Abstract
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.
Original language | English |
---|---|
Title of host publication | Proceedings - 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2021 |
Publisher | Institute of Electrical and Electronics Engineers |
Pages | 3877-3883 |
Number of pages | 7 |
ISBN (Electronic) | 978-1-6654-4899-4 |
DOIs | |
Publication status | Published - 1 Sept 2021 |
Event | 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2021 - Nashville, United States Duration: 19 Jun 2021 → 25 Jun 2021 |
Conference
Conference | 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2021 |
---|---|
Abbreviated title | CVPRW 2021 |
Country/Territory | United States |
City | Nashville |
Period | 19/06/21 → 25/06/21 |