摘要
目的探讨多屏桌面交互过程中,利用眼动意图预测来辅助鼠标跨屏移动,促进人机交互效率的提升。方法采用眼动分析仪采集眼动和手控数据,运用聚类和贝叶斯推断方法建立眼动意图算法,基于眼动交互模式构建模拟业务平台。结果(1)提出了鼠标移动的眼动意图预测算法;(2)搭建了手控鼠标眼动交互模式的模拟业务平台;(3)基于眼动意图预测算法的鼠标有效眼控精度达到了95.0%,眼动辅助手控鼠标移动效率提升24.4%。结论眼动意图分析可以辅助手控鼠标操控,大大提升交互效率。
Objective Explore the way to use gaze-based intention prediction to assist the cross-screen mouse moving,to improve the efficiency of human computer interaction in multi-screen desktop interaction scenarios.Methods Capture the gaze and operational data using eye tracker devices,design the gaze-based intention prediction methods based on clustering and Bayes inference,and construct the simulation business platform.Results(1)Gaze-based intention prediction method is proposed for assisting mouse moving.(2)Simulation business platform for gaze interaction coordinated with manually controlled mouse is constructed.(3)The Bayes-based intention prediction method achieves the accuracy of 95.0%on gaze-based functional mouse control and the efficiency promotion of 24.4%on manually controlled mouse movement.Conclusion Gaze can assist the mouse control and greatly improve the interaction efficiency.
作者
朱光明
张宇
鲁特刚
高尔扬
李宁
张亮
ZHU Guang-ming;ZHANG Yu;LU Te-gang;GAO Er-yang;LI Ning;ZHANG Liang(School of Computer Science and Technology,Xidian University,Xi'an,Shanxi 710071,China;Xi'an Key Laboratory of Intelligent Software Engineering,Xi'an,Shanxi 710071,China;China Institute of Marine Technology&Economy,Beijing 100081,China)
出处
《人类工效学》
2022年第5期25-31,共7页
Chinese Journal of Ergonomics
基金
国防预先研究项目(50912020105),国家自然科学基金(62073252)。
关键词
视线追踪
人机交互
贝叶斯
聚类
意图预测
眼动仪
人工智能
眼控
gaze tracking
human-computer interaction
bayes
clustering
intention prediction
eye movement tracker
artifical intelligence
eye controlling