.png){kind=icon}
返回
Simultaneous higher-order optical flow estimation and decomposition
.png){kind=icon}
OA
AI
DOI：10.1137/060660709.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
We study the estimation and decomposition of optical flows from highly nonrigid motions. To this end, recent methods from image decomposition into structural and textural parts are combined with variational optical flow estimation. The approaches we suggest amount to minimizing discrete convex functionals using second-order cone programming. Higher-order regularization is necessary in order to accurately recover important flow structure like vortices, and to incorporate key physical properties such as vanishing divergence. For proper discretization, we apply the finite mimetic difference method, which preserves the identities fulilled by the continuous differential operators. Numerical examples demonstrate the feasibility of the complex approaches.
Keyword:
optical flow estimation
optical flow decomposition
divergence-free flows
higher-order regularization
mimetic finite difference method
convex optimization
dual optimization techniques
second-order cone programming
期刊
IF:
2.6
论文数:
5.1K
被引数:
1.8W
机构
暂无机构信息
引用论文
.png){kind=icon}
Simulation of alternatives for the Dutch Johne’s disease certification-and-monitoring program荷兰约翰氏病认证和监测计划的替代方案的模拟
PREAI
分享收藏Structure-texture image decomposition - Modeling, algorithms, and parameter selection结构-纹理图像分解-建模、算法和参数选择
PREAI
分享收藏分享收藏
查看更多内容