基于集成学习的人眼定位和头部状态检测研究

doi:10.16182/j.issn1004731x.joss.19-FZ0358

系统仿真学报 ›› 2019, Vol. 31 ›› Issue (11): 2366-2373.doi: 10.16182/j.issn1004731x.joss.19-FZ0358

基于集成学习的人眼定位和头部状态检测研究

吴迎年, 贺梦嘉, 项伟

北京信息科技大学自动化学院,北京 100192

收稿日期:2019-05-30 修回日期:2019-07-30 出版日期:2019-11-10 发布日期:2019-12-13
作者简介:吴迎年(1976-),男,河北晋州,博士,副教授,硕导,研究方向为物联网控制、机器人自然交互、高性能仿真。
基金资助:
促进高校内涵发展“信息+”项目(5111823311),北京信息科技大学重点研究培育项目(5221823307),北京信息科技大学教改重点资助项目(2019JGZD02)

Research on Eye Location and Head State Detection Based on Integrated Learning

Wu Yingnian, He Mengjia, Xiang Wei

School of Automation Beijing Information Science and Technology University, Beijing 100192, China

Received:2019-05-30 Revised:2019-07-30 Online:2019-11-10 Published:2019-12-13

摘要/Abstract

摘要： 针对人眼定位中的实时性检测问题,设计了基于Viola-Jones算法的人眼实时检测系统,通过MATLAB控制外接或网络摄像头对检测到的人眼图片进行实时读取和实时定位,通过正面图、侧视图、俯仰图的检测,表明人眼实时定位系统检测效果较好并具有很好的鲁棒性。针对小数据集对头部状态的分类效果较差的情况,使用随机森林算法将俯仰角和偏航角的分别用HOG-LBP融合特征和Haar-like特征分类,再将得到的俯仰角和偏转角进行融合,在Pointing'04数据集上对比直接分类准确率提升了4.5%。

关键词: 集成学习, Viola-Jones算法, 人眼定位, 头部状态检测, 实时检测

Abstract: For real-time detection of eye location problem, a real-time detection system of human eye based on Viola Jones algorithm is designed. Through the MATLAB, the real-time reading and positioning of the detected human eye pictures are controlled by the external or webcam. Through side view, top view, and upward view, it is shown that the human eye real-time positioning system has good detection effect and robustness. In view of the poor classification effect of small data sets on the head state, the random forest algorithm is used to classify the pitching Angle and yaw Angle by HOG-LBP fusion feature and haar-like feature respectively, and then the obtained pitching Angle and deflection Angle are fused. The accuracy of direct classification is improved by 4.5% compared with the point'04 data set.

Key words: integrated learning, viola-jones algorithm, eye location, head state detection, real-time detection

中图分类号:

TP242.6

吴迎年, 贺梦嘉, 项伟. 基于集成学习的人眼定位和头部状态检测研究[J]. 系统仿真学报, 2019, 31(11): 2366-2373.

Wu Yingnian, He Mengjia, Xiang Wei. Research on Eye Location and Head State Detection Based on Integrated Learning[J]. Journal of System Simulation, 2019, 31(11): 2366-2373.

参考文献

[1] 崔景春, 王静. 基于增强头部姿态估计的人脸表情识别模型[J]. 计算机科学, 2019, 46(6): 322-327.
Cui Jingchun, Wang Jing.Facial expression recognition model based on enhanced head posture estimation[J]. Computer science, 2019, 46(6): 322-327.
[2] 马卫华. 人机交互系统的实时人眼跟踪技术研究[J]. 现代电子技术, 2019, 42(13): 65-68.
Ma Weihua.Research on real-time human eye tracking technology of human-computer interaction system[J]. Modern electronic technology, 2019, 42(13): 65-68.
[3] 房爱青, 吴金强, 李长勇, 等. 一种改进的人眼定位算法研究[J]. 机械设计与制造, 2018(5): 82-85.
Fang Aiqing, Wu Jinqiang, Li Changyong, et al.Research on an improved human eye positioning algorithm[J]. Mechanical design and manufacturing, 2018 (5): 82-85.
[4] 项伟. 脑电与眼球信号融合的轮椅式机器人控制研究[D]. 北京: 北京信息科技大学, 2018.
Xiang Wei.Research on wheelchair robot control based on EEG and eyeball signal fusion [D]. Beijing: Beijing University of information technology, 2018.
[5] 冯建强, 刘文波, 于盛林. 基于灰度积分投影的人眼定位[J]. 计算机仿真, 2005(4): 75-76,104.
Feng Jianqiang, Liu Wenbo, Yu Shenglin.Eye location based on gray integral projection[J]. Computer simulation, 2005(4): 75-76,104.
[6] 黄增喜, 张海军, 李一波, 等. 一种快速的自动人眼定位方法[J]. 计算机工程与应用, 2011, 47(7): 183-186.
Huang Zengxi, Zhang Haijun, Li Yibo, et al.A fast automatic eye location method[J]. Computer engineering and application, 2011, 47(7): 183-186.
[7] 崔庆华, 程科, 李肇基. 积分投影与连通域法结合的人眼定位[J]. 计算机与数字工程, 2019, 47(4): 949-953.
Cui Qinghua, Cheng Ke, Li Zhaoji.Eye location by integrating projection and connected domain method[J]. Computer and digital engineering, 2019, 47(4): 949-953.
[8] 荔小虎, 唐晶磊. 基于肤色匹配和积分投影结合的人眼定位方法研究[J]. 自动化应用, 2018(12): 59-61.
Li Xiaohu, Tang Jinglei.Research on eye location method based on skin color matching and integral projection[J]. Automation application, 2018(12): 59-61.
[9] 彭明莎, 刘翠响. 基于运动区域Viola-Jones算法的视频人脸检测[J]. 电子设计工程, 2015, 23(21): 15-17.
Peng Mingsha, Liu Cuixiang.Video face detection based on motion region Viola Jones algorithm[J]. Electronic design engineering, 2015, 23(21): 15-17.
[10] Zelenkov Y. Example-dependent cost-sensitive adaptive boosting[J]. Expert Systems with Applications (S0957-4174), 2019, 135: 71-82.
[11] Michor J, Sakhnovich A L.GBDT and algebro-geometric approaches to explicit solutions and wave functions for nonlocal NLS[J]. Journal of Physics A-Mathematical and Theoretical(S1751-8113), 2019, 52(0252012).
[12] 方阳, 刘英杰, 孙立博, 等. 基于SSD模型的人脸检测与头部姿态估计融合算法[J]. 江苏大学学报(自然科学版), 2019, 40(4): 451-457.
Fang Yang, Liu Yingjie, Sun Libo, et al.Fusion algorithm of face detection and head pose estimation based on SSD model[J]. Journal of Jiangsu University (Natural Science Edtion), 2019, 40(4): 451-457.
[13] 武文韬. 基于HOG-LBP的行人检测系统的研究与实现[D]. 北京: 北京邮电大学, 2019.
Wu Wentao.Research and implementation of pedestrian detection system based on hog-lbp [D]. Beijing: Beijing University of Posts and telecommunications, 2019.
[14] 孙伟, 赵玉普. 增强旋转不变LBP算法及其在图像检索中的应用[J]. 计算机科学, 2019, 46(7): 263-267.
Sun Wei, Zhao Yupu.Enhanced rotation invariant LBP algorithm and its application in image retrieval[J]. Computer science, 2019, 46(7): 263-267.
[15] 刘林涛, 董雪莹, 刘俊, 等. 基于时空上下文和随机森林的人眼跟踪定位算法研究[J]. 液晶与显示, 2018, 33(5): 443-449.
Liu Lintao, Dong Xueying, Liu Jun, et al.Huang Ziqiang. Research on human eye tracking and positioning algorithm based on spatiotemporal context and random forest[J]. Liquid crystal and display, 2018, 33(5): 443-449.
[16] 梁令羽, 孙铭堃, 何为, 等. Bagging-SVM集成分类器估计头部姿态方法[J/OL]. 计算机科学与探索: [2019-07-30]. http://kns.cnki.net/kcms/detail/11. 5602.TP. 20190329.1805.013.html.
[17] Xue N, Deng J, Cheng S, et al.Side Information for Face Completion: a Robust PCA Approach[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence (S0162-8828), 2015, 14(8): 1.
[18] 汪雯琦, 高广阔. 基于PCA和SVM分类的跨年龄人脸识别[J]. 计算机时代, 2019(7): 1-4, 8.

基于集成学习的人眼定位和头部状态检测研究

Research on Eye Location and Head State Detection Based on Integrated Learning

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 2

编辑推荐

Metrics

本文评价

[1]	邓欣, 龙灿, 米建勋, 张博宪, 孙开伟, 王进. 基于多域特征与随机子空间集成的脑电分类[J]. 系统仿真学报, 2020, 32(9): 1787-1798.
[2]	金炜东, 陈春利. 基于集成深度学习的雷达信号分选研究[J]. 系统仿真学报, 2019, 31(9): 1868-1874.