Heart rate estimation in intense exercise videos
This addresses a practical limitation in non-contact health monitoring for applications like sports and patient care, though it is incremental as it builds on existing remote photo-plethysmography methods.
The authors tackled the problem of estimating heart rate from video in intense exercise scenarios where faces are often occluded, by creating the IntensePhysio dataset with 11 subjects and 20 hours of video, and developed IBIS-CNN, a new baseline method that improves on existing models by eliminating the need for visible faces.
Estimating heart rate from video allows non-contact health monitoring with applications in patient care, human interaction, and sports. Existing work can robustly measure heart rate under some degree of motion by face tracking. However, this is not always possible in unconstrained settings, as the face might be occluded or even outside the camera. Here, we present IntensePhysio: a challenging video heart rate estimation dataset with realistic face occlusions, severe subject motion, and ample heart rate variation. To ensure heart rate variation in a realistic setting we record each subject for around 1-2 hours. The subject is exercising (at a moderate to high intensity) on a cycling ergometer with an attached video camera and is given no instructions regarding positioning or movement. We have 11 subjects, and approximately 20 total hours of video. We show that the existing remote photo-plethysmography methods have difficulty in estimating heart rate in this setting. In addition, we present IBIS-CNN, a new baseline using spatio-temporal superpixels, which improves on existing models by eliminating the need for a visible face/face tracking. We will make the code and data publically available soon.