Spatial relationship-assisted classification from high-resolution remote sensing imagery

Spatial information remains to be an important topic in geographic information system and in remote sensing fields, and spatial relationships have been increasingly incorporated into the image classification processes. Previous studies have employed multiple occurrences of spatial features (shape, texture, etc.,) to improve classification results. However, less attention has been focused on using higher-level spatial relationships for image classification. In this study, two novel spatial relationships, namely, maximum spatial adjacency (MSA) and directional spatial adjacency (DSA), were proposed to assist in image classification. The proposed methods were implemented to extract buildings, beach, and emergent vegetation land-cover classes according to their spatial relationships with their corresponding reference classes. The promising results obtained from this study suggest that the proposed MSA and DSA spatial relationships can be valuable information in defining rule sets for a more reasonable and accurate classification.