ISO-Compatible Personal Temperature Measurement Using Visual and Thermal Images With Facial Region of Interest Detection
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 corre...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10472492/ |
| _version_ | 1797236601584091136 |
|---|---|
| author | Bartosz Ptak Przemyslaw Aszkowski Joanna Weissenberg Marek Kraft Michal Weissenberg |
| author_facet | Bartosz Ptak Przemyslaw Aszkowski Joanna Weissenberg Marek Kraft Michal Weissenberg |
| author_sort | Bartosz Ptak |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-04-24T17:06:27Z |
| format | Article |
| id | doaj.art-a3f8ef50789b46fda661850a3cd38967 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-24T17:06:27Z |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-a3f8ef50789b46fda661850a3cd389672024-03-28T23:00:38ZengIEEEIEEE Access2169-35362024-01-0112442624427710.1109/ACCESS.2024.337744810472492ISO-Compatible Personal Temperature Measurement Using Visual and Thermal Images With Facial Region of Interest DetectionBartosz Ptak0Przemyslaw Aszkowski1https://orcid.org/0000-0003-0388-8546Joanna Weissenberg2https://orcid.org/0000-0002-3982-4862Marek Kraft3https://orcid.org/0000-0001-6483-2357Michal Weissenberg4https://orcid.org/0000-0003-4830-433XInstitute of Robotics and Machine Intelligence, Poznań University of Technology, Poznań, PolandInstitute of Robotics and Machine Intelligence, Poznań University of Technology, Poznań, PolandInstitute of Communication and Computer Networks, Poznań University of Technology, Poznań, PolandInstitute of Robotics and Machine Intelligence, Poznań University of Technology, Poznań, PolandInstitute of Communication and Computer Networks, Poznań University of Technology, Poznań, PolandDisease 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.https://ieeexplore.ieee.org/document/10472492/Thermal imagingtemperature measurementcomputer visiondeep learning |
| spellingShingle | Bartosz Ptak Przemyslaw Aszkowski Joanna Weissenberg Marek Kraft Michal Weissenberg ISO-Compatible Personal Temperature Measurement Using Visual and Thermal Images With Facial Region of Interest Detection IEEE Access Thermal imaging temperature measurement computer vision deep learning |
| title | ISO-Compatible Personal Temperature Measurement Using Visual and Thermal Images With Facial Region of Interest Detection |
| title_full | ISO-Compatible Personal Temperature Measurement Using Visual and Thermal Images With Facial Region of Interest Detection |
| title_fullStr | ISO-Compatible Personal Temperature Measurement Using Visual and Thermal Images With Facial Region of Interest Detection |
| title_full_unstemmed | ISO-Compatible Personal Temperature Measurement Using Visual and Thermal Images With Facial Region of Interest Detection |
| title_short | ISO-Compatible Personal Temperature Measurement Using Visual and Thermal Images With Facial Region of Interest Detection |
| title_sort | iso compatible personal temperature measurement using visual and thermal images with facial region of interest detection |
| topic | Thermal imaging temperature measurement computer vision deep learning |
| url | https://ieeexplore.ieee.org/document/10472492/ |
| work_keys_str_mv | AT bartoszptak isocompatiblepersonaltemperaturemeasurementusingvisualandthermalimageswithfacialregionofinterestdetection AT przemyslawaszkowski isocompatiblepersonaltemperaturemeasurementusingvisualandthermalimageswithfacialregionofinterestdetection AT joannaweissenberg isocompatiblepersonaltemperaturemeasurementusingvisualandthermalimageswithfacialregionofinterestdetection AT marekkraft isocompatiblepersonaltemperaturemeasurementusingvisualandthermalimageswithfacialregionofinterestdetection AT michalweissenberg isocompatiblepersonaltemperaturemeasurementusingvisualandthermalimageswithfacialregionofinterestdetection |