Why the study?
Existing transformer-based remote photoplethysmography methods for heart rate estimation have high computational complexity and focus mainly on local features, neglecting long-distance features.
Answers are grounded in this paper and cite their sources.
The proposed LSDASCFormer network accurately extracts remote photoplethysmography signals from facial videos for heart rate estimation with low computational complexity.
In recent years, many methods for extracting remote photoplethysmography (rPPG) signals for remote heart rate (HR) estimation based on the transformer approach have predominantly used multihead self-attention mechanisms. However, these methods suffer from high computational complexity, making them unsuitable for deployment on terminal and mobile devices. In addition, most approaches focus solely on local features, neglecting long-distance features. This article proposes a transformer-like network structure called LSDASCFormer for HR extraction. The fundamental idea is to use LSDASCFormer to accurately extract rPPG signals from facial videos, followed by specific postprocessing of the rPPG signals to calculate relevant HR indicators. LSDASCFormer comprises convolutional blocks, feature fusion blocks (LSDASCFormer block), and rPPG prediction blocks. The introduced feature fusion module effectively extracts both long-distance and short-distance features while reducing computational complexity. Our model demonstrates excellent performance in terms of mean absolute error (MAE), root mean square error (RMSE), and Pearson correlation coefficient (r) in experiments conducted on the UBFC-rPPG and PURE datasets. On the PURE dataset, our method achieves an MAE of 0.41 bpm, an RMSE of 0.66 bpm, and a Pearson correlation coefficient (r) of 1.00. Similarly, on the UBFC-rPPG dataset, the method yields an MAE of 0.49 bpm, an RMSE of 1.12 bpm, and a Pearson correlation coefficient (r) of 0.99. These results substantiate the effectiveness of our proposed method.
No takes yet. Share an insight, caveat, or question.
Liu et al. (2024) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: