Head pose free 3D gaze estimation using RGB-D camera

Head pose free 3D gaze estimation using RGB-D camera
复制标题

使用 RGB-D 相机进行头部姿势自由 3D 凝视估计

DOI:
10.1117/12.2266091
复制
发表时间:
2017
影响因子:
5.2
通讯作者:
J. Royan
J. Royan
中科院分区:
计算机科学1区
文献类型:
--
作者:
Amine Kacete;R. Séguier;M. Collobert;J. Royan

文献摘要

被引文献

相似文献

在本文中,我们提出了一种方法,在头部姿态变化的RGB-D相机的三维视线估计。我们的方法使用3D眼睛模型来确定3D光轴并推断3D视轴。为此,我们鲁棒地估计用户头部姿势参数和眼睛瞳孔位置与一个重要的注释训练集训练的随机树的集合。在使用传感器固有参数在传感器坐标系中投影瞳孔位置以及通过在不同方向下注视已知3D目标进行一次性简单校准之后,针对特定用户确定双眼的3D眼球中心,从而确定视轴。实验结果表明,我们的方法显示出良好的凝视估计精度,即使环境是高度不受约束的,即大的用户传感器距离(> 1 m50),而不是处理相对较小的距离(<1 m)的最先进的方法。
In this paper, we propose an approach for 3D gaze estimation under head pose variation using RGB-D camera. Our method uses a 3D eye model to determine the 3D optical axis and infer the 3D visual axis. For this, we estimate robustly user head pose parameters and eye pupil locations with an ensembles of randomized trees trained with an important annotated training sets. After projecting eye pupil locations in the sensor coordinate system using the sensor intrinsic parameters and a one-time simple calibration by gazing a known 3D target under different directions, the 3D eyeball centers are determined for a specific user for both eyes yielding the determination of the visual axis. Experimental results demonstrate that our method shows a good gaze estimation accuracy even if the environment is highly unconstrained namely large user-sensor distances (> 1m50) unlike state-of-the-art methods which deal with relatively small distances (<1m).