Motion Based Decompositing of Video

Brostow, Gabriel Julian; Essa, Irfan

Title:

Motion Based Decompositing of Video

dc.contributor.author	Brostow, Gabriel Julian
dc.contributor.author	Essa, Irfan
dc.date.accessioned	2004-10-15T18:43:00Z
dc.date.available	2004-10-15T18:43:00Z
dc.date.issued	1999
dc.description.abstract	We present a method to decompose video sequences into layers that represent the relative depths of complex scenes. Our method combines spatial information with temporal occlusions to determine relative depths of these layers. Spatial information is obtained through edge detection and a customized contour completion algorithm. Activity in a scene is used to extract temporal occlusion events, which are in turn, used to classify objects as occluders or occludees. The path traversed by the moving objects determines the segmentation of the scene. Several examples of decompositing and compositing of video are shown. This approach can be applied in the pre-processing of sequences for compositing or tracking purposes and to determine the approximate 3D structure of a scene.	en
dc.format.extent	166282 bytes
dc.format.mimetype	application/pdf
dc.identifier.uri	http://hdl.handle.net/1853/3398
dc.language.iso	en_US
dc.publisher	Georgia Institute of Technology	en
dc.relation.ispartofseries	GVU Technical Report;GIT-GVU-99-31
dc.subject	Vision	en
dc.subject	Occlusion tracking	en
dc.subject	Special effect	en
dc.subject	Layers	en
dc.title	Motion Based Decompositing of Video	en
dc.type	Text
dc.type.genre	Technical Report
dspace.entity.type	Publication
local.contributor.author	Essa, Irfan
local.contributor.corporatename	GVU Center
local.relation.ispartofseries	GVU Technical Report Series
relation.isAuthorOfPublication	84ae0044-6f5b-4733-8388-4f6427a0f817
relation.isOrgUnitOfPublication	d5666874-cf8d-45f6-8017-3781c955500f
relation.isSeriesOfPublication	a13d1649-8f8b-4a59-9dec-d602fa26bc32