Respiratory rate detection algorithm based on RGB‐D camera: theoretical background and experimental results. Issue 3 (29th September 2014)

• Record Type: Journal Article
• Authors: Benetazzo, Flavia; Freddi, Alessandro; Monteriù, Andrea; Longhi, Sauro
• Is Part Of: Healthcare technology letters. Volume 1:Issue 3(2014)
• Page Start: 81
• Page End: 86
• Publication Date: 2014-09-29
• Subjects: pneumodynamics -- CCD image sensors -- biomedical optical imaging -- patient monitoring; person respiratory activity monitoring -- light conditions -- chest movements -- sampling frequency -- benchmark -- spirometer -- person being monitoring -- human chest wall -- morphological changes -- image sensing techniques -- human respiratory rate measurements -- red green blue‐depth camera -- respiratory rate detection algorithm; Biomedical engineering -- Periodicals; Medical technology -- Periodicals; 610.28
• DOI: 10.1049/htl.2014.0063
• Languages: English
• ISSNs: 2053-3713

Abstract

Abstract : Both the theoretical background and the experimental results of an algorithm developed to perform human respiratory rate measurements without any physical contact are presented. Based on depth image sensing techniques, the respiratory rate is derived by measuring morphological changes of the chest wall. The algorithm identifies the human chest, computes its distance from the camera and compares this value with the instantaneous distance, discerning if it is due to the respiratory act or due to a limited movement of the person being monitored. To experimentally validate the proposed algorithm, the respiratory rate measurements coming from a spirometer were taken as a benchmark and compared with those estimated by the algorithm. Five tests were performed, with five different persons sat in front of the camera. The first test aimed to choose the suitable sampling frequency. The second test was conducted to compare the performances of the proposed system with respect to the gold standard in ideal conditions of light, orientation and clothing. The third, fourth and fifth tests evaluated the algorithm performances under different operating conditions. The experimental results showed that the system can correctly measure the respiratory rate, and it is a viable alternative to monitor the respiratory activity of a person without using invasive sensors.