\CPL\Project\Graphics and Multimedia



Interactive Mosaic Generation for Video Navigation



Kihwan Kim, Irfan Essa, Gregory D. Abowd

College of Computing, Georgia Institute of Technology





Navigation through large multimedia collections that include videos and images still remains a hard problem. In this paper, we introduce a novel method to visualize and navigate through the collection by creating a mosaic image that represents the compilation. This image is generated by a labeling-based  layout algorithm using various sizes of sample tile images from the collection. Each tile represents both the photographs and video files representing scenes selected by matching algorithms. This generated mosaic image provides a new way for thematic video and also visually summarizes the videos. Users can generate these mosaics with some predefined themes and layouts, or base it on the results of their queries. Our approach supports automatic generation of these layouts by using meta-information such as color, time-line and existence of faces or manually generated annotated information from existing systems (e.g., the Family Video Archive).



 K.Kim , I.Essa and G.Abowd Interactive Mosaic Generation for Video Navigation. In Proceeding of the ACM International conference on Multimedia 2006 (ACMMM06) - (to be appeared) [PDF]




[1] Result of each step of interactive mosaic

 (a) Original template image (b) Labeling and Packing image (c) Result of matching image ( using 1000 key-frames from "Hero(2003)")


[2] Diagram : Process of interactive mosaicing.

[3] Result of interactive mosaic using some chinese letter as a template



[4]Making mosaic with phrase "Anthony's Pics" as a template, and using the keyframes from family-videos where anthony is appeared on them.







Related work @GT


- Mediating Photo Collage Authoring

- Family Video Archive in Ubicomp in the home(Aware Home)


Other related work


-Hausner, A. Simulating Decorative Mosaics. In Proceedings of ACM SIGGRAPH '01, (Los Angeles,CA), 2001, 573-580


-Kim, J. and F. Pellacini. Jigsaw Image Mosaics. In Proceedings of ACM SIGGRAPH '02, (San Antonio, TX) ,2002, 657-664


-Smith, K., Y. Liu, et al. Animosaics. In Proc. of the ACM SIGGRAPH/Eurographics symposium on Computer Animation, 2005, 201-208


-Arman, F., R.Depommier, et al. Content-based Browsing of Video Sequences. In Proc. of the ACM Multimedia, 1994, 1-8


-etc ..