Abstract:
This paper presents a methodology and results of evaluating damaged building extraction using an object recognition task based on Differential Morphological Profile (DMP) for Very High Resolution (VHR) remotely sensed images. The proposed approach involves several advanced morphological operators among which an adaptive transforms with varying size, shape and gray level of the structuring elements. IKONOS-2 Satellite images consisting of pre and post 2004 Indian Ocean Tsunami site of Kalmunai area in east cost of Sri Lanka were used. Morphological operation of opening and closing by constructions using structural element are applied for segmented images, then derivative of the opening profile is defined as the vector. ISODATA algorithm is used for the feature extraction and the results comparison with ground truth data. This result appeared to have high accuracy, the confidence measures produced of completely destroyed structure gives 60% and 86% by object base and pixel base respectively after the tsunami in one segment of Maruthamunai GN Division.
