Evaluation of Video-Based rPPG in Challenging Environments: Artifact Mitigation and Network Resilience
Nhi Nguyen, Le Nguyen, Honghan Li, Miguel Bordallo López, Constantino Álvarez Casado
TL;DR
The paper tackles the challenge of reliable video-based rPPG in real-world conditions by introducing a systematic evaluation framework that injects degradation artifacts (spatial, occlusion, and temporal) and tests mitigation strategies. It compares learning-based and non-learning rPPG methods across seven public datasets, detailing how factors like color depth, blur, noise, occlusions, and frame drops affect heart-rate estimation, and proposes denoising, inpainting, and frame-reconstruction strategies. Key findings show that while some degradations minimally impact extraction (e.g., sunglasses), others (notably facemasks and significant frame loss) substantially degrade performance, though mitigations such as GAN-based inpainting and timestamped reconstruction can improve robustness. The work provides actionable insights for deploying remote vital signs monitoring, highlighting when simple occlusion handling or denoising suffices and when advanced strategies are required, with clear guidance for future resilience improvements in real-time systems.
Abstract
Video-based remote photoplethysmography (rPPG) has emerged as a promising technology for non-contact vital sign monitoring, especially under controlled conditions. However, the accurate measurement of vital signs in real-world scenarios faces several challenges, including artifacts induced by videocodecs, low-light noise, degradation, low dynamic range, occlusions, and hardware and network constraints. In this article, we systematically investigate comprehensive investigate these issues, measuring their detrimental effects on the quality of rPPG measurements. Additionally, we propose practical strategies for mitigating these challenges to improve the dependability and resilience of video-based rPPG systems. We detail methods for effective biosignal recovery in the presence of network limitations and present denoising and inpainting techniques aimed at preserving video frame integrity. Through extensive evaluations and direct comparisons, we demonstrate the effectiveness of the approaches in enhancing rPPG measurements under challenging environments, contributing to the development of more reliable and effective remote vital sign monitoring technologies.