부산대학교 도서관

Slums (Informal Settlements) are the most dynamic areas whose geographical locations are inaccurate according to official statistics and maps because of the exponential expansion of urbanization strategies. As a result, a method has to be developed to distinguish between informal settlements and track their spatial patterns. This paper presents an integrated method for detecting slums from satellite images that employs homogeneous urban patches (HUP) and grey level co-occurrence matrix (GLCM)-based image segmentation. In order to extract meaningful spatial features, urban patches are segmented according to their homogeneity and GLCM analysis provides useful texture information about slum areas. The combination of both these GLCM and HUP features allows for the creation of a classification map that accurately identifies and maps slum areas. We utilized WorldView-2 (1.84m) satellite imagery of Madurai to test the effectiveness of proposed HUP approach. The validation process includes rigorous testing against ground truth data, with careful consideration given to the selection of training and testing datasets. The effectiveness of the proposed method is evaluated using metrics including overall accuracy, user accuracy, and producer accuracy Furthermore, the proposed algorithm outperformed existing GLCM-based approaches in terms of accuracy.