閱讀全文 | |
篇名 |
Appearance Based Gaze Estimation Using Eye Region Landmarks and Math Approach
|
---|---|
並列篇名 | Appearance Based Gaze Estimation Using Eye Region Landmarks and Math Approach |
作者 | Shichao Cheng、Bocheng Zhang、Jianjun Li、Zheng Tang、Korhan Cengiz |
英文摘要 | The gaze direction can be defined by the pupil and the center of the eyeball, the latter cannot be observed in the 2D image, which can cause ill-posed problems and cannot achieve highly accurate gaze estimation. Therefore, we try to extract several effective landmarks around the eyeball and iris from the monocular input for gaze estimation. Instead of directly returning the two angles for the pitch and yaw of the eyeball, we return to an intermediate graphical representation, which in turn simplifies the task of 3D gaze estimation. We try to use a novel learningbased method to locate the landmarks of an eyeball with the appearance-based method. Through these highaccuracy feature points, we have proposed a new and effective formula for drawing more accurate gaze directions. As for the individual gaze estimation of independent people, our method is superior to existing model fitting and appearance-based methods. |
起訖頁 | 1717-1724 |
關鍵詞 | Gaze estimation、Convolutional neural network、Mathematical method |
刊名 | 網際網路技術學刊 |
期數 | 202011 (21:6期) |
出版單位 | 台灣學術網路管理委員會 |
DOI |
|
QR Code | |
該期刊 上一篇
| An Improved Cellular Automata-Based Classifier with Soft Decision |
該期刊 下一篇
| Online Handwritten Verification Algorithms Based on DTW and SVM |