适用于遮挡的网格跟踪算法

Mesh Tracking Algorithm Applied for Occlusion

引入遮挡网络模型的概念 ,提出了一种适用于遮挡的网格跟踪算法 .遮挡区域检测和网格节点运动估计是跟踪算法的关键 .改进的遮挡检测方法可以更加准确检测遮挡区域 ,能有效地提高遮挡及其相邻区域运动估计的准确度 ;采用了基于特征窗口匹配的网格节点运动估计方法 ,有效地避免了块匹配法产生的块效应 .实验证明 ,本文算法可以有效进行运动跟踪 。

The concept of an occlusion mesh model was introduced. A mesh tracking algorithm applied for occlusion was proposed. Occlusion region detection and mesh node motion estimation are the keys of the tracking algorithm. A modified occlusion detection method is considered to improve the detection accuracy. A mesh node motion estimation method based on feature window matching was presented to overcome block artifacts produced by block matching. The experimental results indicate that the proposed algorithm can track objects effectively, and shows better visual performance.