Dedeoglu Göksel, Kanade Takeo, Baker Simon
Robotics Institute, Carnegie Mellon University, Pittsburgh, PA 15213, USA.
IEEE Trans Pattern Anal Mach Intell. 2007 May;29(5):807-23. doi: 10.1109/TPAMI.2007.1054.
Most image registration problems are formulated in an asymmetric fashion. Given a pair of images, one is implicitly or explicitly regarded as a template and warped onto the other to match as well as possible. In this paper, we focus on this seemingly arbitrary choice of the roles and reveal how it may lead to biased warp estimates in the presence of relative scaling. We present a principled way of selecting the template and explain why only the correct asymmetric form, with the potential inclusion of a blurring step, can yield an unbiased estimator. We validate our analysis in the domain of model-based face tracking. We show how the usual Active Appearance Model (AAM) formulation overlooks the asymmetry issue, causing the fitting accuracy to degrade quickly when the observed objects are smaller than their model. We formulate a novel, "resolution-aware fitting" (RAF) algorithm that respects the asymmetry and incorporates an explicit model of the blur caused by the camera's sensing elements into the fitting formulation. We compare the RAF algorithm against a state-of-the-art tracker across a variety of resolutions and AAM complexity levels. Experimental results show that RAF significantly improves the estimation accuracy of both shape and appearance parameters when fitting to low-resolution data. Recognizing and accounting for the asymmetry of image registration leads to tangible accuracy improvements in analyzing low-resolution imagery.
大多数图像配准问题是以一种不对称的方式来表述的。给定一对图像，其中一幅图像被隐含地或明确地视为模板，并被扭曲到另一幅图像上以尽可能地匹配。在本文中，我们关注这种看似随意的角色选择，并揭示在存在相对缩放的情况下，它是如何导致扭曲估计出现偏差的。我们提出了一种选择模板的原则性方法，并解释了为什么只有正确的不对称形式（可能包括模糊步骤）才能产生无偏估计器。我们在基于模型的面部跟踪领域验证了我们的分析。我们展示了通常的主动外观模型（AAM）公式是如何忽略不对称问题的，当观察到的物体小于其模型时，会导致拟合精度迅速下降。我们制定了一种新颖的“分辨率感知拟合”（RAF）算法，该算法考虑了不对称性，并将由相机传感元件引起的模糊的显式模型纳入拟合公式中。我们在各种分辨率和AAM复杂度水平下，将RAF算法与一种先进的跟踪器进行了比较。实验结果表明，在拟合低分辨率数据时，RAF显著提高了形状和外观参数的估计精度。认识到并考虑图像配准的不对称性会在分析低分辨率图像时带来切实的精度提升。
