Zobrazeno 1 - 10
of 16
pro vyhledávání: '"R. P. Bohush"'
Autor:
S. A. Ihnatsyeva, R. P. Bohush
Publikováno v:
Sistemnyj Analiz i Prikladnaâ Informatika, Vol 0, Iss 1, Pp 12-17 (2024)
For people re-identification in distributed video surveillance systems, it is important to have an algorithm that ensures efficiency when a person is blocked by other people or objects. Therefore, for this task, an algorithm has been developed that i
Externí odkaz:
https://doaj.org/article/1573e318033146a1b7ccb5cade850805
Autor:
S. A. Ihnatsyeva, R. P. Bohush
Publikováno v:
Doklady Belorusskogo gosudarstvennogo universiteta informatiki i radioèlektroniki, Vol 21, Iss 3, Pp 87-95 (2023)
To improve the person re-identification system accuracy, an integrated approach is proposed in the formation of a training sample for convolutional neural networks, which involves the use of a new image dataset, an increase in the training examples n
Externí odkaz:
https://doaj.org/article/0e143ce65f754685b8251bdb389648de
Autor:
S. A. Ihnatsyeva, R. P. Bohush
Publikováno v:
Informatika, Vol 20, Iss 1, Pp 40-54 (2023)
Objectives. The main goal is to improve person re-identification accuracy in distributed video surveillance systems.Methods. Machine learning methods are applied.Result. A technology for two-stage training of convolutional neural networks (CNN) is pr
Externí odkaz:
https://doaj.org/article/6ab3b11bd74a4b58895c8c876286f078
Publikováno v:
Doklady Belorusskogo gosudarstvennogo universiteta informatiki i radioèlektroniki, Vol 19, Iss 4, Pp 70-79 (2021)
An algorithmic support for metallographic images preprocessing and analysis is presented. The software product implements metallographic methods for the grain size determination by comparison of rating scales, counting beans, calculation of grain bou
Externí odkaz:
https://doaj.org/article/8e4b3d905f044133a708b3356d1f5ba8
Autor:
R. P. Bohush, S. V. Ablameyko
Publikováno v:
Informatika, Vol 18, Iss 1, Pp 43-60 (2021)
One of the promising areas of development and implementation of artificial intelligence is the automatic detection and tracking of moving objects in video sequence. The paper presents a formalization of the detection and tracking of one and many obje
Externí odkaz:
https://doaj.org/article/4dc01f13859c4592af073a0e7c467c76
Publikováno v:
Informatika, Vol 17, Iss 2, Pp 7-16 (2020)
In the paper the algorithm for object detection in high resolution images is proposed. The approach uses multiscale image representation followed by block processing with the overlapping value. For each block the object detection with convolutional n
Externí odkaz:
https://doaj.org/article/15037df4de9248b2b7f6161ade40a3ae
Autor:
R. P. Bohush, D. A. Tychko
Publikováno v:
Doklady Belorusskogo gosudarstvennogo universiteta informatiki i radioèlektroniki, Vol 0, Iss 6, Pp 65-71 (2019)
An algorithm to detect the main signs of fire for video surveillance systems, which allows the detection of smoke, open flames, and their combination on dynamic images is proposed. A distinctive feature of the algorithm is the use of motion estimatio
Externí odkaz:
https://doaj.org/article/367fd285cc8041398268d8ca3f207229
Publikováno v:
Journal of Applied Spectroscopy. 89:322-329
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::862b8dc1bc19fa771f3b2c06f89792c8
https://doi.org/10.1007/s10812-022-01361-1
https://doi.org/10.1007/s10812-022-01361-1
Publikováno v:
Pattern Recognition and Image Analysis. 31:261-270
An algorithm for detecting and tracking moving people on video sequences using the block optical flow method and motion maps is proposed. To reduce time expenditures, a pyramidal representation of the frame and template search are used at the stage o
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c42f70fe4ccf6e6b1eceffc215b47ca7
https://doi.org/10.1134/s105466182102005x
https://doi.org/10.1134/s105466182102005x
Publikováno v:
Pattern Recognition and Image Analysis. 30:147-159
Some similarity functions for comparing the features of objects in the processing of static images and video sequences are proposed. These functions provide the possibility to find the normalized similarity value and are determined by calculating the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e6475cb77c548f2a33c04fca70b8bc2c
https://doi.org/10.1134/s1054661820020030
https://doi.org/10.1134/s1054661820020030