Illumination-robust Camera-PPG via Skin-Guided Auto-Exposure
Shuhan Yi, Dongfang Yu, Yingen Zhu, Wenjin Wang
Southern University of Science and Technology
阅读操作
确认中在文库中上传 PDF 后可生成中文音频讲解。
摘要与影响
In case of varying lighting conditions, especially in frontal lighting and backlighting, current remote photoplethysmography (rPPG) methods face many challenges. This study proposes a novel strategy, called Skin-Guided Auto-Exposure (Skin-AE) that significantly enhances the quality of rPPG signal extraction under these adverse lighting conditions, by using facial skin intensity to control the camera exposure setting in real-time. The Skin-AE utilizes a Proportional-Integral-Derivative (PID) algorithm to dynamically adjust the exposure time according to the average brightness of the facial region. This approach allows for adaptive optimization of facial brightness in real-time, significantly improving the performance of rPPG extraction in frontal lighting and backlighting conditions. The results indicate that Skin-AE improved the accuracy of heart rate measurement to 94.25%, significantly higher than 57.96% obtained by the Global-AE algorithm of an industrial camera (IDS). This demonstrates the effectiveness of the Skin-AE method in measuring rPPG signals.
逐年被引趋势
关键指标
同类平均 = 1
同领域 · 同年份 · 同类型
Google Scholar 与 OpenAlex 的被引统计范围不同,数值存在差异属正常。
AI 辅助阅读
依据:摘要
可就本文提问;依据不足时会说明。
学术脉络
学科主题
工程Non-Invasive Vital Sign Monitoring
Heart Rate Variability and Autonomic Control · Biometric Identification and Security