Hyperspectral Imaging and Signal Processing

Abstract submission deadline

closed (31 January 2025)

Manuscript submission deadline

closed (31 March 2025)

Viewed by

47375

Topic Information

Dear Colleagues,

Hyperspectral imaging technology has been used for Earth observation for more than four decades. A variety of hyperspectral sensors based on different platforms, such as satellites, aircraft, drones, cars, and ground, have been developed, which have greatly promoted the applications of hyperspectral imaging technology. With the development of computer science and the availability of hyperspectral datasets, more and more artificial intelligence algorithms based on machine learning or deep learning are used for the processing and application of hyperspectral imagery. In addition, some potential applications using hyperspectral imaging technology are investigated with the improvement of the spatial and spectral resolution of hyperspectral sensors. In this Topic, we focus on hyperspectral sensor design, data processing, and applications. Authors are encouraged to submit contributions that report original studies on hyperspectral imaging and signal processing. If your research is limited by spaceborne hyperspectral images, you can contact the Topic editor team to seek data support. Topics will include but not be limited to:

• Hyperspectral sensor design, development, and performance valuation;
• Key techniques in sub-systems, including optics, electronics, mechanics, and detectors;
• Hyperspectral data preprocessing and image quality improvement, e.g., radiometric calibration, geometric correction, and atmosphere correction;
• Innovative algorithm development for hyperspectral remote sensing;
• Data fusion of multiple remote sensing sources;
• Hyperspectral LiDAR;
• Hyperspectral applications in the ocean, forests, agriculture, environment, minerals and oil, etc.

Prof. Dr. Yinnian Liu
Prof. Dr. Bing Zhang
Prof. Dr. Liangpei Zhang
Dr. Chenchao Xiao
Prof. Dr. Yueming Wang
Prof. Dr. Yongguang Zhang
Prof. Dr. Qingli Li
Dr. Yuwei Chen
Dr. Jianxin Jia
Dr. Mingyang Zhang
Topic Editors

Keywords

Participating Journals

Journal Name	Impact Factor	CiteScore	Launched Year	First Decision (median)	APC
Drones drones	4.4	5.6	2017	19.2 Days	CHF 2600
Electronics electronics	2.6	5.3	2012	16.4 Days	CHF 2400
Land land	3.2	4.9	2012	16.9 Days	CHF 2600
Photonics photonics	2.1	2.6	2014	14.9 Days	CHF 2400
Remote Sensing remotesensing	4.2	8.3	2009	23.9 Days	CHF 2700
Sensors sensors	3.4	7.3	2001	18.6 Days	CHF 2600

Preprints.org is a multidisciplinary platform offering a preprint service designed to facilitate the early sharing of your research. It supports and empowers your research journey from the very beginning.

MDPI Topics is collaborating with Preprints.org and has established a direct connection between MDPI journals and the platform. Authors are encouraged to take advantage of this opportunity by posting their preprints at Preprints.org prior to publication:

1. Share your research immediately: disseminate your ideas prior to publication and establish priority for your work.
2. Safeguard your intellectual contribution: Protect your ideas with a time-stamped preprint that serves as proof of your research timeline.
3. Boost visibility and impact: Increase the reach and influence of your research by making it accessible to a global audience.
4. Gain early feedback: Receive valuable input and insights from peers before submitting to a journal.
5. Ensure broad indexing: Web of Science (Preprint Citation Index), Google Scholar, Crossref, SHARE, PrePubMed, Scilit and Europe PMC.

Published Papers (27 papers)

Order results

Content type Publication Date

Result details

Normal Extended Compact

Journals

All Drones Electronics Land Photonics Remote Sensing Sensors

Show export options expand_more Show export options expand_less

Select all

Export citation of selected articles as:

Plain Text BibTeX BibTeX (without abstracts) Endnote Endnote (without abstracts) Tab-delimited RIS

Error

Oops... you haven't selected anything for export.

Ok

clear

22 pages, 10867 KiB  

Open AccessArticle

Design and Analysis of Spaceborne Hyperspectral Imaging System for Coastal Studies

by Yin Wu, Yueming Wang and Dong Zhang

Remote Sens. 2025, 17(6), 986; https://doi.org/10.3390/rs17060986 - 11 Mar 2025

Viewed by 554

Abstract

Hyperspectral payloads with high spatial and spectral resolution, combined with a wide field of view, are crucial for tackling the complexity of coastal and estuarine water ecosystems, enabling effective monitoring of water quality and ecological conditions. This study introduces a modular spectrometer design [...] Read more.

Hyperspectral payloads with high spatial and spectral resolution, combined with a wide field of view, are crucial for tackling the complexity of coastal and estuarine water ecosystems, enabling effective monitoring of water quality and ecological conditions. This study introduces a modular spectrometer design utilizing multiple sub-modules in an extended slit configuration. The system delivers a spectral resolution of 5 nm (400–1000 nm) and 10 nm (1000–2500 nm), a spatial resolution of 20 m, and a swath width of 80 km. Smile and keystone distortions are maintained below 1/5 of a pixel. Using Modran to simulate solar irradiance, the SNR of different targets under typical background conditions is calculated. Compared to conventional designs, the proposed modular approach provides compactness and high fidelity, effectively addressing size and optical aberration challenges. The simulation results confirm the system’s robustness, setting a benchmark for next-generation coast observation missions, particularly in coastal monitoring, underwater exploration, and dynamic environmental change tracking. Full article

(This article belongs to the Topic Hyperspectral Imaging and Signal Processing)

►▼ Show Figures

Figure 1

17 pages, 72606 KiB  

Open AccessArticle

Classification of Large Scale Hyperspectral Remote Sensing Images Based on LS3EU-Net++

by Hengqian Zhao, Zhengpu Lu, Shasha Sun, Pan Wang, Tianyu Jia, Yu Xie and Fei Xu

Remote Sens. 2025, 17(5), 872; https://doi.org/10.3390/rs17050872 - 28 Feb 2025

Viewed by 510

Abstract

Aimed at the limitation that existing hyperspectral classification methods were mainly oriented to small-scale images, this paper proposed a new large-scale hyperspectral remote sensing image classification method, LS3EU-Net++ (Lightweight Encoder and Integrated Spatial Spectral Squeeze and Excitation U-Net++). The method optimized the U-Net++ [...] Read more.

Aimed at the limitation that existing hyperspectral classification methods were mainly oriented to small-scale images, this paper proposed a new large-scale hyperspectral remote sensing image classification method, LS3EU-Net++ (Lightweight Encoder and Integrated Spatial Spectral Squeeze and Excitation U-Net++). The method optimized the U-Net++ architecture by introducing a lightweight encoder and combining the Spatial Spectral Squeeze and Excitation (S3E) Attention Module, which maintained the powerful feature extraction capability while significantly reducing the training cost. In addition, the model employed a composite loss function combining focal loss and Jaccard loss, which could focus more on difficult samples, thus improving pixel-level accuracy and classification results. To solve the sample imbalance problem in hyperspectral images, this paper also proposed a data enhancement strategy based on “copy–paste”, which effectively increased the diversity of the training dataset. Experiments on large-scale satellite hyperspectral remote sensing images from the Zhuhai-1 satellite demonstrated that LS3EU-Net++ exhibited superiority over the U-Net++ benchmark. Specifically, the overall accuracy (OA) was improved by 5.35%, and the mean Intersection over Union (mIoU) by 12.4%. These findings suggested that the proposed method provided a robust solution for large-scale hyperspectral image classification, effectively balancing accuracy and computational efficiency. Full article

(This article belongs to the Topic Hyperspectral Imaging and Signal Processing)

►▼ Show Figures

Figure 1

21 pages, 5065 KiB  

Open AccessArticle

Application of DS-DFT to the Fine Spectral Estimation of High-Noise Signals

by Lin Qin, Suihu Dang, Di Fu and Yutao Feng

Electronics 2024, 13(24), 5057; https://doi.org/10.3390/electronics13245057 - 23 Dec 2024

Viewed by 566

Abstract

This paper presented an extended double-subsegment discrete Fourier transform (DS-DFT) algorithm as a tool for the fine spectral estimation of high-noise environments, which was previously effective in low-noise scenarios, and as such, its application to the analysis of noisy signals observed by a [...] Read more.

This paper presented an extended double-subsegment discrete Fourier transform (DS-DFT) algorithm as a tool for the fine spectral estimation of high-noise environments, which was previously effective in low-noise scenarios, and as such, its application to the analysis of noisy signals observed by a satellite-based interferometer was investigated. The observation of satellite-borne Doppler asymmetric spatial heterodyne spectroscopy (DASH) was first simulated to obtain the signals of low- and high-noise levels; then, a practical criterion to classify noise levels in the interferograms based on the DS-DFT results was introduced and validated by calculating the SNR. For high-noise signals, DS-DFT remains robust by employing phase differences and amplitude ratios for fine frequency estimation. Full article

(This article belongs to the Topic Hyperspectral Imaging and Signal Processing)

►▼ Show Figures

Figure 1

20 pages, 1285 KiB  

Open AccessArticle

RS-Net: Hyperspectral Image Land Cover Classification Based on Spectral Imager Combined with Random Forest Algorithm

by Xuyang Li, Xiangsuo Fan, Qi Li and Xueqiang Zhao

Electronics 2024, 13(20), 4046; https://doi.org/10.3390/electronics13204046 - 14 Oct 2024

Cited by 2 | Viewed by 1405

Abstract

Recursive neural networks and transformers have recently become dominant in hyperspectral (HS) image classification due to their ability to capture long-range dependencies in spectral sequences. Despite the success of these sequential architectures, mainstream deep learning methods primarily handle two-dimensional structured data. However, challenges [...] Read more.

Recursive neural networks and transformers have recently become dominant in hyperspectral (HS) image classification due to their ability to capture long-range dependencies in spectral sequences. Despite the success of these sequential architectures, mainstream deep learning methods primarily handle two-dimensional structured data. However, challenges such as the curse of dimensionality, spectral variability, and confounding factors in hyperspectral remote sensing images limit their effectiveness, especially in remote sensing applications. To address this issue, this paper proposes a novel land cover classification algorithm that integrates random forests with a spectral transformer network structure (RS-Net). Firstly, this paper presents a combination of the Gramian Angular Field (GASF) and Gramian Angular Difference Field (GADF) algorithms, which effectively maps the multidimensional time series constructed for each pixel onto two-dimensional image features, enabling precise extraction and recognition in the backend network algorithms and improving the classification accuracy of land cover types. Secondly, to capture the relationships between features at different scales, this paper proposes a SpectralFormer network architecture using the Context and Structure Encoding (CASE) module to effectively learn dependencies between channels. This architecture enhances important features and suppresses unimportant ones, thereby addressing the semantic gap and improving the recognition capability of land cover features. Finally, the final prediction results are determined by a voting mechanism from the Random Forest algorithm, which synthesizes predictions from multiple decision trees to enhance classification stability and accuracy. To better compare the performance of RS-Net, this paper conducted extensive experiments on three benchmark HS datasets obtained from satellite and airborne imagers, comparing various classic neural network models. Surprisingly, the RS-Net algorithm achieves high performance and efficiency, offering a new and effective tool for land cover classification. Full article

(This article belongs to the Topic Hyperspectral Imaging and Signal Processing)

►▼ Show Figures

Figure 1

17 pages, 2730 KiB  

Open AccessArticle

Spectral Calibration of the Spectrometer on Board the Colombian FACSAT-2 Satellite Mission

by Lorena Paola Cárdenas Espinosa, Enrique Mejía-Ospino, Luis Guarnizo, Jorge Prada Mejia, Erick Enrique Gutiérrez, Jorge Paiba Alzate, Iván Plata, Efraín Rodríguez Rubio, Alejandro Carvajal and Paola Zarate

Remote Sens. 2024, 16(19), 3674; https://doi.org/10.3390/rs16193674 - 1 Oct 2024

Cited by 1 | Viewed by 1562

Abstract

This paper presents the results of the integration, commissioning, and in-orbit calibration of the ARGUS 2000 SWIR wavelength spectrometer onboard the Colombian FACSAT-2 satellite, Colombia’s first satellite used for the measurement of greenhouse gases (GHG). The satellite has been in orbit for approximately [...] Read more.

This paper presents the results of the integration, commissioning, and in-orbit calibration of the ARGUS 2000 SWIR wavelength spectrometer onboard the Colombian FACSAT-2 satellite, Colombia’s first satellite used for the measurement of greenhouse gases (GHG). The satellite has been in orbit for approximately one year, gathering spectral signatures in order to characterize the data and perform calibration. The calibration represents a certain behavior following a second-order adjustment. For data analysis, retrieval algorithms have been developed to obtain synthetic spectra using the Genspect 1.2 software code. These synthetic spectra were obtained from the spectroscopic data associated with atmospheric gases (H₂O, O₂, CO, and CO₂), which are stored in the HITRAN database. Attempting to achieve a more accurate simulation of the experimental spectrum, certain instrumental parameters have been incorporated into the synthetic spectrum, including the resolution of the spectrometer, the field of view (FOV) angle of observation, the limited quantum efficiency of detection, and the slit function. As a result, six slit functions were tested, with the Gaussian and the diffraction functions proving to be the most effective. Finally, a profile of Total Carbon Column Observing Network (TCCON) concentrations was used for comparison with a spectral signature acquired by FACSAT-2, resulting in a close match between the synthetic spectrum and the measured spectrum. Full article

(This article belongs to the Topic Hyperspectral Imaging and Signal Processing)

►▼ Show Figures

Figure 1

20 pages, 10736 KiB  

Open AccessArticle

Application of Hyperspectral Imaging and Multi-Module Joint Hierarchical Residual Network in Seed Cotton Foreign Fiber Recognition

by Yunlong Zhang, Laigang Zhang, Zhijun Guo and Ran Zhang

Sensors 2024, 24(18), 5892; https://doi.org/10.3390/s24185892 - 11 Sep 2024

Viewed by 837

Abstract

Due to the difficulty in distinguishing transparent and white foreign fibers from seed cotton in RGB images and in order to improve the recognition ability of deep learning (DL) algorithms for white, transparent, and multi-class mixed foreign fibers with different sizes in seed [...] Read more.

Due to the difficulty in distinguishing transparent and white foreign fibers from seed cotton in RGB images and in order to improve the recognition ability of deep learning (DL) algorithms for white, transparent, and multi-class mixed foreign fibers with different sizes in seed cotton, this paper proposes a method of combining hyperspectral imaging technology with a multi-module joint hierarchical residue network (MJHResNet). Firstly, a series of preprocessing methods are performed on the hyperspectral image (HSI) to reduce the interference of noise. Secondly, a double-hierarchical residual (DHR) structure is designed, which can not only obtain multi-scale information, but also avoid gradient vanishing to some extent. After that, a squeeze-and-excitation network (SENet) is integrated to reduce redundant information, improve the expression of model features, and improve the accuracy of foreign fiber identification in seed cotton. Finally, by analyzing the experimental results with advanced classifiers, this method has significant advantages. The average accuracy is 98.71% and the overall accuracy is 99.28%. This method has great potential for application in the field of foreign fiber identification in seed cotton. Full article

(This article belongs to the Topic Hyperspectral Imaging and Signal Processing)

►▼ Show Figures

Figure 1

25 pages, 37830 KiB  

Open AccessArticle

A Microscope Setup and Methodology for Capturing Hyperspectral and RGB Histopathological Imaging Databases

by Gonzalo Rosa-Olmeda, Manuel Villa, Sara Hiller-Vallina, Miguel Chavarrías, Fernando Pescador and Ricardo Gargini

Sensors 2024, 24(17), 5654; https://doi.org/10.3390/s24175654 - 30 Aug 2024

Viewed by 1342

Abstract

The digitization of pathology departments in hospitals around the world is now a reality. The current commercial solutions applied to digitize histopathological samples consist of a robotic microscope with an RGB-type camera attached to it. This technology is very limited in terms of [...] Read more.

The digitization of pathology departments in hospitals around the world is now a reality. The current commercial solutions applied to digitize histopathological samples consist of a robotic microscope with an RGB-type camera attached to it. This technology is very limited in terms of information captured, as it only works with three spectral bands of the visible electromagnetic spectrum. Therefore, we present an automated system that combines RGB and hyperspectral technology. Throughout this work, the hardware of the system and its components are described along with the developed software and a working methodology to ensure the correct capture of histopathological samples. The software is integrated by the controller of the microscope, which features an autofocus functionality, whole slide scanning with a stitching algorithm, and hyperspectral scanning functionality. As a reference, the time to capture and process a complete sample with 20 regions of high biological interest using the proposed method is estimated at a maximum of 79 min, reducing the time required by a manual operator by at least three times. Both hardware and software can be easily adapted to other systems that might benefit from the advantages of hyperspectral technology. Full article

(This article belongs to the Topic Hyperspectral Imaging and Signal Processing)

►▼ Show Figures

Figure 1

21 pages, 1668 KiB  

Open AccessArticle

DCG-Net: Enhanced Hyperspectral Image Classification with Dual-Branch Convolutional Neural Network and Graph Convolutional Neural Network Integration

by Wenkai Zhu, Xueying Sun and Qiang Zhang

Electronics 2024, 13(16), 3271; https://doi.org/10.3390/electronics13163271 - 18 Aug 2024

Cited by 1 | Viewed by 1333

Abstract

In recent years, graph convolutional neural networks (GCNs) and convolutional neural networks (CNNs) have made significant strides in hyperspectral image (HSI) classification. However, existing models often encounter information redundancy and feature mismatch during feature fusion, and they struggle with small-scale refined features. To [...] Read more.

In recent years, graph convolutional neural networks (GCNs) and convolutional neural networks (CNNs) have made significant strides in hyperspectral image (HSI) classification. However, existing models often encounter information redundancy and feature mismatch during feature fusion, and they struggle with small-scale refined features. To address these issues, we propose DCG-Net, an innovative classification network integrating CNN and GCN architectures. Our approach includes the development of a double-branch expanding network (E-Net) to enhance spectral features and efficiently extract high-level features. Additionally, we incorporate a GCN with an attention mechanism to facilitate the integration of multi-space scale superpixel-level and pixel-level features. To further improve feature fusion, we introduce a feature aggregation module (FAM) that adaptively learns channel features, enhancing classification robustness and accuracy. Comprehensive experiments on three widely used datasets show that DCG-Net achieves superior classification results compared to other state-of-the-art methods. Full article

(This article belongs to the Topic Hyperspectral Imaging and Signal Processing)

►▼ Show Figures

Figure 1

16 pages, 2541 KiB  

Open AccessArticle

Improving the Estimation Accuracy of Soil Organic Matter Content Based on the Spectral Reflectance from Soils with Different Grain Sizes

by Xayida Subi, Mamattursun Eziz and Ning Wang

Land 2024, 13(7), 1111; https://doi.org/10.3390/land13071111 - 22 Jul 2024

Cited by 2 | Viewed by 1048

Abstract

Accurate and rapid estimation of soil organic matter (SOM) content is of great significance for advancing precision agriculture. Compared with traditional chemical methods, the hyperspectral estimation is superior in rapidly estimating SOM content. Soil grain size affects soil spectral reflectance, thereby affecting the [...] Read more.

Accurate and rapid estimation of soil organic matter (SOM) content is of great significance for advancing precision agriculture. Compared with traditional chemical methods, the hyperspectral estimation is superior in rapidly estimating SOM content. Soil grain size affects soil spectral reflectance, thereby affecting the accuracy of hyperspectral estimation. However, the appropriate soil grain size for the hyperspectral analysis is nearly unknown. This study propose a best hyperspectral estimation method for determining SOM content of farmland soil in the Ibinur Lake Irrigation Area (ILIA) of the northwest arid zones of China. The original spectral reflectance of the 20-mesh (0.85 mm) and 60-mesh (0.25 mm) sieved soil were obtained, and the feature wavebands were selected using five types of spectral transformations. Then, hyperspectral estimation models were constructed based on the partial least squares regression (PLSR), support vector machine (SVM), random forest (RF), and extreme gradient boosting (XGBoost) models. Results show that the SOM content had relatively higher correlation coefficient with spectral reflectance of the 0.85 mm sieved soil than that of the 0.25 mm sieved soil. The transformation of original spectral reflectance of soil effectively enhanced the spectral characteristics related to SOM content. Soil grain size obviously affected spectral reflectance and the accuracy of hyperspectral estimation models. The overall stability and estimation accuracy of RF model was significantly higher compared with the PLSR, SVM, and XGBoost. Finally, the RF model combined with the root mean first-order differentiation (RMSFD) of spectral reflectance of the 0.85 mm sieved soil (R² = 0.82, RMSE = 2.37, RPD = 2.27) was identified as the best method for estimating SOM content of farmland soil in the ILIA. Full article

(This article belongs to the Topic Hyperspectral Imaging and Signal Processing)

►▼ Show Figures

Figure 1

18 pages, 13110 KiB  

Open AccessArticle

TSC-1 Offner Spectrometer Prototype Characterization

by Weerapot Wanajaroen, Thierry Lepine, Pearachad Chartsiriwattana, Suwicha Wannawichian, Wiphu Rujopakarn, Saran Poshyachinda and Boonrucksar Soonthornthum

Photonics 2024, 11(7), 644; https://doi.org/10.3390/photonics11070644 - 6 Jul 2024

Viewed by 1451

Abstract

The Thai Space Consortium (TSC) has undertaken the development of an Offner spectrometer prototype for the TSC-1 satellite mission, aiming to enhance Earth observation capabilities. Through systematic parameter selection and radiometric analyses, optimal performance of the hyperspectral imager within established specifications was achieved [...] Read more.

The Thai Space Consortium (TSC) has undertaken the development of an Offner spectrometer prototype for the TSC-1 satellite mission, aiming to enhance Earth observation capabilities. Through systematic parameter selection and radiometric analyses, optimal performance of the hyperspectral imager within established specifications was achieved in the previous study. The design phase involved selecting a two-mirror off-axis telescope coupled with the Offner spectrometer for its diffraction-limited performance. Rigorous testing validated the prototype’s alignment with simulated performance, affirming its ability to meet demanding Earth observation requirements. The experimental results demonstrate that the Offner spectrometer prototype has been successfully developed. The spatial resolution ranges between 21.0 and 24.1 µm, and the spectral resolution ranges between 7.3 and 8.7 nm, with no significant distortion. Furthermore, the signal-to-noise ratio at 550 nm is 100. This achievement positions the TSC at the forefront of innovative Earth observation instrumentation in Thailand, with implications for future space missions requiring precise and efficient hyperspectral imaging. Full article

(This article belongs to the Topic Hyperspectral Imaging and Signal Processing)

►▼ Show Figures

Figure 1

18 pages, 54275 KiB  

Open AccessArticle

Unsupervised Characterization of Water Composition with UAV-Based Hyperspectral Imaging and Generative Topographic Mapping

by John Waczak, Adam Aker, Lakitha O. H. Wijeratne, Shawhin Talebi, Ashen Fernando, Prabuddha M. H. Dewage, Mazhar Iqbal, Matthew Lary, David Schaefer, Gokul Balagopal and David J. Lary

Remote Sens. 2024, 16(13), 2430; https://doi.org/10.3390/rs16132430 - 2 Jul 2024

Cited by 1 | Viewed by 1716

Abstract

Unmanned aerial vehicles equipped with hyperspectral imagers have emerged as an essential technology for the characterization of inland water bodies. The high spectral and spatial resolutions of these systems enable the retrieval of a plethora of optically active water quality parameters via band [...] Read more.

Unmanned aerial vehicles equipped with hyperspectral imagers have emerged as an essential technology for the characterization of inland water bodies. The high spectral and spatial resolutions of these systems enable the retrieval of a plethora of optically active water quality parameters via band ratio algorithms and machine learning methods. However, fitting and validating these models requires access to sufficient quantities of in situ reference data which are time-consuming and expensive to obtain. In this study, we demonstrate how Generative Topographic Mapping (GTM), a probabilistic realization of the self-organizing map, can be used to visualize high-dimensional hyperspectral imagery and extract spectral signatures corresponding to unique endmembers present in the water. Using data collected across a North Texas pond, we first apply GTM to visualize the distribution of captured reflectance spectra, revealing the small-scale spatial variability of the water composition. Next, we demonstrate how the nodes of the fitted GTM can be interpreted as unique spectral endmembers. Using extracted endmembers together with the normalized spectral similarity score, we are able to efficiently map the abundance of nearshore algae, as well as the evolution of a rhodamine tracer dye used to simulate water contamination by a localized source. Full article

(This article belongs to the Topic Hyperspectral Imaging and Signal Processing)

►▼ Show Figures

Figure 1

11 pages, 4623 KiB  

Open AccessArticle

Feasibility Study of Scanning Spectral Imaging Based on a Birefringence Flat Plate

by Ilan Gadasi and Yoel Arieli

Sensors 2024, 24(10), 3092; https://doi.org/10.3390/s24103092 - 13 May 2024

Viewed by 1075

Abstract

Hyper-spectral imaging (HSI) systems can be divided into two main types as follows: a group of systems that includes a dedicated dispersion/filtering component whose role is to physically separate the different wavelengths and a group of systems that sample all wavelengths in parallel, [...] Read more.

Hyper-spectral imaging (HSI) systems can be divided into two main types as follows: a group of systems that includes a dedicated dispersion/filtering component whose role is to physically separate the different wavelengths and a group of systems that sample all wavelengths in parallel, so that the separation into wavelengths is performed by signal processing (interferometric method). There is a significant advantage to systems of the second type in terms of the integration time required to obtain a signal with a high signal-to-noise ratio since the signal-to-noise ratio of methods based on scanning interferometry (Windowing method) is better compared to methods based on dispersion. The current research deals with the feasibility study of a new concept for an HSI system that is based on scanning interferometry using the “push-broom” method. In this study, we investigated the viability of incorporating a simple birefringent plate into a scanning optical system. By exploiting the motion of the platform on which the system is mounted, we extracted the spectral information of the scanned region. This approach combines the benefits of scanning interferometry with the simplicity of the setup. According to the theory, a chirped cosine-shaped interferogram is obtained for each wavelength due to the nonlinear behavior of the optical path difference of light in the birefringent plate as a function of the angle. An algorithm converts the signal from a superposition of chirped cosine signals to a scaled interferogram such that Fourier transforming (FT) the interferogram retrieves the spectral information. This innovative idea can turn a simple monochrome camera into a hyperspectral camera by adding a relief lens and a birefringent plate. Full article

(This article belongs to the Topic Hyperspectral Imaging and Signal Processing)

►▼ Show Figures

Figure 1

18 pages, 9402 KiB  

Open AccessArticle

Transfer Learning-Based Hyperspectral Image Classification Using Residual Dense Connection Networks

by Hao Zhou, Xianwang Wang, Kunming Xia, Yi Ma and Guowu Yuan

Sensors 2024, 24(9), 2664; https://doi.org/10.3390/s24092664 - 23 Apr 2024

Cited by 4 | Viewed by 2361

Abstract

The extraction of effective classification features from high-dimensional hyperspectral images, impeded by the scarcity of labeled samples and uneven sample distribution, represents a formidable challenge within hyperspectral image classification. Traditional few-shot learning methods confront the dual dilemma of limited annotated samples and the [...] Read more.

The extraction of effective classification features from high-dimensional hyperspectral images, impeded by the scarcity of labeled samples and uneven sample distribution, represents a formidable challenge within hyperspectral image classification. Traditional few-shot learning methods confront the dual dilemma of limited annotated samples and the necessity for deeper, more effective features from complex hyperspectral data, often resulting in suboptimal outcomes. The prohibitive cost of sample annotation further exacerbates the challenge, making it difficult to rely on a scant number of annotated samples for effective feature extraction. Prevailing high-accuracy algorithms require abundant annotated samples and falter in deriving deep, discriminative features from limited data, compromising classification performance for complex substances. This paper advocates for an integration of advanced spectral–spatial feature extraction with meta-transfer learning to address the classification of hyperspectral signals amidst insufficient labeled samples. Initially trained on a source domain dataset with ample labels, the model undergoes transference to a target domain with minimal samples, utilizing dense connection blocks and tree-dimensional convolutional residual connections to enhance feature extraction and maximize spatial and spectral information retrieval. This approach, validated on three diverse hyperspectral datasets—IP, UP, and Salinas—significantly surpasses existing classification algorithms and small-sample techniques in accuracy, demonstrating its applicability to high-dimensional signal classification under label constraints. Full article

(This article belongs to the Topic Hyperspectral Imaging and Signal Processing)

►▼ Show Figures

Figure 1

21 pages, 2495 KiB  

Open AccessArticle

Hyperspectral Image Classification Using Multi-Scale Lightweight Transformer

by Quan Gu, Hongkang Luan, Kaixuan Huang and Yubao Sun

Electronics 2024, 13(5), 949; https://doi.org/10.3390/electronics13050949 - 29 Feb 2024

Cited by 4 | Viewed by 1858

Abstract

The distinctive feature of hyperspectral images (HSIs) is their large number of spectral bands, which allows us to identify categories of ground objects by capturing discrepancies in spectral information. Convolutional neural networks (CNN) with attention modules effectively improve the classification accuracy of HSI. [...] Read more.

The distinctive feature of hyperspectral images (HSIs) is their large number of spectral bands, which allows us to identify categories of ground objects by capturing discrepancies in spectral information. Convolutional neural networks (CNN) with attention modules effectively improve the classification accuracy of HSI. However, CNNs are not successful in capturing long-range spectral–spatial dependence. In recent years, Vision Transformer (VIT) has received widespread attention due to its excellent performance in acquiring long-range features. However, it requires calculating the pairwise correlation between token embeddings and has the complexity of the square of the number of tokens, which leads to an increase in the computational complexity of the network. In order to cope with this issue, this paper proposes a multi-scale spectral–spatial attention network with frequency-domain lightweight Transformer (MSA-LWFormer) for HSI classification. This method synergistically integrates CNN, attention mechanisms, and Transformer into the spectral–spatial feature extraction module and frequency-domain fused classification module. Specifically, the spectral–spatial feature extraction module employs a multi-scale 2D-CNN with multi-scale spectral attention (MS-SA) to extract the shallow spectral–spatial features and capture the long-range spectral dependence. In addition, The frequency-domain fused classification module designs a frequency-domain lightweight Transformer that employs the Fast Fourier Transform (FFT) to convert features from the spatial domain to the frequency domain, effectively extracting global information and significantly reducing the time complexity of the network. Experiments on three classic hyperspectral datasets show that MSA-LWFormer has excellent performance. Full article

(This article belongs to the Topic Hyperspectral Imaging and Signal Processing)

►▼ Show Figures

Figure 1

12 pages, 1919 KiB  

Open AccessCommunication

Spatial-Spectral BERT for Hyperspectral Image Classification

by Mahmood Ashraf, Xichuan Zhou, Gemine Vivone, Lihui Chen, Rong Chen and Reza Seifi Majdard

Remote Sens. 2024, 16(3), 539; https://doi.org/10.3390/rs16030539 - 31 Jan 2024

Cited by 8 | Viewed by 2984

Abstract

Several deep learning and transformer models have been recommended in previous research to deal with the classification of hyperspectral images (HSIs). Among them, one of the most innovative is the bidirectional encoder representation from transformers (BERT), which applies a distance-independent approach to capture [...] Read more.

Several deep learning and transformer models have been recommended in previous research to deal with the classification of hyperspectral images (HSIs). Among them, one of the most innovative is the bidirectional encoder representation from transformers (BERT), which applies a distance-independent approach to capture the global dependency among all pixels in a selected region. However, this model does not consider the local spatial-spectral and spectral sequential relations. In this paper, a dual-dimensional (i.e., spatial and spectral) BERT (the so-called D²BERT) is proposed, which improves the existing BERT model by capturing more global and local dependencies between sequential spectral bands regardless of distance. In the proposed model, two BERT branches work in parallel to investigate relations among pixels and spectral bands, respectively. In addition, the layer intermediate information is used for supervision during the training phase to enhance the performance. We used two widely employed datasets for our experimental analysis. The proposed D²BERT shows superior classification accuracy and computational efficiency with respect to some state-of-the-art neural networks and the previously developed BERT model for this task. Full article

(This article belongs to the Topic Hyperspectral Imaging and Signal Processing)

►▼ Show Figures

Figure 1

24 pages, 1764 KiB  

Open AccessArticle

Hyperspectral Image Shadow Enhancement Using Three-Dimensional Dynamic Stochastic Resonance and Classification Based on ResNet

by Xuefeng Liu, Yangyang Kou and Min Fu

Electronics 2024, 13(3), 500; https://doi.org/10.3390/electronics13030500 - 24 Jan 2024

Cited by 2 | Viewed by 1204

Abstract

Classification is an important means of extracting rich information from hyperspectral images (HSIs). However, many HSIs contain shadowed areas, where noise severely affects the extraction of useful information. General noise removal may lead to loss of spatial correlation and spectral features. In contrast, [...] Read more.

Classification is an important means of extracting rich information from hyperspectral images (HSIs). However, many HSIs contain shadowed areas, where noise severely affects the extraction of useful information. General noise removal may lead to loss of spatial correlation and spectral features. In contrast, dynamic stochastic resonance (DSR) converts noise into capability that enhances the signal in a way that better preserves the image’s original information. Nevertheless, current one-dimensional and 2D DSR methods fail to fully utilize the tensor properties of hyperspectral data and preserve the complete spectral features. Therefore, a hexa-directional differential format is derived in this paper to solve the system’s output, and the iterative equation for HSI shadow enhancement is obtained, enabling 3D parallel processing of HSI spatial–spectral information. Meanwhile, internal parameters are adjusted to achieve optimal resonance. Furthermore, the residual neural network 152 model embedded with the convolutional block attention module is proposed to diminish information redundancy and leverage data concealed within shadow areas. Experimental results on a real-world HSI demonstrate the potential performance of 3D DSR in enhancing weak signals in HSI shadow regions and the proposed approach’s effectiveness in improving classification. Full article

(This article belongs to the Topic Hyperspectral Imaging and Signal Processing)

►▼ Show Figures

Figure 1

20 pages, 9554 KiB  

Open AccessArticle

A U-Shaped Convolution-Aided Transformer with Double Attention for Hyperspectral Image Classification

by Ruiru Qin, Chuanzhi Wang, Yongmei Wu, Huafei Du and Mingyun Lv

Remote Sens. 2024, 16(2), 288; https://doi.org/10.3390/rs16020288 - 11 Jan 2024

Cited by 2 | Viewed by 1580

Abstract

Convolutional neural networks (CNNs) and transformers have achieved great success in hyperspectral image (HSI) classification. However, CNNs are inefficient in establishing long-range dependencies, and transformers may overlook some local information. To overcome these limitations, we propose a U-shaped convolution-aided transformer (UCaT) that incorporates [...] Read more.

Convolutional neural networks (CNNs) and transformers have achieved great success in hyperspectral image (HSI) classification. However, CNNs are inefficient in establishing long-range dependencies, and transformers may overlook some local information. To overcome these limitations, we propose a U-shaped convolution-aided transformer (UCaT) that incorporates convolutions into a novel transformer architecture to aid classification. The group convolution is employed as parallel local descriptors to extract detailed features, and then the multi-head self-attention recalibrates these features in consistent groups, emphasizing informative features while maintaining the inherent spectral–spatial data structure. Specifically, three components are constructed using particular strategies. First, the spectral groupwise self-attention (spectral-GSA) component is developed for spectral attention, which selectively emphasizes diagnostic spectral features among neighboring bands and reduces the spectral dimension. Then, the spatial dual-scale convolution-aided self-attention (spatial-DCSA) encoder and spatial convolution-aided cross-attention (spatial-CCA) decoder form a U-shaped architecture for per-pixel classifications over HSI patches, where the encoder utilizes a dual-scale strategy to explore information in different scales and the decoder adopts the cross-attention for information fusion. Experimental results on three datasets demonstrate that the proposed UCaT outperforms the competitors. Additionally, a visual explanation of the UCaT is given, showing its ability to build global interactions and capture pixel-level dependencies. Full article

(This article belongs to the Topic Hyperspectral Imaging and Signal Processing)

►▼ Show Figures

Figure 1

24 pages, 7871 KiB  

Open AccessArticle

An Optimized Inversion Method for Hyperspectral Image Fusion Based on a Hue–Intensity–Saturation, Wavelet, and Trust-Region Conjugate Gradient Method

by Jiangbo Wu, Aiming Ge, Shuo Liu, Qiuyang Wang, Dongsheng Zhu and Xindi Chen

Electronics 2024, 13(2), 252; https://doi.org/10.3390/electronics13020252 - 5 Jan 2024

Cited by 2 | Viewed by 1642

Abstract

In hyperspectral remote sensing, achieving high spatial resolution holds paramount importance for an array of applications, such as environmental monitoring, geographic mapping, and precision agriculture. Nevertheless, conventional hyperspectral images frequently grapple with the issue of restricted spatial resolution. We apply optimized inversion methods [...] Read more.

In hyperspectral remote sensing, achieving high spatial resolution holds paramount importance for an array of applications, such as environmental monitoring, geographic mapping, and precision agriculture. Nevertheless, conventional hyperspectral images frequently grapple with the issue of restricted spatial resolution. We apply optimized inversion methods to hyperspectral image fusion and present an innovative approach for hyperspectral image fusion which combines the Hue–Intensity–Saturation (HIS) transform, the wavelet transform, and the Trust-Region Conjugate Gradient technique. This amalgamation not only refines spatial precision but also augments spectral faithfulness, which is a pivotal aspect for applications like precise object detection and classification. In the context of our investigation, we conducted a thorough validation of our proposed HIS, Wavelet, and Trust-Region Conjugate Gradient (TRCG-HW) method for image fusion using a comprehensive suite of evaluation metrics. These metrics encompassed the Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index (SSIM), Correlation Coefficient (CC), Spectral Angle Mapper (SAM), and Error Relative Global Accuracy Score (ERGAS). The findings incontrovertibly establish TRCG-HW as the preeminent method among those considered. Our study effectively tackles the pressing predicament of low spatial resolution encountered in hyperspectral imaging. This innovative paradigm harbors the potential to revolutionize high-resolution hyperspectral data acquisition, propelling the field of hyperspectral remote sensing forward and efficiently catering to crucial application. Full article

(This article belongs to the Topic Hyperspectral Imaging and Signal Processing)

►▼ Show Figures

Figure 1

17 pages, 21887 KiB  

Open AccessArticle

A Neural Network for Hyperspectral Image Denoising by Combining Spatial–Spectral Information

by Xiaoying Lian, Zhonghai Yin, Siwei Zhao, Dandan Li, Shuai Lv, Boyu Pang and Dexin Sun

Remote Sens. 2023, 15(21), 5174; https://doi.org/10.3390/rs15215174 - 30 Oct 2023

Cited by 4 | Viewed by 2386

Abstract

Hyperspectral imaging often suffers from various types of noise, including sensor non-uniformity and atmospheric disturbances. Removing multiple types of complex noise in hyperspectral images (HSIs) while preserving high fidelity in spectral dimensions is a challenging task in hyperspectral data processing. Existing methods typically [...] Read more.

Hyperspectral imaging often suffers from various types of noise, including sensor non-uniformity and atmospheric disturbances. Removing multiple types of complex noise in hyperspectral images (HSIs) while preserving high fidelity in spectral dimensions is a challenging task in hyperspectral data processing. Existing methods typically focus on specific types of noise, resulting in limited applicability and an inadequate ability to handle complex noise scenarios. This paper proposes a denoising method based on a network that considers both the spatial structure and spectral differences of noise in an image data cube. The proposed network takes into account the DN value of the current band, as well as the horizontal, vertical, and spectral gradients as inputs. A multi-resolution convolutional module is employed to accurately extract spatial and spectral noise features, which are then aggregated through residual connections at different levels. Finally, the residual mixed noise is approximated. Both simulated and real case studies confirm the effectiveness of the proposed denoising method. In the simulation experiment, the average PSNR value of the denoised results reached 31.47 at a signal-to-noise ratio of 8 dB, and the experimental results on the real data set Indian Pines show that the classification accuracy of the denoised hyperspectral image (HSI) is improved by 16.31% compared to the original noisy version. Full article

(This article belongs to the Topic Hyperspectral Imaging and Signal Processing)

►▼ Show Figures

Figure 1

22 pages, 12136 KiB  

Open AccessArticle

The Use of a Stable Super-Resolution Generative Adversarial Network (SSRGAN) on Remote Sensing Images

by Boyu Pang, Siwei Zhao and Yinnian Liu

Remote Sens. 2023, 15(20), 5064; https://doi.org/10.3390/rs15205064 - 22 Oct 2023

Cited by 7 | Viewed by 2239

Abstract

Because of the complicated imaging conditions in space and the finite imaging systems on satellites, the resolution of remote sensing images is limited. The process of increasing an image’s resolution, image super-resolution, aims to obtain a clearer image. High-resolution (HR) images are affected [...] Read more.

Because of the complicated imaging conditions in space and the finite imaging systems on satellites, the resolution of remote sensing images is limited. The process of increasing an image’s resolution, image super-resolution, aims to obtain a clearer image. High-resolution (HR) images are affected by various input conditions, such as motion, imaging blur, down-sampling matrix, and various types of noise. Changes in these conditions seriously affect low-resolution (LR) images, so if the imaging process is a pathological problem, super-resolution reconstruction is a pathological anti-problem. To optimize the imaging quality of satellites without changing the optical system, we chose to reconstruct images acquired by satellites using deep learning. We changed the original super-resolution generative adversarial nets network, upgraded the generator’s network part to ResNet-50, and inserted an additional fully connected (FC) layer in the network of the discriminator part. We also modified the loss function by changing the weight of regularization loss from 2 × 10⁻⁸ to 2 × 10⁻⁹, aiming to preserve more detail. In addition, we carefully and specifically chose remote sensing images taken under low-light circumstances from GF-5 satellites to form a new dataset for training and validation. The test results proved that our method can obtain good results. The reconstruction peak signal-to-noise ratio (PSNR) at the scaling factors of 2, 3, and 4 reached 32.6847, 31.8191, and 30.5095 dB, respectively, and the corresponding structural similarity (SSIM) reached 0.8962, 0.8434, and 0.8124. The super-resolution speed was also satisfactory, making real-time reconstruction more probable. Full article

(This article belongs to the Topic Hyperspectral Imaging and Signal Processing)

►▼ Show Figures

Figure 1

12 pages, 4761 KiB  

Open AccessCommunication

Pre-Launch Spectral Calibration of the Absorbed Aerosol Sensor

by Jinghua Mao, Yongmei Wang, Entao Shi and Jinduo Wang

Sensors 2023, 23(20), 8590; https://doi.org/10.3390/s23208590 - 20 Oct 2023

Cited by 1 | Viewed by 1160

Abstract

Spectral calibration consists of the calibration of wavelengths and the measurement of the instrument’s spectral response function (SRF). Unlike conventional slits, the absorbed aerosol sensors (AAS) are used as a slit homogenizer, in which the SRF is not a conventional Gaussian curve. To [...] Read more.

Spectral calibration consists of the calibration of wavelengths and the measurement of the instrument’s spectral response function (SRF). Unlike conventional slits, the absorbed aerosol sensors (AAS) are used as a slit homogenizer, in which the SRF is not a conventional Gaussian curve. To be more precise, the SRF is the convolution of the slit function of the spectrometer, the line spread function of the optical system, and the detector response function. The SRF of the slit homogenizer is a flat-topped multi-Gaussian function. Considering the convenience of fitting, a super-Gaussian function, which has a distribution similar to the flat-topped multi-Gaussian function, is employed to fit the measured data in a spectral calibration. According to the results, the SRF’s shapes resembling a Gaussian curve with a flat top could be derived, which contains a full width at half maximum (FWHM) of 1.78–1.82 nm for the AAS. The results show that the correlation is about 0.99, which indicates the usefulness of the fitting function that could better characterize the SRF of the instrument. Full article

(This article belongs to the Topic Hyperspectral Imaging and Signal Processing)

►▼ Show Figures

Figure 1

24 pages, 10759 KiB  

Open AccessArticle

Impact of a Hyperspectral Satellite Cross-Calibration Radiometer’s Spatial and Noise Characteristics on Cross-Calibration

by Robert E. Ryan, Mary Pagnutti, Max Huggins, Kara Burch, David Sitton, Kimberly Manriquez and Hannah Ryan

Remote Sens. 2023, 15(18), 4419; https://doi.org/10.3390/rs15184419 - 8 Sep 2023

Cited by 6 | Viewed by 1673

Abstract

The satellite cross-calibration radiometer (SCR) is a conceptual on-orbit hyperspectral imaging radiometer that transfers the radiometric calibration from a “gold-standard” reference instrument such as the Landsat 8/9 Operational Land Imager (OLI) to other civil, international, or commercial “client” multispectral satellite systems via near-simultaneous [...] Read more.

The satellite cross-calibration radiometer (SCR) is a conceptual on-orbit hyperspectral imaging radiometer that transfers the radiometric calibration from a “gold-standard” reference instrument such as the Landsat 8/9 Operational Land Imager (OLI) to other civil, international, or commercial “client” multispectral satellite systems via near-simultaneous cross-calibration acquisitions. The spectral resolution, spectral range, spatial resolution, and signal-to-noise ratio (SNR) all significantly impact the complexity and cost of hyperspectral SCRs, so it is important to understand their effect on cross-calibration quality. This paper discusses the results of a trade study to quantify the effects of varying ground sample distance (GSD), number of independent samples, and instrument/scene noise on cross-calibration gain uncertainties. The trade study used a simulated SCR cross-calibration with near-simultaneous nadir overpasses (SNOs) of the Landsat 8 OLI acting as the reference instrument and the DLR Earth Sensing Imaging Spectrometer (DESIS) acting as a surrogate SCR hyperspectral instrument. Results demonstrate that cross-calibration uncertainty is only minimally affected by spatial resolution and SNR, which may allow SCR instruments to be developed at a lower cost. Full article

(This article belongs to the Topic Hyperspectral Imaging and Signal Processing)

►▼ Show Figures

Figure 1

16 pages, 3895 KiB  

Open AccessArticle

Spectral Image Reconstruction Using Recovered Basis Vector Coefficients

by Wei Xu, Liangzhuang Wei, Xiangwei Yi and Yandan Lin

Photonics 2023, 10(9), 1018; https://doi.org/10.3390/photonics10091018 - 6 Sep 2023

Cited by 1 | Viewed by 1670

Abstract

Spectral imaging plays a crucial role in various fields, including remote sensing, medical imaging, and material analysis, but it often requires specialized and expensive equipment, making it inaccessible to many. Its application is also limited by the interdependent constraints of temporal, spatial, and [...] Read more.

Spectral imaging plays a crucial role in various fields, including remote sensing, medical imaging, and material analysis, but it often requires specialized and expensive equipment, making it inaccessible to many. Its application is also limited by the interdependent constraints of temporal, spatial, and spectral resolutions. In order to address these issues, and thus, obtain high-quality spectral images in a time-efficient and affordable manner, we proposed one two-step method for spectral image reconstruction from easily available RGB images under the down-sampling schemes. Specifically, we investigated how RGB values characterize spectral reflectance and found that, compared to the intuitive and straightforward RGB images themselves, their corresponding basis vector coefficients can represent the prior information of spectral images more explicitly and are better suited for spectral image reconstruction tasks. Thus, we derived one data-driven algebraic method to recover the corresponding basis vector coefficients from RGB images in an analytical form and then employed one CNN-based neural network to learn the patch-level mapping from the recovered basis vector coefficients to spectral images. To evaluate the effect of introducing the basis vector coefficient recovery step, several CNNs which typically perform well in spectral image reconstruction are chosen as benchmarks to compare the variation in reconstruction performance. Experimental results on a large public spectral image dataset and our real-world dataset demonstrate that compared to the unaltered version, those CNNs guided by the recovered basis vector coefficients can achieve significant performance improvement in the reconstruction accuracy. Furthermore, this method is plug-and-play, with very little computational performance consumption, thus maintaining a high speed of calculation. Full article

(This article belongs to the Topic Hyperspectral Imaging and Signal Processing)

►▼ Show Figures

Figure 1

18 pages, 6899 KiB  

Open AccessArticle

Hyperspectral Channel-Modulated Static Birefringent Fourier Transform Imaging Spectropolarimeter with Zoomable Spectral Resolution

by Xiangzhe Zhang, Jingping Zhu, Liqing Huang, Yu Zhang, Huimin Wang, Haoxiang Li, Fengqi Guo and Jinxin Deng

Photonics 2023, 10(8), 950; https://doi.org/10.3390/photonics10080950 - 18 Aug 2023

Cited by 3 | Viewed by 1566

Abstract

A novel channel-modulated static birefringent Fourier transform imaging spectropolarimeter (CSBFTIS) is introduced, which is based on a double Wollaston prism (DWP). With an adjustable air gap (AG), the spectral resolution can be adjusted by changing the AG. The CSBFTIS combines the channel-modulated imaging [...] Read more.

A novel channel-modulated static birefringent Fourier transform imaging spectropolarimeter (CSBFTIS) is introduced, which is based on a double Wollaston prism (DWP). With an adjustable air gap (AG), the spectral resolution can be adjusted by changing the AG. The CSBFTIS combines the channel-modulated imaging spectropolarimeter and the slit-free static birefringent Fourier transform imaging spectrometer technology with adjustable spectral resolution. The device is compact and robust, with a wide spectral range and a large luminous flux. Compared with various previous spectropolarimeters, it can greatly reduce the size of the spectral image data to adapt to different application requirements. A prototype is built, and simulation and experiments are carried out, and the results prove the effectiveness of the method. Full article

(This article belongs to the Topic Hyperspectral Imaging and Signal Processing)

►▼ Show Figures

Figure 1

20 pages, 6306 KiB  

Open AccessArticle

Few-Shot Hyperspectral Image Classification Based on Convolutional Residuals and SAM Siamese Networks

by Mengen Xia, Guowu Yuan, Lingyu Yang, Kunming Xia, Ying Ren, Zhiliang Shi and Hao Zhou

Electronics 2023, 12(16), 3415; https://doi.org/10.3390/electronics12163415 - 11 Aug 2023

Cited by 11 | Viewed by 2153

Abstract

With the development of few-shot learning, significant progress has been achieved in hyperspectral image classification using related networks, leading to improved classification outcomes. However, practical few-shot hyperspectral image classification encounters challenges such as network overfitting and insufficient feature extraction during the model training [...] Read more.

With the development of few-shot learning, significant progress has been achieved in hyperspectral image classification using related networks, leading to improved classification outcomes. However, practical few-shot hyperspectral image classification encounters challenges such as network overfitting and insufficient feature extraction during the model training process. To address these issues, we propose a model called CRSSNet (Convolutional Residuals and SAM Siamese Networks) for few-shot hyperspectral image classification. In this model, we deepen the network depth and employ the convolutional residual technique to enhance the feature extraction capabilities and alleviate the problem of network gradient degradation. Additionally, we introduce the Spatial Attention Mechanism (SAM) to effectively leverage spatial information features in hyperspectral images. Lastly, metric learning is employed by comparing the distance between two output feature vectors to determine the label category. Experimental results demonstrate that our method achieves superior classification performance compared to other methods. Full article

(This article belongs to the Topic Hyperspectral Imaging and Signal Processing)

►▼ Show Figures

Figure 1

17 pages, 9720 KiB  

Open AccessArticle

Thangka Hyperspectral Image Super-Resolution Based on a Spatial–Spectral Integration Network

by Sai Wang and Fenglei Fan

Remote Sens. 2023, 15(14), 3603; https://doi.org/10.3390/rs15143603 - 19 Jul 2023

Cited by 3 | Viewed by 2665

Abstract

Thangka refers to a form of Tibetan Buddhist painting on a fabric, scroll, or Thangka, often depicting deities, scenes, or mandalas. Deep-learning-based super-resolution techniques have been applied to improve the spatial resolution of hyperspectral images (HSIs), especially for the preservation and analysis of [...] Read more.

Thangka refers to a form of Tibetan Buddhist painting on a fabric, scroll, or Thangka, often depicting deities, scenes, or mandalas. Deep-learning-based super-resolution techniques have been applied to improve the spatial resolution of hyperspectral images (HSIs), especially for the preservation and analysis of Thangka cultural heritage. However, existing CNN-based methods encounter difficulties in effectively preserving spatial information, due to challenges such as registration errors and spectral variability. To overcome these limitations, we present a novel cross-sensor super-resolution (SR) framework that utilizes high-resolution RGBs (HR-RGBs) to enhance the spectral features in low-resolution hyperspectral images (LR-HSIs). Our approach utilizes spatial–spectral integration (SSI) blocks and spatial–spectral restoration (SSR) blocks to effectively integrate and reconstruct spatial and spectral features. Furthermore, we introduce a frequency multi-head self-attention (F-MSA) mechanism that treats high-, medium-, and low-frequency features as tokens, enabling self-attention computations across the frequency dimension. We evaluate our method on a custom dataset of ancient Thangka paintings and demonstrate its effectiveness in enhancing the spectral resolution in high-resolution hyperspectral images (HR-HSIs), while preserving the spatial characteristics of Thangka artwork with minimal information loss. Full article

(This article belongs to the Topic Hyperspectral Imaging and Signal Processing)

►▼ Show Figures

Figure 1

21 pages, 12231 KiB  

Open AccessArticle

Spatial–Spectral Joint Hyperspectral Anomaly Detection Based on a Two-Branch 3D Convolutional Autoencoder and Spatial Filtering

by Shuai Lv, Siwei Zhao, Dandan Li, Boyu Pang, Xiaoying Lian and Yinnian Liu

Remote Sens. 2023, 15(10), 2542; https://doi.org/10.3390/rs15102542 - 12 May 2023

Cited by 7 | Viewed by 2190

Abstract

Hyperspectral anomaly detection (HAD) is an important application of hyperspectral images (HSI) that can distinguish anomalies from background in an unsupervised manner. As a common unsupervised network in deep learning, autoencoders (AE) have been widely used in HAD and can highlight anomalies by [...] Read more.

Hyperspectral anomaly detection (HAD) is an important application of hyperspectral images (HSI) that can distinguish anomalies from background in an unsupervised manner. As a common unsupervised network in deep learning, autoencoders (AE) have been widely used in HAD and can highlight anomalies by reconstructing the background. This study proposed a novel spatial–spectral joint HAD method based on a two-branch 3D convolutional autoencoder and spatial filtering. We used the two-branch 3D convolutional autoencoder to fully extract the spatial–spectral joint features and spectral interband features of HSI. In addition, we used a morphological filter and a total variance curvature filter for spatial detection. Currently, most of the datasets used to validate the performance of HAD methods are airborne HSI, and there are few available satellite-borne HSI. For this reason, we constructed a dataset of satellite-borne HSI based on the GF-5 satellite for experimental validation of our anomaly detection method. The experimental results for the airborne and satellite-borne HSI demonstrated the superior performance of the proposed method compared with six state-of-the-art methods. The area under the curve (AUC) values of our proposed method on different HSI reached above 0.9, which is higher than those of the other methods. Full article

(This article belongs to the Topic Hyperspectral Imaging and Signal Processing)

►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less

Select all

Export citation of selected articles as:

Plain Text BibTeX BibTeX (without abstracts) Endnote Endnote (without abstracts) Tab-delimited RIS

 

Error

Oops... you haven't selected anything for export.

Ok

clear

Displaying articles 1-27