基于自寻优归一化最小均方误差算法的非接触式心率测量方法研究  

Research on Non-Contact Heart Rate Measurement Method Based on Self-Optimizing Normalized Least Mean Square Algorithm

作　　者：吴芬 彭力[1,2] 韩鹏[1,2] 骆开庆[1,2] 刘冬梅[1,2] 邱健[1,2] Wu Fen;Peng Li;Han Peng;Luo Kaiqing;Liu Dongmei;Qiu Jian(Guangdong Provincial Engineering Technology Research Center for Optoelectronic Instrument,School of Physics and Telecommunication Engineering,South China Normal University,Guangzhou,Guangdong 510006,China;Qingyuan Institute of Science and Technology Innovation,South China Normal University,Qingyuan,Guangdong 511517,China)

机构地区：[1]华南师范大学物理与电信工程学院广东省光电检测仪器工程研究中心,广东广州510006 [2]华南师范大学(清远)科技创新研究院,广东清远511517

出　　处：《激光与光电子学进展》2021年第20期303-310,共8页Laser & Optoelectronics Progress

基　　金：国家自然科学基金(61975058);广东省自然科学基金(2019A1515011401);广州市科技计划项目(201707010485,201704020137);华南师大物电学院蓝盾信息安全技术联合实验室课题项目(LD20170208)。

摘　　要：基于成像式光电容积脉搏波的非接触式心率测量方法受到环境光干扰会严重影响心率信号的辨别与提取,为了解决这个难点,提出了一种基于自寻优归一化最小均方误差算法的心率信号降噪方法。该方法可根据原始心率信号和背景信号中光线变化的趋势,在归一化最小均方自适应滤波器的基础上,通过最小均方误差自动地调整最优控制因子,最大化地去除拾取的图像中的光照干扰。通过与指夹式脉搏血氧仪实际测得的心率结果对比,在光强剧烈变化的条件下,两种方法测量得到的心率平均值的Pearson相关系数为0.95,平均绝对百分比误差为2.16%。本文方法极大地提高了成像式光电容积脉搏波对环境光的抗噪能力,大大提升了成像式光电容积脉搏波测量方法的实用性、可靠性和稳定性。The non-contact heart rate measurement method based on imaging photoplethysmography is affected by the interference of ambient light,which will seriously affect the identification and extraction of heart rate signals.In order to solve this problem,this paper proposes a denoising method of heart rate signal based on a self-optimizing normalized least mean square algorithm.According to the trend of light changes in the original heart rate signal and the background signal,this method can automatically select the control factor through the least mean square error based on the normalized least mean square adaptive filter,which can maximize the removal of light interference in the image.Compared with the actual heart rate results using finger clip pulse oximeter,the Person correlation coefficient between the average heart rate measured by the two methods under the condition of drastic changes in light intensity is 0.95,and the mean absolute percentage error is 2.16%.The results indicate that the method greatly improves the anti-noise ability of the imaging photoplethysmographic against ambient light,which improves the practicability,reliability,and stability of the imaging photoplethysmographic measurement method.

关 键 词：成像系统 成像式光电容积脉搏波 心率测量 光照干扰 归一化最小均方误差 自寻优算法 

分 类 号：O436[机械工程—光学工程]