Buildings Detection from Very High Resolution Satellite Images Using Segmentation and Morphological Operations

Extraction of high-resolution satellite image buildings is difficult task for researchers in remote sensing area. In the proposed work Region Growing Segmentation, morphological operations and perceptual-grouping techniques are developed and to detect the buildings in high spatial-resolution images. The necessary algorithm for the implementation of Region growing segmentation is developed using MATLAB-software and its performance is tested by inputting several images. It is founded that the proposed algorithm successfully detect the rectangular building footprints. The efficacy of the designed algorithm is tested by repeating the experiment multiple times successfully.