非接触式眼压计人眼跟踪算法研究  

Research on Eye Tracking Algorithm of Non-contact Tonometer

作　　者：刘颖 王劲松[1] 王苗 LIU Ying;WANG Jin-song;WANG Miao(School of Optoelectronic Engineering,Changchun University of Science and Technology,Changchun 130022)

机构地区：[1]长春理工大学光电工程学院,长春130022

出　　处：《长春理工大学学报（自然科学版）》2021年第5期27-31,共5页Journal of Changchun University of Science and Technology(Natural Science Edition)

基　　金：吉林省重点科技研发项目(20180201025GX)。

摘　　要：非接触式眼压计测量眼压的前提是对人眼瞳孔进行精确跟踪定位。通过对非接触式眼压测量跟踪系统的研究,提出汇聚式双目视觉的人眼瞳孔跟踪方法,采用结合帧差法和Mean-Shift算法的改进算法进行目标跟踪,解决了Mean-Shift算法对瞳孔进行跟踪过程中,有跟踪目标丢失现象的问题,通过下位机驱动三轴电机进行移动,调整系统与人眼的相对位置,以实现人眼瞳孔的精确跟踪。经在样机上实验,其结果表明:系统跟踪定位误差≤0.1 mm,跟踪过程在1 s内完成。The premise of measuring IOP with non-contact tonometer was to accurately track and locate the pupil.Based on the research of non-contact intraocular pressure measurement and tracking system,a convergent binocular vision eye pupil tracking system was proposed.An improved algorithm combining frame difference method and Mean-shift algorithm was used to track the target.The problem of tracking target missing in the process of Mean-shift algorithm tracking pupil was solved.The system was moved by driving a three-axis motor through the lower computer.The relative position of human eye was adjusted to realize the accurate tracking of human pupil.The results show that the tracking error of the system was less than 0.1 mm;and the tracking process was completed within 1 s.

关 键 词：非接触式眼压测量 瞳孔跟踪 双目视觉 图像处理 Mean-Shift算法改进 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术] TH89[自动化与计算机技术—计算机科学与技术]