Skip to main content
Springer Nature Link
Log in

From Motion Patterns to Visual Concepts for Event Analysis in Dynamic Scenes

  • Conference paper
Computer Vision – ACCV 2006 (ACCV 2006)

Part of the book series: Lecture Notes in Computer Science ((LNIP,volume 3851))

Included in the following conference series:

  • 1623 Accesses

Abstract

The analysis of events in dynamic scenes has become an important and challenging problem increasingly in recent years. Events can be considered as obvious changes of important features with semantic meanings. From this viewpoint, the fundamental task of events analysis is to extract semantically meaningful changes and associate all of these basic motion patterns and changes with relevant visual concepts of moving objects in dynamic scenes. In this paper, we propose a method to extract lower level motion patterns and associate them with visual concepts respectively in a well-defined structure. Furthermore we also analyze latent spatial-temporal relationships among these basic visual concepts for event modeling and analysis. Finally, we present experimental results which prove the effectiveness of our approach on some real-world videos of dynamic scenes.

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

Access this chapter

Log in via an institution

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Shah, M.: Guest Introduction: The Changing Shape of Computer Vision in the Twenty-First Century. International Journal of Computer Vision 50(2), 103–110 (2002)

    Article  Google Scholar 

  2. Ekinci, A., Tekalp, A.M.: Generic Event Detection in Sports Video using Cinematic Features. In: Second IEEE Workshop on Event Mining (EVENT 2003), June 2003, pp. 17–24 (2003)

    Google Scholar 

  3. Fauconnier, G.: Mapping in Thought and Language. Cambridge University Press, Cambridge (1997)

    Google Scholar 

  4. Dahlberg, I.: Conceptual Definitions for Interconcept. International Classification 8(1), 16–22 (1981)

    Google Scholar 

  5. Thibadeau, R.: Artificial Perception of Actions. Cognitive Science 10(2), 117–149 (1986)

    Article  Google Scholar 

  6. Newtson, D.: Foundations of Attribution: the Perception of Ongoing Behaviour. In: New Directions in Attribution Research, pp. 147–223. Lawrence Erlbaum, Hillsdala (1976)

    Google Scholar 

  7. Howarth, R.J., Buxton, H.: Conceptual Descriptions from Monitoring and Watching Image Sequences. Image and Vision Computing 18, 105–135 (2000)

    Article  Google Scholar 

  8. Neumann, B.: A Conceptual Framework for High-level Vision. Bericht. FB Informatik. FBI-HH-B245/02 (Juli 2002)

    Google Scholar 

  9. Badler, N.I.: Temporal Scene Analysis: Conceptual Descriptions of Object Movements. Technical Report No. 80. Dept. of Computer Science. University of Toronto (1975)

    Google Scholar 

  10. Intille, S.S., Davis, J.W., Bobick, A.F.: Real Time Closed World Tracking. In: IEEE Proc. Computer Vision and Pattern Recognition, pp. 697–703 (1997)

    Google Scholar 

  11. Lipton, A.J., Fujiyoshi, H., Patil, R.S.: Moving Target Classification and Tracking from Real Time Video. In: Proc. Fourth IEEE Workshop Application of Computer Vision, pp. 8–14 (1998)

    Google Scholar 

  12. Haritaoglu, I., Harwood, D., Davis, L.S.: W4: real-time surveillance of people and their activities. IEEE Transactions on Pattern Analysis and Machine Intelligence 22(8), 809–830 (2000)

    Article  Google Scholar 

  13. Wren, C.R., Azarbayejani, A., et al.: Pfinder: Real Time Tracking of the Human Body. IEEE Trans. Pattern Analysis and Machine Intelligence 19(7) (1997)

    Google Scholar 

  14. Davis, L., Chelappa, R., Rosenfeld, A., Harwood, D., Haritaoglu, I., Cutler, R.: Visual Surveillance and Monitoring. In: DARPA Image Understanding Workshop, pp. 73–76 (1998)

    Google Scholar 

  15. Galton, A.: Towards an Integrated Logic of Space, Time and Motion. In: Proc. International Joint Conf. Artificial Intelligence (IJCAI) (August 1993)

    Google Scholar 

  16. Ivanov, Y.A., Bobick, A.F.: Recognition of Visual Activities and Interactions by Stochastic Parsing. IEEE Trans. on Pattern Analysis and Machine Intelligence 22(8), 852–872 (2000)

    Article  Google Scholar 

  17. Dance, S., Caelli, T.: A Symbolic Object-oriented Picture Interpretation Network: SOO-PIN. In: Bunke, H. (ed.) Advances in Structural and Syntactic Pattern Recognition. Proceedings of the International Workshop, pp. 530–541. World Scientific Publishing Co., Singapore (1993)

    Google Scholar 

  18. Haag, M., Nagel, H.-H.: Incremental Recognition of Traffic Situations from Video Image Sequences. Image and Vision Computing 18, 137–153 (2000)

    Article  Google Scholar 

  19. Howarth, R.J., Buxton, H.: Conceptual descriptions from Monitoring and Watching Image Sequences. Image and Vision Computing 18, 105–135 (2000)

    Article  Google Scholar 

  20. Oliver, N., Garg, A., Horvitz, E.: Layered Representations for Learning and Inferring Office Activity from Multiple Sensory Channels. Computer Vision and Image Understanding. Special Issue on Event Detection in Video 96(2), 163–180 (2004)

    Google Scholar 

  21. Kojima, A., Tamura, T., Fukunaga, K.: Natural Language Description of Human Activities from Video Images Based on Concept Hierarchy of Actions. International Journal of Computer Vision 50(2), 171–184 (2002)

    Article  MATH  Google Scholar 

  22. Chaudron, L., Cossart, C., Maille, N., Tessier, C.: A Purely Symbolic Model for Dynamic Scene Interpretation. International Journal on Artificial Intelligence Tools 6(4), 635–664 (1997)

    Article  Google Scholar 

  23. Galata, A., Johnson, N., Hogg, D.: Learning Structured Behaviour Models Using Variable Length Markov Models. Computer Vision and Image Understanding (CVIU) Journal 81(3), 398–413 (2001)

    Article  MATH  Google Scholar 

  24. Brand, M., Oliver, N., Pentland, A.: Coupled Hidden Markov Models for Complex Action Recognition. In: Proc. of the Conference on Computer Vision and Pattern Recognition (CVPR 1997), pp. 994–998 (1997)

    Google Scholar 

  25. Birnbaum, L., Brand, M., Cooper, P.: Looking for Trouble: Using Causal Semantics. In: Proceedings of the Fourth International Conference on Computer Vision, pp. 49–56. IEEE Computer Society Press, Silver spring (1993)

    Google Scholar 

  26. Town, C.: Ontology-driven Bayesian Networks for Dynamic Scene Understanding. In: Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPRW 2004), 27-02 June, pp. 116–123 (2004)

    Google Scholar 

  27. Varga, P., Mészáros, T., Dezsényi, C., Dobrowiecki, T.P.: An Ontology-based Information Retrieval System. In: The 16th International Conference on Industrial & Engineering Applications of Artificial Intelligence and Expert Systems, Loughborough. U.K, 23-26 June (2003)

    Google Scholar 

  28. Wang, Y., Yang, Z., Kong, P.H.H., Gay, R.K.L.: Ontology-based Web knowledge management. In: Proceedings of the 2003 Joint Conference of the Fourth International Conference on Information, Communications and Signal Processing, 15-18 December, vol. 3, pp. 1859–1863 (2003)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, 100080, Beijing, P.R. China

    Lun Xin & Tieniu Tan

Authors
  1. Lun Xin
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Tieniu Tan
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. International Institute of Information Technology, Center for Visual Information Technology, Hyderabad, India

    P. J. Narayanan

  2. Department of Computer Science, Columbia University, 500 West 120th Street, 10027, New York, NY, USA

    Shree K. Nayar

  3. Microsoft Research Asia, Beijing, P.R. China

    Heung-Yeung Shum

Rights and permissions

Reprints and permissions

Copyright information

© 2006 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Xin, L., Tan, T. (2006). From Motion Patterns to Visual Concepts for Event Analysis in Dynamic Scenes. In: Narayanan, P.J., Nayar, S.K., Shum, HY. (eds) Computer Vision – ACCV 2006. ACCV 2006. Lecture Notes in Computer Science, vol 3851. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11612032_83

Download citation

  • DOI: https://doi.org/10.1007/11612032_83

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-31219-2

  • Online ISBN: 978-3-540-32433-1

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics