Scholarlink

Background <p>Remote photoplethysmography (rPPG) is a technique that extracts physiological signals, such as heart rate, from facial videos using standard Red-Green-Blue cameras. While rPPG offers valuable health insights, it also exposes individuals to potential misuse, as sensitive information can be inferred without consent.</p> Methods <p>This paper introduces a reversible video modification framework for removing, encrypting, transmitting, and restoring rPPG signals in facial videos, using frame-wise sinusoidal modulation applied to specific rPPG-rich facial regions, with a focus on maintaining perceptual quality and concealing the true heart rate. Our approach is contrasted with prior methods using seven rPPG techniques on the LGI-PPGI dataset, encompassing various activities. Evaluation metrics include PSNR, SSIM, correlation, dynamic time warping, and a composite score reflecting both signal suppression and visual fidelity.</p> Results <p>Here we show that our method achieves an overall score above 0.75 across all rPPG methods, approximately 50% higher than previous approaches. It also demonstrates high visual fidelity (PSNR ≈ 68, SSIM ≈ 0.97) and effectively conceals physiological information, inducing an average heart rate estimation error 22 bpm higher than prior methods.</p> Conclusions <p>This study presents the first end-to-end reversible framework for secure, privacy-preserving video transmission of facial recordings. The approach is lightweight, effective across diverse activities, and holds promise for real-time applications such as video conferencing and telehealth.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Balancing cardiac privacy with quality in video recordings

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年11月20日

查看全文
  • Mohamed Elgendi,
  • Aojie Yu,
  • Saksham Bhutani,
  • Carlo Menon

摘要

Background

Remote photoplethysmography (rPPG) is a technique that extracts physiological signals, such as heart rate, from facial videos using standard Red-Green-Blue cameras. While rPPG offers valuable health insights, it also exposes individuals to potential misuse, as sensitive information can be inferred without consent.

Methods

This paper introduces a reversible video modification framework for removing, encrypting, transmitting, and restoring rPPG signals in facial videos, using frame-wise sinusoidal modulation applied to specific rPPG-rich facial regions, with a focus on maintaining perceptual quality and concealing the true heart rate. Our approach is contrasted with prior methods using seven rPPG techniques on the LGI-PPGI dataset, encompassing various activities. Evaluation metrics include PSNR, SSIM, correlation, dynamic time warping, and a composite score reflecting both signal suppression and visual fidelity.

Results

Here we show that our method achieves an overall score above 0.75 across all rPPG methods, approximately 50% higher than previous approaches. It also demonstrates high visual fidelity (PSNR ≈ 68, SSIM ≈ 0.97) and effectively conceals physiological information, inducing an average heart rate estimation error 22 bpm higher than prior methods.

Conclusions

This study presents the first end-to-end reversible framework for secure, privacy-preserving video transmission of facial recordings. The approach is lightweight, effective across diverse activities, and holds promise for real-time applications such as video conferencing and telehealth.