Multispectral interest points for RGB-NIR image registration

This paper explores the use of joint colour and near-infrared (NIR) information for feature based matching and image registration. In particular, we investigate multispectral generalisations of two popular interest point detectors (Harris and difference of Gaussians), and show that these give a mark...

Full description

Saved in:
Bibliographic Details
Published in2011 18th IEEE International Conference on Image Processing pp. 181 - 184
Main Authors Firmenichy, D., Brown, M., Susstrunk, S.
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.09.2011
Subjects
Computer vision
Conferences
Detectors
Image color analysis
Image Registration
Interest points
Joints
Laplace equations
Near Infrared
Online AccessGet full text

Cover

More Information
Summary:This paper explores the use of joint colour and near-infrared (NIR) information for feature based matching and image registration. In particular, we investigate multispectral generalisations of two popular interest point detectors (Harris and difference of Gaussians), and show that these give a marked improvement in performance when the extra NIR channel is available. We also look at the problem of multimodal RGB to NIR registration, and propose a variant of the SIFT descriptor that gives improved performance.
ISBN:1457713047
9781457713040
ISSN:1522-4880
DOI:10.1109/ICIP.2011.6115818