(49-5) 15 * << * >> * Russian * English * Content * All Issues

Development of a methodology for selecting machine learning models for recognizing moving objects in a video stream based on production rules
A.A. Smetanin 1, A.V. Dukhanov 1, M.Y. Gerasimchuk 1

National Research University of ITMO,
Kronverksky pr-t 49, St. Petersburg, 197101, Russia

 PDF, 1355 kB

DOI: 10.18287/2412-6179-CO-1583

Pages: 826-834.

Full text of article: Russian language.

Abstract:
To date, technologies in the field of photo-video data processing, algorithms for recognizing and classifying objects in images, have become more accurate, often exceeding the accuracy threshold of 90%. Such technological breakthroughs have led to extensive use of these innovations for professional and personal purposes. However, the variation of factors such as the conditions for obtaining and processing images, the dynamics and deformation of objects in the frame, can complicate the practical application of these algorithms. The presented scientific research focuses on the development of a recommendation system for choosing optimal machine learning models in order to solve a wide range of tasks related to object recognition. The principle of forming recommendations is generated on the basis of production rules, which are developed taking into account experimental data and analysis of academic sources. The result of the proposed system is not just a list of models indicating their relevance, but also proposals for the creation of machine learning pipelines and recommendations for the installation and use of appropriate program libraries. The current article describes a methodology for automating the formation of recommendations, including a priori estimation of metric values in the context of object classification tasks in images.

Keywords:
machine learning algorithms, object recognition, recommendation system, production rules, machine learning pipelines.

Citation:
Smetanin AA, Dukhanov AV, Gerasimchuk MY. Development of a methodology for selecting machine learning models for recognizing moving objects in a video stream based on production rules. Computer Optics 2025; 49(5): 826-834. DOI: 10.18287/2412-6179-CO-1583.

Acknowledgements:
This research is financially supported by the Ministry of Science and Higher Education, agreement FSER-2024-0004.

References:

  1. LeCun Y, Bengio Y, Hinton G. Deep learning. Nature 2015; 521(7553): 436-444. DOI: 10.1038/nature14539.
  2. Butz MV. Towards strong AI. KI – Künstliche Intelligenz 2021; 35(1): 91-101. DOI: 10.1007/s13218-021-00705-x.
  3. Adomavicius G, Tuzhilin A. Toward the next generation of recommender systems: A survey of the state-of-the-art and possible extensions. IEEE Trans Knowl Data Eng 2005; 17(6): 734-749. DOI: 10.1109/TKDE.2005.99.
  4. Tu NV, Cuong LA. A deep learning model of multiple knowledge sources integration for community question answering. VNU Journal of Science: Computer Science and Communication Engineering 2021; 37(1). Source: <https://jcsce.vnu.edu.vn/index.php/jcsce/article/view/295/128>. DOI: 10.25073/2588-1086/vnucsce.295.
  5. Diwan T, Anirudh G, Tembhurne JV. Object detection using YOLO: challenges, architectural successors, datasets and applications.Multimed Tools Appl 2023; 82(6): 9243-9275. DOI: 10.1007/s11042-022-13644-y.
  6. Chen W, et al. YOLO-face: a real-time face detector. Vis Comput 2021; 37(4): 805-813. DOI: 10.1007/s00371-020-01831-7.
  7. Liu W, et al. SSD: Single shot multibox detector. In Book: Leibe B, Matas J, Sebe N, Welling M, eds. Computer vision – ECCV 2016. 14th European Conference, Amsterdam, The Netherlands, October 11–14, 2016, Proceedings, Part I. Cham, Switzerland: Springer International Publishing AG; 2016: 21-37. DOI: 10.1007/978-3-319-46448-0_2.
  8. He K, et al. Mask R-CNN. IEEE Trans Pattern Anal Mach Intell 2020; 42(2): 386-397. DOI: 10.1109/TPAMI.2018.2844175.
  9. Chaudhuri A. Hierarchical modified fast R-CNN for object detection. Informatica (Slovenia) 2021; 45(7): 67-82. DOI: 10.31449/inf.v45i7.3732.
  10. Chen W, et al. A review of object detection: Datasets, performance evaluation, architecture, applications and current trends.Multimed Tools Appl 2024; 83(24): 65603-65661. DOI: 10.1007/S11042-023-17949-4.
  11. He X, Zhao K, Chu X. AutoML: A survey of the state-of-the-art.Knowl Based Syst 2021; 212: 106622. DOI: 10.1016/j.knosys.2020.106622.
  12. saaresearch/ODRS 2025. Source: <https://github.com/saaresearch/ODRS>.
  13. Chen X, et al. No-reference color image quality assessment: from entropy to perceptual quality. EURASIP J Image Video Process 2019; 2019(1): 77. DOI: 10.1186/s13640-019-0479-7.
  14. saaresearch/ODRS_WEB. 2025. Source: <https://github.com/saaresearch/ODRS_WEB>.
  15. Aerial Maritime Drone. 2025. Source: <https://www.kaggle.com/datasets/ammarnassanalhajali/aerial-maritime>.
  16. InSystem – Intelligent Systems AI. 2025. Source: <https://insystem.io/>.
  17. iTMO. 2025. Source: <https://en.itmo.ru/>.
  18. AIRI. AIRI Institute. 2025. Source: <https://airi.net/?force=en>.

© 2009, IPSI RAS
151, Molodogvardeiskaya str., Samara, 443001, Russia; E-mail: journal@computeroptics.ru ; Tel: +7 (846) 242-41-24 (Executive secretary), +7 (846) 332-56-22 (Issuing editor), Fax: +7 (846) 332-56-20