Deep Multi-Spectral Registration Using Invariant Descriptor Learning

In this paper, we introduce a novel deep-learning method to align cross-spectral images. Our approach relies on a learned descriptor which is invariant to different spectra. Multi-modal images of the same scene capture different signals and therefore their registration is challenging and it is not s...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Ofir, Nati, Silberstein, Shai, Levi, Hila, Rozenbaum, Dani, Keller, Yosi, Sharon Duvdevani Bar
Format Paper Journal Article
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 23.05.2018
Subjects
Algorithms
Computer Science - Computer Vision and Pattern Recognition
Image quality
Invariants
Registration
Spectra
Online AccessGet full text

Cover

More Information
Summary:In this paper, we introduce a novel deep-learning method to align cross-spectral images. Our approach relies on a learned descriptor which is invariant to different spectra. Multi-modal images of the same scene capture different signals and therefore their registration is challenging and it is not solved by classic approaches. To that end, we developed a feature-based approach that solves the visible (VIS) to Near-Infra-Red (NIR) registration problem. Our algorithm detects corners by Harris and matches them by a patch-metric learned on top of CIFAR-10 network descriptor. As our experiments demonstrate we achieve a high-quality alignment of cross-spectral images with a sub-pixel accuracy. Comparing to other existing methods, our approach is more accurate in the task of VIS to NIR registration.
ISSN:2331-8422
DOI:10.48550/arxiv.1801.05171