Skip to main content

Robust Camera Location Estimation by Convex Programming

Author(s): Ozyosil, Onur; Singer, Amit

To refer to this page use:
Abstract: 3D structure recovery from a collection of 2D images requires the estimation of the camera locations and orientations, i.e. the camera motion. For large, irregular collections of images, existing methods for the location estimation part, which can be formulated as the inverse problem of estimating n locations t(2),t(2,) . . . ,t(n) in R-3 from noisy measurements of a subset of the pairwise directions t(i) t(j)/parallel to t(i)-t(j)parallel to, are sensitive to outliers in direction measurements. In this paper, we firstly provide a complete characterization of well posed instances of the location estimation problem, by presenting its relation to the existing theory of parallel rigidity. For robust estimation of camera locations, we introduce a two-step approach, comprised of a pairwise direction estimation method robust to outliers in point correspondences between image pairs, and a convex program to maintain robustness to outlier directions. In the presence of partially corrupted measurements, we empirically demonstrate that our convex formulation can even recover the locations exactly. Lastly, we demonstrate the utility of our formulations through experiments on Internet photo collections.
Publication Date: 2015
Electronic Publication Date: 15-Oct-2015
Citation: Ozyosil, Onur, Singer, Amit. (2015). Robust Camera Location Estimation by Convex Programming. 2015 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2674 - 2683
ISSN: 1063-6919
Pages: 2674 - 2683
Type of Material: Conference Article
Version: Author's manuscript

Items in OAR@Princeton are protected by copyright, with all rights reserved, unless otherwise indicated.