Automatic rectangular building detection from VHR aerial imagery using shadow and image segmentation

This paper introduces a novel approach for the automated detection of rectangular buildings from monocular very high resolution (VHR) aerial images. The overall idea of this work is first to decompose the image into small homogeneous regions and treat all regions as candidates. According to the position of the shadows, a merging process is then performed over regions having similar spectral characteristics to produce building regions whose shapes are appropriate to rectangles. The experimental results prove that the proposed method is applicable in various areas (high dense urban, suburban, and rural) and is highly robust and reliable.