Lucas-Kanade 20 Years On: A Unifying Framework: Part 3
Lucas-Kanade 20 Years On: A Unifying Framework: Part 3
复制标题
DOI：
--
复制
发表时间：
2004
影响因子：
19.5
通讯作者：
Simon Baker;Ralph Gross;I. Matthews
中科院分区：
文献类型：
--
作者：
Simon Baker;Ralph Gross;I. Matthews
自1981年Lucas-Kanade算法提出以来，图像对齐已成为计算机视觉中应用最广泛的技术之一。应用范围从光流、跟踪和分层运动到马赛克构造、医学图像配准和人脸编码。已经提出了许多算法，并对原始公式进行了各种扩展。我们提出了图像对齐的概述，在一致的框架中描述了大多数算法。我们将重点介绍逆组合算法，这是我们最近提出的一种高效算法。我们研究了Lucas-Kanade算法的哪些扩展可以与逆组合算法一起使用而不会造成任何显著的效率损失，哪些不能。在本文（系列论文的第3部分）中，我们将介绍图像对齐的扩展，以允许线性外观变化。当误差函数为欧氏L2范数时，我们首先考虑线性外观变化。我们描述了三种不同的算法，即同步、投影和归一化逆组合算法，并对它们进行了经验比较。然后，我们考虑线性外观变化与本系列第2部分中描述的鲁棒误差函数的组合。我们首先推导出同步和归一化算法的鲁棒版本。由于这两种算法都非常低效，因此在第2部分中，我们将基于空间相干性推导出有效的近似。最后，我们对鲁棒算法进行了实证评估。
Since the Lucas-Kanade algorithm was proposed in 1981 image alignment has become one of the most widely used techniques in computer vision. Applications range from optical flow, tracking, and layered motion, to mosaic construction, medical image registration, and face coding. Numerous algorithms have been proposed and a variety of extensions have been made to the original formulation. We present an overview of image alignment, describing most of the algorithms in a consistent framework. We concentrate on the inverse compositional algorithm, an efficient algorithm that we recently proposed. We examine which of the extensions to the Lucas-Kanade algorithm can be used with the inverse compositional algorithm without any significant loss of efficiency, and which cannot. In this paper, Part 3 in a series of papers, we cover the extension of image alignment to allow linear appearance variation. We first consider linear appearance variation when the error function is the Euclidean L2 norm. We describe three different algorithms, the simultaneous, project out, and normalization inverse compositional algorithms, and empirically compare them. Afterwards we consider the combination of linear appearance variation with the robust error functions described in Part 2 of this series. We first derive robust versions of the simultaneous and normalization algorithms. Since both of these algorithms are very inefficient, as in Part 2 we derive efficient approximations based on spatial coherence. We end with an empirical evaluation of the robust algorithms.