Research output: Contribution to conference › Paper
Abstract
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.
title = "Multispectral Interest Points for RGN-NIR Image Registration",
abstract = "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.",
author = "D Firmenich and Matthew Brown and S Susstrunk",
year = "2011",
month = "9",
language = "English",
note = "ICIP 2011: IEEE International Conference on Image Processing ; Conference date: 11-09-2011 Through 14-09-2011",
}
TY - CONF
T1 - Multispectral Interest Points for RGN-NIR Image Registration
AU - Firmenich, D
AU - Brown, Matthew
AU - Susstrunk, S
PY - 2011/9
Y1 - 2011/9
N2 - 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.
AB - 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.