Toward designing intelligent PDEs for computer vision: An optimal control approach

Toward designing intelligent PDEs for computer vision: An optimal control approach
复制标题

为计算机视觉设计智能偏微分方程:一种最优控制方法

DOI:
10.1016/j.imavis.2012.09.004
复制
发表时间:
2011-09
影响因子:
4.7
通讯作者:
Su, Zhixun
Su, Zhixun
中科院分区:
计算机科学3区
文献类型:
--
作者:
Lin, Zhouchen;Zhang, Wei;Tang, Kewei;Su, Zhixun

文献摘要

参考文献

被引文献

相似文献

许多计算机视觉和图像处理问题可以归结为求解偏微分方程(PDE)。然而,设计PDE系统通常需要很高的数学技能和对问题的良好洞察力。在本文中,我们考虑以一种懒惰的方式为计算机视觉和图像处理中出现的各种问题设计偏微分方程:通过最优控制方法从训练数据中学习偏微分方程。我们首先提出了一个通用的智能PDE系统,它拥有大多数视觉问题的基本平移和旋转不变性规则。通过引入PDE约束的最优控制框架,可以使用多种方式产生的训练数据(地面实况,其他方法的结果和人类的手动结果)来学习不同计算机视觉任务的PDE。所提出的基于最优控制的训练框架旨在学习基于偏微分方程的回归器来近似不同视觉任务的未知(通常是非线性)映射。实验结果表明,学习的偏微分方程可以合理地解决不同的视觉问题。特别是,我们不仅可以获得传统偏微分方程工作良好的问题,而且还可以获得基于偏微分方程的方法从未尝试过的问题,由于难以用数学方式描述这些问题。
Many computer vision and image processing problems can be posed as solving partial differential equations (PDEs). However, designing a PDE system usually requires high mathematical skills and good insight into the problems. In this paper, we consider designing PDEs for various problems arising in computer vision and image processing in a lazy manner: learning PDEs from training data via an optimal control approach. We first propose a general intelligent PDE system which holds the basic translational and rotational invariance rule for most vision problems. By introducing a PDE-constrained optimal control framework, it is possible to use the training data resulting from multiple ways (ground truth, results from other methods, and manual results from humans) to learn PDEs for different computer vision tasks. The proposed optimal control based training framework aims at learning a PDE-based regressor to approximate the unknown (and usually nonlinear) mapping of different vision tasks. The experimental results show that the learnt PDEs can solve different vision problems reasonably well. In particular, we can obtain PDEs not only for problems that traditional PDEs work well but also for problems that PDE-based methods have never been tried before, due to the difficulty in describing those problems in a mathematical way.
DOI: 10.1137/0727053
发表时间: 1990-08-01
影响因子: 2.9
作者:
OSHER, S;RUDIN, LI
通讯作者: RUDIN, LI
DOI: 10.1007/978-3-642-15549-9_9
发表时间: 2010-09
影响因子: 2.4
作者:
Risheng Liu;Zhouchen Lin;Wayne Zhang;Zhixun Su
通讯作者: Risheng Liu;Zhouchen Lin;Wayne Zhang;Zhixun Su
DOI: 10.1109/tip.2004.838697
发表时间: 2005-02
影响因子: 10.6
作者:
D. D. Muresan-D.;T. Parks
通讯作者: D. D. Muresan-D.;T. Parks
DOI: 10.1109/34.868688
发表时间: 2000-08-01
影响因子: 23.6
作者:
Shi, JB;Malik, J
通讯作者: Malik, J
DOI: 10.1016/0167-2789(92)90242-f
发表时间: 1992-11-01
期刊: PHYSICA D
影响因子: 4
作者:
RUDIN, LI;OSHER, S;FATEMI, E
通讯作者: FATEMI, E