一种基于欧拉的非接触式检测生理参数的加速方法

A Quick Method Based on Euler For Non-Contact Detection of Physiological Parameters

成像式光电容积描记技术(IPPG)是近几年发展起来的一种新的检测生理参数的技术.欧拉视频放大技术以一种空间多尺度的方法来研究像素随时间的变化,揭示了视频中微弱运动的变化,使得现代的医学技术更好地发展.在环境光照射下使用智能手机的摄像头采集人脸部视频,将原始视频信号进行欧拉放大提取心率和血氧饱和度.传统的欧拉放大技术基于YIQ色彩空间,所以要对采集到的视频做一个色彩空间转换,放大完后再由YIQ空间转换到RGB空间,这种方法计算量大,耗时多,不利于生理参数的实时检测.提出一种不对色彩空间进行转换,直接利用RGB空间对视频进行放大的方法.与传统方法相比,RGB色彩空间测量的准确性与YIQ色彩空间具有高度的一致性,同时处理速度提升了百分之三十以上.

Imaging Photoplethysmography(IPPG) is a new technique for detecting physiological parameters in recent years.Euler video amplification technology studies the variation of pixels over time in a spatial multi-scale approach.It reveals the changes in the weak movements in the video,making modern medical technology develop better.In this paper,the camera of smart phone is used to collect video of human face under ambient light,and the original video is subjected to Euler amplification to extract the heart rate and blood oxygen saturation.The traditional Euler amplification technology is based on the YIQ color space.It converts the input video from RGB color space to YIQ color space,and then convertes the RGB color space to the YIQ color space after being enlarged.This method is computationally intensive and time consuming,which is not conducive to real-time detection of heart rate.This paper proposes a method that does not convert the color space and directly enlarges the video using RGB color space.Compared with the traditional method,the accuracy of the RGB color space measurement heart rate is highly consistent with the YIQ color space,and the processing speed is increased by more than 30%.