Deep-HR: Fast heart rate estimation from face video under realistic conditions

作者：

Highlights：

• We propose an effective yet simple remote HR estimation method based on deep learning.

• The propsoed method is robust against noise, face movement and low-quality videos.

• Two deep networks are adversarially learned to refine the outputs for HR estimation.

• We introduce a new challenging data-set named HR-D.

• Our results are better than state-of-the-art in terms of complexity and accuracy.

摘要

•We propose an effective yet simple remote HR estimation method based on deep learning.•The propsoed method is robust against noise, face movement and low-quality videos.•Two deep networks are adversarially learned to refine the outputs for HR estimation.•We introduce a new challenging data-set named HR-D.•Our results are better than state-of-the-art in terms of complexity and accuracy.

论文关键词：Remote heart-rate,Video processing,End to end,CNN

论文评审过程：Received 13 December 2020, Revised 19 June 2021, Accepted 10 July 2021, Available online 31 July 2021, Version of Record 18 August 2021.

论文官网地址：https://doi.org/10.1016/j.eswa.2021.115596