This Article 
 Bibliographic References 
 Add to: 
Semantic Representation and Correspondence for State-Based Motion Transition
October-December 2003 (vol. 9 no. 4)
pp. 481-499

Abstract—Consistent transition algorithms preserve salient source motion features by establishing feature-based correspondence between motions and accordingly warping them before interpolation. These processes are commonly dubbed as preprocessing in motion transition literature. Current transition methods suffer from a lack of economical and generic preprocessing algorithms. Classical computer vision methods for human motion classification and correspondence are too computationally intensive for computer animation. This paper proposes an analytical framework that combines low-level kinematics analysis and high-level knowledge-based analysis to create states that provide coherent snapshots of body-parts active during the motion. These states are then corresponded via a globally optimal search tree algorithm. The framework proposed here is intuitive, controllable, and delivers results in near real-time. The validity and performance of the proposed system are tangibly proven with extensive experiments.

[1] J.K. Aggarwal and Q. Cai, Human Motion Analysis: A Review Proc. Computer Vision and Image Understanding, pp. 428-440, 1999.
[2] G. Ashraf, Demonstrating Semantic Classification and Correspondence for State-Based Motion Transition http://www.cgit. , 2000.
[3] G. Ashraf and K.C. Wong, Generating Consistent Motion Transition via Framespace Interpolation Eurographics, Computer Graphics Forum, vol. 19, no. 3, pp. 447-456, Aug. 2000.
[4] G. Ashraf and K.C. Wong, Constrained Framespace Interpolation Proc. Computer Animation 2001, pp. 61-72, Nov. 2001.
[5] R. Bindiganavale and N.I. Badler, Motion Abstraction and Mapping with Spatial Constraints Modelling&Motion Capture Techniques for Virtual Environment, CAPTECH '98 Proc., pp. 70-82, 1998.
[6] R. Boulic, N. Magnenat-Thalmann, and D. Thalmann, Human Free-Walking Model for a Real-Time Interactive Design of Gaits Proc. Computer Animation '90, pp. 61-81, 1990.
[7] M. Brand and A. Hertzmann, Style Machines Proc. SIGGRAPH 2000, pp. 183-192, Aug. 2000.
[8] A. Bruderlin, Procedural Motion Control Techniques for Interactive Animation of Human Figures PhD thesis, School of Computer Science, Simon Fraser Univ., Mar. 1995.
[9] A. Bruderlin and L. Williams, Motion Signal Processing Proc. SIGGRAPH '95, pp. 97-104, Aug. 1995.
[10] M. Gleicher and P. Litwinowicz, Constraint-Based Motion Adaptation J. Visualization and Computer Animation, vol. 9, no. 2, pp. 65-94, 1998.
[11] H. Gray, P.L. Williams, and L.H. Bannister, Gray's Anatomy: The Anatomical Basis of Medicine and Surgery. New York: Churchill Livingstone, 1995.
[12] S. Guo and J. Roberge, A High-Level control Mechanism for Human Locomotion Based on Parametric Frame Space Interpolation Proc. Eurographics Computer Animation and Simulation (EGCAS '96), pp. 95-107, 1996.
[13] Y. Kang and E. Lee, An Efficient Control over Human Running Animation with Extension of Planar Hopper Model Proc. Pacific Graphics '98, Sixth Pacific Conf. Computer Graphics and Applications, pp. 169-176, Oct. 1998.
[14] A. Lees and T. Green, An Analysis of Muscles Acting in the Forearm during Two Different Arm Curl Exercises Inst. of Mechanical Engineers, Mechanical Eng. Publications, pp. 65-70, July 1988.
[15] Y. Luo, Handling Motion Processing Constraints for Articulated Figure Animation master's thesis, School of Computer Science, Simon Fraser Univ., Nov. 1997.
[16] R. Maiocchi, A Knowledge-Based approach to the synthesis of Human Motion Proc. IFIP Conf. Graphics Modeling, pp. 157-178, 1991.
[17] K. Perlin, Real Time Responsive Animation with Personality IEEE Trans. Visualization and Computer Graphics, vol. 1, no. 1, pp. 5-15, Mar. 1995.
[18] W. Press, S. Teukolsky, W. Vellering, and B. Flannery, Numerical Recipes In C. Cambridge Univ. Press, 1992.
[19] C. Rose, M.F. Cohen, and B. Bodenheimer, Verbs and Adverbs: Multidimensional Motion Interpolation IEEE Computer Graphics and Applications, vol. 18, no. 5, pp. 32-40, Sept./Oct. 1998.
[20] C. Rose et al., "Efficient Generation of Motion Transitions Using Spacetime Constraints," Proc. Siggraph 96, ACM Press, New York, 1996, pp. 147-154.
[21] T.W. Sederberg and E. Greenwood, A Physically Based Approach to 2D Shape Blending Proc. SIGGRAPH '92, pp. 25-34, July 1992.
[22] H.C. Sun and D.N. Metaxas, Automating Gait Generation Proc. SIGGRAPH '01, pp. 261-270, 2001.
[23] J.B. Tenebaum and W.T. Freeman, Separating Style and Content with Bilinear Models Neural Computation, vol. 12, pp. 1247-1283, 2000.
[24] A. Wilson and A.F. Bobick, "Parametric Hidden Markov Models for Gesture Recognition," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 21, no. 9, 1999, pp. 884—900.
[25] V. Zordan and J. Hodgins, Tracking and Modifying Upper-Body Human Motion Data with Dynamic Simulation Proc. Computer Animation and Simulation '99, pp. 13-22, Sept. 1999.

Index Terms:
Computer animation, representation, correspondence, consistent interpolation, motion transition.
Golam Ashraf, Kok Cheong Wong, "Semantic Representation and Correspondence for State-Based Motion Transition," IEEE Transactions on Visualization and Computer Graphics, vol. 9, no. 4, pp. 481-499, Oct.-Dec. 2003, doi:10.1109/TVCG.2003.1260743
Usage of this product signifies your acceptance of the Terms of Use.