Motion based decompositing of video
- 1 January 1999
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1, 8-13 vol.1
- https://doi.org/10.1109/iccv.1999.791190
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 occludes. 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
This publication has 12 references indexed in Scilit:
- Robust estimation of a multi-layered motion representationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Interpolating cubic spline contours by minimizing second derivative discontinuityPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Active blobsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Using adaptive tracking to classify and monitor activities in a sitePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Pfinder: real-time tracking of the human bodyPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1997
- Tour into the picturePublished by Association for Computing Machinery (ACM) ,1997
- Blue screen mattingPublished by Association for Computing Machinery (ACM) ,1996
- An appearance-based representation of actionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1996
- Representing moving images with layersIEEE Transactions on Image Processing, 1994
- Biological image motion processing: A reviewVision Research, 1985