Advertisement

Variable Size Block Matching Trajectories for Human Action Recognition

  • Fábio L. M. de OliveiraEmail author
  • Marcelo B. Vieira
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9155)

Abstract

In the context of the human action recognition problem, we propose a tensor descriptor based on sparse trajectories extracted via Variable Size Block Matching. Compared to other action recognition descriptors, our method runs fast and yields a compact descriptor, due to its simplicity and the coarse representation of movement provided by block matching. We validate our method using the KTH dataset, showing improvements over a previous block matching based descriptor. The recognition rates are comparable to those of state-of-the-art methods with the additional feature of having frame rates close to real-time computation.

Keywords

Human action recognition Variable size block matching Self-descriptor Tensor descriptor 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Amel, A.M., Abdessalem, B.A., Abdellatif, M.: Video shot boundary detection using motion activity descriptor. Journal of Telecommunications 2(1), 54–59 (2010)Google Scholar
  2. 2.
    Calzone, S., Chen, K., Chuang, C.C., Divakaran, A., Dube, S., Hurd, L., Kari, J., Liang, G., Lin, F.H., Muller, J., Rising, H.K.: Video compression by mean-corrected motion compensation of partial quadtrees. IEEE Transactions on Circuits and Systems for Video Technology 7(1), 86–96 (1997)CrossRefGoogle Scholar
  3. 3.
    Chan, M., Yu, Y., Constantinides, A.: Variable size block matching motion compensation with applications to video coding. IEEE in Proceedings 137(4), 205–212 (1990). http://dl.acm.org/citation.cfm?id=646271.685624 Google Scholar
  4. 4.
    Chen, C.Y., Chien, S.Y., Huang, Y.W., Chen, T.C., Wang, T.C., Chen, L.G.: Analysis and architecture design of variable block-size motion estimation for h.264/avc. IEEE Transactions on Circuits and Systems I: Regular Papers 53(3), 578–593 (2006)CrossRefGoogle Scholar
  5. 5.
    Choi, S.J., Woods, J.: Motion-compensated 3-d subband coding of video. IEEE Transactions on Image Processing 8(2), 155–167 (1999)CrossRefGoogle Scholar
  6. 6.
    Figueiredo, A.M.O., Maia, H.A., Oliveira, F.L.M., Mota, V.F., Vieira, M.B.: A video tensor self-descriptor based on block matching. In: Murgante, B., Misra, S., Rocha, A.M.A.C., Torre, C., Rocha, J.G., Falcão, M.I., Taniar, D., Apduhan, B.O., Gervasi, O. (eds.) ICCSA 2014, Part VI. LNCS, vol. 8584, pp. 401–414. Springer, Heidelberg (2014) Google Scholar
  7. 7.
    Hafiane, A., Palaniappan, K., Seetharaman, G.: Uav-video registration using block-based features. In: IEEE International Geoscience and Remote Sensing Symposium (IGARSS), vol. 2, pp. 1104–1107 (2008)Google Scholar
  8. 8.
    Horowitz, S.L., Pavlidis, T.: Picture segmentation by a tree traversal algorithm. J. ACM 23(2), 368–388 (1976). http://doi.acm.org/10.1145/321941.321956 zbMATHCrossRefGoogle Scholar
  9. 9.
    Jain, J.R., Jain, A.K.: Displacement measurement and its application in interframe image coding. IEEE Transactions on Communications COM 29(12), 1799–1808 (1981)CrossRefGoogle Scholar
  10. 10.
    Jain, M., Jegou, H., Bouthemy, P.: Better exploiting motion for better action recognition. In: 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2555–2562, June 2013Google Scholar
  11. 11.
    Ji, Y., Shimada, A., Taniguchi, R.I.: A compact 3d descriptor in roi for human action recognition. In: IEEE TENCON, pp. 454–459 (2010)Google Scholar
  12. 12.
    Johansson, B., Farnebäck, G.: A theoretical comparison of different orientation tensors. In: Proceedings of the SSAB Symposium on Image Analysis, pp. 69–73 (2002)Google Scholar
  13. 13.
    Kim, J.W., Lee, S.U.: Hierarchical variable block size motion estimation technique for motion sequence coding. Optical Engineering 33(8), 2553–2561 (1994)CrossRefGoogle Scholar
  14. 14.
    Kläser, A., Marszałek, M., Schmid, C.: A spatio-temporal descriptor based on 3d-gradients. In: British Machine Vision Conference (BMVC), pp. 995–1004, September 2008Google Scholar
  15. 15.
    Ku, C.W., Lin, G.S., Chen, L.G., Lee, Y.P.: Architecture design of motion estimation for itu-t h.263, vol. 3024, pp. 482–493 (1997). http://dx.doi.org/10.1117/12.263260
  16. 16.
    Li, R., Zeng, B., Liou, M.L.: A new three-step search algorithm for block motion estimation. IEEE Transactions on Circuits and Systems for Video Technology 4(4), 438–442 (1994)CrossRefGoogle Scholar
  17. 17.
    Liu, J., Luo, J., Shah, M.: Recognizing realistic actions from videos in the wild. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR),pp. 1996–2003. IEEE (2009)Google Scholar
  18. 18.
    Lu, J., Liou, M.L.: A simple and efficient search algorithm for block-matching motion estimation. IEEE Transactions on Circuits and Systems for Video Technology 7(2), 429–433 (1997)CrossRefGoogle Scholar
  19. 19.
    Mota, V.F., Souza, J.I., de A. Araújo, A., Vieira, M.B.: Combining orientation tensors for human action recognition. In: Conference on Graphics, Patterns and Images (SIBGRAPI), pp. 328–333. IEEE (2013)Google Scholar
  20. 20.
    Mota, V.F., Perez, E.D.A., Maciel, L.M., Vieira, M.B., Gosselin, P.H.: A tensor motion descriptor based on histograms of gradients and optical flow. Pattern Recognition Letters 31, 85–91 (2013)Google Scholar
  21. 21.
    Mota, V.F., Perez, E.D.A., Vieira, M.B., Maciel, L., Precioso, F., Gosselin, P.H.: A tensor based on optical flow for global description of motion in videos. In: Conference on Graphics, Patterns and Images (SIBGRAPI), pp. 298–301. IEEE (2012)Google Scholar
  22. 22.
    Nie, Y., Ma, K.K.: Adaptive rood pattern search for fast block-matching motion estimation. IEEE Transactions on Image Processing 11(12), 1442–1449 (2002)CrossRefGoogle Scholar
  23. 23.
    Muralidhar, P., Rama Rao, C.B., Ranjith Kumar, I.: Efficient architecture for variable block size motion estimation of h.264 video encoder. In: International Conference on Solid-State and Integrated Circuit (ICSIC), vol. 32, p. 6 (2012)Google Scholar
  24. 24.
    Pirsch, P., Demassieux, N., Gehrke, W.: Vlsi architectures for video compression-a survey. Proceedings of the IEEE 83(2), 220–246 (1995)CrossRefGoogle Scholar
  25. 25.
    Po, L.M., Ma, W.C.: A novel four-step search algorithm for fast block motion estimation. IEEE Transactions on Circuits and Systems for Video Technology 6(3), 313–317 (1996)CrossRefGoogle Scholar
  26. 26.
    Puri, A., Hang, H., Schilling, D.: Interframe coding with variable block-size motion compensation. In: IEEE Global Telecommunication Conference, pp. 65–69 (1987)Google Scholar
  27. 27.
    Sad, D., Mota, V.F., Maciel, L.M., Vieira, M.B., Araújo, A.d.A.: A tensor motion descriptor based on multiple gradient estimators. In: Conference on Graphics, Patterns and Images (SIBGRAPI), pp. 70–74. IEEE (2013)Google Scholar
  28. 28.
    Schuldt, C., Laptev, I., Caputo, B.: Recognizing human actions: a local svm approach. In: Proceedings of the 17th International Conference on Pattern Recognition (ICPR), vol. 3, pp. 32–36. IEEE (2004)Google Scholar
  29. 29.
    Sullivan, G., Baker, R.: Rate-distortion optimized motion compensation for video compression using fixed or variable size blocks. In: Global Telecommunications Conference, GLOBECOM 1991. ’Countdown to the New Millennium. Featuring a Mini-Theme on: Personal Communications Services, vol. 1, pp. 85–90, December 1991Google Scholar
  30. 30.
    Sullivan, G., Ohm, J., Han, W.J., Wiegand, T.: Overview of the high efficiency video coding (hevc) standard. IEEE Transactions on Circuits and Systems for Video Technology 22(12), 1649–1668 (2012)CrossRefGoogle Scholar
  31. 31.
    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, June 2011Google Scholar
  32. 32.
    Wang, H., Kläser, A., Schmid, C., Liu, C.L.: Dense trajectories and motion boundary descriptors for action recognition. International Journal of Computer Vision 103(1), 60–79 (2013)MathSciNetCrossRefGoogle Scholar
  33. 33.
    Wang, H., Schmid, C., et al.: Action recognition with improved trajectories. In: International Conference on Computer Vision (2013)Google Scholar
  34. 34.
    Zhu, S., Ma, K.K.: A new diamond search algorithm for fast block-matching motion estimation. IEEE Transactions on Image Processing 9(2), 287–290 (2000)MathSciNetCrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  • Fábio L. M. de Oliveira
    • 1
    Email author
  • Marcelo B. Vieira
    • 1
  1. 1.Universidade Federal de Juiz de ForaJuiz de ForaBrazil

Personalised recommendations