Built-up area detection of remote sensing images using static clustering technique

Robust unsupervised classification for simultaneously detecting possible built-up areas from given set of high-resolution remote sensing images covering different scenes is presented in this paper. Based on the region of interest in the input image, frequently recurring appearance patterns or repeated textures used to discriminate built-up areas from others which is formulated in two stages: The first stage is to extract large set of corners from each input image by Harris corner detector and at the second stage corners are extracted using likelihood function which localizes the candidate regions in each input image. In order to discover the frequently recurring texture patterns corresponding to built-up areas as an unsupervised grouping problem, the candidate regions with histogram representation of texture feature is modeled and the grouping problem is solved by spectrum clustering.