Respiratory Rate Estimation from Thermal Video Data Using Spatio-Temporal Deep Learning
Open Access
Abstract
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.Keywords
Funding Information
- NRC’s Pandemic Response and Aging in Place challenge programs
This publication has 37 references indexed in Scilit:
- Non-Contact Respiration Rate Measurement From Thermal Images Using Multi-Resolution Window and Phase-Sensitive ProcessingIEEE Access, 2023
- Video-based real-time monitoring for heart rate and respiration rateExpert Systems with Applications, 2023
- Hyperparameter optimization: Foundations, algorithms, best practices, and open challengesWIREs Data Mining and Knowledge Discovery, 2023
- Airflow recovery from thoracic and abdominal movements using synchrosqueezing transform and locally stationary Gaussian process regressionComputational Statistics & Data Analysis, 2022
- rPPG-FuseNet: Non-contact heart rate estimation from facial video via RGB/MSR signal fusionBiomedical Signal Processing and Control, 2022
- TFW: Annotated Thermal Faces in the Wild DatasetIEEE Transactions on Information Forensics and Security, 2022
- A Contactless On-Bed Radar System for Human Respiration MonitoringIEEE Transactions on Instrumentation and Measurement, 2022
- Probabilistic Framework with Bayesian Optimization for Predicting Typhoon-Induced Dynamic Responses of a Long-Span BridgeJournal of Structural Engineering, 2021
- Contact-Free Respiration Rate Monitoring Using a Pan–Tilt Thermal Camera for Stationary Bike Telerehabilitation SessionsIEEE Systems Journal, 2014
- Non-contact, automated cardiac pulse measurements using video imaging and blind source separationOptics Express, 2010