VideoStyler: multi-dimensional video computing for eloquent media interface

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.

[1]  Yoshinobu Tonomura,et al.  Video handling based on structured information for hypermedia systems , 1991 .

[2]  Steve Mann,et al.  Virtual bellows: constructing high quality stills from video , 1994, Proceedings of 1st International Conference on Image Processing.

[3]  Harpreet S. Sawhney,et al.  Model-based 2D&3D dominant motion estimation for mosaicing and video representation , 1995, Proceedings of IEEE International Conference on Computer Vision.

[4]  Glorianna Davenport,et al.  Creating and Viewing the Elastic Charles - A Hypermedia Journal , 1989, UK Hypertext.

[5]  Minoru Asada,et al.  Color-based panoramic representation of outdoor environment for a mobile robot , 1988, [1988 Proceedings] 9th International Conference on Pattern Recognition.

[6]  Michal Irani,et al.  Motion Analysis for Image Enhancement: Resolution, Occlusion, and Transparency , 1993, J. Vis. Commun. Image Represent..

[7]  Hideo Hashimoto,et al.  Video indexing using motion vectors , 1992, Other Conferences.

[8]  Takafumi Miyatake,et al.  IMPACT: an interactive natural-motion-picture dedicated multimedia authoring system , 1991, CHI.

[9]  Glorianna Davenport,et al.  Cinematic primitives for multimedia , 1991, IEEE Computer Graphics and Applications.

[10]  Yoshinobu Tonomura,et al.  VideoMAP and VideoSpaceIcon: tools for anatomizing video content , 1993, INTERCHI.

[11]  Walter Bender,et al.  Salient video stills: content and context preserved , 1993, MULTIMEDIA '93.

[12]  Michael Hoetter Differential estimation of the global motion parameters zoom and pan , 1989 .

[13]  Yoshinobu Tonomura,et al.  Video tomography: an efficient method for camerawork extraction and motion analysis , 1994, MULTIMEDIA '94.