Abstract
Geographic entity matching is an important means for multi-source spatial data fusion and information association and sharing. Corresponding matching methods have been designed by existing studies for different types of entity data characteristics, such as line and area. However, these approaches are often limited in the generalization ability for matching heterogeneous data from multiple sources and the accuracy for complex pattern matching. To resolve these problems, a robust geographic entity matching method by maximizing the geometric and semantic similarity of feature arcs is proposed. First, the entire entity is segmented based on shape features, and the partitioned feature arcs are extracted as matching primitives; Second, feature arcs are grouped into patterns, encompassing three major categories and 14 subcategories; Following this, pattern matching is performed based on spatial similarity metric such as maximum projection distance, etc.; Finally, the spatial matches are detected and refined through semantic similarity calculation. The proposed method is tested using two datasets from a region in southeast China. The experimental results demonstrate that our method can be effectively applied to both area and line entity matching. Specifically, 9 different strategies for matching area entities and 6 for line entities are utilized, and the precision and recall are almost above 90%.