High-Spectral Resolution Images for Cultural Heritage and Critical Infrastructure Assessment

Dear Colleagues,

Typically, high-spectral resolution images that have been captured by satellite or aircraft-based sensors are used to remotely observe, monitor, and evaluate the condition of areas across the globe for applications ranging from geography and land surveying to urban planning. Advances, however, in hyperspectral and multispectral sensing have enabled the acquisition of high-spectral resolution images using hand-held sensors. Although high-spectral resolution images can provide very precise information for a depicted scene, no special attention has been paid to the exploitation of this kind of data for applications beyond earth observation, such as cultural heritage asset inspection and documentation, critical infrastructure assessment, civil engineering, and disaster management.   

Exploiting hyperspectral and multispectral imagery in applications such as those mentioned above poses several challenges that mainly stem from the high dimensionality of high-spectral resolution images. For example, the above applications require high-dimensional data processing in real or pseudo-real-time. On top of that, most of the everyday applications that employ hyperspectral or multispectral images can be characterized as small-sample setting problems, where the number of annotated data are limited, compromising the statistical properties of the developed solutions. The present Special Issue aims to serve a collection of high-quality state-of-the-art approaches for processing hyperspectral and multispectral data in beyond earth observation applications, including theoretical studies focusing on the development of efficient novel techniques for processing such data and application-oriented studies.

Topics for this Special Issue include but are not limited to:

• Novel tensor-based and deep supervised learning models for tackling small-sample setting problems employing hyperspectral and multispectral imagery.
• Unsupervised and self-supervised learning techniques tailored for high-dimensional hyperspectral and multispectral data.
• Explainable machine learning-based approaches for decision making using high-spectral resolution data.
• Methodologies based on established state-of-the-art tensor and deep learning models for
  • cultural heritage applications;
  • critical infrastructure assessment (tunnels, power plants, etc.);
  • civil engineering (e.g., safe urban development);
  • disaster management.
• New databases to benchmark hyperspectral and multispectral processing algorithms targeting the abovementioned applications.

Dr. Konstantinos Makantasis
Dr. Eftychios Protopapadakis 
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.

• hyper-/multi-spectral image processing
• representation learning from high-spectral images
• cultural heritage inspection
• critical infrastructure assessment
• supervised learning
• un-/self-supervised learning