Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
8.3
4.2
Journals
Remote Sensing
Special Issues
Deep Learning for Spectral-Spatial Hyperspectral Image Classification
remotesensing-logo
Submit to Special Issue Submit Abstract to Special Issue Review for Remote Sensing Propose a Special Issue

Journal Menu

► Journal Menu

Journal Browser

► Journal Browser
share announcement

Deep Learning for Spectral-Spatial Hyperspectral Image Classification

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

Deadline for manuscript submissions: 25 January 2025 | Viewed by 6994

Special Issue Editors

Dr. Jiayi Li

E-Mail Website
Guest Editor
School of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430079, China
Interests: urban remote sensing; urban ecology and environmental analysis; high-resolution remote sensing processing
Special Issues, Collections and Topics in MDPI journals
Prof. Dr. Maria Grazia D’Urso

E-Mail Website
Guest Editor
Department of Engineering and Applied Sciences, University of Bergamo, Via Salvecchio 19, 24129 Bergamo, Italy
Interests: structural and infra-structural monitoring with new geomatic techniques (MEMS sensors, UAV platforms, remote sensing)
Special Issues, Collections and Topics in MDPI journals
Dr. Xian Guo

E-Mail Website
Guest Editor
School of Geomatics and Urban Spatial Informatics, Beijing University of Civil Engineering and Architecture, Beijing, China
Interests: high-dimensional spatiotemporal data mining; hyperspectral image classification
Special Issues, Collections and Topics in MDPI journals
Dr. Jie Yang

E-Mail Website
Guest Editor
School of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430079, China
Interests: urban remote sensing; operational land cover mapping; spatiotemporal analysis
Prof. Dr. Pedram Ghamisi

grade E-Mail Website
Guest Editor
1.Helmholtz Institute Freiberg for Resource Technology, Helmholtz-Zentrum Dresden-Rossendorf (HZDR), D-09599 Freiberg, Germany
2. Institute of Advanced Research in Artificial Intelligence (IARAI), 1030 Wien, Austria
Interests: hyperspectral image interpretation; multisensor and multitemporal data fusion
Special Issues, Collections and Topics in MDPI journals
Prof. Dr. Xin Huang

grade E-Mail Website
Guest Editor
School of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430079, China
Interests: high spatial and hyperspectral remote sensing image processing methods and applications
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Hyperspectral imaging has greatly expanded our ability to gather detailed data about the Earth's surface. However, effectively utilizing this rich spectral information remains a challenge. Deep learning has emerged as a promising solution, revolutionizing hyperspectral image classification by automatically learning intricate spectral-spatial patterns. We invite contributions that advance the state-of-the-art in this exciting field to unlock new insights to more accurate and impactful applications.

This Special Issue aims to explore the cutting-edge developments in the application of deep learning techniques for spectral-spatial hyperspectral image classification. Researchers are encouraged to submit original research papers, reviews, or surveys. Submissions should adhere to high scientific standards, demonstrate the significance of their contributions, and offer clear experimental validation. We welcome submissions that address both theoretical advancements and real-world applications.

This Special Issue aims to cover a wide range of topics related to deep learning for spectral-spatial hyperspectral image classification, including but not limited to:

  • Development and optimization of deep neural network architectures tailored for hyperspectral data.
  • Spectral and spatial information fusion in deep learning models.
  • Dimensionality reduction methods for hyperspectral data pre-processing.
  • Transfer learning and domain adaptation in hyperspectral image classification.
  • Data augmentation and label noise learning.
  • Benchmark datasets for hyperspectral classification.
  • Explainable deep learning.
  • Applications in environmental monitoring, agriculture, mineral exploration, and more.
  • Integration of multi-modal data sources with hyperspectral imagery.

Dr. Jiayi Li
Prof. Dr. Maria Grazia D’Urso
Dr. Xian Guo
Dr. Jie Yang
Prof. Dr. Pedram Ghamisi
Prof. Dr. Xin Huang
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

  • deep learning
  • hyperspectral imaging
  • spectral-spatial classification
  • domain adaption
  • attention mechanisms

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • e-Book format: Special Issues with more than 10 articles can be published as dedicated e-books, ensuring wide and rapid dissemination.

Further information on MDPI's Special Issue polices can be found here.

Published Papers (6 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

23 pages, 16427 KiB  
Article
Identifying Rare Earth Elements Using a Tripod and Drone-Mounted Hyperspectral Camera: A Case Study of the Mountain Pass Birthday Stock and Sulphide Queen Mine Pit, California
by Muhammad Qasim, Shuhab D. Khan, Virginia Sisson, Presley Greer, Lin Xia, Unal Okyay and Nicole Franco
Remote Sens. 2024, 16(17), 3353; https://doi.org/10.3390/rs16173353 - 9 Sep 2024
Viewed by 791
Abstract
As the 21st century advances, the demand for rare earth elements (REEs) is rising, necessitating more robust exploration methods. Our research group is using hyperspectral remote sensing as a tool for mapping REEs. Unique spectral features of bastnaesite mineral, has proven effective for [...] Read more.
As the 21st century advances, the demand for rare earth elements (REEs) is rising, necessitating more robust exploration methods. Our research group is using hyperspectral remote sensing as a tool for mapping REEs. Unique spectral features of bastnaesite mineral, has proven effective for detection of REE with both spaceborne and airborne data. In our study, we collected hyperspectral data using a Senop hyperspectral camera in field and a SPECIM hyperspectral camera in the laboratory settings. Data gathered from California’s Mountain Pass district revealed bastnaesite-rich zones and provided detailed insights into bastnaesite distribution within rocks. Further analysis identified specific bastnaesite-rich rock grains. Our results indicated higher concentrations of bastnaesite in carbonatite rocks compared to alkaline igneous rocks. Additionally, rocks from the Sulphide Queen mine showed richer bastnaesite concentrations than those from the Birthday shonkinite stock. Results were validated with thin-section studies and geochemical data, confirming the reliability across different hyperspectral data modalities. This study demonstrates the potential of drone-based hyperspectral technology in augmenting conventional mineral mapping methods and aiding the mining industry in making informed decisions about mining REEs efficiently and effectively. Full article
(This article belongs to the Special Issue Deep Learning for Spectral-Spatial Hyperspectral Image Classification)
►▼ Show Figures

Figure 1

22 pages, 9228 KiB  
Article
Cross-Hopping Graph Networks for Hyperspectral–High Spatial Resolution (H2) Image Classification
by Tao Chen, Tingting Wang, Huayue Chen, Bochuan Zheng and Wu Deng
Remote Sens. 2024, 16(17), 3155; https://doi.org/10.3390/rs16173155 - 27 Aug 2024
Viewed by 541
Abstract
As we take stock of the contemporary issue, remote sensing images are gradually advancing towards hyperspectral–high spatial resolution (H2) double-high images. However, high resolution produces serious spatial heterogeneity and spectral variability while improving image resolution, which increases the difficulty of feature [...] Read more.
As we take stock of the contemporary issue, remote sensing images are gradually advancing towards hyperspectral–high spatial resolution (H2) double-high images. However, high resolution produces serious spatial heterogeneity and spectral variability while improving image resolution, which increases the difficulty of feature recognition. So as to make the best of spectral and spatial features under an insufficient number of marking samples, we would like to achieve effective recognition and accurate classification of features in H2 images. In this paper, a cross-hop graph network for H2 image classification(H2-CHGN) is proposed. It is a two-branch network for deep feature extraction geared towards H2 images, consisting of a cross-hop graph attention network (CGAT) and a multiscale convolutional neural network (MCNN): the CGAT branch utilizes the superpixel information of H2 images to filter samples with high spatial relevance and designate them as the samples to be classified, then utilizes the cross-hop graph and attention mechanism to broaden the range of graph convolution to obtain more representative global features. As another branch, the MCNN uses dual convolutional kernels to extract features and fuse them at various scales while attaining pixel-level multi-scale local features by parallel cross connecting. Finally, the dual-channel attention mechanism is utilized for fusion to make image elements more prominent. This experiment on the classical dataset (Pavia University) and double-high (H2) datasets (WHU-Hi-LongKou and WHU-Hi-HongHu) shows that the H2-CHGN can be efficiently and competently used in H2 image classification. In detail, experimental results showcase superior performance, outpacing state-of-the-art methods by 0.75–2.16% in overall accuracy. Full article
(This article belongs to the Special Issue Deep Learning for Spectral-Spatial Hyperspectral Image Classification)
►▼ Show Figures

Figure 1

24 pages, 5210 KiB  
Article
Enhancing Semi-Supervised Few-Shot Hyperspectral Image Classification via Progressive Sample Selection
by Jiaguo Zhao, Junjie Zhang, Huaxi Huang and Jian Zhang
Remote Sens. 2024, 16(10), 1747; https://doi.org/10.3390/rs16101747 - 15 May 2024
Viewed by 919
Abstract
Hyperspectral images (HSIs) provide valuable spatial–spectral information for ground analysis. However, in few-shot (FS) scenarios, the limited availability of training samples poses significant challenges in capturing the sample distribution under diverse environmental conditions. Semi-supervised learning has shown promise in exploring the distribution of [...] Read more.
Hyperspectral images (HSIs) provide valuable spatial–spectral information for ground analysis. However, in few-shot (FS) scenarios, the limited availability of training samples poses significant challenges in capturing the sample distribution under diverse environmental conditions. Semi-supervised learning has shown promise in exploring the distribution of unlabeled samples through pseudo-labels. Nonetheless, FS HSI classification encounters the issue of high intra-class spectral variability and inter-class spectral similarity, which often lead to the diffusion of unreliable pseudo-labels during the iterative process. In this paper, we propose a simple yet effective progressive pseudo-label selection strategy that leverages the spatial–spectral consistency of HSI pixel samples. By leveraging spatially aligned ground materials as connected regions with the same semantic and similar spectrum, pseudo-labeled samples were selected based on round-wise confidence scores. Samples within both spatially and semantically connected regions of FS samples were assigned pseudo-labels and joined subsequent training rounds. Moreover, considering the spatial positions of FS samples that may appear in diverse patterns, to fully utilize unlabeled samples that fall outside the neighborhood of FS samples but still belong to certain connected regions, we designed a matching active learning approach for expert annotation based on the temporal confidence difference. We identified samples with the highest training value in specific regions, utilizing the consistency between predictive labels and expert labels to decide whether to include the region or the sample itself in the subsequent semi-supervised iteration. Experiments on both classic and more recent HSI datasets demonstrated that the proposed base model achieved SOTA performance even with extremely rare labeled samples. Moreover, the extended version with active learning further enhances performance by involving limited additional annotation. Full article
(This article belongs to the Special Issue Deep Learning for Spectral-Spatial Hyperspectral Image Classification)
►▼ Show Figures

Figure 1

21 pages, 4386 KiB  
Article
Spectral-Spatial-Sensorial Attention Network with Controllable Factors for Hyperspectral Image Classification
by Sheng Li, Mingwei Wang, Chong Cheng, Xianjun Gao, Zhiwei Ye and Wei Liu
Remote Sens. 2024, 16(7), 1253; https://doi.org/10.3390/rs16071253 - 1 Apr 2024
Cited by 1 | Viewed by 1040
Abstract
Hyperspectral image (HSI) classification aims to recognize categories of objects based on spectral–spatial features and has been used in a wide range of real-world application areas. Attention mechanisms are widely used in HSI classification for their ability to focus on important information in [...] Read more.
Hyperspectral image (HSI) classification aims to recognize categories of objects based on spectral–spatial features and has been used in a wide range of real-world application areas. Attention mechanisms are widely used in HSI classification for their ability to focus on important information in images automatically. However, due to the approximate spectral–spatial features in HSI, mainstream attention mechanisms are difficult to accurately distinguish the small difference, which limits the classification accuracy. To overcome this problem, a spectral–spatial-sensorial attention network (S3AN) with controllable factors is proposed to efficiently recognize different objects. Specifically, two controllable factors, dynamic exponential pooling (DE-Pooling) and adaptive convolution (Adapt-Conv), are designed to enlarge the difference in approximate features and enhance the attention weight interaction. Then, attention mechanisms with controllable factors are utilized to build the redundancy reduction module (RRM), feature learning module (FLM), and label prediction module (LPM) to process HSI spectral–spatial features. The RRM utilizes the spectral attention mechanism to select representative band combinations, and the FLM introduces the spatial attention mechanism to highlight important objects. Furthermore, the sensorial attention mechanism extracts location and category information in a pseudo label to guide the LPM for label prediction and avoid details from being ignored. Experimental results on three public HSI datasets show that the proposed method is able to accurately recognize different objects with an overall accuracy (OA) of 98.69%, 98.89%, and 97.56%, respectively. Full article
(This article belongs to the Special Issue Deep Learning for Spectral-Spatial Hyperspectral Image Classification)
►▼ Show Figures

Graphical abstract

25 pages, 15523 KiB  
Article
A Framework for Fine-Grained Land-Cover Classification Using 10 m Sentinel-2 Images
by Wenge Zhang, Xuan Yang, Zhanliang Yuan, Zhengchao Chen and Yue Xu
Remote Sens. 2024, 16(2), 390; https://doi.org/10.3390/rs16020390 - 18 Jan 2024
Cited by 1 | Viewed by 1217
Abstract
Land-cover mapping plays a crucial role in resource detection, ecological environmental protection, and sustainable development planning. The existing large-scale land-cover products with coarse spatial resolution have a wide range of categories, but they suffer from low mapping accuracy. Conversely, land-cover products with fine [...] Read more.
Land-cover mapping plays a crucial role in resource detection, ecological environmental protection, and sustainable development planning. The existing large-scale land-cover products with coarse spatial resolution have a wide range of categories, but they suffer from low mapping accuracy. Conversely, land-cover products with fine spatial resolution tend to lack diversity in the types of land cover they encompass. Currently, there is a lack of large-scale land-cover products simultaneously possessing fine-grained classifications and high accuracy. Therefore, we propose a mapping framework for fine-grained land-cover classification. Firstly, we propose an iterative method for developing fine-grained classification systems, establishing a classification system suitable for Sentinel-2 data based on the target area. This system comprises 23 fine-grained land-cover types and achieves the most stable mapping results. Secondly, to address the challenges in large-scale scenes, such as varying scales of target features, imbalanced sample quantities, and the weak connectivity of slender features, we propose an improved network based on Swin-UNet. This network incorporates a pyramid pooling module and a weighted combination loss function based on class balance. Additionally, we independently trained models for roads and water. Guided by the natural spatial relationships, we used a voting algorithm to integrate predictions from these independent models with the full classification model. Based on this framework, we created the 2017 Beijing–Tianjin–Hebei regional fine-grained land-cover product JJJLC-10. Through validation using 4254 sample datasets, the results indicate that JJJLC-10 achieves an overall accuracy of 80.3% in the I-level validation system (covering seven land-cover types) and 72.2% in the II-level validation system (covering 23 land-cover types), with kappa coefficients of 0.7602 and 0.706, respectively. In comparison with widely used land-cover products, JJJLC-10 excels in accurately depicting the spatial distribution of various land-cover types and exhibits significant advantages in terms of classification quantity and accuracy. Full article
(This article belongs to the Special Issue Deep Learning for Spectral-Spatial Hyperspectral Image Classification)
►▼ Show Figures

Graphical abstract

30 pages, 4719 KiB  
Article
Training Methods of Multi-Label Prediction Classifiers for Hyperspectral Remote Sensing Images
by Salma Haidar and José Oramas
Remote Sens. 2023, 15(24), 5656; https://doi.org/10.3390/rs15245656 - 7 Dec 2023
Cited by 1 | Viewed by 1389
Abstract
Hyperspectral remote sensing images, with their amalgamation of spectral richness and geometric precision, encapsulate intricate, non-linear information that poses significant challenges to traditional machine learning methodologies. Deep learning techniques, recognised for their superior representation learning capabilities, exhibit enhanced proficiency in managing such intricate [...] Read more.
Hyperspectral remote sensing images, with their amalgamation of spectral richness and geometric precision, encapsulate intricate, non-linear information that poses significant challenges to traditional machine learning methodologies. Deep learning techniques, recognised for their superior representation learning capabilities, exhibit enhanced proficiency in managing such intricate data. In this study, we introduce a novel approach in hyperspectral image analysis focusing on multi-label, patch-level classification, as opposed to applications in the literature concentrating predominantly on single-label, pixel-level classification for hyperspectral remote sensing images. The proposed model comprises a two-component deep learning network and employs patches of hyperspectral remote sensing scenes with reduced spatial dimensions yet with a complete spectral depth derived from the original scene. Additionally, this work explores three distinct training schemes for our network: Iterative, Joint, and Cascade. Empirical evidence suggests the Joint approach as the optimal strategy, but it requires an extensive search to ascertain the optimal weight combination of the loss constituents. The Iterative scheme facilitates feature sharing between the network components from the early phases of training and demonstrates superior performance with complex, multi-labelled data. Subsequent analysis reveals that models with varying architectures, when trained on patches derived and annotated per our proposed single-label sampling procedure, exhibit commendable performance. Full article
(This article belongs to the Special Issue Deep Learning for Spectral-Spatial Hyperspectral Image Classification)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-6
Back to TopTop