Special Issue "Deep Learning for Remote Sensing"
Deadline for manuscript submissions: closed (30 November 2018).
Interests: image processing; remote sensing; digital multimedia forensics
Interests: remote sensing; image processing; deep learning; pansharpening; data fusion; image segmentation; despeckling
Interests: image processing, remote sensing, deep learning, image forensics
In the last few years, space agencies have deployed a large number of Earth observing satellites. End users are flooded with a huge quantity of images of diverse nature, e.g., optical vs. SAR, high-resolution vs. wide-coverage, mono- vs. multi-spectral, often in regular time series. Key towards their full exploitation are fully automated analysis methods, which calls for new tools to extract reliable and expressive information.
Deep learning holds great promise to fulfil the challenging needs of remote sensing (RS) image processing. It leverages the huge computing power of modern GPUs to perform human-like reasoning and extract compact features which embody the semantics of input images. The interest of the RS community towards deep learning methods is growing fast, and many architectures have been proposed in the last few years to address RS problems, often with an outstanding performance.
This Special Issue aims to report the latest advances and trends concerning the application of deep learning to remote sensing problems. Papers of both theoretical and applicative nature are welcome, as well as contributions regarding new deep learning-oriented public datasets for the RS research community.
Major topics of interest, by no means exclusive, are:
- Large-scale datasets for training and testing deep learning solutions to RS problems;
- Deep learning for RS image processing (e.g., compression, denoising, segmentation, classification)
- Deep learning for RS image understanding (e.g., semantic labeling, object detection, data mining, image retrieval)
- Deep learning for RS data fusion (e.g., optical-SAR fusion, pan-sharpening)
- Deep learning with scarce or low-quality RS data, transfer learning, cross-sensor learning
- Processing of RS time-series through deep recurrent networks
Dr. Giuseppe Scarpa
Dr. Luisa Verdoliva
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 papers will be 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 2200 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.
- remote sensing
- deep learning
- image processing
- large-scale datasets
- transfer learning