Scientific and Technical Journal


ISSN Print 2221-3937
ISSN Online 2221-3805

In this paper, the authors presented a system for evaluating the performance of event models for semantic analysis of video. The structure of the system, which consists of four modules, an input receives a video sequence, the scene specification, event model, and the ground truth. Matched sets of video data that allow the system input video and tagged data. The parameters of the model performance evaluation of events according to particular tasks recognition events for the combined model with a particle filter proposed to estimate the optimal number of particles to optimize the time complexity of the model. Experimental testing of model performance evaluation system events, the quantitative performance indicators event models .

Main modules of the developed system for evaluating the performance event models can be used for semantic analysis of video systems.  Our results will be interesting to specialists involved in the development of various applications of artificial intelligence applications based on the mining of dynamic video, such as security systems, law enforcement, traffic control systems , intelligent video surveillance systems , robotic systems, etc.


1. Antoshchuk S.G., and Godovychenko N.A. Modeli predstavleniya sobytiy pri analize videopotoka [Events Representation Models for Videostream Analysis], (2013), Elektrotechnic and Computer Systems Publ., Kiev, Ukraine, No. 11, pp. 142 – 149 (In Russian).

2. Antoshchuk S.G., and Godovychenko N.A. Modelirovanie sobytiy v videopotoke s pomoschyu stohasticheskih setey Petri [Modeling Events in Videostream With Stochastic Petri Nets], (2013), Optoelectronic Information-energy Technologies Publ., Vinnitsa, Ukraine, No. 1, pp. 5 – 12 (In Russian).

3. Antoshchuk S.G., and Godovychenko N.A. Uchet neopredelennosti dannyh pri modeli-rovanii sobytij s pomoshh'ju seti Petri [Accounting Data Uncertainty in Modeling Events With Petri Nets], (2013), Elektrotechnic and Computer Systems Publ., Kiev, Ukraine, No. 12 pp. 138 – 146 (In Russian).

4. Babenko B., Yang M. and Belongie S. Visual Tracking with Online Multiple Instance Learning, IEEE Transactions on Pattern Analysis and Machine Intelligence, (2011), pp. 102 – 110 (In English), doi:, url:

5. Cohn A. G., Magee D. R., Galata A., and others. Towards an Architecture for Cognitive Vision Using Spatial–temporal Representations and Abduction, (2003), In Spatial Cognition, No. 2, pp. 232 – 248 (In English), doi:

6. Hongeng S., and Nevatia R. Multi-agent Event Recognition,(2001), International Conference on Computer Vision, pp. 84 – 93 (In English), doi:10.1109/ICCV.2001.937608, url:

7. Hu W., Tan T., Wang L., and others. A Survey on Visual Surveillance of Object Motion and Behaviors, Systems, Man and Cybernetics, Part C., (2004), No. 4, pp. 334 – 352 (In English), doi: 10.1109/TSMCC.2004.829274, url: tion%20and%20Behaviors.pdf.

8. Isard M., and Blake A. Condensation – Conditional Density Propagation for Visual Tracking, (1998), International Journal of Computer Vision Publ., pp. 5 – 28 (In English), doi:

url: a/Stat_202C/lecture_note/Particle_filtering_Isard_1998.pdf

9. Medioni G.G., Cohen I., Bremond F., and others. Event detection and analysis from video streams, (2001), IEEE Transactions on Pattern Analysis and Machine Intelligence, No. 8, pp. 873 – 889 (In English), doi:10.1109/34.946990, url:

10. Shi Y., Huang Y., Minnen D., and others. Propagation Networks for Recognition of Partially Ordered Sequential Action, (2004), IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 862 – 869 (In English), doi:, url: 21364362_Propagation_Networks_for_Recogntion_of_Partially_Ordered_Sequential_Action/file/9c960514cab7b204cc.pdf.

11. Van Rijsbergen C. J. Information Retrieval, Oxford, (1979), Butterworth-Heinemann, 224 P.

12. Vu V., Bremond F., and Thonnat M. Automatic Video Interpretation: a Novel Algorithm for Temporal Scenario Recognition, (2003), International Joint Conference on Artificial Intelligence, No. 1, pp. 1295 – 1300 (In English), url:

Last download:
20 Jan 2020

[ © KarelWintersky ] [ All articles ] [ All authors ]
[ © Odessa National Polytechnic University, 2014-2018. Any use of information from the site is possible only under the condition that the source link! ]