In this paper, we present a new non-contact strategy to estimate the breathing rate based on the Eulerianmotion video magnification technique and a system based on a Convolutional Neural Network (CNN). After themagnification procedure, a CNN is trained to detect the inhalation and exhalation frames in the video. From thisclassification, the respiratory rate is estimated. The magnification procedure was carried out using the Hermitedecomposition. Two strategies are used as input to the CNN. A CNN-ROI proposal where a region of interestis selected manually on the image frame and in the second case, a CNN-Whole-Image proposal where the entireimage frame is selected. Finally, the respiratory rate (RR) is estimated from the classified frames. The CNN-ROIproposal is tested on five subjects in lying face down position and it is compared to a procedure using differentimage processing steps to tag the frames as inhalation or exhalation. The mean average error in percentageobtained for this proposal is 2:326 1:144%. The CNN-whole-image proposal is tested on eight subjects in lyingface down position. The mean average error in percentage obtained for this proposal is 2:115 1:135%.
展开▼
