TR2021-099

TURNIP: Time-series U-NET with Recurrence for NIR Imaging PPG

    •  Comas, A., Marks, T.K., Mansour, H., Lohit, S., Ma, Y., Liu, X., "TURNIP: Time-series U-NET with Recurrence for NIR Imaging PPG", IEEE International Conference on Image Processing (ICIP), DOI: 10.1109/​ICIP42928.2021.9506663, September 2021, pp. 309-313.
      BibTeX TR2021-099 PDF
      • @inproceedings{Comas2021sep,
      • author = {Comas, Armand and Marks, Tim K. and Mansour, Hassan and Lohit, Suhas and Ma, Yechi and Liu, Xiaoming},
      • title = {TURNIP: Time-series U-NET with Recurrence for NIR Imaging PPG},
      • booktitle = {IEEE International Conference on Image Processing (ICIP)},
      • year = 2021,
      • pages = {309--313},
      • month = sep,
      • publisher = {IEEE},
      • doi = {10.1109/ICIP42928.2021.9506663},
      • url = {https://www.merl.com/publications/TR2021-099}
      • }
  • MERL Contacts:
  • Research Areas:

    Artificial Intelligence, Computer Vision, Machine Learning

Abstract:

Near-Infrared (NIR) videos of faces acquired with active illumination for the problem of estimating the photoplethysmogram (PPG) signal from a distance have demonstrated improved robustness to ambient illumination. Contrary to the multichannel RGB-based solutions, prior work in the NIR regime has been purely model-based and has exploited sparsity of the PPG signal in the frequency domain. In contrast, we propose in this paper a modular neural network-based framework for estimating the remote PPG (rPPG) signal. We test our approach on two challenging datasets where the subjects are inside a car and can have a lot of head motion. We show that our method outperforms existing model-based methods as well as end-to-end deep learning methods for rPPG estimation from NIR videos.