Image Processing and Analysis: Trends in Registration, Data Fusion, 3D Reconstruction, and Change Detection (Third Edition)

Dear Colleagues,

Satellite, aerial, UAV, and terrestrial imaging techniques are constantly evolving, both in terms of data volumes, quality, and variety. Earth observation programs, both public and private, are making available a growing amount of multi-temporal data, often publicly accessible, at an increased spatial resolution with a high revisit time. At the opposite end of the platform scale, UAVs, due to their higher flexibility, represent a new paradigm for acquiring high-resolution information at high frequencies. Similarly, consumer-grade 360° cameras and hyperspectral sensors are becoming more widespread on different terrestrial platforms and applications.

Remotely sensed data can provide the basis for timely and efficient analysis in several fields, such as land usage and environmental monitoring, cultural heritage, archaeology, precision farming, human activity monitoring, and others engaging research and practical fields of interest. Its availability, the increasing need for fast and reliable responses, and the increase in the number of active (but often unskilled) users all pose new relevant challenges in research fields connected to data registration, data fusion, 3D reconstruction, and change detection. In such a context, automated and reliable techniques are needed to process and extract information from such a large amount of data.

This Special Issue is the third edition on these subjects (the first edition is available at https://www.mdpi.com/journal/remotesensing/special_issues/rs_image_trends, and the second edition is available at https://www.mdpi.com/journal/remotesensing/special_issues/rs_image_trends_II) and aims to present the latest advances in innovative image analysis and image processing techniques and their contribution in a wide range of application fields in an attempt to foresee where they will lead the discipline and practice in the next few years. As far as process automation is concerned, it is of the utmost importance to invest in an appropriate understanding of the algorithmic implementation of the different techniques and identify their maturity as well as possible applications where their use might leverage their full potential. For this reason, special focusing features might be (i) accuracy: the agreement between the reference (check) and measured data (e.g., accuracy of check point in image orientation or accuracy of testing set in data classification); (ii) completeness: the amount of information obtained from the different methodologies and their space/time distribution; (iii) reliability: the algorithm’s consistency, intended as stability to noise, and algorithm’s robustness, intended as estimation of the measurements’ reliability level and capability to identify gross errors; and (iv) processing speed: the algorithm’s computational load.

Scope includes, but is not limited to, the following:

• image registration and multi-source data integration or fusion methods;
• deep learning methods for data classification and pattern recognition;
• automation in thematic map production (e.g., spatial and temporal pattern analysis, change detection, and definition of specific change metrics);
• cross-calibration of sensors and cross-validation of data/models;
• orientation in a seamless way of images acquired with different platforms;
• object extraction and accuracy evaluation in 3D reconstruction, including volume rendering methods (e.g., NeRF and Gaussian Splatting);
• low-cost 360° and fisheye consumer-grade camera calibration, orientation, and 3D reconstruction;
• direct georeferencing of images acquired by different platforms.

Prof. Dr. Riccardo Roncella
Dr. Mattia Previtali
Dr. Luca Perfetti
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.

• image registration
• change detection
• 3D reconstruction
• deep learning
• hyperspectral
• image matching
• data/sensor fusion
• object-based image analysis
• pattern recognition
• volume rendering

• Image Processing and Analysis: Trends in Registration, Data Fusion, 3D Reconstruction, and Change Detection II in Remote Sensing (18 articles)
• Image Processing and Analysis: Trends in Registration, Data Fusion, 3D Reconstruction and Change Detection in Remote Sensing (18 articles)