Visual Heart Rate Estimation from RGB Facial Video using Spectral Reflectance

TL;DR

This paper introduces a spectral reflectance-based framework for heart rate estimation from facial videos, demonstrating robustness to motion and lighting artifacts and outperforming previous methods on a standard dataset.

Contribution

It presents a novel spectral reflectance approach combined with deep learning face detection, improving accuracy and robustness over existing techniques.

Findings

Outperforms previous methods on MAHNOB HCI dataset

Robust to motion and illumination artifacts

Uses Faster R-CNN for face detection

Abstract

Estimation of the Heart rate from the facial video has a number of applications in the medical and fitness industries. Additionally, it has become useful in the field of gaming as well. Several approaches have been proposed to seamlessly obtain the Heart rate from the facial video, but these approaches have had issues in dealing with motion and illumination artifacts. In this work, we propose a reliable HR estimation framework using the spectral reflectance of the user, which makes it robust to motion and illumination disturbances. We employ deep learning-based frameworks such as Faster RCNNs to perform face detection as opposed to the Viola Jones algorithm employed by previous approaches. We evaluate our method on the MAHNOB HCI dataset and found that the proposed method is able to outperform previous approaches.Estimation of the Heart rate from facial video has a number of applications in the medical and the fitness industries. Additionally, it has become useful in the field of gaming as well. Several approaches have been proposed to seamlessly obtain the Heart rate from the facial video, but these approaches have had issues in dealing with motion and illumination artifacts. In this work, we propose a reliable HR estimation framework using the spectral reflectance of the user, which makes it robust to motion and illumination disturbances. We employ deep learning-based frameworks such as Faster RCNNs to perform face detection as opposed to the Viola-Jones algorithm employed by previous approaches. We evaluate our method on the MAHNOB HCI dataset and found that the proposed method is able to outperform previous approaches.