|Title||Statistical assessment of dataset shift and model portability in multi-angle in-track image acquisitions|
|Author(s)||Matasci, Giona; Longbotham, Nathan; Pacifici, Fabio; Kanevski, Mikhail; Tuia, Devis|
|Source||In: 2013 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2013 - Proceedings. - - p. 4134 - 4137.|
|Event||2013 33rd IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2013, Melbourne, VIC, 2013-07-21/2013-07-26|
|Publication type||Contribution in proceedings|
|Keyword(s)||Domain adaptation - Image classification - Maximum mean discrepancy - Multi-angle acquisitions|
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.