How Suboptimal is Training rPPG Models with Videos and Targets from Different Body Sites?

arXiv:2403.10582v1 Announce Type: cross
Abstract: Remote camera measurement of the blood volume pulse via photoplethysmography (rPPG) is a compelling technology for scalable, low-cost, and accessible assessment of cardiovascular information. Neural networks currently provide the state-of-the-art for this task and supervised training or fine-tuning is an important step in creating these models. However, most current models are trained on facial videos using contact PPG measurements from the fingertip as targets/ labels. One of the reasons for this is that few public …

abstract art arxiv assessment cost cs.lg eess.iv fine-tuning information low measurement networks neural networks scalable state supervised training targets technology training type via videos