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.
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.References
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
Arcelli, C., Sanniti, G., Svensson, S.: Computing and analysing convex deficiencies to characterise 3d complex objects. Image Vis. Comput. 23(2), 203–211 (2005)
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)
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)
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)
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)
Cohn, A.: A hierarchical representation of qualitative shape based on connection and convexity. In: Proc COSIT95. LNCS, pp. 311–326. Springer (1995)
Dollár, P., Rabaud, V., Cottrell, G., Belongie, S.: Behavior recognition via sparse spatio-temporal features. In: In VS-PETS, pp. 65–72 (2005)
Efros, A.A., Berg, A.C., Mori, G., Malik, J.: Recognizing action at a distance. In: Proc. Int. Conf. Computer Vision ICCV03 (2003)
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
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)
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)
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)
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
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)
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)
Haxhimusa, Y., Saib, M., Langs, G., Kropatsch, W.G.: Logarithmic tapering graph pyramid. In: In Proc. of 24th DAGM Symposium LNCS (2002)
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)
Ikizler, N., Cinbis, R.G., Duygulu, P.: Human action recognition with line and flow histograms. In: ICPR, pp. 1–4. IEEE (2008)
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)
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)
Johansson, G.: Visual perception of biological motion and a model for its analysis. Percept. Psychophys. 14, 201–211 (1973)
Kropatsch, W.G.: Building irregular pyramids by dual graph contraction. IEE Proc. Vis. Image Signal Process. 142(6), 366–374 (1995)
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
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
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)
Niebles, J.C., Wang, H., Fei-fei, L.: Unsupervised learning of human action categories using spatial-temporal words. In: In Proc. BMVC (2006)
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)
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)
Stavrianopoulou, A., Anastassopoulos, V.: The euler feature vector. Int. Conf. Pattern Recognit. 3, 7034 (2000)
Wu, X., Liang, W., Jia, Y.: Human action recognition based on self organizing map. In: In ICASSP (2009)
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
Zelnik-manor, L., Irani, M.: Event-based analysis of video. In: In Proc. CVPR, pp. 123–130 (2001)
Author information
Authors and Affiliations
Corresponding author
Additional information
This work was supported by the Austrian Science Fund under grant P18716-N13.
Rights 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
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10846-011-9540-1