Abstract
Remote photoplethysmography (rPPG) technique extracts blood volume pulse (BVP) signals from subtle pixel changes in video frames. This study introduces rFaceNet, an advanced rPPG method that enhances the extraction of facial BVP signals with a focus on facial contours. rFaceNet integrates identity-specific facial contour information and eliminates redundant data. It efficiently extracts facial contours from temporally normalized frame inputs through a Temporal Compressor Unit (TCU) and steers the model focus to relevant facial regions by using the Cross-Task Feature Combiner (CTFC). Through elaborate training, the quality and interpretability of facial physiological signals extracted by rFaceNet are greatly improved compared to previous methods. Moreover, our novel approach demonstrates superior performance than SOTA methods in various heart rate estimation benchmarks.
Abstract (translated)
远程光脉搏计（rPPG）技术从视频帧中微小的像素变化中提取血容量脉冲（BVP）信号。本研究引入了rFaceNet，一种专注于面部轮廓的先进rPPG方法，通过增强面部BVP信号的提取来提高。rFaceNet整合了与身份相关的面部轮廓信息，并消除了冗余数据。它通过Temporal Compressor Unit（TCU）高效地从时间归一化的帧输入中提取面部轮廓。通过详细的训练，rFaceNet提取面部生理信号的质量和对解释性的提高与以前的方法相比有了很大的改善。此外，我们的新方法在各种心率估计基准测试中的性能优于目前的最优方法。
URL
https://arxiv.org/abs/2403.09034
