RobustPPG: camera-based robust heart rate estimation using motion cancellation

Maity, Akash Kumar; Wang, Jian; Sabharwal, Ashutosh; Nayar, Shree K.

doi:10.1364/boe.465143

Cited by 13 publications

(4 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…That said, a more thorough analysis must be conducted to verify the generalization capabilities (especially for end-to-end neural network systems); gain broader insights into the roles that a system with principled, explainable approaches such as ours can have on these neural network methods; and use these insights to guide the future design of neural networks for PR extraction under challenging fitness scenarios. Such efforts can lead to the design and optimization of explainable neural-network-based modules in a systematic pipeline, for example, to understand the roles of adaptive filtering versus the recurrent neural network adopted in Maity et al's design [70] to handle motion.…”

Section: F Discussionmentioning

confidence: 99%

A Comparative Study of rPPG-Based Pulse Rate Tracking Algorithms for Fitness Activities

Zhu¹,

Wong²,

Lazri³

et al. 2023

Preprint

View full text Add to dashboard Cite

<p>Recent studies have shown that subtle changes in human face color due to heartbeats can be captured by regular RGB digital video cameras. It is possible, though challenging, to track one's pulse rate when a video contains significant subject's body motions in a fitness setting. The robustness gain in the recently proposed systems is often achieved by adding or changing certain modules in the system's pipeline. Most existing works, however, only evaluate the performance of the pulse rate estimation at the system level of particular pipeline configurations, whereas the contribution from each module remains unclear. To gain a better understanding of the performance at the module level and facilitate future research in explainable learning and artificial intelligence (AI) in physiological monitoring, this paper conducts an in-depth comparative study at the module level for video-based pulse rate tracking algorithms; a special focus is placed on challenging fitness scenarios involving significant movement. The representative efforts over the past decade in the field are reviewed, upon which a reconfigurable rPPG framework/pipeline is constructed comprising of major processing modules. For performance attribution, different candidates for each module are evaluated while having the rest of modules fixed. The performance evaluation is based on a signal quality metric and four pulse-rate estimation metrics and uses the simultaneously recorded ECG-based heart rate measurement as a reference. Experimental results using a challenging fitness dataset reveals the synergy between pulse color mapping and adaptive motion filtering in obtaining accurate pulse rate estimates. The results also suggest the importance of robust frequency tracking for accurate PR estimation in low signal-to-noise ratio fitness scenarios.</p>

show abstract

Section: F Discussionmentioning

confidence: 99%

A Comparative Study of rPPG-Based Pulse Rate Tracking Algorithms for Fitness Activities

Zhu¹,

Wong²,

Lazri³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

Section: E Impact Of the Fitness Motion Typementioning

confidence: 99%

A Comparative Study of rPPG-Based Pulse Rate Tracking Algorithms for Fitness Activities

Zhu,

Wong,

Lazri

et al. 2024

Preprint

View full text Add to dashboard Cite

Recent studies have shown that subtle changes in human face color due to heartbeats can be captured by regular RGB digital video cameras. It is possible, though challenging, to track one’s pulse rate when a video contains significant subject’s body motions in a fitness setting. The robustness gain in the recently proposed systems is often achieved by adding or changing certain modules in the system’s pipeline. Most existing works, however, only evaluate the performance of the pulse rate estimation at the system level of particular pipeline configurations, whereas the contribution from each module remains unclear. To gain a better understanding of the performance at the module level and facilitate future research in explainable learning and artificial intelligence (AI) in physiological monitoring, this paper conducts an in-depth comparative study for video-based pulse rate tracking algorithms; a special focus is placed on challenging fitness scenarios involving significant movement. The representative efforts over the past decade in the field are reviewed, upon which a reconfigurable rPPG framework/pipeline is constructed comprising of major processing modules. For performance attribution, different candidates for each module are evaluated while having the rest of modules fixed. The performance evaluation is based on a signal quality metric and four pulse-rate estimation metrics and uses the simultaneously recorded ECG-based heart rate measurement as a reference. Experimental results using a challenging fitness dataset reveals the synergy between pulse color mapping and adaptive motion filtering in obtaining accurate pulse rate estimates. The results also suggest the importance of robust frequency tracking for accurate PR estimation in low signal-to-noise ratio fitness scenarios.

show abstract

“…4,5 Although the feasibility of rPPG in remote health monitoring has been demonstrated 6 , little attention has been given to the impact of the age factor in datasets. Most state-of-theart research primarily focuses on enhancing model architectures to mitigate various interference factors, such as illumination changes 7 , skin tone variations 8 , and body movements 9 . Nevertheless, a high-performing rPPG model trained and tested on public datasets might not generalize well to the elderly population.…”

Section: Introductionmentioning

confidence: 99%

Addressing healthcare needs of the elderly in contactless blood oxygen saturation estimation with rPPG

Cao,

Li,

Yiu

et al. 2024

Computational Optical Imaging and Artificial Intelligence in Biomedical Sciences

View full text Add to dashboard Cite

Remote photoplethysmography (rPPG) is an effective technique for non-contact estimation of vital signs using video-based detection of exposed skin. It enables contactless healthcare services for clinical measurements and medical diagnosis. While existing rPPG methods primarily focus on enhancing robustness against interference factors like motion artifacts and illumination changes, limited attention has been given to the influence of the age factor on rPPG model performance. This study explicitly analyzed the impact of the age factor on the application of an rPPG method to the blood oxygen saturation (SpO 2 ) estimation. Two key observations were made. First, it was more challenging to estimate SpO 2 with rPPG for the elderly than for young individuals. Second, the performance of SpO 2 estimation for the elderly could be improved by dividing the training data into different age groups and exclusively training the model on data collected from the elderly. These observations highlighted that the age factor had a significant impact on rPPG methods, emphasizing the need for explicit consideration of the age factor in rPPG method design.

show abstract

RobustPPG: camera-based robust heart rate estimation using motion cancellation

Cited by 13 publications

References 22 publications

A Comparative Study of rPPG-Based Pulse Rate Tracking Algorithms for Fitness Activities

A Comparative Study of rPPG-Based Pulse Rate Tracking Algorithms for Fitness Activities

A Comparative Study of rPPG-Based Pulse Rate Tracking Algorithms for Fitness Activities

Addressing healthcare needs of the elderly in contactless blood oxygen saturation estimation with rPPG

Contact Info

Product

Resources

About