Learning gaze biases with head motion for head pose-free gaze estimation

详细信息    查看全文

• 作者：Feng Lu^a ; ^{lufeng@iis.u-tokyo.ac.jp" class="auth_mail} ; Takahiro Okabe^b ; Yusuke Sugano^a ; Yoichi Sato^a
• 关键词：Gaze estimation ; Free head motion ; Head pose compensation ; Appearance-based approach
• 刊名：Image and Vision Computing
• 出版年：March, 2014
• 年：2014
• 卷：32
• 期：3
• 页码：169-179
• 全文大小：1114 K

文摘

When estimating human gaze directions from captured eye appearances, most existing methods assume a fixed head pose because head motion changes eye appearance greatly and makes the estimation inaccurate. To handle this difficult problem, in this paper, we propose a novel method that performs accurate gaze estimation without restricting the user's head motion. The key idea is to decompose the original free-head motion problem into subproblems, including an initial fixed head pose problem and subsequent compensations to correct the initial estimation biases. For the initial estimation, automatic image rectification and joint alignment with gaze estimation are introduced. Then compensations are done by either learning-based regression or geometric-based calculation. The merit of using such a compensation strategy is that the training requirement to allow head motion is not significantly increased; only capturing a 5-s video clip is required. Experiments are conducted, and the results show that our method achieves an average accuracy of around 3掳 by using only a single camera.