Modeling Temporal Structure of Decomposable Motion Segments for Activity Classification

  • Juan Carlos Niebles
  • Chih-Wei Chen
  • Li Fei-Fei
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6312)

Abstract

Much recent research in human activity recognition has focused on the problem of recognizing simple repetitive (walking, running, waving) and punctual actions (sitting up, opening a door, hugging). However, many interesting human activities are characterized by a complex temporal composition of simple actions. Automatic recognition of such complex actions can benefit from a good understanding of the temporal structures. We present in this paper a framework for modeling motion by exploiting the temporal structure of the human activities. In our framework, we represent activities as temporal compositions of motion segments. We train a discriminative model that encodes a temporal decomposition of video sequences, and appearance models for each motion segment. In recognition, a query video is matched to the model according to the learned appearances and motion segment decomposition. Classification is made based on the quality of matching between the motion segment classifiers and the temporal segments in the query sequence. To validate our approach, we introduce a new dataset of complex Olympic Sports activities. We show that our algorithm performs better than other state of the art methods.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Turaga, P., Chellappa, R., Subrahmanian, V.S., Udrea, O.: Machine Recognition of Human Activities: A Survey. IEEE Transactions on Circuits and Systems for Video Technology 18, 1473–1488 (2008)CrossRefGoogle Scholar
  2. 2.
    Forsyth, D.A., Arikan, O., Ikemoto, L., O’Brien, J., Ramanan, D.: Computational Studies of Human Motion: Part 1, Tracking and Motion Synthesis. Foundations and Trends in Computer Graphics and Vision 1, 77–254 (2005)CrossRefGoogle Scholar
  3. 3.
    Laptev, I.: On Space-Time Interest Points. IJCV 64, 107–123 (2005)CrossRefGoogle Scholar
  4. 4.
    Marszalek, M., Laptev, I., Schmid, C.: Actions in context. In: CVPR, pp. 2929–2936. IEEE, Los Alamitos (2009)Google Scholar
  5. 5.
    Laptev, I., Marszalek, M., Schmid, C., Rozenfeld, B.: Learning realistic human actions from movies. In: CVPR, p. 18. IEEE, Los Alamitos (2008)Google Scholar
  6. 6.
    Wang, Y., Mori, G.: Human action recognition by semilatent topic models. IEEE TPAMI 31, 1762–1774 (2009)Google Scholar
  7. 7.
    Niebles, J.C., Wang, H., Fei-Fei, L.: Unsupervised Learning of Human Action Categories Using Spatial-Temporal Words. IJCV 79, 299–318 (2008)CrossRefGoogle Scholar
  8. 8.
    Wong, S.F., Kim, T.K., Cipolla, R.: Learning Motion Categories using both Semantic and Structural Information. In: CVPR, pp. 1–6. IEEE, Los Alamitos (2007)Google Scholar
  9. 9.
    Laxton, B., Lim, J., Kriegman, D.: Leveraging temporal, contextual and ordering constraints for recognizing complex activities in video. In: CVPR. IEEE, Los Alamitos (2007)Google Scholar
  10. 10.
    Ikizler, N., Forsyth, D.A.: Searching for Complex Human Activities with No Visual Examples. IJCV 80, 337–357 (2008)CrossRefGoogle Scholar
  11. 11.
    Gupta, A., Srinivasan, P., Shi, J., Davis, L.S.: Understanding videos, constructing plots learning a visually grounded storyline model from annotated videos. In: CVPR, pp. 2012–2019. IEEE, Los Alamitos (2009)Google Scholar
  12. 12.
    Sminchisescu, C., Kanaujia, A., Metaxas, D.: Conditional models for contextual human motion recognition. CVIU 104, 210–220 (2006)Google Scholar
  13. 13.
    Wang, S.B., Quattoni, A., Morency, L.P., Demirdjian, D., Darrell, T.: Hidden Conditional Random Fields for Gesture Recognition. In: CVPR, vol. 2, pp. 1521–1527. IEEE, Los Alamitos (2006)Google Scholar
  14. 14.
    Quattoni, A., Wang, S.B., Morency, L.P., Collins, M., Darrell, T.: Hidden conditional random fields. IEEE TPAMI 29, 1848–1853 (2007)Google Scholar
  15. 15.
    Rodriguez, M.D., Ahmed, J., Shah, M.: Action MACH a spatio-temporal Maximum Average Correlation Height filter for action recognition. In: CVPR. IEEE, Los Alamitos (2008)Google Scholar
  16. 16.
    Yao, B., Fei-Fei, L.: Modeling Mutual Context of Object and Human Pose in Human-Object Interaction Activities. In: CVPR. IEEE, Los Alamitos (2010)Google Scholar
  17. 17.
    Bouchard, G., Triggs, B.: Hierarchical Part-Based Visual Object Categorization. In: CVPR, pp. 710–715. IEEE, Los Alamitos (2005)Google Scholar
  18. 18.
    Felzenszwalb, P.F., Huttenlocher, D.P.: Pictorial Structures for Object Recognition. IJCV 61, 55–79 (2005)CrossRefGoogle Scholar
  19. 19.
    Fergus, R., Perona, P., Zisserman, A.: Weakly Supervised Scale-Invariant Learning of Models for Visual Recognition. IJCV 71, 273–303 (2007)CrossRefGoogle Scholar
  20. 20.
    Niebles, J.C., Fei-Fei, L.: A Hierarchical Model of Shape and Appearance for Human Action Classification. In: CVPR, pp. 1–8. IEEE, Los Alamitos (2007)Google Scholar
  21. 21.
    Felzenszwalb, P.F., Girshick, R.B., McAllester, D., Ramanan, D.: Object Detection with Discriminatively Trained Part Based Models. IEEE TPAMI, 1–20 (2009)Google Scholar
  22. 22.
    Ke, Y., Sukthankar, R., Hebert, M.: Event Detection in Crowded Videos. In: ICCV, pp. 1–8. IEEE, Los Alamitos (2007)Google Scholar
  23. 23.
    Dollár, P., Rabaud, V., Cottrell, G., Belongie, S.: Behavior Recognition via Sparse Spatio-Temporal Features. In: VSPETS, pp. 65–72. IEEE, Los Alamitos (2005)Google Scholar
  24. 24.
    Blank, M., Gorelick, L., Shechtman, E., Irani, M., Basri, R.: Actions as Space-Time Shapes. In: ICCV, vol. 2, pp. 1395–1402. IEEE, Los Alamitos (2005)Google Scholar
  25. 25.
    Felzenszwalb, P.F., McAllester, D., Ramanan, D.: A discriminatively trained, multiscale, deformable part model. In: CVPR, pp. 1–8. IEEE, Los Alamitos (2008)Google Scholar
  26. 26.
    Chang, C.C., Lin, C.J.: LIBSVM: a library for support vector machines (2001), http://www.csie.ntu.edu.tw/~cjlin/libsvm
  27. 27.
    Schuldt, C., Laptev, I., Caputo, B.: Recognizing human actions: a local SVM approach. In: ICPR, pp. 32–36. IEEE, Los Alamitos (2004)Google Scholar
  28. 28.
    Wang, H., Ullah, M.M., Klaser, A., Laptev, I., Schmid, C.: Evaluation of local spatio-temporal features for action recognition. In: BMVC (2009)Google Scholar
  29. 29.
    Kim, T.K., Wong, S.F., Cipolla, R.: Tensor Canonical Correlation Analysis for Action Classification. In: CVPR, pp. 1–8. IEEE, Los Alamitos (2007)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Juan Carlos Niebles
    • 1
    • 2
    • 3
  • Chih-Wei Chen
    • 1
  • Li Fei-Fei
    • 1
  1. 1.Stanford UniversityStanfordUSA
  2. 2.Princeton UniversityPrincetonUSA
  3. 3.Universidad del NorteBarranquillaColombia

Personalised recommendations