GVU Technical Report Number:
GIT-GVU-99-31
Title:
Motion Based Decomposition of Video
Authors:
Gabriel J. Brostow
Irfan A. Essa
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.
Keywords:
Vision, occlusion tracking, special effect, chromakeying, layers
You can access this technical report via:
PDF
Postscript
|
