用无监督方法实现抗运动干扰的远程心率精准估计
BeatFormer: Efficient motion-robust remote heart rate estimation through unsupervised spectral zoomed attention filters
- 引入频域聚焦注意力机制，高效提取脉搏信号
- 在三个数据集上实现跨场景高鲁棒性，尤其抗运动干扰强
- 无需生理标签即可训练，适合真实场景部署
远程光体积变化描记法（rPPG）通过面部视频捕捉心脏信号，应用广泛。深度学习虽提升性能，但依赖大规模多样数据集；而手工设计方法利用生理先验，在未见场景（如运动）中泛化性强且计算高效，但线性假设限制其复杂条件下的表现。为此，本文提出BeatFormer，一种轻量级频谱注意力模型，融合聚焦正交复数注意力与频域能量度量，实现高效建模。同时引入频谱对比学习（SCL），使模型可在无任何PPG或心率标签情况下训练。在PURE、UBFC-rPPG和MMPD数据集上的验证表明，该模型在运动场景下跨数据集评估中表现出强鲁棒性与优异性能。
原文摘要 · Abstract (English)
Remote photoplethysmography (rPPG) captures cardiac signals from facial videos and is gaining attention for its diverse applications. While deep learning has advanced rPPG estimation, it relies on large, diverse datasets for effective generalization. In contrast, handcrafted methods utilize physiological priors for better generalization in unseen scenarios like motion while maintaining computational efficiency. However, their linear assumptions limit performance in complex conditions, where deep learning provides superior pulsatile information extraction. This highlights the need for hybrid approaches that combine the strengths of both methods. To address this, we present BeatFormer, a lightweight spectral attention model for rPPG estimation, which integrates zoomed orthonormal complex attention and frequency-domain energy measurement, enabling a highly efficient model. Additionally, we introduce Spectral Contrastive Learning (SCL), which allows BeatFormer to be trained without any PPG or HR labels. We validate BeatFormer on the PURE, UBFC-rPPG, and MMPD datasets, demonstrating its robustness and performance, particularly in cross-dataset evaluations under motion scenarios.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。