Video editing using figure tracking and image-based rendering

Author

Rehg, James M. ; Kang, Sing Bing ; Cham, Tat-Jen

Author_Institution

Res. Lab., Compaq Comput. Corp., Cambridge, MA, USA

Volume

2

fYear

2000

fDate

10-13 Sept. 2000

Firstpage

17

Abstract

We describe a new approach to video editing based on the semi-automatic segmentation of video into multiple layers and the composition of layers using image-based rendering. Using figure tracking and background motion estimation, we can segment a moving figure and reconstruct the background. Using geometrically-correct pixel reprojection, layers can be composited on the basis of the geometry of the underlying scene and the position of a virtual camera. We have implemented a prototype editing system called SpliceWorld.

Keywords

image reconstruction; image segmentation; motion estimation; rendering (computer graphics); tracking; video signal processing; SpliceWorld; background motion estimation; background reconstruction; figure tracking; geometrically-correct pixel reprojection; image-based rendering; layers composition; multiple layers; prototype editing system; semi-automatic video segmentation; video editing; virtual camera position; Cameras; Image reconstruction; Image segmentation; Laboratories; Layout; Motion estimation; Painting; Rendering (computer graphics); Torso; Tracking;

fLanguage

English

Publisher

ieee

Conference_Titel

Image Processing, 2000. Proceedings. 2000 International Conference on

Conference_Location

Vancouver, BC, Canada

ISSN

1522-4880

Print_ISBN

0-7803-6297-7

Type

conf

DOI

10.1109/ICIP.2000.899213

Filename

899213