Behavior Histograms for Action Recognition and Human Detection

  • Christian Thurau
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4814)


This paper presents an approach for human detection and simultaneous behavior recognition from images and image sequences. An action representation is derived by applying a clustering algorithm to sequences of Histogram of Oriented Gradient (HOG) descriptors of human motion images. For novel image sequences, we first detect the human by matching extracted descriptors with the prototypical action primitives. Given a sequence of assigned action primitives, we can build a histogram from observed motion. Thus, behavior can be classified by means of histogram comparison, interpreting behavior recognition as a problem of statistical sequence analysis. Results on publicly available benchmark-data show a high accuracy for action recognition.


Recognition Rate IEEE Computer Society Action Recognition Detector Window Human Detection 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Thurau, C., Hlaváč, V.: n-grams of Action Primitives for Recognizing Human Behavior. In: CAIP 2007. The 12th International Conference on Computer Analysis of Images and Patterns, Springer, Heidelberg (2007)Google Scholar
  2. 2.
    Blank, M., Gorelick, L., Shechtman, E., Irani, M., Basri, R.: Actions as Space-Time Shapes. In: Tenth IEEE International Conference on Computer Vision, IEEE Computer Society Press, Los Alamitos (2005)Google Scholar
  3. 3.
    Niebles, J.C., Fei-Fei, L.: A Hierarchical Model of Shape and Appearance for Human Action Classification. In: CVPR 2007. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, IEEE Computer Society Press, Los Alamitos (2007)Google Scholar
  4. 4.
    Dalal, N., Triggs, B.: Histograms of Oriented Gradients for Human Detection. In: CVPR 2005. 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, IEEE Computer Society Press, Los Alamitos (2005)Google Scholar
  5. 5.
    Thurau, C., Bauckhage, C., Sagerer, G.: Synthesizing Movements for Computer Game Characters. In: Rasmussen, C.E., Bülthoff, H.H., Schölkopf, B., Giese, M.A. (eds.) DAGM 2004. LNCS, vol. 3175, pp. 179–186. Springer, Heidelberg (2004)Google Scholar
  6. 6.
    Schack, T., Mechsner, F.: Representation of motor skills in human long-term memory. Neuroscience Letters 391, 77–81 (2006)CrossRefGoogle Scholar
  7. 7.
    Niebles, J.C., Wang, H., Fei-Fei, L.: Unsupervised Learning of Human Action Categories Using Spatial-Temporal Words. In: BMVC 2006. British Machine Vision Conference (2006)Google Scholar
  8. 8.
    Lu, W.L., Little, J.J.: Simultaneous tracking and action recognition using the pca-hog descriptor. In: CRV 2006. The Third Canadian Conference on Computer and Robot Vision (2006)Google Scholar
  9. 9.
    Ghahramani, Z.: Building blocks of movement. Nature 407, 682–683 (2000)CrossRefGoogle Scholar
  10. 10.
    Wolpert, D.M., Ghahramani, Z., Flanagan, J.R.: Perspectives and problems in motor learning. TRENDS in Cognitive Sciences 5(11), 487–494 (2001)CrossRefGoogle Scholar
  11. 11.
    Krüger, V., Kragic, D., Ude, A., Geib, C.: Meaning of action (2007)Google Scholar
  12. 12.
    Thoroughman, K., Shadmehr, R.: Learning of action through adaptive combination of motor primitives. Nature 407, 742–747 (2000)CrossRefGoogle Scholar
  13. 13.
    Fod, A., Matarić, M., Jenkins, O.: Automated Derivation of Primitives for Movement Classification. Autonomous Robots 12(1), 39–54 (2002)zbMATHCrossRefGoogle Scholar
  14. 14.
    Lee, C.S., Elgammal, A.: Human motion synthesis by motion manifold learning and motion primitive segmentation. In: Perales, F.J., Fisher, R.B. (eds.) AMDO 2006. LNCS, vol. 4069, pp. 464–473. Springer, Heidelberg (2006)Google Scholar
  15. 15.
    Moeslund, T., Reng, L., Granum, E.: Finding Motion Primitives in Human Body Gestures. In: Gibet, S., Courty, N., Kamp, J.F. (eds.) GW 2005. LNCS (LNAI), vol. 3881, pp. 133–144. Springer, Heidelberg (2006)Google Scholar
  16. 16.
    Moeslund, T., Fihl, P., Holte, M.: Action Recognition using Motion Primitives. In: The 15th Danish conference on pattern recognition and image analysis (2006)Google Scholar
  17. 17.
    Ogale, A.S., Karapurkar, A., Aloimonos, Y.: View-invariant modeling and recognition of human actions using grammars. In: ICCV Workshop on Dynamical Vision (2005)Google Scholar
  18. 18.
    Guerra-Filho, G., Aloimonos, Y.: A Sensory-Motor Language for Human Activity Understanding. In: HUMANOIDS 2006. 6th IEEE-RAS International Conference on Humanoid Robots, pp. 69–75. IEEE Computer Society Press, Los Alamitos (2006)Google Scholar
  19. 19.
    Hamid, R., Johnson, A., Batta, S., Bobick, A., Isbell, C., Coleman, G.: Detection and Explanation of Anomalous Activities: Representing Activities as Bags of Event n-Grams. In: CVPR 2005. 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, IEEE Computer Society Press, Los Alamitos (2005)Google Scholar
  20. 20.
    Goldenberg, R., Kimmel, R., Rivlin, E., Rudzsky, M.: Behavior classification by eigendecomposition of periodic motions. Pattern Recognition 38, 1033–1043 (2005)CrossRefGoogle Scholar
  21. 21.
    Lowe, D.: Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision 20, 91–110 (2003)Google Scholar
  22. 22.
    Schroff, F., Criminisi, A., Zisserman, A.: Single-Histogram Class Models for Image Segmentation. In: Proceedings of the Indian Conference on Computer Vision, Graphics and Image Processing (2006)Google Scholar
  23. 23.
    Porikli, F.: Integral histogram: A fast way to extract higtograms in cartesian spaces. In: CVPR. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 829–836. IEEE Computer Society Press, Los Alamitos (2005)Google Scholar
  24. 24.
    Zhu, Q., Avidan, S., Yeh, M., Cheng, K.: Fast Human Detection Using a Cascade of Histograms of Oriented Gradients. In: IEEE Computer Society Conference on Computer vision and Pattern Recognition, pp. 1491–1498. IEEE Computer Society Press, Los Alamitos (2006)Google Scholar
  25. 25.
    Dalal, N., Triggs, B., Schmid, C.: Human detection using oriented histograms of flow and appearance. In: European Conference on Computer Vision (2006)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2007

Authors and Affiliations

  • Christian Thurau
    • 1
  1. 1.Czech Technical University, Faculty of Electrical Engineering, Department for Cybernetics, Center for Machine Perception, 121 35 Prague 2, Karlovo náměstíCzech Republic

Personalised recommendations