首页 > 论文 > 液晶与显示 > 33卷 > 11期(pp:958-964)

基于人眼检测优化的立体人机交互技术的研究

3D human-machine interaction based on human eye detection

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

随着3D显示技术的逐渐成熟,越来越多基于3D显示技术的产品被应用于各个领域,例如3D电影、裸眼3D电视、体感交互式系统和影像教学等。基于3D显示的人机交互系统也是近年来越来越热门的研究方向,但是却没有高效地利用深度信息作为交互的线索,因此本文提出将3D显示与体感交互结合,实现立体人机交互的虚拟键盘,让用户只需点击屏幕前方键盘的图像即可进行对应按键信息的录入和编辑,其帧率可达10.6 fps。针对3D显示中用户视角偏离会导致按键的像在视觉上的偏移,容易造成误输入的问题,在系统中整合人眼检测功能,修正因视角偏离带来按键定位误差,从而实现了准确率100%的字符输入交互功能。

Abstract

With the growing of 3D display, more and more products based on 3D display are used in various fields, for example, 3D movies, auto-stereoscopic television, 3D surgery, etc. Human-computer interaction (HCI) system based on 3D display is also a popular research direction in recent years. However, most of these systems don’t use depth information as a clue for interaction which limit interaction orientation into a 2D plane. To extend control on depth direction, a novel HCI system based on 3D display is presented. The system shows a keyboard style interaction interface by a 3D monitor, and uses binocular cameras to acquire the gesture and positions of the user’s hand and fingers which can input information to the computer. And the system input frame rate can reach 10.6 fps. For problem that the movement of the user will cause the image of the button in his vision to be shifted correspondingly, which may cause incorrect input the human eye detection is integrated into the system. By the optimization of user’s viewing angle calibration, we can correct button’s positioning error, thus achieve a great accuracy of character input 100%.

Newport宣传-MKS新实验室计划
补充资料

中图分类号:TN27

DOI:10.3788/yjyxs20183311.0958

所属栏目:图像处理

基金项目:广东省自然科学基金(No.2015A030310388)与(No.2016A030313333)

收稿日期:2018-04-12

修改稿日期:2018-07-16

网络出版日期:--

作者单位    点击查看

薛钊鸿:中山大学 电子与信息工程学院,广东 广州 510275
孙梓瀚:中山大学 电子与信息工程学院,广东 广州 510275
成泽锐:中山大学 电子与信息工程学院,广东 广州 510275
方衡:中山大学 物理学院 物理实验教学中心,广东 广州 510275
黄梓钊:中山大学 电子与信息工程学院,广东 广州 510275
李佼洋:中山大学 物理学院 物理实验教学中心,广东 广州 510275
蔡志岗:中山大学 物理学院 物理实验教学中心,广东 广州 510275
王嘉辉:中山大学 物理学院 物理实验教学中心,广东 广州 510275

联系人作者:王嘉辉(wangjh@mail.sysu.edu.cn)

备注:薛钊鸿(1993-),男,广东江门人,硕士研究生,主要从事图像处理技术及应用的研究。E-mail:xue_zhaohong@qq.com

【1】王琼华,邓欢.集成成像3D拍摄与显示方法[J].液晶与显示,2014,29(2):153-158.
WANG Q H, DENG H. 3D pickup and display method of integral imaging [J]. Chinese Journal of Liquid Crystals and Displays, 2014, 29(2): 153-158. (in Chinese)

【2】LUEDER E.3D显示技术[M].余宏生,王彤彤,梅军进,译.北京:电子工业出版社,2016.
LUEDER E. 3D display [M]. YU H S, WANG T T, MEI J J, trans. Beijing: Publishing House of Electronics Industry, 2016.

【3】孙博.裸眼3D显示技术的现状与发展[J].科技传播,2017,9(21):115-116.
SUN B. Present situation and development of naked eye 3D display technology [J]. Public Communication of Science & Technology, 2017, 9(21): 115-116.

【4】林孜铠,戴思璋,梁浩文,等.基于混合颜色空间与码本背景减除的虚拟触控优化技术[J].液晶与显示,2015,30(4):722-728.
LIN Z K, DAI S Z, LIANG H W, et al. Touch technology based on mixed color space and codebook background difference [J]. Chinese Journal of Liquid Crystals and Displays, 2015, 30(4): 722-728. (in Chinese)

【5】张超,王琼华,李大海,等.从平面图生成多视点自由立体显示视差图的研究[J].液晶与显示,2009,24(2):258-261.
ZHANG C, WANG Q H, LI D H, et al. Capture of parallax image from 2D images for multi-view auto-stereoscopic display [J]. Chinese Journal of Liquid Crystals and Displays, 2009, 24(2): 258-261. (in Chinese)

【6】刘江华,陈佳品,程君实.双目视觉平台的研究[J].机器人技术与应用,2002(1):36-40.
LIU J H, CHEN J P, CHENG J S. Research on binocular vision platform [J]. Robot Technique and Application, 2002(1): 36-40. (in Chinese)

【7】林岱昆,梁伟棠,梁浩文,等.基于人脸跟踪的时空无缝裸眼3D显示技术研究[J].电视技术,2015,39(5):70-73,77.
LIN D K, LIANG W T, LIANG H W, et al. Spatially and temporally seamless autostereoscopic display technology research based on face-tracking [J]. Video Engineering, 2015, 39(5): 70-73, 77. (in Chinese)

【8】龙伶敏.基于Adaboost的人脸检测方法及眼睛定位算法研究[D].成都:电子科技大学,2008.
LONGL M. Face detection method and eye location algorithm based on Adaboost [D]. Chengdu: University of Electronic Science and Technology of China, 2008. (in Chinese)

【9】胡涛,冯玉娜,王亚丹,等.一种人脸三庭五眼自动定位及比例确定方法:中国,104021550B[P].2017-01-18.
HU T, FENG Y N, WANG Y D, et al. A method of automatic location and proportion determination of three faces and five eyes in human faces: CN, 104021550B [P]. 2017-01-18. (in Chinese)

【10】张华坤,王敏,罗开,等.三庭五眼的最佳定点探索[J].医学与哲学:B,2017,38(5):64-69.
ZHANG H K, WANG M, LUO K, et al. A study of the best fixed-point of facial proportions [J]. Medicine & Philosophy: B, 2017, 38(5): 64-69. (in Chinese)

引用该论文

XUE Zhao-hong,SUN Zi-han,CHENG Ze-rui,FANG Heng,HUANG Zi-zhao,LI Jiao-yang,CAI Zhi-gang,HUANG Jia-hui. 3D human-machine interaction based on human eye detection[J]. Chinese Journal of Liquid Crystals and Displays, 2018, 33(11): 958-964

薛钊鸿,孙梓瀚,成泽锐,方衡,黄梓钊,李佼洋,蔡志岗,王嘉辉. 基于人眼检测优化的立体人机交互技术的研究[J]. 液晶与显示, 2018, 33(11): 958-964

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF