期刊名称：ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
印刷版ISSN：2194-9042
电子版ISSN：2194-9050
出版年度：2005
卷号：XXXVI-8/W27
出版社：Copernicus Publications
摘要：Image registration is one of the important image processing procedures in remote sensing; it has been studied and developed for a long time. However, until now, it is still rare to find an accurate, robust, and automatic image registration method, and most existing image registration methods are designed for particular application. At present, high resolution remote sensing images have made it more convenient for people to study the earth; however, they also bring some challenges for the traditional research methods. In terms of image registration, there are some problems with using current image registration techniques for high resolution images, namely: (a) precisely locating control points is not as simple as with moderate resolution images; (b) manually selecting the large number of control points required for precise registration is tedious and time consuming; (c) high data volume will adversely affect the processing speed in the image registration; and (d) local geometric distortion can not be removed very well using traditional image registration methods even with enough control points. Based on these reasons, the need for an image registration approach that will resolve these problems is urgent. This paper proposes a new automated image registration technique, which is based on the combination of feature-based and area-based matching. Wavelet-based feature extraction technique and relaxation-based image matching technique are employed in this research. Local distortions caused by terrain relief can be greatly reduced in this procedure. IKONOS and QuickBird data are used to evaluate this technique
关键词：image matching; wavelet decomposition; image registration; least square
