Feature Selection from SAR Images for Terrain Surface Classification
A special issue of Remote Sensing (ISSN 2072-4292). This special issue belongs to the section "Remote Sensing Image Processing".
Deadline for manuscript submissions: closed (15 December 2023) | Viewed by 613
Special Issue Editors
Interests: signal and image processing; pattern recognition; remote sensing; information fusion
Special Issues, Collections and Topics in MDPI journals
Interests: registration; fusion; detection; classification; change detection; tracking
Interests: remote sensing; multispectral/hyperspectral imaging; imaging spectroscopy; optical/SAR sensors; image processing; geology; lithological and mineral mapping; terrestrial surface mapping
Special Issues, Collections and Topics in MDPI journals
Special Issue Information
Dear Colleagues,
This Special Issue aims to attract papers with new results on features suitable for classifying terrain surfaces.
The data to be used will be mainly from single, dual or fully polarimetric SAR scenes of Level 0, Level 1 or Level 2 preprocessed SAR components. However, other kinds of satellite imagery can be employed in a complementary way in order to construct features for terrain classification. In this sense, data other than SAR will be employed to qualify the SAR data or improve their information by means of fusion techniques.
The proposed features should appear as the results of mathematical processes carried out on the original data. Such processes could be target decomposition techniques, scattering properties, first-order (or 1-D) statistics, higher-order statistics (texture, co-occurrence approaches between the same band or different bands), geometric, fusion of existing features etc.
The combination of existing features which are incorporated in well-established feature-extraction techniques is not acceptable, except if the authors describe completely in a mathematical framework the existing features and the way in which they are combined (fused). In this case, a complete mathematical background is required. Combinations of existing features explained only by means of block diagrams cannot provide solid mathematical evidence, and thus are not acceptable for this Special Issue.
The terrain classification performance of the proposed features should be compared with existing approaches in three aspects:
- The number of different terrain types they are able to discriminate;
- The degree (percent) of successful classification as a weighted average for all types of terrain;
- The flexibility of the proposed features to adapt easily to different sets of SAR data.
Prof. Dr. Vassilis Anastassopoulos
Dr. George Lampropoulos
Dr. Olga Sykioti
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
- SAR imagery
- feature extraction
- terrain classification
- scattering properties
- statistical properties
- fusion approaches
- classification performance
