Neurodata Lab's Approach to the Challenge on Computer Vision for Physiological Measurement

Mikhail Artemyev, Marina Churikova, Mikhail Grinenko, Olga Perepelkina; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2020, pp. 316-317

This paper introduces the Neurodata Lab's approach presented at the 1st Challenge on Remote Physiological Signal Sensing (RePSS) organized within CVPR2020. The RePSS challenge was focused on measuring the average heart rate from color facial videos, which is one of the most fundamental problems in the field of computer vision. Our deep learning-based approach includes 3D spatiotemporal attention convolutional neural network for photoplethysmogram extraction and 1D convolutional neural network pre-trained on synthetic data for time series analysis. It provides state-of-the-art results outperforming those of other participants on a mixture of VIPL and OBF databases: MAE=6.94 (12.3% improvement compared to the top-2 result), RMSE=10.68 (24.6% improvement), Pearson R = 0.755 (28.2% improvement).