基于三维模型和深度灰度约束加权的人脸姿态跟踪

Face Pose Tracking with 3D Model and Weighted Depth and Brightness Constraints

提出一种基于人脸三维模型和深度灰度约束加权对单目视频图像序列中的人脸空间姿态进行跟踪的方法.首先用仿射变换的方法得到初始帧的人脸姿态参数并作为姿态跟踪的起点;然后用三维几何信息对线性灰度和深度约束方程加权得到更精确的帧间运动参数,为了消除光照变化和遮蔽的影响,在跟踪过程中逐帧自动进行特征点更新.对模特头像和真实人脸的实验结果表明:该方法能实现精确而可靠的姿态跟踪,特别对深度方向变化较大的运动,效果更为明显.

This paper proposes a robust method of tracking human head poses from a sequence of monocular images. First we estimate the head pose parameters in the first frame by an affine correspondence based method. Then linear brightness and depth constraint equations are derived from the small interframe rigid motion assumption. At the same time, we use a 3D head model to provide depth measurements and take advantage of geometry information of the features on the face surface to weight the brightness and depth constraints and refine the results. Finally, in order to remove the effects of gradual lighting changes and occlusions, we estimate the reliability of the features frame by frame and dynamically update the reliable feature set. Experiments show that the proposed method can robustly track the head poses even for heads moving with large depth changes.