Repozytorium publikacji - Politechnika Gdańska

Non-contact evaluation of vital signs has been becoming increasingly important, especially in light of the COVID- 19 pandemic, which is causing the whole world to examine people’s interactions in public places at a scale never seen before. However, evaluating one’s vital signs can be a relatively complex procedure, which requires both time and physical contact between examiner and examinee. These re- quirements limit the number of people who can be efficiently checked, either due to the medical station throughput, pa- tients’ remote locations or the need for social distancing. This study is a first step to increasing the accuracy of com- puter vision-based respiratory rate estimation by transfer- ring texture information from images acquired in different domains. Experiments conducted with two deep neural net- work topologies, a recursive convolutional model and trans- formers, proved their robustness in the analyzed scenario by reducing estimation error by 50% compared to low resolu- tion sequences. All resources used in this research, including links to the dataset and code, have been made publicly available.

Autorzy

• mgr inż Alicja Kwaśniewska,
• mgr inż. Maciej Szankin,
• prof. dr hab. inż. Jacek Rumiński link otwiera się w nowej karcie ,
• Anthony Sarah,
• David Gamba