Dense Optical Flow Estimation from the Monogenic Curvature Tensor
Dense Optical Flow Estimation from the Monogenic Curvature Tensor
复制标题
单基曲率张量的密集光流估计
DOI：
10.1007/978-3-540-72823-8_21
复制
发表时间：
2007
期刊：
影响因子：
3.3
通讯作者：
G. Sommer
中科院分区：
文献类型：
--
作者：
D. Zang;Lennart Wietzke;Christian Schmaltz;G. Sommer
在本文中，我们解决的主题估计两帧稠密光流从单演曲率张量。单演曲率张量是一种新的图像模型，它可以在多尺度下获得图像结构的局部相位。我们适应结合本地和全球（CLG）光流估计方法，我们的框架。以这种方式，强度约束方程被局部相位矢量信息代替。研究了光照变化条件下的光流估计问题。实验结果表明，我们的方法给出了准确的估计，并对噪声污染具有鲁棒性。与基于强度的方法相比，该方法在亮度变化下的流场估计中表现出更好的性能。
In this paper, we address the topic of estimating two-frame dense optical flow from the monogenic curvature tensor. The monogenic curvature tensor is a novel image model, from which local phases of image structures can be obtained in a multi-scale way. We adapt the combined local and global (CLG) optical flow estimation approach to our framework. In this way, the intensity constraint equation is replaced by the local phase vector information. Optical flow estimation under the illumination change is investigated in detail. Experimental results demonstrate that our approach gives accurate estimation and is robust against noise contamination. Compared with the intensity based approach, the proposed method shows much better performance in estimating flow fields under brightness variations.
登记。
DOI：
10.1007/978-1-4939-7647-8_1
发表时间：
2018
期刊：
Neuromethods
影响因子：
--
作者：
Joshi,AnandA
通讯作者：
Joshi,AnandA