Samenvatting
Nose breathing is preferred during sleep, although health issues may cause a subject to breathe through the mouth, and long-term mouth breathing may raise other health issues like sleep apnea. This paper proposes a first-ever classification of nose breathing and mouth breathing using the thermography of the subject. The measurement uses the relative temperature variations of different facial regions to classify mouth or nose breathing. This measurement is particularly health-/well-being relevant as it can be used as an early sign for sleep disorders or an indicator of sleep quality. An end-to-end processing flowchart has been provided for proof-of-concept validation on real-life recordings of thermal videos. Eight volunteers participated in our experiments and our proposed method achieved an overall classification accuracy of 91% in ideal lab conditions.
Originele taal-2 | Engels |
---|---|
Titel | Proceedings - 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2021 |
Uitgeverij | Institute of Electrical and Electronics Engineers |
Pagina's | 3877-3883 |
Aantal pagina's | 7 |
ISBN van elektronische versie | 978-1-6654-4899-4 |
DOI's | |
Status | Gepubliceerd - 1 sep. 2021 |
Evenement | 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2021 - Nashville, Verenigde Staten van Amerika Duur: 19 jun. 2021 → 25 jun. 2021 |
Congres
Congres | 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2021 |
---|---|
Verkorte titel | CVPRW 2021 |
Land/Regio | Verenigde Staten van Amerika |
Stad | Nashville |
Periode | 19/06/21 → 25/06/21 |