Advertisement

Quaternion Watershed Transform in Segmentation of Motion Capture Data

  • Adam ŚwitońskiEmail author
  • Agnieszka Michalczuk
  • Henryk Josiński
  • Konrad Wojciechowski
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11432)

Abstract

The novel approach for segmentation of motion capture data is proposed. It utilizes hierarchical watershed transform for time series containing unit quaternions which describe rotations of human skeleton joints as well as their angular velocities. To approximate gradient magnitudes of subsequent time instants, aggregated geodesic distance on hypersphere \(S^3\) for preceding and following quaternions is computed. The introduced segmentation method was applied to gait analysis. The highly precise motion capture data, registered in a human motion lab (HML), were used. A fully automatic watershed transform with detection of catchment basins as well as a marker controlled one were investigated. The obtained results are promising. By selecting proper hierarchy of a segmentation or by specifying adequate markers, it is even feasible to divide gait cycle into consecutive steps. The segmentation can be improved in respect to a considered problem, if only selected joints are taken into account by watershed transform.

Keywords

Motion capture Watershed transform Motion segmentation Gait analysis Unit quaternions 

Notes

Acknowledgments

The work was supported by Silesian University of Technology, Institute of Informatics under statute project BK/RAU2/2018.

References

  1. 1.
    Aoki, T., Venture, G., Kulic, D.: Segmentation of human body movement using inertial measurement unit. In: IEEE International Conference on Systems, Man, and Cybernetics (SMC), pp. 1181–1186. IEEE (2013)Google Scholar
  2. 2.
    Arikan, O., Forsyth, D.A., O’Brien, J.F.: Motion synthesis from annotations. In: ACM Transactions on Graphics (TOG), vol. 22, pp. 402–408. ACM (2003)Google Scholar
  3. 3.
    Arn, R., Narayana, P., Draper, B., Emerson, T., Kirby, M., Peterson, C.: Motion segmentation via generalized curvatures. IEEE Trans. Pattern Anal. Mach. Intell. (2018)Google Scholar
  4. 4.
    Barbič, J., Safonova, A., Pan, J.Y., Faloutsos, C., Hodgins, J.K., Pollard, N.S.: Segmenting motion capture data into distinct behaviors. In: Proceedings of Graphics Interface 2004, pp. 185–194. Canadian Human-Computer Communications Society (2004)Google Scholar
  5. 5.
    Beucher, S.: Use of watersheds in contour detection. In: Proceedings of the International Workshop on Image Processing. CCETT (1979)Google Scholar
  6. 6.
    Beucher, S.: Watershed, hierarchical segmentation and waterfall algorithm. In: Serra, J., Soille, P. (eds.) Mathematical Morphology and Its Applications to Image Processing, pp. 69–76. Springer, Dordrecht (1994).  https://doi.org/10.1007/978-94-011-1040-2_10CrossRefGoogle Scholar
  7. 7.
    Beucher, S., Meyer, F.: The Morphological Approach to Segmentation: The Watershed Transformation, Mathematical Morphology in Image Processing, pp. 433–481. Marcel Dekker Inc., New York (1992)Google Scholar
  8. 8.
    Bouchard, D., Badler, N.: Semantic segmentation of motion capture using Laban Movement Analysis. In: Pelachaud, C., Martin, J.-C., André, E., Chollet, G., Karpouzis, K., Pelé, D. (eds.) IVA 2007. LNCS (LNAI), vol. 4722, pp. 37–44. Springer, Heidelberg (2007).  https://doi.org/10.1007/978-3-540-74997-4_4CrossRefGoogle Scholar
  9. 9.
    Ciecholewski, M.: River channel segmentation in polarimetric SAR images: watershed transform combined with average contrast maximisation. Expert Syst. Appl. 82, 196–215 (2017)CrossRefGoogle Scholar
  10. 10.
    Huynh, H.T., Le-Trong, N., Oto, A., Suzuki, K., et al.: Fully automated MR liver volumetry using watershed segmentation coupled with active contouring. Int. J. Comput. Assist. Radiol. Surg. 12(2), 235–243 (2017)CrossRefGoogle Scholar
  11. 11.
    Lin, J.F.S., Joukov, V., Kulic, D.: Human motion segmentation by data point classification. In: 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pp. 9–13. IEEE (2014)Google Scholar
  12. 12.
    Lin, J.F.S., Kulic, D.: Online segmentation of human motion for automated rehabilitation exercise analysis. IEEE Trans. Neural Syst. Rehabil. Eng. 22(1), 168–180 (2014)CrossRefGoogle Scholar
  13. 13.
    Switonski, A., Josinski, H., Wojciechowski, K.: Dynamic time warping in classification and selection of motion capture data. In: Multidimensional Systems and Signal Processing, pp. 1–32 (2018)Google Scholar
  14. 14.
    Szczesna, A., Switonski, A., Slupik, J., Zghidi, H., Josinski, H., Wojciechowski, K.: Quaternion lifting scheme applied to the classification of motion data. Inf. Sci. (2018)Google Scholar
  15. 15.
    Wisaeng, K., Sa-ngiamvibool, W.: Automatic detection and recognition of optic disk with maker-controlled watershed segmentation and mathematical morphology in color retinal images. Soft Comput. 22, 6329 (2018).  https://doi.org/10.1007/s00500-017-2681-9CrossRefGoogle Scholar
  16. 16.
    Wu, Z., Liu, W., Xing, W.: A novel method for human motion capture data segmentation. In: IEEE 15th International Conference on Dependable, Autonomic and Secure Computing, 15th International Conference on Pervasive Intelligence & Computing, 3rd International Conference on Big Data Intelligence and Computing and Cyber Science and Technology Congress (DASC/PiCom/DataCom/CyberSciTech), pp. 780–787. IEEE (2017)Google Scholar
  17. 17.
    Xie, X., Liu, R., Zhou, D., Wei, X., Zhang, Q.: Segmentation of human motion capture data based on Laplasse eigenmaps. In: Chen, H., Zeng, D.D., Karahanna, E., Bardhan, I. (eds.) ICSH 2017. LNCS, vol. 10347, pp. 134–145. Springer, Cham (2017).  https://doi.org/10.1007/978-3-319-67964-8_13CrossRefGoogle Scholar
  18. 18.
    Yang, Y., Chen, J., Liu, Z., Zhan, Y., Wang, X.: Low level segmentation of motion capture data based on hierarchical clustering with cosine distance. Int. J. Database Theor. Appl. 8(4), 231–240 (2015)CrossRefGoogle Scholar
  19. 19.
    Yang, Y., Shum, H.P., Aslam, N., Zeng, L.: Temporal clustering of motion capture data with optimal partitioning. In: Proceedings of the 15th ACM SIGGRAPH Conference on Virtual-Reality Continuum and Its Applications in Industry-Volume 1, pp. 479–482. ACM (2016)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Adam Świtoński
    • 1
    Email author
  • Agnieszka Michalczuk
    • 1
  • Henryk Josiński
    • 1
  • Konrad Wojciechowski
    • 2
  1. 1.Institute of InformaticsSilesian University of TechnologyGliwicePoland
  2. 2.Research and Development CenterPolish-Japanese Academy of Information TechnologyBytomPoland

Personalised recommendations