Depending on the amount of data to process, file generation may take longer.

If it takes too long to generate, you can limit the data by, for example, reducing the range of years.

Article

Download file Download BibTeX

Title

ISO-compatible personal temperature measurement using visual and thermal images with facial region of interest detection

Authors

[ 1 ] Wydział Automatyki, Robotyki i Elektrotechniki, Politechnika Poznańska | [ 2 ] Instytut Sieci Teleinformatycznych, Wydział Informatyki i Telekomunikacji, Politechnika Poznańska | [ 3 ] Instytut Robotyki i Inteligencji Maszynowej, Wydział Automatyki, Robotyki i Elektrotechniki, Politechnika Poznańska | [ SzD ] doctoral school student | [ P ] employee

Scientific discipline (Law 2.0)

[2.2] Automation, electronics, electrical engineering and space technologies
[2.3] Information and communication technology

Year of publication

2024

Published in

IEEE Access

Journal year: 2024 | Journal volume: vol. 12

Article type

scientific article

Publication language

english

Keywords
EN
  • thermal imaging
  • temperature measurement
  • computer vision
  • deep learning
Abstract

EN Disease outbreaks and pandemics show us how important it is to limit the spread of diseases. One common indicator of many ailments is body temperature. It’s a measurement that can be taken quickly, also using contactless methods. However, it is necessary to ensure the methodological correctness, repeatability and reliability of such measurement. In this manuscript, we introduce a non-intrusive approach for individual body temperature assessment that adheres to the stipulated criteria outlined by ISO/IEC 80601-2-59 standard. The measurements are performed at specific regions of interest (ROIs) of a human face, at the inner canthi of both eyes, which show high robustness to the environment temperature change. The method utilises the fusion of RGB-D (red, green, blue and depth) and thermal cameras. The system detects the ROIs on the RGB image employing deep learning methods and transfers them to the thermal image, from which the temperature can be read. The system was tested on our validation dataset consisting of 210 individuals, achieving ROI’s position identification mean error below 3 mm and temperature measurement error below 0.5°C, which is in line with the ISO norm requirements.

Pages (from - to)

44262 - 44277

DOI

10.1109/ACCESS.2024.3377448

URL

https://ieeexplore.ieee.org/document/10472492

License type

CC BY-NC-ND (attribution - noncommercial - no derivatives)

Open Access Mode

open journal

Open Access Text Version

final published version

Date of Open Access to the publication

at the time of publication

Full text of article

Download file

Access level to full text

public

Ministry points / journal

100

Impact Factor

3,4 [List 2023]

This website uses cookies to remember the authenticated session of the user. For more information, read about Cookies and Privacy Policy.