Uncertainty Quantification for Deep Learning-Based Remote Photoplethysmography
- 25 September 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 72 (00189456) , 1-12
Abstract
Recently, deep learning (DL) based remote photoplethysmography (rPPG) methods have made great progress in non-contact heart rate (HR) measurements. However, the reliability of rPPG measurements is still a bottleneck for realistic applications due to its susceptibility to motion and illumination noise. It is increasingly important to develop quantitative assessment methods for rPPG measurements. In this paper, we propose to quantify the uncertainty of a convolutional neural network (CNN)-based rPPG model as the reference-free quantitative quality assessment metric. Specifically, we evaluate and compare both the Bayesian neural network (BNN) method and the deep ensemble method to estimate the uncertainty of HR measurements from the CNN model. The effectiveness of the predicted uncertainty from both methods is verified on two public databases, where the uncertainty is found to be highly correlated with the true absolute error, and the advantages and limitations of BNN and ensemble methods are also analyzed. This study is instructive for the development of uncertainty-aware DL-based rPPG models for realistic applications.Keywords
Funding Information
- National Natural Science Foundation of China (62271186, 62171176, 32271431, 41901350)
- Anhui key project of research and development plan (202104d07020005)
- Fundamental Research Funds for the Central Universities (JZ2021HGPA0061)
This publication has 28 references indexed in Scilit:
- Unsupervised skin tissue segmentation for remote photoplethysmographyPattern Recognition Letters, 2019
- Deep and Confident Prediction for Time Series at Uber2017
- DistancePPG: Robust non-contact vital signs monitoring using a cameraBiomedical Optics Express, 2015
- Dynamic ROI based on K-means for remote photoplethysmography2015
- Non-contact video-based pulse rate measurement on a mobile service robot2014
- Facial Landmark Detection by Deep Multi-task Learning2014
- Robust Pulse Rate From Chrominance-Based rPPGIEEE Transactions on Biomedical Engineering, 2013
- A Multimodal Database for Affect Recognition and Implicit TaggingIEEE Transactions on Affective Computing, 2011
- Remote plethysmographic imaging using ambient lightOptics Express, 2008
- Neural network ensemblesIEEE Transactions on Pattern Analysis and Machine Intelligence, 1990