Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2504.03915 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908302713028608 |
|---|---|
| author | Ma, Rufei Chen, Chao |
| author_facet | Ma, Rufei Chen, Chao |
| contents | Remote photoplethysmography (rPPG) technology infers heart rate by capturing subtle color changes in facial skin
using a camera, demonstrating great potential in non-contact heart rate measurement. However, measurement
accuracy significantly decreases in complex scenarios such as lighting changes and head movements compared
to ideal laboratory conditions. Existing deep learning models often neglect the quantification of measurement
uncertainty, limiting their credibility in dynamic scenes. To address the issue of insufficient rPPG measurement
reliability in complex scenarios, this paper introduces Bayesian neural networks to the rPPG field for the first time,
proposing the Robust Fusion Bayesian Physiological Network (RF-BayesPhysNet), which can model both aleatoric
and epistemic uncertainty. It leverages variational inference to balance accuracy and computational efficiency.
Due to the current lack of uncertainty estimation metrics in the rPPG field, this paper also proposes a new set of
methods, using Spearman correlation coefficient, prediction interval coverage, and confidence interval width, to
measure the effectiveness of uncertainty estimation methods under different noise conditions. Experiments show
that the model, with only double the parameters compared to traditional network models, achieves a MAE of 2.56
on the UBFC-RPPG dataset, surpassing most models. It demonstrates good uncertainty estimation capability
in no-noise and low-noise conditions, providing prediction confidence and significantly enhancing robustness in
real-world applications. We have open-sourced the code at https://github.com/AIDC-rPPG/RF-Net |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_03915 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | RF-BayesPhysNet: A Bayesian rPPG Uncertainty Estimation Method for Complex Scenarios Ma, Rufei Chen, Chao Machine Learning Artificial Intelligence 68T07, 62F15, 94A12 I.2.6; I.5.4; C.3 Remote photoplethysmography (rPPG) technology infers heart rate by capturing subtle color changes in facial skin using a camera, demonstrating great potential in non-contact heart rate measurement. However, measurement accuracy significantly decreases in complex scenarios such as lighting changes and head movements compared to ideal laboratory conditions. Existing deep learning models often neglect the quantification of measurement uncertainty, limiting their credibility in dynamic scenes. To address the issue of insufficient rPPG measurement reliability in complex scenarios, this paper introduces Bayesian neural networks to the rPPG field for the first time, proposing the Robust Fusion Bayesian Physiological Network (RF-BayesPhysNet), which can model both aleatoric and epistemic uncertainty. It leverages variational inference to balance accuracy and computational efficiency. Due to the current lack of uncertainty estimation metrics in the rPPG field, this paper also proposes a new set of methods, using Spearman correlation coefficient, prediction interval coverage, and confidence interval width, to measure the effectiveness of uncertainty estimation methods under different noise conditions. Experiments show that the model, with only double the parameters compared to traditional network models, achieves a MAE of 2.56 on the UBFC-RPPG dataset, surpassing most models. It demonstrates good uncertainty estimation capability in no-noise and low-noise conditions, providing prediction confidence and significantly enhancing robustness in real-world applications. We have open-sourced the code at https://github.com/AIDC-rPPG/RF-Net |
| title | RF-BayesPhysNet: A Bayesian rPPG Uncertainty Estimation Method for Complex Scenarios |
| topic | Machine Learning Artificial Intelligence 68T07, 62F15, 94A12 I.2.6; I.5.4; C.3 |
| url | https://arxiv.org/abs/2504.03915 |