Extracting heart rate from visible spectrum video based on diagonal cumulant algorithm

WANG Meng-jun; WANG Nan; WANG Xia; FU Xiao-jing; LI Gang

doi:10.3788/OPE.20152309.2698

您当前的位置：

首页 >

文章列表页 >

Extracting heart rate from visible spectrum video based on diagonal cumulant algorithm

更新时间：2020-08-12

- Extracting heart rate from visible spectrum video based on diagonal cumulant algorithm
- Optics and Precision Engineering Vol. 23, Issue 9, Pages: 2698-2707(2015)
- 作者机构：
  
  1. 河北工业大学电子信息工程学院天津,300401
  2. 天津大学精密仪器与光电子工程学院天津,300072
- 作者简介：
- 基金信息：
- DOI：10.3788/OPE.20152309.2698
  CLC： R540.4;TP391.41
- Received：10 April 2015，
  
  Revised：09 June 2015，
  
  Published：25 September 2015
- 稿件说明：
移动端阅览
王蒙军, 王楠, 王霞等. 由可见光谱视频中提取心率的对角累积量法[J]. 光学精密工程, 2015,23(9): 2698-2707

WANG Meng-jun, WANG Nan, WANG Xia etc. Extracting heart rate from visible spectrum video based on diagonal cumulant algorithm[J]. Editorial Office of Optics and Precision Engineering, 2015,23(9): 2698-2707
王蒙军, 王楠, 王霞等. 由可见光谱视频中提取心率的对角累积量法[J]. 光学精密工程, 2015,23(9): 2698-2707 DOI： 10.3788/OPE.20152309.2698.

WANG Meng-jun, WANG Nan, WANG Xia etc. Extracting heart rate from visible spectrum video based on diagonal cumulant algorithm[J]. Editorial Office of Optics and Precision Engineering, 2015,23(9): 2698-2707 DOI： 10.3788/OPE.20152309.2698.

摘要

由于使用经典的联合近似特征对角化(JADE)算法从视频中估计光电容积脉搏波(Photoplethysmography

PPG)信号

再经快速傅里叶变换转化成的心率值与真实心率值的误差较大

本文提出使用基于对角累积量算法从视频中分离PPG信号

再经过快速傅里叶变换转换成心率的方法来提高心率测量的准确性。进行了从RGB彩色可见光视频信号中恢复心率值的实验。对比实验表明

基于对角累积量分离算法所得心率值与真实心率值差的绝对值的统计特征参数较JADE算法均有所降低

均值、标准差、均方根误差平均分别下降1.46

4.98和4.49。通过Bland-Altman图的分析表明

在95%的置信区间内

对角累积量算法所得心率的浮动范围较JADE算法减小了2倍以上

显示对角累积量算法具有更高的估计精度

对肤色亮度和外界自然光的要求更低

通过调整参数值

可使运行时间控制在1 s之内

基本满足实时提取心率的要求。

Abstract

Photoplethysmography(PPG) signal is usually acquired from a video image by using the classic Joint Approximate Diagonalization of Eigenmatrices(JADE) algorithm

and the heart rate is extracted from PPG signal using Fast Fourier Transform. However

the obtained value has larger deviation with the actual heart rate value. To improve the accuracy of measured results

a new blind source separation algorithm was proposed. The algorithm used diagonal cumulant to separate the PPG signal

and took the Fast Fourier Transform to extract the heart rate. Experiments were carried out by utilizing visible spectrum color video. Compared with the JADE algorithm

the results show that statistical parameter values of the absolute difference between heart rate values extracted from the diagonal cumulant algorithm and the actual heart rate values are decreased. The mean value

standard deviation

and root-mean-square deviation has reduced by 1.46

4.98 and 4.49

respectively. By analytical form of the Bland-Altman graph

the floating range of diagonal cumulant algorithm reduces more than twice as compared with the JADE method in a 95% confidence interval. It suggests that diagonal cumulant algorithm provides higher estimated accuracy

and relies less on intensity of skin and natural light. The calculation time can also be controlled less than 1 s after dramatically reducing the iterations by adjusting the parameter values in diagonal cumulant algorithm

which meets the demand of real-time electrocardiogram signal extraction.

关键词

Keywords

references

PAVLIDIS I, DOWDALL J, SUN N, et al.. Interacting with human physiology [J]. Computer Vision and Image Understanding, 2007, 108(1-2):150-170.

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.

de H G, JEANNE V. Robust pulse-rate from chrominance-based rPPG [J]. IEEE Transactions on Biomedical Engineering, 2013, 60(10):2878-2886.

Poh M Z, MCDUFF D J, PICARD R W. Advancements in noncontact, multi-parameter physiological measurements using a webcam [J]. IEEE Transactions on Biomedical Engineering, 2011, 58(1):7-11.

KWON S J, HYUNSEOK K, PARK K S. Validation of heart rate extraction using video imaging on a built-in camera system of a smartphone [C]. Proceedings of IEEE Engineering in Medicine and Biology Society, 2012:2174-2177.

BOUSEFSAF F, MAAOUI C, PRUSKI A. Continuous wavelet filtering on webcam photoplethysmographic signals to remotely assess the instantaneous heart rate [J]. Biomedical Signal Processing and Control, 2013, 8(6):568-574.

DATCU D, CIDOTA M, LUKOSCH S, et.al.. Noncontact automatic heart rate analysis in visible spectrum by specific face regions [C]. Proceedings of the 14th ACM International Conference on Computer Systems and Technologies, 2013:120-127.

PENG F L, ZHANG Z B, GOU X M, et al.. Motion artifact removal from photoplethysmographic signals by combining temporally constrained independent component analysis and adaptive filter [J]. Biomedical Engineering Online, 2014, 13(6):694-694.

TARASSENKO L, VILLARROEL M, GUAZZI A, et al.. Non-contact video-based vital sign monitoring using ambient light and auto-regressive models [J]. Physiological Measurement, 2014, 35(5):807-831.

MONKARESI H, CALVO R A, YAN H. A machine learning approach to improve contactless heart rate monitoring using a webcam [J]. IEEE Journal of Biomedical and Health Informatics, 2014, 18(4):1153-1160.

MCDUFF D, GONTAREK S, PICARD R W. Improvements in remote cardiopulmonary measurement using a five band digital camera [J]. IEEE Transactions on Biomedical Engineering, 2014, 61(10):2593-2601.

SWEENEY K T, WARD T E, MCLOONE S F. Artifact removal in physiological signals-practices and possibilities [J]. IEEE Transactions on Information Technology in Biomedicine, 2012, 16(3):488-500.

KUZILEK J, KREMEN V, LHOTSKA L. Comparison of JADE and canonical correlation analysis for ECG denoising [C]. Proceedings of the 36th Engineering in Medicine and Biology Society Annual International Conference, 2014:3857-3860.

YU J W. FENG Q Y. A blind separation algorithm based on WVD and JADE for speech signal [C]. Proceedings of 4th International Conference on Image and Signal Processing, 2011:6-9.

杨利平, 辜小花. 用于人脸识别的相对梯度直方图特征描述[J]. 光学精密工程, 2014, 22(1):152-159. YANG L P, GU X H. Relative gradient histogram features for face recognition [J]. Opt. Precision Eng., 2014, 22(1):152-159. (in Chinese)

刘琚, 孙建德, 许宏吉. 盲信号处理理论与应用[M]. 北京:科学出版社, 2013. LIU J, SUN J D, XU H J. Theory and Application of Blind Signal Processing [M]. Beijing:Science Press, 2013 (in Chinese)

李海森, 张艳宁, 姚睿,等. 基于主成分分析的直线运动模糊参数估计[J]. 光学精密工程, 2013, 21(10):2656-2662. LI H S, ZHANG Y N, YAO R, et al.. Parameter estimation of linear motion blur based on principal component analysis [J]. Opt. Precision Eng., 2013, 21(10):2656-2662. (in Chinese)

BLAND J M, ALTMAN D G. Statistical methods for assessing agreement between two methods of clinical measurement [J]. International Journal of Nursing Studies, 2010, 47(8):931-936.

Views

463

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Extraction of heart rate parameters from video of human face

Non-contact respiratory rate and heart rate signal acquisition system

Related Author

Xiao-yuan LI

Peng WU

Yun LIU

Hong-yu SI

Zhen-long WANG

Jian GUO

Yu-hang CHEN

Li-rong WANG

Related Institution

School of Mechatronics Engineering and Automation, Shanghai University

Suzhou Institute of Biomedical Engineering and Technology, Chinese Academy of Sciences, Soochow

School of Electronic and Information Engineering, Soochow University, Soochow

AI问答

Address：No.3888 Dong Nanhu Road, Changchun, Jilin, China Postal code：130033
Tel：0431-86176855 Email：gxjmgc@ciomp.ac.cn
Technical support is provided by Beijing Founder electronics co., LTD 吉ICP备11002662号-17 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰