Shanghai Jiao Tong University, Institute of Image Communication and Information Processing, Shanghai, China.
J Biomed Opt. 2017 Mar 1;22(3):36006. doi: 10.1117/1.JBO.22.3.036006.
We present a dual-mode imaging system operating on visible and long-wave infrared wavelengths for achieving the noncontact and nonobtrusive measurements of breathing rate and pattern, no matter whether the subjects use the nose and mouth simultaneously, alternately, or individually when they breathe. The improved classifiers in tandem with the biological characteristics outperformed the custom cascade classifiers using the Viola–Jones algorithm for the cross-spectrum detection of face and nose as well as mouth. In terms of breathing rate estimation, the results obtained by this system were verified to be consistent with those measured by reference method via the Bland–Altman plot with 95% limits of agreement from ? 2.998 to 2.391 and linear correlation analysis with a correlation coefficient of 0.971, indicating that this method was acceptable for the quantitative analysis of breathing. In addition, the breathing waveforms extracted by the dual-mode imaging system were basically the same as the corresponding standard breathing sequences. Since the validation experiments were conducted under challenging conditions, such as the significant positional and abrupt physiological variations, we stated that this dual-mode imaging system utilizing the respective advantages of RGB and thermal cameras was a promising breathing measurement tool for residential care and clinical applications.
我们提出了一种双模成像系统，可在可见和长波红外波长下运行，以实现对呼吸率和模式的非接触式和非侵入式测量，无论受试者在呼吸时是同时、交替还是单独使用鼻子和嘴。改进的分类器与生物特征相结合，在用于面部和鼻子以及嘴的交叉光谱检测的 Viola–Jones 算法的自定义级联分类器的性能更好。就呼吸率估计而言，通过 Bland–Altman 图和 95%一致性界限从-2.998 到 2.391 以及线性相关分析与相关系数为 0.971 的方式，验证了该系统获得的结果与通过参考方法测量的结果一致，表明该方法可用于呼吸的定量分析。此外，双模成像系统提取的呼吸波形与相应的标准呼吸序列基本相同。由于验证实验是在具有挑战性的条件下进行的，例如显著的位置和突然的生理变化，因此我们表示，这种利用 RGB 和热摄像机各自优势的双模成像系统是一种有前途的呼吸测量工具，可用于家庭护理和临床应用。
