0000000001173363
AUTHOR
Duncan Luguern
Real-Time Temporal Superpixels for Unsupervised Remote Photoplethysmography
International audience; Segmentation is a critical step for many computer vision applications. Among them, the remote photoplethys-mography technique is significantly impacted by the quality of region of interest segmentation. With the heart-rate estimation accuracy, the processing time is obviously a key issue for real-time monitoring. Recent face detection algorithms can perform real-time processing, however for unsupervised algorithms, i.e. without any subject detection based on supervised learning, existing methods are not able to achieve real-time on regular platform. In this paper, we propose a new method to perform real-time un-supervised remote photoplethysmograhy based on efficient…
Nouvelle approche pour l'estimation du rythme respiratoire basée sur la photopléthysmographie sans contact
Respiratory rhythm is important information in medical context.Its assessment allows to predict some medical complications that could lead to death.However, it is often neglected by the medical staff due to a bad comprehension of its importance, or a lack of time.Automated measurement methods allow to improve this by continuously giving respiratory rate.Most of these methods needs a contact with the patient to efficiently measure the breathing rate.Unfortunately it leads to some issues which could forbid measurement or make it unconfortable for continuous monitoring.The continuous, every-day monitoring especially needs to be as discrete as possible to be forgotten by the patient.To deal wit…
Real-Time Temporal Superpixels for Unsupervised remote photopletysmography
International audience