Authors:
Giona Matasci
1
;
Lorenzo Bruzzone
2
;
Michele Volpi
1
;
Devis Tuia
3
and
Mikhail Kanevski
1
Affiliations:
1
University of Lausanne, Switzerland
;
2
University of Trento, Italy
;
3
Ecole Polytechnique Fédérale de Lausanne, Switzerland
Keyword(s):
Satellite Imagery, Image Classification, Transfer Learning, Manifold Alignment, Kernel Methods.
Related
Ontology
Subjects/Areas/Topics:
Applications
;
Classification
;
Computer Vision, Visualization and Computer Graphics
;
Feature Selection and Extraction
;
Geometry and Modeling
;
Image-Based Modeling
;
Kernel Methods
;
Pattern Recognition
;
Software Engineering
;
Theory and Methods
Abstract:
In this contribution, we explore the feature extraction framework to ease the knowledge transfer in the thematic classification of multiple remotely sensed images. By projecting the images in a common feature space, the purpose is to statistically align a given target image to another source image of the same type for which we dispose of already collected ground truth. Therefore, a classifier trained on the source image can directly be applied on the target image. We analyze and compare the performance of classic feature extraction techniques and that of a dedicated method issued from the field of domain adaptation. We also test the influence of different setups of the problem, namely the application of histogram matching and the origin of the samples used to compute the projections. Experiments on multi- and hyper-spectral images reveal the benefits of the feature extraction step and highlight insightful properties of the different adopted strategies.