面向远程光体积描记的人脸检测与跟踪  

Face detection and tracking algorithm for remote photoplethysmography

作　　者：赵昶辰 梅培义 冯远静[1] Zhao Changchen;Mei Peiyi;Feng Yuanjing(College of Information Engineering,Zhejiang University of Technology,Hangzhou 310023,China)

机构地区：[1]浙江工业大学信息工程学院,杭州310023

出　　处：《中国图象图形学报》2020年第11期2439-2450,共12页Journal of Image and Graphics

基　　金：国家自然科学基金项目(61903336,61976190);浙江省重点研发计划项目(2020C03070)。

摘　　要：目的远程光体积描记(remote photoplethysmograph,r PPG)是一种基于视频的非接触心率测量方法,通过跟踪人脸皮肤区域并从中提取周期性微弱变化的颜色信号估计出心率。目前基于级联回归树的人脸地标方法训练的Dlib库,由于能快速准确定位人脸轮廓,正逐渐被研究者用于跟踪皮肤感兴趣区域(region of interest,ROI)。由于实际应用中存在地标无规则抖动,且现有研究没有考虑目标晃动的影响,因此颜色信号提取不准确,心率估计精度不佳。为了克服以上缺陷,提出一种基于Dlib的抗地标抖动和运动晃动的跟踪方法。方法本文方法主要包含两个步骤:首先,通过阈值判断两帧间地标的区别,若近似则沿用地标,反之使用当前帧地标以解决抖动问题。其次,针对运动晃动,通过左右眼地标中点计算旋转角度,矫正晃动的人脸,保证ROI在运动中也能保持一致。结果通过信噪比(signal-to-noise,SNR)、平均绝对误差(mean absolute error,MAE)和均方根误差(root mean squared error,RMSE)来评价跟踪方法在r PPG中的测量表现。经在UBFC-RPPG(stands for Univ.Bourgogne Franche-ComtéRemote Photo Plethysmo Graphy)和PURE(Pulse Rate Detection Dataset)数据集测试,与Dlib相比,本文方法r PPG测量结果在UBFC-RPPG中SNR提高了约0.425 d B,MAE提高0.2915 bpm,RMSE降低0.6453 bpm;在PURE中SNR降低了0.0411 d B,MAE降低0.0652 bpm,RMSE降低0.2718 bpm。结论本文方法相比于Dlib有效提高跟踪框稳定性,在静止和运动中都能跟踪相同ROI,适合r PPG应用。Objective Remote photoplethysmography(r PPG)is a video-based noncontact heart rate measurement method.It tracks the skin area of the face,extracts periodic subtle color variations within video data,and estimates heart rate from color signals.It has a broad application in the field of medical healthcare and daily living.Currently,facial landmark-based tracking methods are widely used by researchers to track regions of interest(ROIs)because it can quickly and accurately locate face contours.The Dlib library trained based on the cascade regression tree method is widely used.However,in practice,it has problems,such as the irregular jitter of landmarks during tracking,and present research does not consider the effect of target shaking.Thus,color signal extraction is inaccurate,and the accuracy of heart rate estimation is poor.To overcome the above problems,we first use the threshold method to stabilize landmarks,then rotate the image to correct the shaking face,and finally extract the region of interest and extract the color signal to estimate the heart rate.Method When Dlib is applied to a frame,it detects the face bounding box,fits a set of average landmark points in the model to the face frame as the first predicted landmark,and updates the landmark through a cascade of regression trees.In each regression tree,a tree node decides the direction of splitting on the basis of the difference in pixel intensity between two pixels in a graph and threshold,and the offset is obtained until the last layer.When the detected face position is different or the offset obtained by a certain tree is different,deviation appears between the landmarks of two frames,that is,the landmarks jitter irregularly.Dlib suffers from the problem of landmark jitter.In some low-head scenes,the degree of jitter is particularly large,but the contours of landmarks detected using two-frame images are approximate.Nevertheless,the facial landmark detection accuracy of Dlib is more accurate than most object detection and tracking algorithms.Accordingly,t

关 键 词：远程光体积描记(r PPG) 心率测量 目标跟踪 人脸地标 旋转矫正 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]