摘要
基于视频的心率监测相对于传统的心率监测在一些非接触的测量场景下具有独特的优势,因此已成为国内外研究的重点。人体皮肤的颜色会随着心脏的跳动发生微弱的变化,通过摄像头捕捉到这些变化,并进行一定的处理后,就能够计算出心率值的估计。在现有的使用面部视频来提取心率的方法中,通常受人体运动的干扰和环境光线的变化而难以对心率做出准确的估计。针对上述问题,本文利用皮肤在RGB颜色空间中,对于不同波长光线的吸收特性,提出了一种基于脉搏特征平面的方法,从而实现了心率的实时计算和准确估计。通过对比实验表明,本文所使用的方法与指夹式脉搏血氧仪的测量结果具有较高的一致性,且本文的算法较之其他方法具有更高的准确性和更低的复杂度,完全能够满足日常心率监测的要求。
Video-based heart rate monitoring has unique advantages on traditional heart rate monitoring in non-contact measurement scenarios. The color of the human skin changes slightly with the beating of the heart. After capturing these changes through the camera and processing the data, the heart rate can be calculated. The existing methods of extracting heart rate using facial video are difficult to make an accurate estimation of the heart rate due to disturbance of human motion and ambient light change. Aiming at the above problems, this paper proposes a method based on pulse feature plane for the skin absorption characteristics of light with different wavelengths in the RGB color space, and using it to realize the real-time estimation of heart rate. The comparison experiments show that the method used in this paper has a high consistency with the measurement results of the pulse oximeter, and the algorithm of this paper has higher accuracy and lower complexity than other methods, which can meet the requirements of daily heart rate monitoring very well.
作者
关天一
宋春林
Guan tian-yi;Song chun-lin
出处
《信息技术与信息化》
2018年第10期78-82,共5页
Information Technology and Informatization
基金
国家科技重大专项(2017ZX05005-001-005)资助
