skip to main content
research-article

Knowledge discovery from 3D human motion streams through semantic dimensional reduction

Published:07 March 2011Publication History
Skip Abstract Section

Abstract

3D human motion capture is a form of multimedia data that is widely used in entertainment as well as medical fields (such as orthopedics, physical medicine, and rehabilitation where gait analysis is needed). These applications typically create large repositories of motion capture data and need efficient and accurate content-based retrieval techniques. 3D motion capture data is in the form of multidimensional time-series data. To reduce the dimensions of human motion data while maintaining semantically important features, we quantize human motion data by extracting spatio-temporal features through SVD and translate them onto a symbolic sequential representation through our proposed sGMMEM (semantic Gaussian Mixture Modeling with EM). In order to handle variations in motion capture data due to human body characteristics and speed of motion, we transform the semantically quantized values into a histogram representation. This representation is used as a signature for classification and similarity-based retrieval. We achieved good classification accuracies for “coarse” human motion categories (such as walking 92.85%, run 91.42%, and jump 94.11%) and even for subtle categories (such as dance 89.47%, laugh 83.33%, basketball signal 85.71%, golf putting 80.00%). Experiments also demonstrated that the proposed approach outperforms earlier techniques such as the wMSV (weighted Motion Singular Vector) approach and LB_Keogh method.

References

  1. Adjeroh, D. A., King, I., and Lee, M. C. 1998a. Video sequence similarity matching. In Proceedings of the IAPR International Workshop on Multimedia Information Analysis and Retrieval. 80--95. Google ScholarGoogle ScholarDigital LibraryDigital Library
  2. Adjeroh, D. A., King, I., and Lee, M. C. 1998b. A distance measure for video sequence similarity matching. In Proceedings of the International Workshop on Multi-Media Database Management Systems (IW-MMDBS).Google ScholarGoogle Scholar
  3. Alexa, M. and Muller, W. 2000. Representing animations by principal components. Comput. Graph. Forum 19, 3, 411--418.Google ScholarGoogle ScholarCross RefCross Ref
  4. Bishop, C. M. 2006. Pattern Recognition and Machine Learning. Springer. CMU Motion Capture Library. CMU motion capture library homepage. http://mocap.cs.cmu.edu Google ScholarGoogle ScholarDigital LibraryDigital Library
  5. Cardle, M., Vlachos, M., Brooks, S., Keogh, E., and Gunopulos, D. 2003. Fast motion capture matching with replicated motion editing. In Proceedings of the 29th ACM SIGGRAPH Sketches and Applications.Google ScholarGoogle Scholar
  6. Dempster, A. P., Laird, N. M., and Rubin, D. B. 1977. Maximum likelihood from incomplete data via the EM algorithm. J. Royal Statist. Soc. B39, 1--38.Google ScholarGoogle Scholar
  7. Duda, R. O., Hart, P. E., and Stork, D. G. 2001. Pattern Classification. John Wiley and Sons, New York. Google ScholarGoogle ScholarDigital LibraryDigital Library
  8. Golub, G. H. and van Loan, C. F. 1996. Matrix Computation. The Johns Hopkins University Press, Baltimore, MD.Google ScholarGoogle Scholar
  9. Guerra-Filho, G. and Aloimonos, Y. 2007. A language for human action. IEEE Comput. Mag. 40, 5. Google ScholarGoogle ScholarDigital LibraryDigital Library
  10. Guerra-Filho, G. and Aloimonos, Y. 2006. A sensory-motor language for human activity understanding. In Proceedings of the 6th IEEE-RAS International Conference on Humanoid Robotics (HUMANOIDS'06). 69--75.Google ScholarGoogle Scholar
  11. Jin, Y. and Prabhakaran, B. 2008. Semantic quantization of 3D human motion capture data through spatial-temporal feature extraction. In Proceedings of the International Multimedia Modeling Conference (MMM). Google ScholarGoogle ScholarDigital LibraryDigital Library
  12. Ketterer, J., Puzicha, J., Held, M., Fisher, M., Buhmann, J. M., and Fellner, D. 2000. On spatial quantization of color images. IEEE Trans. Image Process. 9, 666--682. Google ScholarGoogle ScholarDigital LibraryDigital Library
  13. Kohonen, T., Kangas, J., Laaksonen, J., and Torkkola, K. 1992. A program package for the correct application of learning vector quantization algorithms. In Proceedings of the International Joint Conference on Neural Networks. 725--730.Google ScholarGoogle Scholar
  14. Kovar, L. and Gleicher, M. 2004. Automated extraction and parameterization of motions in large data sets. ACM Trans. Graph. 23, 3, 559--568. Google ScholarGoogle ScholarDigital LibraryDigital Library
  15. Keogh, E., Palpanas, T., Zordan, V. B., Gunopulos, D., and Cardle, M. 2004. Indexing large human-motion databases. In Proceedings of the 30th International Conference on Very Large Databases (VLDB'04). 780--791. Google ScholarGoogle ScholarDigital LibraryDigital Library
  16. Li, C., Pradhan, G. N., Zheng, S. Q., and Prabhakaran, B. 2004. Indexing of variable length multi-attribute motion data. In Proceedings of the 2nd ACM International Workshop on Multimedia. 75--84. Google ScholarGoogle ScholarDigital LibraryDigital Library
  17. Li, C., Kulkani, P. R., and Prabhakaran, B. 2007a. Motion stream segmentation and recognition by classification. Int. J. Multimedia Tools Appl. 35, 1.Google ScholarGoogle Scholar
  18. Li, C., Zheng, S. Q., and Prabhakaran, B. 2007b. Segmentation and recognition of motion streams by similarity search. ACM Trans. Multimedia Comput., Comm. Appl. 3, 3, Article 16. Google ScholarGoogle ScholarDigital LibraryDigital Library
  19. Liu, F., Zhuang, Y., Wu, F., and Pan, Y. 2003. 3D motion retrieval with motion index tree. Comput. Vis. Image Understand. 92, 265--284. Google ScholarGoogle ScholarDigital LibraryDigital Library
  20. Liu, G., Zhang, J., Wang, W., and McMillan, L. 2005. A system for analyzing and indexing human-motion databases. In Proceedings of the ACM SIGMOD International Conference on Management of Data. Google ScholarGoogle ScholarDigital LibraryDigital Library
  21. Meredith, M. and Maddock, S. Motion capture file format explained. Tech. rep., Department of Computer Science, University of Sheffield.Google ScholarGoogle Scholar
  22. Muller, M., Roder, T., and Clausen, M. 2005. Efficient content based retrieval of motion capture data. ACM Tran. Graph. 24, 677--685. Google ScholarGoogle ScholarDigital LibraryDigital Library
  23. NCBI. National center for biotechnology information. http://www.ncbi.nlm.nih.gov/Google ScholarGoogle Scholar
  24. Pradhan, G. N., Li, C., and Prabhakaran, B. 2007. Hierarchical indexing structure for 3D human motion. In Proceedings of the International Multimedia Modeling Conference (MMM). Google ScholarGoogle ScholarDigital LibraryDigital Library
  25. Redner, R. A. and Walker, H. F. 1984. Mixture densities, maximum likelihood and the EM algorithm. SIAM Rev. 26, 195--239.Google ScholarGoogle ScholarDigital LibraryDigital Library
  26. Wu, C. F. 1983. On the convergence properties of the EM algorithm. Ann. Statist. 11, 95--103.Google ScholarGoogle ScholarCross RefCross Ref
  27. Xu, L. and Jordan, M. I. 1996. On convergence properties of the EM algorithm for Gaussian mixtures. Neur. Comput. 8, 1, 129--151. Google ScholarGoogle ScholarDigital LibraryDigital Library
  28. Yang, K. and Shahabi, C. 2005. Multilevel distance-based index structure for multivariate time series. In Proceedings of the TIME Conference. IEEE Computer Society. Google ScholarGoogle ScholarDigital LibraryDigital Library
  29. Yang, C. F., Ye, M., and Zhao, J. 2003. Document clustering based on nonnegative sparse matrix factorization. In Proceedings of the 26th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval. 267--273. Google ScholarGoogle ScholarDigital LibraryDigital Library
  30. Yu, C., Ooi, B. C., Tan, K.-L., and Jagadish, H. V. 2001. Indexing the distance: An efficient method to knn processing. In Proceedings of the International Conference on Very Large Databases (VLDB'01). 421--430. Google ScholarGoogle ScholarDigital LibraryDigital Library

Index Terms

  1. Knowledge discovery from 3D human motion streams through semantic dimensional reduction

      Recommendations

      Comments

      Login options

      Check if you have access through your login credentials or your institution to get full access on this article.

      Sign in

      Full Access

      • Published in

        cover image ACM Transactions on Multimedia Computing, Communications, and Applications
        ACM Transactions on Multimedia Computing, Communications, and Applications  Volume 7, Issue 2
        February 2011
        142 pages
        ISSN:1551-6857
        EISSN:1551-6865
        DOI:10.1145/1925101
        Issue’s Table of Contents

        Copyright © 2011 ACM

        Publisher

        Association for Computing Machinery

        New York, NY, United States

        Publication History

        • Published: 7 March 2011
        • Revised: 1 October 2009
        • Accepted: 1 October 2009
        • Received: 1 August 2008
        Published in tomm Volume 7, Issue 2

        Permissions

        Request permissions about this article.

        Request Permissions

        Check for updates

        Qualifiers

        • research-article
        • Research
        • Refereed

      PDF Format

      View or Download as a PDF file.

      PDF

      eReader

      View online with eReader.

      eReader
      About Cookies On This Site

      We use cookies to ensure that we give you the best experience on our website.

      Learn more

      Got it!