Feature-Assisted Dense Spatio-temporal Reconstruction from Binocular Sequences
Feature-Assisted Dense Spatio-temporal Reconstruction from Binocular Sequences
复制标题
DOI：
10.1007/978-3-642-19282-1_35
复制
发表时间：
2010-11
期刊：
影响因子：
--
通讯作者：
Yihao Zhou;Y. Chen
中科院分区：
文献类型：
--
作者：
Yihao Zhou;Y. Chen
在本文中，一个动态的表面表示为一个三角形网格与密集的顶点，其三维位置随时间变化。这些随时间变化的位置通过在由两个校准和同步的摄像机捕获的图像中找到它们对应的投影来重建。为了实现跨视图和帧的精确密集对应，我们首先匹配稀疏特征点，并依靠它们来提供良好的初始化和优化密集对应的强约束。时空一致性被用于特征和图像点的匹配。三个协同约束，图像相似性，核几何和运动线索，联合使用，同时优化立体和时间的对应关系。自动处理由于自遮挡或大的外观变化而导致的跟踪失败。实验结果表明，该方法可以成功地重建织物和皮肤等动态表面的复杂形状和运动。
In this paper, a dynamic surface is represented by a triangle mesh with dense vertices whose 3D positions change over time. These time-varying positions are reconstructed by finding their corresponding projections in the images captured by two calibrated and synchronized video cameras. To achieve accurate dense correspondences across views and frames, we first match sparse feature points and rely on them to provide good initialization and strong constraints in optimizing dense correspondence. Spatio-temporal consistency is utilized in matching both features and image points. Three synergistic constraints, image similarity, epipolar geometry and motion clue, are jointly used to optimize stereo and temporal correspondences simultaneously. Tracking failure due to self-occlusion or large appearance change are automatically handled. Experimental results show that complex shape and motion of dynamic surfaces like fabrics and skin can be successfully reconstructed with the proposed method.