基于Kalman滤波和Mean Shift算法的人眼实时跟踪

REAL TIME EYE TRACKING BASED ON KALMAN FILTER AND MEAN SHIFT ALGORITHM

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.

Nonintrusive methods for eye tracking are important for many applications of vision-besed man-machine interaction, but one common problem to eye tracking methods proposed so far is their sensitivity to lighting condition change, partial occlusion of eye, significant clutter, face scale variations and head rotations in depth, which limit its application scope. In this paper one eye tracking method is proposed that is based on Kalman filter and mean shift algorithm. The experimental results show this method is robustness to those proposed conditions.