TR2023-116
Unrolled IPPG: Video Heart Rate Esitmation via Unrolling Proximal Gradient Descent
-
- "Unrolled IPPG: Video Heart Rate Esitmation via Unrolling Proximal Gradient Descent", IEEE International Conference on Image Processing (ICIP), DOI: 10.1109/ICIP49359.2023.10222169, September 2023, pp. 2715-2719.BibTeX TR2023-116 PDF Video
- @inproceedings{Shenoy2023sep,
- author = {{Shenoy, Vineet and Marks, Tim K. and Mansour, Hassan and Lohit, Suhas}},
- title = {Unrolled IPPG: Video Heart Rate Esitmation via Unrolling Proximal Gradient Descent},
- booktitle = {IEEE International Conference on Image Processing (ICIP)},
- year = 2023,
- pages = {2715--2719},
- month = sep,
- publisher = {IEEE},
- doi = {10.1109/ICIP49359.2023.10222169},
- isbn = {978-1-7281-9835-4},
- url = {https://www.merl.com/publications/TR2023-116}
- }
,
- "Unrolled IPPG: Video Heart Rate Esitmation via Unrolling Proximal Gradient Descent", IEEE International Conference on Image Processing (ICIP), DOI: 10.1109/ICIP49359.2023.10222169, September 2023, pp. 2715-2719.
-
MERL Contacts:
-
Research Areas:
Abstract:
Imaging photoplethysmography (iPPG) is the process of estimating a person’s heart rate from video. In this work, we propose Un- rolled iPPG, in which we integrate iterative optimization updates with deep learning-based signal priors to estimate the pulse wave- form and heart rate from facial videos. We model the signal extracted from video as the sum of an underlying pulse signal and noise, but instead of explicitly imposing a handcrafted prior (e.g., sparsity in the frequency domain) on the signal, we learn priors on the signal and noise using neural networks. We solve for the underlying pulse sig- nal by unrolling proximal gradient descent; the algorithm alternates between gradient descent steps and application of learned denoisers, which replace handcrafted priors and their proximal operators. Using this method, we achieve state-of-the-art heart rate estimation on the challenging MMSE-HR dataset.