Spatial content-based scene matching using a relaxation method

Scene matching is a fundamental task for a variety of geospatial analysis applications. In this context, features extracted from vector data contain no intensity information which typically is the significant component in current promising approaches for registration. This dissertation developed a novel methodology for automatic image-to-vector matching, based on contextual information among salient spatial features in a scene. It is important to develop attributes that need less computational efforts, while having sufficient descriptive power. This paper integration enables achieving matching under perplexing scenario where the structure of each intersection in networks is identical.