PAPERS: Motion AnalysisNo Access

DOUBLE-REFERENCE INDEX FOR MOTION RETRIEVAL BY ISOMAP DIMENSIONALITY REDUCTION

School of Information and Electronic Engineering, ZheJiang University of Science and Technology, 310023 Hangzhou, P. R. China

Search for more papers by this author

and

ZHIJUN ZHENG

School of Information and Electronic Engineering, ZheJiang University of Science and Technology, 310023 Hangzhou, P. R. China

Search for more papers by this author

https://doi.org/10.1142/S0218001410008044Cited by:0 (Source: Crossref)

Abstract

Along with the development of the motion capture (mocap) technique, large-scale 3D motion databases have become increasingly available. In this paper, a novel approach is presented for motion retrieval based on double-reference index (DRI). Due to the high dimensionality of motion's features, Isomap nonlinear dimension reduction is used. In addition, an algorithmic framework is employed to approximate the optimal mapping function by a Radial Basis Function (RBF) in handling new data. Subsequently, a DRI is built based on selecting a small set of representative motion clips in the database. Thus, the candidate set is obtained by discarding the most unrelated motion clips to significantly reduce the number of costly similarity measures. Finally, experimental results show that these approaches are effective for motion data retrieval in large-scale databases.

Keywords:

References

J. Assa, Y. Caspi and D. Cohen-Or, Action synopsis: Pose selection and illustration, Proc. ACM SIGGRAPH (2005) pp. 667–676. Google Scholar
S. Basu, S. Shanbhag and S. Chandran, Search and transition for motion captured sequences, Proc. ACM Symp. Virtual Reality Software and Technology (2005) pp. 220–223. Google Scholar
B. Demuthet al., An information retrieval system for motion capture data, ECIR (2006), LNCS pp. 373–384. Google Scholar
R. F. S. Filho, A. J. M. Traina and C. Faloutsos, Similarity search without tears: The OMNI family of all-purpose access methods, Proc. ICDE (2001) pp. 623–630. Google Scholar
E. Giladiet al., Bioinformatics 18(6), 873 (2002), DOI: 10.1093/bioinformatics/18.6.873. Crossref, Web of Science, Google Scholar
X. F. He, W. Y. Ma and H. J. Zhang, Learning an image manifold for retrieval, Proc. 12th ACM Int. Conf. Multimedia (2004) pp. 17–23. Google Scholar
E. Hunt, M. P. Atkinson and R. W. Irving, A database index to large biological sequences, Proc. Int. Conf. Very Large Data Bases (2001) pp. 139–148. Google Scholar
H. V. Jagadishet al., ACM Trans. Database Syst. 30(2), 364 (2005), DOI: 10.1145/1071610.1071612. Crossref, Web of Science, Google Scholar
T. Kahveci, V. Ljosa and A. Singh, Bioinformatics 20(13), 2122 (2004), DOI: 10.1093/bioinformatics/bth212. Crossref, Web of Science, Google Scholar
E. Keoghet al., Indexing large human-motion databases, Proc. Int. Conf. Very Large Data Bases (2004) pp. 780–791. Google Scholar
M. H. C. Law, N. Zhang and A. K. Jain, Nonlinear manifold learning for data stream, Proc. SIAM Data Mining (2004) pp. 33–44. Google Scholar
J. Leeet al., Interactive control of avatars animated with human motion data, Proc. ACM SIGGRAPH (2002) pp. 491–500. Google Scholar
Y. Lin, Efficient motion search in large motion capture databases, ISVC 2006, LNCS pp. 151–160. Google Scholar
F. Liuet al., Comput. Vis. Imag. Underst. 92(3), 265 (2003), DOI: 10.1016/j.cviu.2003.06.001. Crossref, Web of Science, Google Scholar
G. D. Liuet al., A system for analyzing and indexing human-motion databases, Proc. SIGMOD (2005) pp. 924–926. Google Scholar
J. Moody and C. Darken, Neural Comput. 1, 281 (1989), DOI: 10.1162/neco.1989.1.2.281. Crossref, Web of Science, Google Scholar
M. Muller and T. Roder, Motion templates for automatic classification and retrieval of motion capture data, Proc. ACM SIGGRAPH Symp. Computer Animation (2006) pp. 137–146. Google Scholar
S. T. Roweis and L. K. Saul, Science 290(5500), 2323 (2000), DOI: 10.1126/science.290.5500.2323. Crossref, Web of Science, Google Scholar
L. K. Shi, P. L. He and B. Liu, A robust generalization of Isomap for new data, Proc. Fourth Int. Conf. Machine Learning and Cybernetics (2005) pp. 1702–1712. Google Scholar
F. Y. Shihet al., Int. J. Patt. Recogn. Artif. Intell. 22(3), 515 (2008), DOI: 10.1142/S0218001408006296. Link, Web of Science, Google Scholar
F. Y. Shih and Y. Y. Fu, Int. J. Patt. Recogn. Artif. Intell. 22(2), 335 (2008), DOI: 10.1142/S0218001408006235. Link, Web of Science, Google Scholar
J. Tenenbaum, V. D. Silva and J. Langford, Science 290(5500), 2319 (2000), DOI: 10.1126/science.290.5500.2319. Crossref, Web of Science, Google Scholar
C. Trainaet al., How to improve the pruning ability of dynamic metric access methods, Proc. CIKM (2002) pp. 219–226. Google Scholar
E. Ukkonen, Inform. Contr. 100 (1985), DOI: 10.1016/S0019-9958(85)80046-2. Google Scholar
P. Weiner, Linear pattern matching algorithms, IEEE Symp. Switching and Automata Theory (1973) pp. 1–11. Google Scholar
W. T. Wong, F. Y. Shih and T. F. Su, Int. J. Patt. Recogn. Artif. Intell. 21(6), 995 (2007), DOI: 10.1142/S0218001407005843. Link, Web of Science, Google Scholar

Vol. 24, No. 04

Metrics

Downloaded 31 times

History

Keywords

PDF download

System Upgrade on Tue, May 28th, 2024 at 2am (EDT)

DOUBLE-REFERENCE INDEX FOR MOTION RETRIEVAL BY ISOMAP DIMENSIONALITY REDUCTION

Abstract

Recommended