Dynamic Graph Cuts and Their Applications in Computer Vision
Dynamic Graph Cuts and Their Applications in Computer Vision
复制标题
动态图割及其在计算机视觉中的应用
DOI：
--
复制
发表时间：
2010
期刊：
影响因子：
--
通讯作者：
Philip H. S. Torr
中科院分区：
文献类型：
--
作者：
Pushmeet Kohli;Philip H. S. Torr
在过去的几年中，能源最小化已成为计算机视觉中必不可少的工具。这种越来越受欢迎的主要原因是在解决许多低级视力问题（例如图像分割，对象重建，图像恢复和差异估计）方面取得了有效的最小化算法的成功。计算机视觉问题的规模和形式引入了能量最小化的许多挑战。在本章中，我们解决了相似函数组的有效和确切最小化的问题，这些函数可在多项式时间内可解决。我们将提出一种新型的动态算法，以最大程度地减少此类功能。该算法从以前的问题实例重新恢复计算，以求解新实例，从而实现了运行时间的大幅改善。我们将介绍这种方法在交互式图像分割，视频中的图像分割，人体姿势估计和分割的问题以及通过最小化能量功能获得的解决方案的不确定性。
Over the last few years energy minimization has emerged as an indispensable tool in computer vision. The primary reason for this rising popularity has been the successes of efficient graph cut based minimization algorithms in solving many low level vision problems such as image segmentation, object reconstruction, image restoration and disparity estimation. The scale and form of computer vision problems introduce many challenges in energy minimization. In this chapter we address the problem of efficient and exact minimization of groups of similar functions which are known to be solvable in polynomial time. We will present a novel dynamic algorithm for minimizing such functions. This algorithm reuses computation from previous problem instances to solve new instances resulting in a substantial improvement in the running time. We will present the results of using this approach on the problems of interactive image segmentation, image segmentation in video, human pose estimation and segmentation, and measuring uncertainty of solutions obtained by minimizing energy functions.