This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
Regularizing optical-flow computation using tensor theory and complex analysis
Anchorage, AK, USA
June 23-June 28
ISBN: 978-1-4244-2339-2
Dan Koppel, Department of Computer Science, University of California, Santa Barbara, USA
Chang-Ming Tsai, Department of Computer Science, University of California, Santa Barbara, USA
Yuan-Fang Wang, Department of Computer Science, University of California, Santa Barbara, USA
This paper reports a technique that improves the robustness and accuracy in computing dense optical-flow fields. We propose a global formulation with a regularization term. The regularization expressions are derived based on tensor theory and complex analysis. It is shown that while many regularizers have been proposed (image-driven, flow-driven, homogeneous, inhomogeneous, isotropic, anisotropic), they are all variations of a single base expression ∇u∇uT + ∇v∇vT . These regularizers, strictly speaking, are valid for uniform 2D translational motion only, because what they do essentially is to penalize changes in a flow field. However, many flow patterns—such as rotation, zoom, and their combinations, induced by a 3D rigid-body motion.are not constant. The traditional regularizers then incorrectly penalize these legal flow patterns and result in biased estimates. The purpose of this work is then to derive a new suite of regularization expressions that treat all valid flow patterns resulting from a 3D rigid-body motion equally, without unfairly penalizing any of them.
Citation:
Dan Koppel, Chang-Ming Tsai, Yuan-Fang Wang, "Regularizing optical-flow computation using tensor theory and complex analysis," cvprw, pp.1-6, 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, 2008
Usage of this product signifies your acceptance of the Terms of Use.