For those etymologists out there, Proscenium is derived from the Greek "pro" (meaning in front of) and "skene" (the building behind ancient Greek stages where actors dressed).
We present an approach to video editing where movie sequences are treated as spatio-temporal volumes that can be sheered and warped under user control. This simple capability enables new video editing operations that support complex postproduction modifications, such as object removal and/or changes in camera motion. Our methods do not rely on complicated and error-prone image analysis or computer vision methods. Moreover, they facilitate an editing approach to video that is similar to standard image-editing tasks. Central to our system is a movie representation framework that supports efficient queries and operations on spatio-temporal volumes while maintaining the original source content. We have adopted a graph-based lazy evaluation model in order to support interactive visualizations, complex data modifications, efficient processing, and efficient memory utilization of large spatio-temporal volumes.
Eric P. Bennett and Leonard McMillan "Proscenium:
A Framework for Spatio-Temporal Video Editing" In the Proceedings
of ACM Multimedia, 2003 (Berkeley, CA) p. 177-183 "Proscenium: A Framework for Spatio-Temporal Video Editing" (Eric P. Bennett, Leonard McMillan) was named Best Student Paper at ACM Multimedia 2003
3 Minute System Demonstration MPEG-1
(51 MB) (Right-Click to Download)
If you are interested in the Proscenium system please contact Eric Bennett. |