remotesensing-logo

Journal Browser

Journal Browser

Advances in Hyperspectral Data Exploitation II

A special issue of Remote Sensing (ISSN 2072-4292). This special issue belongs to the section "Remote Sensing Image Processing".

Deadline for manuscript submissions: closed (29 February 2024) | Viewed by 19997

Special Issue Editors

Department of Computer Science and Electrical Engineering, University of Maryland, Baltimore County, Baltimore, MA 21250, USA
Interests: hyperspectral/multispectral image processing; medical imaging
Special Issues, Collections and Topics in MDPI journals
School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China
Interests: hyperspectral image processing; remote sensing image fusion and applications
Department of Electrical Engineering, Zhejiang University, Hangzhou 310027, China
Interests: hyperspectral anomaly detection; hyperspectral target detection; multisource remote sensing image registration

Special Issue Information

Dear Colleagues,

This Special Issue is a sequel of the previous Special Issue entitled “Advances in Hyperspectral Data Exploitation”, and explores the potential and promise of hyperspectral imaging (HSI) in data exploitation. Over the past few years, HSI  has witnessed rapid growth in many areas, from detection, classification, band selection, spectral unmixing, endmember finding and image fusion to real-time processing in communication, transmission and hardware design and development. The techniques designed and developed for HSI also range from classic methods to model-based machine and deep learning networks, and to compressive sensing derived from computer vision, statistical signal processing and communications. This particular issue aims to provide a forum for many individuals working in HSI to report their research findings and share their experiences with the HSI community.

The following areas, but not limited to, are of particular interest:

  • Hyperspectral anomaly detection;
  • Hyperspectral target detection;
  • Hyperspectral image classification;
  • Hyperspectral band selection;
  • Hyperspectral unmixing;
  • Hyperspectral endmember finding and extraction;
  • Hyperspectral data dimensionality reduction;
  • Hyperspectral data model and learning;
  • Hyperspectral/multispectral fusion;
  • Hyperspectral data communications and transmission;
  • Hyperspectral high-performance computing;
  • Hyperspectral algorithm design, architecture development and implementation.

Review and tutorial papers are particularly welcome.

Prof. Dr. Chein-I Chang
Dr. Shengwei Zhong
Dr. Shuhan Chen
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Remote Sensing is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2700 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • hyperspectral artificial intelligence
  • hyperspectral image processing
  • hyperspectral signal processing
  • hyperspectral band processing
  • hyperspectral data fusion
  • hyperspectral hardware design and development

Published Papers (15 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

Jump to: Review

15 pages, 3605 KiB  
Communication
Evaluation of Leaf Chlorophyll Content from Acousto-Optic Hyperspectral Data: A Multi-Crop Study
by Anastasia Zolotukhina, Alexander Machikhin, Anastasia Guryleva, Valeria Gresis, Anastasia Kharchenko, Karina Dekhkanova, Sofia Polyakova, Denis Fomin, Georgiy Nesterov and Vitold Pozhar
Remote Sens. 2024, 16(6), 1073; https://doi.org/10.3390/rs16061073 - 18 Mar 2024
Viewed by 435
Abstract
Chlorophyll plays a crucial role in the process of photosynthesis and helps to regulate plants’ growth and development. Timely and accurate evaluation of leaf chlorophyll content provides valuable information about the health and productivity of plants as well as the effectiveness of agricultural [...] Read more.
Chlorophyll plays a crucial role in the process of photosynthesis and helps to regulate plants’ growth and development. Timely and accurate evaluation of leaf chlorophyll content provides valuable information about the health and productivity of plants as well as the effectiveness of agricultural treatments. For non-contact and high-performance chlorophyll content mapping in plants, spectral imaging techniques are the most widely used. Due to agility and rapid random-spectral-access tuning, acousto-optical imagers seem to be very attractive for the detection of vegetation indices and chlorophyll content assessment. This laboratory study demonstrates the capabilities of an acousto-optic imager for evaluation of leaf chlorophyll content in six crops with different biophysical properties: Ribes rubrum, Betula populifolia, Hibiscus rosa-sinensis, Prunus padus, Hordeum vulgare and Triticum aestivum. The experimental protocol includes plant collecting, reference spectrophotometric measurements, hyperspectral imaging data acquisition, processing and analysis and building a multi-crop chlorophyll model. For 90 inspected samples of plant leaves, the optimal vegetation index and model were found. Obtained values of chlorophyll concentrations correlate well with reference values (determination coefficient of 0.89 and relative error of 15%). Applying a multi-crop model to each pixel, we calculated chlorophyll content maps across all plant samples. The results of this study demonstrate that acousto-optic imagery is very promising for fast chlorophyll content assessment and other laboratory spectral-index-based measurements. Full article
(This article belongs to the Special Issue Advances in Hyperspectral Data Exploitation II)
Show Figures

Figure 1

31 pages, 4589 KiB  
Article
Band Selection via Band Density Prominence Clustering for Hyperspectral Image Classification
by Chein-I Chang, Yi-Mei Kuo and Kenneth Yeonkong Ma
Remote Sens. 2024, 16(6), 942; https://doi.org/10.3390/rs16060942 - 07 Mar 2024
Viewed by 375
Abstract
Band clustering has been widely used for hyperspectral band selection (BS). However, selecting an appropriate band to represent a band cluster is a key issue. Density peak clustering (DPC) provides an effective means for this purpose, referred to as DPC-based BS (DPC-BS). It [...] Read more.
Band clustering has been widely used for hyperspectral band selection (BS). However, selecting an appropriate band to represent a band cluster is a key issue. Density peak clustering (DPC) provides an effective means for this purpose, referred to as DPC-based BS (DPC-BS). It uses two indicators, cluster density and cluster distance, to rank all bands for BS. This paper reinterprets cluster density and cluster distance as band local density (BLD) and band distance (BD) and also introduces a new concept called band prominence value (BPV) as a third indicator. Combining BLD and BD with BPV derives new band prioritization criteria for BS, which can extend the currently used DPC-BS to a new DPC-BS method referred to as band density prominence clustering (BDPC). By taking advantage of the three key indicators of BDPC, i.e., cut-off band distance bc, k nearest neighboring-band local density, and BPV, two versions of BDPC can be derived called bc-BDPC and k-BDPC, both of which are quite different from existing DPC-based BS methods in three aspects. One is that the parameter bc of bc-BDPC and the parameter k of k-BDPC can be automatically determined by the number of clusters and virtual dimensionality (VD), respectively. Another is that instead of using Euclidean distance, a spectral discrimination measure is used to calculate BD as well as inter-band correlation. The most important and significant aspect is a novel idea that combines BPV with BLD and BD to derive new band prioritization criteria for BS. Extensive experiments demonstrate that BDPC generally performs better than DPC-BS as well as many current state-of-the art BS methods. Full article
(This article belongs to the Special Issue Advances in Hyperspectral Data Exploitation II)
Show Figures

Figure 1

0 pages, 58879 KiB  
Article
Exploration of Data Scene Characterization and 3D ROC Evaluation for Hyperspectral Anomaly Detection
by Chein-I Chang, Shuhan Chen, Shengwei Zhong and Yidan Shi
Remote Sens. 2024, 16(1), 135; https://doi.org/10.3390/rs16010135 - 28 Dec 2023
Cited by 1 | Viewed by 941
Abstract
Whether or not a hyperspectral anomaly detector is effective is determined by two crucial issues, anomaly detectability and background suppressibility (BS), both of which are very closely related to two factors, the datasets used for a selected hyperspectral anomaly detector and detection measures [...] Read more.
Whether or not a hyperspectral anomaly detector is effective is determined by two crucial issues, anomaly detectability and background suppressibility (BS), both of which are very closely related to two factors, the datasets used for a selected hyperspectral anomaly detector and detection measures used for its performance evaluation. This paper explores how anomaly detectability and BS play key roles in hyperspectral anomaly detection (HAD). To address these two issues, we investigate three key elements attributed to HAD. One is a selected hyperspectral anomaly detector, and another is the datasets used for experiments. The third one is the detection measures used to evaluate the effectiveness of a hyperspectral anomaly detector. As for hyperspectral anomaly detectors, twelve commonly used anomaly detectors were evaluated and compared. To address the appropriate use of datasets for HAD, seven popular and widely used datasets were studied for HAD. As for the third issue, the traditional area under a receiver operating characteristic (ROC) curve of detection probability—PD versus false alarm probability, PF, (AUC(D,F))—was extended to 3D ROC analysis where a 3D ROC curve was developed to generate three 2D ROC curves from which eight detection measures could be derived to evaluate HAD in all round aspects, including anomaly detectability, BS and joint anomaly detectability and BS. Qualitative analysis showed that many works reported in the literature which claimed that their developed hyperspectral anomaly detectors performed better than other anomaly detectors are actually not true because they overlooked these two issues. Specifically, a comprehensive study via extensive experiments demonstrated that these 3D ROC curve-derived detection measures can be further used to address the various characterizations of different data scenes and also to provide explanations as to why certain data scenes are not suitable for HAD. Full article
(This article belongs to the Special Issue Advances in Hyperspectral Data Exploitation II)
Show Figures

Figure 1

18 pages, 7583 KiB  
Article
The Automated Detection of Fusarium Wilt on Phalaenopsis Using VIS-NIR and SWIR Hyperspectral Imaging
by Min-Shao Shih, Kai-Chun Chang, Shao-An Chou, Tsang-Sen Liu and Yen-Chieh Ouyang
Remote Sens. 2023, 15(17), 4174; https://doi.org/10.3390/rs15174174 - 25 Aug 2023
Viewed by 676
Abstract
Phalaenopsis, an essential flower for export, is significantly affected by fusarium wilt, which impacts its export quality. Hyperspectral imaging technology offers the potential to detect fusarium wilt on Phalaenopsis. The goal of this study was to establish an automated platform for [...] Read more.
Phalaenopsis, an essential flower for export, is significantly affected by fusarium wilt, which impacts its export quality. Hyperspectral imaging technology offers the potential to detect fusarium wilt on Phalaenopsis. The goal of this study was to establish an automated platform for the rapid detection of fusarium wilt on Phalaenopsis. In this research, the automatic target generation process (ATGP) method was employed to identify outliers in the hyperspectral spectrum. Subsequently, the Spectral Angle Mapper (SAM) method was utilized to detect signals similar to the outliers. To suppress background noise and extract the region of interest (ROI), the Constrained Energy Minimization (CEM) method was implemented. For ROI classification and detection, a deep neural network (DNN), a support vector machine (SVM), and a Random Forest Classifier (RFC) were employed. Model performance was evaluated using three-dimensional receiver operating characteristics (3D ROC), and the automated identification system was integrated into hyperspectrometers. The proposed system achieved an accuracy of 95.77% with a total detection time of 3380 ms ± 86.36 ms, proving to be a practical and effective tool for detecting fusarium wilt on Phalaenopsis in the industry. Full article
(This article belongs to the Special Issue Advances in Hyperspectral Data Exploitation II)
Show Figures

Figure 1

19 pages, 4977 KiB  
Article
Hyperspectral Unmixing Network Accounting for Spectral Variability Based on a Modified Scaled and a Perturbed Linear Mixing Model
by Ying Cheng, Liaoying Zhao, Shuhan Chen and Xiaorun Li
Remote Sens. 2023, 15(15), 3890; https://doi.org/10.3390/rs15153890 - 05 Aug 2023
Cited by 1 | Viewed by 1217
Abstract
Spectral unmixing is one of the prime topics in hyperspectral image analysis, as images often contain multiple sources of spectra. Spectral variability is one of the key factors affecting unmixing accuracy, since spectral signatures are affected by variations in environmental conditions. These and [...] Read more.
Spectral unmixing is one of the prime topics in hyperspectral image analysis, as images often contain multiple sources of spectra. Spectral variability is one of the key factors affecting unmixing accuracy, since spectral signatures are affected by variations in environmental conditions. These and other factors interfere with the accurate discrimination of source type. Several spectral mixing models have been proposed for hyperspectral unmixing to address the spectral variability problem. The interpretation for the spectral variability of these models is usually insufficient, and the unmixing algorithms corresponding to these models are usually classic unmixing techniques. Hyperspectral unmixing algorithms based on deep learning have outperformed classic algorithms. In this paper, based on the typical extended linear mixing model and the perturbed linear mixing model, the scaled and perturbed linear mixing model is constructed, and a spectral unmixing network based on this model is constructed using fully connected neural networks and variational autoencoders to update the abundances, scales, and perturbations involved in the variable endmembers. Adding spatial smoothness constraints to the scale and adding regularization constraints to the perturbation improve the robustness of the model, and adding sparseness constraints to the abundance determination prevents overfitting. The proposed approach is evaluated on both synthetic and real data sets. Experimental results show the superior performance of the proposed method against other competitors. Full article
(This article belongs to the Special Issue Advances in Hyperspectral Data Exploitation II)
Show Figures

Graphical abstract

21 pages, 6863 KiB  
Article
Dual Homogeneous Patches-Based Band Selection Methodology for Hyperspectral Classification
by Xianyue Wang, Longxia Qian, Mei Hong and Yifan Liu
Remote Sens. 2023, 15(15), 3841; https://doi.org/10.3390/rs15153841 - 01 Aug 2023
Cited by 3 | Viewed by 1137
Abstract
Homogeneous band- or pixel-based feature selection, which exploits the difference between spectral or spatial regions to select informative and low-redundant bands, has been extensively studied in classifying hyperspectral images (HSIs). Although many models have proven effective, they rarely simultaneously exploit homogeneous spatial and [...] Read more.
Homogeneous band- or pixel-based feature selection, which exploits the difference between spectral or spatial regions to select informative and low-redundant bands, has been extensively studied in classifying hyperspectral images (HSIs). Although many models have proven effective, they rarely simultaneously exploit homogeneous spatial and spectral information, which are beneficial to extract potential low-dimensional characteristics even under noise. Moreover, the employed vectorial transformation and unordered assumption destroy the implicit knowledge of HSIs. To solve these issues, a dual homogeneous pixel patches-based methodology termed PHSIMR was created for selecting the most representative, low-redundant, and informative bands, integrating hybrid superpixelwise adjacent band grouping and regional informative mutuality ranking algorithms. Specifically, the adjoining band grouping technique is designed to group adjacent bands into connected clusters with a small homogeneous pixel patch containing several homolabeled adjacent spatial points. Hence, the processing is efficient, and the superpixelwise adjoining band grouping can perceptually and quickly acquire connected band groups. Furthermore, the constructed graph and affiliated group avoid vectorial transformation and unordered assumption, protecting spectral and spatial contextual information. Then, the regional informative mutuality ranking algorithm is employed on another larger pixel patch within each homogeneous band group, acquiring the final representative, low-redundant, and informative band subset. Since the employed dual patches consist of homolabeled spatial pixels, PHSIMR is a supervised methodology. Comparative experiments on three benchmark HSIs were performed to demonstrate the efficiency and effectiveness of the proposed PHSIMR. Full article
(This article belongs to the Special Issue Advances in Hyperspectral Data Exploitation II)
Show Figures

Figure 1

26 pages, 6741 KiB  
Article
DSSFN: A Dual-Stream Self-Attention Fusion Network for Effective Hyperspectral Image Classification
by Zian Yang, Nairong Zheng and Feng Wang
Remote Sens. 2023, 15(15), 3701; https://doi.org/10.3390/rs15153701 - 25 Jul 2023
Cited by 3 | Viewed by 1109
Abstract
Hyperspectral images possess a continuous and analogous spectral nature, enabling the classification of distinctive information by analyzing the subtle variations between adjacent spectra. Meanwhile, a hyperspectral dataset includes redundant and noisy information in addition to larger dimensions, which is the primary barrier preventing [...] Read more.
Hyperspectral images possess a continuous and analogous spectral nature, enabling the classification of distinctive information by analyzing the subtle variations between adjacent spectra. Meanwhile, a hyperspectral dataset includes redundant and noisy information in addition to larger dimensions, which is the primary barrier preventing its use for land cover categorization. Despite the excellent feature extraction capability exhibited by convolutional neural networks, its efficacy is restricted by the constrained receptive field and the inability to acquire long-range features due to the limited size of the convolutional kernels. We construct a dual-stream self-attention fusion network (DSSFN) that combines spectral and spatial information in order to achieve the deep mining of global information via a self-attention mechanism. In addition, dimensionality reduction is required to reduce redundant data and eliminate noisy bands, hence enhancing the performance of hyperspectral classification. A unique band selection algorithm is proposed in this study. This algorithm, which is based on a sliding window grouped normalized matching filter for nearby bands (SWGMF), can minimize the dimensionality of the data while preserving the corresponding spectral information. Comprehensive experiments are carried out on four well-known hyperspectral datasets, where the proposed DSSFN achieves higher classification results in terms of overall accuracy (OA), average accuracy (AA), and kappa than previous approaches. A variety of trials verify the superiority and huge potential of DSSFN. Full article
(This article belongs to the Special Issue Advances in Hyperspectral Data Exploitation II)
Show Figures

Figure 1

20 pages, 1461 KiB  
Article
Spectral–Temporal Transformer for Hyperspectral Image Change Detection
by Xiaorun Li and Jigang Ding
Remote Sens. 2023, 15(14), 3561; https://doi.org/10.3390/rs15143561 - 15 Jul 2023
Cited by 1 | Viewed by 1352
Abstract
Deep-Learning-based (DL-based) approaches have achieved remarkable performance in hyperspectral image (HSI) change detection (CD). Convolutional Neural Networks (CNNs) are often employed to capture fine spatial features, but they do not effectively exploit the spectral sequence information. Furthermore, existing Siamese-based networks ignore the interaction [...] Read more.
Deep-Learning-based (DL-based) approaches have achieved remarkable performance in hyperspectral image (HSI) change detection (CD). Convolutional Neural Networks (CNNs) are often employed to capture fine spatial features, but they do not effectively exploit the spectral sequence information. Furthermore, existing Siamese-based networks ignore the interaction of change information during feature extraction. To address this issue, we propose a novel architecture, the Spectral–Temporal Transformer (STT), which processes the HSI CD task from a completely sequential perspective. The STT concatenates feature embeddings in spectral order, establishing a global spectrum–time-receptive field that can learn different representative features between two bands regardless of spectral or temporal distance, thereby strengthening the learning of temporal change information. Via the multi-head self-attention mechanism, the STT is capable of capturing spectral–temporal features that are weighted and enriched with discriminative sequence information, such as inter-spectral correlations, variations, and time dependency. We conducted experiments on three HSI datasets, demonstrating the competitive performance of our proposed method. Specifically, the overall accuracy of the STT outperforms the second-best method by 0.08%, 0.68%, and 0.99% on the Farmland, Hermiston, and River datasets, respectively. Full article
(This article belongs to the Special Issue Advances in Hyperspectral Data Exploitation II)
Show Figures

Figure 1

25 pages, 5904 KiB  
Article
CRNN: Collaborative Representation Neural Networks for Hyperspectral Anomaly Detection
by Yuxiao Duan, Tongbin Ouyang and Jinshen Wang
Remote Sens. 2023, 15(13), 3357; https://doi.org/10.3390/rs15133357 - 30 Jun 2023
Cited by 1 | Viewed by 998
Abstract
Hyperspectral anomaly detection aims to separate anomalies and backgrounds without prior knowledge. The collaborative representation (CR)-based hyperspectral anomaly detection methods have gained significant interest and development because of their interpretability and high detection rate. However, the traditional CR presents a low utilization rate [...] Read more.
Hyperspectral anomaly detection aims to separate anomalies and backgrounds without prior knowledge. The collaborative representation (CR)-based hyperspectral anomaly detection methods have gained significant interest and development because of their interpretability and high detection rate. However, the traditional CR presents a low utilization rate for deep latent features in hyperspectral images, making the dictionary construction and the optimization of weight matrix sub-optimal. Due to the excellent capacity of neural networks for generation, we formulate the deep learning-based method into CR optimization in both global and local streams, and propose a novel hyperspectral anomaly detection method based on collaborative representation neural networks (CRNN) in this paper. In order to gain a complete background dictionary and avoid the pollution of anomalies, the global dictionary is collected in the global stream by optimizing the dictionary atom loss, while the local background dictionary is obtained by using a sliding dual window. Based on the two dictionaries, our two-stream networks are trained to learn the global and local representation of hyperspectral data by optimizing the objective function of CR. The detection result is calculated by the fusion of residual maps of original and represented data in the two streams. In addition, an autoencoder is introduced to obtain the hidden feature considered as the dense expression of the original hyperspectral image, and a feature extraction network is concerned to further learn the comprehensive features. Compared with the shallow learning CR, the proposed CRNN learns the dictionary and the representation weight matrix in neural networks to increase the detection performance, and the fixed network parameters instead of the complex matrix operations in traditional CR bring a high inference efficiency. The experiments on six public hyperspectral datasets prove that our proposed CRNN presents the state-of-the-art performance. Full article
(This article belongs to the Special Issue Advances in Hyperspectral Data Exploitation II)
Show Figures

Figure 1

19 pages, 1137 KiB  
Article
Unlocking the Potential of Data Augmentation in Contrastive Learning for Hyperspectral Image Classification
by Jinhui Li, Xiaorun Li and Yunfeng Yan
Remote Sens. 2023, 15(12), 3123; https://doi.org/10.3390/rs15123123 - 15 Jun 2023
Cited by 2 | Viewed by 1551
Abstract
Despite the rapid development of deep learning in hyperspectral image classification (HSIC), most models require a large amount of labeled data, which are both time-consuming and laborious to obtain. However, contrastive learning can extract spatial–spectral features from samples without labels, which helps to [...] Read more.
Despite the rapid development of deep learning in hyperspectral image classification (HSIC), most models require a large amount of labeled data, which are both time-consuming and laborious to obtain. However, contrastive learning can extract spatial–spectral features from samples without labels, which helps to solve the above problem. Our focus is on optimizing the contrastive learning process and improving feature extraction from all samples. In this study, we propose the Unlocking-the-Potential-of-Data-Augmentation (UPDA) strategy, which involves adding superior data augmentation methods to enhance the representation of features extracted by contrastive learning. Specifically, we introduce three augmentation methods—band erasure, gradient mask, and random occlusion—to the Bootstrap-Your-Own-Latent (BYOL) structure. Our experimental results demonstrate that our method can effectively improve feature representation and thus improve classification accuracy. Additionally, we conduct ablation experiments to explore the effectiveness of different data augmentation methods. Full article
(This article belongs to the Special Issue Advances in Hyperspectral Data Exploitation II)
Show Figures

Figure 1

19 pages, 5116 KiB  
Article
Spatial-Spectral-Associative Contrastive Learning for Satellite Hyperspectral Image Classification with Transformers
by Jinchun Qin and Hongrui Zhao
Remote Sens. 2023, 15(6), 1612; https://doi.org/10.3390/rs15061612 - 16 Mar 2023
Cited by 2 | Viewed by 1515
Abstract
Albeit hyperspectral image (HSI) classification methods based on deep learning have presented high accuracy in supervised classification, these traditional methods required quite a few labeled samples for parameter optimization. When processing HSIs, however, artificially labeled samples are always insufficient, and class imbalance in [...] Read more.
Albeit hyperspectral image (HSI) classification methods based on deep learning have presented high accuracy in supervised classification, these traditional methods required quite a few labeled samples for parameter optimization. When processing HSIs, however, artificially labeled samples are always insufficient, and class imbalance in limited samples is inevitable. This study proposed a Transformer-based framework of spatial–spectral–associative contrastive learning classification methods to extract both spatial and spectral features of HSIs by the self-supervised method. Firstly, the label information required for contrastive learning is generated by a spatial–spectral augmentation transform and image entropy. Then, the spatial and spectral Transformer modules are used to learn the high-level semantic features of the spatial domain and the spectral domain, respectively, from which the cross-domain features are fused by associative optimization. Finally, we design a classifier based on the Transformer. The invariant features distinguished from spatial–spectral properties are used in the classification of satellite HSIs to further extract the discriminant features between different pixels, and the class intersection over union is imported into the loss function to avoid the classification collapse caused by class imbalance. Conducting experiments on two satellite HSI datasets, this study verified the classification performance of the model. The results showed that the self-supervised contrastive learning model can extract effective features for classification, and the classification generated from this model is more accurate compared with that of the supervised deep learning model, especially in the average accuracy of the various classifications. Full article
(This article belongs to the Special Issue Advances in Hyperspectral Data Exploitation II)
Show Figures

Figure 1

22 pages, 5025 KiB  
Article
Learning General-Purpose Representations for Cross-Domain Hyperspectral Images Classification with Small Samples
by Kuiliang Gao, Anzhu Yu, Xiong You, Chunping Qiu, Bing Liu and Wenyue Guo
Remote Sens. 2023, 15(4), 1080; https://doi.org/10.3390/rs15041080 - 16 Feb 2023
Cited by 2 | Viewed by 1343
Abstract
Cross-domain classification with small samples is a more challenging and realistic experimental setup. Until now, few studies have focused on the problem of small-sample cross-domain classification between completely different hyperspectral images (HSIs) since they possess different land cover types and statistical characteristics. To [...] Read more.
Cross-domain classification with small samples is a more challenging and realistic experimental setup. Until now, few studies have focused on the problem of small-sample cross-domain classification between completely different hyperspectral images (HSIs) since they possess different land cover types and statistical characteristics. To this end, this paper proposes a general-purpose representation learning method for cross-domain HSI classification, aiming to enable the model to learn more general-purpose deep representations that can quickly adapt to different target domains with small samples. The core of this method is to propose a novel three-level distillation strategy to transfer knowledge from multiple models well-trained on source HSIs into a single distilled model at the channel-, feature- and logit-level simultaneously. The learned representations can be further fine-tuned with small samples and quickly adapt to new target HSIs and previously unseen classes. Specifically, to transfer and fuse knowledge from multiple-source domains into a single model simultaneously and solve the inconsistency of the number of bands in different HSIs, an extensible multi-task model, including the channel transformation module, the feature extraction module and the linear classification module, is designed. Only the feature extraction module is shared across different HSIs, while the other two modules are domain-specific. Furthermore, the typical episode-based learning strategy of the metric-based meta-learning is adopted in the whole learning process to further improve the generalization ability and data efficiency. Extensive experiments are conducted on six source HSIs and four target HSIs, and the results demonstrate that the proposed method outperforms the existing advanced methods in cross-domain HSI classification with small samples. Full article
(This article belongs to the Special Issue Advances in Hyperspectral Data Exploitation II)
Show Figures

Figure 1

18 pages, 6134 KiB  
Article
PSSA: PCA-Domain Superpixelwise Singular Spectral Analysis for Unsupervised Hyperspectral Image Classification
by Qiaoyuan Liu, Donglin Xue, Yanhui Tang, Yongxian Zhao, Jinchang Ren and Haijiang Sun
Remote Sens. 2023, 15(4), 890; https://doi.org/10.3390/rs15040890 - 06 Feb 2023
Cited by 4 | Viewed by 1440
Abstract
Although supervised classification of hyperspectral images (HSI) has achieved success in remote sensing, its applications in real scenarios are often constrained, mainly due to the insufficiently available or lack of labelled data. As a result, unsupervised HSI classification based on data clustering is [...] Read more.
Although supervised classification of hyperspectral images (HSI) has achieved success in remote sensing, its applications in real scenarios are often constrained, mainly due to the insufficiently available or lack of labelled data. As a result, unsupervised HSI classification based on data clustering is highly desired, yet it generally suffers from high computational cost and low classification accuracy, especially in large datasets. To tackle these challenges, a novel unsupervised spatial-spectral HSI classification method is proposed. By combining the entropy rate superpixel segmentation (ERS), superpixel-based principal component analysis (PCA), and PCA-domain 2D singular spectral analysis (SSA), both the efficacy and efficiency of feature extraction are improved, followed by the anchor-based graph clustering (AGC) for effective classification. Experiments on three publicly available and five self-collected aerial HSI datasets have fully demonstrated the efficacy of the proposed PCA-domain superpixelwise SSA (PSSA) method, with a gain of 15–20% in terms of the overall accuracy, in comparison to a few state-of-the-art methods. In addition, as an extra outcome, the HSI dataset we acquired is provided freely online. Full article
(This article belongs to the Special Issue Advances in Hyperspectral Data Exploitation II)
Show Figures

Graphical abstract

25 pages, 7311 KiB  
Article
A Band Subset Selection Approach Based on Sparse Self-Representation and Band Grouping for Hyperspectral Image Classification
by Keng-Hao Liu, Yu-Kai Chen and Tsun-Yang Chen
Remote Sens. 2022, 14(22), 5686; https://doi.org/10.3390/rs14225686 - 10 Nov 2022
Cited by 5 | Viewed by 1319
Abstract
Band subset selection (BSS) is one of the ways to implement band selection (BS) for a hyperspectral image (HSI). Different from conventional BS methods, which select bands one by one, BSS selects a band subset each time and preserves the best one from [...] Read more.
Band subset selection (BSS) is one of the ways to implement band selection (BS) for a hyperspectral image (HSI). Different from conventional BS methods, which select bands one by one, BSS selects a band subset each time and preserves the best one from the collection of the band subsets. This paper proposes a BSS method, called band grouping-based sparse self-representation BSS (BG-SSRBSS), for hyperspectral image classification. It formulates BS as a sparse self-representation (SSR) problem in which the entire bands can be represented by a set of informatively complementary bands. The BG-SSRBSS consists of two steps. To tackle the issue of selecting redundant bands, it first applies band grouping (BG) techniques to pre-group the entire bands to form multiple band groups, and then performs band group subset selection (BGSS) to find the optimal band group subset. The corresponding representative bands are taken as the BS result. To efficiently find the nearly global optimal subset among all possible band group subsets, sequential and successive iterative search algorithms are adopted. Land cover classification experiments conducted on three real HSI datasets show that BG-SSRBSS can improve classification accuracy by 4–20% compared to the existing BSS methods and requires less computation time. Full article
(This article belongs to the Special Issue Advances in Hyperspectral Data Exploitation II)
Show Figures

Figure 1

Review

Jump to: Research

28 pages, 4150 KiB  
Review
Target Detection in Hyperspectral Remote Sensing Image: Current Status and Challenges
by Bowen Chen, Liqin Liu, Zhengxia Zou and Zhenwei Shi
Remote Sens. 2023, 15(13), 3223; https://doi.org/10.3390/rs15133223 - 21 Jun 2023
Cited by 3 | Viewed by 2151
Abstract
Abundant spectral information endows unique advantages of hyperspectral remote sensing images in target location and recognition. Target detection techniques locate materials or objects of interest from hyperspectral images with given prior target spectra, and have been widely used in military, mineral exploration, ecological [...] Read more.
Abundant spectral information endows unique advantages of hyperspectral remote sensing images in target location and recognition. Target detection techniques locate materials or objects of interest from hyperspectral images with given prior target spectra, and have been widely used in military, mineral exploration, ecological protection, etc. However, hyperspectral target detection is a challenging task due to high-dimension data, spectral changes, spectral mixing, and so on. To this end, many methods based on optimization and machine learning have been proposed in the past decades. In this paper, we review the representatives of hyperspectral image target detection methods and group them into seven categories: hypothesis testing-based methods, spectral angle-based methods, signal decomposition-based methods, constrained energy minimization (CEM)-based methods, kernel-based methods, sparse representation-based methods, and deep learning-based methods. We then comprehensively summarize their basic principles, classical algorithms, advantages, limitations, and connections. Meanwhile, we give critical comparisons of the methods on the summarized datasets and evaluation metrics. Furthermore, the future challenges and directions in the area are analyzed. Full article
(This article belongs to the Special Issue Advances in Hyperspectral Data Exploitation II)
Show Figures

Graphical abstract

Back to TopTop