基于非线性滤波器的多人及多角度的人眼检测和跟踪-工程学研究-CSCIED科技核心评价数据库-手机版

基于非线性滤波器的多人及多角度的人眼检测和跟踪

Multi-user and Multi-view human eyes’ detection and tracking

ES评分 0 浏览量：568 下载量：0

DOI	10.12208/j.jer.20230024
刊名	工程学研究 Journal of Engineering Research
年，卷(期)	2023, 2(4)
作者	余涛¹*,邹建华^2,3,徐君¹,龙卓群¹,
作者单位	1 西安航空学院电子工程学院陕西西安 ; 2 西安交通大学系统工程研究所，系统工程国家重点实验室陕西西安 ; 3 广东西安交通大学研究院广东顺德 ; ;
摘要	本文基于非线性滤波提出一种针对多人及多角度人眼的检测和跟踪方法。首先用五种分别具有四个不同尺度的AdaBoost人脸检测器依次在图像中每个区域检测人脸；然后用四种AdaBoost 人眼检测器锁定眼部位置；若眼睛检测失败，则应用解剖学中器官位置的先验比例模板法作为补充；接着用非线性滤波器Unscented filter预测目标下一位置；最后用上述检测方法检测后续帧，修正相关预测；如此重复上述循环直至跟踪结束。相关测试得出该方法对多人及多角度的垂直主体的眨眼，闭眼，戴眼镜及部分遮挡等均具有一定程度鲁棒性，并且非线性滤波使其能够以变化速度的曲线方式跟踪目标。
Abstract	This paper presents a framework on multi-user and multi-view human eyes’ detection and tracking. First, it uses fives kinds of AdaBoost face detectors with four different sizes at each area of image to detect faces in turn. Then, to locate eyes’ positions, four kinds of AdaBoost eye detectors are used and if the eye-detection above fails, the prior knowledge of human organs’ positions in anatomy is applied as a spare method. Next, it uses the unscented filter to predict the targets’ next possible positions. Finally, the detection method above is used to detect the third frame and amend the relative forecasting. And repeat above cycle until tracking over. This framework is robust to subject’s eyes’ blinking, closing, wearing glasses and partly sheltering in multi-face and multi-view to a certain extent for the optimized structure performance and reasonable selected features. And because of the nonlinear filtering, it can track targets in curves with changing speeds. It mainly fits most usual vertical head scenes in monitoring environment.
关键词	多人；多角度；人眼检测；跟踪；非线性滤波；检测器；目标；特征
KeyWord	Multi-user; Multi-view; Eyes’ detection; Tracking; Unscented filter; Detector; Target; Feature
基金项目
页码	1-9

参考文献
相关文献

[1] Kington, J.M., et al., Impaired eye expression recognition in schizophrenia
[J]. Journal of Psychiatric Research, 2000. 34(4): p. 341-347.

[2] Ji, Q. and X. Yang, Real-time eye, gaze, and face pose tracking for monitoring driver vigilance
[J]. Real-Time Imaging, 2002. 8(5): p. 357-377.

[3] 颜红金, 张永林, 医用眼睛图像检测系统的构建
[J]. 计算机工程与设计, 2010(24): p. 5339-5342.

[4] YAN Hong jinZHANG Yong-lin Construction of medical eye image detection system
[J], COMPUTER ENGINEERING AND DESIGN, 2010(24): p. 5339-5342.

[5] De Santis, A. and D. Iacoviello, Robust real time eye tracking for computer interface for disabled people
[J]. Computer methods and programs in biomedicine, 2009. 96(1): p. 1-11.

[6] Poole, A. and L.J. Ball, Eye tracking in human-computer interaction and usability research: current status and future prospects
[M]. Encyclopedia of human computer interaction, 2005: p. 211-219.

[7] Dodgson, N.A., Autostereoscopic 3D displays
[J]. Computer, 2005. 38(8): p. 31-36.

[8] Zhou, Z.H. and X. Geng, Projection functions for eye detection
[J]. Pattern Recognition, 2004. 37(5): p. 1049-1056.

[9] 程文冬, 魏庆媛, 非约束条件下驾驶人眼睛检测与跟踪方法研究
[J]. 西安工业大学学报 2019. 039(002): p. 203-210.

[10] CHENG Wendong, WEI Qingyuan, Research on Driver Eye Detection and Tracking under Non-Restraint Conditions
[J], Journal of Xi'an Technological University, 2019. 039(002): p. 203-210.

[11] Yan, C., Y. Wang, and Z. Zhang, Robust real-time multi-user pupil detection and tracking under various illumination and large-scale head motion
[J]. Computer Vision and Image Understanding, 2011.

[12] 朱真真, 等, 基于Kinect的人脸眼部状态实时检测
[J]. 大连民族学院学报, 2015. 17(1): p. 81-81.

[13] ZHU Zhen-zhen, WANG Wei, DUAN Xiao-dong et al. Real-time Detection of Facial Eye Status Based on Kinect Sensor
[J], Journal of Dalian Nationalities University, 2015. 17(1): p. 81-81.

[14] Yang, M., et al., AdaBoost-based face detection for embedded systems
[J]. Computer Vision and Image Understanding, 2010. 114(11): p. 1116-1125.

[15] 严超, 王元庆, 张兆扬, 基于AdaBoost和Kalman算法的人眼检测与跟踪
[J]. 南京大学学报 2010(06): p. 681-687.

[16] Yan Chao, Wang Yuan-Qing, Zhang Zhao-Yang Eye detection and tracking based on AdaBoost and Kalman algorithms
[J], JOURNAL OF NANJING UNIVERSITY (NATURAL SCIENCES) 2010(06): p. 681-687.

[17] Schapire, R.E. and Y. Singer, Improved boosting algorithms using confidence-rated predictions
[J]. Machine learning, 1999. 37(3): p. 297-336.

[18] Freund, Y. and R.E. Schapire. Experiments with a new boosting algorithm
[C]. in MACHINE LEARNING --INTERNATIONAL WORKSHOP THEN CONFEREN -CE-. 1996. Citeseer.

[19] Lienhart, R., A. Kuranov, and V. Pisarevsky, Empirical analysis of detection cascades of boosted classifiers for rapid object detection
[J]. Pattern Recognition, 2003: p. 297-304.

[20] Marie, E., K. Hoehn, and B. Cleary, Human Anatomy and Physiology
[M]. Science, 1998.

[21] Julier, S., J. Uhlmann, and H.F. Durrant-Whyte, A new method for the nonlinear transformation of means and covariances in filters and estimators
[J]. Automatic Control, IEEE Transactions on, 2000. 45(3): p. 477-482.

[22] Rowley, H.A., S. Baluja, and T. Kanade, Neural network-based face detection
[J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 1998. 20(1): p. 23-38.

[23] Schneiderman, H. and T. Kanade. A statistical method for 3D object detection applied to faces and cars
[C]. in cvpr. 2000. Published by the IEEE Computer Society.

引用本文

余涛*,邹建华^,,徐君,龙卓群. 基于非线性滤波器的多人及多角度的人眼检测和跟踪 [J]. 工程学研究. 2023; 2; (4). 1 - 9.

文献评论

相关学者

相关机构