[论文] Illumination-Robust Camera-Based Heart-Rate Estimation for Physio...

论文概要

研究领域: CV 作者: Zhi Wei Xu, Torbjörn E. M. Nordling 发布时间: 2026-06-10 arXiv: 2606.12378

中文摘要

生理感知对在家庭环境中与人类交互的服务、社交和辅助机器人很重要。远程光电容积脉搏波（rPPG）使从RGB相机进行非接触心率估计成为可能，使其成为机器人安装视觉系统的有前景的感知模态。然而，光照变化仍是鲁棒部署的主要障碍。本文提出端到端时空变换框架，用于在新数据集上具有变化光照的远程心率估计。我们的估计器集成PRNet基础的3D面部对齐、片段级光照增强、残差时间标准化模块和控制的混合时频监督。训练目标结合软偏移Pearson波形损失和谱Kullback-Leibler散度损失，其中调谐权重beta控制频域心率指导的贡献。在涵盖三个光照水平的静态全级别混合协议实验中，beta=5在测试的beta设置中提供最强结果，实现最佳运行心率平均绝对误差（MAE）0.79 bpm和心率相关性0.982。与在我们的数据集上评估的PhysFormer基线相比，我们的估计器将心率MAE降低93.6%，同时将心率相关性从0.088提升至0.982，使其在光照变化时可用。

原文摘要

Physiological awareness is important for service, social, and assistive robots that interact with humans in everyday environments. Remote photoplethysmography (rPPG) enables non-contact heart-rate (HR) estimation from an RGB camera, making it a promising sensing modality for robot-mounted vision systems. However, illumination variation remains a major barrier to robust deployment. This paper presents an end-to-end spatial-temporal transformer framework for remote HR estimation on a new dataset with varied illumination. Our estimator integrates PRNet-based 3D face alignment, clip-level illumination augmentation, the Residual Temporal Standardization Module, and controlled hybrid temporal-frequency supervision. The training objective combines a Soft-Shifted Pearson waveform loss with a spect...

--- *自动采集于 2026-06-12*

#论文 #arXiv #CV #小凯