Advertisement

International Journal of Computer Vision

, Volume 67, Issue 1, pp 21–51 | Cite as

Beyond Tracking: Modelling Activity and Understanding Behaviour

  • Tao XiangEmail author
  • Shaogang Gong
Article

Abstract

In this work, we present a unified bottom-up and top-down automatic model selection based approach for modelling complex activities of multiple objects in cluttered scenes. An activity of multiple objects is represented based on discrete scene events and their behaviours are modelled by reasoning about the temporal and causal correlations among different events. This is significantly different from the majority of the existing techniques that are centred on object tracking followed by trajectory matching. In our approach, object-independent events are detected and classified by unsupervised clustering using Expectation-Maximisation (EM) and classified using automatic model selection based on Schwarz's Bayesian Information Criterion (BIC). Dynamic Probabilistic Networks (DPNs) are formulated for modelling the temporal and causal correlations among discrete events for robust and holistic scene-level behaviour interpretation. In particular, we developed a Dynamically Multi-Linked Hidden Markov Model (DML-HMM) based on the discovery of salient dynamic interlinks among multiple temporal processes corresponding to multiple event classes. A DML-HMM is built using BIC based factorisation resulting in its topology being intrinsically determined by the underlying causality and temporal order among events. Extensive experiments are conducted on modelling activities captured in different indoor and outdoor scenes. Our experimental results demonstrate that the performance of a DML-HMM on modelling group activities in a noisy and cluttered scene is superior compared to those of other comparable dynamic probabilistic networks including a Multi-Observation Hidden Markov Model (MOHMM), a Parallel Hidden Markov Model (PaHMM) and a Coupled Hidden Markov Model (CHMM).

Keywords

dynamic scene modelling graph models discrete event recognition activity representation behaviour recognition dynamic probabilistic networks Bayesian model selection 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Akaike, H. 1973. Information theory and an extension of the maximum likelihood principle. In 2nd International Symposium on Information Theory, pp. 267–281.Google Scholar
  2. Babaguchi, N., Kawai, Y., and Kitahashi, T. 2002. Event based indexing of broadcasting sports video by intermodal collaboration. IEEE Transactions on Multimedia, 4(1):68–75.CrossRefGoogle Scholar
  3. Baum, L.E. and Petrie, T. 1996. Statistical inference for probabilistic functions of finite state markov chains. Ann. Math. Stat., 37:1554–1563.MathSciNetGoogle Scholar
  4. Biernacki, C., Celeux, G., and Govaert, G. 2000. Assessing a mixture model for clustering with the integrated completed likelihood. IEEE Transactions on Pattern Analysis and Machine Intelligence, 22(7):719–725.CrossRefGoogle Scholar
  5. Bishop, C. 1995. Neural Networks for Pattern Recognition. Cambridge University Press.Google Scholar
  6. Bobick, A. and Wilson, A. 1997. A state-based approach to the representation and recognition of gesture. IEEE Transactions on Pattern Analysis and Machine Intelligence, 19(12):1325–1337.CrossRefGoogle Scholar
  7. Bobick, A.F. and Davis, J.W. 2001. The recognition of human movement using temporal templates. IEEE Transactions on Pattern Analysis and Machine Intelligence, 23(3):257–267.CrossRefGoogle Scholar
  8. Brand, M. and Kettnaker, V. 2000. Discovery and segmentation of activities in video. IEEE Transactions on Pattern Analysis and Machine Intelligence, 22(8):844–851.CrossRefGoogle Scholar
  9. Brand, M., Oliver, N., and Pentland, A. 1996. Coupled hidden markov models for complex action recognition. In IEEE Conference on Computer Vision and Pattern Recognition, Puerto Rico, pp. 994–999.Google Scholar
  10. Bregler, C. 1997. Learning and recognizing human dynamics in video sequences. In IEEE Conference on Computer Vision and Pattern Recognition, pp. 568–575.Google Scholar
  11. Buxton, H. and Gong, S. 1995. Visual surveillance in a dynamic and uncertain world. Artificial Intelligence, 78:431–459.CrossRefGoogle Scholar
  12. Chomat, O., Martin, J., and Crowley, J. 2000. A probabilistic sensor for the perception and the recognition of activities. In European Conference on Computer Vision, pp. 487–503.Google Scholar
  13. Figueiredo, M. and Jain, A.K. 2002. Unsupervised learning of finite mixture models. IEEE Transactions on Pattern Analysis and Machine Intelligence, 24(3):381–396.CrossRefGoogle Scholar
  14. Forney, G.D. 1973. The viterbi algorithm. Proceedings of the IEEE, 61:268–278.MathSciNetGoogle Scholar
  15. Friedman, N., Murphy, K., and Russell, S. 1998. Learning the structure of dynamic probabilistic networks. In Uncertainty in AI, pp. 139–147.Google Scholar
  16. Gath, I. and Geva, B. 1989. Unsupervised optimal fuzzy clustering. IEEE Transactions on Pattern Analysis and Machine Intelligence, 11(7):773–781.CrossRefGoogle Scholar
  17. Ghahramani, Z. 1998. Learning dynamic bayesian networks. In Adaptive Processing of Sequences and Data Structures. Lecture Notes in AI, pp. 168–197.Google Scholar
  18. Gong, S. and Buxton, H. 1992. On the visual expectations of moving objects: A probabilistic approach with augmented hidden markov models. In European Conference on Artificial Intelligence, Vienna, pp. 781–786.Google Scholar
  19. Gong, S., Ng, J., and Sherrah, J. 2002. On the semantics of visual behaviour, structured events and trajectories of human action. Image Vision Computing, 20(12):873–888.Google Scholar
  20. Gong, S., Walter, M., and Psarrou, A. 1999. Recognition of temporal structures: Learning prior and propagating observation augmented densities via hidden markov states. In IEEE International Conference on Computer Vision, Corfu, pp. 157–162.Google Scholar
  21. Gong, S. and Xiang, T. 2003. Recognition of group activities using dynamic probabilistic networks. In IEEE International Conference on Computer Vision, pp. 742–749.Google Scholar
  22. Greenspan, H., Goldberger, J., and Mayer, A. 2004. Probabilistic space-time video modelling via piecewise GMM. IEEE Transactions on Pattern Analysis and Machine Intelligence, 26(3):384–396.CrossRefGoogle Scholar
  23. Haritaoglu, I., Harwood, D., and Davis, L.S. 2000. w4: Real-time surveillance of people and their activities. IEEE Transactions on Pattern Analysis and Machine Intelligence, 22(8):809–830.CrossRefGoogle Scholar
  24. Heckerman, D. 1995. A tutorial on learning with Bayesian networks. Technical Report MSR-TR-95-06, Microsoft Research.Google Scholar
  25. Hongeng, S. and Nevatia, R. 2001. Multi-agent event recognition. In IEEE International Conference on Computer Vision, pp. 80–86.Google Scholar
  26. Hung, H. and Gong, S. 2004. Quantifying temporal saliency. In British Machine Vision Conference, pp. 727–736.Google Scholar
  27. Intille, S. and Bobick, A. 1998. Representation and visual recognition of complex multi-agent actions using Belief networks. In ECCV Workshop on Perception of Human Action, Freiburg, Germany.Google Scholar
  28. Intille, S., Davis, J., and Bobick, A. 1997. Real-time closed-world tracking. In IEEE Conference on Computer Vision and Pattern Recognition, pp. 697–703.Google Scholar
  29. Johnson, N., Galata, A., and Hogg, D. 1998. The acquisition and use of interaction behaviour models. In IEEE Conference on Computer Vision and Pattern Recognition, Santa Barbara, USA, pp. 866–871.Google Scholar
  30. Kass, R. and Raftery, A. 1995. Bayes factors. Journal of the American Statistical Association, 90:377–395.Google Scholar
  31. Rabiner, L.R. 1989. A tutorial on hidden Markov models and selected applications in speech recognition. Proceedings of the IEEE, 77(2):257–286.CrossRefGoogle Scholar
  32. McKenna, S., Jabri, S., Duric, Z., Rosenfeld, A., and Wechsler, H. 2000. Tracking group of people. Computer Vision and Image Understanding, 80:42–56.CrossRefGoogle Scholar
  33. Mclachlan, G. and Peel, D. 1997. Finite Mixture Models. John Wiley & Sons.Google Scholar
  34. Medioni, G., Cohen, I., Bremond, F., Hongeng, S., and Nevatia, R. 2001. Event detection and analysis from video streams. IEEE Transactions on Pattern Analysis and Machine Intelligence, 23(8):873–889.CrossRefGoogle Scholar
  35. Ng, J. and Gong, S. 2001. Learning pixel-wise signal energy for understanding semantics. In British Machine Vision Conference, pp. 695–704.Google Scholar
  36. Oliver, N., Rosario, B., and Pentland, A. 2000. A bayesian computer vision system for modelling human interactions. IEEE Transactions on Pattern Analysis and Machine Intelligence, 22(8):831–843.CrossRefGoogle Scholar
  37. Pavlovic, V., Rehg, J.M., Cham, T., and Murphy, K.P. 1999. A dynamic bayesian network approach to figure tracking using learned dynamic models. In IEEE International Conference on Computer Vision, pp. 94–101.Google Scholar
  38. Piater, J.H. and Crowley, J.L. 2001. Multi-modal tracking of interacting targets using gaussian approximation. In Proceedings of 2nd IEEE Workshop on Performance Evaluation of Tracking and Surveillance, pp. 141–147.Google Scholar
  39. Raftery, A. 1995. Bayes model selection in social research. Sociological Methodology, 90:181–196.Google Scholar
  40. Rao, C., Yilmaz, A., and Shah, M. 2002. View-invariant representation and recognition of actions. International Journal of Computer Vision, 50:203–226.CrossRefGoogle Scholar
  41. Rissanen, J. 1989. Stochastic Complexity in Statistical Inquiry. World Scentific.Google Scholar
  42. Roberts, S. 1997. Parametric and non-parametric unsupervised cluster analysis. Pattern Recognition, 30(2):261–272.CrossRefGoogle Scholar
  43. Roberts, S., Husmeier, D., Rezek, I., and Penny, W. 1998. Bayesian approaches to Gaussian mixture modelling. IEEE Transactions on Pattern Analysis and Machine Intelligence, 20(11):1133–1142.CrossRefGoogle Scholar
  44. Schwarz, G. 1978. Estimating the dimension of a model. Annals of Statistics, 6:461–464.zbMATHMathSciNetGoogle Scholar
  45. Sherrah, J. and Gong, S. 2000. VIGOUR: A system for tracking and recognition of multiple people and their activities. In International Conference on Pattern Recognition, Barcelona, pp. 179–182.Google Scholar
  46. Sherrah, J. and Gong, S. 2001. Automated detection of localised visual events over varying temporal scales. In Proc. European Workshop on Advanced Video-based Surveillance System.Google Scholar
  47. Smyth, P. 2000. Model selection for probabilistic clustering using cross-validated likelihood. Statistics and Computing, 10:63–72.CrossRefGoogle Scholar
  48. Stauffer, C. and Grimson, W. 2000. Learning patterns of activity using real-time tracking. IEEE Transactions on Pattern Analysis and Machine Intelligence, 22(8):747–758.CrossRefGoogle Scholar
  49. Vogler, C. and Metaxas, D. 2001. A framework for recognizing the simultaneous aspects of american sign language. Computer Vision and Image Understanding, 81:358–384.CrossRefGoogle Scholar
  50. Wada, T. and Matsuyama, T. 2000. Multiobject behavior recognition by event driven selective attention method. IEEE Transactions on Pattern Analysis and Machine Intelligence, 22(8):873–887.CrossRefGoogle Scholar
  51. Xiang, T. and Gong, S. 2003. Discovering bayesian causality among visual events in a complex outdoor scene. In IEEE International Conference on Advanced Video- and Signal-based Surveillance, pp. 177–182.Google Scholar
  52. Xiang, T., Gong, S., and Parkinson, D. 2002. Autonomous visual events detection and classification without explicit object-centred segmentation and tracking. In British Machine Vision Conference, pp. 233–242.Google Scholar

Copyright information

© Springer Science + Business Media, Inc. 2006

Authors and Affiliations

  1. 1.Department of Computer ScienceQueen Mary, University of LondonUK

Personalised recommendations