Object-based image analysis based on a region-line primitive association framework

Abstract

The current study introduces a region-line primitive association framework (RLPAF) for OBIA. Regions and lines are used collaboratively from low-level image processing (segmentation) and feature extraction to high-level image analysis (classification and recognition). Several region-line associating techniques for analysing object shapes and relationships were designed. Our techniques have been validated by impervious surface and road network extraction from high spatial resolution (HSR) images.