Abstract
We present a method for the efficient retrieval and browsing of immense amounts of realistic 3D human body motion capture data. The proposed method organizes motion capture data based on statistical K-means (SK–means), democratic decision making, unsupervised learning, and visual key frame extraction, thus achieving intuitive retrieval by browsing thumbnails of semantic key frames. We apply three steps for the efficient retrieval of motion capture data. The first is obtaining the basic type clusters by clustering motion capture data using the novel SK-means algorithm, and after which, immediately performing character matching. The second is learning the retrieval information of users during the retrieval process and updating the successful retrieval rate of each data; the search results are then ranked on the basis of successful retrieval rate by democratic decision making to improve accuracy. The last step is generating thumbnails with semantic generalization, which is conducted by using a novel key frame extraction algorithm based on visualized data analysis. The experiment demonstrates that this method can be utilised for the efficient organization and retrieval of enormous motion capture data.










Similar content being viewed by others
Explore related subjects
Discover the latest articles and news from researchers in related subjects, suggested using machine learning.References
Anil KJ (2010) Data clustering: 50 years beyond K-Means. Pattern Recogn Lett 651–666
Bulut E, Capin T (2007) Key frame extraction from motion capture data by curve saliency, proc. Comp Anim Soc Agent 63–67
Chao MW, Lin CH, Assa J, et al (2012) Human motion retrieval from hand-drawn sketch., IEEE Trans Vis Comput Graph 729–740
Deng ZG, Gu Q, Li Q (2009) Perceptually consistent example-based human motion retrieval, proc. Computer graphics proceedings, annual conference series, ACM S IGGRAPH. ACM Press, New York, pp 191–198
Ioannidis AI, Chasanis VT, Likas AC (2014) Key-frame extraction using weighted multi-view convex mixture models and spectral clustering, proc. Pattern Recog 22nd Int Conf IEEE (ICPR) 3463–3468
Lim I S, Thalmann D (2001) Key-posture extraction out of human motion data by curve simplification, Proc. the 23rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Istanbul 1167–1169
Lim IS, Thalmann D (2001) Key-posture extraction out of human motion data by curve simplification, proc. Proc EMBC 1167–1169
Liu F, Zhuang YT, Wu F, et al (2003) 3D motion retrieval with motion index tree. Comput Vis Image Underst 265–284
Loy G, Sullivan J, Carlsson S (2003) Pose-based clustering in action sequences, Proc. the 1st IEEE International Workshop on Higher-Level Knowledge in 3DModeling and Motion Analysis, Nice 66–72
Miura T, Kaiga T, Shibata T, et al (2014) A hybrid approach to key frame extraction from motion capture data using curve simplification and principal component analysis. IEEE Trans Electr Electron Eng 697–699
Numaguchi N, Nakazawa A, Shiratori T, et al (2011) A puppet interface for retrieval of motion capture data, Proc. 2011 ACM SIGGRAPH/Eurographics Symposium on Computer Animation. ACM 157–166
Tang JKT, Leung H (2012) Retrieval of logically relevant 3D human motions by adaptive feature selection with graded relevance feedback. Pattern Recogn Lett 420–430
Wu SG, Wang ZQ, Xia SH (2009) Indexing and retrieval of human motion data by a hierarchical tree, proc. 16th ACM symposium on virtual reality software and technology. ACM Press, New York, pp 207–-214
Wu S, Xia S, Wang Z, et al (2009) Efficient motion data indexing and retrieval with local similarity measure of motion strings. Vis Comput 499–508
Yang T, Xiao J, Wu F, et al (2006) Extraction of key-frame of motion capture data based on layered curve simplification. J Comput Aided Des Comput Graph 1691–1697
Zhang Z P (2008) Content-based motion retrieval using vector space model. Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Zhang Q, Xue X, Zhou D, et al (2014) Motion key-frames extraction based on amplitude of distance characteristic curve. Int J Comput Intell Syst 506–514
Zhao L, Qi W, Li S Z, et al (2000) Key-frame extraction and shot retrieval using nearest feature line (NFL),proc. Proceedings of ACM Workshops on Multimedia, Los Angeles, CA 217–220
Acknowledgments
This work was supported by National Science Foundation of China(NO.61303142, 60970021,61173096),Natural Science Foundation of Zhejiang Province(N0. Y1110882,Y1110688,R1110679), Higher School Specialized Research Fund for the Doctoral Program.(N0.20113317110001).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Wang, X., Chen, L., Jing, J. et al. Human motion capture data retrieval based on semantic thumbnail. Multimed Tools Appl 75, 11723–11740 (2016). https://doi.org/10.1007/s11042-015-2705-3
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-015-2705-3