Building Detection from Pan-Sharpened GeoEye-1 Satellite Imagery Using Context Based Multi-Level Image Segmentation

Abstract

Availability of high resolution satellite imageries has increased its applications in the areas of aerial imageries. Few noted examples are update of GIS database of urban city, change detection and urban monitoring. Building detection is one of the most basic tasks in most of the aforementioned urban applications. This research is focused on automatic building detection from pan-sharpened very high spatial resolution satellite imagery. Building detection results are also used for subsequent evaluation of UNB pansharpening algorithm. The building detection utilizes shadow context, color tone, size, edge features, structural and geometric features, and prior knowledge in a multi-level segmentation based building detection. It first finds shadows using both pixels based and shadow region based analysis. In the next step, multi-resolution segmentation is performed using eCognition software with Sobel edge gradient image and principal component image as additional layers. Then, shadow geometry, according to Sun's azimuth angle, is utilized to detect the positions of buildings. Finally, spurious buildings are eliminated based on prior knowledge of objects which surround the buildings e.g., bare lands and roads. The performance is evaluated by both qualitative and quantitative analysis. The detection results are promising but still need modifications for real applications. Further, it also shows that UNB pansharpening performs well in applications utilizing spectral and spatial features.