Object Detection for Virtual Assistant in Cryolaboratory Based on Detectron2 Framework

Research output: Chapter in book/report/conference proceedingConference contributionResearchpeer review

Authors

  • Anastasiia Lytvyn
  • Kateryna Posokhova
  • Maksym Tymkovych
  • Oleg Avrunin
  • Oleksandra Hubenia
  • Birgit Glasmacher

Research Organisations

External Research Organisations

  • Kharkov National University of Radio Electronics
  • National Academy of Sciences of Ukraine
  • Institute for Problems of Cryobiology and Cryomedicine
View graph of relations

Details

Original languageEnglish
Title of host publication2024 IEEE 17th International Conference on Advanced Trends in Radioelectronics, Telecommunications and Computer Engineering (TCSET)
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages534-539
Number of pages6
ISBN (electronic)9798331520564
ISBN (print)979-8-3315-2057-1
Publication statusPublished - 2024
Event17th IEEE International Conference on Advanced Trends in Radioelectronics, Telecommunications and Computer Engineering, TCSET 2024 - Lviv, Ukraine
Duration: 8 Oct 202412 Oct 2024

Abstract

In this work, the previously proposed structural scheme of a virtual assistant is intended for training biomedical engineers and other specialists in working with specialized high-tech equipment, using a cryolaboratory as an example. The necessity of incorporating a specialized detection stage, which should consider the specific visual characteristics of the particular laboratory, has been demonstrated. Three models were trained on the R-CNN architecture (based on the Detectron2 framework) to create a virtual guide for a 3D cryolaboratory. The metrics of the obtained models were analyzed, and their suitability for specific tasks was evaluated. The obtained results indicate sufficient detection performance of the cryo-laboratory components, allowing the use of the developed models to create a specialized virtual assistant.

Keywords

    biomedical engineering, cryo laborato ry, deep learning, Detectron2, education, health care, object detection

ASJC Scopus subject areas

Cite this

Object Detection for Virtual Assistant in Cryolaboratory Based on Detectron2 Framework. / Lytvyn, Anastasiia; Posokhova, Kateryna; Tymkovych, Maksym et al.
2024 IEEE 17th International Conference on Advanced Trends in Radioelectronics, Telecommunications and Computer Engineering (TCSET). Institute of Electrical and Electronics Engineers Inc., 2024. p. 534-539.

Research output: Chapter in book/report/conference proceedingConference contributionResearchpeer review

Lytvyn, A, Posokhova, K, Tymkovych, M, Avrunin, O, Hubenia, O & Glasmacher, B 2024, Object Detection for Virtual Assistant in Cryolaboratory Based on Detectron2 Framework. in 2024 IEEE 17th International Conference on Advanced Trends in Radioelectronics, Telecommunications and Computer Engineering (TCSET). Institute of Electrical and Electronics Engineers Inc., pp. 534-539, 17th IEEE International Conference on Advanced Trends in Radioelectronics, Telecommunications and Computer Engineering, TCSET 2024, Lviv, Ukraine, 8 Oct 2024. https://doi.org/10.1109/TCSET64720.2024.10755685
Lytvyn, A., Posokhova, K., Tymkovych, M., Avrunin, O., Hubenia, O., & Glasmacher, B. (2024). Object Detection for Virtual Assistant in Cryolaboratory Based on Detectron2 Framework. In 2024 IEEE 17th International Conference on Advanced Trends in Radioelectronics, Telecommunications and Computer Engineering (TCSET) (pp. 534-539). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/TCSET64720.2024.10755685
Lytvyn A, Posokhova K, Tymkovych M, Avrunin O, Hubenia O, Glasmacher B. Object Detection for Virtual Assistant in Cryolaboratory Based on Detectron2 Framework. In 2024 IEEE 17th International Conference on Advanced Trends in Radioelectronics, Telecommunications and Computer Engineering (TCSET). Institute of Electrical and Electronics Engineers Inc. 2024. p. 534-539 doi: 10.1109/TCSET64720.2024.10755685
Lytvyn, Anastasiia ; Posokhova, Kateryna ; Tymkovych, Maksym et al. / Object Detection for Virtual Assistant in Cryolaboratory Based on Detectron2 Framework. 2024 IEEE 17th International Conference on Advanced Trends in Radioelectronics, Telecommunications and Computer Engineering (TCSET). Institute of Electrical and Electronics Engineers Inc., 2024. pp. 534-539
Download
@inproceedings{d3b3c10dd6b64a44a7efb4501b094026,
title = "Object Detection for Virtual Assistant in Cryolaboratory Based on Detectron2 Framework",
abstract = "In this work, the previously proposed structural scheme of a virtual assistant is intended for training biomedical engineers and other specialists in working with specialized high-tech equipment, using a cryolaboratory as an example. The necessity of incorporating a specialized detection stage, which should consider the specific visual characteristics of the particular laboratory, has been demonstrated. Three models were trained on the R-CNN architecture (based on the Detectron2 framework) to create a virtual guide for a 3D cryolaboratory. The metrics of the obtained models were analyzed, and their suitability for specific tasks was evaluated. The obtained results indicate sufficient detection performance of the cryo-laboratory components, allowing the use of the developed models to create a specialized virtual assistant.",
keywords = "biomedical engineering, cryo laborato ry, deep learning, Detectron2, education, health care, object detection",
author = "Anastasiia Lytvyn and Kateryna Posokhova and Maksym Tymkovych and Oleg Avrunin and Oleksandra Hubenia and Birgit Glasmacher",
note = "Publisher Copyright: {\textcopyright} 2024 IEEE.; 17th IEEE International Conference on Advanced Trends in Radioelectronics, Telecommunications and Computer Engineering, TCSET 2024 ; Conference date: 08-10-2024 Through 12-10-2024",
year = "2024",
doi = "10.1109/TCSET64720.2024.10755685",
language = "English",
isbn = "979-8-3315-2057-1",
pages = "534--539",
booktitle = "2024 IEEE 17th International Conference on Advanced Trends in Radioelectronics, Telecommunications and Computer Engineering (TCSET)",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

Download

TY - GEN

T1 - Object Detection for Virtual Assistant in Cryolaboratory Based on Detectron2 Framework

AU - Lytvyn, Anastasiia

AU - Posokhova, Kateryna

AU - Tymkovych, Maksym

AU - Avrunin, Oleg

AU - Hubenia, Oleksandra

AU - Glasmacher, Birgit

N1 - Publisher Copyright: © 2024 IEEE.

PY - 2024

Y1 - 2024

N2 - In this work, the previously proposed structural scheme of a virtual assistant is intended for training biomedical engineers and other specialists in working with specialized high-tech equipment, using a cryolaboratory as an example. The necessity of incorporating a specialized detection stage, which should consider the specific visual characteristics of the particular laboratory, has been demonstrated. Three models were trained on the R-CNN architecture (based on the Detectron2 framework) to create a virtual guide for a 3D cryolaboratory. The metrics of the obtained models were analyzed, and their suitability for specific tasks was evaluated. The obtained results indicate sufficient detection performance of the cryo-laboratory components, allowing the use of the developed models to create a specialized virtual assistant.

AB - In this work, the previously proposed structural scheme of a virtual assistant is intended for training biomedical engineers and other specialists in working with specialized high-tech equipment, using a cryolaboratory as an example. The necessity of incorporating a specialized detection stage, which should consider the specific visual characteristics of the particular laboratory, has been demonstrated. Three models were trained on the R-CNN architecture (based on the Detectron2 framework) to create a virtual guide for a 3D cryolaboratory. The metrics of the obtained models were analyzed, and their suitability for specific tasks was evaluated. The obtained results indicate sufficient detection performance of the cryo-laboratory components, allowing the use of the developed models to create a specialized virtual assistant.

KW - biomedical engineering

KW - cryo laborato ry

KW - deep learning

KW - Detectron2

KW - education

KW - health care

KW - object detection

UR - http://www.scopus.com/inward/record.url?scp=85212405748&partnerID=8YFLogxK

U2 - 10.1109/TCSET64720.2024.10755685

DO - 10.1109/TCSET64720.2024.10755685

M3 - Conference contribution

AN - SCOPUS:85212405748

SN - 979-8-3315-2057-1

SP - 534

EP - 539

BT - 2024 IEEE 17th International Conference on Advanced Trends in Radioelectronics, Telecommunications and Computer Engineering (TCSET)

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 17th IEEE International Conference on Advanced Trends in Radioelectronics, Telecommunications and Computer Engineering, TCSET 2024

Y2 - 8 October 2024 through 12 October 2024

ER -