A Study of the Possibility of Usage Motion Vectors of Compressed Videos to Create Video Identification
https://doi.org/10.31854/1813-324X-2022-8-1-57-64
Abstract
The use of motion vectors for identifying video sequences has been well studied (in the framework of research on the topic CBCD – Content-Based Copy Detection ‒ detecting copies of videos based on content analysis). This makes it possible to check the similarity of two video fragments or search for a fragment in a larger video sequence. Existing and well-known methods for forming identification datasets typically use complete video stream decoding. The authors suggested using the motion vectors of a compressed video stream, which reduces the computational costs for identifying video sequences and uses simplified algorithms to generate identification data. Unlike the previously proposed methods, which implement either modified video codecs or obsolete ones, the authors propose using data formed by compression codecs that are used in the most common video hosting platforms (Youtube, Vimeo, etc.) The possibility of forming an automated system of comparing video sequences, along with its possibilities and limitations, will be studied in the following works.
About the Authors
R. Fahrutdinov
Saint Petersburg Federal Research Center of the Russian Academy of Sciences
Russian Federation
Russian Federation
St. Petersburg, 199178
A. Mirin
Saint Petersburg Federal Research Center of the Russian Academy of Sciences
Russian Federation
Russian Federation
St. Petersburg, 199178
References
1. Hampapur A., Bolle R.M. Comparison of Distance Measures for Video Copy Detection. IBM Research Report. Report number: RC 22056 (W0105-007). 14 May 2001. Available from: https://dominoweb.draco.res.ibm.com/reports/RC22056.pdf [Accessed 08th February 2022]
2. Ministry of Justice of Russian Federation. Extremist Materials. (in Russ.) Available from: https://minjust.gov.ru/ru/extremist-materials [Accessed 08th February 2022]
3. Yang X., Zhu Q., Cheng K.T. Near-Duplicate Detection for Images and Videos. Proceedings of the 1-st ACM workshop on Large-scale multimedia retrieval and mining, LS-MMRM’09, 23rd October 2009, Beijing, China. New York: Association for Computing Machinery; 2009. p.73‒80. DOI:10.1145/1631058.1631073
4. Chiu C.Y., Tsai T.H., Hsieh C.Y. Efficient video segment matching for detecting temporal-based video copies. Neurocomputing. 2013;105:70–80. DOI:10.1016/j.neucom.2012.04.036
5. Thomas R.M., Sumesh M.S. A Simple and Robust Colour Based Video Copy Detection on Summarized Videos. Procedia Computer Science. 2015;46:1668–1675. DOI:10.1016/j.procs.2015.02.106
6. Hu Y., Lu X. Learning spatial-temporal features for video copy detection by the combination of CNN and RNN. Journal of Visual Communication and Image Representation. 2018;55:21–29. DOI:10.1016/j.jvcir.2018.05.013
7. Lu Z.M., Li B., Ji Q.G., Tan Z.F., Zhang Y. Robust video identification approach based on local non-negative matrix factorization. International Journal of Electronics and Communications (AEÜ). 2015;69(1):82–89. DOI:10.1016/j.aeue.2014.07.021
8. Roopalakshmi R., Guddeti R.M.R. A Novel CBCD Approach Using MPEG-7 Motion Activity Descriptors. Proceedings of International Symposium on Multimedia, USA, 5‒7 December 2011, Dana Point. IEEE; 2011. p.179‒184. DOI:10.1109/ISM.2011.36
9. Taşdemir K., Çetin A.E. Content-based video copy detection based on motion vectors estimated using a lower frame rate. Signal, Image and Video Processing. 2014;8:1049–1057. DOI:10.1007/s11760-014-0627-6
10. Wasserman L. All of Statistics: A Concise Course in Statistical Inference. Springer Texts in Statistics. New York: Springer; 2004. DOI:10.1007/978-0-387-21736-9
Review
For citations:
Fahrutdinov R., Mirin A. A Study of the Possibility of Usage Motion Vectors of Compressed Videos to Create Video Identification. Proceedings of Telecommunication Universities. 2022;8(1):57-64. (In Russ.) https://doi.org/10.31854/1813-324X-2022-8-1-57-64
Views:
323
Email this article 