Abstract
We describe a novel method to monitor pulse rate (PR) on a continuous basis of patients in a neonatal intensive care unit (NICU) using videos taken from a high definition (HD) webcam. We describe algorithms that determine PR from videoplethysmographic (VPG) signals extracted from multiple regions of interest (ROI) simultaneously available within the field of view of the camera where cardiac signal is registered. We detect motion from video images and compensate for motion artifacts from each ROI. Preliminary clinical results are presented on 8 neonates each with 30 minutes of uninterrupted video. Comparisons to hospital equipment indicate that the proposed technology can meet medical industry standards and give improved patient comfort and ease of use for practitioners when instrumented with proper hardware.
Original language | English |
---|---|
Pages (from-to) | 3817-3820 |
Number of pages | 4 |
Journal | Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual Conference |
Volume | 2014 |
DOIs | |
Publication status | Published - 01-01-2014 |
All Science Journal Classification (ASJC) codes
- Signal Processing
- Biomedical Engineering
- Computer Vision and Pattern Recognition
- Health Informatics