基于视频图像的人眼动态追踪  

Human Eye Dynamic Tracking Based on Video Images

作　　者：宋琴琴 杨国平 SONG Qinqin;YANG Guoping(School of Mechanical and Automotive Engineering,Shanghai University of Engineering Science,Shanghai 201620)

机构地区：[1]上海工程技术大学机械与汽车工程学院,上海201620

出　　处：《计算机与数字工程》2021年第7期1457-1459,1474,共4页Computer & Digital Engineering

摘　　要：论文基于视频图像对人眼的瞳孔中心进行实时定位,根据该点的位置变化从而判断人眼的注视方向即人眼的动态追踪。首先对视频图像进行灰度化处理,将视频图像从RGB色彩空间转换到灰度空间。然后对灰度图像进行高斯滤波处理,去除图像的噪点。接着对图像进行二值化处理找到人眼区域并检测出瞳孔轮廓,最后进行瞳孔中心定位实现人眼动态追踪。实验结果表明,该方法是有效的,能够实时追踪眼动方向。In this paper,the pupil center of the human eye is positioned in real time based on the video image,and the gaze direction of the human eye,that is,the dynamic tracking of the human eye,is judged according to the position change of the point.First,the video image is grayscaled to convert the video image from the RGB color space to the gray space.The gray image is pro⁃cessed by Gaussian filtering to remove the image noise.Then the image is binarized to find the human eye area and the pupil contour is detected.Finally,the pupil center positioning is performed to realize the human eye dynamic tracking.The experimental results show that the method is effective and can track the direction of eye movement in real time.

关 键 词：瞳孔定位 二值化 高斯滤波 

分 类 号：TP751[自动化与计算机技术—检测技术与自动化装置]