基于AAM和T型结构的人脸3D姿态估计  

3D face pose estimation method based on active appearance model and T-structure

作　　者：刘春生[1] 常发亮[1] 陈振学[1] 李爽[1] 

机构地区：[1]山东大学控制科学与工程学院,济南250061

出　　处：《计算机工程与应用》2012年第25期163-167,共5页Computer Engineering and Applications

基　　金：国家自然科学基金(No.60975025);山东省自然科学基金(No.ZR2011FM032);教育部留学回国人员科研启动基金

摘　　要：在分析已有的人脸姿态估计方法基础上,提出了一种基于主动表观模型(AAM)和T型结构的人脸3D姿态估计方法。对多姿态的人脸样本进行训练,得到多姿态的AAM模板集;利用训练得到的多姿态的AAM模板集进行最佳模板匹配,并对人脸的特征点进行精确定位;用人脸的双眼和嘴部构建T型模型,进行人脸3D姿态的参数估计。实验结果表明,该方法能适应较大的姿态旋转角度,并具有良好的姿态估计精度。Based on analysis of the pro-existing face pose estimation methods, a new 3D face pose estimation method based on Active Appearance Model （AAM） and T-structure is proposed. A set of AAM models can be obtained after training different poses faces. Then, the objective face is matched with the set of AAM models, to choose the opti- mum model to accurate position of the face characteristic points. The T-structure is built with the two eyes and the mouth, which is used to estimate the face pose. The experiments show that the method can be adopted to large rotation angles, and can reach a good accuracy of 3D face pose estimation.

关 键 词：主动表观模型 人脸姿态估计 特征点定位 T形结构 人脸检测 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]