EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Respiratory Rate Estimation from Thermal Video Data Using Spatio-Temporal Deep Learning

Mohsen Mozafari, Andrew J Law iD, Rafik A Goubran, James R Green iD

Sensors · 02.10.2024 · 24 (19) · 6386

DOI: 10.3390/s24196386 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 02.10.2024. Verfasst von Mohsen Mozafari und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Systems and Computer Engineering, Carleton University, Ottawa, ON K1S 5B6, Canada. Hauptthemen laut MEDLINE: Deep Learning, Respiratory Rate. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Research Council of Canada, NRC’s Pandemic Response and Aging in Place challenge programs.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Thermal videos provide a privacy-preserving yet information-rich data source for remote health monitoring, especially for respiration rate (RR) estimation. This paper introduces an end-to-end deep learning approach to RR measurement using thermal video data. A detection transformer (DeTr) first finds the subject’s facial region of interest in each thermal frame. A respiratory signal is estimated from a dynamically cropped thermal video using 3D convolutional neural networks and bi-directional long short-term memory stages. To account for the expected phase shift between the respiration measured using a respiratory effort belt vs. a facial video, a novel loss function based on negative maximum cross-correlation and absolute frequency peak difference was introduced. Thermal recordings from 22 subjects, with simultaneous gold standard respiratory effort measurements, were studied while sitting or standing, both with and without a face mask. The RR estimation results showed that our proposed method outperformed existing models, achieving an error of only 1.6 breaths per minute across the four conditions. The proposed method sets a new State-of-the-Art for RR estimation accuracy, while still permitting real-time RR estimation.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningRespiratory RateHumansNeural Networks, ComputerVideo RecordingMaleAdultFemaleMonitoring, PhysiologicAlgorithms

Stichwörter der Autor:innen

deep learningface detectionrespiration rate estimationthermal video

Autor:innen und Institutionen

  • Department of Systems and Computer Engineering, Carleton University, Ottawa, ON K1S 5B6, Canada.
  • Flight Research Laboratory, National Research Council of Canada (NRC), Ottawa, ON K1A 0R6, Canada.

ORCID-Profile: Andrew J Law, James R Green

Förderung

  • National Research Council of Canada
  • NRC’s Pandemic Response and Aging in Place challenge programs

Zitieren

APA

Mozafari, M., Law, A. J., Goubran, R. A., & Green, J. R. (2024). Respiratory Rate Estimation from Thermal Video Data Using Spatio-Temporal Deep Learning. Sensors, 24(19), 6386. https://doi.org/10.3390/s24196386

Vancouver

Mozafari M, Law AJ, Goubran RA, Green JR. Respiratory Rate Estimation from Thermal Video Data Using Spatio-Temporal Deep Learning. Sensors. 2024;24(19):6386. doi:10.3390/s24196386

BibTeX
@article{Mozafari2024,
  author = {Mozafari, Mohsen and Law, Andrew J and Goubran, Rafik A and Green, James R},
  title = {Respiratory Rate Estimation from Thermal Video Data Using Spatio-Temporal Deep Learning},
  journal = {Sensors},
  year = {2024},
  volume = {24},
  number = {19},
  pages = {6386},
  doi = {10.3390/s24196386}
}
Kostenlos starten →