Electrical and Computer Engineering Department, Morgan State University, Baltimore, MD 21251, USA.
IEEE Trans Image Process. 2003;12(12):1495-511. doi: 10.1109/TIP.2003.819237.
Image registration is the process by which we determine a transformation that provides the most accurate match between two images. The search for the matching transformation can be automated with the use of a suitable metric, but it can be very time-consuming and tedious. We introduce a registration algorithm that combines a simple yet powerful search strategy based on a stochastic gradient with two similarity measures, correlation and mutual information, together with a wavelet-based multiresolution pyramid. We limit our study to pairs of images, which are misaligned by rotation and/or translation, and present two main results. First, we demonstrate that, in our application, mutual information may be better suited for sub-pixel registration as it produces consistently sharper optimum peaks than correlation. Then, we show that the stochastic gradient search combined with either measure produces accurate results when applied to synthetic data, as well as to multitemporal or multisensor collections of satellite data. Mutual information is generally found to optimize with one-third the number of iterations required by correlation. Results also show that a multiresolution implementation of the algorithm yields significant improvements in terms of both speed and robustness over a single-resolution implementation.
图像配准是确定两个图像之间最准确匹配的变换的过程。通过使用适当的度量标准，可以自动搜索匹配的变换，但这可能非常耗时和乏味。我们引入了一种注册算法，该算法结合了基于随机梯度的简单而强大的搜索策略以及两种相似性度量，相关性和互信息，以及基于小波的多分辨率金字塔。我们将研究仅限于通过旋转和/或平移而未对准的图像对，并提出两个主要结果。首先，我们证明在我们的应用中，互信息可能更适合亚像素配准，因为它产生的最佳峰值比相关性更清晰。然后，我们表明，当应用于合成数据以及多时相或多传感器卫星数据时，随机梯度搜索与任何一种度量相结合都可以产生准确的结果。互信息通常需要比相关性少三分之一的迭代次数即可达到最佳状态。结果还表明，与单分辨率实现相比，算法的多分辨率实现可在速度和鲁棒性方面获得显著提高。
