Artificial intelligence and machine learning

Research Article

DOI 10.25209/2079-3316-2024-15-4-111-151

An analytical review of architectures, models, methods and algorithms for localization and tracking of non-rigid objects

Grigory Glebovich Gricenko¹, Vitaly Petrovich Fralenko²

1,2	Ailamazyan Program Systems Institute of RAS, Ves'kovo, Russia
1	GregorGre@mail.ru

Abstract. Computer vision requires video stream analysis, including extracting information from frames, detecting specific objects, and collecting data about them. After detection, tracking or following objects in the video stream is often required. Non-rigidity or shape variability hinders object analysis, complicates their detection and tracking, and worsens localization.

The review considers architectures, models, methods, and algorithms used in practice for detection and tracking of non-rigid objects, and highlights promising solutions. (In Russian).

Keywords: non-rigid object, artificial neural network, deep learning, object localization, object tracking, fire and smoke detection, medical image analysis

MSC-2020

68T45; 68T07

Acknowledgments: This work was financially supported by the Russian Science Foundation, project № 21-71-10056 and a grant in the form of a subsidy from the regional budget to organizations of the Yaroslavl region.

For citation: Grigory G. Gricenko, Vitaly P. Fralenko. An analytical review of architectures, models, methods and algorithms for localization and tracking of non-rigid objects. Program Systems: Theory and Applications, 2024, 15:4, pp. 111–151. (In Russ.). https://psta.psiras.ru/2024/4_111-151.

Full text of article (PDF): https://psta.psiras.ru/read/psta2024_4_111-151.pdf.

The article was submitted 08.10.2024; approved after reviewing 22.12.2024; accepted for publication 22.12.2024; published online 26.12.2024.