基于指端脉搏波视频信号的心率稳定检测算法
|
摘要
目的:研究一种基于脉搏波的稳定检测心率的算法。方法:提出一种基于快速独立成分分析(FastICA)算法处理指端脉搏波视频信号。首先通过手机摄像头采集手指视频,在每帧图片中提取感兴趣区域(ROI),根据每个区域中像素灰度值的变化得到血液容积变化的时序曲线;然后通过对ROI进行RGB通道分离和FastICA后,分别选取红、绿色分量与盲源分离后的估计信号进行相关性分析,筛选出相关性最大的作为后续提取心率的信号,并与波峰法测得的心率进行对比,得到一种稳定的心率检测算法,并利用SPSS软件做相关性分析。结果:选取R、G通道信号的一致性在95%以上,基于FastICA的算法与统计波峰法获取心率的一致性在95%以上。结论:FastICA算法能够有效地提高心率测量的稳定性,实验结果验证了该方法的可行性和有效性,对于基于脉搏波的人体生理参数获取具有重要意义。
Objective To propose a pulse wave-based algorithm that can detect the heart rates stably. Methods A fast independent component analysis(Fast ICA) algorithm is proposed to process the video signals of pulse waves on the finger tip. Firstly, the video of the finger was obtained by cell phone camera; and the region of interest was extracted in each frame of the picture; and the curve of the blood volume changing with time was obtained by investigating the variation of pixel gray values of each frame image. Then, RGB channel segregation and Fast ICA were conducted on regions of interest. The correlative analysis was performed on R, G channel signals and the estimated signals after blind source separation. The most relevant signals were adopted to obtain heart rates which were then compared with the heart rates measured by wave peak detection. Finally, an algorithm for stably detecting heart rates was obtained, and SPSS Software was utilized for correlation analysis. Results The consistency of the R and G channel signals was higher than 95%. Moreover, the agreement between the algorithm and the wave peak detection was higher than 95%. Conclusion Fast ICA algorithm can effectively improve the stability of heart rate measurement. The experimental results verify the feasibility and effectiveness of the proposed method which is of great significance for the acquisition of human physiological parameters based on the pulse waves.
Objective To propose a pulse wave-based algorithm that can detect the heart rates stably. Methods A fast independent component analysis(Fast ICA) algorithm is proposed to process the video signals of pulse waves on the finger tip. Firstly, the video of the finger was obtained by cell phone camera; and the region of interest was extracted in each frame of the picture; and the curve of the blood volume changing with time was obtained by investigating the variation of pixel gray values of each frame image. Then, RGB channel segregation and Fast ICA were conducted on regions of interest. The correlative analysis was performed on R, G channel signals and the estimated signals after blind source separation. The most relevant signals were adopted to obtain heart rates which were then compared with the heart rates measured by wave peak detection. Finally, an algorithm for stably detecting heart rates was obtained, and SPSS Software was utilized for correlation analysis. Results The consistency of the R and G channel signals was higher than 95%. Moreover, the agreement between the algorithm and the wave peak detection was higher than 95%. Conclusion Fast ICA algorithm can effectively improve the stability of heart rate measurement. The experimental results verify the feasibility and effectiveness of the proposed method which is of great significance for the acquisition of human physiological parameters based on the pulse waves.
引文
[1]汪洋.基于PPG的人体生理指标的测量方法研究[D].武汉:武汉工程大学, 2015.WANG Y. Study of measuring the physiological indexes of humanbody based on PPG[D]. Wuhan:Wuhan Institute of Technology,2015.
[2] GIL E, ORINI M, BAILON R, et al. Photoplethysmography pulse ratevariability as a surrogate measurement of heart rate variability duringnon-stationary conditions[J]. Physiol Meas, 2010, 31(9):1271-1290.
[3]万铮结.基于人脸视频图像的心率检测研究[D].杭州:浙江工业大学, 2014.WAN Z J. Research of heart rate detection based on facial video[D].Hangzhou:Zhejiang University of Technology, 2014.
[4]赵素文,高凡,邓莉.小波变换结合快速傅里叶变换从PPG中提取呼吸率[J].中国医学物理学杂志, 2016, 33(1):39-43.ZHAO S W, GAO F, DENG L. Respiratory rate extracted fromphotoplethysmography signals by using wavelet transform and fastFourier transform[J]. Chinese Journal of Medical Physics, 2016, 33(1):39-43.
[5]李向东,乐建威,王新图.脉搏波信号分析方法的研究进展[J].数据采集与处理, 2009, 24(b10):29-33.LI X D, LE J W, WANG X T. Research progress in pulse wave signalanalysis methods[J]. Journal of Data Acquisition&Processing, 2009,24(b10):29-33.
[6]杨建.脉搏波信号采集与分析方法的研究[J].电脑与信息技术, 2014,22(3):53-55.YANG J. Research in pulse wave signal acquisition and analysismethods[J]. Computer and Information Technology, 2014, 22(3):53-55.
[7]祝宇虹,张富强,李满天,等.一种基于数学形态学的脉搏波信号预处理方法研究[J].北京生物医学工程, 2009, 28(2):122-125.ZHU Y H, ZHANG F Q, LI M T, et al. A new signal pre-processingmethod of pulse wave based on mathematical morphology theory[J].Beijing Biomedical Engineering, 2009, 28(2):122-125.
[8]马俊领,王成,李章俊,等.基于PPG的心率和呼吸频率的测量研究[J].光学技术, 2011, 37(3):309-312.MA J L, WANG C, LI Z J, et al. Study of measuring heart rate andrespiration rate based on PPG[J]. Optical Technique, 2011, 37(3):309-312.
[9]雷恒波,郭友达,莫镜清,等.基于人脸视频的光电容积脉搏波信号获取与处理[J].中国医学物理学杂志, 2016, 33(11):1178-1182.LEI H B, GUO Y D, MO J Q, et al. Photoplethysmography signalacquisition and processing based on facial video[J]. Chinese Journalof Medical Physics, 2016, 33(11):1178-1182.
[10]雷恒波,莫镜清,郭友达,等.基于手指视频的光电容积脉搏波信号获取[J].中国医疗设备, 2016, 31(11):42-45.LEI H B, MO J Q, GUO Y D, et al. Photoplethysmography signalacquisition based on finger video[J]. China Medical Equipment, 2016,31(11):42-45.
[11]胡爱军,孙敬敬,向玲.经验模态分解中的模态混叠问题[J].振动测试与诊断, 2011, 31(4):429-434.HU A J, SUN J J, XIANG L. Modal aliasing in empirical modedecomposition[J]. Vibration Test and Diagnosis, 2011, 31(4):429-434.
[12]POH M Z, MCDUFF D J, PICARD R W. Advancements in noncontact,multiparameter physiological measurements using a webcam[J]. IEEETrans Biomed Eng, 2011, 58(1):7.
[13]POH M Z, MCDUFF D J, PICARD R W. Non-contact, automatedcardiac pulse measurements using video imaging and blind sourceseparation[J]. Opt Express, 2010, 18(10):10762-10774.
[14]杨竹青,李勇,胡德文.独立成分分析方法综述[J].自动化学报, 2002,28(5):762-772.YANG Z Q, LI Y, HU D W. Independent component analysis:a survey[J]. Acta Automatica Sinica, 2002, 28(5):762-772.
[15]詹银周,张兴安,郭春明,等. PICCO监测心率变异性及心输出量与Narcotrend麻醉深度监测对比研究[J].实用医学杂志, 2018, 34(5):791-799.ZHAN Y Z, ZHANG X A, GUO C M, et al. PICCO monitoring heartrate variability and cardiac output vs. narcotrend anesthetic depthmonitoring[J]. The Journal of Practical Medicine, 2018, 34(5):791-799.
[16]豆彩霞.基于视频的非接触式心率检测的研究[D].南京:南京理工大学, 2017.DOU C X. Non-contact heart rate detection based on video[D].Nanjing:Nanjing University of Science and Technology, 2017.
[17]赵飞帆,方路平,陈仕骁.基于人脸视频测量脉搏方法的初步研究[J].生物医学工程学杂志, 2012, 29(5):876-879.ZHAO F F, FANG L P, CHEN S X. A new method of measuring thepluse based on facial video[J]. Journal of Biomedical Engineering,2012, 29(5):876-879.
[18]陈映果.基于图像处理技术的非接触式心率检测算法研究[D].泉州:华侨大学, 2015.CHENG Y G. Research on no-contact measurement of heart rate basedon image processing[D]. Quanzhou:Huaqiao University, 2015.
[19]刘祎,欧阳健飞.基于人脸视频的非接触式心率测量方法[J].纳米技术与精密工程, 2016, 14(1):76-79.LIU Y, OUYANG J F. Non-contact method of heart rate measurementbased on facial video[J]. Nanotechnology and Precision Engineering,2016, 14(1):76-79.
[20]王楠,王霞,付晓静,等.视频中提取光电容积脉搏波的盲信号估计方法[J].电子设计工程, 2017, 25(3):176-180.WANG N, WANG X, FU X J, et al. Extracting photoplethysmographyfrom video based on blind signal estimation algorithm[J]. ElectronicDesign Engineering, 2017, 25(3):176-180.
[2] GIL E, ORINI M, BAILON R, et al. Photoplethysmography pulse ratevariability as a surrogate measurement of heart rate variability duringnon-stationary conditions[J]. Physiol Meas, 2010, 31(9):1271-1290.
[3]万铮结.基于人脸视频图像的心率检测研究[D].杭州:浙江工业大学, 2014.WAN Z J. Research of heart rate detection based on facial video[D].Hangzhou:Zhejiang University of Technology, 2014.
[4]赵素文,高凡,邓莉.小波变换结合快速傅里叶变换从PPG中提取呼吸率[J].中国医学物理学杂志, 2016, 33(1):39-43.ZHAO S W, GAO F, DENG L. Respiratory rate extracted fromphotoplethysmography signals by using wavelet transform and fastFourier transform[J]. Chinese Journal of Medical Physics, 2016, 33(1):39-43.
[5]李向东,乐建威,王新图.脉搏波信号分析方法的研究进展[J].数据采集与处理, 2009, 24(b10):29-33.LI X D, LE J W, WANG X T. Research progress in pulse wave signalanalysis methods[J]. Journal of Data Acquisition&Processing, 2009,24(b10):29-33.
[6]杨建.脉搏波信号采集与分析方法的研究[J].电脑与信息技术, 2014,22(3):53-55.YANG J. Research in pulse wave signal acquisition and analysismethods[J]. Computer and Information Technology, 2014, 22(3):53-55.
[7]祝宇虹,张富强,李满天,等.一种基于数学形态学的脉搏波信号预处理方法研究[J].北京生物医学工程, 2009, 28(2):122-125.ZHU Y H, ZHANG F Q, LI M T, et al. A new signal pre-processingmethod of pulse wave based on mathematical morphology theory[J].Beijing Biomedical Engineering, 2009, 28(2):122-125.
[8]马俊领,王成,李章俊,等.基于PPG的心率和呼吸频率的测量研究[J].光学技术, 2011, 37(3):309-312.MA J L, WANG C, LI Z J, et al. Study of measuring heart rate andrespiration rate based on PPG[J]. Optical Technique, 2011, 37(3):309-312.
[9]雷恒波,郭友达,莫镜清,等.基于人脸视频的光电容积脉搏波信号获取与处理[J].中国医学物理学杂志, 2016, 33(11):1178-1182.LEI H B, GUO Y D, MO J Q, et al. Photoplethysmography signalacquisition and processing based on facial video[J]. Chinese Journalof Medical Physics, 2016, 33(11):1178-1182.
[10]雷恒波,莫镜清,郭友达,等.基于手指视频的光电容积脉搏波信号获取[J].中国医疗设备, 2016, 31(11):42-45.LEI H B, MO J Q, GUO Y D, et al. Photoplethysmography signalacquisition based on finger video[J]. China Medical Equipment, 2016,31(11):42-45.
[11]胡爱军,孙敬敬,向玲.经验模态分解中的模态混叠问题[J].振动测试与诊断, 2011, 31(4):429-434.HU A J, SUN J J, XIANG L. Modal aliasing in empirical modedecomposition[J]. Vibration Test and Diagnosis, 2011, 31(4):429-434.
[12]POH M Z, MCDUFF D J, PICARD R W. Advancements in noncontact,multiparameter physiological measurements using a webcam[J]. IEEETrans Biomed Eng, 2011, 58(1):7.
[13]POH M Z, MCDUFF D J, PICARD R W. Non-contact, automatedcardiac pulse measurements using video imaging and blind sourceseparation[J]. Opt Express, 2010, 18(10):10762-10774.
[14]杨竹青,李勇,胡德文.独立成分分析方法综述[J].自动化学报, 2002,28(5):762-772.YANG Z Q, LI Y, HU D W. Independent component analysis:a survey[J]. Acta Automatica Sinica, 2002, 28(5):762-772.
[15]詹银周,张兴安,郭春明,等. PICCO监测心率变异性及心输出量与Narcotrend麻醉深度监测对比研究[J].实用医学杂志, 2018, 34(5):791-799.ZHAN Y Z, ZHANG X A, GUO C M, et al. PICCO monitoring heartrate variability and cardiac output vs. narcotrend anesthetic depthmonitoring[J]. The Journal of Practical Medicine, 2018, 34(5):791-799.
[16]豆彩霞.基于视频的非接触式心率检测的研究[D].南京:南京理工大学, 2017.DOU C X. Non-contact heart rate detection based on video[D].Nanjing:Nanjing University of Science and Technology, 2017.
[17]赵飞帆,方路平,陈仕骁.基于人脸视频测量脉搏方法的初步研究[J].生物医学工程学杂志, 2012, 29(5):876-879.ZHAO F F, FANG L P, CHEN S X. A new method of measuring thepluse based on facial video[J]. Journal of Biomedical Engineering,2012, 29(5):876-879.
[18]陈映果.基于图像处理技术的非接触式心率检测算法研究[D].泉州:华侨大学, 2015.CHENG Y G. Research on no-contact measurement of heart rate basedon image processing[D]. Quanzhou:Huaqiao University, 2015.
[19]刘祎,欧阳健飞.基于人脸视频的非接触式心率测量方法[J].纳米技术与精密工程, 2016, 14(1):76-79.LIU Y, OUYANG J F. Non-contact method of heart rate measurementbased on facial video[J]. Nanotechnology and Precision Engineering,2016, 14(1):76-79.
[20]王楠,王霞,付晓静,等.视频中提取光电容积脉搏波的盲信号估计方法[J].电子设计工程, 2017, 25(3):176-180.WANG N, WANG X, FU X J, et al. Extracting photoplethysmographyfrom video based on blind signal estimation algorithm[J]. ElectronicDesign Engineering, 2017, 25(3):176-180.