Differential Pseudo-Image For Skeleton-Based Dynamic Gesture Recognition

Estimating heart rate from video allows non-contact health monitoring with applications in patient care, human interac- tion, and sports. Existing work can robustly measure heart rate under some degree of motion by face tracking. How- ever, 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 moder- ate to high intensity) on a cycling ergometer with an attached video camera and is given no instructions regarding position- ing 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 im- proves on existing models by eliminating the need for a visi- ble face/face tracking.