Human eye locating and tracking using space-time context and random forest

Lin-tao LIU; Xue-ying DONG; Jun LIU; Xiang-ru WANG; Zi-qiang HUANG

doi:10.3788/YJYXS20183305.0443

您当前的位置：

首页 >

文章列表页 >

Human eye locating and tracking using space-time context and random forest

Image Processing | 更新时间：2020-08-12

- Human eye locating and tracking using space-time context and random forest
- Chinese Journal of Liquid Crystals and Displays Vol. 33, Issue 5, Pages: 443-449(2018)
- 作者机构：
  
  1.电子科技大学电子科学技术研究院, 四川成都 611731
  2.贵州大学大数据与信息工程学院, 贵州贵阳 550025
  3.电子科技大学光电科学与工程学院, 四川成都 610054
- 作者简介：
- 基金信息：
- DOI：10.3788/YJYXS20183305.0443
  CLC： TP751.1
- Received：07 March 2018，
  
  Accepted：15 March 2018，
  
  Published：2018-05
- 稿件说明：
移动端阅览
Lin-tao LIU, Xue-ying DONG, Jun LIU, et al. Human eye locating and tracking using space-time context and random forest[J]. Chinese journal of liquid crystals and displays, 2018, 33(5): 443-449.
DOI：

Lin-tao LIU, Xue-ying DONG, Jun LIU, et al. Human eye locating and tracking using space-time context and random forest[J]. Chinese journal of liquid crystals and displays, 2018, 33(5): 443-449. DOI： 10.3788/YJYXS20183305.0443.

摘要

为了得到人眼跟踪过程中更好的鲁棒性和实时性以及跟踪精度，提出一种基于自适应增强分类算法（AdaBoost）、随机森林（RF）和时空上下文（STC）的重定位跟踪算法。该算法结构分为3层，分别为AdaBoost人脸检测、STC人脸跟踪和RF人眼定位。首先，利用AdaBoost在第一帧识别出人脸，从而提取出人脸窗口。接着，使用时空上下文跟踪算法进行人脸跟踪。然后，联合定向梯度直方图（HOG）算法进行相似度判断，以达到目标丢失后继续跟踪的目的。最后，采用随机森林算法进行人眼定位。实验结果表明，与传统的随机森林人眼跟踪算法相比，该算法在跟踪速度达到原方法的2倍左右，并在跟踪精度和鲁棒性上和原算法相同。基本满足在裸眼3D显示时人脸跟踪和人眼定位的精度高、实时性快、鲁棒性好的要求。

Abstract

In order to obtain better robustness

real-time and tracking accuracy in human eye tracking process

this paper proposed a relocation tracking method based on adaptive boosting (AdaBoost)

random forest (RF) and space-time context (STC). The algorithm structure was divided into three layers

which was AdaBoost face detection

STC face tracking and RF eye positioning. First

AdaBoost was used to recognize faces in the first frame to extract face windows. Then

the spatio-temporal context algorithm was employed for face tracking. Afterwards

the histogram of oriented gradient (HOG) was used to judge the similarity

so as to achieve the goal of tracking after the target is lost. Finally

the random forest algorithm was used to locate the human eye. Experimental results indicate that the algorithm has a tracking speed of about 2 times as much as the original method. Moreover

this method had the same tracking accuracy and robustness as the original algorithm. It can satisfy high precision for human eye location

real-time

good robustness in naked eye 3D display.

关键词

Keywords

references

熊晶莹, 戴明.适应移动智能设备的目标跟踪器[J].光学精密工程, 2017, 12(25):3152-3159.

XIONG J Y, DAI M.Design of tracker for mobile smart devices[J]. Opt. Precision Eng. , 2017, 12(25):3152-3159. (in Chinese)

田华, 曾小名, 戴涛涛, 等.柱透镜光栅投影3D显示的视点数与串扰容限[J].液晶与显示, 2013, 28(3):330-337.

TIANG H, ZHENG X M, DAI X, et al .. New Problems about Number of Views and Grosstalk Tolerance in Projective AutoSterepic Display Based on Lenticlar Grating[J]. Chinese Journal of Liquid Crystals and Displays , 2013, 28(3):330-337. (in Chinese)

王嘉辉, 邓玉桃, 苏剑邦, 等.全高清裸眼3D显示效果的评价与测量[J].液晶与显示, 2013, 28(5):805-809.

WANG J H, DENG YT, SU J B, et al .. Evaluation and Measurement of Display Effect in Full High Resolution Autostereoscopic Display[J]. Journal of Liquid Crystals and Displays , 2013, 28 (5):805-809. (in Chinese)

谢雨桐, 苏晓煌, 郑集文, 等.裸眼3D显示设备关键指标测试方案的研究[J].液晶与显示, 2015, 5(30):888-893.

XIE Y T, SU X H, Z J W, et al .. Key properties of autostereoscopic display[J]. Journal of Liquid Crystals and Displays , 2015, 5(30):888-893. (in Chinese)

VALENTI R, GEVERS T. Accurate eye center location and tracking using isophote curvature[C]. Computer Vision and Pattern Recognition. America : CVPR 2008: 1-8.

PENG K, CHEN L T, RUAN S, KUKHAREY G. A robust algorithm for eye detection on gray intensity face without spectacles[J]. J. Comput. Sci. Technol, 2005, 5(8):127-132.

FASEL I, FORTENBERRY B, MOVELLAN J. A generative framework for real time object detection and classification[J]. Computer Vision & Image Understanding , 2005, 98(1):182-210.

REN S, CAO X, WEI Y, SUN J. Face Alignment at 3000 FPS via Regressing Local Binary Features[C]. Computer Vision and Pattern Recognition. America : CVPR , 2014: 1685-1692.

ZHANG K, ZHANG L, YANG M, ZHANG, D. Fast tracking via spatio-temporal context learning[J]. Computer Science, 2013, 11(8):1-16.

DALAL N, TRIGGS B. Histograms of Oriented Gradients for Human Detection[C]. P Computer Vision and Pattern Recognition . America : CVPR , 2005: 886-893.

BREIMAN L. Random Forests[J]. Machine Learing. 2001, 45(1):5-32.

BURGOS A, X P, PERONA P, DOLL, PIOTR R. Robust Face Landmark Estimation under Occlusion[C]. Computer Vision and Pattern Recognition. America : CVPR , 2013: 1513-1520.

XING X, TORRE F, F D L. Supervised descent method and its applications to face alignment[C]. Computer Vision and Pattern Recognition. America : CVPR , 2013: 532-539.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Face detection algorithm based on LVQ neural network model

Face detection algorithm based on skin color location

3 D human-machine interaction based on human eye detection

X-ray image illegal object classification based on computer vision

RGBD salient object detection based on regional feature integration

Related Author

Meng QI

Yan WANG

Ming-zhong YANG

Guo-jun LIN

Ming-ju CHEN

Mei XIE

Zi-zhao HUANG

Jia-hui HUANG

Related Institution

School of Electronics Engineering, Chengdu Technological University

School of Automation & Information Engineering, Sichuan University of Science & Engineering

School of Electronic Engineering, University of Electronic Science and Technology of China

School of Electronics and Information Technology, SunYat-sen University

Physics Experiment Teaching Center, School of Physics,Sun Yat-sen University

AI问答

Address：No.3888 Dong Nanhu Road, Changchun, Jilin, China 130033 Postal code：130033
Tel：0431-86176059 Email：yjxs@ciomp.ac.cn
Technical support is provided by Beijing Founder electronics co., LTD 吉ICP备11002662号-17 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰