A similarity measure for motion stream segmentation and recognition

ABSTRACT

Recognition of motion streams such as data streams generated by different sign languages or various captured human body motions requires a high performance similarity measure. The motion streams have multiple attributes, and motion patterns in the streams can have different lengths from those of isolated motion patterns and different attributes can have different temporal shifts and variations. To address these issues, this paper proposes a similarity measure based on singular value decomposition (SVD) of motion matrices. Eigenvector differences weighed by the corresponding eigenvalues are considered for the proposed similarity measure. Experiments with general hand gestures and human motion streams show that the proposed similarity measure gives good performance for recognizing motion patterns in the motion streams in real time.

References

1. D. Berndt and J. Clifford. Using dynamic time warping to find patterns in time series. In AAAI-94 Workshop on Knowledge Discovery in Databases, pages 229--248, 1994.
2. V. M. Dyaberi, H. Sundaram, J. James, and G. Qian. Phrase structure detection in dance. In Proceedings of the ACM Multimedia Conference 2004, pages 332--335, Oct. 2004.
3. G. H. Golub and C. F. V. Loan. Matrix Computations. The Johns Hopkins University Press, Baltimore, Maryland, 1996.
4. L. Ikemoto and D. A. Forsyth. Enriching a motion collection by transplanting limbs. In Proceedings of the 2004 ACM SIGGRAPH/Eurographics symposium on Computer animation, pages 99 -- 108, 2004.
5. K. Kahol, P. Tripathi, S. Panchanathan, and T. Rikakis. Gesture segmentation in complex motion sequences. In Proceedings of IEEE International Conference on Image Processing, pages II - 105--108, Sept. 2003.
6. W. Krzanowski. Between-groups comparison of principal components. J. Amer. Stat. Assoc., 74(367): 703--707, 1979.
7. C. Li, B. Prabhakaran, and S. Zheng. Similarity measure for multi-attribute data. In Proceedings of the 2005 IEEE International Conference on Acoustics, Speach, and Signal Processing (ICASSP), Mar. 2005.
8. C. Li, P. Zhai, S.-Q. Zheng, and B. Prabhakaran. Segmentation and recognition of multi-attribute motion sequences. In Proceedings of the ACM Multimedia Conference 2004, pages 836--843, Oct. 2004.
9. R. H. Liang and M. Ouhyoung. A real-time continuous gesture recognition system for sign language. In Proceedings of the 3rd. International Conference on Face and Gesture Recognition, pages 558--565, 1998.
10. K. Pullen and C. Bregler. Motion capture assisted animation: texturing and synthesis. In SIGGRAPH, pages 501--508, 2002.
11. G. Qian, F. Guo, T. Ingalls, L. Olson, J. James, and T. Rikakis. A gesture-driven multimodal interactive dance system. In Proceedings of IEEE International Conference on Multimedia and Expo, June 2004.
12. C. Shahabi and D. Yan. Real-time pattern isolation and recognition over immersive sensor data streams. In Proceedings of the 9th International Conference on Multi-Media Modeling, pages 93--113, Jan 2003.
13. A. Singhal and D. E. Seborg. Clustering of multivariate time-series data. In Proceedings of the American Control Conference, pages 3931--3936, 2002.
14. T. Starner, J. Weaver, and A. Pentland. Real-time american sign language recognition using desk and wearable computer based video. IEEE Transactions on Pattern Analysis and Machine Intelligence, 20(12):1371--1375, 1998.
15. C. J. Taylor. Reconstruction of articulated objects from point correspondences in a single image. Computer Vision and Image Understanding, 80(3):349--363, 2000.
16. K. Yang and C. Shahabi. A PCA-based similarity measure for multivariate time series. In Proceedings of the Second ACM International Workshop on Multimedia Databases, pages 65--74, Nov. 2004.

Index Terms

• Information systems

  • Information systems applications

    • Data mining