Skip to main content
SpringerLink
Log in

Visual event recognition using decision trees

  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

This paper presents a classifier-based approach to recognize dynamic events in video surveillance sequences. The goal of this work is to propose a flexible event recognition system that can be used without relying on a long-term explicit tracking procedure. It is composed of three stages. The first one aims at defining and building a set of relevant features describing the shape and movements of the foreground objects in the scene. To this aim, we introduce new motion descriptors based on space-time volumes. Second, an unsupervised learning-based method is used to cluster the objects, thereby defining a set of coarse to fine local patterns of features, representing primitive events in the video sequences. Finally, events are modeled as a spatio-temporal organization of patterns based on an ensemble of randomized trees. In particular, we want this classifier to discover the temporal and causal correlations between the most discriminative patterns. Our system is experimented and validated both on simulated and real-life data.

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

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6

Similar content being viewed by others

Notes

  1. Scale invariance is required in numerous visual surveillance contexts.

  2. http://homepages.inf.ed.ac.uk/rbf/CAVIARDATA1/

References

  1. Amit Y, Geman D (1997) Shape quantization and recognition with randomized trees. Neural Comput 9(7):1545–1588

    Article  Google Scholar 

  2. Bobick AF, Davis JW (2001) The recognition of human movement using temporal templates. IEEE Trans Pattern Anal Mach Intell 23:257–267

    Article  Google Scholar 

  3. Breiman L (2001) Random forests. Mach Learn 45(1):5–32

    Article  MATH  Google Scholar 

  4. Breiman L, Friedman J, Olsen R, Stone C (1984) Classification and regression trees. CRC, Boca Raton. ISBN 0412048418

    MATH  Google Scholar 

  5. Buxton H (2003) Learning and understanding dynamic scene activity: a review. Image Vis Comput 21(1):125–136

    Article  Google Scholar 

  6. Cucchiara R, Grana C, Piccardi M, Prati A (2003) Detecting moving objects, ghosts and shadows in video stream. IEEE Trans Pattern Anal Mach Intell 25:1337–1342

    Article  Google Scholar 

  7. Dee H, Velastin S (2007) How close are we to solving the problem of automated visual surveillance? A review of real-world surveillance, scientific progress and evaluative mechanisms. In: Machine vision and applications, special issue on video surveillance research in industry and Academic Springer. Springer, New York

    Google Scholar 

  8. Geurts P, Ernst D, Wehenkel L (2006) Extremely randomized trees. Mach Learn 63(1):3–42

    Article  MATH  Google Scholar 

  9. Gorelick L, Blank M, Shechtman E, IM, Basri R (2005) Actions as space-time shapes. In: ICCV, pp 1395–1402

  10. Haering N, Venetianer PL, Lipton A (2008) The evolution of video surveillance: an overview. Mach Vis Appl 19(5–6):279–290

    Article  MATH  Google Scholar 

  11. Haritaoglu I, Harwood D, Davis L (2000) W4: real-time surveillance of people and their activities. IEEE Trans Pattern Anal Mach Intell 22:809–830

    Article  Google Scholar 

  12. Hu W, Tan T, Wang L, Maybank S (2004) A survey on visual surveillance of object motion and behaviors. IEEE Trans Syst Man Cybern 34:334–352

    Google Scholar 

  13. Kadous M, Sammut C (2005) Classification of multivariate time series and structured data using constructive induction. Mach Learn J 58:179–216

    Article  Google Scholar 

  14. Lee D (2005) Effective gaussian mixture learning for video background substraction. IEEE Trans Pattern Anal Mach Intell 27(5):827–832

    Article  Google Scholar 

  15. Lin W, Sun M-T, Poovandran R, Zhang Z (2008) Human activity recognition for video surveillance. In: IEEE international symposium on circuits and systems, 2008. ISCAS 2008, pp 2737–2740

  16. McKenna S, Jabri S, Duric Z, Rosenfeld A, Wechsler H (2000) Tracking groups of people. Comput Vis Image Underst 80:42–56

    Article  MATH  Google Scholar 

  17. Medioni G, Cohen I, Bremond F, Hongeng S, Nevatia R (2001) Event detection and analysis from video streams. IEEE Trans Pattern Anal Mach Intell 23(8):873–889

    Article  Google Scholar 

  18. Moosmann F, Nowak E, Jurie F (2008) Randomized clustering forests for image classification. IEEE Trans Pattern Anal Mach Intell 30(9):1632–1646

    Article  Google Scholar 

  19. Nascimento J, Marques J (2006) Performance evaluation of object detection algorithms for video surveillance. IEEE Trans Multimedia 8:761–774

    Article  Google Scholar 

  20. Ohta N (2001) A statistical approach to backgound suppression for surveillance systems. ICCVÕ01 1:481–486

    Google Scholar 

  21. Oliver N, Rosario B, Pentland A (2000) A bayesian computer vision system for modeling human interactions. IEEE Trans Pattern Anal Mach Intell 22(8):831–843

    Article  Google Scholar 

  22. Orrite C, Martinez F, Herrero E, Ragheb H, Velastin S (2008) Independent viewpoint silhouette-based human action modelling and recognition. In: 1st int workshop on machine learning for vision-based motion analysis (MLVMA’08), in ECCV’08. Marseille, France

    Google Scholar 

  23. Pérez Ó, Piccardi M, García J, Molina JM (2007) Comparison of classifiers for human activity recognition. In: IWINAC (2), pp 192–201

  24. Pérez Ó, Piccardi M, García J, Molina JM (2007) Comparison of classifiers for human activity recognition. In: IWINAC ’07: proceedings of the 2nd international work-conference on nature inspired problem-solving methods in knowledge engineering, pp 192–201

  25. Remagnino P, Tan T, Baker K (1998) Multi-agent visual surveillance of dynamic scenes. Image Vis Comput 16(8):529–532

    Article  Google Scholar 

  26. Ribeiro P, Santos-Victor J (2005) Human activities recognition from video: modeling, feature selection and classification architecture. In: Proc. workshop on human activity recognition and modelling (HAREM 2005), pp 61–70

  27. Simon C (2009) Visual event recognition: application on the caviar video clips and simulated trajectories. Technical report, TELE Lab, UCL, Belgium

  28. Simon C, Meessen J, Tzovaras D, De Vleeschouwer C (2007) Using decision trees for knowledge-assisted topologically structured data analysis. In: International workshop on image analysis for multimedia interactive services (WIAMIS). Santorini

  29. Stauffer C, Grimson W (1999) Adaptive background mixture models for real-time tracking. IEEE Comput Vis Pattern Recognit 2:25–258

    Google Scholar 

  30. Veeraraghavan H, Papanikolopoulos N, Schrater PR (2007) Learning dynamic event descriptions in image sequences. In: CVPR

  31. Wang L, Suter D (2007) Learning and matching of dynamic shape manifolds for human action recognition. Image Process IEEE Trans 16(6):1646–1661

    Article  MathSciNet  Google Scholar 

  32. Wehenkel L (1998) Automatic learning techniques in power systems. Kluwer, Boston

    MATH  Google Scholar 

  33. Xiang T, Shaogang G (2006) Beyond tracking: modelling activity and understanding behaviour. Int J Comput Vis 67(1):21–51

    Article  Google Scholar 

  34. Yilmaz A, Shah M (2005) Actions sketch: a novel action representation. Comput VisPattern Recognit (CVPR 05), IEEE Comput Soc Conf 1:984–989

    Article  Google Scholar 

  35. Zhang D, Gatica-Perez D, Bengio S, McCowan I (2005) Semi-supervised adapted hmms for unusual event detection. In: CVPR ’05: proceedings of the 2005 IEEE computer society conference on computer vision and pattern recognition (CVPR’05), vol 1, pp 611–618

Download references

Author information

Authors and Affiliations

  1. UCL, Communication and Remote Sensing Lab, Louvain-la-Neuve, Belgium

    Cédric Simon & Christophe De Vleeschouwer

  2. Multitel, Mons, Belgium

    Jérôme Meessen

Authors
  1. Cédric Simon
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Jérôme Meessen
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Christophe De Vleeschouwer
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Cédric Simon.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Simon, C., Meessen, J. & De Vleeschouwer, C. Visual event recognition using decision trees. Multimed Tools Appl 50, 95–121 (2010). https://doi.org/10.1007/s11042-009-0364-y

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-009-0364-y

Keywords

Search

Navigation