Keypoint-Based Gaze Tracking
Keypoint-Based Gaze Tracking
复制标题
DOI：
10.1007/978-3-030-68790-8_12
复制
发表时间：
2020
期刊：
影响因子：
--
通讯作者：
Paris Her;Logan Manderle;P. Dias;Henry Medeiros;F. Odone
中科院分区：
文献类型：
--
作者：
Paris Her;Logan Manderle;P. Dias;Henry Medeiros;F. Odone
有效的辅助生活环境必须能够对居住者如何与环境相互作用进行推断。凝视方向提供了人们如何与周围环境互动的有力指示。在本文中，我们提出了一种凝视跟踪方法，该方法使用神经网络回归器从关键点估计凝视，并使用移动平均机制随时间集成它们。我们的凝视回归模型使用置信度门控单元来处理关键点遮挡的情况，并估计其自身的预测不确定性。我们的注视跟踪的时间方法将这些预测不确定性作为移动平均方案的权重。在辅助生活设施中收集的数据集上的实验结果表明，我们的凝视回归网络与复杂的数据集特定基线相当，而其不确定性预测与相应估计的实际角度误差高度相关。最后，对视频序列的实验表明，我们的时间方法产生了更准确和稳定的凝视预测。
Effective assisted living environments must be able to perform inferences on how their occupants interact with their environment. Gaze direction provides strong indications of how people interact with their surroundings. In this paper, we propose a gaze tracking method that uses a neural network regressor to estimate gazes from keypoints and integrates them over time using a moving average mechanism. Our gaze regression model uses confidence gated units to handle cases of keypoint occlusion and estimate its own prediction uncertainty. Our temporal approach for gaze tracking incorporates these prediction uncertainties as weights in the moving average scheme. Experimental results on a dataset collected in an assisted living facility demonstrate that our gaze regression network performs on par with a complex, dataset-specific baseline, while its uncertainty predictions are highly correlated with the actual angular error of corresponding estimations. Finally, experiments on videos sequences show that our temporal approach generates more accurate and stable gaze predictions.