基于特征的视线跟踪方法研究综述  

A Review of Feature-based Gaze Tracking Methods

作　　者：刘佳惠 迟健男[1,2] 尹怡欣 LIU Jia-Hui;CHI Jian-Nan;YIN Yi-Xin(School of Automation and Electrical Engineering,University of Science and Technology Beijing,Beijing 100083;Shunde Graduate School of University Of Science and Technology Beijing,Foshan 528399)

机构地区：[1]北京科技大学自动化学院,北京100083 [2]北京科技大学顺德研究生院,佛山528399

出　　处：《自动化学报》2021年第2期252-277,共26页Acta Automatica Sinica

基　　金：国家重点研发计划(2018YFC2001700);北京市自然科学基金(4172040);北京科技大学顺德研究生院科技创新专项资金;中央高校基本科研业务费专项资金(FRF-GF-20-04A)资助。

摘　　要：针对基于特征的视线跟踪方法进行了综述.首先对视线跟踪技术的发展、相关研究工作和研究现状进行了阐述;然后将基于特征的视线跟踪方法分成了两大类:二维视线跟踪方法和三维视线跟踪方法,从硬件系统配置、误差主要来源、头部运动影响、优缺点等多个方面重点分析了这两类视线跟踪方法,对近五年现有的部分基于特征的视线跟踪方法进行了对比分析,并对二维视线跟踪系统和三维视线跟踪系统中的几个关键问题进行了探讨;此外,介绍了视线跟踪技术在人机交互、医学、军事、智能交通等多个领域的应用;最后对基于特征的视线跟踪方法的发展趋势和研究热点进行了总结与展望.In this paper,the feature-based gaze tracking methods are reviewed.Firstly,the development,the related works and the research status of gaze tracking technology are introduced.Then,the feature-based gaze tracking methods are classified into two categories:Two-dimensional gaze tracking methods and three-dimensional gaze tracking methods.These two kinds of gaze tracking methods are emphatically analyzed in terms of hardware system configuration,main error sources,head movement,advantages and disadvantages,etc.Some of the existing feature-based gaze tracking methods in recent five years are compared,and several key issues in two-dimensional gaze tracking systems and three-dimensional gaze tracking systems are discussed.Moreover,the applications of gaze tracking technology in many fields,such as human-computer interaction,medicine,military,intelligent transportation,etc.are introduced.Finally,the development trends and research topics of feature-based gaze tracking methods are summarized.

关 键 词：基于特征 视线跟踪 二维映射模型 三维视线估计 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]