Non-invasive respiratory rate detection using thermal imaging and facial recognition

Savannah M. Orton; Erin R. O'Brien; Ashley D. DeCock; Julian J. Lee; Samson A. Segovia; Ian C. Crochet; Oladimeji A. Apaokagi; Evan J. Kowal; Morgan B. Nix; Francis I. Ko; Esther H. Kim; Joon W. Kim

doi:10.1117/12.2657803

25 April 2023 Non-invasive respiratory rate detection using thermal imaging and facial recognition

Savannah M. Orton, Erin R. O'Brien, Ashley D. DeCock, Julian J. Lee, Samson A. Segovia, Ian C. Crochet, Oladimeji A. Apaokagi, Evan J. Kowal, Morgan B. Nix, Francis I. Ko, Esther H. Kim, Joon W. Kim

Author Affiliations +

Proceedings Volume 12488, Health Monitoring of Structural and Biological Systems XVII; 124881G (2023) https://doi.org/10.1117/12.2657803
Event: SPIE Smart Structures + Nondestructive Evaluation, 2023, Long Beach, California, United States

Abstract

Respiratory rate is a vital sign that signifies the movement of air into and out of the lungs through ventilation. In modern medical practices, this vital sign is often inaccurately measured by hospital staff [1]. This phenomenon is problematic considering a fluctuation in respiratory rate is often observed as an early indicator of illness. The recent COVID-19 pandemic resulted in an influx of patients visiting hospitals and a greater need for hospital staff to monitor the vitals of patients in case of respiratory distress. To aid in the important measuring of patient vitals, a device was created to non-invasively measure respiratory rate. This portable, cost-effective device utilizes thermal analysis and facial recognition through two cameras to measure and calculate a patient's respiratory rate from a distance of 30-60 cm away. The respiratory rate is then displayed via a smartphone application. A group of subjects participated in a testing procedure to determine the accuracy of the device. Subject respiration was recorded by the device over a period of 30 seconds. The results were compared to a manual count, verified by a real-time heart rate monitor. The device’s algorithm was found to have an increase in accuracy compared to a previous study of respiratory rates manually counted by trained medical staff [2]. This device, the LeTourneau Engineering Vital Imaging System (LEVIS), provides a more accurate measurement of respiratory rate, which can enable medical staff to attend to other tasks during the measurement period.

Conference Presentation

Citation Download Citation

Savannah M. Orton, Erin R. O'Brien, Ashley D. DeCock, Julian J. Lee, Samson A. Segovia, Ian C. Crochet, Oladimeji A. Apaokagi, Evan J. Kowal, Morgan B. Nix, Francis I. Ko, Esther H. Kim, and Joon W. Kim "Non-invasive respiratory rate detection using thermal imaging and facial recognition", Proc. SPIE 12488, Health Monitoring of Structural and Biological Systems XVII, 124881G (25 April 2023); https://doi.org/10.1117/12.2657803

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available