Fitting 3D face models for tracking and active appearance model training
Fitting 3D face models for tracking and active appearance model training
复制标题
DOI：
10.1016/j.imavis.2006.02.025
复制
发表时间：
2006-09-01
影响因子：
4.7
通讯作者：
Ahlberg, Jorgen
中科院分区：
文献类型：
--
作者：
Dornaika, Fadi;Ahlberg, Jorgen
在本文中，我们考虑拟合一个三维可变形的人脸模型，连续的视频序列的跟踪和训练的任务。我们提出了两种基于外观的方法，只需要一个简单的统计面部纹理模型，不需要任何信息的经验或分析梯度矩阵，因为最好的搜索方向估计的飞行。第一种方法使用局部穷举和定向搜索来计算拟合，其中同时估计3D头部姿势和面部动作。第二种方法简化了这些参数的估计。它使用一个强大的基于特征的姿态估计器，结合面部纹理一致性措施计算的3D头部姿态。然后，它估计的面部动作与穷举和定向搜索。拟合和跟踪实验验证了所提出方法的可行性和有效性。性能评估也表明，所提出的方法可以优于拟合的基础上采用预先计算的梯度矩阵的主动外观模型搜索。虽然所提出的计划是不一样快的计划，采用定向连续搜索，他们可以解决许多与这种方法相关的缺点。(c)2006 Elsevier B.V.保留所有权利。
In this paper, we consider fitting a 3D deformable face model to continuous video sequences for the tasks of tracking and training. We propose two appearance-based methods that only require a simple statistical facial texture model and do not require any information about an empirical or analytical gradient matrix, since the best search directions are estimated on the fly. The first method computes the fitting using a locally exhaustive and directed search where the 3D head pose and the facial actions are simultaneously estimated. The second method decouples the estimation of these parameters. It computes the 3D head pose using a robust feature-based pose estimator incorporating a facial texture consistency measure. Then, it estimates the facial actions with an exhaustive and directed search. Fitting and tracking experiments demonstrate the feasibility and usefulness of the developed methods. A performance evaluation also shows that the proposed methods can outperform the fitting based on an active appearance model search adopting a pre-computed gradient matrix. Although the proposed schemes are not as fast as the schemes adopting a directed continuous search, they can tackle many disadvantages associated with such approaches. (c) 2006 Elsevier B.V. All rights reserved.