中文摘要：

提出一种基于KINECT的视线方向估测方法,通过KINECT获取人脸图像数据及人脸网格信息,检测和消除人眼区域的光斑,进而利用人眼灰度分布特点对瞳孔进行粗定位得到瞳孔中心;通过计算眼睛参考点与瞳孔中心形成的距离和其连线与坐标轴形成的角度关系对视线方向进行分类处理,完成视线方向的估测。实验结果表明所提出的方法在低分率的图像条件下能准确地估测出人眼视线方向。

英文摘要：

This paper proposes an eye gaze direction estimation method based on KINECT. The process of the estimation method includes getting face image and face grid information through KINECT, detecting and eliminating spots around the eye area, utilizing the gray - scale distribution characteristics of the human eyes to roughly position the pupil and then get the pupil center, classifying and processing the sight directions by calculating formulated distance from the eye reference point to the pupil center and the angle relationship formed by this distance connection and coordinate axis to complete the eye gaze direction estimation. The experimental results show that the proposed method can accurately assess the human eye gaze direction under the condition of the low rate of image.