超越接触式传感器：基于伪标签的远程光电容积描记深度学习
Beyond Contact Sensors: Deep learning with Pseudo-Labeling for remote Photoplethysmography
浏览论文内容
中文总结 AI 辅助
本研究探讨用无监督信号处理生成的伪标签替代接触式传感器标签训练rPPG深度学习模型，发现同步不佳时伪标签更优，同步良好时结果不一，但去除异常样本可提升跨数据集性能。
中文摘要 AI 辅助
心率是健康的关键生物标志物，远程光电容积描记（rPPG）技术能够从视频数据中实现无接触式心率估计，适用于远程医疗应用。近年来，基于深度学习的rPPG方法取得了最先进的成果，在复杂场景中优于经典信号处理方法。然而，深度学习方法依赖于视频与通过接触式传感器采集的基准信号之间精确同步的数据集，而基于信号处理的方法则无此要求。为解决对标注数据集的依赖（此类数据集收集成本高昂），我们研究了在何种情况下，使用无监督信号处理方法提取的伪标签能够替代接触式传感器标签来训练深度学习方法。我们的系统性评估发现，对于同步不完美的数据集，伪标签方法优于基于接触式传感器的监督训练。对于同步良好的数据集，结果不一：数据集内评估显示两种训练方法无显著差异，而跨数据集评估则倾向于监督训练。然而，移除单个异常参与者可显著提升伪标签方法的跨数据集性能，凸显了标签质量的重要性。这些结果表明，信号处理方法能够为深度学习模型生成有效的训练信号，在保持竞争性能的同时减少对劳动密集型数据集收集的依赖。
英文摘要
Heart rate is a critical biomarker of health, and remote photoplethysmography (rPPG) enables its contactless estimation from video data for telemedicine applications. Recent advancements in deep learning based rPPG methods achieve state-of-the-art results, outperforming classical signal-processing methods in complex scenarios. However, deep learning methods depend on datasets with precise synchronization between videos and ground truth signals collected via contact sensors, whereas signal-processing-based methods do not. To address this dependence on labeled datasets, which are labor-intensive to collect, we investigate under which circumstances pseudo-labels extracted using unsupervised signal-processing methods can replace contact sensors labels for training deep learning methods. Our systematic evaluations found that for datasets with imperfect synchronization, the pseudo-label approach outperforms supervised training on contact sensors. For datasets with good synchronization, results are mixed: within-dataset evaluation shows no significant difference between training methods, while cross-dataset evaluation favors supervised training. However, removing a single outlier participant significantly improves the pseudo-label approach's cross-dataset performance, highlighting the importance of label quality. These results demonstrate that signal-processing methods can generate valid training signals for deep learning models, reducing dependency on labor-intensive dataset collection while maintaining competitive performance.
发表机构
- Center for Cognitive Interaction Technology (CITEC), Bielefeld University（比勒费尔德大学认知交互技术中心（CITEC））
机构由 AI 辅助整理，请以论文原文为准。
