A Method of Hyper-sphere Cover in Multidimensional Space for Human Mocap Data Retrieval

• Authors: Xiaopeng Wei , Boxiang Xiao , Qiang Zhang , Rui Liu
• Languages of publication: EN

Abstracts

EN

A method of hyper-sphere cover in multidimensional space for human Mocap (Motion Capture) data retrieval is presented in this paper. After normalization and feature extraction, both the retrieval instance and the motion data are mapping into a multidimensional space. Several hyper-spheres are constructed according to the retrieval instance, and the domain covered by these hyper-spheres can be considered as the distribution range of a same kind of motions. By use of CMU free motion database, the retrieval algorithm has been implemented and examined and the experimental results are illustrated. At the same time, the main contributions and limitations are discussed.

Keywords

EN

MoCap (Motion Capture) Data; Retrieval; Multidimensional Space; Hyper-sphere Cover

• Publisher: De Gruyter Open
• Journal: Journal of Human Kinetics
• Year: 2011
• Volume: 28
• Pages: 133-139

Dates

published

1 - 6 - 2011

online

4 - 7 - 2011

Contributors

author

Xiaopeng Wei

author

Boxiang Xiao

• Key Laboratory of Advanced Design and Intelligent Computing, Dalian University, Ministry of Education, Dalian, China

author

Qiang Zhang

• Key Laboratory of Advanced Design and Intelligent Computing, Dalian University, Ministry of Education, Dalian, China

author

Rui Liu

• School of Mechanical Engineering, Dalian University of Technology, Dalian, China

References

• Demuth B., Roder T., Muller M., and Eberhardt B. An Information Retrieval System for Motion Capture Data. LNCS 3936. 2006, 373-384.
• Chiu C., Chao S., Wu M., Yang S., Lin H. Content-based retrieval for human motion data. Journal of Visual Communication and Image Representation. 2004, (15)3: 446-466.[Crossref][WoS]
• Muller M. and Roder T. Motion Templates for Automatic Classification and Retrieval of Motion Capture Data. Eurographics/ACM SIGGRAPH Symposium on Computer Animation. 2006, 137-146.
• Roder T. Similarity, Retrieval, and Classification of Motion Capture Data. University of Bonn. 2006, 93-110.
• Muller M., Roder T., Clausen M. Efficient Content-Based Retrieval of Motion Capture Data. ACM Transactions on Graphics (TOG). 2005, (24)3: 677-685.[Crossref]
• Yamasaki T., Aizawa K. Content-Based Cross Search for Human Motion Data Using Time-Varying Mesh and Motion Capture Data. Proceeding of IEEE International Conference on Multimedia and Expo (ICME2007). 2007, 2007-2009.
• Chao S., Chiu C., Chao J., Ruan Y., Yang S. Motion Retrieval and Synthesis Based on Posture Feature Indexing. Proceedings of the Fifth International Conference on Computational Intelligence and Multimedia Applications (ICCIMA'03). 2003, 266-271.
• Liu F., Zhuang Y., Wu F., and Pan Y. 3D motion retrieval with motion index tree. Computer Vision and Image Understanding. 2003, (92)2: 265-284.[Crossref]
• Xiang J. and Zhu H. Motion Retrieval Based on Temporal-Spatial Features by Decision Tree. LNCS 4561. 2007, 224-233.
• Lin Y. Efficient Motion Search in Large Motion Capture Databases. LNCS 4291. 2006, 151-160.
• Wang X., Yu Z., Wong H. 3D Motion Sequence Retrieval Based on Data Distribution. ICME 2008. 2008, 1229-1232.
• Yu T., Shen X., Li Q. and Geng W. Motion retrieval based on movement notation language. Computer Animation and Virtual Worlds. 2005, 16: 273-282.[Crossref]
• Xiang J. and Zhu H. Ensemble HMM Learning for Motion Retrieval with Non-linear PCA Dimensionality Reduction. IIHMSP. 2007, 604-607.
• Tam G., Zheng Q., Rynson M., Lau W.H. Motion Retrieval Based on Energy Morphing. Ninth IEEE International Symposium on Multimedia 2007, 210-217.
• Wei X., Xiao B., Zhang Q., Zhou D. Effective approach based on semantic matching for retrieval of MoCap data. Journal of Computational Information Systems. 2008, (4)3: 859-866.
• CMU motion capture database.

Identifiers

DOI

10.2478/v10078-011-0030-0