Region Based Classification (RBC), Object Based Image Analysis (OBIA) and Deep Learning (DL) for Remote Sensing Applications

Dear Colleagues,

The large amount of remote sensing (RS) data, of a variety of source types, spectral characteristics, spatial and time resolutions, as well a plethora of analysis algorithms, have opened up new perspectives in many application fields, but made the choosing of the best set of resources more difficult.

Region Based Classification (RBC) also known as Object-based Image Analysis (OBIA), for land cover mapping, has attracted substantial attention. Basically, RBC comprises three main steps, segmentation, feature extraction and classification, executed and configured separately. In this processing chain, segmentation is the critical step. Typically, it relies solely on the image data and ignores semantic, which is considered when the user non-automatically defines the parameter values of the segmentation algorithm. Deep Learning (DL) provide methods to jointly learn from raw input data, a series of features tailored for the task, as well as the optimum parameter values for the underlying classifier. However, DL based solutions, normally, do not rely on image segmentation and demand a huge amount of labeled training data not available in most RS applications. This Special Issue focuses on RBC steps for land use mapping under restricted availability of labeled training data, especially with DL methods. Alternatively, how to specify the segmentation parameters and features coupled with the configuration of standard classifiers (Random Forests, Support Vector Machines, Maximum Likelihood,  and others), for improving  RBC of Remote Sensing data.

Submissions may relate to the following scientific questions (but not limited to):

• How to specify the best segmentation parameters as function of the classifier to be used, and the set of classes of interest?
• How to design a system to resolve hard to separate land cover classes?
• How to use DL methods for Region Based Classification?
• How to take in account semantics in RBC?
• How to take in account source data characteristics, like SAR and hyperspectral and/or multi-temporal into RBC processes?

Dr. Luciano Vieira Dutra
Dr. Raul Queiroz Feitosa
Dr. Rogério Galante Negri
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 250 words) can be sent to the Editorial Office for assessment.

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.