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.
|Publication status||Published - Sep 2011|
|Event||ICIP 2011: IEEE International Conference on Image Processing - Brussels|
Duration: 11 Sep 2011 → 14 Sep 2011
|Conference||ICIP 2011: IEEE International Conference on Image Processing|
|Period||11/09/11 → 14/09/11|
Firmenich, D., Brown, M., & Susstrunk, S. (2011). Multispectral Interest Points for RGN-NIR Image Registration. Paper presented at ICIP 2011: IEEE International Conference on Image Processing, Brussels, .