计算机科学 ›› 2022, Vol. 49 ›› Issue (11A): 211000182-6.doi: 10.11896/jsjkx.211000182

• 图像处理&多媒体技术 • 上一篇    下一篇

基于面部视频的非接触式心率检测方法研究

曾梓琳1, 胡志刚1,3, 尚鹏2, 王新征1, 付东辽1   

  1. 1 河南科技大学医学技术与工程学院 河南 洛阳 471023
    2 中国科学院深圳先进技术研究院 广东 深圳 518055
    3 河南省智能康复医疗机器人工程研究中心 河南 洛阳 471023
  • 出版日期:2022-11-10 发布日期:2022-11-21
  • 通讯作者: 胡志刚(hu.robert@126.com)
  • 作者简介:(704898787@qq.com)
  • 基金资助:
    河南省科技攻关计划(182102410046);深圳市科技项目计划(JCYJ20180507182446643)

Non-contact Heart Rate Detection Based on Facial Video

ZENG Zi-lin1, HU Zhi-gang1,3, SHANG Peng2, WANG Xin-zheng1, FU Dong-liao1   

  1. 1 School of Medical Technology and Engineering,Henan University of Science and Technology,Luoyang,Henan 471023,China
    2 Shenzhen Institutes of Advanced Technology,Chinese Academy of Sciences,Shenzhen,Guangdong 518055,China
    3 Henan Engineering Research Center of Intelligent Rehabilitation Robot,Luoyang,Henan 471023,China
  • Online:2022-11-10 Published:2022-11-21
  • About author:ZENG Zi-lin,born in 1998,postgra-duate.Her main research interests include medical image processing and rehabilitation robot.
    HU Zhi-gang,born in 1972,Ph.D,professor,Ph.D supervisor.His main research interests include three-dimensional reconstruction and computational biomechanics,biomedical robots.
  • Supported by:
    Key Science and Technology Program of Hennan Province,China(182102410046) and Shenzhen Science and Technology Project(JCYJ20180507182446643).

摘要: 基于视频的非接触式面部心率检测易受到环境光和运动伪迹的干扰,检测心率结果的准确度低。针对上述问题,提出了一种集合经典模态分解(Ensemble Empirical Mode Decomposition,EEMD)和标准欧几里得距离相结合的自适应阈值化去噪方法,降低了外界干扰,提高了准确度。首先从视频录制的RGB图像模型中选取绿色(G)通道像素均值作为PPG(Photo Plethysmo Graphy)信号,然后用滤波器对信号进行预处理,消除心率范围外的信号;然后将EEMD与标准欧几里得距离相结合,对固有模态函数进行阈值化处理并重构;最后用傅里叶变换进行功率谱分析来计算心率值。实验结果表明,与基于小波变换和基于自适应集合经典模态分解的方法相比,所提方法在非接触式面部心率检测去噪中有更好的稳定性和准确性,提高了心率检测的鲁棒性,适用于日常非接触式实时心率监测。

关键词: 心率检测, EEMD, 欧氏距离, 阈值, 非接触式

Abstract: Non-contact facial heart rate detection based on video is susceptible to interference from ambient light and motion artifacts,and the accuracy of heart rate detection results is low.To address the above problems,this paper proposes an adaptive thresholding denoising method which combines ensemble empirical mode decomposition(EEMD) and standardized Euclidean distance to reduce external interference and improve accuracy.Firstly,the green channel pixel mean is selected as PPG signal from RGB image model recorded by camera,and then the signal is preprocessed with a filter to eliminate the signals outside the heart rate range.Secondly,the EEMD is combined with standardized Euclidean distance to threshold and reconstruct the intrinsic modal function.Finally,power spectrum analysis with Fourier transform is performed to calculate the heart rate.Experiments show that,compared with the methods based on wavelet transform and empirical mode decomposition with adaptive,this method has better stability and accuracy in denoising of non-contact facial heart rate detection,improves the robustness of heart rate detection,which is suitable for daily non-contact real-time heart rate monitoring.

Key words: Heart rate measurement, EEMD, Euclidean distance, Threshold, Non-contact

中图分类号: 

  • TP391
[1]POH M Z,MCDUFF D J,PICARD R W,et al.Non-contact,automated cardiac pulse measurements using video imaging and blind source separation[J].Optics Express,2010,18(10):10762-10774.
[2]POH M Z,MCDUFF D J,PICARD R W.Advancements in noncontact,multiparameter physiological measurements using a webcam[J].IEEE Transactions on Biomedical Engineering,2010,58(1):7-11.
[3]WANG Y D,LI F H.Non-Contact Heart Rate Detection ofMulti-Feature Area Fast ICA[J].Computer Systems & Applications,2021,30(1):154-161.
[4]CHEN H,ZHENG X J,NI Z J.Vital Signs Detection Based on Facial Video Analysis[J].Journal of Beijing University of Aeronautics and Astronautics,2020,46(9):1770-1777.
[5]CUMO S,DE G,FARINA R,et al.A novel on numerical scheme for ECG signal denoising[J].Procedia Computer Science,2015,51(1):775-784.
[6]MOEIN S.An MLP neural network for ECG noise removalbased on Kalman filter[J].Oxygen Transport to Tissue XXXIII,2010,680(680):109-116.
[7]SMITAL L,VITEK M,KOZUMPLIK J,et al.Adaptive wavelet wiener filtering of ECG signals[J].IEEE Transactions on Biomedical Engineering,2013,60(2):437-445.
[8]HUANG N E,SHEN Z,LONG S R,et al.The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis[J].Proceedings Mathematical Physical & Engineering Sciences,1998,454(1971):903-995.
[9]NGUYEN P,KIM J M.Adaptive ECG denoising using genetic algorithm-based thresholding and ensemble empirical mode decomposition[J].Information Sciences,2016,373(C):499-511.
[10]MOHGUEN W,BEKKA R E.EMD-Based Denoising by Customized Thresholding[C]//International Conference on Control,2017:19-23.
[11]LING L Y,WANG Q Q,ZHOU M R.Non-Contact Measurement of Heart Rate Based on CEEMDAN-FastICA[J].Journal of Anhui University of Science and Technology(Natural Science Edition),2021,41(2):1-8.
[12]WU T,BLAZEK V,SCHMITT H J.Photoplethysmography Imaging:A New Noninvasive and Noncontact Method for Mapping of the Dermal Perfusion Changes[C]//European Confe-rence on Biomedical Optics.2000.
[13]BOUDRAA A O,CEXUS J C,SAIDI Z.EMD-based signal noise reduction[J].International Journal of Signal Processing,2004,1(1):33-37.
[14]TANG J T,ZOU Q,YAN T,et al.Hilbert-Huang Transform for ECG De-Noising[C]//International Conference on Bioinformatics & Biomedical Engineering.2007.
[15]LIU Y,OUYANG J F,YAN Y G.Method of Measuring Heart Rate Using A Webcam[J].Computer Engineering and Applications,2016,52(7):210-214.
[16]QI G,YANG X Z,WU X.Heart Rate Detection for Non-coope-rative Shaking Face[J].Journal of Image and Graphics,2017,22(1):126-136.
[17]SANG H F,JIN Z Y.Face Local Heart Rate Detection Based on Illumination Correction [J].Journal of Computer Applications,2018,38(S2):301-305.
[18]LI C X,ZHONG Q H,LIAO J X.Heart Rate Measurementfrom Face Video Based on ICEEMD[J].Laser Journal,2019,40(1):33-36.
[19]SU P Q,XU L,LIANG Y J.Non-Contact Heart Rate Measurement Method Based on Eulerian Video Magnification[J].Journal of Computer Applications,2018,38(3):916-922.
[20]WU Z,HUANG N E.Ensemble empirical mode decomposition:a noise-assisted data analysis method [J].Advances in Adaptive Data Analysis,2011,1(1):1-41.
[21]CENNINI G,ARGUEL J,AKIT K,et al.Heart rate monitoring via remote photoplethysmography with motion artifacts reduction[J].Optics Express,2010,18(5):4867-4875.
[22]SHIMAZAKI T,HARA S,OKUHATA H,et al.Cancellation of motion artifact induced by exercise for PPG-based heart rate sensing[C]//2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.IEEE,2014:3216-3219.
[23]FLANDTIN P,GONCALVES P,RILLING G.EMD equivalent filter banks,from interpretation to applications[M].Hilbert-Huang Transformand Its Applications,2011.
[24]TERRIENE J,MARQUE C,KARLSSON B.Automatic detec-tion of mode mixing in empirical mode decomposition using non-stationarity detection:application to selecting IMFs of interest and denoising[J].EURASIP Journal on Advances in Signal Processing,2011,2011(1):1-8.
[25]XU Z J,GAO G Q,FANG Z M.Non-Contact Infant Heart Rate Monitoring Based on Facial Images[J].Software Guide,2019,18(10):12-18.
[26]HUANG B H,CHEN R,ZENG H S,et al.The impact of blood content in skin tissue on skin spectra[J].Guang pu xue yu Guang pu fen xi= Guang pu,2007,27(1): 95-98.
[1] 杨文坤, 原晓佩, 陈小锋, 郭睿.
三维激光雷达点云空间多特征分割
Spatial Multi-feature Segmentation of 3D Lidar Point Cloud
计算机科学, 2022, 49(8): 143-149. https://doi.org/10.11896/jsjkx.210300275
[2] 张翕然, 刘万平, 龙华.
物联网僵尸网络病毒的传播动力学模型与分析
Dynamic Model and Analysis of Spreading of Botnet Viruses over Internet of Things
计算机科学, 2022, 49(6A): 738-743. https://doi.org/10.11896/jsjkx.210300212
[3] 徐汝利, 黄樟灿, 谢秦秦, 李华峰, 湛航.
基于金字塔演化策略的彩色图像多阈值分割
Multi-threshold Segmentation for Color Image Based on Pyramid Evolution Strategy
计算机科学, 2022, 49(6): 231-237. https://doi.org/10.11896/jsjkx.210300096
[4] 周俊, 王帅, 刘凡漪.
基于小波包分析的虹膜识别研究
Research on Iris Recognition Algorithm Based on Wavelet Packet Decomposition
计算机科学, 2021, 48(6A): 57-62. https://doi.org/10.11896/jsjkx.200900218
[5] 张蔷, 黄樟灿, 谈庆, 李华峰, 湛航.
基于动态近邻套索算子的金字塔演化策略
Pyramid Evolution Strategy Based on Dynamic Neighbor Lasso
计算机科学, 2021, 48(6): 215-221. https://doi.org/10.11896/jsjkx.200400115
[6] 刘峰, 王一帆, 杨杰, 周爱民, 齐佳音.
一种基于区块链的融合DKG与BLS的高阈值签名协议
Blockchain-based High-threshold Signature Protocol Integrating DKG and BLS
计算机科学, 2021, 48(11): 46-53. https://doi.org/10.11896/jsjkx.210200129
[7] 王静宇, 刘思睿.
大数据风险访问控制研究进展
Research Progress on Risk Access Control
计算机科学, 2020, 47(7): 56-65. https://doi.org/10.11896/jsjkx.190700157
[8] 彭浩, 和丽芳.
基于改进树种算法的彩色图像多阈值分割
Multi-threshold Segmentation for Color Image Based on Improved Tree-seed Algorithm
计算机科学, 2020, 47(6A): 220-225. https://doi.org/10.11896/JsJkx.191000180
[9] 丁子昂, 乐曹伟, 吴玲玲, 付明磊.
基于CEEMD-Pearson和深度LSTM混合模型的PM2.5浓度预测方法
PM2.5 Concentration Prediction Method Based on CEEMD-Pearson and Deep LSTM Hybrid Model
计算机科学, 2020, 47(6A): 444-449. https://doi.org/10.11896/JsJkx.190700158
[10] 曹义亲, 段也钰, 武丹.
基于WFSOA的2D-Otsu钢轨缺陷图像分割方法
2D-Otsu Rail Defect Image Segmentation Method Based on WFSOA
计算机科学, 2020, 47(5): 154-160. https://doi.org/10.11896/jsjkx.190200295
[11] 程煜, 刘伟, 孙童心, 魏志刚, 杜薇.
近阈值电压下可容错的一级缓存结构设计
Design of Fault-tolerant L1 Cache Architecture at Near-threshold Voltage
计算机科学, 2020, 47(4): 42-49. https://doi.org/10.11896/jsjkx.190300088
[12] 刘云,尹传环,胡迪,赵田,梁宇.
基于循环神经网络的通信卫星故障检测
Communication Satellite Fault Detection Based on Recurrent Neural Network
计算机科学, 2020, 47(2): 227-232. https://doi.org/10.11896/jsjkx.190600147
[13] 王淑云, 干宗良, 刘峰.
基于层级聚类回归模型的人脸超分辨率重建算法
Face Hallucination Reconstruction Algorithm Based on Hierarchical Clustering Regression Model
计算机科学, 2019, 46(8): 298-302. https://doi.org/10.11896/j.issn.1002-137X.2019.08.049
[14] 孙伟, 赵玉普.
增强旋转不变LBP算法及其在图像检索中的应用
Enhanced Rotation Invariant LBP Algorithm and Its Application in Image Retrieval
计算机科学, 2019, 46(7): 263-267. https://doi.org/10.11896/j.issn.1002-137X.2019.07.040
[15] 宋鑫,朱宗良,高银萍,苌道方.
动态阈值结合全局优化的船舶AIS轨迹在线压缩算法
Vessel AIS Trajectory Online Compression Algorithm Combining Dynamic Thresholding and Global Optimization
计算机科学, 2019, 46(7): 333-338. https://doi.org/10.11896/j.issn.1002-137X.2019.07.051
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!