The Bag of Micro-Movements for Human Activity Recognition

  • Pejman HabashiEmail author
  • Boubakeur Boufama
  • Imran Shafiq Ahmad
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9164)


The bag of words is a popular and successful method for human activity recognition. This method usually uses visual based sparse features for activity classification. It is also known that movement has useful clues for activity detection, but sparse features usually miss this vital piece of information. Two-dimensional image planar motion information is easy to extract but it is very dependant on depth and calibration parameters. Three-dimensional motion is rich in information and can be calculated from active cameras or multiple passive cameras, but it restricts the applicability of the method. To overcome these issues, we have proposed the use of disparity maps, which are relatively easy to extract from stereo videos and are more informative than 2D image planar motion information. In this work, we have combined the motion information and disparity maps to introduce a new sparse feature descriptor that encodes motion information, instead of visual information.


Micro-movements Feature descriptor Motion-based descriptor Human Activity Recognition Machine vision 


  1. 1.
    Campbell, L.W., Bobick, A.F.: Recognition of human body motion using phase space constraints. In: Fifth International Conference on Computer Vision, Proceedings, pp. 624–630. IEEE (1995)Google Scholar
  2. 2.
    Rao, C., Shah, M.: View-invariance in action recognition. In: Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2001, vol. 2, pp. II–316. IEEE (2001)Google Scholar
  3. 3.
    Dollár, P., Rabaud, V., Cottrell, G., Belongie, S.: Behavior recognition via sparse spatio-temporal features. In: 2nd Joint IEEE International Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance 2005, pp. 65–72. IEEE (2005)Google Scholar
  4. 4.
    Sheikh, Y., Sheikh, M., Shah, M.: Exploring the space of a human action. In: Tenth IEEE International Conference on Computer Vision, ICCV 2005, vol. 1, pp. 144–149. IEEE (2005)Google Scholar
  5. 5.
    Yilmaz, A., Shah, M.: Actions sketch: A novel action representation. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005, vol. 1, pp. 984–989. IEEE (2005)Google Scholar
  6. 6.
    Yilmaz, A., Shah, M.: Recognizing human actions in videos acquired by uncalibrated moving cameras. In: Tenth IEEE International Conference on Computer Vision, ICCV 2005, vol. 1, pp. 150–157. IEEE (2005)Google Scholar
  7. 7.
    Bobick, A.F., Davis, J.W.: The recognition of human movement using temporal templates. IEEE Trans. Pattern Anal. Mach. Intel. 23(3), 257–267 (2001)CrossRefGoogle Scholar
  8. 8.
    Blank, M., Gorelick, L., Shechtman, E., Irani, M., Basri, R.: Actions as space-time shapes. In: Tenth IEEE International Conference on Computer Vision, ICCV 2005, vol. 2, pp. 1395–1402. IEEE (2005)Google Scholar
  9. 9.
    Laptev, I.: On space-time interest points. Int. J. Comput. Vis. 64(2–3), 107–123 (2005)CrossRefGoogle Scholar
  10. 10.
    Laptev, I., Marszalek, M., Schmid, C., Rozenfeld, C.: Learning realistic human actions from movies. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2008, pp. 1–8. IEEE (2008)Google Scholar
  11. 11.
    Uddin, M.Z., Thang, N.D., Kim, J.T., Kim, T.-S.: Human activity recognition using body joint-angle features and hidden markov model. Etri J. 33(4), 569–579 (2011)CrossRefGoogle Scholar
  12. 12.
    Barnachon, M., Bouakaz, S., Boufama, B., Guillou, E.: Human actions recognition from streamed motion capture. In: 2012 21st International Conference on Pattern Recognition (ICPR), pp. 3807–3810. IEEE (2012)Google Scholar
  13. 13.
    Wang, H., Kläser, A., Schmid, C., Liu, C.-L.: Dense trajectories and motion boundary descriptors for action recognition. Int. J. Comput. Vis. 103(1), 60–79 (2013)MathSciNetCrossRefGoogle Scholar
  14. 14.
    Wang, H., Schmid, C.: Action recognition with improved trajectories. In: 2013 IEEE International Conference on Computer Vision (ICCV), pp. 3551–3558. IEEE (2013)Google Scholar
  15. 15.
    Diaf, A.A.: Eigenvector-based dimensionality reduction for human activity recognition and data classification. Ph.D. thesis, University of Windsor (2013)Google Scholar
  16. 16.
    Barnachon, M., Bouakaz, S., Boufama, B., Guillou, E.: Ongoing human action recognition with motion capture. Pattern Recog. 47(1), 238–247 (2014)CrossRefGoogle Scholar
  17. 17.
    Niebles, J.C., Wang, H., Fei-Fei, L.: Unsupervised learning of human action categories using spatial-temporal words. Int. J. Comput. Vis. 79(3), 299–318 (2008)CrossRefGoogle Scholar
  18. 18.
    Willems, G., Tuytelaars, T., Van Gool, L.: An efficient dense and scale-invariant spatio-temporal interest point detector. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part II. LNCS, vol. 5303, pp. 650–663. Springer, Heidelberg (2008) CrossRefGoogle Scholar
  19. 19.
    Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 60(2), 91–110 (2004)CrossRefGoogle Scholar
  20. 20.
    Wang, H., Klaser, A., Schmid, C., Liu, C.-L.: Action recognition by dense trajectories. In: 2011 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3169–3176. IEEE (2011)Google Scholar
  21. 21.
    Kang, Y.-S., Ho, Y.-S.: Efficient stereo image rectification method using horizontal baseline. In: Ho, Y.-S. (ed.) PSIVT 2011, Part I. LNCS, vol. 7087, pp. 301–310. Springer, Heidelberg (2011) CrossRefGoogle Scholar
  22. 22.
    Rosten, E., Drummond, T.W.: Machine learning for high-speed corner detection. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006, Part I. LNCS, vol. 3951, pp. 430–443. Springer, Heidelberg (2006) CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  • Pejman Habashi
    • 1
    Email author
  • Boubakeur Boufama
    • 1
  • Imran Shafiq Ahmad
    • 1
  1. 1.Computer Science DepartmentUniversity of WindsorOntarioCanada

Personalised recommendations