Improved algorithm for tracking an object of one of the several predefined types
https://doi.org/10.29235/1561-8323-2026-70-2-102-107
Abstract
A new neural network algorithm for tracking objects observed in frames of video has been developed. The algorithm enables automatic detection of objects of one of the predefined types, reliable subsequent tracking, rapid redetection of the object if tracking was interrupted, and detection of a different object of the desired type if the tracked object disappears. Detection of the object of interest in video frames is performed using a neural network detector, and tracking is carried out by the developed algorithm using a neural network transformer.
About the Authors
B. A. Zalesky
United Institute of Informatics Problems of the National Academy of Sciences of Belarus
Belarus
Belarus
Zalesky Boris A. – D. Sc. (Physics and Mathematics), Head of the Laboratory
6, Surganov Str., 220012, Minsk
V. A. Ivanyukovich
United Institute of Informatics Problems of the National Academy of Sciences of Belarus
Belarus
Belarus
Ivanyukovich Vladimir A. – Junior Researcher
6, Surganov Str., 220012, Minsk
References
1. Object Tracking (2024). Available at: https://paperswithcode.com/task/object-tracking (accessed 05 January 2024).
2. Proceedings of Conference on Computer Vision and Pattern Recognition 2025. CVPR 2025. June 11th–15th, 2025. Available at: https://cvpr.thecvf.com/Conferences/2025 (accessed 03 Fabruary 2026).
3. Meibodi F. A., Alijani Sh., Najjaran H. A Deep Dive into Generic Object Tracking: A Survey. arXiv preprint, 2025, Jul. 31. Available at: https://arxiv.org/abs/2507.23251; https://doi.org/10.48550/arXiv.2507.23251
4. Zalesky B. A., Ivanyukovich V. A. Algorithm for tracking an object observed by а video camera. Doklady Natsional’noi akademii nauk Belarusi = Doklady of the National Academy of Sciences of Belarus, 2024, vol. 68, no. 2, pp. 105–111 (in Russian). https://doi.org/10.29235/1561-8323-2024-68-2-105-111
5. Zhang Y., Sun P., Jiang Y., Yu D., Weng F., Yuan Z., Luo P., Liu W., Wang X. ByteTrack: Multi-Object Tracking by Associating Every Detection. Avidan S., Brostow G., Cissé M., Farinella G.M., Hassner T. (eds). Computer Vision – ECCV 2022. ECCV 2022. Lecture Notes in Computer Science, vol. 13682. Springer, Cham., 2022, pp. 1–21. https://doi.org/10.1007/978-3-031-20047-2_1
Review
Views:
119
JATS XML
Email this article 