IEMEK Journal of Embedded Systems and Applications (대한임베디드공학회논문지)

Institute of Embedded Engineering of Korea (대한임베디드공학회)
권호 표지
DOI QR코드

DOI QR Code

Noise-robust Heart Rate Estimation Algorithm for Remote Photoplethysmography

원격 PPG를 위한 잡음에 강인한 심박수 추정 알고리즘

  • JunHo Cha (Kumoh National Institute of Technology) ;
  • JaeWook Shin (Kumoh National Institute of Technology)
  • 차준호 ;
  • 신재욱
  • Received : 2024.06.26
  • Accepted : 2024.08.01
  • Published : 2024.08.31
Download PDF
⟨ Previous Next ⟩

Abstract

This paper proposes a robust algorithm for heart rate estimation using remote photoplethysmography (rPPG). The algorithm employs a combination of adaptive filtering and frequency tracking to enhance the signal-to-noise ratio (SNR) and accurately estimate heart rates from facial videos. The LGI dataset, comprising videos of six participants performing various activities (resting, rotation, talk, gym), was utilized for evaluation. The ground truth heart rate was obtained using a CMS50E pulse oximeter, and a 10-second data window with FFT-based frequency analysis was applied to derive reference heart rates. The proposed method detects the face using Mediapipe API, selects the forehead region of interest (ROI), and extracts RGB signals. The signals undergo preprocessing, motion noise removal via adaptive filtering, and heart rate estimation using an adaptive notch filter. Experimental results demonstrate that the proposed algorithm outperforms existing methods, especially in challenging conditions such as during gym and talk activities.

Keywords

Acknowledgement

이 연구는 금오공과대학교 학술연구비로 지원되었음 (2022).

References

  1. G. De Haan, A. Van Leest, "Improved Motion Robustness of Remote-PPG by Using the Blood Volume Pulse Signature," Physiological Measurement, Vol. 35, No. 9, pp. 1913, 2014.
  2. W. Wang, A.C. Den Brinker, S. Stuijk, G. De Haan, "Algorithmic Principles of Remote PPG," IEEE Transactions on Biomedical Engineering, Vol. 64, No. 7, pp. 1479-1491, 2016.
  3. G. De Haan, V. Jeanne, "Robust Pulse Rate from Chrominance-based rPPG," IEEE Transactions on Biomedical Engineering, Vol. 60, No. 10, pp. 2878-2886, 2013.
  4. C. S. Pilz, A. Boccignone, A. Marcelli, "Local Group Invariance for Heart Rate Estimation from Face Videos in the Wild," Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 1254-1262, 2018.
  5. C. Zhao, M. Zhou, W. Han, Y. Feng, "Anti-motion Remote Measurement of Heart Rate based on Region Proposal Generation and Multi-scale ROI Fusion," IEEE Transactions on Instrumentation and Measurement, Vol. 71, pp. 1-13, 2022.
  6. S. Fiedler, K. Lange, J. Tresp, A. M. Kreitlow, "FaSeNet: Overcoming Limitations of Traditional ROI Extraction Methods for Remote PPG," Journal of Biomedical Optics, Vol. 25, No. 8, pp. 080501, 2020.
  7. J. Wei, S. Deng, L. Zhang, "Dynamic ROI Tracking Using MediaPipe Face Mesh for Remote Photoplethysmography," Biomedical Optics Express, Vol. 12, No. 2, pp. 1234-1245, 2021.
  8. C. Alvarez Casado, M. Bordallo Lopez, "Face2ppg: An Unsupervised Pipeline for Blood Volume Pulse Extraction from Faces," arXiv preprint arXiv:2202.04101, 2022.
  9. W. Chen, D. McDuff, "Deepphys: Video-based Physiological Measurement Using Convolutional Attention Networks," In Proceedings of the European Conference on Computer Vision (ECCV), pp. 349-365, 2018.
  10. G. De Haan, V. Jeanne, "Robust Pulse Rate from Chrominance-based rPPG," IEEE Transactions on Biomedical Engineering, Vol. 60, No. 10, pp. 2878-2886, 2013.
  11. G. De Haan, A. Van Leest, "Improved Motion Robustness of Remote-PPG by Using the Blood Volume Pulse Signature," Physiological Measurement, Vol. 35, No. 9, pp. 1913, 2014.
  12. J. Gideon, S. Stent, "The Way to My Heart is Through Contrastive Learning: Remote Photoplethysmography from Unlabelled Video," In Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 3995-4004, 2021.
  13. F. Haugg, M. Elgendi, C. Menon, "Effectiveness of Remote PPG Construction Methods: A Preliminary Analysis," Bioengineering, Vol. 9, No. 10, pp. 485, 2022.
  14. X. Liu, J. Fromm, S. Patel, D. McDuff, "Multi-task Temporal Shift Attention Networks for On-device Contactless Vitals Measurement," Advances in Neural Information Processing Systems, Vol. 33, pp. 19400-19411, 2020.
  15. W. Wang, A. C. den Brinker, G. De Haan, "Discriminative Signatures for Remote-PPG," IEEE Transactions on Biomedical Engineering, Vol. 67, No. 5, pp. 1462-1473, 2019.
  16. Z. Yu, Y. Shen, J. Shi, H. Zhao, P. H. S. Torr, G. Zhao, "Physformer: Facial Video-based Physiological Measurement with Temporal Difference Transformer," In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4186-4196, 2022.
  17. M. R. Petraglia, S. K. Mitra, J. Szczupak, "Adaptive Sinusoid Detection Using IIR Notch Filters and Multirate Techniques," IEEE Transactions on Circuits and Systems II: Analog and Digital Signal Processing, Vol. 41, No. 11, pp. 709-717, Nov. 1994.
  18. H. E. Liao, "Two Discrete Oscillator Based Adaptive Notch Filters (osc ANFs) for Noisy Sinusoids," IEEE Transactions on Signal Processing, Vol. 53, No. 2, pp. 528-538, Feb. 2005.
  19. W. Wu, Y. Xiao, J. Lin, L. Ma, K. Khorasani, "An Efficient Filter Bank Structure for Adaptive Notch Filtering and Applications," IEEE/ACM Transactions on Audio, Speech, and Language Processing, Vol. 29, pp. 3226-3241, Oct. 2021.
  20. J. Shin, J. Cho, "Noise-Robust Heart Rate Estimation Algorithm from Photoplethysmography Signal with Low Computational Complexity," Journal of Healthcare Engineering, Vol. 2019, pp. 1-7, 2019