留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

基于面部视频分析的生命体征检测

陈辉 郑秀娟 倪宗军 张昀 杨晓梅

陈辉, 郑秀娟, 倪宗军, 等 . 基于面部视频分析的生命体征检测[J]. 北京航空航天大学学报, 2020, 46(9): 1770-1777. doi: 10.13700/j.bh.1001-5965.2020.0065
引用本文: 陈辉, 郑秀娟, 倪宗军, 等 . 基于面部视频分析的生命体征检测[J]. 北京航空航天大学学报, 2020, 46(9): 1770-1777. doi: 10.13700/j.bh.1001-5965.2020.0065
CHEN Hui, ZHENG Xiujuan, NI Zongjun, et al. Vital signs detection via facial video analysis[J]. Journal of Beijing University of Aeronautics and Astronautics, 2020, 46(9): 1770-1777. doi: 10.13700/j.bh.1001-5965.2020.0065(in Chinese)
Citation: CHEN Hui, ZHENG Xiujuan, NI Zongjun, et al. Vital signs detection via facial video analysis[J]. Journal of Beijing University of Aeronautics and Astronautics, 2020, 46(9): 1770-1777. doi: 10.13700/j.bh.1001-5965.2020.0065(in Chinese)

基于面部视频分析的生命体征检测

doi: 10.13700/j.bh.1001-5965.2020.0065
基金项目: 

成都市重点研发支撑计划技术创新研发项目 2020-YF05-00056-SN

详细信息
    作者简介:

    陈辉   男, 硕士研究生。主要研究方向:信号处理、机器学习

    郑秀娟   女, 博士, 副教授, 硕士生导师。主要研究方向:信号信息处理、智能检测技术、自然人机交互

    倪宗军   男, 硕士研究生。主要研究方向:图像处理、机器学习

    张昀   女, 博士, 副研究员。主要研究方向:多模态数据分析

    杨晓梅   女, 博士, 副教授。主要研究方向:图像重建、计算机视觉

    通讯作者:

    郑秀娟, E-mail:xiujuanzheng@scu.edu.cn

  • 中图分类号: V221+.3;TB553

Vital signs detection via facial video analysis

Funds: 

Chengdu Key R & D Support Plan Technology Innovation R & D Project 2020-YF05-00056-SN

More Information
  • 摘要:

    在面部视频中提取生命体征相关的生理信号时易受环境光和受试者头部运动的影响,为了降低外界干扰并提高生命体征检测的准确度,提出了一种联合集合经验模态分解(EEMD)算法与信号质量检测的面部视频分析方法,用于精确检测人体的心率与呼吸频率等生命体征。通过公开数据集进行实验验证,实验结果表明,所提方法相较于目前已有的常用信号处理方法能够得到更精确的心率与呼吸频率的估计值,所得估计值与标准值的相关系数分别高于0.9和0.8。同时,所提方法将为实时活体人脸识别提供一种思路,也有助于丰富监控视频智能分析的应用研究。

     

  • 图 1  本文方法流程

    Figure 1.  Flowchart of proposed method

    图 2  面部ROI选择

    Figure 2.  Facial ROI selection

    图 3  用EEMD-PCA技术从BVP信号中提取心率和呼吸频率的主成分的步骤

    Figure 3.  Steps of using EEMD-PCA technique to extract principal component signal of heart rate and respiratory rate from BVP signals

    图 4  原始主成分信号及对应的方差特征序列表示

    Figure 4.  Original principal component signals and corresponding variance characterization series representation

    图 5  频谱跟踪算法流程图

    Figure 5.  Flowchart of spectrum tracking algorithm

    表  1  不同方法的心率比较

    Table  1.   Comparison of heart rate among different methods

    方法 MAE/bpm MEP/% P相关系数
    ICA[24] 9.866 11.966 0.733
    AR[25] 5.334 6.755 0.751
    CEEMD[15] 3.804 4.881 0.860
    FastICA[16] 4.541 5.881 0.821
    本文方法 2.928 4.161 0.902
    下载: 导出CSV

    表  2  不同方法的呼吸频率比较

    Table  2.   Comparison of respiratory rate among different methods

    方法 MAE/bpm MEP/% P相关系数
    ICA[24] 7.300 16.292 0.556
    AR[25] 6.718 14.294 0.612
    CEEMD[15] 3.804 9.878 0.753
    FastICA[16] 4.541 15.726 0.623
    本文方法 3.085 7.769 0.829
    下载: 导出CSV
  • [1] 杨哲.基于视频监控的人群异常行为检测[D].秦皇岛: 燕山大学, 2019. http://cdmd.cnki.com.cn/Article/CDMD-10216-1019921057.htm

    YANG Z.Detection of crowd abnormal behavior based on video surveillance[D].Qinhuangdao: Yanshan University, 2019(in Chinese). http://cdmd.cnki.com.cn/Article/CDMD-10216-1019921057.htm
    [2] BLEDSOE W.The model method in facial recognition: Technical report: PRI-15[R].Palo Alto: Panoramic Research, Inc., 1964.
    [3] HE J, CAI J F, FANG L Z, et al.A method of facial expression recognition based on LBP fusion of key expressions areas[C]//The 27th Chinese Control and Decision Conference.Piscataway: IEEE Press, 2015: 4200-4204.
    [4] AHONEN T, HADID A, PIETIKÄINEN M.Face recognition with local binary patterns[C]//European Conference on Computer Vision.Berlin: Springer, 2004: 469-481.
    [5] LENC L, KRÁL P.Local binary pattern based face recognition with automatically detected fiducial points[J].Integrated Computer-Aided Engineering, 2016, 23(2):129-139. doi: 10.3233/ICA-150506
    [6] KRANJEC J, BEGUŠ S, GERŠAK G, et al.Non-contact heart rate and heart rate variability measurements:A review[J].Biomedical Signal Processing and Control, 2014, 13:102-112. doi: 10.1016/j.bspc.2014.03.004
    [7] SUN Y, THAKOR N.Photoplethysmography revisited:From contact to noncontact, from point to imaging[J].IEEE Transactions on Bio-Medical Engineering, 2016, 63(3):463-477. doi: 10.1109/TBME.2015.2476337
    [8] WU T, BLAZEK V, SCHMITT H J.Photoplethysmography imaging: A new noninvasive and noncontact method for mapping of the dermal perfusion changes[C]//Optical Techniques and Instrumentation for the Measurement of Blood Composition, Structure, and Dynamics.Bellingham: International Society for Optics and Photonics, 2000, 4163: 62-70. https://www.researchgate.net/publication/253321950_Photoplethysmography_imaging_a_new_noninvasive_and_noncontact_method_for_mapping_of_the_dermal_perfusion_changes
    [9] LI X B, CHEN J, ZHAO G Y, et al.Remote heart rate measurement from face videos under realistic situations[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Piscataway: IEEE Press, 2014: 4264-4271. https://www.researchgate.net/publication/286594471_Remote_Heart_Rate_Measurement_from_Face_Videos_under_Realistic_Situations
    [10] BEATSON A, GREEN R.Calculating a vagal tone index using webcam photoplethysmography[C]//Proceedings of the 29th International Conference on Image and Vision Computing.New York: ACM, 2014: 242-246. doi: 10.1145/2683405.2683446
    [11] CHENG J, CHEN X, XU L X, et al.Illumination variation-resistant video-based heart rate measurement using joint blind source separation and ensemble empirical mode decomposition[J].IEEE Journal of Biomedical and Health Informatics, 2017, 21(3):1422-1433. http://ieeexplore.ieee.org/document/7585027
    [12] 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. doi: 10.1364/OE.18.010762
    [13] 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. http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=zgyxwlxzz201611019

    LEI H B, GUO Y D, MO J Q, et al.Acquisition and processing of photoelectric volume pulse wave signal based on face video[J].Chinese Journal of Medical Physics, 2016, 33(11):1178-1182(in Chinese). http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=zgyxwlxzz201611019
    [14] WU Z, HUANG N E.Ensemble empirical mode decomposition:A noise-assisted data analysis method[J].Advances in Adaptive Data Analysis, 2009, 1(1):1-41.
    [15] ZHAO J, HUANG J F, JIA G Q, et al.Non-contact method of heart rate using a webcam[C]//IEEE International Conference on Internet of Things and IEEE Green Computing and Communications and IEEE Cyber, Physical and Social Computing and IEEE Smart Data.Piscataway: IEEE Press, 2018: 1902-1906. https://www.researchgate.net/publication/333595344_Non-Contact_Method_of_Heart_Rate_Using_a_Webcam
    [16] FAVILLA R, ZUCCALÀ V C, COPPINI G.Heart rate and heart rate variability from single-channel video and ICA integration of multiple signals[J].IEEE Journal of Biomedical and Health Informatics, 2019, 23(6):2398-2408. doi: 10.1109/JBHI.2018.2880097
    [17] LEI Y G, HE Z J, ZI Y Y.Application of the EEMD method to rotor fault diagnosis of rotating machinery[J].Mechanical Systems and Signal Processing, 2009, 23(4):1327-1338. doi: 10.1016/j.ymssp.2008.11.005
    [18] ZHANG K P, ZHANG Z P, LI Z F, et al.Joint face detection and alignment using multitask cascaded convolutional networks[J].IEEE Signal Processing Letters, 2016, 23(10):1499-1503. doi: 10.1109/LSP.2016.2603342
    [19] NEUBECK A, VAN GOOL L.Efficient non-maximum suppression[C]//18th International Conference on Pattern Recognition.Piscataway: IEEE Press, 2006, 3: 850-855. https://www.researchgate.net/publication/220929789_Efficient_Non-Maximum_Suppression
    [20] KING D E.Dlib-ml:A machine learning toolkit[J].Journal of Machine Learning Research, 2009, 10:1755-1758. http://cn.bing.com/academic/profile?id=763e0724818935e117719c1aedaec5fa&encoded=0&v=paper_preview&mkt=zh-cn
    [21] DE H G, JEANNE V.Robust pulse rate from chrominance-based rPPG[J].IEEE Transactions on Biomedical Engineering, 2013, 60(10):2878-2886. doi: 10.1109/TBME.2013.2266196
    [22] PANG B, LIU M, ZHANG X, et al.Advanced EMD method using variance characterization for PPG with motion artifact[C]//IEEE Biomedical Circuits and Systems Conference.Piscataway: IEEE Press, 2016: 196-199.
    [23] KOELSTRA S, MUHL C, SOLEYMANI M, et al.Deap:A database for emotion analysis using physiological signals[J].IEEE Transactions on Affective Computing, 2011, 3(1):18-31. http://dl.acm.org/citation.cfm?id=2197060
    [24] POH M Z, MCDUFF D J, PICARD R W.Advancements in noncontact, multiparameter physiological measurements using a webcam[J].IEEE Transactions on Bio-Medical Engineering, 2011, 58(1):7-11. doi: 10.1109/TBME.2010.2086456
    [25] 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. doi: 10.1088/0967-3334/35/5/807
  • 加载中
图(5) / 表(2)
计量
  • 文章访问数:  873
  • HTML全文浏览量:  148
  • PDF下载量:  174
  • 被引次数: 0
出版历程
  • 收稿日期:  2020-03-02
  • 录用日期:  2020-04-18
  • 网络出版日期:  2020-09-20

目录

    /

    返回文章
    返回
    常见问答