Contribution of Normalized DSM to Automatic Building Extraction from HR Mono Optical Satellite Imagery

Abstract

Building extraction from high resolution (HR) satellite imagery is one of the most significant issue for remote sensing community. Manual extraction process is onerous and time consuming that's why the improvement of the best automation is a crucial topic for the researchers. In this study, we aimed to expose the significant contribution of normalized digital surface model (nDSM) to the automatic building extraction from mono HR satellite imagery performing two-step application in an appropriate study area which includes various terrain formations. In first step, the buildings were manually and object-based automatically extracted from ortho-rectified pan-sharpened IKONOS and Quickbird HR imagery that have 1 m and 0.6 m ground sampling distances (GSD), respectively. Next, the nDSM was created using available aerial photos to represent the height of individual non-terrain objects and used as an additional channel for segmentation. All of the results were compared with the reference data, produced from aerial photos that have 5 cm GSD. With the contribution of nDSM, the number of extracted buildings was increased and more importantly, the number of falsely extracted buildings occurred by automatic extraction errors was sharply decreased, both are the main components of precision, completeness and overall quality.