Real-time interactive motion transitions by a uniform posture map

Abstract

Motion transition is a useful method for reusing existing motion data. It generates a seamless intermediate motion with two short motion sequences. In this paper, the Uniform Posture Map (UPM) is proposed to perform motion transitions. The UPM is organized through the quantization of various postures with an unsupervised learning algorithm; it places the output neurons with similar postures in adjacent positions. Using this property, an intermediate posture of two applied postures is generated; the generating posture is used as a key-frame to make an interpolating motion. The UPM has lower computational costs in comparison with other motion transition algorithms. It provides a control parameter; an animator can not only control the motion simply by adjusting this parameter, but can also produce animation interactively. The UPM prevents the generating of invalid output neurons to present unrealistic postures in the learning phase; thus, it makes more realistic motion curves. Finally, it contributes to the making of more natural motions. The motion transition algorithm proposed in this paper can be applied to various fields such as real-time 3D games, virtual reality applications, and web 3D applications.

References

1. [1] Sun, H.C. and Metaxas, D.N., Automating gait generation. In: Proceedings of the SIGGRAPH 2001, ACM Press. pp. 261-270.
2. [2] Shin, H.J., Lee, J., Shin, S.Y. and Gleicher, M., Computer puppetry, ACM Trans. Graphics. v20 i2. 67-94.
3. [3] Brand, M. and Hertzmann, A., Style machine. In: Proceedings of the SIGGRAPH 2000, ACM Press. pp. 183-192.
4. [4] Sannier, G., Balcisoy, S., Thalmann, N.M. and Thalmann, D., A system for directing real-time virtual actors. The Visual Computer. v15 i78. 320-329.
5. [5] Popović, Z., Controlling physics in realistic character animation. Commun. ACM. v43 i7. 50-58.
6. [6] Noser, H. and Thalmann, D., A rule-based interactive behavioral animation system for humanoids. IEEE Trans. Visualization Comput. Graphics. v5 i4. 281-307.
7. [7] Wiley, D.J. and Hahn, J.K., Interpolation synthesis of articulated figure motion. IEEE Comput. Graphics Appl. v17 i6. 39-45.
8. [8] S.K. Jung, Motion analysis of articulated objects for optical motion capture, Ph.D. Dissertation, KAIST, Department of Computer Science, 1997.
9. [9] Brudelin, A. and Williams, L., Motion signal processing. In: Proceedings of the SIGGRAPH'95, ACM Press. pp. 97
10. [10] Witkin, A. and Popović, Z., Motion warping. In: Proceedings of the SIGGRAPH'95, ACM Press. pp. 105-108.
11. [11] Rose, C., Bodenheimer, B. and Cohen, M.F., Verbs and adverbs: multidimensional motion interpolation. IEEE Comput. Graphics Appl. v18 i5. 32-40.
12. [12] Zhao, J. and Badler, N.I., Inverse kinematics positioning using nonlinear programming for highly articulated figures. ACM Trans. Graphics. v13 i4. 313-336.
13. [13] Lee, J. and Shin, S.Y., A hierarchical approach to interactive motion editing for human-like figures. In: Proceedings of the SIGGRAPH'99, ACM Press.
14. [14] Gleicher, M., Motion editing with spacetime constraints. In: Proceedings of the Symposium on Interactive 3D Graphics, pp. 139-148.
15. [15] Grzeszczuk, R., Terzopoulos, D. and Hinton, G., Neuro animator: fast neural emulation and control of physics-based models. In: Proceedings of the SIGGRAPH'98, ACM Press. pp. 9-20.
16. [16] Rose, C., Guenter, B., Bodenheimer, B. and Cohen, M.F., Efficient generation of motion transitions using spacetime constraints. In: Proceedings of the SIGGRAPH'96, ACM Press. pp. 147-154.
17. [17] Cohen, M.F., Interactive spacetime control for animation. In: Proceedings of the SIGGRAPH'92, ACM Press. pp. 293-302.
18. [18] Kohonen, T., Huang, T.S. and Schroeder, M.R., Self-organizing Maps. 2000. 3rd ed. Springer-Verlag.
19. [19] Gallant, S.I., Neural Network Learning and Expert System. 1993. MIT Press, Cambridge, MA.
20. [20] Ritter, H., Martinetz, T. and Schulten, K., Neural Computation and Self-organizing Maps. 1992. Addison-Wesley, New York.
21. [21] Fritzke, B., Growing cell structures-a self-organizing network for unsupervised and supervised learning. Neural Netw. v7 i9. 1441-1460.
22. [22] Martinetz, T.M., Berkovich, S.G. and Schulten, K.J., Neural-gas network for vector quantization and its application to time-series prediction. IEEE Trans. Neural Netw. v4. 558-568.
23. [23] Baraldi, A. and Alpaydin, E., Constructive feedforward art clustering networks. IEEE Trans. Neural Netw. v13 i3. 662

Index Terms

• Computer systems organization

  • Architectures

    • Other architectures

      • Neural networks

  • Embedded and cyber-physical systems

    • Embedded systems

• Computing methodologies

  • Artificial intelligence

    • Computer vision

      • Image and video acquisition

        • Motion capture

  • Computer graphics

    • Animation

      • Motion capture

      • Motion processing

• Human-centered computing

  • Human computer interaction (HCI)

    • Interactive systems and tools

• Software and its engineering

  • Software organization and properties

    • Software system structures

      • Embedded software

      • Real-time systems software