Motion vector extraction method for computer vision systems employing lossy compression

Purpose of research.  In the modern digital era, the role of video cameras as high‑quality sources of primary data is increasing. However, raw video data by themselves carry low informational value without subsequent analysis. The key tasks that allow extracting semantic information from a video sequence are object localization and motion detection. The relevance of this task is determined by its critical importance for a wide range of applied and research disciplines. Despite its long history, detecting moving objects remains a relevant scientific problem due to the following challenges: variability of lighting conditions, dynamic background, occlusion effects, and the need to operate in real time. The aim of this work is to reduce computational load when solving object motion analysis tasks in real time by developing and testing a method for extracting motion vectors from compressed video streams.

Methods. To achieve this goal, the framework of motion vectors was used as the basis for compensating temporal redundancy, along with computer vision algorithms and motion compensation algorithms in video data.

Results.  A software module has been developed that allows extracting motion vectors directly from a video stream. An experimental evaluation of the proposed method’s effectiveness was carried out, demonstrating its efficiency in various applied fields, including video surveillance, agriculture, and robotics, with a significant reduction in computational costs.

Conclusion. The experimental evaluations have shown that using motion vectors already contained in compressed video data allows effectively solving motion analysis tasks without the need to recalculate them. This is especially relevant for systems with limited computational resources.

1. Ryumin D., Axyonov A., Ryumina E., Ivanko D., Kashevnik A., Karpov A. Audiovisual speech recognition based on regulated transformer and spatio-temporal fusion strategy for driver assistive systems. Expert Systems with Applications. 2024; 252(12):124159. https://doi.org/10.1016/j.eswa.2024.124159.

2. Gupta S., Mamodiya U., Al-Gburi A. Speech Recognition-Based Wireless Control System for Mobile Robotics: Design, Implementation, and Analysis. Automation. 2025; 6(3):25. https://doi.org/10.3390/automation6030025.

3. Kashevnik A., Kovalenko S., Mamonov A., Hamoud B., Bulygin A., Kuznetsov V., Shoshina I., Brak I., Kiselev G. Intelligent Human Operator Mental Fatigue Assessment Method Based on Gaze Movement Monitoring. Sensors. 2024; 24(21):6805. https://doi.org/10.3390/s24216805.

4. Gershman S.J., Bill J., Drugowitsch J. Hierarchical Vector Analysis of Visual Motion Perception. Annual Review of Vision Science. 2025; 11:411-422. https://doi.org/10.1146/annurev-vision-110323-031344.

5. Paragios N., Chen Y., Faugeras O. (eds.). Mathematical Models in Computer Vision: The Handbook. New York: Springer; 2005. P. 239-258.

6. Kesrarat D., Patanavijit V. Noise resistance evaluation of spatial-field optical flow using modifying Lorentzian function. Bulletin of Electrical Engineering and Informatics. 2022; 11(5):2603-2610. https://doi.org/10.11591/eei.v11i5.3815.

7. Liu H., Fach S., Steinebach M. Motion Vector based Robust Video Hash. In: Proc. IS&T Int’l. Symp. on Electronic Imaging: Media Watermarking, Security, and Forensics. 2020. P. 218-1–218-7. https://doi.org/10.2352/ISSN.2470-1173.2020.4.MWSF-218.

8. Chang S., Wang R. Novel motion estimation algorithm for image stabilizer. Engineering Computations. 2017;34(1):77-89. https://doi.org/10.1108/EC-11-2015-0345.

9. Favorskaya M.N., Pakhirka A.I., Shilov A.S., Damov M.V. Motion search methods in video sequences. Vestnik Sibirskogo gosudarstvennogo aerokosmicheskogo universiteta im. akademika M.F. Reshetneva = Bulletin of the Siberian State Aerospace University. academician M.F. Reshetnev. 2009;(1-2):69-73. (In Russ.)

10. Chu Z, Li M. A Specific Algorithm Based on Motion Direction Prediction. Complexity. 2021; 2021:6678596. https://doi.org/10.1155/2021/6678596.

11. Richardson I.E.G. H.264 and MPEG-4 Video Compression. Chichester: John Wiley & Sons; 2003. P. 27-28.

12. Li D. Moving objects detection by block comparison. In: Proceedings of the 2000 IEEE International Conference on Electronics, Circuits and Systems. 2000. Vol. 1. P. 341-344.

13. Kuleshov S.V., Zaytseva A.A. Temporal analysis of H.264 codecs. Izvestiya Vysshikh Uchebnykh Zavedenii. Priborostroenie = News of higher educational institutions. Instrument engineerin. 2017;60(11):1092-1095. (In Russ.)

14. Kuleshov S.V. Hybrid codecs and their application in digital programmable data transmission channels. Informatsionno-izmeritel'nye i upravlyayushchie sistemy = Information-measuring and control systems. 2012;10(5):41-45. (In Russ.)

15. Chen R.-X., Zhao W., Fan J., Davari A. Vector Bank Based Multimedia Codec System-on-a-Chip (SoC) Design. In: 2009 International Symposium on Pervasive Systems, Algorithms, and Networks. 2009. P. 515-520. https://doi.org/10.1109/I-SPAN.2009.74.

16. Bratulin A.V., Nikiforov M.B., Belyakov P.V., Kholopov E.Y. Method for computing dense optical flow on FPGA in real time. Sovremennye informatsionnye tekhnologii i ITobrazovanie = Modern information technologies and IT education. 2019; 15(2):320-330. (In Russ.). https://doi.org/10.25559/SITITO.15.201902.320-330

17. Osipov V.Y., Kuleshov S.V., Zaytseva A.A., Surovtsev V.N., Achilov V.V. Analysis of the dynamics of the physiological state of productive cows based on video monitoring. Selskokhozyaistvennaya Biologiya = Agricultural Biology. 2024;59(6):1131-1144. (In Russ.). https://doi.org/10.15389/agrobiology.2024.6.1131rus.

18. Kuleshov S.V., Kvasnov A.V., Zaytseva A.A., Ronzhin A.L. An integrated approach to visual navigation by natural landmarks for UAVs operating in GNSS-denied conditions. Izvestiya YuFU. Tekhnicheskie Nauki = Izvestiya SFU. Technical sciences. 2025;(2):269278. (In Russ.)

19. Fakhrutdinov R.Sh., Mirin A.Y. Studying the possibility of using compressed video stream motion vectors for its identification. Trudy Uchebnykh Zavedenii Svyazi = Proceedings of educational institutions of communication. 2022; (8):57-64. (In Russ.). https://doi.org/10.31854/1813-324X-2022-8-1-57-64.