Video as an image data source: efficient representations and applications
- 19 November 2002
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1, 318-321
- https://doi.org/10.1109/icip.1995.529710
Abstract
The two fundamental advantages of video over still imagery are: (i) the ability capture temporal information, and (ii) the ability to acquire a continuously varying set of views of a scene. These advantages are obtained, however, at the cost of vastly increased amount of data. This paper describes an approach to video representation that is based on frame-to-frame alignment, mosaic construction, and 3D parallax recovery. The basic motivation behind our approach is to enable rapid access to the contents, while maintaining the data in a form as close to the source as possible. This representation supports a wide variety of applications that involve transmission, storage, visualization, retrieval, analysis, and manipulation of video sequences.Keywords
This publication has 5 references indexed in Scilit:
- Direct recovery of shape from multiple views: a parallax based approachPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Real-time scene stabilization and mosaic constructionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Mosaic based representations of video sequences and their applicationsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Representation of scenes from collections of imagesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- A three-frame algorithm for estimating two-component image motionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1992