DeepPhys: Video-Based Physiological Measurement Using Convolutional Attention Networks

Weixuan Chen, Daniel McDuff; Proceedings of the European Conference on Computer Vision (ECCV), 2018, pp. 349-365

Abstract


Non-contact video-based physiological measurement has many applications in health care and human-computer interaction. Practical applications require measurements to be accurate even in the presence of large head rotations. We propose the first end-to-end system for video-based measurement of heart and breathing rate using a deep convolutional network. The system features a new motion representation based on a skin reflection model and a new attention mechanism using appearance information to guide motion estimation, both of which enable robust measurement under heterogeneous lighting and major motions. Our approach significantly outperforms all current state-of-the-art methods on both RGB and infrared video datasets. Furthermore, it allows spatial-temporal distributions of physiological signals to be visualized via the attention mechanism.

Related Material


[pdf] [arXiv]
[bibtex]
@InProceedings{Chen_2018_ECCV,
author = {Chen, Weixuan and McDuff, Daniel},
title = {DeepPhys: Video-Based Physiological Measurement Using Convolutional Attention Networks},
booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
month = {September},
year = {2018}
}