Premium
Robust Blind Image Fusion for Misaligned Hyperspectral Imaging Data
Author(s) -
Bungert Leon,
Ehrhardt Matthias J.,
Reisenhofer Rafael
Publication year - 2018
Publication title -
pamm
Language(s) - English
Resource type - Journals
ISSN - 1617-7061
DOI - 10.1002/pamm.201800033
Subject(s) - hyperspectral imaging , initialization , computer science , deconvolution , artificial intelligence , a priori and a posteriori , computer vision , image resolution , image (mathematics) , remote sensing , pattern recognition (psychology) , algorithm , geology , philosophy , epistemology , programming language
The low spatial resolution of hyperspectral imaging can be significantly improved by fusing the hyperspectral image with a high resolution photograph. In most practical cases, however, the exact alignment between the fused images is not known a priori. In this work, we study how including a blind deconvolution approach in the mathematical model can help resolve translational misalignments. In particular, we investigate the influence of different initialization strategies. The efficiency of the proposed model is validated by numerical experiments using both simulated and real remote sensing data.