Skip to main content

Advertisement

SpringerLink
Log in

Convex Deficiencies for Human Action Recognition

  • Published:
Journal of Intelligent & Robotic Systems Aims and scope Submit manuscript

Abstract

A human action can be identified by visualizing the sequence of 2D binary projections over time. Here, one of the most representative features is shape and a wide range of algorithms have been proposed using its descriptors. This paper proposes convex deficiencies, the difference between an object and its convex hull, to be considered as a representation for the human action classification problem. A simple description using the centroids of the convex deficiencies over time is presented. Recognition of human actions is done with a fast matching algorithm that considers the spatial distribution of the centroid trajectories and the shape of the clusters in its 2D projection. The proposed representation is robust to deformations, scale, speed of the performed action and to the starting point of the movement sequence. Experiments using the videos of the Weizmann database show promising results demonstrating the effectiveness of the proposed methodology in classifying simple human actions, e.g. walking and running. The new proposed methodology should be extendable to a broader set of actions.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. Ali, S., Basharat, A., Shah, M.: Chaotic invariants for human action recognition. In: IEEE International Conference on Computer Vision, pp. 1–8 (2007). doi:http://doi.ieeecomputersociety.org/10.1109/ICCV.2007.4409046

  2. Arcelli, C., Sanniti, G., Svensson, S.: Computing and analysing convex deficiencies to characterise 3d complex objects. Image Vis. Comput. 23(2), 203–211 (2005)

    Article  Google Scholar 

  3. Badawy, O.E., Kamel, M.: Matching concavity trees. In: Fred, A.L.N., Caelli, T., Duin, R.P.W., Campilho, A.C., de Ridder, D. (eds.) SSPR/SPR. LNCS, vol. 3138, pp. 556–564. Springer (2004)

  4. Bobick, A., Davis, J.: Real-time recognition of activity using temporal templates. In: WACV ’96: Proceedings of the 3rd IEEE Workshop on Applications of Computer Vision (WACV ’96), p. 39. IEEE Computer Society, Washington, DC, USA (1996)

    Chapter  Google Scholar 

  5. Carlsson, S., Sullivan, J.: Action recognition by shape matching to key frames. In: IEEE Computer Society Workshop on Models Versus Exemplars in Computer Vision (2001)

  6. Chen, D.Y., Shih, S.W., Liao, H.Y.M.: Human action recognition using 2-d spatio-temporal templates. In: ICME, pp. 667–670 (2007)

  7. Cohn, A.: A hierarchical representation of qualitative shape based on connection and convexity. In: Proc COSIT95. LNCS, pp. 311–326. Springer (1995)

  8. Dollár, P., Rabaud, V., Cottrell, G., Belongie, S.: Behavior recognition via sparse spatio-temporal features. In: In VS-PETS, pp. 65–72 (2005)

  9. Efros, A.A., Berg, A.C., Mori, G., Malik, J.: Recognizing action at a distance. In: Proc. Int. Conf. Computer Vision ICCV03 (2003)

  10. El Badawy, O., Kamel, M.S.: Hierarchical representation of 2-d shapes using convex polygons: a contour-based approach. Pattern Recogn. Lett. 26(7), 865–877 (2005). doi:10.1016/j.patrec.2004.09.031

    Article  Google Scholar 

  11. Farhadi, A., Tabrizi, M.K.: Learning to recognize activities from the wrong view point. In: ECCV ’08: Proceedings of the 10th European Conference on Computer Vision, pp. 154–166. Springer, Berlin, Heidelberg (2008)

    Google Scholar 

  12. González, J., Varona, J., Roca, F., Villanueva, J.J.: A human action comparison framework for motion understanding. In: In 6th Catalan Conference for Artificial Intelligence (CCIA’2003), vol. 100, pp. 168–177. Palma de Mallorca, Spain (2003)

  13. González, R., Ion, A., Iglesias, M., Kropatsch, W.G.: Irregular graph pyramids and representative cocycles of cohomology generators. In: Torsello, A., Escolano, F., Brun, L. (eds.) Proc. 7th GbR. LNCS, vol. 5534, pp. 263–272. Springer, Venice, Italy (2009)

    Google Scholar 

  14. Gorelick, L., Blank, M., Shechtman, E., Irani, M., Basri, R.: Actions as space-time shapes. Trans. Pattern Anal. Mach. Intell. 29(12), 2247–2253 (2007). www.wisdom.weizmann.ac.il/~vision/SpaceTimeActions.html

    Article  Google Scholar 

  15. Grundmann, M., Meier, F., Essa, I.: 3d shape context and distance transform for action recognition. In: 19th International Conference on Pattern Recognition, ICPR2008, pp. 1–4. IEEE Computer Society Press (2008)

  16. Hatun, K., Duygulu, P.: Pose sentences: a new representation for action recognition using sequence of pose words. In: 19th International Conference on Pattern Recognition, ICPR2008, pp. 1–4. IEEE Computer Society Press (2008)

  17. Haxhimusa, Y., Saib, M., Langs, G., Kropatsch, W.G.: Logarithmic tapering graph pyramid. In: In Proc. of 24th DAGM Symposium LNCS (2002)

  18. Huang, W., Wu, Q.M.J.: Incremental discriminative-analysis of canonical correlations for action recognition. In: In IEEE 12th International Conference on Computer Vision (ICCV) (2010)

  19. Ikizler, N., Cinbis, R.G., Duygulu, P.: Human action recognition with line and flow histograms. In: ICPR, pp. 1–4. IEEE (2008)

  20. Ikizler, N., Duygulu, P.: Human action recognition using distribution of oriented rectangular patches. In: Workshop on Human Motion—Understanding, Modeling, Capture and Animation. Lecture Notes in Computer Science, vol. 4814, pp. 271–284. Springer (2007)

  21. Illetschko, T.: Minimal combinatorial maps for analyzing 3d data. Tech. Rep. PRIP-TR-110, Vienna University of Technology, Inst. of Computer Aided Automation, Pattern Recognition and Image Processing Group (2006)

  22. Johansson, G.: Visual perception of biological motion and a model for its analysis. Percept. Psychophys. 14, 201–211 (1973)

    Article  Google Scholar 

  23. Kropatsch, W.G.: Building irregular pyramids by dual graph contraction. IEE Proc. Vis. Image Signal Process. 142(6), 366–374 (1995)

    Article  Google Scholar 

  24. Kropatsch, W.G., Haxhimusa, Y., Pizlo, Z., Langs, G.: Vision pyramids that do not grow too high. Pattern Recogn. Lett. 26(3), 319–337 (2005). doi:10.1016/j.patrec.2004.10.026

    Article  Google Scholar 

  25. Laptev, I., Lindeberg, T.: Velocity adaptation of space-time interest points. In: ICPR ’04: Proceedings of the Pattern Recognition, 17th International Conference on (ICPR’04), vol. 1, pp. 52–56. IEEE Computer Society, Washington, DC, USA (2004). doi:10.1109/ICPR.2004.971

    Chapter  Google Scholar 

  26. Niebles, J.C., Fei-Fei, L.: A hierarchical model of shape and appearance for human action classification. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 1–8 (2007)

  27. Niebles, J.C., Wang, H., Fei-fei, L.: Unsupervised learning of human action categories using spatial-temporal words. In: In Proc. BMVC (2006)

  28. Parker, J.R.: The use of convex deficiencies for the recognition of hand printed digits. In: Melter, R.A., Wu, A.Y. (eds.) Vision Geometry III, vol. 2356, pp. 169–175 (1994)

  29. Peltier, S., Ion, A., Kropatsch, W.G., Damiand, G., Haxhimusa, Y.: Directly computing the generators of image homology using graph pyramids. Image Vis. Comput. 27, 846–853 (2009)

    Article  Google Scholar 

  30. Stavrianopoulou, A., Anastassopoulos, V.: The euler feature vector. Int. Conf. Pattern Recognit. 3, 7034 (2000)

    Google Scholar 

  31. Wu, X., Liang, W., Jia, Y.: Human action recognition based on self organizing map. In: In ICASSP (2009)

  32. Yilmaz, A., Shah, M.: A differential geometric approach to representing the human actions. Comput. Vis. Image Underst. 109(3), 335–351 (2008). http://dblp.uni-trier.de/db/journals/cviu/cviu109.html#YilmazS08

    Article  Google Scholar 

  33. Zelnik-manor, L., Irani, M.: Event-based analysis of video. In: In Proc. CVPR, pp. 123–130 (2001)

Download references

Author information

Authors and Affiliations

  1. Pattern Recognition Department, CENATAV, Havana, Cuba

    Mabel Iglesias-Ham & Edel Bartolo García-Reyes

  2. PRIP, Vienna University of Technology, Vienna, Austria

    Mabel Iglesias-Ham, Walter George Kropatsch & Nicole Maria Artner

Authors
  1. Mabel Iglesias-Ham
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Edel Bartolo García-Reyes
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Walter George Kropatsch
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Nicole Maria Artner
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Mabel Iglesias-Ham.

Additional information

This work was supported by the Austrian Science Fund under grant P18716-N13.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Iglesias-Ham, M., García-Reyes, E.B., Kropatsch, W.G. et al. Convex Deficiencies for Human Action Recognition. J Intell Robot Syst 64, 353–364 (2011). https://doi.org/10.1007/s10846-011-9540-1

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10846-011-9540-1

Keywords

Search

Navigation