Optimal transport for visual tracking and registration

Optimal transport for visual tracking and registration
复制标题

视觉跟踪和注册的最佳传输

DOI:
10.1109/phycon.2003.1236829
复制
发表时间:
2003
期刊:
2003 IEEE International Workshop on Workload Characterization (IEEE Cat. No.03EX775)
影响因子:
--
通讯作者:
A. Goldstein
A. Goldstein
中科院分区:
--
文献类型:
--
作者:
S. Haker;A. Tannenbaum;A. Goldstein

文献摘要

参考文献

被引文献

相似文献

在这篇文章中,我们考虑了一种解决视觉跟踪问题的重要方面的新方法。存在干扰时的跟踪是一个经典的控制问题,但由于干扰的高度不确定性,此类问题非常困难。许多视觉跟踪任务中的一个关键问题是配准。图像配准是在不同时间拍摄的多个数据集中建立公共几何参考系的过程。我们提出了一种基于最优大众运输的 Monge-Kantorovich 问题的配准方法。我们认为这种方法对于受控主动视觉中的几个问题也非常有用。
In this note, we consider a new method for an important aspect of the visual tracking problem. Tracking in the presence of a disturbance is a classical control issue, but because of the highly uncertain nature of the disturbance, this type of problem is very difficult. A key issue in many visual tracking tasks is that of registration. Image registration is the process of establishing a common geometric reference frame among several data sets taken at different times. We propose a method of registration based on the Monge-Kantorovich problem of optimal mass transport. We argue that such an approach can also be very useful for several problems in controlled active vision.
DOI: 10.1007/pl00001679
发表时间: 2001-01-01
影响因子: 2.2
作者:
McCann, RJ
通讯作者: McCann, RJ