基于树莓派摄像头的心率测量方法研究

详细信息    查看全文 | 推荐本文 |

英文篇名：Heart Rate Measurement Based on Raspberry Pi Camera 作者：罗凯 ; 候晓旭 英文作者：LUO Kai;HOU Xiao-xu;School of Biological Science and Medical Engineering, Beihang University;Optical Mechanical and Electrical Room, National Institutes for Food and Drug Control; 关键词：树莓派 ; 心率 ; 成像式光电容积描计术 英文关键词：raspberry pi;;heart rate;;image photoplethysmography 中文刊名：SZJT 英文刊名：Digital Technology and Application 机构：北京航空航天大学生物与医学工程学院;中国食品药品检定研究院光机电室; 出版日期：2018-05-05 出版单位：数字技术与应用 年：2018 期：v.36;No.335 语种：中文; 页：SZJT201805054 页数：2 CN：05 ISSN：12-1369/TN 分类号：117-118

摘要

心率是一项重要的生命体征,可以有效直接的评估人们的健康状态。本文提出了一种基于树莓派摄像头的心率测量方法,并搭建了一个树莓派心率测量平台。基于成像式光电容积描计术(iPPG)原理~([1]),使用独立成分分析(ICA)方法从人脸视频原始信号当中分离出脉搏波相关分量;用傅里叶变换进行频域分析得到心率值。实验结果证明该方法测量准确度高,误差在每分种4跳以内。由于树莓派廉价、便携、操作方便,并且基于光电容积描计术的测量方式具有无创、非接触的特点,因此该设备在日常生理信号监测领域有着具大的应用前景。
        Heart rate is an important vital sign, which can directly and effectively evaluate people's health. This paper presents a heart rate measurement method based on Raspberry Pi camera and builds a heart rate measurement platform. Based on the principle of image Photoplethysmography(iPPG)~([1]), pulse wave related components are separated from the original signal of face video by independent component analysis(ICA), and Fourier transform is used to analyze the heart rate in frequency domain. The experimental results show that the accuracy of the method is high and the error is within 4 beats per minutes. Because the Raspberry Pi is cheap, portable, convenient to operate, and the measurement method based on i PPG has the characteristics of non-invasive and non-contact, it has a great application prospect in the field of daily physiological signal monitoring.

引文

[1]Wu T,Blazek V,Schmitt H J.Photoplethysmography imaging:a new noninvasive and noncontact method for mapping of the dermal perfusion changes[J].2000,4163:62-70.
    [2]Zhao M,Adib F,Katabi D.Emotion recognition using wireless signals[C]//International Conference on Mobile Computing and NETWORKING.ACM,2017:95-108.
    [3]Castaldo R,Melillo P,Pecchia L.Acute Mental Stress Assessment via Short Term HRV Analysis in Healthy Adults:A Systematic Review[J].Biomedical Signal Processing&Control,2015,18:370-377.
    [4]Al-Libawy H,Al-Ataby A,Al-Nuaimy W,et al.HRV-based operator fatigue analysis and classification using wearable sensors[C]//International Multi-Conference on Systems,Signals&Devices.IEEE,2016:268-273.
    [5]Poh M Z,Mcduff D J,Picard R W.Non-contact,automated cardiac pulse measurements using video imaging and blind source separation[J].Optics Express,2010,18(10):10762-10774.
    [6]Fan Q,Li K.Non-contact remote estimation of cardiovascular parameters[J].Biomedical Signal Processing&Control,2018,40:192-203.
    [7]冯军,汤文明,曹剑剑,等.非接触式心率测量研究初步[J].中国生物医学工程学报,2017,36(5):627-631.
    [8]孔令琴.非接触式生理信号检测关键技术研究[D].北京理工大学,2014.
    [9]Kazemi V,Sullivan J.One millisecond face alignment with an ensemble of regression trees[C]//Computer Vision and Pattern Recognition.IEEE,2014:1867-1874.
    [10]Lee J,Matsumura K,Yamakoshi K I,et al.Comparison between red,green and blue light reflection photoplethysmography for heart rate monitoring during motion[C]//Engineering in Medicine and Biology Society.IEEE,2013:1724-1727.