DocumentCode
2030187
Title
VideoStyler: multi-dimensional video computing for eloquent media interface
Author
Akutsu, A. ; Tonomura, Y. ; Hamada, H.
Author_Institution
NTT Human Interface Labs., Kanagawa, Japan
Volume
1
fYear
1995
fDate
23-26 Oct 1995
Firstpage
330
Abstract
We propose VideoStyler, a new eloquent video interface concept made possible by multi-dimensional video computing. VideoStyler allows the user to visualize video structures in several different ways. The implementation described in this paper offers VideoSpaceIcon, VideoPanorama, and VideoJigsaw by using multi-dimensional video computing that robustly supports camera operations estimation at speeds much faster than conventional optical flow methods. The accuracy of the estimation using the proposed method was better than 90% in a simulated experiment. VideoStyler is an efficient interface for intuitively understanding the spatio-temporal structure of related video shots. It explicitly permits spatio-temporal interaction: the temporal replay point can be selected directly from the visualized representation
Keywords
multimedia computing; user interfaces; video cameras; video signal processing; visual databases; VideoJigsaw; VideoPanorama; VideoSpaceIcon; VideoStyler; camera operations estimation; media interface; multi-dimensional video computing; spatio-temporal structure; temporal replay point; video interface concept; video libraries; video structures; visualized representation; Cameras; Computer interfaces; Data mining; Humans; Indexing; Laboratories; Layout; Optical computing; Visualization; Watches;
fLanguage
English
Publisher
ieee
Conference_Titel
Image Processing, 1995. Proceedings., International Conference on
Conference_Location
Washington, DC
Print_ISBN
0-8186-7310-9
Type
conf
DOI
10.1109/ICIP.1995.529713
Filename
529713
Link To Document