and Unregistered Hyperspectral Image Super-resolution 196
7.5 Improving SR Performance with Endmember-assisted Camera Response Function Learning 200
7.6 Conclusions 201
References 201
8 Hyperspectral Image Reconstruction Based on Adaptive Learning 207
Ke Zheng, Jiaxin Li, Lianru Gao, and Bing Zhang
Mathematical Symbols Used in This Chapter 207
8.1 Introduction 207
8.2 Problem Formulation 208
8.3 Numerical Model-guided Nonlinear Spectral Unmixing 209
8.4 Experiment and Results 218
8.5 Conclusion 227
References 227
9 Hyperspectral Unmixing with Nonnegative Matrix Factorization 229
Jun Li, Yuanchao Su, Shaoquan Zhang, and Ruoqing Xu
9.1 Introduction 229
9.2 Methodologies 230
9.3 Experiments 235
9.4 Conclusion 239
References 239
10 Hyperspectral Unmixing Based on Low-rank Representation and Sparse Constraint 243
Xiangrong Zhang, Jingyan Zhang, Guanchun Wang, and Licheng Jiao
10.1 Introduction 243
10.2 Linear Unmixing Algorithms 244
10.3 Hybrid Unmixing Algorithms 251
10.4 Experiments 257
10.5 Conclusions 266
References 267
11 Endmember Purification and Geographical Knowledge Graph-guided Endmember Selection 271
Wenfei Luo and Rui Wu
11.1 Introduction 271
11.2 Endmember Purification 272
11.3 Unmixing with Geographic Knowledge Graph 283
11.4 Experimental Results and Analysis 289
11.5 Conclusion 298
Acknowledgment 298
References 298
12 Hyperspectral Unmixing Based on Deep Autoencoder Networks 301
Yuanchao Su, Jun Li, Lianru Gao, Ruoqing Xu, Zhiqing Zhu, and Paolo Gamba
12.1 Introduction 301
12.2 Methodologies 302
12.3 Experimental Results 314
12.4 Conclusion 318
12.5 Discussion 318
References 318
13 Numerical-model-guided Nonlinear Spectral Unmixing 321
Bin Yang and Bin Wang
13.1 Introduction 321
13.2 Nonlinear Mixture Models and Extensions 324
13.3 Numerical-model-guided Nonlinear Spectral Unmixing 327
13.4 Conclusions 344
13.5 Challenges and Future Directions 346
References 347
14 Spatial-Spectral Gabor-based Hyperspectral Image Classification 351
Sen Jia, Shuyu Zhang, Qi Ren, Wangquan He, Meng Xu, and Jiasong Zhu
14.1 Spatial-Spectral Gabor Feature Extraction 351
14.2 Pixel-wise Gabor Features for Hyperspectral Image Classification 359
14.3 Superpixel-wise Gabor Features for HSI Classification 372
References 386
15 Domain Adaptation for Hyperspectral Image Classification 389
Chong Li, Weiwei Sun, Jiangtao Peng, and Kai Ren
15.1 Basic Concepts of Domain Adaptation 389
15.2 Domain Adaptation for Hyperspectral Image Classification 390
15.3 Deep Domain-adaptation-based Hyperspectral Image Classification 391
15.4 Conclusion 402
References 402
16 Unsupervised Domain Adaptation for Classification of Hyperspectral Images 405
li Ma and Qian Du
16.1 Introduction 405
16.2 Unsupervised Domain Adaptation Problem 408
16.3 Traditional Unsupervised Domain Adaptation Methods 408
16.4 Deep-learning-based Unsupervised Domain Adaptation Methods 411
16.5 Experimental Results and Analysis 414
16.6 Conclusions 420
References 420
17 Lightweight Models for Hyperspectral Image Classification 425
Hongmin Gao, Shufang Xu, Zhonghao Chen, and Yiyan Zhang
17.1 Introduction 425
17.2 Lightweight Feature Extraction-based Hyperspectral Image Classification 427
17.3 Experimental Results and Analysis 438
17.4 Conclusion 446
References 448
18 Ensemble Method Based Hyperspectral Image Classification 453
Wei Feng and Mengdao Xing
18.1 Background 453
18.2 Introduction to Ensemble Learning 454
18.3 Ensemble Learning in HSI Classification 459
18.4 Conclusion 467
References 468
19 Spectral-Spatial Hyperspectral Image Classification Based on Sparse Representation 471
Haoyang Yu, Jia Jia, Chuhan Shen, Jiaochan Hu, Chein-I Chang, and Lianru Gao
19.1 Introduction 471
19.2 Related Models Description 472
19.3 Hyperspectral Image Classification Based on Sparse Representation 475
19.4 Experimental Results and Analysis 485
19.5 Conclusion 495
Acknowledgment 496
References 496
20 Hyperspectral Image Classification with Limited Samples 499
Yuebin Wang, Liqiang Zhang, Bing Zhang, Antonio Plaza, and Xiao Xiang Zhu
20.1 Introduction 499
20.2 Method 503
20.3 Experimental Results 509
20.4 Conclusions 519
References 520
21 Constrained Energy Minimization Based Hyperspectral Image Target Detection 521
Zhenwei Shi, Zhengxia Zou, Bowen Chen, and Liqin Liu
21.1 Introduction 521
21.2 Overview of CEM 522
21.3 CEM-based Methods 525
21.4 Conclusions 539
References 541
22 Hyperspectral Target Detection Based on Weighted Cauchy Distance Graph and Local Adaptive Collaborative Representation 543
Wei Li and Kun Gao
22.1 Introduction 543
22.2 Related Works 545
22.3 The Proposed Detection Methodology 546
22.4 Experiments and Analysis 551
22.5 Conclusion 558
References 558
23 Weakly Supervised Learning-based Hyperspectral Image Anomaly/Target Detection 561
Weiying Xie, Xin Zhang, Yunsong Li, and Qian Du
23.1 Introduction 561
23.2 Weakly Supervised Hyperspectral Anomaly Detection (WSLRR) 564
23.3 Weakly Supervised Hyperspectral Target Detection (BLTSC) 573
23.4 Rank-aware Hyperspectral Band Selection (R-GAN) 578
23.5 Conclusions 587
References 589
24 Hyperspectral Anomaly Detection via Background-separable Mode 593
Bing Tu, Xianchang Yang, Jun Li, Antonio Plaza, and Kaiyuan Chen
24.1 Hyperspectral Anomaly Detection Using Dual Window Density 593
24.2 Hyperspectral Anomaly Detection Using Reconstruction Fusion of Quaternion Frequency Domain Analysis 603
24.3 Ensemble Entropy Metric for Hyperspectral Anomaly Detection 619
References 631
25 Spectral Change Analysis for Multitemporal Change Detection in Hyperspectral Remote Sensing Images 633
Sicong Liu, Kecheng Du, Xiaohua Tong, and Peijun Du
25.1 Introduction 633
25.2 Related Works 635
25.3 Spectral Change Analysis in Hyperspectral Images 637
25.4 Experimental Setup 643
25.5 Results and Analysis 643
25.6 Conclusion 650
Acknowledgement 650
References 650
26 Challenges and Future Directions 655
Bing Zhang, He Sun, and Ruitong Du
26.1 Challenges and Future Directions in Hyperspectral Image Denoising 655
26.2 Challenges and Future Directions in Hyperspectral (HS) and Multispectral (MS) Image Fusion 657
26.3 Challenges and Future Directions in NMF-based Hyperspectral Unmixing 659
26.4 Challenges and Future Directions in Knowledge Graph-enhanced Hyperspectral Unmixing 660
26.5 Challenges and Future Directions in Numerical Model-guided Nonlinear Hyperspectral Unmixing 660
26.6 Challenges and Future Directions in Hyperspectral Image Classification 661
26.7 Chapter on Challenges and Future Directions in Hyperspectral Target Detection 662
References 663
Index 665