liu.seSearch for publications in DiVA
Change search
ReferencesLink to record
Permanent link

Direct link
Multiple Motion Estimation using Channel Matrices
Linköping University, The Institute of Technology. Linköping University, Department of Electrical Engineering, Computer Vision.ORCID iD: 0000-0002-5698-5983
RnD ContextVision AB.
2007 (English)In: International Workshop on Complex Motion IWCM,2004, LNCS 3417: Springer , 2007, 54- p.Conference paper (Refereed)
Abstract [en]

 The motion field from image sequences of a dynamic 3D scene is in general piecewise continuous. Since two neighbouring regions may have completely different motions, motion estimation at the discontinuities is problematic. In particular spatial averaging of motion vectors is inappropriate at such positions. We avoid this problem by channel encoding brightness change constraint equations (BCCE) for each spatial position into a channel matrix. By spatial averaging of this channel representation and subsequently decoding we are able to estimate all significantly different motions occurring at the discontinuity, as well as their covariances. This paper extends and improves this multiple motion estimation scheme by locally selecting the appropriate scale for the spatial averaging.  

Place, publisher, year, edition, pages
LNCS 3417: Springer , 2007. 54- p.
National Category
Engineering and Technology
URN: urn:nbn:se:liu:diva-41583Local ID: 57975OAI: diva2:262437
Available from: 2009-10-10 Created: 2009-10-10 Last updated: 2015-12-10

Open Access in DiVA

No full text

Other links

Extern länk

Search in DiVA

By author/editor
Forssén, Per-Erik
By organisation
The Institute of TechnologyComputer Vision
Engineering and Technology

Search outside of DiVA

GoogleGoogle Scholar
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Total: 154 hits
ReferencesLink to record
Permanent link

Direct link