BVPNet: Video-to-BVP Signal Prediction for Remote Heart Rate Estimation

Abhijit Das (1) , Hao Lu (2) , Hu Han (2) , Antitza Dantcheva (3) , Shiguang Shan (2) , Xilin Chen (2)

1 Computer Science & Engineering Department [Patiala, Thapar Uni.]
2 ICT - CAS Institute of Computing Technology
3 STARS - Spatio-Temporal Activity Recognition Systems

In this paper, we propose a new method for remote photoplethysmography (rPPG) based heart rate (HR) estimation. In particular, our proposed method BVPNet is streamlined to predict the blood volume pulse (BVP) signals from face videos. Towards this, we firstly define ROIs based on facial landmarks and then extract the raw temporal signal from each ROI. Then the extracted signals are pre-processed via first-order difference and Butterworth filter and combined to form a Spatial-Temporal map (STMap). We then propose to revise U-Net, in order to predict BVP signals from the STMap. BVPNet takes into account both temporal and frequency domain losses in order to learn better than conventional models. Our experimental results suggest that our BVPNet outperforms the state-of-the-art methods on two publicly available datasets (MMSE-HR and VIPL-HR).

Domaines: Traitement des images [eess.IV]

Abhijit Das, Hao Lu, Hu Han, Antitza Dantcheva, Shiguang Shan, et al.. BVPNet: Video-to-BVP Signal Prediction for Remote Heart Rate Estimation. FG 2021 - IEEE International Conference on Automatic Face and Gesture Recognition, Dec 2021, Jodhpur (virtual), India. ⟨10.1109/FG52635.2021.9666996⟩. ⟨hal-03536497⟩