PROJECT TITLE :

Automatic Building Detection From High-Resolution Satellite Images Based on Morphology and Internal Gray Variance

ABSTRACT:

Automatic building extraction remains an open research topic in digital photogrammetry and remote sensing. While several algorithms have been proposed for building extraction, none of them solve the problem utterly. This is often even a bigger challenge in urban areas, because of high-object density and scene complexity. Customary approaches don't achieve satisfactory performance, particularly with high-resolution satellite pictures. This paper presents a novel framework for reliable and correct building extraction from high-resolution panchromatic pictures. Proposed framework exploits the domain data (spatial and spectral properties) concerning the character of objects within the scene, their optical interactions and their impact on the ensuing image. The steps in the approach contains one) directional morphological enhancement; 2) multiseed-based clustering technique using internal grey variance (IGV); three) shadow detection; 4) false alarm reduction using positional data of each building edge and shadow; and 5) adaptive threshold based mostly segmentation technique. We have a tendency to have evaluated the algorithm using a selection of images from IKONOS and QuickBird satellites. The results demonstrate that the proposed algorithm is both accurate and economical.