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：2008
卷号：XXXVII Part B4
页码：193-198
出版社：Copernicus Publications
摘要：Geospatial analysis is becoming increasingly dependent on the integration of data from heterogeneous sources. In this paper, we present an automated, feature-based approach for geometric co-registration using networks of roads (or other similar features). This approach is based on a graph matching scheme that models networks as graphs with embedded invariant attributes. The main advantages of our approach reside in its ability of using both geometric and topological attributes to reduce the ambiguity in search space for inexact matching as well as its invariance to translation, rotation and scale differences (through the use of appropriate attributes). Furthermore, our approach requires no user-defined threshold to justify local matches. Using the information derived from this matching process, the registration of two datasets can be accomplished
