21 March 2013 Linking local and global optical flow computation by subspace regularization
Yan Niu, Anthony Dick, Michael J. Brooks
Author Affiliations +
Abstract
Optical flow computation methods are traditionally classified to two categories: local and global. Several previous works have investigated the combination of them by exploiting their complementary effects. Unlike previous works, this paper is motivated by the common weakness of the two schemes and proposes linking local and global computation by subspace regularization. We will show that the subspace regularization can effectively reduce the error caused by ill-conditioned local computation systems, while inhibiting error diffusion suffered by the global regularization. Experimental results on benchmark sequences validate the enhanced performance of the proposed combination scheme.
© 2013 Society of Photo-Optical Instrumentation Engineers (SPIE) 0091-3286/2013/$25.00 © 2013 SPIE
Yan Niu, Anthony Dick, and Michael J. Brooks "Linking local and global optical flow computation by subspace regularization," Optical Engineering 52(3), 037205 (21 March 2013). https://doi.org/10.1117/1.OE.52.3.037205
Published: 21 March 2013
Lens.org Logo
CITATIONS
Cited by 4 scholarly publications.
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Optical flow

Computing systems

Motion models

Image segmentation

Optical engineering

Cameras

Clouds

Back to Top