| 基于高斯过程的表情运动单元跟踪技术 |
| |
| 引用本文： | 王磊,邹北骥,彭小宁,潘丽丽.基于高斯过程的表情运动单元跟踪技术[J].电子学报,2007,35(11):2087-2091. |
| |
| 作者姓名： | 王磊 邹北骥 彭小宁 潘丽丽 |
| |
| 作者单位： | 1. 湖南大学计算机与通信学院,湖南长沙 410082;2. 中南大学信息科学与工程学院,湖南长沙 410083;3. 浙江大学计算机辅助设计与图形学国家重点实验室, 浙江杭州 310058 |
| |
| 摘 要： | 在表情动作单元的跟踪中有两个常见问题:一是跟踪结果有小幅而频繁的抖动;二是跟踪过程会产生难以检测的误差.针对这两个问题,本文提出了一种基于高斯过程和粒子滤波的表情动作单元跟踪技术.实验结果表明本文算法比传统的梯度优化和粒子滤波法具有更好的平滑性和跟踪精度,而精度的优势在头部有偏转的情况下尤为突出.
|
| 关 键 词： | 表情动作单元跟踪 梯度优化 粒子滤波 高斯过程 |
| 文章编号： | 0372-2112（2007）11-2087-05 |
| 收稿时间： | 2007-01-31 |
| 修稿时间： | 2007-05-30 |
Facial Tracking by Gaussian Process |
| |
| WANG Lei,ZOU Bei-ji,PENG Xiao-ning,PAN Li-li.Facial Tracking by Gaussian Process[J].Acta Electronica Sinica,2007,35(11):2087-2091. |
| |
| Authors: | WANG Lei ZOU Bei-ji PENG Xiao-ning PAN Li-li |
| |
| Institution: | 1. School of Computer and Communication,Hunan University,Changsha,Hunan 410082,China;2. School of Information Science & Engineering,Central South University,Changsha,Hunan 410083,China;3. State Key Laboratory of CAD & CG,Zhejiang University,Hangzhou,Zhejiang 310058,China |
| |
| Abstract: | Facial Action Units(FAU)tracking is a hard problem for the rigid and non-rigid transformations of human face. The constantly trembling in the tracking result and the tracking failures caused by the absence of constraint remain open problems. This paper presents a novel method to attack these problems by combining Gaussian Process and Particle Filtering.Gradient-based method and particle filtering based method are compared with our method and the experiment results are encouraging. |
| |
| Keywords: | FAU tracking gradient optimization particle filtering Gaussian process |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
| 点击此处可从《电子学报》浏览原始摘要信息 |
| 点击此处可从《电子学报》下载免费的PDF全文 |
|
