Authors: Aguiar, Pedro
Xavier, João
Stošić, Marko 
Title: Globally optimal solution to exploit rigidity when recovering structure from motion under occlusion
Journal: Proceedings - International Conference on Image Processing, ICIP
First page: 197
Last page: 200
Conference: IEEE International Conference on Image Processing, ICIP 2008; San Diego, CA; United States; 12 October 2008 through 15 October 2008
Issue Date: 1-Dec-2008
ISBN: 978-1-424-41764-3
ISSN: 1522-4880
DOI: 10.1109/ICIP.2008.4711725
Widely used SVD-based matrix factorization approaches to the recovery of 3D rigid structure from motion (SFM), require a set of feature points to be visible in a set of images. When there is occlusion, several feature points disappear, the observation matrix misses some entries, there is not equivalent to the SVD, and only suboptimal solutions have been proposed to exploit rigidity. In this paper, we propose a method to complete the trajectories that correspond to a rigid scene, in an optimal way. Our algorithm is not iterative (thus avoiding problems like sensitivity to initialization and local optima); it rather computes in a finite number of steps the globally optimal completion of the observation matrix. We describe experiments that illustrate the gain in accuracy of SFM.
Keywords: Global optimization | Matrix completion | Missing data | Occlusion | SPOC | Structure from motion
Publisher: IEEE

Show full item record


checked on Jul 22, 2024

Page view(s)

checked on May 9, 2024

Google ScholarTM




Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.