Analysis of features of application of neural networks for intellectual processing of video flows of technical vision systems

Скорочена інформація про документ
dc.contributor.authorTimoshin, Y.
dc.contributor.authorYuzhda, Y.
dc.date.accessioned2023-02-16T09:34:44Z
dc.date.available2023-02-16T09:34:44Z
dc.date.issued2021
dc.description.abstractenThe article considers topical issues of application of modern technologies and methods of object detection and recognition. The article is devoted to the analysis of the peculiarities of the application of different types of neural networks in the process of step - by - step processing of video data obtained from the systems of technical vision of robots, video monitoring systems, intelligent security systems. A review of modern literature, which describes the method of forming a space of features of the description of objects and methods of their recognition. The review shows that the process of intelligent processing of video data consists of many stages of image processing, one of which is processing using neural networks as intelligent components. The validity of the stages of processing in real time requires justification for the use of different types of neural networks in different processing processes in order to improve the quality and optimize the processing time of such data. The structure of the video image processing model is given. The article also defines the types of neural network at different stages of data processing (such as identification of parameters and characteristics of the group, finding group objects, sector-by-sector image processing, object classification, object recognition, creating a contour model of the object, detection object in the sector, evaluation of sector parameters, definition of information sectors, division of frames into sectors, processing of information frames) according to the proposed hierarchical model, with subsequent use of the obtained results for multiagent system of distributed intelligent processing of video monitoring objects and examples of further application the results obtained.uk
dc.format.pagerangeС. 12-19uk
dc.identifier.citationTimoshin, Y. Analysis of features of application of neural networks for intellectual processing of video flows of technical vision systems / Y. Timoshin, Y. Yuzhda // Адаптивні системи автоматичного управління : міжвідомчий науково-технічний збірник. – 2021. – № 2 (39). – С. 12-19. – Бібліогр.: 12 назв.uk
dc.identifier.doihttps://doi.org/10.20535/1560-8956.39.2021.247372
dc.identifier.urihttps://ela.kpi.ua/handle/123456789/52670
dc.language.isoenuk
dc.publisherКПІ ім. Ігоря Сікорськогоuk
dc.publisher.placeКиївuk
dc.sourceАдаптивні системи автоматичного управління : міжвідомчий науково-технічний збірник, 2021, № 2 (39)uk
dc.subjectneural networksuk
dc.subjectintellectual processinguk
dc.subjectreal-time processinguk
dc.subjectvideo datauk
dc.subjectvideo streamuk
dc.subjectcomputer vision systemsuk
dc.subjectprocessing modeluk
dc.subjectmultiagent systemuk
dc.subject.udc681.5.01uk
dc.titleAnalysis of features of application of neural networks for intellectual processing of video flows of technical vision systemsuk
dc.typeArticleuk

Файли

Контейнер файлів
Зараз показуємо 1 - 1 з 1
Ескіз
Назва:
ASAU_2021_2_p12-19.pdf
Розмір:
267.24 KB
Формат:
Adobe Portable Document Format
Опис:
Завантажити
Ліцензійна угода
Зараз показуємо 1 - 1 з 1
Ескіз недоступний
Назва:
license.txt
Розмір:
9.1 KB
Формат:
Item-specific license agreed upon to submission
Опис:
Завантажити

Зібрання

Адаптивні системи автоматичного управління : міжвідомчий науково-технічний збірник. – 2021. – № 2 (39)