删除或更新信息，请邮件至freekaoyan#163.com(#换成@)

基于样本扩充和改进Lasso回归的视线估计

本站小编 Free考研考试/2021-12-21
本文二维码信息
二维码（扫一下试试看！）
基于样本扩充和改进Lasso回归的视线估计
Gaze Estimation Based on Sample Expansion and Improved Lasso Regression
投稿时间：2019-10-16
DOI：10.15918/j.tbit1001-0645.2019.260
中文关键词:视线估计样本扩充改进Lasso回归
English Keywords:gaze estimationsample extensionLasso regression improvement
基金项目:国家部委基础科研计划资助（JCKY2017602C016）
作者单位E-mail
王洪枫北京理工大学 机电学院, 北京 100081
王建中北京理工大学 机电学院, 北京 100081cwjzwang@bit.edu.cn
白柯萌北京理工大学 机电学院, 北京 100081
张晟北京理工大学 机电学院, 北京 100081
摘要点击次数:570
全文下载次数:280
中文摘要:
为了利用眼部特征进行准确的视线估计，提出了一种基于样本扩充和改进Lasso回归的方法，建立眼部特征与视线之间的映射关系.通过对小样本评分得到优质样本，进而完成样本扩充，利用改进的Lasso回归得到准确的视线估计模型.该方法对标定过程中的眨眼等干扰具有鲁棒性，受干扰后仍可保持相对较高的视线估计准确度.实验结果表明：标定过程无干扰，该方法视线估计准确度比传统方法提高11.25%；标定数据加入6.67%异常数据，该方法视线估计准确度比传统方法提高22.62%.
English Summary:
In order to make use of eye features for accurate line-of-sight estimation, a method based on sample expansion and improved Lasso regression was proposed to establish the mapping relationship between eye features and line of sight. Quality samples were obtained by scoring all samples, and then sample expansion was completed. The improved Lasso regression was used to obtain an accurate line-of-sight estimation model. This method is robust for interference such as blinking in the calibration process, and can still maintain a relatively high accuracy of line-of-sight estimation with interference. The experimental results show that the accuracy of sight estimation of this method is 11.25% higher than that of the traditional method without interference; the accuracy of sight estimation of this method is 22.62% higher than that of the traditional method with 6.67% abnormal data in the calibration data.
查看全文查看/发表评论下载PDF阅读器
相关话题/机电 北京 北京理工大学 干扰 中文

Free考研考试FreeKaoYan.Com
欢迎来到Free考研考试，"为实现人生的Free而奋斗"

© 2020 FreeKaoYan! . All rights reserved.