DESIGN OF EVENTS IN A VIDEOSTREAM BY MEANS OF STOCHASTIC PETRI NETS

Authors

  • S. H. Antoshchuk Odessa National Polytechnic University
  • N. A. Hodovychenko Odessa National Polytechnic University

Keywords:

event recognition, event model, semantic model, Petri net, Markov Chain, probabilistic prediction

Abstract

The event model based on a modified Petri net for the problem of event recognition was suggested. The new type of transition – stochastic transition for the simulation of events with elective duration was introduced. Representation of temporal relations between the components of the event based on temporal logic was offered. For the probabilistic prediction of future events a Markov chain based on Petri net markup was introduced. Testing of the proposed model was conducted.

Author Biographies

S. H. Antoshchuk, Odessa National Polytechnic University

Doctor. Sc. Science, professor, information systems zaveduyuschaya kafedroy

N. A. Hodovychenko, Odessa National Polytechnic University

PhD student, Department of Information Systems Assistant

References

1. Hu W. A survey on visual surveillance of object motion and behaviors / W. Hu, T. Tan, L. Wang, S. Maybank // Systems, Man and Cybernetics, Part C. – 2004. – №4. – P. 334-352.
2. 2. Ghanem N. Representation and recognition of events in surveillance video using Petri Nets / N. Ghanem, D. DeMenthon, D. Doermann, L. Davis // Computer Vision and Pattern Recognition Workshop. – 2004. – №1. – P. 112-132.
3. 3. Medioni G. G. Event detection and analysis from video streams / G. G. Medioni, I. Cohen, F. Bremond, S. Hongeng, R. Nevatia // IEEE Transactions on Pattern Analysis and Machine Intelligence. – 2001. – №8. – P. 873-889.
4. 4. Cohn A. G. Towards an architecture for cognitive vision using spatio-temporal representations and abduction / A. G. Cohn, D. R. Magee, A. Galata, D. Hogg, S. M. Hazarika // In Spatial Cognition. – 2003. – №2. – P. 232-248.
5. 5. Buxton H. Generative Models for Learning and Understanding Dynamic Scene Activity / H. Buxton // ECCV Workshop on Generative Model Based Vision. – 2002. – P. 154-169.
6. 6. Howarth R. J. Conceptual descriptions from monitoring and watching image sequences / R. J. Howarth, H. Buxton // Image and Vision Computing. – 2000. – №18. – P. 105-135.
7. 7. Bobick A. F. Movement, activity and action: The role of knowledge in the perception of motion / A. F. Bobick // Royal Society Workshop on Knowledge-based Vision in Man and Machine. – 1997. – №6. – P. 1257-1265.
8. Ng A. Y. On discriminative vs. generative classifiers: A comparison of logistic regression and naive Bayes / A. Y. Ng, M. I. Jordan // Neural Information Processing Systems. – 2001. – №1. – P. 841-848.
9. Ulusoy I. Generative versus discriminative methods for object recognition / I. Ulusoy, C. M. Bishop // Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. – 2005. – №2. – P. 258-265.
10. Коваленко Н. В., Годовиченко Н. А. Модель системы семантического анализа видеопотока для выявления девиантного поведения объектов интереса / Н. В. Коваленко, Н. А. Годовиченко // Искусственный интеллект. – 2012. – №4. – C. 124-132.
11. Hongeng S. Multi-agent event recognition / S. Hongenhg, R. Nevatia // International Conference on Computer Vision. – 2001. – P. 84-93.
12. Allen F. J. Actions and Events in Interval Temporal Logic / J. F. Allen, G. Ferguson // Journal of Logic and Computation. – 1994. - №4(5). – P. 531 – 579.

Downloads

Abstract views: 216

How to Cite

[1]
S. H. Antoshchuk and N. A. Hodovychenko, “DESIGN OF EVENTS IN A VIDEOSTREAM BY MEANS OF STOCHASTIC PETRI NETS”, Опт-ел. інф-енерг. техн., vol. 25, no. 1, pp. 5–11, Jan. 2014.

Issue

Section

OptoElectronic/Digital Methods and Systems for Image/Signal Processing

Metrics

Downloads

Download data is not yet available.