• On Importance of Off-Diagonal Elements in the Polarimetric Covariance Matrix: A Sea Ice Application Perspective 

      Ratha, Debanshu; Doulgeris, Anthony Paul; Marinoni, Andrea; Eltoft, Torbjørn (Conference object; Konferansebidrag, 2023-06)
    • On Measures of Uncertainty in Classification 

      Chlaily, Saloua; Ratha, Debanshu; Lozou, Pigi; Marinoni, Andrea (Journal article; Tidsskriftartikkel; Peer reviewed, 2023-10-12)
      Uncertainty is unavoidable in classification tasks and might originate from data (e.g., due to noise or wrong labeling), or the model (e.g., due to erroneous assumptions, etc). Providing an assessment of uncertainty associated with each outcome is of paramount importance in assessing the reliability of classification algorithms, especially on unseen data. In this work, we propose two measures of ...
    • Performance Analysis of Roll-Invariant PolSAR Parameters from C-band images with Regard to Sea Ice Type Separation 

      Ratha, Debanshu; Johansson, Malin; Marinoni, Andrea; Eltoft, Torbjørn (Journal article; Tidsskriftartikkel; Peer reviewed, 2022-06)
      The Polarimetric Synthetic Aperture Radar (PolSAR) backscatter from a target is dependent on the incidence angle. Consequently, the associated roll invariant parameters are affected by changes in incidence angle. In this work, we identify a few of these parameters that remain robust in identifying sea ice features even under large incidence angle variations. We conclude that the helicity angle ...