Space-Time Pose Representation for 3D Human Action Recognition

  • Maxime Devanne
  • Hazem Wannous
  • Stefano Berretti
  • Pietro Pala
  • Mohamed Daoudi
  • Alberto Del Bimbo
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8158)

Abstract

3D human action recognition is an important current challenge at the heart of many research areas lying to the modeling of the spatio-temporal information. In this paper, we propose representing human actions using spatio-temporal motion trajectories. In the proposed approach, each trajectory consists of one motion channel corresponding to the evolution of the 3D position of all joint coordinates within frames of action sequence. Action recognition is achieved through a shape trajectory representation that is learnt by a K-NN classifier, which takes benefit from Riemannian geometry in an open curve shape space. Experiments on the MSR Action 3D and UTKinect human action datasets show that, in comparison to state-of-the-art methods, the proposed approach obtains promising results that show the potential of our approach.

Keywords

3D human action activity recognition temporal modeling 

References

  1. 1.
    Abdelkader, M.F., Abd-Almageed, W., Srivastava, A., Chellappa, R.: Silhouette-based gesture and action recognition via modeling trajectories on riemannian shape manifolds. Computer Vision and Image Understanding 115(3), 439–455 (2011)CrossRefGoogle Scholar
  2. 2.
    Cheng, Z., Qin, L., Ye, Y., Huang, Q., Tian, Q.: Human daily action analysis with multi-view and color-depth data. In: Proc. of Work. on Consumer Depth Cameras for Computer Vision, Florence, Italy, pp. 52–61 (October 2012)Google Scholar
  3. 3.
    Joshi, S.H., Klassen, E., Srivastava, A., Jermyn, I.: A novel representation for riemannian analysis of elastic curves in rn. In: Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern. Recognit., July 16 (2007)Google Scholar
  4. 4.
    Li, W., Zhang, Z., Liu, Z.: Action recognition based on a bag of 3D points. In: Proc. of Work. on Human Communicative Behavior Analysis, San Francisco, California, USA, pp. 9–14 (June 2010)Google Scholar
  5. 5.
    Shotton, J., Fitzgibbon, A., Cook, M., Sharp, T., Finocchio, M., Moore, R., Kipman, A., Blake, A.: Real-time human pose recognition in parts from single depth images. In: Proc. of IEEE Conf. on Computer Vision and Pattern Recognition, Colorado Springs, Colorado, USA, pp. 1–8 (June 2011)Google Scholar
  6. 6.
    Slama, R., Wannous, H., Daoudi, M.: Extremal human curves: a new human body shape and pose descriptor. In: 10th IEEE International Conference on Automatic Face and Gesture Recognition, Shanghai (2013)Google Scholar
  7. 7.
    Srivastava, A., Klassen, E., Joshi, S.H., Jermyn, I.: Shape analysis of elastic curves in euclidean spaces. IEEE Trans. Pattern Anal. Mach. Intell. 33, 1415–1428 (2011)CrossRefGoogle Scholar
  8. 8.
    Turaga, P., Veeraraghavan, A., Srivastava, A., Chellappa, R.: Statistical computations on grassmann and stiefel manifolds for image and video-based recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence 33(11), 2273–2286 (2011)CrossRefGoogle Scholar
  9. 9.
    Vieira, A.W., Nascimento, E.R., Oliveira, G.L., Liu, Z., Campos, M.F.: Stop: Space-time occupancy patterns for 3d action recognition from depth map sequences. In: 17th Iberoamerican Congress on Pattern Recognition, Buenos Airies (2012)Google Scholar
  10. 10.
    Wang, J., Liu, Z., Chorowski, J., Chen, Z., Wu, Y.: Robust 3D action recognition with random occupancy patterns. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part II. LNCS, vol. 7573, pp. 872–885. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  11. 11.
    Wang, J., Liu, Z., Wu, Y., Yuan, J.: Mining actionlet ensemble for action recognition with depth cameras. In: Proc. of IEEE Conf. on Computer Vision and Pattern Recognition, Providence, Rhode Island, USA, pp. 1–8 (June 2012)Google Scholar
  12. 12.
    Xia, L., Chen, C.C., Aggarwal, J.K.: View invariant human action recognition using histograms of 3D joints. In: Proc. of Work. on Human Activity Understanding from 3D Data, Providence, Rhode Island, USA, pp. 20–27 (June 2012)Google Scholar
  13. 13.
    Yang, X., Tian, Y.: Eigenjoints-based action recognition using naive-bayes-nearest-neighbor. In: Proc. of Work. on Human Activity Understanding from 3D Data, Providence, Rhode Island, USA, pp. 14–19 (June 2012)Google Scholar
  14. 14.
    Yang, X., Zhang, C., Tian, Y.: Recognizing actions using depth motion maps-based histograms of oriented gradients. In: Proc. of ACM Int. Conf. on Multimedia, Nara, Japan, pp. 1057–1060 (October 2012)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Maxime Devanne
    • 1
    • 2
    • 3
  • Hazem Wannous
    • 1
  • Stefano Berretti
    • 3
  • Pietro Pala
    • 3
  • Mohamed Daoudi
    • 2
  • Alberto Del Bimbo
    • 3
  1. 1.University of Lille 1 - LIFL (UMR Lille1/CNRS 8022)France
  2. 2.Institut Mines-TelecomFrance
  3. 3.University of FirenzeFrance

Personalised recommendations