UNSUPERVISED DANCE FIGURE ANALYSIS FROM VIDEO FOR DANCING AVATAR ANIMATION. Ofli, F., Erzin, E., Yemez, Y., Tekalp, A. M., Erdem, C. E., Erdem, A. T., Abaci, T., & Ozkan, M. K. In 2008 15TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, VOLS 1-5, of IEEE International Conference on Image Processing (ICIP), pages 1484-1487, 2008. IEEE Signal Proc Soc. 15th IEEE International Conference on Image Processing (ICIP 2008), San Diego, CA, OCT 12-15, 2008
doi  abstract   bibtex   
This paper presents a framework for unsupervised video analysis in the context of dance performances, where gestures and 3D movements of a dancer are characterized by repetition of a set of unknown dance figures. The system is trained in an unsupervised manner using Hidden Markov Models (HMMs) to automatically segment multi-view video recordings of a dancer into recurring elementary temporal body motion patterns to identify the dance figures. That is, a parallel HMM structure is employed to automatically determine the number and the temporal boundaries of different dance figures in a given dance video. The success of the analysis framework has been evaluated by visualizing these dance figures on a dancing avatar animated by the computed 3D analysis parameters. Experimental results demonstrate that the proposed framework enables synthetic agents and/or robots to learn dance figures from video automatically.
@inproceedings{ ISI:000265921400372,
Author = {Ofli, F. and Erzin, E. and Yemez, Y. and Tekalp, A. M. and Erdem, C. E.
   and Erdem, A. T. and Abaci, T. and Ozkan, M. K.},
Book-Group-Author = {{IEEE}},
Title = {{UNSUPERVISED DANCE FIGURE ANALYSIS FROM VIDEO FOR DANCING AVATAR
   ANIMATION}},
Booktitle = {{2008 15TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, VOLS 1-5}},
Series = {{IEEE International Conference on Image Processing (ICIP)}},
Year = {{2008}},
Pages = {{1484-1487}},
Note = {{15th IEEE International Conference on Image Processing (ICIP 2008), San
   Diego, CA, OCT 12-15, 2008}},
Organization = {{IEEE Signal Proc Soc}},
Abstract = {{This paper presents a framework for unsupervised video analysis in the
   context of dance performances, where gestures and 3D movements of a
   dancer are characterized by repetition of a set of unknown dance
   figures. The system is trained in an unsupervised manner using Hidden
   Markov Models (HMMs) to automatically segment multi-view video
   recordings of a dancer into recurring elementary temporal body motion
   patterns to identify the dance figures. That is, a parallel HMM
   structure is employed to automatically determine the number and the
   temporal boundaries of different dance figures in a given dance video.
   The success of the analysis framework has been evaluated by visualizing
   these dance figures on a dancing avatar animated by the computed 3D
   analysis parameters. Experimental results demonstrate that the proposed
   framework enables synthetic agents and/or robots to learn dance figures
   from video automatically.}},
DOI = {{10.1109/ICIP.2008.4712047}},
ISSN = {{1522-4880}},
ISBN = {{978-1-4244-1765-0}},
ResearcherID-Numbers = {{Erzin, Engin/H-1716-2011
   Eroglu Erdem, Cigdem/J-4216-2012}},
ORCID-Numbers = {{Erzin, Engin/0000-0002-2715-2368
   Eroglu Erdem, Cigdem/0000-0002-9264-5652}},
Unique-ID = {{ISI:000265921400372}},
}

Downloads: 0