Region-based optical flow estimation

Fuh, C; Maragos, P

dc.contributor.author	Fuh, C	en
dc.contributor.author	Maragos, P	en
dc.date.accessioned	2014-03-01T02:47:53Z
dc.date.available	2014-03-01T02:47:53Z
dc.date.issued	1989	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/33403
dc.subject	Gradient Method	en
dc.subject	Median Filter	en
dc.subject	Optical Flow Estimation	en
dc.subject	Velocity Estimation	en
dc.subject	Optical Flow	en
dc.title	Region-based optical flow estimation	en
heal.type	conferenceItem	en
heal.identifier.primary	10.1109/CVPR.1989.37840	en
heal.identifier.secondary	http://dx.doi.org/10.1109/CVPR.1989.37840	en
heal.publicationDate	1989	en
heal.abstract	A correspondence method is developed for determining optical flow where the primitive motion tokens to be matched between consecutive time frames are regions. The computation of optical flow consists of three stages: region extraction, region matching, and optical flow smoothing. The computation is completed by smoothing the initial optical flow, where the sparse velocity data are either smoothed with a	en
heal.journalName	Computer Vision and Pattern Recognition	en
dc.identifier.doi	10.1109/CVPR.1989.37840	en