Deep Learning and Transformers’ Methods Applied to Remotely Captured Data

Dear Colleagues,

The areas of machine learning and deep learning have experienced impressive progress in recent years. This progress has mainly been driven by the availability of high processing performance at an affordable cost and a large quantity of data. Most state-of-the-art techniques today are based on deep neural networks or the more recently proposed transformers. This progress has sparked innovations in technologies, algorithms, and approaches and led to results that were unachievable until recently. Among the various research areas that have been significantly impacted by this progress is the processing of remotely captured data such as airborne and spaceborne passive and active imagery, underwater imagery, mobile mapping data, etc. This Topic aims to gather cutting-edge contributions from researchers using deep learning and transformers for remote sensing and for processing remotely captured data. Contributions are accepted in different areas of application, including but not limited to environmental studies, precision agriculture, forestry, disaster response, building information modeling, infrastructure inspection, defense and security, benchmarking, and open-access datasets for remote sensing. Studies using active or passive sensors from satellites, airborne platforms, drones, and underwater and terrestrial vehicles are welcome. Contributions can be submitted in various forms, such as research papers, review papers, datasets, and comparative analyses.

Prof. Dr. Moulay A. Akhloufi
Dr. Mozhdeh Shahbazi
Topic Editors