VitalLens 2.0：基于面部视频进行心率变异性估计的高保真远程光电容积描记技术 (VitalLens 2.0: High-Fidelity rPPG for Heart Rate Variability Estimation from Face Video)

from arxiv, Technical Report. 8 pages, 5 figures. Introduces the VitalLens 2.0 model for rPPG and Heart Rate Variability (HRV) estimation. Project website: https://rouast.com/api

This report introduces VitalLens 2.0, a new deep learning model for estimating physiological signals from face video. This new model demonstrates a significant leap in accuracy for remote photoplethysmography (rPPG), enabling the robust estimation of not only heart rate (HR) and respiratory rate (RR) but also Heart Rate Variability (HRV) metrics. This advance is achieved through a combination of a new model architecture and a substantial increase in the size and diversity of our training data, now totaling 1,413 unique individuals. We evaluate VitalLens 2.0 on a new, combined test set of 422 unique individuals from four public and private datasets. When averaging results by individual, VitalLens 2.0 achieves a Mean Absolute Error (MAE) of 1.57 bpm for HR, 1.08 bpm for RR, 10.18 ms for HRV-SDNN, and 16.45 ms for HRV-RMSSD. These results represent a new state-of-the-art, significantly outperforming previous methods. This model is now available to developers via the VitalLens API at https://rouast.com/api.

翻译：本报告介绍了VitalLens 2.0，一种从面部视频中估计生理信号的新型深度学习模型。该模型在远程光电容积描记技术（rPPG）的准确性上实现了显著飞跃，不仅能够稳健地估计心率（HR）和呼吸频率（RR），还能精确计算心率变异性（HRV）指标。这一进展是通过结合新的模型架构以及大幅增加训练数据的规模和多样性实现的，目前训练数据总计包含1,413名独特个体。我们在一个由四个公共和私有数据集组成的、包含422名独特个体的新组合测试集上评估了VitalLens 2.0。按个体平均结果时，VitalLens 2.0在心率上的平均绝对误差（MAE）为1.57 bpm，呼吸频率为1.08 bpm，HRV-SDNN为10.18毫秒，HRV-RMSSD为16.45毫秒。这些结果代表了新的最先进水平，显著优于先前的方法。该模型现已通过VitalLens API（https://rouast.com/api）向开发者开放。