Multi-level background initialization using Hidden Markov Models

ABSTRACT

Most of the automated video-surveillance applications are based on the process of background modelling, aimed at discriminating motion patterns of interest at pixel, region or frame level in a nearly static scene. The issues characterizing an ordinary background modelling process are typically three: the background model representation, the initialization, and the adaptation. This paper proposes a novel initialization algorithm, able to bootstrap an integrated pixel and region-based background modelling algorithm. The input is an uncontrolled video sequence in which moving objects are present, the output is a pixel- and region-level statistical background model describing the static information of a scene. At the pixel level, multiple hypotheses of the background values are generated by modelling the intensity of each pixel with a Hidden Markov Model (HMM), also capturing the sequentiality of the different color (or gray-level) intensities. At the region level, the resulting HMMs are clustered with a novel similarity measure, able to remove moving objects from a sequence, and obtaining a segmented image of the observed scene, in which each region is characterized by a similar spatio-temporal evolution. Experimental trials on synthetic and real sequences have shown the effectiveness of the proposed approach.

References

1. C. Bahlmann and H. Burkhardt. Measuring hmm similarity with the bayes probability of error and its application to online handwriting recognition. In Proc. Int. Conf. Document Analysis and Recognition, pages 406--411, 2001.
2. M. Bicego, V. Murino, and M. Figueiredo. A sequential pruning strategy for the selection of the number of states in Hidden Markov Models. Pattern Recognition Letters, 24(9--10):1395--1407, 2003.
3. M. Bicego, V. Murino, and M. Figueiredo. Similarity-based clustering of sequences using hidden Markov models. In P. Perner and A. Rosenfeld, editors, Machine Learning and Data Mining in Pattern Recognition, volume LNAI 2734, pages 86--95. Springer, 2003.
4. P. Brémaud. Markov Chains. Springer-Verlag, 1999.
5. M. Cristani, M. Bicego, and V. Murino. Integrated region- and pixel-based approach to background modelling. In Proc. of IEEE Workshop on Motion and Video Computing, pages 3--8, 2002.
6. Y. Deng and B. Manjunath. Unsupervised segmentation of color-texture regions in images and video. IEEE Trans. on Pattern Analysis and Machine Intelligence, 23(8):800--810, 2001.
7. N. Friedman and S. Russell. Image segmentation in video sequences: A probabilistic approach. In Uncertainty in Artificial Intelligence: Proceedings of the Thirteenth Conference (UAI-1997), pages 175--181, San Francisco, CA, 1997. Morgan Kaufmann Publishers.
8. X. Gao, T. Boult, F. Coetzee, and V. Ramesh. Error analysis of background adaption. In Proc. of IEEE Conf. on Computer Vision Pattern Recognition, volume I, pages 503--510, 2000.
9. B. Gloyer, H. Aghajan, K.-Y. Siu, and T. Kailath. Video-based freeway monitoring system using recursive vehicle tracking. In C. M. Bishop and B. J. Frey, editors, Proc. SPIE - The International Society for Optical Engineering, volume 2421, pages 747--757, 1995.
10. B. Gloyer, H. K. Aghajan, K. Y. Siu, and T. Kailath. Video-based freeway monitoring system using recursive vehicle tracking. In IS&T-SPIE Symposium on Electronic Imaging: Image and Video Processing, 1995.
11. D. Gutchessy, M. Trajkovicz, E. Cohen-Solalz, D. Lyonsz, and A. K. Jain. A background model initialization algorithm for video surveillance. In Proc. of IEEE Conf. on Computer Vision, 2001.
12. I. Haritaoglu, D. Harwood, and L. Davis. W4: real-time surveillance of people and their activities. IEEE Trans. on Pattern Analysis and Machine Intelligence, 22(8):809--830, 2000.
13. M. Harville. A framework for high-level feedback to adaptive, per-pixel, mixture-of-gaussian background models. In European Conf. Computer Vision, volume 3, pages 543--560, 2002.
14. O. Javed, K. Shafique, and M. Shah. A hierarchical approach to robust background subtraction using color and gradient information. In Proc. of IEEE Workshop on Motion and Video Computing, pages 22--27, 2002.
15. M. Law and J. Kwok. Rival penalized competitive learning for model-based sequence. In Proc. Int. Conf. Pattern Recognition, volume 2, pages 195--198, 2000.
16. C. Li and G. Biswas. A bayesian approach to temporal data clustering using hidden Markov models. In Proc. Int. Conf. on Machine Learning, pages 543--550, 2000.
17. C. Li and G. Biswas. Applying the Hidden Markov Model methodology for unsupervised learning of temporal data. Int. Journal of Knowledge-based Intelligent Engineering Systems, 6(3):152--160, 2002.
18. W. Long and Y. Yang. Stationary background generation: An alternative to the difference of two images. Pattern Recognition, 23:1351--1359, 1990.
19. N. Ohta. A statistical approach to background subtraction for surveillance systems. In Int. Conf. Computer Vision, volume 2, pages 481--486, 2001.
20. A. Panuccio, M. Bicego, and V. Murino. A Hidden Markov Model-based approach to sequential data clustering. In T. Caelli, A. Amin, R. Duin, M. Kamel, and D. de Ridder, editors, Structural, Syntactic and Statistical Pattern Recognition, LNCS 2396, pages 734--742. Springer, 2002.
21. M. Petkovic and W. Jonker. Content-based video retrieval by integrating spatio-temporal and stochastic recognition of events. In Proc. of IEEE Workshop on Detection and Recognition of Events in Video, pages 75--82, 2001.
22. N. Petrovic, N. Jojic, B. J. Frey, and T. S. Huang. Real-time on-line learning of transformed hidden markov models from video. In C. M. Bishop and B. J. Frey, editors, Ninth International Workshop on Artificial Intelligence and Statistics, 2003.
23. L. Rabiner. A tutorial on Hidden Markov Models and selected applications in speech recognition. Proc. of IEEE, 77(2):257--286, 1989.
24. P. Smyth. Clustering sequences with hidden Markov models. In M. Mozer, M. Jordan, and T. Petsche, editors, Advances in Neural Information Processing, volume 9. MIT Press, 1997.
25. C. Stauffer and W. Grimson. Adaptive background mixture models for real-time tracking. In Int. Conf. Computer Vision and Pattern Recognition, volume 2, 1999.
26. C. Stauffer and W. Grimson. Learning patterns of activity using real-time tracking. IEEE Trans. on Pattern Analysis and Machine Intelligence, 22(8):747--757, 2000.
27. B. Stenger, V. Ramesh, N. Paragios, F. Coetzee, and J. M. Buhmann. Topology free hidden Markov models: Application to background modeling. In Int. Conf. Computer Vision, volume 1, pages 294--301, 2001.
28. H. Tao, H. Sawhney, and R. Kumar. Object tracking with bayesian estimation of dynamic layer representations. IEEE Trans. on Pattern Analysis and Machine Intelligence, 24(1):75--89, 2002.
29. K. Toyama, J. Krumm, B. Brumitt, and B. Meyers. Wallflower: Principles and practice of background maintenance. In Int. Conf. Computer Vision, pages 255--261, 1999.
30. C. Wren, A. Azarbayejani, T. Darrell, and A. Pentland. Pfinder: Real-time tracking of the human body. IEEE Trans. on Pattern Analysis and Machine Intelligence, 19(7):780--785, 1997.
31. Y. Yacoob and M. Black. Parameterized modeling and recognition of activities. Computer Vision and Image Understanding: CVIU, 73(2):232--247, 1999.

Index Terms

• Computing methodologies

  • Artificial intelligence

    • Computer vision

      • Computer vision tasks

        • Video summarization

  • Machine learning

    • Learning paradigms

      • Unsupervised learning

        • Cluster analysis