Latest Developments in Clustering Algorithms for Hyperspectral Images
A special issue of Remote Sensing (ISSN 2072-4292).
Deadline for manuscript submissions: closed (31 October 2021) | Viewed by 5343
Special Issue Editors
Interests: hyperspectral image analysis; applied mathematics; classification; clustering
Special Issue Information
Dear Colleagues,
Clustering is an essential data mining tool to help data scientists and end-users explore and interpret their data with little to no prior information (e.g., class labels, number of clusters). Remote sensing applications, particularly those based on hyperspectral imaging, involve data clusters in high-dimensional representation spaces with arbitrary shapes and possibly high imbalance. Furthermore, ground truth information is costly and not always reliable, which makes unsupervised learning approaches like clustering particularly attractive.
In the 2000’s, kernel-based and early density-based clustering approaches like DBSCAN, together with unsupervised dimensionality reduction methods, have provided some answers to the problem of hyperspectral data clustering. However, with the advent of artificial intelligence and deep clustering approaches about a decade ago, a new paradigm for hyperspectral pixel clustering has arisen and received an exponentially growing popularity. This paradigm has already shown outstanding capability and efficiency over classical approaches, at the cost of requiring much attention regarding hyper-parameterization. Selecting the right model, training methods, and objective functions to achieve efficiency, generalizability, and interpretability is still a largely unsolved problem. Other original clustering approaches have been proposed recently and successfully applied to hyperspectral images, such as collaborative clustering, possibilistic clustering, density peak clustering, which introduce new concepts and still constitute interesting alternatives − if not complementary − approaches to deep learning.
In this Special Issue, we wish to provide a comprehensive overview of the latest advances in the field of clustering for hyperspectral image analysis, and we invite researchers to present their latest findings, as well as review papers on this topic. Papers will be selected based on the quality and rigor of the research.
Dr. Claude Cariou
Dr. Steven Le Moan
Guest Editors
Manuscript Submission Information
Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.
Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Remote Sensing is an international peer-reviewed open access semimonthly journal published by MDPI.
Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2700 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.
Keywords
- Hyperspectral images
- Clustering
- Unsupervised Classification
- Deep Learning
- Spectral-spatial approaches
- Density-based approaches
- Online approaches
- Graph-based approaches
- Subspace clustering
- Bi-clustering
- Possibilistic clustering
- Convex clustering
- Collaborative clustering
- Ensemble clustering
- Sparse coding
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 policies can be found here.
