BYHE: A Simple Framework for Boosting End-to-end Video-based Heart Rate Measurement Network

TL;DR

This paper introduces BYHE, a framework that improves end-to-end video-based heart rate measurement by addressing label representation issues, leading to more efficient training and competitive performance.

Contribution

Proposes a comprehensive methodology with new label representations, network adjustments, and loss functions to enhance training efficiency of end-to-end rPPG-based heart rate estimation networks.

Findings

BYHE improves training efficiency and dataset utilization.

Achieves competitive performance on standard datasets.

Reduces need for manual label wave alignment.

Abstract

Heart rate measuring based on remote photoplethysmography (rPPG) plays an important role in health caring, which estimates heart rate from facial video in a non-contact, less-constrained way. End-to-end neural network is a main branch of rPPG-based heart rate estimation methods, whose trait is recovering rPPG signal containing sufficient heart rate message from original facial video directly. However, there exists some easily neglected problems on relevant datasets which thwarting the efficient training of end-to-end methods, such as uncertain temporal delay and indefinite envelope shape of label waves. Although many novel and powerful networks are proposed, hitherto there are no systematic research digging into these problems. In this paper, from perspective of common intrinsic rhythm periodical self-similarity results from cardiac activities, we propose a comprehensive methodology, Boost Your Heartbeat Estimation (BYHE), including new label representations, corresponding network adjustments and loss functions. BYHE can be easily grafted on current end-to-end network and boost its training efficiency. By applying our methodology, we can save tremendous time without conducting laborious handworks, such as label wave alignment which is necessary for previous end-to-end methods, and meanwhile enhance the utilization on datasets. According to our experiments, BYHE can leverage classical end-to-end network to reach competitive performance against those state-of-the-art methods on mostly used datasets. Such improvement indicates selecting perspicuous and efficient label representation is also a promising direction towards better remote physiological signal measurement.