Share Email Print

Proceedings Paper

Image registration under poor illumination using calibrated cameras
Author(s): Prakash Duraisamy; Stephen Craig Jackson; Mohammed S. Alam; Bill Buckles
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Image registration is basic step in image fusion and in many 2D applications. Registering the 2D image with recent robust algorithms like SIFT (Scale invariant Feature Transform) works well in most situations. However, registering the 2D images under poor illumination is a challenging problem. In several situations, conventional registration algorithms like SIFT fail to register the images. Aside from poor illumination conditions, images involving too much symmetry can also pose registration difficulties for conventional methods. In our approach, we overcome these limitations by using the knowledge of the intrinsic camera parameters together with a new registration method to help in registering the features (lines) between the two overlapping images. Our approach is useful especially in registering the images taken by different sensors or the same sensor at different times under poor illumination conditions. Experiments are tested on real world environments.

Paper Details

Date Published: 29 April 2013
PDF: 7 pages
Proc. SPIE 8748, Optical Pattern Recognition XXIV, 87480F (29 April 2013); doi: 10.1117/12.2016355
Show Author Affiliations
Prakash Duraisamy, Massachusetts Institute of Technology (United States)
Stephen Craig Jackson, Univ. of North Texas (United States)
Mohammed S. Alam, Univ. of South Alabama (United States)
Bill Buckles, Univ. of South Alabama (United States)

Published in SPIE Proceedings Vol. 8748:
Optical Pattern Recognition XXIV
David Casasent; Tien-Hsin Chao, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?