基于Kalman滤波和Mean Shift算法的人眼实时跟踪

被引:5
作者
陈艳琴
罗大庸
机构
[1] 中南大学信息科学与工程学院
关键词
眼睛定位; 眼睛跟踪; Kalman滤波; Mean Shift算法;
D O I
暂无
中图分类号
TP391.41 [];
学科分类号
080203 ;
摘要
非接触式的人眼跟踪方法在一些基于视觉的人机交互应用中具有很重要的意义.但目前的人眼跟踪方法普遍存在着诸如对眼睛的部分遮挡、人脸尺度变化和头部的深度旋转等过于敏感的不足,这就极大地限制了其应用范围.本文提出了一种综合运用Kalman滤波和Mean shift算法的人眼跟踪算法,实验结果验证了该算法对于上面所提到的不足情况具有较强的鲁棒性.
引用
收藏
页码:173 / 177
页数:5
相关论文
共 8 条
[1]  
Detecting and Tracking Eyes by Using Their Physiological Properties, Dynamics, and Appearance. Haro A,Flickner M,Essa I. Proc of the IEEE Conference on Computer Vision and Pattern Recognition . 2000
[2]  
The Quality of Training Sample Estimates of the Bhattacharyya Coefficient. Djouadi A,Snorrason O,Garber F D. IEEE Trans on Pattern Analysis and Machine Intelligent . 1990
[3]  
Mean shift and optimal prediction for efficient object tracking. Comaniciu Dorin,Ramesh Visvanathan. IEEE International Conference on Image Processing . 2000
[4]  
Real-time tracking of non-rigid objects using mean shift. Dorin Comaniciu,Visvanathan Ramesh,Peter Meer. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition . 2000
[5]  
Realtime Detection of Eyes and Faces. Morimoto C,,Koons D,Amir A,Flickner M. Proc of the International Workshop on Percep-tual User Interfaces . 1998
[6]  
Real Time Visual Cues Extraction for Monitoring Driver Vigilance. Ji Q,,Yang X. Proc of the International Workshop on Computer Vision Systems . 2001
[7]  
Color-based tracking of headsand other mobile objects at video frame rates. Fieguth P,,Terzopoulos D. Proc.ofthe IEEE VCPR . 1997
[8]  
The Divergence and Bhattacharyya Distance Measures in Signal Selection. Kailath T. IEEE Transactions on Communication Technology . 1967