BUILDING LOCAL K-D TREE FOR FLEXIBLY LABELING ARTICULATED POINT SETS

Wu Huang, Shihong Xia

2011

Abstract

Optical motion capture system is widely used to acquire human motions by capturing the trajectories of markers that are attached to the body. Identifying the marker trajectories is challenging but indispensable in most of real applications. Conventional methods rely on either labor-intensive manually labeling or auto-labeling with assumption of pose similarity to the topological model. This paper presents a novel method to flexibly label markers from human motion capture sequences. The point sets in a rigid segment defined in the topological model are firstly clustered by using the spectral clustering algorithm. For each rigid segment, a local k-d tree is constructed to robustly match two point sets without pose similarity assumption. To match all rigid bodies with those in topological model for efficiently and correctly labeling, the labeling process is carefully designed using the articulated structure of acquired data. Experiments show that our method outperforms conventional methods in accuracy and is robust when labeling markers in motion capture sequences from different subjects.

References

  1. Aguiar, E. D., Theobalt, C., and Seidel, H.-P. (2006). Automatic learning of articulated skeletons from 3d marker trajectories. International Symposium on Visual Computing, 1:485-494.
  2. Arun, K., Huang, T., and Blostein, S. (1987). Least-squares fitting of two 3-D point sets. IEEE Transactions on Pattern Analysis and Machine Intelligence, 9(5):698- 700.
  3. Bentley, J. L. (1975). Multidimensional binary search trees used for associative searching. Communications of the ACM, 18:509-517.
  4. Bentley, J. L. (1990). K-d trees for semidynamic point sets. In Proc.6th Ann. ACM Symp. on Computational Geometry, pages 187-197.
  5. CMU, G. L. (2009). http://mocap.cs.cmu.edu.
  6. Gaede, V. and Gnther, O. (1998). Multidimensional access methods. J. of Computer Surveys, 30(2):170-231.
  7. Gleicher, M. (1999). Animation from observation: Motion capture and modtion editing. Computer Graphics, 33(4):51-55.
  8. Guerra-Filho, G. (2005). Optical motion capture: Theory and implementation. J. of Theoretical and Applied Informatics, 12(2):61-90.
  9. Hornung, A., Sar-Dessai, S., and Kobbelt, L. (2005). Skeletal parameter estimation from optical motion capture data. In VR'05,In: Proceedings of the IEEE Virtual Reality Conference, pages 75-82. IEEE.
  10. Kirk, A. G., O'Brien, J. F., and Forsyth, D. A. (2005). Skeletal parameter estimation from optical motion capture data. In CVPR'05,In: Proceedings of the 18th IEEE Conference on Computer Vision and Pattern Recognition. IEEE.
  11. Li, B., Meng, Q., and Holstein, H. (2003). Point pattern matching and applicationsla review. In SMC'03,In: Proceedings of the IEEE International Conference on Systems,Man and Cybernetics.
  12. Li, B., Meng, Q., and Holstein, H. (2004). Articulated pose identification with sparse point features. IEEE Transactions on Systems, Man, and Cybernetics PartB, 34(3):1412-1422.
  13. Li, B., Meng, Q., and Holstein, H. (2005). Similarity k-d tree method for sparse point pattern matching with underlying non-rigidity. Pattern Recognition, 38(12):2391-2399.
  14. Li, B., Meng, Q., and Holstein, H. (2008). Articulated motion reconstruction from feature points. Pattern Recognition, 41(1):418-431.
  15. Mount, D., Netanyahu, N., and Moigne, J. (1999). Efficient algorithms for robust feature matching. Pattern Recognition, 32:17-38.
  16. Ng, A. Y., Jordan, M. I., and Y.Weiss (2001). On spectral clustering: Analysis and an algorithm. In NIPS'01,In: Proceedings of the 15th Advances in Neural Information Processing Systems, pages 849-856. MIT Press.
  17. OMG (2009). Motion capture systems from vicon. http://www.vicon.com/.
  18. Wolfson, H. and Rigoutsos, I. (1997). Geometric hashing: an overview. IEEE Transactions on Computational Science and Engineering, 4(4):10-21.
  19. Yu, Q., Li, Q., and Deng, Z. (2007). Online motion capture marker labeling for multiple interacting articulated targets. Computer Graphics Forum (Proceedings of Eurographics 2007), 26(3):477-483.
  20. Zelnik-manor, L. and Perona, P. (2004). Self-tuning spectral clustering. In Advances in Neural Information Processing Systems 17, pages 1601-1608. MIT Press.
Download


Paper Citation


in Harvard Style

Huang W. and Xia S. (2011). BUILDING LOCAL K-D TREE FOR FLEXIBLY LABELING ARTICULATED POINT SETS . In Proceedings of the International Conference on Biomedical Electronics and Devices - Volume 1: BIODEVICES, (BIOSTEC 2011) ISBN 978-989-8425-37-9, pages 288-294. DOI: 10.5220/0003299802880294


in Bibtex Style

@conference{biodevices11,
author={Wu Huang and Shihong Xia},
title={BUILDING LOCAL K-D TREE FOR FLEXIBLY LABELING ARTICULATED POINT SETS},
booktitle={Proceedings of the International Conference on Biomedical Electronics and Devices - Volume 1: BIODEVICES, (BIOSTEC 2011)},
year={2011},
pages={288-294},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0003299802880294},
isbn={978-989-8425-37-9},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Biomedical Electronics and Devices - Volume 1: BIODEVICES, (BIOSTEC 2011)
TI - BUILDING LOCAL K-D TREE FOR FLEXIBLY LABELING ARTICULATED POINT SETS
SN - 978-989-8425-37-9
AU - Huang W.
AU - Xia S.
PY - 2011
SP - 288
EP - 294
DO - 10.5220/0003299802880294