Automatic 3D Video Summarization: Key Frame Extraction from Self-Similarity
作者： Adrian Hilton , Peng Huang , Jonathan Starck
DOI:
关键词:
摘要: In this paper we present an automatic key frame selection method to summarise 3D video sequences. Key-frame is based on optimisation for the set of frames which give best representation sequence according a rate-distortion trade-off. Distortion summarization from original measurement self-similarity using volume histograms. The evaluates globally optimal key-frames represent entire without requiring pre-segmentation into shots or temporal correspondence. Results demonstrate that sequences people wearing variety clothing automatically selects dynamics. Comparative evaluation characteristics with previous demonstrates improved performance.
参考文章(25)
Daniel Thalmann, Ik Soo Lim, Key-posture extraction out of human motion data by curve simplification Kyoto University. ,(2001)
Jun Xiao, Yueting Zhuang, Tao Yang, Fei Wu, An Efficient Keyframe Extraction from Motion Capture Data Advances in Computer Graphics. pp. 494- 501 ,(2006) , 10.1007/11784203_44
Jackie Assa, Yaron Caspi, Daniel Cohen-Or, Action synopsis: pose selection and illustration international conference on computer graphics and interactive techniques. ,vol. 24, pp. 667- 676 ,(2005) , 10.1145/1073204.1073246
Yukinobu Taniguchi, Akihito Akutsu, Yoshinobu Tonomura, Hiroshi Hamada, An intuitive and efficient access interface to real-time incoming video based on automatic indexing acm multimedia. pp. 25- 33 ,(1995) , 10.1145/217279.215075
Daniel DeMenthon, Vikrant Kobla, David Doermann, Video summarization by curve simplification acm multimedia. pp. 211- 218 ,(1998) , 10.1145/290747.290773
T. Kanade, P. Rander, P.J. Narayanan, Virtualized reality: constructing virtual worlds from real scenes IEEE MultiMedia. ,vol. 4, pp. 34- 47 ,(1997) , 10.1109/93.580394
Michael Waschbüsch, Stephan Würmlin, Daniel Cotting, Filip Sadlo, Markus Gross, Scalable 3D video of dynamic scenes The Visual Computer. ,vol. 21, pp. 629- 638 ,(2005) , 10.1007/S00371-005-0346-7
Adrian Hilton, Daniel Beresford, Thomas Gentils, Raymond Smith, Wei Sun, John Illingworth, Whole-body modelling of people from multiview images to populate virtual worlds The Visual Computer. ,vol. 16, pp. 411- 436 ,(2000) , 10.1007/PL00013395
J. XU, T. YAMASAKI, K. AIZAWA, Summarization of 3D Video by Rate-Distortion Trade-off The IEICE transactions on information and systems. ,vol. 90, pp. 1430- 1438 ,(2007) , 10.1093/IETISY/E90-D.9.1430
Jaco Vermaak, Patrick Pérez, Michel Gangnet, Andrew Blake, Rapid Summarisation and Browsing of Video Sequences british machine vision conference. pp. 1- 10 ,(2002) , 10.5244/C.16.40