Fast Software Image Stabilization with Color Registration - Robotics Institute Carnegie Mellon University

Fast Software Image Stabilization with Color Registration

C. Guestrin, Fabio Cozman, and Eric Krotkov
Conference Paper, Proceedings of (IROS) IEEE/RSJ International Conference on Intelligent Robots and Systems, Vol. 1, pp. 19 - 24, October, 1998

Abstract

We present the formulation and implementation of an image stabilization system capable of stabilizing video with very large displacements between frames. A coarse-to-fine technique is applied in resolution and in model spaces. The registration algorithm uses phase correlation to obtain an initial estimate for translation between images; then Levenberg-Marquardt method for nonlinear optimization is applied to refine the solution. Registration is performed in color space, using a subset of the pixels selected by a gradient-based sub-sampling criterion. This software implementation runs at 5 Hz on non-dedicated hardware (Silicon Graphics R10000 workstation).

BibTeX

@conference{Guestrin-1998-14784,
author = {C. Guestrin and Fabio Cozman and Eric Krotkov},
title = {Fast Software Image Stabilization with Color Registration},
booktitle = {Proceedings of (IROS) IEEE/RSJ International Conference on Intelligent Robots and Systems},
year = {1998},
month = {October},
volume = {1},
pages = {19 - 24},
}