Statistical assessment of dataset shift and model portability in multi-angle in-track image acquisitions

Détails

ID Serval
serval:BIB_C4227B5722E7
Type
Actes de conférence (partie): contribution originale à la littérature scientifique, publiée à l'occasion de conférences scientifiques, dans un ouvrage de compte-rendu (proceedings), ou dans l'édition spéciale d'un journal reconnu (conference proceedings).
Collection
Publications
Titre
Statistical assessment of dataset shift and model portability in multi-angle in-track image acquisitions
Titre de la conférence
Geoscience and Remote Sensing Symposium (IGARSS), 2013 IEEE International
Auteur(s)
Matasci G., Longbotham N., Pacifici F., Kanevski M., Tuia D.
Adresse
Melbourne, Australia
ISSN-L
2153-6996
Statut éditorial
Publié
Date de publication
2013
Pages
4134 - 4137
Langue
anglais
Résumé
In this study we propose an evaluation of the angular effects altering the spectral response of the land-cover over multi-angle remote sensing image acquisitions. The shift in the statistical distribution of the pixels observed in an in-track sequence of WorldView-2 images is analyzed by means of a kernel-based measure of distance between probability distributions. Afterwards, the portability of supervised classifiers across the sequence is investigated by looking at the evolution of the classification accuracy with respect to the changing observation angle. In this context, the efficiency of various physically and statistically based preprocessing methods in obtaining angle-invariant data spaces is compared and possible synergies are discussed.
Création de la notice
19/09/2013 10:59
Dernière modification de la notice
03/03/2018 21:13
Données d'usage