Scholarlink

<p>Remote Photoplethysmography (rPPG) is a non-invasive, contactless monitoring method that enables real-time measurement of heart rate and other cardiac-related physiological parameters by extracting blood volume pulse signals. This technology facilitates timely cardiovascular health assessment and early detection of potential cardiac abnormalities, thereby aiding in the prevention of adverse events. However, rPPG performance is often degraded in real-world applications due to factors such as lighting variations, complex backgrounds, and facial movements, which increase feature extraction difficulty. To address these challenges, this study proposes ChromaConv-RPPG, an improved rPPG model based on chromaticity conversion for remote heart rate detection. The model locates facial regions in video frames and employs video magnification to suppress background interference. By converting RGB images to the CIELab color space and leveraging the enhanced sensitivity of the <InlineEquation ID="IEq1"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="11760_2025_4732_Article_IEq1.gif" Format="GIF" Height="14" Rendition="HTML" Resolution="72" Type="Linedraw" Width="18" /> </InlineMediaObject> <EquationSource Format="TEX">\(a^*\)</EquationSource> <EquationSource Format="MATHML"><math> <msup> <mi>a</mi> <mo>∗</mo> </msup> </math></EquationSource> </InlineEquation>-channel to subtle color variations, it achieves more precise facial color dynamics tracking while mitigating illumination effects and motion artifacts. Additionally, to address the issues of high-frequency noise and baseline drift in pulse wave signals, a wavelet transform-based denoising method is employed, which significantly enhances the accuracy and robustness of rPPG signals in complex environments. Experimental results demonstrate that the proposed model outperforms existing approaches in key metrics such as accuracy and stability, with processed signal quality approaching that of contact-based monitoring devices, making it a viable alternative in certain scenarios.</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

ChromaConv-RPPG: Anti-Interference Remote Photoplethysmography via Chromaticity Conversion

  • 期刊论文

  • 发表日期：

    2025年9月11日

查看全文
  • Xiujuan Sun,
  • Hongxue Li,
  • Dong Cao,
  • Ying Su,
  • Wangning Chen,
  • Chuanjiang Wang

摘要

Remote Photoplethysmography (rPPG) is a non-invasive, contactless monitoring method that enables real-time measurement of heart rate and other cardiac-related physiological parameters by extracting blood volume pulse signals. This technology facilitates timely cardiovascular health assessment and early detection of potential cardiac abnormalities, thereby aiding in the prevention of adverse events. However, rPPG performance is often degraded in real-world applications due to factors such as lighting variations, complex backgrounds, and facial movements, which increase feature extraction difficulty. To address these challenges, this study proposes ChromaConv-RPPG, an improved rPPG model based on chromaticity conversion for remote heart rate detection. The model locates facial regions in video frames and employs video magnification to suppress background interference. By converting RGB images to the CIELab color space and leveraging the enhanced sensitivity of the \(a^*\) a ∗ -channel to subtle color variations, it achieves more precise facial color dynamics tracking while mitigating illumination effects and motion artifacts. Additionally, to address the issues of high-frequency noise and baseline drift in pulse wave signals, a wavelet transform-based denoising method is employed, which significantly enhances the accuracy and robustness of rPPG signals in complex environments. Experimental results demonstrate that the proposed model outperforms existing approaches in key metrics such as accuracy and stability, with processed signal quality approaching that of contact-based monitoring devices, making it a viable alternative in certain scenarios.