Abstract
The linear combination of prototypical views provides a powerful approach for the recognition and the synthesis of images of stationary three-dimensional objects. In this article, we present initial results that demonstrate that similar ideas can be developed for the recognition and synthesis of complex motion patterns. We present a technique that permits to represent complex motion or action patterns by linear combinations of a small number of prototypical image sequences. We demonstrate the applicability of this new approach for the synthesis and analysis of biological motion using simulated and real video data from different locomotion patterns. Our results show that complex motion patterns are embedded in pattern spaces with a defined topological structure, which can be uncovered with our methods. The underlying pattern space seems to have locally, but not globally, the properties of a linear vector space. We show how the knowledge about the topology of the pattern space can be exploited during pattern recognition. Our method may provide a new interesting approach for the analysis and synthesis of video sequences and complex movements.
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.References
Ahmad, T., Taylor, C.J., Lanitis, A., and Cootes, T.F. 1997. Tracking and recognizing hand gestures, using statistical shape models. Image and Vision Computing, 19, in press.
Badler, N.I. 1993. Simulating Humans. Oxford University Press: New York.
Beymer, D. and Poggio, T. 1996. Image representations for visual learning. Science, 272:1905–1909.
Beymer, D., Shashua, A., and Poggio, T. 1993. Example-based image analysis and synthesis. Technical Report 1431, Massachusetts Institute of Technology, Cambridge, MA.
Black, M.J. and Jepson, A.D. 1996. Eigen tracking: Robust matching and tracking of articulated objects using a view-based representation. In Proceedings of the European Conference on Computer Vision, Cambridge. Springer, NY.
Blake, A. and Isard, M. 1998. Active Contours. Springer: New York.
Blanz, V. and Vetter, T. 1999. Morphable model for the synthesis of 3D faces. In Proceedings of SIGGRAPH 99, Los Angeles, pp. 187–194.
Bruderlin, A. and Williams, L. 1995. Motion signal processing. In Proceedings of SIGGRAPH 95, Los Angeles, pp. 97–104.
Darrell, T.J., Essa, I.A., and Pentland, A. 1995. Task-specific gesture analysis in real-time using interpolated views. Technical Report 364, Massachusetts Institute of Technology, Cambridge, MA.
Davis, J.W. and Bobick, A.F. 1996. The representation and recognition of action using temporal templates. Technical Report 402, Massachusetts Institute of Technology, Cambridge, MA.
Essa, I.A. and Pentland, A.P. 1997. Coding, analysis, interpretation and recognition of facial expressions. IEEE Transactions on Pattern Recognition and Machine Intelligence, 19:757–763.
Ezzat, T. and Poggio, T. 1999. Visual speech synthesis by morphing visemes. Technical Report 1658, Massachusetts Institute of Technology, Cambridge, MA.
Gavrila, D.M. 1999. The visual analysis of human movement: A survey. Computer Vision and Image Understanding, 73:82–98.
Giese, M.A. and Poggio, T. 1999. Synthesis and recognition of biological motion patterns based on linear superposition of prototypical motion sequences. In Proceedings of the MVIEW 99 Symposium at CVPR, Fort Collins, CO, IEEE (Ed.), IEEE Computer Society, Los Alamitos, pp. 73–80.
Girosi, F., Jones, M., and Poggio, T. 1995. Regularization theory and neural network architectures. Neural Computation, 7:219–269.
Jones, M. and Pogio, T. 1997. Model-based matching by linear combinations of prototypes. In Proceedings of the DARPA Image Understanding Workshop, New Orleans, LA, pp. 1357–1365.
Jones, M.J. 1997. Multidimensional morphable models: A framework for representing and matching object classes. Ph.D. Thesis, Massachusetts Institute of Technology, Cambridge, MA.
Lee, J. and Shin, S.Y. 1999. A hierarchical approach to interactive motion editiong for human-like figures. In Proceedings of SIGGRAPH 99, Los Angeles, pp. 39–48.
Niyogi, S.A. and Adelson, E.H. 1994. Analyzing and recognizing walking figures in XYT. Technical Report 223, Massachusetts Institute of Technology, Cambridge, MA.
O'Rourke, J. and Badler, N.I. 1982. Model-based analysis of human motion using constraint propagation. IEEE Transactions on Pattern Recognition and Machine Intelligence, 2:522–536.
Poggio, T. and Edelman, S. 1990. A network that learns to recognize three-dimensional objects. Nature, 343:263–266.
Rabiner, L. and Juang, B.H. 1993. Fundamentals of Speech Recognition. Prentice-Hall: Englewood Cliffs, NJ.
Shelton, C.R. 1998. Three-dimensional correspondence. Master's Thesis, Dept. of Computer Science, Cambridge, MA.
Starner, T. and Pentland, A.P. 1995. Recognition of American sign language using hidden Markov models. In Proceeding of International Workshop on Automatic Face and Gesture Recognition. IEEE Press, Los Alamitos, pp. 265–270.
Takahashi, K., Seki, S., Kojima, H., and Oka, R. 1994. Recognition of dexterous manipulations from time-varying images. In Proceedings of the Workshop on Motion of Non-Rigid and Articulated Objects, IEEE Computer Society, Los Alamitos CA, pp. 23–28.
Ullman, S. and Basri, R. 1991. Recognition by linear combination of models. IEEE Transactions on Pattern Recognition and Machine Intelligence, 13:992–1006.
Vapnik, V.N. 1998. Statistical Learning Theory. Wiley: New York.
Vetter, T. 1998. Synthesis of novel views from a single face image. International Journal of Computer Vision, 28(2):103–116.
Vetter, T. and Poggio, T. 1995. Linear object classes and image synthesis from a single example image. Technical Report 1531, Massachusetts Institute of Technology, Cambridge, MA.
Vetter, T. and Poggio, T. 1997. Linear object classes and image synthesis from a single example. IEEE Transactions on Pattern Recognition and Machine Intelligence, 19(7):733–742.
Wren, C., Azarbayejani, A., Darrell, T., and Pantland, A. 1997. Real-time tracking of a human body. IEEE Transactions on Pattern Recognition and Machine Intelligence, 19:780–785.
Yacoob, Y. and Black, M.J. 1999. Parameterized modeling and recognition of activities. Computer Vision and Image Understanding, 73(2):232–247.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Giese, M.A., Poggio, T. Morphable Models for the Analysis and Synthesis of Complex Motion Patterns. International Journal of Computer Vision 38, 59–73 (2000). https://doi.org/10.1023/A:1008118801668
Issue Date:
DOI: https://doi.org/10.1023/A:1008118801668