Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
7.9
5.0
Journals
Remote Sensing
Special Issues
Deep Neural Networks for Hyperspectral Remote Sensing Image Processing
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

Special Issue "Deep Neural Networks for Hyperspectral Remote Sensing Image Processing"

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

Deadline for manuscript submissions: 31 December 2023 | Viewed by 2052

Special Issue Editors

Dr. Yulei Wang

E-Mail Website
Guest Editor
Center for Hyperspectral Imaging in Remote Sensing (CHIRS), Information and Technology College Dalian Maritime University, Dalian, China
Interests: hyperspectral image processing; multi-source remote sensing image fusion; artificial intelligence
Special Issues, Collections and Topics in MDPI journals
Prof. Dr. Meiping Song

E-Mail Website
Guest Editor
Center for Hyperspectral Imaging in Remote Sensing (CHIRS), Information Science and Technology College, Dalian Maritime University, Dalian 116026, China
Interests: hyperspectral image processing; artificial intelligence; remote sensing
Special Issues, Collections and Topics in MDPI journals
Dr. Enyu Zhao
E-Mail Website
Guest Editor
Center for Hyperspectral Imaging in Remote Sensing (CHIRS), Information Science and Technology College, Dalian Maritime University, Dalian 116026, China
Interests: thermal infrared; hyperspectral; quantitative remote sensing
Dr. Weiying Xie

E-Mail Website
Guest Editor
State Key Laboratory of Integrated Services Networks, Xidian University, Xi’an 710071, China
Interests: hyperspectral anomaly detection; network compression; efficient distributed learning
Special Issues, Collections and Topics in MDPI journals
Dr. Chunyan Yu
E-Mail Website
Guest Editor
Center for Hyperspectral Imaging in Remote Sensing (CHIRS), Information Science and Technology College, Dalian Maritime University, Dalian 116026, China
Interests: remote sensing image processing
Special Issues, Collections and Topics in MDPI journals
Prof. Dr. Caixia Gao
E-Mail Website
Guest Editor
Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China
Interests: thermal infrared; hyperspectral; quantitative remote sensing
Prof. Silvia Liberata Ullo

E-Mail Website
Guest Editor
Department of Engineering (DING), University of Sannio, Benevento, Italy
Interests: signal processing; data and image analysis; satellite remote sensing; sensor networks; machine learning applied to satellite images
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

A hyperspectral image (HSI) is a three-dimensional cube containing rich spatial and spectral information with hundreds of narrow and contiguous wavebands generated by an imaging spectrometer. Each pixel in hyperspectral remote sensing images corresponds to a nearly continuous spectral curve, which can reflect substances’ diagnostic spectral absorption differences and provide rich spectral information for an accurate extraction of ground object information. Thanks to its high spectral resolution, hyperspectral images have received reasonable attention and have essential applications in military and civil fields. In recent years, with the continuous improvement of the hyperspectral data acquisition capability of satellites and aerial platforms, hyperspectral image processing has also developed towards big data-driven feature information extraction. However, processing the massive data collected by these platforms using traditional image analysis methodologies is impractical and ineffective. This calls for the adoption of powerful techniques that can extract reliable and useful information, where deep neural networks have been gradually applied in HSI processing due to the strong generalization and deep extraction properties of advanced semantic features.

This Special Issue aims to explore features that truly benefit hyperspectral remote sensing interpretation tasks and provides a forum for many individuals working in deep-learning-based hyperspectral image processing to report their research findings and share their experiences with the HSI community. All contributions to deep neural networks for hyperspectral remote sensing image processing are welcome to this Special Issue. Topics of interest include, but are not limited to, the following:

  • Deep neural networks for target detection, band selection, and classification in hyperspectral images.
  • Deep learning for surface parameters retrieval from thermal infrared images.
  • Deep feature extraction for multi-source remote sensing images.
  • The hybrid architecture of CNN and transformer for hyperspectral applications.
  • Feature fusion and learning for hyperspectral image processing.
  • Light-weight design of deep models.
  • Review/surveys of recent applications and techniques of hyperspectral images.

Dr. Yulei Wang
Prof. Dr. Meiping Song
Dr. Enyu Zhao
Dr. Weiying Xie
Dr. Chunyan Yu
Prof. Dr. Caixia Gao
Prof. Dr. Silvia Liberata Ullo
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 neural networks
  • deep feature extraction
  • light weighed model
  • hyperspectral remote sensing images
  • thermal infrared
  • quantitative remote sensing
  • multi-sensor and multi-platform analysis
  • remote sensing applications

Published Papers (4 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

Jump to: Other

27 pages, 7141 KiB  
Article
TransHSI: A Hybrid CNN-Transformer Method for Disjoint Sample-Based Hyperspectral Image Classification
by
Ping Zhang
,
Haiyang Yu
,
Pengao Li
and
Ruili Wang
Remote Sens. 2023, 15(22), 5331; https://doi.org/10.3390/rs15225331 - 12 Nov 2023
Viewed by 571
Abstract
Hyperspectral images’ (HSIs) classification research has seen significant progress with the use of convolutional neural networks (CNNs) and Transformer blocks. However, these studies primarily incorporated Transformer blocks at the end of their network architectures. Due to significant differences between the spectral and spatial [...] Read more.
Hyperspectral images’ (HSIs) classification research has seen significant progress with the use of convolutional neural networks (CNNs) and Transformer blocks. However, these studies primarily incorporated Transformer blocks at the end of their network architectures. Due to significant differences between the spectral and spatial features in HSIs, the extraction of both global and local spectral–spatial features remains incomplete. To address this challenge, this paper introduces a novel method called TransHSI. This method incorporates a new spectral–spatial feature extraction module that leverages 3D CNNs to fuse Transformer to extract the local and global spectral features of HSIs, then combining 2D CNNs and Transformer to capture the local and global spatial features of HSIs comprehensively. Furthermore, a fusion module is proposed, which not only integrates the learned shallow and deep features of HSIs but also applies a semantic tokenizer to transform the fused features, enhancing the discriminative power of the features. This paper conducts experiments on three public datasets: Indian Pines, Pavia University, and Data Fusion Contest 2018. The training and test sets are selected based on a disjoint sampling strategy. We perform a comparative analysis with 11 traditional and advanced HSI classification algorithms. The experimental results demonstrate that the proposed method, TransHSI algorithm, achieves the highest overall accuracies and kappa coefficients, indicating a competitive performance. Full article
(This article belongs to the Special Issue Deep Neural Networks for Hyperspectral Remote Sensing Image Processing)
►▼ Show Figures

Graphical abstract

17 pages, 6875 KiB  
Article
Invariant Attribute-Driven Binary Bi-Branch Classification of Hyperspectral and LiDAR Images
by
Jiaqing Zhang
,
Jie Lei
,
Weiying Xie
and
Daixun Li
Remote Sens. 2023, 15(17), 4255; https://doi.org/10.3390/rs15174255 - 30 Aug 2023
Viewed by 423
Abstract
The fusion of hyperspectral and LiDAR images plays a crucial role in remote sensing by capturing spatial relationships and modeling semantic information for accurate classification and recognition. However, existing methods, such as Graph Convolutional Networks (GCNs), face challenges in constructing effective graph structures [...] Read more.
The fusion of hyperspectral and LiDAR images plays a crucial role in remote sensing by capturing spatial relationships and modeling semantic information for accurate classification and recognition. However, existing methods, such as Graph Convolutional Networks (GCNs), face challenges in constructing effective graph structures due to variations in local semantic information and limited receptiveness to large-scale contextual structures. To overcome these limitations, we propose an Invariant Attribute-driven Binary Bi-branch Classification (IABC) method, which is a unified network that combines a binary Convolutional Neural Network (CNN) and a GCN with invariant attributes. Our approach utilizes a joint detection framework that can simultaneously learn features from small-scale regular regions and large-scale irregular regions, resulting in an enhanced structural representation of HSI and LiDAR images in the spectral–spatial domain. This approach not only improves the accuracy of classification and recognition but also reduces storage requirements and enables real-time decision making, which is crucial for effectively processing large-scale remote sensing data. Extensive experiments demonstrate the superior performance of our proposed method in hyperspectral image analysis tasks. The combination of CNNs and GCNs allows for the accurate modeling of spatial relationships and effective construction of graph structures. Furthermore, the integration of binary quantization enhances computational efficiency, enabling the real-time processing of large-scale data. Therefore, our approach presents a promising opportunity for advancing remote sensing applications using deep learning techniques. Full article
(This article belongs to the Special Issue Deep Neural Networks for Hyperspectral Remote Sensing Image Processing)
►▼ Show Figures

Figure 1

Other

Jump to: Research

15 pages, 10968 KiB  
Technical Note
RANet: Relationship Attention for Hyperspectral Anomaly Detection
by
Yingzhao Shao
,
Yunsong Li
,
Li Li
,
Yuanle Wang
,
Yuchen Yang
,
Yueli Ding
,
Mingming Zhang
,
Yang Liu
and
Xiangqiang Gao
Remote Sens. 2023, 15(23), 5570; https://doi.org/10.3390/rs15235570 - 30 Nov 2023
Viewed by 219
Abstract
Hyperspectral anomaly detection (HAD) is of great interest for unknown exploration. Existing methods only focus on local similarity, which may show limitations in detection performance. To cope with this problem, we propose a relationship attention-guided unsupervised learning with convolutional autoencoders (CAEs) for HAD, [...] Read more.
Hyperspectral anomaly detection (HAD) is of great interest for unknown exploration. Existing methods only focus on local similarity, which may show limitations in detection performance. To cope with this problem, we propose a relationship attention-guided unsupervised learning with convolutional autoencoders (CAEs) for HAD, called RANet. First, instead of only focusing on the local similarity, RANet, for the first time, pays attention to topological similarity by leveraging the graph attention network (GAT) to capture deep topological relationships embedded in a customized incidence matrix from absolutely unlabeled data mixed with anomalies. Notably, the attention intensity of GAT is self-adaptively controlled by adjacency reconstruction ability, which can effectively reduce human intervention. Next, we adopt an unsupervised CAE to jointly learn with the topological relationship attention to achieve satisfactory model performance. Finally, on the basis of background reconstruction, we detect anomalies by the reconstruction error. Extensive experiments on hyperspectral images (HSIs) demonstrate that our proposed RANet outperforms existing fully unsupervised methods. Full article
(This article belongs to the Special Issue Deep Neural Networks for Hyperspectral Remote Sensing Image Processing)
►▼ Show Figures

Figure 1

13 pages, 15032 KiB  
Technical Note
Retrieval of Land Surface Temperature over Mountainous Areas Using Fengyun-3D MERSI-II Data
by
Yixuan Xue
,
Xiaolin Zhu
,
Zihao Wu
and
Si-Bo Duan
Remote Sens. 2023, 15(23), 5465; https://doi.org/10.3390/rs15235465 - 23 Nov 2023
Viewed by 405
Abstract
Land surface temperature (LST) is an important physical quantity in the energy exchange of hydrothermal cycles between the land and near-surface atmosphere at regional and global scales. However, the traditional thermal infrared transfer equation (RTE) and LST retrieval algorithms are always based on [...] Read more.
Land surface temperature (LST) is an important physical quantity in the energy exchange of hydrothermal cycles between the land and near-surface atmosphere at regional and global scales. However, the traditional thermal infrared transfer equation (RTE) and LST retrieval algorithms are always based on the underlying assumptions of homogeneity and isotropy, which ignore the terrain effect influence of a heterogeneous topography. It can cause significant errors when traditional RTE and other algorithms are used to retrieve LST in such mountainous research. In this study, the mountainous thermal infrared transfer model considering terrain effect correction is used to retrieve the mountainous LST using FY-3D MERSI-II data, and the in situ site data are simultaneously utilized to evaluate the performance of the iterative single-channel algorithm. The elevation of this study region ranges from 500 m to 2200 m, whereas the minimum SVF can reach 0.75. Results show that the spatial distribution of the retrieved LST is similar to topographic features, and the LST has larger values in the lower valley and smaller values in the higher ridge. In addition, the overall bias and RMSE between the retrieved LSTs and five in situ stations are respectively −0.70 K and 2.64 K, which demonstrates this iterative single-channel algorithm performs well in taking into account the terrain effect influence. Accuracy of the LST estimation is meaningful for mountainous ecological environmental monitoring and global climate research. Such an adjacent terrain effect correction should be considered in future research on complex terrains, especially with high spatial resolution TIR data. Full article
(This article belongs to the Special Issue Deep Neural Networks for Hyperspectral Remote Sensing Image Processing)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-4
Back to TopTop