Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

DHA-eGCN: Differential Hyperedge Attention-Enhanced Graph Convolution Network for Skeleton-Based Human Action Recognition.

Sensors (Basel, Switzerland)·2026
Same author

Web-Based Explainable Machine Learning-Based Drug Surveillance for Predicting Sunitinib- and Sorafenib-Associated Thyroid Dysfunction: Model Development and Validation Study.

JMIR formative research·2025
Same author

Estimating a 3D Human Skeleton from a Single RGB Image by Fusing Predicted Depths from Multiple Virtual Viewpoints.

Sensors (Basel, Switzerland)·2025
Same author

Multi-Focus Image Fusion and Depth Map Estimation Based on Iterative Region Splitting Techniques.

Journal of imaging·2021

Related Experiment Video

Updated: Jul 23, 2025

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

3.8K

Heart Rate Estimation from Facial Image Sequences of a Dual-Modality RGB-NIR Camera.

Wen-Nung Lie1, Dao-Quang Le1, Chun-Yu Lai1

  • 1Department of Electrical Engineering, Center for Innovative Research on Aging Society (CIRAS), and Advanced Institute of Manufacturing with High-Tech Innovations (AIM-HI), National Chung Cheng University, Chia-Yi 621, Taiwan.

Sensors (Basel, Switzerland)
|July 14, 2023
PubMed
Summary

This study introduces an RGB-NIR dual-modality technique for accurate remote heart rate estimation using facial videos. The method employs advanced denoising to effectively analyze remote photoplethysmogram (rPPG) signals, even in challenging conditions.

Keywords:
RGB-NIR dual modalitiesfacial image sequenceheart rate estimationremote PPGrobust PCA

More Related Videos

Author Spotlight: Automated Deep Brain Stimulation for Parkinson's Disease - Exploring the Possibilities and Challenges of Home Monitoring
06:32

Author Spotlight: Automated Deep Brain Stimulation for Parkinson's Disease - Exploring the Possibilities and Challenges of Home Monitoring

Published on: July 14, 2023

1.3K
Dual-mode Imaging of Cutaneous Tissue Oxygenation and Vascular Function
11:35

Dual-mode Imaging of Cutaneous Tissue Oxygenation and Vascular Function

Published on: December 8, 2010

16.6K

Related Experiment Videos

Last Updated: Jul 23, 2025

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

3.8K
Author Spotlight: Automated Deep Brain Stimulation for Parkinson's Disease - Exploring the Possibilities and Challenges of Home Monitoring
06:32

Author Spotlight: Automated Deep Brain Stimulation for Parkinson's Disease - Exploring the Possibilities and Challenges of Home Monitoring

Published on: July 14, 2023

1.3K
Dual-mode Imaging of Cutaneous Tissue Oxygenation and Vascular Function
11:35

Dual-mode Imaging of Cutaneous Tissue Oxygenation and Vascular Function

Published on: December 8, 2010

16.6K

Area of Science:

  • Biomedical Engineering
  • Computer Vision
  • Signal Processing

Background:

  • Remote photoplethysmogram (rPPG) analysis enables non-contact heart rate estimation.
  • Existing rPPG methods often struggle with noise and varying illumination conditions.
  • Dual-modality (RGB-NIR) approaches offer potential for improved signal extraction.

Purpose of the Study:

  • To develop and validate an RGB-NIR dual-modality technique for robust remote heart rate estimation.
  • To introduce novel denoising techniques (MASF, WD, RPCA) for enhanced rPPG signal analysis.
  • To evaluate the system's performance on diverse datasets under varying lighting and motion conditions.

Main Methods:

  • Utilized an Independent Component Analysis (ICA)-based algorithm for rPPG signal extraction.
  • Implemented Modified Amplitude Selective Filtering (MASF), Wavelet Decomposition (WD), and Robust Principal Component Analysis (RPCA) for denoising.
  • Collected and analyzed data from the public PURE dataset and a custom CCUHR dataset using an Intel RealSense D435 camera.

Main Results:

  • Achieved competitive accuracy compared to state-of-the-art methods, even with short video durations.
  • Demonstrated mean absolute error (MAE) of 4.45 bpm and RMSE of 6.18 bpm for RGB-NIR videos (10-20s) in the CCUHR dataset.
  • Reported MAE of 3.24 bpm and RMSE of 4.1 bpm for RGB videos (60s) in the PURE dataset.

Conclusions:

  • The proposed RGB-NIR dual-modality rPPG technique provides accurate heart rate estimation.
  • The integrated denoising methods effectively improve rPPG signal quality under diverse conditions.
  • The system offers advantages of accessible hardware, efficient computation, and broad applicability.