基于眼角精确定位的视线估计

Eye Gaze Estimation Based on Accurate Location of Eye Corner

设计了一个单摄像机、单红外光源的视线估计系统.利用了眼角的位置信息,提出了利用USM锐化粗定位和Gabor眼角滤波器精确定位的两步定位眼角的方法;针对传统的利用瞳孔普尔钦斑点向量进行多项式拟合在头部运动时估计精度下降的问题,提出了利用内眼角间距对普尔钦斑点向量进行矫正,并采用支持向量回归建立眼部特征参数与多项式拟合误差之间的关系,进行误差补偿;结合精确定位的眼角位置,建立了二维眼部特征与屏幕坐标之间的映射关系.实验表明,该方法实现了一定范围内头部自由运动下精确的视线估计.

A gaze estimation system based on a single camera and IR light was proposed. The eye comers＇ location was used in this paper, and a two-step eye comer locating method combining USM coarse positioning with fine positioning by Gabor eye comer filter was presented. To solve the problem that the accuracy of traditional use of pupil-Purkinje image vector for polynomial fitting decreases when head moves, the vector was corrected by using the distance of inner eye comers, and the error was compensated by using the support vector regression to build the relationship between eye characteristic parameters and the polynomial error. Combined with the accurate location of eye comers, the relationship between 2D features around the eye and the screen coordinates was built based on the designed system. Experimental results showed that the accurate eye gaze estimation within a certain range of head movement could be realized with the proposed system.