Advanced Hyperspectral Imaging: Techniques, Data Analysis, and Applications

A special issue of Journal of Imaging (ISSN 2313-433X). This special issue belongs to the section "Color, Multi-spectral, and Hyperspectral Imaging".

Deadline for manuscript submissions: 31 July 2025 | Viewed by 368

Special Issue Editor

Centre for Electronic Warfare, Information and Cyber, Defence Academy of the United Kingdom, Cranfield University, Shrivenham SN6 8LA, UK
Interests: hyperspectral imaging; remote sensing; machine vision; computer vision; statistical machine learning; artificial intelligence

Special Issue Information

Dear Colleagues,

Hyperspectral imaging (HSI) technology has been one of the most effective techniques for the identification of targets from heavily cluttered backgrounds across industrial, agricultural, environmental monitoring, and defence/military sectors. Like other technologies, cutting-edge HSI research has evolved into using deep learning (DL) and artificial intelligence (AI) for enhancing imaging hardware, particularly its snap-shot multispectral form, and hyperspectral imagers; it is also used for data analysis to detect subpixel targets that are embedded in scenes with complicated geographical, vegetation, and textual-rich backgrounds. While conventional techniques such as compressive sensing, data integrity enhancements using multivariate analysis, and target detections through likelihood approaches have been very successful for many practical applications, AI-based methods and their combination with conventional model-based methodologies have emerged, being increasingly successful from the perspective of target detection.

This Special Issue addresses the use of DL and AI for solving real world problems, particularly for long range target detections with a high degree of universality; articles and reviews on this subject are highly welcome. Particular interests include, but are not limited to, the following: multiplex image-acquisition techniques, super-resolutions, supervised or unsupervised target detections, transfer learning, band selections, network optimizations, and self-organized DL. Direct comparisons of the effectiveness of AI versus conventional model-based methodologies are also highly sought.

Dr. Peter Yuen
Guest Editor

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. Journal of Imaging is an international peer-reviewed open access monthly 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 1800 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • hyperspectral imaging
  • remote sensing
  • deep learning
  • artificial intelligence
  • multiplex image-acquisition techniques
  • super-resolutions
  • supervised or unsupervised target detection
  • band selections

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.
  • Reprint: MDPI Books provides the opportunity to republish successful Special Issues in book format, both online and in print.

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

Published Papers (1 paper)

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

Research

26 pages, 3942 KiB  
Article
Unleashing the Potential of Residual and Dual-Stream Transformers for the Remote Sensing Image Analysis
by Priya Mittal, Vishesh Tanwar, Bhisham Sharma and Dhirendra Prasad Yadav
J. Imaging 2025, 11(5), 156; https://doi.org/10.3390/jimaging11050156 - 15 May 2025
Viewed by 176
Abstract
The categorization of remote sensing satellite imagery is crucial for various applications, including environmental monitoring, urban planning, and disaster management. Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) have exhibited exceptional performance among deep learning techniques, excelling in feature extraction and representational learning. [...] Read more.
The categorization of remote sensing satellite imagery is crucial for various applications, including environmental monitoring, urban planning, and disaster management. Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) have exhibited exceptional performance among deep learning techniques, excelling in feature extraction and representational learning. This paper presents a hybrid dual-stream ResV2ViT model that combines the advantages of ResNet50 V2 and Vision Transformer (ViT) architectures. The dual-stream approach allows the model to extract both local spatial features and global contextual information by processing data through two complementary pathways. The ResNet50V2 component is utilized for hierarchical feature extraction and captures short-range dependencies, whereas the ViT module efficiently models long-range dependencies and global contextual information. After position embedding in the hybrid model, the tokens are bifurcated into two parts: q1 and q2. q1 is passed into the convolutional block to refine local spatial details, and q2 is given to the Transformer to provide global attention to the spatial feature. Combining these two architectures allows the model to acquire low-level and high-level feature representations, improving classification performance. We assess the proposed ResV2ViT model using the RSI-CB256 dataset and another dataset with 21 classes. The proposed model attains an average accuracy of 99.91%, with precision and F1 score of 99.90% for the first dataset and 98.75% accuracy for the second dataset, illustrating its efficacy in satellite image classification. The findings demonstrate that the dual-stream hybrid ResV2ViT model surpasses traditional CNN and Transformer-based models, establishing it as a formidable framework for remote sensing applications. Full article
Show Figures

Figure 1

Back to TopTop